Merge remote-tracking branch 'origin' into irqdomain/next

186 files changed, 4904 insertions, 3011 deletions

diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 050cb371a69e..9a5d3cdc3e12 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -653,7 +653,7 @@ config SBUS
 config FSL_SOC
 	bool
 	select HAVE_CAN_FLEXCAN if NET && CAN
-	select PPC_CLOCK if CAN_FLEXCAN
+	select PPC_CLOCK
 
 config FSL_PCI
  	bool
diff --git a/arch/powerpc/Kconfig.debug b/arch/powerpc/Kconfig.debug
index e5f26890a69e..5416e28a7538 100644
--- a/arch/powerpc/Kconfig.debug
+++ b/arch/powerpc/Kconfig.debug
@@ -331,4 +331,13 @@ config STRICT_DEVMEM
 
 	  If you are unsure, say Y.
 
+config FAIL_IOMMU
+	bool "Fault-injection capability for IOMMU"
+	depends on FAULT_INJECTION
+	help
+	  Provide fault-injection capability for IOMMU. Each device can
+	  be selectively enabled via the fail_iommu property.
+
+	  If you are unsure, say N.
+
 endmenu
diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile
index e8461cb18d04..b7d833382be4 100644
--- a/arch/powerpc/boot/Makefile
+++ b/arch/powerpc/boot/Makefile
@@ -62,26 +62,45 @@ libfdtheader := fdt.h libfdt.h libfdt_internal.h
 $(addprefix $(obj)/,$(libfdt) libfdt-wrapper.o simpleboot.o epapr.o): \
 	$(addprefix $(obj)/,$(libfdtheader))
 
-src-wlib := string.S crt0.S crtsavres.S stdio.c main.c \
+src-wlib-y := string.S crt0.S crtsavres.S stdio.c main.c \
 		$(libfdt) libfdt-wrapper.c \
 		ns16550.c serial.c simple_alloc.c div64.S util.S \
-		gunzip_util.c elf_util.c $(zlib) devtree.c oflib.c ofconsole.c \
-		4xx.c ebony.c mv64x60.c mpsc.c mv64x60_i2c.c cuboot.c bamboo.c \
-		cpm-serial.c stdlib.c mpc52xx-psc.c planetcore.c uartlite.c \
-		fsl-soc.c mpc8xx.c pq2.c ugecon.c
-src-plat := of.c cuboot-52xx.c cuboot-824x.c cuboot-83xx.c cuboot-85xx.c holly.c \
-		cuboot-ebony.c cuboot-hotfoot.c epapr.c treeboot-ebony.c \
-		prpmc2800.c \
-		ps3-head.S ps3-hvcall.S ps3.c treeboot-bamboo.c cuboot-8xx.c \
-		cuboot-pq2.c cuboot-sequoia.c treeboot-walnut.c \
-		cuboot-bamboo.c cuboot-mpc7448hpc2.c cuboot-taishan.c \
-		fixed-head.S ep88xc.c ep405.c cuboot-c2k.c \
-		cuboot-katmai.c cuboot-rainier.c redboot-8xx.c ep8248e.c \
-		cuboot-warp.c cuboot-85xx-cpm2.c cuboot-yosemite.c simpleboot.c \
-		virtex405-head.S virtex.c redboot-83xx.c cuboot-sam440ep.c \
-		cuboot-acadia.c cuboot-amigaone.c cuboot-kilauea.c \
-		gamecube-head.S gamecube.c wii-head.S wii.c treeboot-iss4xx.c \
-		treeboot-currituck.c
+		gunzip_util.c elf_util.c $(zlib) devtree.c stdlib.c \
+		oflib.c ofconsole.c cuboot.c mpsc.c cpm-serial.c \
+		uartlite.c mpc52xx-psc.c
+src-wlib-$(CONFIG_40x) += 4xx.c planetcore.c
+src-wlib-$(CONFIG_44x) += 4xx.c ebony.c bamboo.c
+src-wlib-$(CONFIG_8xx) += mpc8xx.c planetcore.c
+src-wlib-$(CONFIG_PPC_82xx) += pq2.c fsl-soc.c planetcore.c
+src-wlib-$(CONFIG_EMBEDDED6xx) += mv64x60.c mv64x60_i2c.c ugecon.c
+
+src-plat-y := of.c
+src-plat-$(CONFIG_40x) += fixed-head.S ep405.c cuboot-hotfoot.c \
+				treeboot-walnut.c cuboot-acadia.c \
+				cuboot-kilauea.c simpleboot.c \
+				virtex405-head.S virtex.c
+src-plat-$(CONFIG_44x) += treeboot-ebony.c cuboot-ebony.c treeboot-bamboo.c \
+				cuboot-bamboo.c cuboot-sam440ep.c \
+				cuboot-sequoia.c cuboot-rainier.c \
+				cuboot-taishan.c cuboot-katmai.c \
+				cuboot-warp.c cuboot-yosemite.c \
+				treeboot-iss4xx.c treeboot-currituck.c \
+				simpleboot.c fixed-head.S virtex.c
+src-plat-$(CONFIG_8xx) += cuboot-8xx.c fixed-head.S ep88xc.c redboot-8xx.c
+src-plat-$(CONFIG_PPC_MPC52xx) += cuboot-52xx.c
+src-plat-$(CONFIG_PPC_82xx) += cuboot-pq2.c fixed-head.S ep8248e.c cuboot-824x.c
+src-plat-$(CONFIG_PPC_83xx) += cuboot-83xx.c fixed-head.S redboot-83xx.c
+src-plat-$(CONFIG_FSL_SOC_BOOKE) += cuboot-85xx.c cuboot-85xx-cpm2.c
+src-plat-$(CONFIG_EMBEDDED6xx) += cuboot-pq2.c cuboot-mpc7448hpc2.c \
+					cuboot-c2k.c gamecube-head.S \
+					gamecube.c wii-head.S wii.c holly.c \
+					prpmc2800.c
+src-plat-$(CONFIG_AMIGAONE) += cuboot-amigaone.c
+src-plat-$(CONFIG_PPC_PS3) += ps3-head.S ps3-hvcall.S ps3.c
+src-plat-$(CONFIG_EPAPR_BOOT) += epapr.c
+
+src-wlib := $(sort $(src-wlib-y))
+src-plat := $(sort $(src-plat-y))
 src-boot := $(src-wlib) $(src-plat) empty.c
 
 src-boot := $(addprefix $(obj)/, $(src-boot))
@@ -257,7 +276,6 @@ image-$(CONFIG_TQM8548)			+= cuImage.tqm8548
 image-$(CONFIG_TQM8555)			+= cuImage.tqm8555
 image-$(CONFIG_TQM8560)			+= cuImage.tqm8560
 image-$(CONFIG_SBC8548)			+= cuImage.sbc8548
-image-$(CONFIG_SBC8560)			+= cuImage.sbc8560
 image-$(CONFIG_KSI8560)			+= cuImage.ksi8560
 
 # Board ports in arch/powerpc/platform/embedded6xx/Kconfig
@@ -412,4 +430,3 @@ $(wrapper-installed): $(DESTDIR)$(WRAPPER_BINDIR) $(srctree)/$(obj)/wrapper | $(
 	$(call cmd,install_wrapper)
 
 $(obj)/bootwrapper_install: $(all-installed)
-
diff --git a/arch/powerpc/boot/dts/bsc9131rdb.dts b/arch/powerpc/boot/dts/bsc9131rdb.dts
new file mode 100644
index 000000000000..e13d2d4877b0
--- /dev/null
+++ b/arch/powerpc/boot/dts/bsc9131rdb.dts
@@ -0,0 +1,34 @@
+/*
+ * BSC9131 RDB Device Tree Source
+ *
+ * Copyright 2011-2012 Freescale Semiconductor Inc.
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ */
+
+/include/ "fsl/bsc9131si-pre.dtsi"
+
+/ {
+	model = "fsl,bsc9131rdb";
+	compatible = "fsl,bsc9131rdb";
+
+	memory {
+		device_type = "memory";
+	};
+
+	board_ifc: ifc: ifc@ff71e000 {
+		/* NAND Flash on board */
+		ranges = <0x0 0x0 0x0 0xff800000 0x00004000>;
+		reg = <0x0 0xff71e000 0x0 0x2000>;
+	};
+
+	board_soc: soc: soc@ff700000 {
+		ranges = <0x0 0x0 0xff700000 0x100000>;
+	};
+};
+
+/include/ "bsc9131rdb.dtsi"
+/include/ "fsl/bsc9131si-post.dtsi"
diff --git a/arch/powerpc/boot/dts/bsc9131rdb.dtsi b/arch/powerpc/boot/dts/bsc9131rdb.dtsi
new file mode 100644
index 000000000000..638adda2c218
--- /dev/null
+++ b/arch/powerpc/boot/dts/bsc9131rdb.dtsi
@@ -0,0 +1,142 @@
+/*
+ * BSC9131 RDB Device Tree Source stub (no addresses or top-level ranges)
+ *
+ * Copyright 2011-2012 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in the
+ *       documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Freescale Semiconductor nor the
+ *       names of its contributors may be used to endorse or promote products
+ *       derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+&board_ifc {
+
+	nand@0,0 {
+		#address-cells = <1>;
+		#size-cells = <1>;
+		compatible = "fsl,ifc-nand";
+		reg = <0x0 0x0 0x4000>;
+
+		partition@0 {
+			/* This location must not be altered  */
+			/* 3MB for u-boot Bootloader Image */
+			reg = <0x0 0x00300000>;
+			label = "NAND U-Boot Image";
+			read-only;
+		};
+
+		partition@300000 {
+			/* 1MB for DTB Image */
+			reg = <0x00300000 0x00100000>;
+			label = "NAND DTB Image";
+		};
+
+		partition@400000 {
+			/* 8MB for Linux Kernel Image */
+			reg = <0x00400000 0x00800000>;
+			label = "NAND Linux Kernel Image";
+		};
+
+		partition@c00000 {
+			/* Rest space for Root file System Image */
+			reg = <0x00c00000 0x07400000>;
+			label = "NAND RFS Image";
+		};
+	};
+};
+
+&board_soc {
+	/* BSC9131RDB does not have any device on i2c@3100 */
+	i2c@3100 {
+		status = "disabled";
+	};
+
+	spi@7000 {
+		flash@0 {
+			#address-cells = <1>;
+			#size-cells = <1>;
+			compatible = "spansion,s25sl12801";
+			reg = <0>;
+			spi-max-frequency = <50000000>;
+
+			/* 512KB for u-boot Bootloader Image */
+			partition@0 {
+				reg = <0x0 0x00080000>;
+				label = "SPI Flash U-Boot Image";
+				read-only;
+			};
+
+			/* 512KB for DTB Image */
+			partition@80000 {
+				reg = <0x00080000 0x00080000>;
+				label = "SPI Flash DTB Image";
+			};
+
+			/* 4MB for Linux Kernel Image */
+			partition@100000 {
+				reg = <0x00100000 0x00400000>;
+				label = "SPI Flash Kernel Image";
+			};
+
+			/*11MB for RFS Image */
+			partition@500000 {
+				reg = <0x00500000 0x00B00000>;
+				label = "SPI Flash RFS Image";
+			};
+
+		};
+	};
+
+	usb@22000 {
+		phy_type = "ulpi";
+	};
+
+	mdio@24000 {
+		phy0: ethernet-phy@0 {
+			interrupts = <3 1 0 0>;
+			reg = <0x0>;
+		};
+
+		phy1: ethernet-phy@1 {
+			interrupts = <2 1 0 0>;
+			reg = <0x3>;
+		};
+	};
+
+	sdhci@2e000 {
+		status = "disabled";
+	};
+
+	enet0: ethernet@b0000 {
+		phy-handle = <&phy0>;
+		phy-connection-type = "rgmii-id";
+	};
+
+	enet1: ethernet@b1000 {
+		phy-handle = <&phy1>;
+		phy-connection-type = "rgmii-id";
+	};
+};
diff --git a/arch/powerpc/boot/dts/fsl/bsc9131si-post.dtsi b/arch/powerpc/boot/dts/fsl/bsc9131si-post.dtsi
new file mode 100644
index 000000000000..5180d9d37989
--- /dev/null
+++ b/arch/powerpc/boot/dts/fsl/bsc9131si-post.dtsi
@@ -0,0 +1,193 @@
+/*
+ * BSC9131 Silicon/SoC Device Tree Source (post include)
+ *
+ * Copyright 2011-2012 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in the
+ *       documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Freescale Semiconductor nor the
+ *       names of its contributors may be used to endorse or promote products
+ *       derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+&ifc {
+	#address-cells = <2>;
+	#size-cells = <1>;
+	compatible = "fsl,ifc", "simple-bus";
+	interrupts = <16 2 0 0 20 2 0 0>;
+};
+
+&soc {
+	#address-cells = <1>;
+	#size-cells = <1>;
+	device_type = "soc";
+	compatible = "fsl,bsc9131-immr", "simple-bus";
+	bus-frequency = <0>;		// Filled out by uboot.
+
+	ecm-law@0 {
+		compatible = "fsl,ecm-law";
+		reg = <0x0 0x1000>;
+		fsl,num-laws = <12>;
+	};
+
+	ecm@1000 {
+		compatible = "fsl,bsc9131-ecm", "fsl,ecm";
+		reg = <0x1000 0x1000>;
+		interrupts = <16 2 0 0>;
+	};
+
+	memory-controller@2000 {
+		compatible = "fsl,bsc9131-memory-controller";
+		reg = <0x2000 0x1000>;
+		interrupts = <16 2 0 0>;
+	};
+
+/include/ "pq3-i2c-0.dtsi"
+	i2c@3000 {
+		interrupts = <17 2 0 0>;
+	};
+
+/include/ "pq3-i2c-1.dtsi"
+	i2c@3100 {
+		interrupts = <17 2 0 0>;
+	};
+
+/include/ "pq3-duart-0.dtsi"
+	serial0: serial@4500 {
+		interrupts = <18 2 0 0>;
+	};
+
+	serial1: serial@4600 {
+		interrupts = <18 2 0 0 >;
+	};
+/include/ "pq3-espi-0.dtsi"
+	spi0: spi@7000 {
+		fsl,espi-num-chipselects = <1>;
+		interrupts = <22 0x2 0 0>;
+	};
+
+/include/ "pq3-gpio-0.dtsi"
+	gpio-controller@f000 {
+		interrupts = <19 0x2 0 0>;
+		};
+
+	L2: l2-cache-controller@20000 {
+		compatible = "fsl,bsc9131-l2-cache-controller";
+		reg = <0x20000 0x1000>;
+		cache-line-size = <32>;	// 32 bytes
+		cache-size = <0x40000>; // L2,256K
+		interrupts = <16 2 0 0>;
+	};
+
+/include/ "pq3-dma-0.dtsi"
+
+dma@21300 {
+
+	dma-channel@0 {
+		interrupts = <62 2 0 0>;
+	};
+
+	dma-channel@80 {
+		interrupts = <63 2 0 0>;
+	};
+
+	dma-channel@100 {
+		interrupts = <64 2 0 0>;
+	};
+
+	dma-channel@180 {
+		interrupts = <65 2 0 0>;
+	};
+};
+
+/include/ "pq3-usb2-dr-0.dtsi"
+usb@22000 {
+	compatible = "fsl-usb2-dr","fsl-usb2-dr-v2.2";
+	interrupts = <40 0x2 0 0>;
+};
+
+/include/ "pq3-esdhc-0.dtsi"
+	sdhc@2e000 {
+		fsl,sdhci-auto-cmd12;
+		interrupts = <41 0x2 0 0>;
+	};
+
+/include/ "pq3-sec4.4-0.dtsi"
+crypto@30000 {
+	interrupts	 = <57 2 0 0>;
+
+	sec_jr0: jr@1000 {
+		interrupts	 = <58 2 0 0>;
+	};
+
+	sec_jr1: jr@2000 {
+		interrupts	 = <59 2 0 0>;
+	};
+
+	sec_jr2: jr@3000 {
+		interrupts	 = <60 2 0 0>;
+	};
+
+	sec_jr3: jr@4000 {
+		interrupts	 = <61 2 0 0>;
+	};
+};
+
+/include/ "pq3-mpic.dtsi"
+
+timer@41100 {
+	compatible = "fsl,mpic-v1.2-msgr", "fsl,mpic-msg";
+	reg = <0x41400 0x200>;
+	interrupts = <
+		0xb0 2
+		0xb1 2
+		0xb2 2
+		0xb3 2>;
+};
+
+/include/ "pq3-etsec2-0.dtsi"
+enet0: ethernet@b0000 {
+	queue-group@b0000 {
+		fsl,rx-bit-map = <0xff>;
+		fsl,tx-bit-map = <0xff>;
+		interrupts = <26 2 0 0 27 2 0 0 28 2 0 0>;
+	};
+};
+
+/include/ "pq3-etsec2-1.dtsi"
+enet1: ethernet@b1000 {
+	queue-group@b1000 {
+		fsl,rx-bit-map = <0xff>;
+		fsl,tx-bit-map = <0xff>;
+		interrupts = <33 2 0 0 34 2 0 0 35 2 0 0>;
+	};
+};
+
+global-utilities@e0000 {
+		compatible = "fsl,bsc9131-guts";
+		reg = <0xe0000 0x1000>;
+		fsl,has-rstcr;
+	};
+};
diff --git a/arch/powerpc/boot/dts/fsl/p3060si-pre.dtsi b/arch/powerpc/boot/dts/fsl/bsc9131si-pre.dtsi
index 00c8e70e7b90..743e4aeda349 100644
--- a/arch/powerpc/boot/dts/fsl/p3060si-pre.dtsi
+++ b/arch/powerpc/boot/dts/fsl/bsc9131si-pre.dtsi
@@ -1,7 +1,7 @@
 /*
- * P3060 Silicon/SoC Device Tree Source (pre include)
+ * BSC9131 Silicon/SoC Device Tree Source (pre include)
  *
- * Copyright 2011 Freescale Semiconductor Inc.
+ * Copyright 2011-2012 Freescale Semiconductor Inc.
  *
  * Redistribution and use in source and binary forms, with or without
  * modification, are permitted provided that the following conditions are met:
@@ -34,92 +34,26 @@
 
 /dts-v1/;
 / {
-	compatible = "fsl,P3060";
+	compatible = "fsl,BSC9131";
 	#address-cells = <2>;
 	#size-cells = <2>;
 	interrupt-parent = <&mpic>;
 
 	aliases {
-		ccsr = &soc;
-		dcsr = &dcsr;
-
 		serial0 = &serial0;
-		serial1 = &serial1;
-		serial2 = &serial2;
-		serial3 = &serial3;
-		pci0 = &pci0;
-		pci1 = &pci1;
-		usb0 = &usb0;
-		usb1 = &usb1;
-		dma0 = &dma0;
-		dma1 = &dma1;
-		msi0 = &msi0;
-		msi1 = &msi1;
-		msi2 = &msi2;
-
-		crypto = &crypto;
-		sec_jr0 = &sec_jr0;
-		sec_jr1 = &sec_jr1;
-		sec_jr2 = &sec_jr2;
-		sec_jr3 = &sec_jr3;
-		rtic_a = &rtic_a;
-		rtic_b = &rtic_b;
-		rtic_c = &rtic_c;
-		rtic_d = &rtic_d;
-		sec_mon = &sec_mon;
+		ethernet0 = &enet0;
+		ethernet1 = &enet1;
 	};
 
 	cpus {
 		#address-cells = <1>;
 		#size-cells = <0>;
 
-		cpu0: PowerPC,e500mc@0 {
-			device_type = "cpu";
-			reg = <0>;
-			next-level-cache = <&L2_0>;
-			L2_0: l2-cache {
-				next-level-cache = <&cpc>;
-			};
-		};
-		cpu1: PowerPC,e500mc@1 {
-			device_type = "cpu";
-			reg = <1>;
-			next-level-cache = <&L2_1>;
-			L2_1: l2-cache {
-				next-level-cache = <&cpc>;
-			};
-		};
-		cpu4: PowerPC,e500mc@4 {
-			device_type = "cpu";
-			reg = <4>;
-			next-level-cache = <&L2_4>;
-			L2_4: l2-cache {
-				next-level-cache = <&cpc>;
-			};
-		};
-		cpu5: PowerPC,e500mc@5 {
-			device_type = "cpu";
-			reg = <5>;
-			next-level-cache = <&L2_5>;
-			L2_5: l2-cache {
-				next-level-cache = <&cpc>;
-			};
-		};
-		cpu6: PowerPC,e500mc@6 {
-			device_type = "cpu";
-			reg = <6>;
-			next-level-cache = <&L2_6>;
-			L2_6: l2-cache {
-				next-level-cache = <&cpc>;
-			};
-		};
-		cpu7: PowerPC,e500mc@7 {
+		PowerPC,BSC9131@0 {
 			device_type = "cpu";
-			reg = <7>;
-			next-level-cache = <&L2_7>;
-			L2_7: l2-cache {
-				next-level-cache = <&cpc>;
-			};
+			compatible = "fsl,e500v2";
+			reg = <0x0>;
+			next-level-cache = <&L2>;
 		};
 	};
 };
diff --git a/arch/powerpc/boot/dts/fsl/p1021si-post.dtsi b/arch/powerpc/boot/dts/fsl/p1021si-post.dtsi
index 4252ef85fb7a..adb82fd9057f 100644
--- a/arch/powerpc/boot/dts/fsl/p1021si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/p1021si-post.dtsi
@@ -1,7 +1,7 @@
 /*
  * P1021/P1012 Silicon/SoC Device Tree Source (post include)
  *
- * Copyright 2011 Freescale Semiconductor Inc.
+ * Copyright 2011-2012 Freescale Semiconductor Inc.
  *
  * Redistribution and use in source and binary forms, with or without
  * modification, are permitted provided that the following conditions are met:
@@ -213,6 +213,20 @@
 		interrupt-parent = <&qeic>;
 	};
 
+	ucc@2600 {
+		cell-index = <7>;
+		reg = <0x2600 0x200>;
+		interrupts = <42>;
+		interrupt-parent = <&qeic>;
+	};
+
+	ucc@2200 {
+		cell-index = <3>;
+		reg = <0x2200 0x200>;
+		interrupts = <34>;
+		interrupt-parent = <&qeic>;
+	};
+
 	muram@10000 {
 		#address-cells = <1>;
 		#size-cells = <1>;
diff --git a/arch/powerpc/boot/dts/fsl/p3060si-post.dtsi b/arch/powerpc/boot/dts/fsl/p3060si-post.dtsi
deleted file mode 100644
index b3e56929eee2..000000000000
--- a/arch/powerpc/boot/dts/fsl/p3060si-post.dtsi
+++ /dev/null
@@ -1,302 +0,0 @@
-/*
- * P3060 Silicon/SoC Device Tree Source (post include)
- *
- * Copyright 2011 Freescale Semiconductor Inc.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *     * Redistributions of source code must retain the above copyright
- *       notice, this list of conditions and the following disclaimer.
- *     * Redistributions in binary form must reproduce the above copyright
- *       notice, this list of conditions and the following disclaimer in the
- *       documentation and/or other materials provided with the distribution.
- *     * Neither the name of Freescale Semiconductor nor the
- *       names of its contributors may be used to endorse or promote products
- *       derived from this software without specific prior written permission.
- *
- *
- * ALTERNATIVELY, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") as published by the Free Software
- * Foundation, either version 2 of that License or (at your option) any
- * later version.
- *
- * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
- * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
- * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
- * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
- * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
- * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
- * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
- * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
- * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- */
-
-&lbc {
-	compatible = "fsl,p3060-elbc", "fsl,elbc", "simple-bus";
-	interrupts = <25 2 0 0>;
-	#address-cells = <2>;
-	#size-cells = <1>;
-};
-
-/* controller at 0x200000 */
-&pci0 {
-	compatible = "fsl,p3060-pcie", "fsl,qoriq-pcie-v2.2";
-	device_type = "pci";
-	#size-cells = <2>;
-	#address-cells = <3>;
-	bus-range = <0x0 0xff>;
-	clock-frequency = <33333333>;
-	interrupts = <16 2 1 15>;
-	pcie@0 {
-		reg = <0 0 0 0 0>;
-		#interrupt-cells = <1>;
-		#size-cells = <2>;
-		#address-cells = <3>;
-		device_type = "pci";
-		interrupts = <16 2 1 15>;
-		interrupt-map-mask = <0xf800 0 0 7>;
-		interrupt-map = <
-			/* IDSEL 0x0 */
-			0000 0 0 1 &mpic 40 1 0 0
-			0000 0 0 2 &mpic 1 1 0 0
-			0000 0 0 3 &mpic 2 1 0 0
-			0000 0 0 4 &mpic 3 1 0 0
-			>;
-	};
-};
-
-/* controller at 0x201000 */
-&pci1 {
-	compatible = "fsl,p3060-pcie", "fsl,qoriq-pcie-v2.2";
-	device_type = "pci";
-	#size-cells = <2>;
-	#address-cells = <3>;
-	bus-range = <0 0xff>;
-	clock-frequency = <33333333>;
-	interrupts = <16 2 1 14>;
-	pcie@0 {
-		reg = <0 0 0 0 0>;
-		#interrupt-cells = <1>;
-		#size-cells = <2>;
-		#address-cells = <3>;
-		device_type = "pci";
-		interrupts = <16 2 1 14>;
-		interrupt-map-mask = <0xf800 0 0 7>;
-		interrupt-map = <
-			/* IDSEL 0x0 */
-			0000 0 0 1 &mpic 41 1 0 0
-			0000 0 0 2 &mpic 5 1 0 0
-			0000 0 0 3 &mpic 6 1 0 0
-			0000 0 0 4 &mpic 7 1 0 0
-			>;
-	};
-};
-
-&rio {
-	compatible = "fsl,srio";
-	interrupts = <16 2 1 11>;
-	#address-cells = <2>;
-	#size-cells = <2>;
-	fsl,srio-rmu-handle = <&rmu>;
-	ranges;
-
-	port1 {
-		#address-cells = <2>;
-		#size-cells = <2>;
-		cell-index = <1>;
-	};
-
-	port2 {
-		#address-cells = <2>;
-		#size-cells = <2>;
-		cell-index = <2>;
-	};
-};
-
-&dcsr {
-	#address-cells = <1>;
-	#size-cells = <1>;
-	compatible = "fsl,dcsr", "simple-bus";
-
-	dcsr-epu@0 {
-		compatible = "fsl,dcsr-epu";
-		interrupts = <52 2 0 0
-			      84 2 0 0
-			      85 2 0 0>;
-		reg = <0x0 0x1000>;
-	};
-	dcsr-npc {
-		compatible = "fsl,dcsr-npc";
-		reg = <0x1000 0x1000 0x1000000 0x8000>;
-	};
-	dcsr-nxc@2000 {
-		compatible = "fsl,dcsr-nxc";
-		reg = <0x2000 0x1000>;
-	};
-	dcsr-corenet {
-		compatible = "fsl,dcsr-corenet";
-		reg = <0x8000 0x1000 0xB0000 0x1000>;
-	};
-	dcsr-dpaa@9000 {
-		compatible = "fsl,p3060-dcsr-dpaa", "fsl,dcsr-dpaa";
-		reg = <0x9000 0x1000>;
-	};
-	dcsr-ocn@11000 {
-		compatible = "fsl,p3060-dcsr-ocn", "fsl,dcsr-ocn";
-		reg = <0x11000 0x1000>;
-	};
-	dcsr-ddr@12000 {
-		compatible = "fsl,dcsr-ddr";
-		dev-handle = <&ddr1>;
-		reg = <0x12000 0x1000>;
-	};
-	dcsr-nal@18000 {
-		compatible = "fsl,p3060-dcsr-nal", "fsl,dcsr-nal";
-		reg = <0x18000 0x1000>;
-	};
-	dcsr-rcpm@22000 {
-		compatible = "fsl,p3060-dcsr-rcpm", "fsl,dcsr-rcpm";
-		reg = <0x22000 0x1000>;
-	};
-	dcsr-cpu-sb-proxy@40000 {
-		compatible = "fsl,dcsr-e500mc-sb-proxy", "fsl,dcsr-cpu-sb-proxy";
-		cpu-handle = <&cpu0>;
-		reg = <0x40000 0x1000>;
-	};
-	dcsr-cpu-sb-proxy@41000 {
-		compatible = "fsl,dcsr-e500mc-sb-proxy", "fsl,dcsr-cpu-sb-proxy";
-		cpu-handle = <&cpu1>;
-		reg = <0x41000 0x1000>;
-	};
-	dcsr-cpu-sb-proxy@44000 {
-		compatible = "fsl,dcsr-e500mc-sb-proxy", "fsl,dcsr-cpu-sb-proxy";
-		cpu-handle = <&cpu4>;
-		reg = <0x44000 0x1000>;
-	};
-	dcsr-cpu-sb-proxy@45000 {
-		compatible = "fsl,dcsr-e500mc-sb-proxy", "fsl,dcsr-cpu-sb-proxy";
-		cpu-handle = <&cpu5>;
-		reg = <0x45000 0x1000>;
-	};
-	dcsr-cpu-sb-proxy@46000 {
-		compatible = "fsl,dcsr-e500mc-sb-proxy", "fsl,dcsr-cpu-sb-proxy";
-		cpu-handle = <&cpu6>;
-		reg = <0x46000 0x1000>;
-	};
-	dcsr-cpu-sb-proxy@47000 {
-		compatible = "fsl,dcsr-e500mc-sb-proxy", "fsl,dcsr-cpu-sb-proxy";
-		cpu-handle = <&cpu7>;
-		reg = <0x47000 0x1000>;
-	};
-
-};
-
-&soc {
-	#address-cells = <1>;
-	#size-cells = <1>;
-	device_type = "soc";
-	compatible = "simple-bus";
-
-	soc-sram-error {
-		compatible = "fsl,soc-sram-error";
-		interrupts = <16 2 1 29>;
-	};
-
-	corenet-law@0 {
-		compatible = "fsl,corenet-law";
-		reg = <0x0 0x1000>;
-		fsl,num-laws = <32>;
-	};
-
-	ddr1: memory-controller@8000 {
-		compatible = "fsl,qoriq-memory-controller-v4.4", "fsl,qoriq-memory-controller";
-		reg = <0x8000 0x1000>;
-		interrupts = <16 2 1 23>;
-	};
-
-	cpc: l3-cache-controller@10000 {
-		compatible = "fsl,p3060-l3-cache-controller", "cache";
-		reg = <0x10000 0x1000
-		       0x11000 0x1000>;
-		interrupts = <16 2 1 27
-			      16 2 1 26>;
-	};
-
-	corenet-cf@18000 {
-		compatible = "fsl,corenet-cf";
-		reg = <0x18000 0x1000>;
-		interrupts = <16 2 1 31>;
-		fsl,ccf-num-csdids = <32>;
-		fsl,ccf-num-snoopids = <32>;
-	};
-
-	iommu@20000 {
-		compatible = "fsl,pamu-v1.0", "fsl,pamu";
-		reg = <0x20000 0x5000>;
-		interrupts = <
-			24 2 0 0
-			16 2 1 30>;
-	};
-
-/include/ "qoriq-rmu-0.dtsi"
-/include/ "qoriq-mpic.dtsi"
-
-	guts: global-utilities@e0000 {
-		compatible = "fsl,qoriq-device-config-1.0";
-		reg = <0xe0000 0xe00>;
-		fsl,has-rstcr;
-		#sleep-cells = <1>;
-		fsl,liodn-bits = <12>;
-	};
-
-	pins: global-utilities@e0e00 {
-		compatible = "fsl,qoriq-pin-control-1.0";
-		reg = <0xe0e00 0x200>;
-		#sleep-cells = <2>;
-	};
-
-	clockgen: global-utilities@e1000 {
-		compatible = "fsl,p3060-clockgen", "fsl,qoriq-clockgen-1.0";
-		reg = <0xe1000 0x1000>;
-		clock-frequency = <0>;
-	};
-
-	rcpm: global-utilities@e2000 {
-		compatible = "fsl,qoriq-rcpm-1.0";
-		reg = <0xe2000 0x1000>;
-		#sleep-cells = <1>;
-	};
-
-	sfp: sfp@e8000 {
-		compatible = "fsl,p3060-sfp", "fsl,qoriq-sfp-1.0";
-		reg	   = <0xe8000 0x1000>;
-	};
-
-	serdes: serdes@ea000 {
-		compatible = "fsl,p3060-serdes";
-		reg	   = <0xea000 0x1000>;
-	};
-
-/include/ "qoriq-dma-0.dtsi"
-/include/ "qoriq-dma-1.dtsi"
-/include/ "qoriq-espi-0.dtsi"
-	spi@110000 {
-		fsl,espi-num-chipselects = <4>;
-	};
-
-/include/ "qoriq-i2c-0.dtsi"
-/include/ "qoriq-i2c-1.dtsi"
-/include/ "qoriq-duart-0.dtsi"
-/include/ "qoriq-duart-1.dtsi"
-/include/ "qoriq-gpio-0.dtsi"
-/include/ "qoriq-usb2-mph-0.dtsi"
-	usb@210000 {
-		compatible = "fsl-usb2-mph-v2.2", "fsl,mpc85xx-usb2-mph", "fsl-usb2-mph";
-	};
-/include/ "qoriq-usb2-dr-0.dtsi"
-	usb@211000 {
-		compatible = "fsl-usb2-dr-v2.2", "fsl,mpc85xx-usb2-dr", "fsl-usb2-dr";
-	};
-/include/ "qoriq-sec4.1-0.dtsi"
-};
diff --git a/arch/powerpc/boot/dts/mgcoge.dts b/arch/powerpc/boot/dts/mgcoge.dts
index ededaf5ac015..d72fb5e219d0 100644
--- a/arch/powerpc/boot/dts/mgcoge.dts
+++ b/arch/powerpc/boot/dts/mgcoge.dts
@@ -222,6 +222,29 @@
 				interrupt-parent = <&PIC>;
 				usb-clock = <5>;
 			};
+			spi@11aa0 {
+				cell-index = <0>;
+				compatible = "fsl,spi", "fsl,cpm2-spi";
+				reg = <0x11a80 0x40 0x89fc 0x2>;
+				interrupts = <2 8>;
+				interrupt-parent = <&PIC>;
+				gpios = < &cpm2_pio_d 19 0>;
+				#address-cells = <1>;
+				#size-cells = <0>;
+				ds3106@1 {
+					compatible = "gen,spidev";
+					reg = <0>;
+					spi-max-frequency = <8000000>;
+				};
+			};
+
+		};
+
+		cpm2_pio_d: gpio-controller@10d60 {
+			#gpio-cells = <2>;
+			compatible = "fsl,cpm2-pario-bank";
+			reg = <0x10d60 0x14>;
+			gpio-controller;
 		};
 
 		cpm2_pio_c: gpio-controller@10d40 {
diff --git a/arch/powerpc/boot/dts/mpc8536ds.dtsi b/arch/powerpc/boot/dts/mpc8536ds.dtsi
index cc46dbd9746d..d304a2d68c62 100644
--- a/arch/powerpc/boot/dts/mpc8536ds.dtsi
+++ b/arch/powerpc/boot/dts/mpc8536ds.dtsi
@@ -203,6 +203,14 @@
 			reg = <1>;
 			device_type = "ethernet-phy";
 		};
+		sgmii_phy0: sgmii-phy@0 {
+			interrupts = <6 1 0 0>;
+			reg = <0x1d>;
+		};
+		sgmii_phy1: sgmii-phy@1 {
+			interrupts = <6 1 0 0>;
+			reg = <0x1c>;
+		};
 		tbi0: tbi-phy@11 {
 			reg = <0x11>;
 			device_type = "tbi-phy";
diff --git a/arch/powerpc/boot/dts/mpc8544ds.dtsi b/arch/powerpc/boot/dts/mpc8544ds.dtsi
index 270f64b90f4e..77ebc9f1d37c 100644
--- a/arch/powerpc/boot/dts/mpc8544ds.dtsi
+++ b/arch/powerpc/boot/dts/mpc8544ds.dtsi
@@ -51,6 +51,15 @@
 			device_type = "ethernet-phy";
 		};
 
+		sgmii_phy0: sgmii-phy@0 {
+			interrupts = <6 1 0 0>;
+			reg = <0x1c>;
+		};
+		sgmii_phy1: sgmii-phy@1 {
+			interrupts = <6 1 0 0>;
+			reg = <0x1d>;
+		};
+
 		tbi0: tbi-phy@11 {
 			reg = <0x11>;
 			device_type = "tbi-phy";
diff --git a/arch/powerpc/boot/dts/mpc8572ds.dtsi b/arch/powerpc/boot/dts/mpc8572ds.dtsi
index 14178944e220..357490bb84da 100644
--- a/arch/powerpc/boot/dts/mpc8572ds.dtsi
+++ b/arch/powerpc/boot/dts/mpc8572ds.dtsi
@@ -169,6 +169,23 @@
 			reg = <0x3>;
 		};
 
+		sgmii_phy0: sgmii-phy@0 {
+			interrupts = <6 1 0 0>;
+			reg = <0x1c>;
+		};
+		sgmii_phy1: sgmii-phy@1 {
+			interrupts = <6 1 0 0>;
+			reg = <0x1d>;
+		};
+		sgmii_phy2: sgmii-phy@2 {
+			interrupts = <7 1 0 0>;
+			reg = <0x1e>;
+		};
+		sgmii_phy3: sgmii-phy@3 {
+			interrupts = <7 1 0 0>;
+			reg = <0x1f>;
+		};
+
 		tbi0: tbi-phy@11 {
 			reg = <0x11>;
 			device_type = "tbi-phy";
diff --git a/arch/powerpc/boot/dts/mpc8572ds_camp_core0.dts b/arch/powerpc/boot/dts/mpc8572ds_camp_core0.dts
index d34d12712125..ef9ef56b3eeb 100644
--- a/arch/powerpc/boot/dts/mpc8572ds_camp_core0.dts
+++ b/arch/powerpc/boot/dts/mpc8572ds_camp_core0.dts
@@ -67,10 +67,10 @@
 		msi@41600 {
 			msi-available-ranges = <0 0x80>;
 			interrupts = <
-				0xe0 0
-				0xe1 0
-				0xe2 0
-				0xe3 0>;
+				0xe0 0 0 0
+				0xe1 0 0 0
+				0xe2 0 0 0
+				0xe3 0 0 0>;
 		};
 		timer@42100 {
 			status = "disabled";
diff --git a/arch/powerpc/boot/dts/mpc8572ds_camp_core1.dts b/arch/powerpc/boot/dts/mpc8572ds_camp_core1.dts
index d6a8fafc0d0d..24564ee108e5 100644
--- a/arch/powerpc/boot/dts/mpc8572ds_camp_core1.dts
+++ b/arch/powerpc/boot/dts/mpc8572ds_camp_core1.dts
@@ -67,9 +67,6 @@
 		ethernet@24000 {
 			status = "disabled";
 		};
-		mdio@24520 {
-			status = "disabled";
-		};
 		ptp_clock@24e00 {
 			status = "disabled";
 		};
@@ -100,10 +97,10 @@
 		msi@41600 {
 			msi-available-ranges = <0x80 0x80>;
 			interrupts = <
-				0xe4 0
-				0xe5 0
-				0xe6 0
-				0xe7 0>;
+				0xe4 0 0 0
+				0xe5 0 0 0
+				0xe6 0 0 0
+				0xe7 0 0 0>;
 		};
 		global-utilities@e0000 {
 			status = "disabled";
diff --git a/arch/powerpc/boot/dts/p1010rdb.dtsi b/arch/powerpc/boot/dts/p1010rdb.dtsi
index 49776143a1b8..ec7c27a64671 100644
--- a/arch/powerpc/boot/dts/p1010rdb.dtsi
+++ b/arch/powerpc/boot/dts/p1010rdb.dtsi
@@ -126,12 +126,24 @@
 
 &board_soc {
 	i2c@3000 {
+		eeprom@50 {
+			compatible = "st,24c256";
+			reg = <0x50>;
+		};
+
 		rtc@68 {
 			compatible = "pericom,pt7c4338";
 			reg = <0x68>;
 		};
 	};
 
+	i2c@3100 {
+		eeprom@52 {
+			compatible = "atmel,24c01";
+			reg = <0x52>;
+		};
+	};
+
 	spi@7000 {
 		flash@0 {
 			#address-cells = <1>;
diff --git a/arch/powerpc/boot/dts/p1021rdb.dtsi b/arch/powerpc/boot/dts/p1021rdb-pc.dtsi
index b973461ab751..c13abfbbe2e2 100644
--- a/arch/powerpc/boot/dts/p1021rdb.dtsi
+++ b/arch/powerpc/boot/dts/p1021rdb-pc.dtsi
@@ -1,7 +1,7 @@
 /*
  * P1021 RDB Device Tree Source stub (no addresses or top-level ranges)
  *
- * Copyright 2011 Freescale Semiconductor Inc.
+ * Copyright 2012 Freescale Semiconductor Inc.
  *
  * Redistribution and use in source and binary forms, with or without
  * modification, are permitted provided that the following conditions are met:
diff --git a/arch/powerpc/boot/dts/p1021rdb.dts b/arch/powerpc/boot/dts/p1021rdb-pc_32b.dts
index 90b6b4caa273..7cefa12b629a 100644
--- a/arch/powerpc/boot/dts/p1021rdb.dts
+++ b/arch/powerpc/boot/dts/p1021rdb-pc_32b.dts
@@ -1,7 +1,7 @@
 /*
  * P1021 RDB Device Tree Source
  *
- * Copyright 2011 Freescale Semiconductor Inc.
+ * Copyright 2012 Freescale Semiconductor Inc.
  *
  * Redistribution and use in source and binary forms, with or without
  * modification, are permitted provided that the following conditions are met:
@@ -92,5 +92,5 @@
         };
 };
 
-/include/ "p1021rdb.dtsi"
+/include/ "p1021rdb-pc.dtsi"
 /include/ "fsl/p1021si-post.dtsi"
diff --git a/arch/powerpc/boot/dts/p1021rdb_36b.dts b/arch/powerpc/boot/dts/p1021rdb-pc_36b.dts
index ea6d8b5fa10b..53d0c889039c 100644
--- a/arch/powerpc/boot/dts/p1021rdb_36b.dts
+++ b/arch/powerpc/boot/dts/p1021rdb-pc_36b.dts
@@ -1,7 +1,7 @@
 /*
  * P1021 RDB Device Tree Source (36-bit address map)
  *
- * Copyright 2011 Freescale Semiconductor Inc.
+ * Copyright 2012 Freescale Semiconductor Inc.
  *
  * Redistribution and use in source and binary forms, with or without
  * modification, are permitted provided that the following conditions are met:
@@ -92,5 +92,5 @@
         };
 };
 
-/include/ "p1021rdb.dtsi"
+/include/ "p1021rdb-pc.dtsi"
 /include/ "fsl/p1021si-post.dtsi"
diff --git a/arch/powerpc/boot/dts/p1022ds.dtsi b/arch/powerpc/boot/dts/p1022ds.dtsi
index 7cdb505036bb..c3344b04d8ff 100644
--- a/arch/powerpc/boot/dts/p1022ds.dtsi
+++ b/arch/powerpc/boot/dts/p1022ds.dtsi
@@ -33,22 +33,6 @@
  */
 
 &board_lbc {
-	/*
-	 * This node is used to access the pixis via "indirect" mode,
-	 * which is done by writing the pixis register index to chip
-	 * select 0 and the value to/from chip select 1.  Indirect
-	 * mode is the only way to access the pixis when DIU video
-	 * is enabled.  Note that this assumes that the first column
-	 * of the 'ranges' property above is the chip select number.
-	 */
-	board-control@0,0 {
-		compatible = "fsl,p1022ds-indirect-pixis";
-		reg = <0x0 0x0 1	/* CS0 */
-		       0x1 0x0 1>;	/* CS1 */
-		interrupt-parent = <&mpic>;
-		interrupts = <8 0 0 0>;
-	};
-
 	nor@0,0 {
 		#address-cells = <1>;
 		#size-cells = <1>;
@@ -161,6 +145,10 @@
 			 * the clock is enabled.
 			 */
 		};
+		rtc@68 {
+			compatible = "dallas,ds1339";
+			reg = <0x68>;
+		};
 	};
 
 	spi@7000 {
diff --git a/arch/powerpc/boot/dts/p1024rdb.dtsi b/arch/powerpc/boot/dts/p1024rdb.dtsi
new file mode 100644
index 000000000000..b05dcb40f800
--- /dev/null
+++ b/arch/powerpc/boot/dts/p1024rdb.dtsi
@@ -0,0 +1,228 @@
+/*
+ * P1024 RDB Device Tree Source stub (no addresses or top-level ranges)
+ *
+ * Copyright 2012 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in the
+ *       documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Freescale Semiconductor nor the
+ *       names of its contributors may be used to endorse or promote products
+ *       derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+&lbc {
+	nor@0,0 {
+		#address-cells = <1>;
+		#size-cells = <1>;
+		compatible = "cfi-flash";
+		reg = <0x0 0x0 0x1000000>;
+		bank-width = <2>;
+		device-width = <1>;
+
+		partition@0 {
+			/* This location must not be altered  */
+			/* 256KB for Vitesse 7385 Switch firmware */
+			reg = <0x0 0x00040000>;
+			label = "NOR Vitesse-7385 Firmware";
+			read-only;
+		};
+
+		partition@40000 {
+			/* 256KB for DTB Image */
+			reg = <0x00040000 0x00040000>;
+			label = "NOR DTB Image";
+		};
+
+		partition@80000 {
+			/* 3.5 MB for Linux Kernel Image */
+			reg = <0x00080000 0x00380000>;
+			label = "NOR Linux Kernel Image";
+		};
+
+		partition@400000 {
+			/* 11MB for JFFS2 based Root file System */
+			reg = <0x00400000 0x00b00000>;
+			label = "NOR JFFS2 Root File System";
+		};
+
+		partition@f00000 {
+			/* This location must not be altered  */
+			/* 512KB for u-boot Bootloader Image */
+			/* 512KB for u-boot Environment Variables */
+			reg = <0x00f00000 0x00100000>;
+			label = "NOR U-Boot Image";
+			read-only;
+		};
+	};
+
+	nand@1,0 {
+		#address-cells = <1>;
+		#size-cells = <1>;
+		compatible = "fsl,p1020-fcm-nand",
+				 "fsl,elbc-fcm-nand";
+		reg = <0x1 0x0 0x40000>;
+
+		partition@0 {
+			/* This location must not be altered  */
+			/* 1MB for u-boot Bootloader Image */
+			reg = <0x0 0x00100000>;
+			label = "NAND U-Boot Image";
+			read-only;
+		};
+
+		partition@100000 {
+			/* 1MB for DTB Image */
+			reg = <0x00100000 0x00100000>;
+			label = "NAND DTB Image";
+		};
+
+		partition@200000 {
+			/* 4MB for Linux Kernel Image */
+			reg = <0x00200000 0x00400000>;
+			label = "NAND Linux Kernel Image";
+		};
+
+		partition@600000 {
+			/* 4MB for Compressed Root file System Image */
+			reg = <0x00600000 0x00400000>;
+			label = "NAND Compressed RFS Image";
+		};
+
+		partition@a00000 {
+			/* 15MB for JFFS2 based Root file System */
+			reg = <0x00a00000 0x00f00000>;
+			label = "NAND JFFS2 Root File System";
+		};
+
+		partition@1900000 {
+			/* 7MB for User Writable Area */
+			reg = <0x01900000 0x00700000>;
+			label = "NAND Writable User area";
+		};
+	};
+};
+
+&soc {
+	spi@7000 {
+		flash@0 {
+			#address-cells = <1>;
+			#size-cells = <1>;
+			compatible = "spansion,m25p80";
+			reg = <0>;
+			spi-max-frequency = <40000000>;
+
+			partition@0 {
+				/* 512KB for u-boot Bootloader Image */
+				reg = <0x0 0x00080000>;
+				label = "SPI U-Boot Image";
+				read-only;
+			};
+
+			partition@80000 {
+				/* 512KB for DTB Image */
+				reg = <0x00080000 0x00080000>;
+				label = "SPI DTB Image";
+			};
+
+			partition@100000 {
+				/* 4MB for Linux Kernel Image */
+				reg = <0x00100000 0x00400000>;
+				label = "SPI Linux Kernel Image";
+			};
+
+			partition@500000 {
+				/* 4MB for Compressed RFS Image */
+				reg = <0x00500000 0x00400000>;
+				label = "SPI Compressed RFS Image";
+			};
+
+			partition@900000 {
+				/* 7MB for JFFS2 based RFS */
+				reg = <0x00900000 0x00700000>;
+				label = "SPI JFFS2 RFS";
+			};
+		};
+	};
+
+	i2c@3000 {
+		rtc@68 {
+			compatible = "dallas,ds1339";
+			reg = <0x68>;
+		};
+	};
+
+	usb@22000 {
+		phy_type = "ulpi";
+	};
+
+	usb@23000 {
+		status = "disabled";
+	};
+
+	mdio@24000 {
+		phy0: ethernet-phy@0 {
+			interrupts = <3 1 0 0>;
+			reg = <0x0>;
+		};
+		phy1: ethernet-phy@1 {
+			interrupts = <2 1 0 0>;
+			reg = <0x1>;
+		};
+		phy2: ethernet-phy@2 {
+			interrupts = <1 1 0 0>;
+			reg = <0x2>;
+		};
+	};
+
+	mdio@25000 {
+		tbi0: tbi-phy@11 {
+			reg = <0x11>;
+			device_type = "tbi-phy";
+		};
+	};
+
+	mdio@26000 {
+		tbi1: tbi-phy@11 {
+			reg = <0x11>;
+			device_type = "tbi-phy";
+		};
+	};
+
+	ethernet@b0000 {
+		phy-handle = <&phy2>;
+		phy-connection-type = "rgmii-id";
+	};
+
+	ethernet@b1000 {
+		phy-handle = <&phy0>;
+		tbi-handle = <&tbi0>;
+		phy-connection-type = "sgmii";
+	};
+
+	ethernet@b2000 {
+		phy-handle = <&phy1>;
+		phy-connection-type = "rgmii-id";
+	};
+};
diff --git a/arch/powerpc/boot/dts/p1024rdb_32b.dts b/arch/powerpc/boot/dts/p1024rdb_32b.dts
new file mode 100644
index 000000000000..90e803e9ba5f
--- /dev/null
+++ b/arch/powerpc/boot/dts/p1024rdb_32b.dts
@@ -0,0 +1,87 @@
+/*
+ * P1024 RDB 32Bit Physical Address Map Device Tree Source
+ *
+ * Copyright 2012 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in the
+ *       documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Freescale Semiconductor nor the
+ *       names of its contributors may be used to endorse or promote products
+ *       derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+/include/ "fsl/p1020si-pre.dtsi"
+/ {
+	model = "fsl,P1024RDB";
+	compatible = "fsl,P1024RDB";
+
+	memory {
+		device_type = "memory";
+	};
+
+	lbc: localbus@ffe05000 {
+		reg = <0x0 0xffe05000 0 0x1000>;
+		ranges = <0x0 0x0 0x0 0xef000000 0x01000000
+			  0x1 0x0 0x0 0xff800000 0x00040000>;
+	};
+
+	soc: soc@ffe00000 {
+		ranges = <0x0 0x0 0xffe00000 0x100000>;
+	};
+
+	pci0: pcie@ffe09000 {
+		reg = <0x0 0xffe09000 0 0x1000>;
+		ranges = <0x2000000 0x0 0xe0000000 0x0 0xa0000000 0x0 0x20000000
+			  0x1000000 0x0 0x00000000 0x0 0xffc10000 0x0 0x10000>;
+		pcie@0 {
+			ranges = <0x2000000 0x0 0xe0000000
+				  0x2000000 0x0 0xe0000000
+				  0x0 0x20000000
+
+				  0x1000000 0x0 0x0
+				  0x1000000 0x0 0x0
+				  0x0 0x100000>;
+		};
+	};
+
+	pci1: pcie@ffe0a000 {
+		reg = <0x0 0xffe0a000 0 0x1000>;
+		ranges = <0x2000000 0x0 0xe0000000 0x0 0x80000000 0x0 0x20000000
+			  0x1000000 0x0 0x00000000 0x0 0xffc00000 0x0 0x10000>;
+		pcie@0 {
+			reg = <0x0 0x0 0x0 0x0 0x0>;
+			ranges = <0x2000000 0x0 0xe0000000
+				  0x2000000 0x0 0xe0000000
+				  0x0 0x20000000
+
+				  0x1000000 0x0 0x0
+				  0x1000000 0x0 0x0
+				  0x0 0x100000>;
+		};
+	};
+};
+
+/include/ "p1024rdb.dtsi"
+/include/ "fsl/p1020si-post.dtsi"
diff --git a/arch/powerpc/boot/dts/p1024rdb_36b.dts b/arch/powerpc/boot/dts/p1024rdb_36b.dts
new file mode 100644
index 000000000000..3656825b65a1
--- /dev/null
+++ b/arch/powerpc/boot/dts/p1024rdb_36b.dts
@@ -0,0 +1,87 @@
+/*
+ * P1024 RDB 36Bit Physical Address Map Device Tree Source
+ *
+ * Copyright 2012 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in the
+ *       documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Freescale Semiconductor nor the
+ *       names of its contributors may be used to endorse or promote products
+ *       derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+/include/ "fsl/p1020si-pre.dtsi"
+/ {
+	model = "fsl,P1024RDB";
+	compatible = "fsl,P1024RDB";
+
+	memory {
+		device_type = "memory";
+	};
+
+	lbc: localbus@fffe05000 {
+		reg = <0xf 0xffe05000 0 0x1000>;
+		ranges = <0x0 0x0 0xf 0xef000000 0x01000000
+			  0x1 0x0 0xf 0xff800000 0x00040000>;
+	};
+
+	soc: soc@fffe00000 {
+		ranges = <0x0 0xf 0xffe00000 0x100000>;
+	};
+
+	pci0: pcie@fffe09000 {
+		reg = <0xf 0xffe09000 0 0x1000>;
+		ranges = <0x2000000 0x0 0xe0000000 0xc 0x20000000 0x0 0x20000000
+			  0x1000000 0x0 0x00000000 0xf 0xffc10000 0x0 0x10000>;
+		pcie@0 {
+			ranges = <0x2000000 0x0 0xe0000000
+				  0x2000000 0x0 0xe0000000
+				  0x0 0x20000000
+
+				  0x1000000 0x0 0x0
+				  0x1000000 0x0 0x0
+				  0x0 0x100000>;
+		};
+	};
+
+	pci1: pcie@fffe0a000 {
+		reg = <0xf 0xffe0a000 0 0x1000>;
+		ranges = <0x2000000 0x0 0xe0000000 0xc 0x00000000 0x0 0x20000000
+			  0x1000000 0x0 0x00000000 0xf 0xffc00000 0x0 0x10000>;
+		pcie@0 {
+			reg = <0x0 0x0 0x0 0x0 0x0>;
+			ranges = <0x2000000 0x0 0xe0000000
+				  0x2000000 0x0 0xe0000000
+				  0x0 0x20000000
+
+				  0x1000000 0x0 0x0
+				  0x1000000 0x0 0x0
+				  0x0 0x100000>;
+		};
+	};
+};
+
+/include/ "p1024rdb.dtsi"
+/include/ "fsl/p1020si-post.dtsi"
diff --git a/arch/powerpc/boot/dts/p1025rdb.dtsi b/arch/powerpc/boot/dts/p1025rdb.dtsi
index cf3676fc714b..f50256482297 100644
--- a/arch/powerpc/boot/dts/p1025rdb.dtsi
+++ b/arch/powerpc/boot/dts/p1025rdb.dtsi
@@ -282,5 +282,45 @@
 				0x1  0x4  0x2  0x0  0x2  0x0    /* ENET5_RX_DV_SER5_CTS_B */
 				0x1  0x8  0x2  0x0  0x2  0x0>;    /* ENET5_RX_ER_SER5_CD_B */
 		};
+
+		pio3: ucc_pin@03 {
+			pio-map = <
+		/* port  pin  dir  open_drain  assignment  has_irq */
+				0x0  0x16 0x2  0x0  0x2  0x0    /* SER7_CD_B*/
+				0x0  0x12 0x2  0x0  0x2  0x0    /* SER7_CTS_B*/
+				0x0  0x13 0x1  0x0  0x2  0x0    /* SER7_RTS_B*/
+				0x0  0x14 0x2  0x0  0x2  0x0    /* SER7_RXD0*/
+				0x0  0x15 0x1  0x0  0x2  0x0>;    /* SER7_TXD0*/
+		};
+
+		pio4: ucc_pin@04 {
+			pio-map = <
+		/* port  pin  dir  open_drain  assignment  has_irq */
+				0x1  0x0  0x2  0x0  0x2  0x0    /* SER3_CD_B*/
+				0x0  0x1c 0x2  0x0  0x2  0x0    /* SER3_CTS_B*/
+				0x0  0x1d 0x1  0x0  0x2  0x0    /* SER3_RTS_B*/
+				0x0  0x1e 0x2  0x0  0x2  0x0    /* SER3_RXD0*/
+				0x0  0x1f 0x1  0x0  0x2  0x0>;    /* SER3_TXD0*/
+		};
+	};
+};
+
+&qe {
+	serial2: ucc@2600 {
+		device_type = "serial";
+		compatible = "ucc_uart";
+		port-number = <0>;
+		rx-clock-name = "brg6";
+		tx-clock-name = "brg6";
+		pio-handle = <&pio3>;
+	};
+
+	serial3: ucc@2200 {
+		device_type = "serial";
+		compatible = "ucc_uart";
+		port-number = <1>;
+		rx-clock-name = "brg2";
+		tx-clock-name = "brg2";
+		pio-handle = <&pio4>;
 	};
 };
diff --git a/arch/powerpc/boot/dts/p2020ds.dtsi b/arch/powerpc/boot/dts/p2020ds.dtsi
index d3b939c573b0..e699cf95b063 100644
--- a/arch/powerpc/boot/dts/p2020ds.dtsi
+++ b/arch/powerpc/boot/dts/p2020ds.dtsi
@@ -150,6 +150,16 @@
 			interrupts = <3 1 0 0>;
 			reg = <0x2>;
 		};
+
+		sgmii_phy1: sgmii-phy@1 {
+			interrupts = <5 1 0 0>;
+			reg = <0x1c>;
+		};
+		sgmii_phy2: sgmii-phy@2 {
+			interrupts = <5 1 0 0>;
+			reg = <0x1d>;
+		};
+
 		tbi0: tbi-phy@11 {
 			reg = <0x11>;
 			device_type = "tbi-phy";
diff --git a/arch/powerpc/boot/dts/p2020rdb.dts b/arch/powerpc/boot/dts/p2020rdb.dts
index 153bc76bb48e..4d52bce1d5b0 100644
--- a/arch/powerpc/boot/dts/p2020rdb.dts
+++ b/arch/powerpc/boot/dts/p2020rdb.dts
@@ -34,7 +34,7 @@
 
 		/* NOR and NAND Flashes */
 		ranges = <0x0 0x0 0x0 0xef000000 0x01000000
-			  0x1 0x0 0x0 0xff800000 0x00040000
+			  0x1 0x0 0x0 0xffa00000 0x00040000
 			  0x2 0x0 0x0 0xffb00000 0x00020000>;
 
 		nor@0,0 {
diff --git a/arch/powerpc/boot/dts/p2041rdb.dts b/arch/powerpc/boot/dts/p2041rdb.dts
index 285213976a7f..baab0347dab0 100644
--- a/arch/powerpc/boot/dts/p2041rdb.dts
+++ b/arch/powerpc/boot/dts/p2041rdb.dts
@@ -121,7 +121,8 @@
 
 	lbc: localbus@ffe124000 {
 		reg = <0xf 0xfe124000 0 0x1000>;
-		ranges = <0 0 0xf 0xe8000000 0x08000000>;
+		ranges = <0 0 0xf 0xe8000000 0x08000000
+			  1 0 0xf 0xffa00000 0x00040000>;
 
 		flash@0,0 {
 			compatible = "cfi-flash";
@@ -129,6 +130,44 @@
 			bank-width = <2>;
 			device-width = <2>;
 		};
+
+		nand@1,0 {
+			#address-cells = <1>;
+			#size-cells = <1>;
+			compatible = "fsl,elbc-fcm-nand";
+			reg = <0x1 0x0 0x40000>;
+
+			partition@0 {
+				label = "NAND U-Boot Image";
+				reg = <0x0 0x02000000>;
+				read-only;
+			};
+
+			partition@2000000 {
+				label = "NAND Root File System";
+				reg = <0x02000000 0x10000000>;
+			};
+
+			partition@12000000 {
+				label = "NAND Compressed RFS Image";
+				reg = <0x12000000 0x08000000>;
+			};
+
+			partition@1a000000 {
+				label = "NAND Linux Kernel Image";
+				reg = <0x1a000000 0x04000000>;
+			};
+
+			partition@1e000000 {
+				label = "NAND DTB Image";
+				reg = <0x1e000000 0x01000000>;
+			};
+
+			partition@1f000000 {
+				label = "NAND Writable User area";
+				reg = <0x1f000000 0x01000000>;
+			};
+		};
 	};
 
 	pci0: pcie@ffe200000 {
diff --git a/arch/powerpc/boot/dts/p3060qds.dts b/arch/powerpc/boot/dts/p3060qds.dts
deleted file mode 100644
index 9ae875c8a211..000000000000
--- a/arch/powerpc/boot/dts/p3060qds.dts
+++ /dev/null
@@ -1,242 +0,0 @@
-/*
- * P3060QDS Device Tree Source
- *
- * Copyright 2011 Freescale Semiconductor Inc.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *     * Redistributions of source code must retain the above copyright
- *       notice, this list of conditions and the following disclaimer.
- *     * Redistributions in binary form must reproduce the above copyright
- *       notice, this list of conditions and the following disclaimer in the
- *       documentation and/or other materials provided with the distribution.
- *     * Neither the name of Freescale Semiconductor nor the
- *       names of its contributors may be used to endorse or promote products
- *       derived from this software without specific prior written permission.
- *
- *
- * ALTERNATIVELY, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") as published by the Free Software
- * Foundation, either version 2 of that License or (at your option) any
- * later version.
- *
- * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
- * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
- * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
- * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
- * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
- * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
- * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
- * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
- * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- */
-
-/include/ "fsl/p3060si-pre.dtsi"
-
-/ {
-	model = "fsl,P3060QDS";
-	compatible = "fsl,P3060QDS";
-	#address-cells = <2>;
-	#size-cells = <2>;
-	interrupt-parent = <&mpic>;
-
-	memory {
-		device_type = "memory";
-	};
-
-	dcsr: dcsr@f00000000 {
-		ranges = <0x00000000 0xf 0x00000000 0x01008000>;
-	};
-
-	soc: soc@ffe000000 {
-		ranges = <0x00000000 0xf 0xfe000000 0x1000000>;
-		reg = <0xf 0xfe000000 0 0x00001000>;
-		spi@110000 {
-			flash@0 {
-				#address-cells = <1>;
-				#size-cells = <1>;
-				compatible = "spansion,s25sl12801";
-				reg = <0>;
-				spi-max-frequency = <40000000>; /* input clock */
-				partition@u-boot {
-					label = "u-boot";
-					reg = <0x00000000 0x00100000>;
-					read-only;
-				};
-				partition@kernel {
-					label = "kernel";
-					reg = <0x00100000 0x00500000>;
-					read-only;
-				};
-				partition@dtb {
-					label = "dtb";
-					reg = <0x00600000 0x00100000>;
-					read-only;
-				};
-				partition@fs {
-					label = "file system";
-					reg = <0x00700000 0x00900000>;
-				};
-			};
-			flash@1 {
-				#address-cells = <1>;
-				#size-cells = <1>;
-				compatible = "spansion,en25q32b";
-				reg = <1>;
-				spi-max-frequency = <40000000>; /* input clock */
-				partition@spi1 {
-					label = "spi1";
-					reg = <0x00000000 0x00400000>;
-				};
-			};
-			flash@2 {
-				#address-cells = <1>;
-				#size-cells = <1>;
-				compatible = "atmel,at45db081d";
-				reg = <2>;
-				spi-max-frequency = <40000000>; /* input clock */
-				partition@spi1 {
-					label = "spi2";
-					reg = <0x00000000 0x00100000>;
-				};
-			};
-			flash@3 {
-				#address-cells = <1>;
-				#size-cells = <1>;
-				compatible = "spansion,sst25wf040";
-				reg = <3>;
-				spi-max-frequency = <40000000>; /* input clock */
-				partition@spi3 {
-					label = "spi3";
-					reg = <0x00000000 0x00080000>;
-				};
-			};
-		};
-
-		i2c@118000 {
-			eeprom@51 {
-				compatible = "at24,24c256";
-				reg = <0x51>;
-			};
-			eeprom@53 {
-				compatible = "at24,24c256";
-				reg = <0x53>;
-			};
-			rtc@68 {
-				compatible = "dallas,ds3232";
-				reg = <0x68>;
-				interrupts = <0x1 0x1 0 0>;
-			};
-		};
-
-		usb0: usb@210000 {
-			phy_type = "ulpi";
-		};
-
-		usb1: usb@211000 {
-			dr_mode = "host";
-			phy_type = "ulpi";
-		};
-	};
-
-	rio: rapidio@ffe0c0000 {
-		reg = <0xf 0xfe0c0000 0 0x11000>;
-
-		port1 {
-			ranges = <0 0 0xc 0x20000000 0 0x10000000>;
-		};
-		port2 {
-			ranges = <0 0 0xc 0x30000000 0 0x10000000>;
-		};
-	};
-
-	lbc: localbus@ffe124000 {
-		reg = <0xf 0xfe124000 0 0x1000>;
-		ranges = <0 0 0xf 0xe8000000 0x08000000
-			  2 0 0xf 0xffa00000 0x00040000
-			  3 0 0xf 0xffdf0000 0x00008000>;
-
-		flash@0,0 {
-			compatible = "cfi-flash";
-			reg = <0 0 0x08000000>;
-			bank-width = <2>;
-			device-width = <2>;
-		};
-
-		nand@2,0 {
-			#address-cells = <1>;
-			#size-cells = <1>;
-			compatible = "fsl,elbc-fcm-nand";
-			reg = <0x2 0x0 0x40000>;
-
-			partition@0 {
-				label = "NAND U-Boot Image";
-				reg = <0x0 0x02000000>;
-				read-only;
-			};
-
-			partition@2000000 {
-				label = "NAND Root File System";
-				reg = <0x02000000 0x10000000>;
-			};
-
-			partition@12000000 {
-				label = "NAND Compressed RFS Image";
-				reg = <0x12000000 0x08000000>;
-			};
-
-			partition@1a000000 {
-				label = "NAND Linux Kernel Image";
-				reg = <0x1a000000 0x04000000>;
-			};
-
-			partition@1e000000 {
-				label = "NAND DTB Image";
-				reg = <0x1e000000 0x01000000>;
-			};
-
-			partition@1f000000 {
-				label = "NAND Writable User area";
-				reg = <0x1f000000 0x21000000>;
-			};
-		};
-
-		board-control@3,0 {
-			compatible = "fsl,p3060qds-fpga", "fsl,fpga-qixis";
-			reg = <3 0 0x100>;
-		};
-	};
-
-	pci0: pcie@ffe200000 {
-		reg = <0xf 0xfe200000 0 0x1000>;
-		ranges = <0x02000000 0 0xe0000000 0xc 0x00000000 0x0 0x20000000
-			  0x01000000 0 0x00000000 0xf 0xf8000000 0x0 0x00010000>;
-		pcie@0 {
-			ranges = <0x02000000 0 0xe0000000
-				  0x02000000 0 0xe0000000
-				  0 0x20000000
-
-				  0x01000000 0 0x00000000
-				  0x01000000 0 0x00000000
-				  0 0x00010000>;
-		};
-	};
-
-	pci1: pcie@ffe201000 {
-		reg = <0xf 0xfe201000 0 0x1000>;
-		ranges = <0x02000000 0x0 0xe0000000 0xc 0x20000000 0x0 0x20000000
-			  0x01000000 0x0 0x00000000 0xf 0xf8010000 0x0 0x00010000>;
-		pcie@0 {
-			ranges = <0x02000000 0 0xe0000000
-				  0x02000000 0 0xe0000000
-				  0 0x20000000
-
-				  0x01000000 0 0x00000000
-				  0x01000000 0 0x00000000
-				  0 0x00010000>;
-		};
-	};
-};
-
-/include/ "fsl/p3060si-post.dtsi"
diff --git a/arch/powerpc/boot/dts/sbc8560.dts b/arch/powerpc/boot/dts/sbc8560.dts
deleted file mode 100644
index 72078eb15616..000000000000
--- a/arch/powerpc/boot/dts/sbc8560.dts
+++ /dev/null
@@ -1,406 +0,0 @@
-/*
- * SBC8560 Device Tree Source
- *
- * Copyright 2007 Wind River Systems Inc.
- *
- * Paul Gortmaker (see MAINTAINERS for contact information)
- *
- * 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.
- */
-
-/dts-v1/;
-
-/ {
-	model = "SBC8560";
-	compatible = "SBC8560";
-	#address-cells = <1>;
-	#size-cells = <1>;
-
-	aliases {
-		ethernet0 = &enet0;
-		ethernet1 = &enet1;
-		ethernet2 = &enet2;
-		ethernet3 = &enet3;
-		serial0 = &serial0;
-		serial1 = &serial1;
-		pci0 = &pci0;
-	};
-
-	cpus {
-		#address-cells = <1>;
-		#size-cells = <0>;
-
-		PowerPC,8560@0 {
-			device_type = "cpu";
-			reg = <0>;
-			d-cache-line-size = <0x20>;	// 32 bytes
-			i-cache-line-size = <0x20>;	// 32 bytes
-			d-cache-size = <0x8000>;	// L1, 32K
-			i-cache-size = <0x8000>;	// L1, 32K
-			timebase-frequency = <0>;	// From uboot
-			bus-frequency = <0>;
-			clock-frequency = <0>;
-			next-level-cache = <&L2>;
-		};
-	};
-
-	memory {
-		device_type = "memory";
-		reg = <0x00000000 0x20000000>;
-	};
-
-	soc@ff700000 {
-		#address-cells = <1>;
-		#size-cells = <1>;
-		device_type = "soc";
-		ranges = <0x0 0xff700000 0x00100000>;
-		clock-frequency = <0>;
-
-		ecm-law@0 {
-			compatible = "fsl,ecm-law";
-			reg = <0x0 0x1000>;
-			fsl,num-laws = <8>;
-		};
-
-		ecm@1000 {
-			compatible = "fsl,mpc8560-ecm", "fsl,ecm";
-			reg = <0x1000 0x1000>;
-			interrupts = <17 2>;
-			interrupt-parent = <&mpic>;
-		};
-
-		memory-controller@2000 {
-			compatible = "fsl,mpc8560-memory-controller";
-			reg = <0x2000 0x1000>;
-			interrupt-parent = <&mpic>;
-			interrupts = <0x12 0x2>;
-		};
-
-		L2: l2-cache-controller@20000 {
-			compatible = "fsl,mpc8560-l2-cache-controller";
-			reg = <0x20000 0x1000>;
-			cache-line-size = <0x20>;	// 32 bytes
-			cache-size = <0x40000>;		// L2, 256K
-			interrupt-parent = <&mpic>;
-			interrupts = <0x10 0x2>;
-		};
-
-		i2c@3000 {
-			#address-cells = <1>;
-			#size-cells = <0>;
-			cell-index = <0>;
-			compatible = "fsl-i2c";
-			reg = <0x3000 0x100>;
-			interrupts = <0x2b 0x2>;
-			interrupt-parent = <&mpic>;
-			dfsrr;
-		};
-
-		i2c@3100 {
-			#address-cells = <1>;
-			#size-cells = <0>;
-			cell-index = <1>;
-			compatible = "fsl-i2c";
-			reg = <0x3100 0x100>;
-			interrupts = <0x2b 0x2>;
-			interrupt-parent = <&mpic>;
-			dfsrr;
-		};
-
-		dma@21300 {
-			#address-cells = <1>;
-			#size-cells = <1>;
-			compatible = "fsl,mpc8560-dma", "fsl,eloplus-dma";
-			reg = <0x21300 0x4>;
-			ranges = <0x0 0x21100 0x200>;
-			cell-index = <0>;
-			dma-channel@0 {
-				compatible = "fsl,mpc8560-dma-channel",
-						"fsl,eloplus-dma-channel";
-				reg = <0x0 0x80>;
-				cell-index = <0>;
-				interrupt-parent = <&mpic>;
-				interrupts = <20 2>;
-			};
-			dma-channel@80 {
-				compatible = "fsl,mpc8560-dma-channel",
-						"fsl,eloplus-dma-channel";
-				reg = <0x80 0x80>;
-				cell-index = <1>;
-				interrupt-parent = <&mpic>;
-				interrupts = <21 2>;
-			};
-			dma-channel@100 {
-				compatible = "fsl,mpc8560-dma-channel",
-						"fsl,eloplus-dma-channel";
-				reg = <0x100 0x80>;
-				cell-index = <2>;
-				interrupt-parent = <&mpic>;
-				interrupts = <22 2>;
-			};
-			dma-channel@180 {
-				compatible = "fsl,mpc8560-dma-channel",
-						"fsl,eloplus-dma-channel";
-				reg = <0x180 0x80>;
-				cell-index = <3>;
-				interrupt-parent = <&mpic>;
-				interrupts = <23 2>;
-			};
-		};
-
-		enet0: ethernet@24000 {
-			#address-cells = <1>;
-			#size-cells = <1>;
-			cell-index = <0>;
-			device_type = "network";
-			model = "TSEC";
-			compatible = "gianfar";
-			reg = <0x24000 0x1000>;
-			ranges = <0x0 0x24000 0x1000>;
-			local-mac-address = [ 00 00 00 00 00 00 ];
-			interrupts = <0x1d 0x2 0x1e 0x2 0x22 0x2>;
-			interrupt-parent = <&mpic>;
-			tbi-handle = <&tbi0>;
-			phy-handle = <&phy0>;
-
-			mdio@520 {
-				#address-cells = <1>;
-				#size-cells = <0>;
-				compatible = "fsl,gianfar-mdio";
-				reg = <0x520 0x20>;
-				phy0: ethernet-phy@19 {
-					interrupt-parent = <&mpic>;
-					interrupts = <0x6 0x1>;
-					reg = <0x19>;
-					device_type = "ethernet-phy";
-				};
-				phy1: ethernet-phy@1a {
-					interrupt-parent = <&mpic>;
-					interrupts = <0x7 0x1>;
-					reg = <0x1a>;
-					device_type = "ethernet-phy";
-				};
-				phy2: ethernet-phy@1b {
-					interrupt-parent = <&mpic>;
-					interrupts = <0x8 0x1>;
-					reg = <0x1b>;
-					device_type = "ethernet-phy";
-				};
-				phy3: ethernet-phy@1c {
-					interrupt-parent = <&mpic>;
-					interrupts = <0x8 0x1>;
-					reg = <0x1c>;
-					device_type = "ethernet-phy";
-				};
-				tbi0: tbi-phy@11 {
-					reg = <0x11>;
-					device_type = "tbi-phy";
-				};
-			};
-		};
-
-		enet1: ethernet@25000 {
-			#address-cells = <1>;
-			#size-cells = <1>;
-			cell-index = <1>;
-			device_type = "network";
-			model = "TSEC";
-			compatible = "gianfar";
-			reg = <0x25000 0x1000>;
-			ranges = <0x0 0x25000 0x1000>;
-			local-mac-address = [ 00 00 00 00 00 00 ];
-			interrupts = <0x23 0x2 0x24 0x2 0x28 0x2>;
-			interrupt-parent = <&mpic>;
-			tbi-handle = <&tbi1>;
-			phy-handle = <&phy1>;
-
-			mdio@520 {
-				#address-cells = <1>;
-				#size-cells = <0>;
-				compatible = "fsl,gianfar-tbi";
-				reg = <0x520 0x20>;
-
-				tbi1: tbi-phy@11 {
-					reg = <0x11>;
-					device_type = "tbi-phy";
-				};
-			};
-		};
-
-		mpic: pic@40000 {
-			interrupt-controller;
-			#address-cells = <0>;
-			#interrupt-cells = <2>;
-			compatible = "chrp,open-pic";
-			reg = <0x40000 0x40000>;
-			device_type = "open-pic";
-		};
-
-		cpm@919c0 {
-			#address-cells = <1>;
-			#size-cells = <1>;
-			compatible = "fsl,mpc8560-cpm", "fsl,cpm2";
-			reg = <0x919c0 0x30>;
-			ranges;
-
-			muram@80000 {
-				#address-cells = <1>;
-				#size-cells = <1>;
-				ranges = <0x0 0x80000 0x10000>;
-
-				data@0 {
-					compatible = "fsl,cpm-muram-data";
-					reg = <0x0 0x4000 0x9000 0x2000>;
-				};
-			};
-
-			brg@919f0 {
-				compatible = "fsl,mpc8560-brg",
-				             "fsl,cpm2-brg",
-				             "fsl,cpm-brg";
-				reg = <0x919f0 0x10 0x915f0 0x10>;
-				clock-frequency = <165000000>;
-			};
-
-			cpmpic: pic@90c00 {
-				interrupt-controller;
-				#address-cells = <0>;
-				#interrupt-cells = <2>;
-				interrupts = <0x2e 0x2>;
-				interrupt-parent = <&mpic>;
-				reg = <0x90c00 0x80>;
-				compatible = "fsl,mpc8560-cpm-pic", "fsl,cpm2-pic";
-			};
-
-			enet2: ethernet@91320 {
-				device_type = "network";
-				compatible = "fsl,mpc8560-fcc-enet",
-				             "fsl,cpm2-fcc-enet";
-				reg = <0x91320 0x20 0x88500 0x100 0x913b0 0x1>;
-				local-mac-address = [ 00 00 00 00 00 00 ];
-				fsl,cpm-command = <0x16200300>;
-				interrupts = <0x21 0x8>;
-				interrupt-parent = <&cpmpic>;
-				phy-handle = <&phy2>;
-			};
-
-			enet3: ethernet@91340 {
-				device_type = "network";
-				compatible = "fsl,mpc8560-fcc-enet",
-				             "fsl,cpm2-fcc-enet";
-				reg = <0x91340 0x20 0x88600 0x100 0x913d0 0x1>;
-				local-mac-address = [ 00 00 00 00 00 00 ];
-				fsl,cpm-command = <0x1a400300>;
-				interrupts = <0x22 0x8>;
-				interrupt-parent = <&cpmpic>;
-				phy-handle = <&phy3>;
-			};
-		};
-
-		global-utilities@e0000 {
-			compatible = "fsl,mpc8560-guts";
-			reg = <0xe0000 0x1000>;
-		};
-	};
-
-	pci0: pci@ff708000 {
-		#interrupt-cells = <1>;
-		#size-cells = <2>;
-		#address-cells = <3>;
-		compatible = "fsl,mpc8540-pcix", "fsl,mpc8540-pci";
-		device_type = "pci";
-		reg = <0xff708000 0x1000>;
-		clock-frequency = <66666666>;
-		interrupt-map-mask = <0xf800 0x0 0x0 0x7>;
-		interrupt-map = <
-
-			/* IDSEL 0x02 */
-			0x1000 0x0 0x0 0x1 &mpic 0x2 0x1
-			0x1000 0x0 0x0 0x2 &mpic 0x3 0x1
-			0x1000 0x0 0x0 0x3 &mpic 0x4 0x1
-			0x1000 0x0 0x0 0x4 &mpic 0x5 0x1>;
-
-		interrupt-parent = <&mpic>;
-		interrupts = <0x18 0x2>;
-		bus-range = <0x0 0x0>;
-		ranges = <0x02000000 0x0 0x80000000 0x80000000 0x0 0x20000000
-			  0x01000000 0x0 0x00000000 0xe2000000 0x0 0x00100000>;
-	};
-
-	localbus@ff705000 {
-		compatible = "fsl,mpc8560-localbus", "simple-bus";
-		#address-cells = <2>;
-		#size-cells = <1>;
-		reg = <0xff705000 0x100>;	// BRx, ORx, etc.
-
-		ranges = <
-			0x0 0x0 0xff800000 0x0800000	// 8MB boot flash
-			0x1 0x0 0xe4000000 0x4000000	// 64MB flash
-			0x3 0x0 0x20000000 0x4000000	// 64MB SDRAM
-			0x4 0x0 0x24000000 0x4000000	// 64MB SDRAM
-			0x5 0x0 0xfc000000 0x0c00000	// EPLD
-			0x6 0x0 0xe0000000 0x4000000	// 64MB flash
-			0x7 0x0 0x80000000 0x0200000	// ATM1,2
-		>;
-
-		epld@5,0 {
-			compatible = "wrs,epld-localbus";
-			#address-cells = <2>;
-			#size-cells = <1>;
-			reg = <0x5 0x0 0xc00000>;
-			ranges = <
-				0x0 0x0 0x5 0x000000 0x1fff	// LED disp.
-				0x1 0x0 0x5 0x100000 0x1fff	// switches
-				0x2 0x0 0x5 0x200000 0x1fff	// ID reg.
-				0x3 0x0 0x5 0x300000 0x1fff	// status reg.
-				0x4 0x0 0x5 0x400000 0x1fff	// reset reg.
-				0x5 0x0 0x5 0x500000 0x1fff	// Wind port
-				0x7 0x0 0x5 0x700000 0x1fff	// UART #1
-				0x8 0x0 0x5 0x800000 0x1fff	// UART #2
-				0x9 0x0 0x5 0x900000 0x1fff	// RTC
-				0xb 0x0 0x5 0xb00000 0x1fff	// EEPROM
-			>;
-
-			bidr@2,0 {
-				compatible = "wrs,sbc8560-bidr";
-				reg = <0x2 0x0 0x10>;
-			};
-
-			bcsr@3,0 {
-				compatible = "wrs,sbc8560-bcsr";
-				reg = <0x3 0x0 0x10>;
-			};
-
-			brstcr@4,0 {
-				compatible = "wrs,sbc8560-brstcr";
-				reg = <0x4 0x0 0x10>;
-			};
-
-			serial0: serial@7,0 {
-				device_type = "serial";
-				compatible = "ns16550";
-				reg = <0x7 0x0 0x100>;
-				clock-frequency = <1843200>;
-				interrupts = <0x9 0x2>;
-				interrupt-parent = <&mpic>;
-			};
-
-			serial1: serial@8,0 {
-				device_type = "serial";
-				compatible = "ns16550";
-				reg = <0x8 0x0 0x100>;
-				clock-frequency = <1843200>;
-				interrupts = <0xa 0x2>;
-				interrupt-parent = <&mpic>;
-			};
-
-			rtc@9,0 {
-				compatible = "m48t59";
-				reg = <0x9 0x0 0x1fff>;
-			};
-		};
-	};
-};
diff --git a/arch/powerpc/boot/flatdevtree_env.h b/arch/powerpc/boot/flatdevtree_env.h
deleted file mode 100644
index 66e0ebb1a364..000000000000
--- a/arch/powerpc/boot/flatdevtree_env.h
+++ /dev/null
@@ -1,27 +0,0 @@
-/*
- * This file adds the header file glue so that the shared files
- * flatdevicetree.[ch] can compile and work in the powerpc bootwrapper.
- *
- * strncmp & strchr copied from <file:lib/string.c>
- * Copyright (C) 1991, 1992  Linus Torvalds
- *
- * Maintained by: Mark A. Greer <mgreer@mvista.com>
- */
-#ifndef _PPC_BOOT_FLATDEVTREE_ENV_H_
-#define _PPC_BOOT_FLATDEVTREE_ENV_H_
-
-#include <stdarg.h>
-#include <stddef.h>
-#include "types.h"
-#include "string.h"
-#include "stdio.h"
-#include "ops.h"
-
-#define be16_to_cpu(x)		(x)
-#define cpu_to_be16(x)		(x)
-#define be32_to_cpu(x)		(x)
-#define cpu_to_be32(x)		(x)
-#define be64_to_cpu(x)		(x)
-#define cpu_to_be64(x)		(x)
-
-#endif /* _PPC_BOOT_FLATDEVTREE_ENV_H_ */
diff --git a/arch/powerpc/configs/83xx/kmeter1_defconfig b/arch/powerpc/configs/83xx/kmeter1_defconfig
index 07e1bbadebfe..a0dfef1fcdb7 100644
--- a/arch/powerpc/configs/83xx/kmeter1_defconfig
+++ b/arch/powerpc/configs/83xx/kmeter1_defconfig
@@ -2,14 +2,14 @@ CONFIG_EXPERIMENTAL=y
 # CONFIG_SWAP is not set
 CONFIG_SYSVIPC=y
 CONFIG_POSIX_MQUEUE=y
-CONFIG_SPARSE_IRQ=y
 CONFIG_LOG_BUF_SHIFT=14
 CONFIG_EXPERT=y
-# CONFIG_HOTPLUG is not set
 CONFIG_SLAB=y
 CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
 # CONFIG_BLK_DEV_BSG is not set
+CONFIG_PARTITION_ADVANCED=y
+# CONFIG_MSDOS_PARTITION is not set
 # CONFIG_IOSCHED_DEADLINE is not set
 # CONFIG_IOSCHED_CFQ is not set
 # CONFIG_PPC_CHRP is not set
@@ -31,11 +31,10 @@ CONFIG_IP_PNP=y
 # CONFIG_INET_XFRM_MODE_BEET is not set
 # CONFIG_INET_LRO is not set
 # CONFIG_IPV6 is not set
+CONFIG_TIPC=y
 CONFIG_BRIDGE=m
 CONFIG_VLAN_8021Q=y
 CONFIG_MTD=y
-CONFIG_MTD_CONCAT=y
-CONFIG_MTD_PARTITIONS=y
 CONFIG_MTD_CMDLINE_PARTS=y
 CONFIG_MTD_CHAR=y
 CONFIG_MTD_BLOCK=y
@@ -50,17 +49,15 @@ CONFIG_MTD_UBI_DEBUG=y
 CONFIG_PROC_DEVICETREE=y
 CONFIG_NETDEVICES=y
 CONFIG_DUMMY=y
-CONFIG_TUN=y
 CONFIG_MII=y
-CONFIG_MARVELL_PHY=y
-CONFIG_NET_ETHERNET=y
+CONFIG_TUN=y
 CONFIG_UCC_GETH=y
-# CONFIG_NETDEV_10000 is not set
-CONFIG_WAN=y
-CONFIG_HDLC=y
+CONFIG_MARVELL_PHY=y
 CONFIG_PPP=y
 CONFIG_PPP_MULTILINK=y
 CONFIG_PPPOE=y
+CONFIG_WAN=y
+CONFIG_HDLC=y
 # CONFIG_INPUT is not set
 # CONFIG_SERIO is not set
 # CONFIG_VT is not set
@@ -77,10 +74,7 @@ CONFIG_UIO=y
 # CONFIG_DNOTIFY is not set
 CONFIG_TMPFS=y
 CONFIG_JFFS2_FS=y
+CONFIG_UBIFS_FS=y
 CONFIG_NFS_FS=y
 CONFIG_NFS_V3=y
 CONFIG_ROOT_NFS=y
-CONFIG_PARTITION_ADVANCED=y
-# CONFIG_MSDOS_PARTITION is not set
-# CONFIG_RCU_CPU_STALL_DETECTOR is not set
-CONFIG_SYSCTL_SYSCALL_CHECK=y
diff --git a/arch/powerpc/configs/85xx/sbc8560_defconfig b/arch/powerpc/configs/85xx/sbc8560_defconfig
deleted file mode 100644
index f7fdb0318e4c..000000000000
--- a/arch/powerpc/configs/85xx/sbc8560_defconfig
+++ /dev/null
@@ -1,65 +0,0 @@
-CONFIG_PPC_85xx=y
-CONFIG_EXPERIMENTAL=y
-CONFIG_SYSVIPC=y
-CONFIG_LOG_BUF_SHIFT=14
-CONFIG_BLK_DEV_INITRD=y
-# CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
-CONFIG_EXPERT=y
-CONFIG_SLAB=y
-# CONFIG_BLK_DEV_BSG is not set
-CONFIG_SBC8560=y
-CONFIG_BINFMT_MISC=y
-CONFIG_SPARSE_IRQ=y
-# CONFIG_SECCOMP is not set
-CONFIG_NET=y
-CONFIG_PACKET=y
-CONFIG_UNIX=y
-CONFIG_XFRM_USER=y
-CONFIG_INET=y
-CONFIG_IP_MULTICAST=y
-CONFIG_IP_PNP=y
-CONFIG_IP_PNP_DHCP=y
-CONFIG_IP_PNP_BOOTP=y
-CONFIG_SYN_COOKIES=y
-# CONFIG_INET_LRO is not set
-# CONFIG_IPV6 is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
-# CONFIG_FW_LOADER is not set
-CONFIG_PROC_DEVICETREE=y
-CONFIG_BLK_DEV_LOOP=y
-CONFIG_BLK_DEV_RAM=y
-CONFIG_BLK_DEV_RAM_SIZE=32768
-CONFIG_NETDEVICES=y
-CONFIG_BROADCOM_PHY=y
-CONFIG_NET_ETHERNET=y
-CONFIG_MII=y
-CONFIG_GIANFAR=y
-# CONFIG_INPUT_MOUSEDEV is not set
-# CONFIG_INPUT_KEYBOARD is not set
-# CONFIG_INPUT_MOUSE is not set
-# CONFIG_SERIO is not set
-# CONFIG_VT is not set
-CONFIG_SERIAL_8250=y
-CONFIG_SERIAL_8250_CONSOLE=y
-CONFIG_SERIAL_8250_NR_UARTS=2
-CONFIG_SERIAL_8250_RUNTIME_UARTS=2
-# CONFIG_HW_RANDOM is not set
-CONFIG_VIDEO_OUTPUT_CONTROL=y
-CONFIG_RTC_CLASS=y
-CONFIG_RTC_DRV_M48T59=y
-CONFIG_INOTIFY=y
-CONFIG_PROC_KCORE=y
-CONFIG_TMPFS=y
-CONFIG_NFS_FS=y
-CONFIG_ROOT_NFS=y
-CONFIG_PARTITION_ADVANCED=y
-# CONFIG_MSDOS_PARTITION is not set
-CONFIG_MAGIC_SYSRQ=y
-CONFIG_DEBUG_KERNEL=y
-CONFIG_DETECT_HUNG_TASK=y
-CONFIG_DEBUG_MUTEXES=y
-# CONFIG_DEBUG_BUGVERBOSE is not set
-# CONFIG_RCU_CPU_STALL_DETECTOR is not set
-CONFIG_SYSCTL_SYSCALL_CHECK=y
-CONFIG_PPC_EARLY_DEBUG=y
-# CONFIG_CRYPTO_ANSI_CPRNG is not set
diff --git a/arch/powerpc/configs/corenet32_smp_defconfig b/arch/powerpc/configs/corenet32_smp_defconfig
index 91db656294e8..cbb98c1234fd 100644
--- a/arch/powerpc/configs/corenet32_smp_defconfig
+++ b/arch/powerpc/configs/corenet32_smp_defconfig
@@ -23,7 +23,6 @@ CONFIG_MODVERSIONS=y
 # CONFIG_BLK_DEV_BSG is not set
 CONFIG_P2041_RDB=y
 CONFIG_P3041_DS=y
-CONFIG_P3060_QDS=y
 CONFIG_P4080_DS=y
 CONFIG_P5020_DS=y
 CONFIG_HIGHMEM=y
@@ -32,10 +31,12 @@ CONFIG_HIGH_RES_TIMERS=y
 # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
 CONFIG_BINFMT_MISC=m
 CONFIG_KEXEC=y
+CONFIG_IRQ_ALL_CPUS=y
 CONFIG_FORCE_MAX_ZONEORDER=13
 CONFIG_FSL_LBC=y
 CONFIG_PCI=y
 CONFIG_PCIEPORTBUS=y
+CONFIG_PCI_MSI=y
 # CONFIG_PCIEASPM is not set
 CONFIG_RAPIDIO=y
 CONFIG_FSL_RIO=y
@@ -76,6 +77,11 @@ CONFIG_MTD_BLOCK=y
 CONFIG_MTD_CFI=y
 CONFIG_MTD_CFI_AMDSTD=y
 CONFIG_MTD_PHYSMAP_OF=y
+CONFIG_MTD_NAND=y
+CONFIG_MTD_NAND_ECC=y
+CONFIG_MTD_NAND_IDS=y
+CONFIG_MTD_NAND_FSL_IFC=y
+CONFIG_MTD_NAND_FSL_ELBC=y
 CONFIG_MTD_M25P80=y
 CONFIG_PROC_DEVICETREE=y
 CONFIG_BLK_DEV_LOOP=y
@@ -136,6 +142,8 @@ CONFIG_USB_OHCI_HCD_PPC_OF_LE=y
 CONFIG_USB_STORAGE=y
 CONFIG_MMC=y
 CONFIG_MMC_SDHCI=y
+CONFIG_MMC_SDHCI_OF=y
+CONFIG_MMC_SDHCI_OF_ESDHC=y
 CONFIG_EDAC=y
 CONFIG_EDAC_MM_EDAC=y
 CONFIG_EDAC_MPC85XX=y
diff --git a/arch/powerpc/configs/corenet64_smp_defconfig b/arch/powerpc/configs/corenet64_smp_defconfig
index 6798343580f0..dd89de8b0b7f 100644
--- a/arch/powerpc/configs/corenet64_smp_defconfig
+++ b/arch/powerpc/configs/corenet64_smp_defconfig
@@ -6,7 +6,9 @@ CONFIG_NR_CPUS=2
 CONFIG_EXPERIMENTAL=y
 CONFIG_SYSVIPC=y
 CONFIG_BSD_PROCESS_ACCT=y
-CONFIG_SPARSE_IRQ=y
+CONFIG_IRQ_DOMAIN_DEBUG=y
+CONFIG_NO_HZ=y
+CONFIG_HIGH_RES_TIMERS=y
 CONFIG_IKCONFIG=y
 CONFIG_IKCONFIG_PROC=y
 CONFIG_LOG_BUF_SHIFT=14
@@ -18,11 +20,14 @@ CONFIG_MODULE_UNLOAD=y
 CONFIG_MODULE_FORCE_UNLOAD=y
 CONFIG_MODVERSIONS=y
 # CONFIG_BLK_DEV_BSG is not set
+CONFIG_PARTITION_ADVANCED=y
+CONFIG_MAC_PARTITION=y
 CONFIG_P5020_DS=y
 # CONFIG_PPC_OF_BOOT_TRAMPOLINE is not set
-CONFIG_NO_HZ=y
-CONFIG_HIGH_RES_TIMERS=y
 CONFIG_BINFMT_MISC=m
+CONFIG_IRQ_ALL_CPUS=y
+CONFIG_PCIEPORTBUS=y
+CONFIG_PCI_MSI=y
 CONFIG_RAPIDIO=y
 CONFIG_FSL_RIO=y
 CONFIG_NET=y
@@ -51,12 +56,25 @@ CONFIG_INET_ESP=y
 CONFIG_IPV6=y
 CONFIG_IP_SCTP=m
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
+CONFIG_MTD=y
+CONFIG_MTD_CMDLINE_PARTS=y
+CONFIG_MTD_CHAR=y
+CONFIG_MTD_BLOCK=y
+CONFIG_MTD_CFI=y
+CONFIG_MTD_CFI_AMDSTD=y
+CONFIG_MTD_PHYSMAP_OF=y
+CONFIG_MTD_M25P80=y
+CONFIG_MTD_NAND=y
+CONFIG_MTD_NAND_FSL_ELBC=y
+CONFIG_MTD_NAND_FSL_IFC=y
 CONFIG_PROC_DEVICETREE=y
 CONFIG_BLK_DEV_LOOP=y
 CONFIG_BLK_DEV_RAM=y
 CONFIG_BLK_DEV_RAM_SIZE=131072
-CONFIG_MISC_DEVICES=y
 CONFIG_EEPROM_LEGACY=y
+CONFIG_ATA=y
+CONFIG_SATA_FSL=y
+CONFIG_SATA_SIL24=y
 CONFIG_NETDEVICES=y
 CONFIG_DUMMY=y
 CONFIG_INPUT_FF_MEMLESS=m
@@ -66,39 +84,59 @@ CONFIG_INPUT_FF_MEMLESS=m
 CONFIG_SERIO_LIBPS2=y
 CONFIG_SERIAL_8250=y
 CONFIG_SERIAL_8250_CONSOLE=y
-CONFIG_SERIAL_8250_EXTENDED=y
 CONFIG_SERIAL_8250_MANY_PORTS=y
 CONFIG_SERIAL_8250_DETECT_IRQ=y
 CONFIG_SERIAL_8250_RSA=y
 CONFIG_I2C=y
 CONFIG_I2C_CHARDEV=y
 CONFIG_I2C_MPC=y
+CONFIG_SPI=y
+CONFIG_SPI_GPIO=y
+CONFIG_SPI_FSL_SPI=y
+CONFIG_SPI_FSL_ESPI=y
 # CONFIG_HWMON is not set
 CONFIG_VIDEO_OUTPUT_CONTROL=y
-# CONFIG_HID_SUPPORT is not set
-# CONFIG_USB_SUPPORT is not set
+CONFIG_USB_HID=m
+CONFIG_USB=y
+CONFIG_USB_MON=y
+CONFIG_USB_EHCI_HCD=y
+CONFIG_USB_EHCI_FSL=y
+CONFIG_USB_STORAGE=y
+CONFIG_MMC=y
+CONFIG_MMC_SDHCI=y
+CONFIG_EDAC=y
+CONFIG_EDAC_MM_EDAC=y
 CONFIG_DMADEVICES=y
 CONFIG_FSL_DMA=y
 CONFIG_EXT2_FS=y
 CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
+CONFIG_ISO9660_FS=m
+CONFIG_JOLIET=y
+CONFIG_ZISOFS=y
+CONFIG_UDF_FS=m
+CONFIG_MSDOS_FS=m
+CONFIG_VFAT_FS=y
+CONFIG_NTFS_FS=y
 CONFIG_PROC_KCORE=y
 CONFIG_TMPFS=y
 CONFIG_HUGETLBFS=y
 # CONFIG_MISC_FILESYSTEMS is not set
-CONFIG_PARTITION_ADVANCED=y
-CONFIG_MAC_PARTITION=y
-CONFIG_NLS=y
+CONFIG_NFS_FS=y
+CONFIG_NFS_V4=y
+CONFIG_ROOT_NFS=y
+CONFIG_NFSD=m
+CONFIG_NLS_ISO8859_1=y
 CONFIG_NLS_UTF8=m
 CONFIG_CRC_T10DIF=y
-CONFIG_CRC_ITU_T=m
 CONFIG_FRAME_WARN=1024
+CONFIG_MAGIC_SYSRQ=y
 CONFIG_DEBUG_FS=y
+CONFIG_DEBUG_SHIRQ=y
 CONFIG_DETECT_HUNG_TASK=y
 CONFIG_DEBUG_INFO=y
-CONFIG_SYSCTL_SYSCALL_CHECK=y
-CONFIG_IRQ_DOMAIN_DEBUG=y
+CONFIG_CRYPTO_NULL=y
 CONFIG_CRYPTO_PCBC=m
+CONFIG_CRYPTO_MD4=y
 CONFIG_CRYPTO_SHA256=y
 CONFIG_CRYPTO_SHA512=y
 CONFIG_CRYPTO_AES=y
diff --git a/arch/powerpc/configs/mgcoge_defconfig b/arch/powerpc/configs/mgcoge_defconfig
index 0d36b0e1e268..8fa84f156ef3 100644
--- a/arch/powerpc/configs/mgcoge_defconfig
+++ b/arch/powerpc/configs/mgcoge_defconfig
@@ -2,7 +2,6 @@ CONFIG_EXPERIMENTAL=y
 # CONFIG_SWAP is not set
 CONFIG_SYSVIPC=y
 CONFIG_POSIX_MQUEUE=y
-CONFIG_SPARSE_IRQ=y
 CONFIG_IKCONFIG=y
 CONFIG_IKCONFIG_PROC=y
 CONFIG_LOG_BUF_SHIFT=14
@@ -12,6 +11,7 @@ CONFIG_KALLSYMS_ALL=y
 # CONFIG_PCSPKR_PLATFORM is not set
 CONFIG_EMBEDDED=y
 CONFIG_SLAB=y
+CONFIG_PARTITION_ADVANCED=y
 # CONFIG_IOSCHED_CFQ is not set
 # CONFIG_PPC_PMAC is not set
 CONFIG_PPC_82xx=y
@@ -49,12 +49,9 @@ CONFIG_PROC_DEVICETREE=y
 CONFIG_BLK_DEV_LOOP=y
 CONFIG_BLK_DEV_RAM=y
 CONFIG_NETDEVICES=y
-CONFIG_FIXED_PHY=y
-CONFIG_NET_ETHERNET=y
 CONFIG_FS_ENET=y
 CONFIG_FS_ENET_MDIO_FCC=y
-# CONFIG_NETDEV_1000 is not set
-# CONFIG_NETDEV_10000 is not set
+CONFIG_FIXED_PHY=y
 # CONFIG_WLAN is not set
 # CONFIG_INPUT is not set
 # CONFIG_SERIO is not set
@@ -64,6 +61,8 @@ CONFIG_SERIAL_CPM_CONSOLE=y
 CONFIG_I2C=y
 CONFIG_I2C_CHARDEV=y
 CONFIG_I2C_CPM=y
+CONFIG_SPI=y
+CONFIG_SPI_FSL_SPI=y
 # CONFIG_HWMON is not set
 CONFIG_USB_GADGET=y
 CONFIG_USB_FSL_USB2=y
@@ -80,8 +79,6 @@ CONFIG_SQUASHFS=y
 CONFIG_NFS_FS=y
 CONFIG_NFS_V3=y
 CONFIG_ROOT_NFS=y
-CONFIG_PARTITION_ADVANCED=y
-CONFIG_NLS=y
 CONFIG_NLS_CODEPAGE_437=y
 CONFIG_NLS_ASCII=y
 CONFIG_NLS_ISO8859_1=y
@@ -90,7 +87,6 @@ CONFIG_MAGIC_SYSRQ=y
 CONFIG_DEBUG_FS=y
 # CONFIG_SCHED_DEBUG is not set
 CONFIG_DEBUG_INFO=y
-CONFIG_SYSCTL_SYSCALL_CHECK=y
 CONFIG_BDI_SWITCH=y
 CONFIG_CRYPTO_ECB=y
 CONFIG_CRYPTO_PCBC=y
diff --git a/arch/powerpc/configs/mpc85xx_defconfig b/arch/powerpc/configs/mpc85xx_defconfig
index 62bb723c5b54..03ee911c4577 100644
--- a/arch/powerpc/configs/mpc85xx_defconfig
+++ b/arch/powerpc/configs/mpc85xx_defconfig
@@ -74,6 +74,30 @@ CONFIG_INET_ESP=y
 CONFIG_IPV6=y
 CONFIG_IP_SCTP=m
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
+CONFIG_MTD=y
+CONFIG_MTD_CMDLINE_PARTS=y
+CONFIG_MTD_CHAR=y
+CONFIG_MTD_BLOCK=y
+CONFIG_MTD_CFI=y
+CONFIG_FTL=y
+CONFIG_MTD_GEN_PROBE=y
+CONFIG_MTD_MAP_BANK_WIDTH_1=y
+CONFIG_MTD_MAP_BANK_WIDTH_2=y
+CONFIG_MTD_MAP_BANK_WIDTH_4=y
+CONFIG_MTD_CFI_I1=y
+CONFIG_MTD_CFI_I2=y
+CONFIG_MTD_CFI_INTELEXT=y
+CONFIG_MTD_CFI_AMDSTD=y
+CONFIG_MTD_CFI_UTIL=y
+CONFIG_MTD_PHYSMAP_OF=y
+CONFIG_MTD_PARTITIONS=y
+CONFIG_MTD_OF_PARTS=y
+CONFIG_MTD_NAND=y
+CONFIG_MTD_NAND_FSL_ELBC=y
+CONFIG_MTD_NAND_FSL_IFC=y
+CONFIG_MTD_NAND_IDS=y
+CONFIG_MTD_NAND_ECC=y
+CONFIG_MTD_M25P80=y
 CONFIG_PROC_DEVICETREE=y
 CONFIG_BLK_DEV_LOOP=y
 CONFIG_BLK_DEV_NBD=y
diff --git a/arch/powerpc/configs/mpc85xx_smp_defconfig b/arch/powerpc/configs/mpc85xx_smp_defconfig
index d1828427ae55..fdfa84dc908f 100644
--- a/arch/powerpc/configs/mpc85xx_smp_defconfig
+++ b/arch/powerpc/configs/mpc85xx_smp_defconfig
@@ -46,6 +46,7 @@ CONFIG_NO_HZ=y
 CONFIG_HIGH_RES_TIMERS=y
 CONFIG_BINFMT_MISC=m
 CONFIG_MATH_EMULATION=y
+CONFIG_IRQ_ALL_CPUS=y
 CONFIG_FORCE_MAX_ZONEORDER=12
 CONFIG_PCI=y
 CONFIG_PCI_MSI=y
@@ -76,6 +77,30 @@ CONFIG_INET_ESP=y
 CONFIG_IPV6=y
 CONFIG_IP_SCTP=m
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
+CONFIG_MTD=y
+CONFIG_MTD_CMDLINE_PARTS=y
+CONFIG_MTD_CHAR=y
+CONFIG_MTD_BLOCK=y
+CONFIG_MTD_CFI=y
+CONFIG_FTL=y
+CONFIG_MTD_GEN_PROBE=y
+CONFIG_MTD_MAP_BANK_WIDTH_1=y
+CONFIG_MTD_MAP_BANK_WIDTH_2=y
+CONFIG_MTD_MAP_BANK_WIDTH_4=y
+CONFIG_MTD_CFI_I1=y
+CONFIG_MTD_CFI_I2=y
+CONFIG_MTD_CFI_INTELEXT=y
+CONFIG_MTD_CFI_AMDSTD=y
+CONFIG_MTD_CFI_UTIL=y
+CONFIG_MTD_PHYSMAP_OF=y
+CONFIG_MTD_PARTITIONS=y
+CONFIG_MTD_OF_PARTS=y
+CONFIG_MTD_NAND=y
+CONFIG_MTD_NAND_FSL_ELBC=y
+CONFIG_MTD_NAND_FSL_IFC=y
+CONFIG_MTD_NAND_IDS=y
+CONFIG_MTD_NAND_ECC=y
+CONFIG_MTD_M25P80=y
 CONFIG_PROC_DEVICETREE=y
 CONFIG_BLK_DEV_LOOP=y
 CONFIG_BLK_DEV_NBD=y
diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig
index c1442a3758ae..f2fe0c2b41e4 100644
--- a/arch/powerpc/configs/ppc64_defconfig
+++ b/arch/powerpc/configs/ppc64_defconfig
@@ -16,6 +16,7 @@ CONFIG_BLK_DEV_INITRD=y
 CONFIG_PROFILING=y
 CONFIG_OPROFILE=y
 CONFIG_KPROBES=y
+CONFIG_JUMP_LABEL=y
 CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
 CONFIG_MODVERSIONS=y
@@ -489,3 +490,4 @@ CONFIG_VIRTUALIZATION=y
 CONFIG_KVM_BOOK3S_64=m
 CONFIG_KVM_BOOK3S_64_HV=y
 CONFIG_VHOST_NET=m
+CONFIG_BPF_JIT=y
diff --git a/arch/powerpc/configs/pseries_defconfig b/arch/powerpc/configs/pseries_defconfig
index 6608232663cb..187fb8d53605 100644
--- a/arch/powerpc/configs/pseries_defconfig
+++ b/arch/powerpc/configs/pseries_defconfig
@@ -24,6 +24,7 @@ CONFIG_BLK_DEV_INITRD=y
 CONFIG_PROFILING=y
 CONFIG_OPROFILE=y
 CONFIG_KPROBES=y
+CONFIG_JUMP_LABEL=y
 CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
 CONFIG_MODVERSIONS=y
diff --git a/arch/powerpc/include/asm/asm-compat.h b/arch/powerpc/include/asm/asm-compat.h
index 5d7fbe1950f9..6e82f5f9a6fd 100644
--- a/arch/powerpc/include/asm/asm-compat.h
+++ b/arch/powerpc/include/asm/asm-compat.h
@@ -29,7 +29,7 @@
 #define PPC_LLARX(t, a, b, eh)	PPC_LDARX(t, a, b, eh)
 #define PPC_STLCX	stringify_in_c(stdcx.)
 #define PPC_CNTLZL	stringify_in_c(cntlzd)
-#define PPC_MTOCRF(FXM, RS) MTOCRF((FXM), (RS))
+#define PPC_MTOCRF(FXM, RS) MTOCRF((FXM), RS)
 #define PPC_LR_STKOFF	16
 #define PPC_MIN_STKFRM	112
 #else /* 32-bit */
diff --git a/arch/powerpc/include/asm/code-patching.h b/arch/powerpc/include/asm/code-patching.h
index 37c32aba79b7..a6f8c7a5cbb7 100644
--- a/arch/powerpc/include/asm/code-patching.h
+++ b/arch/powerpc/include/asm/code-patching.h
@@ -26,8 +26,8 @@ unsigned int create_branch(const unsigned int *addr,
 			   unsigned long target, int flags);
 unsigned int create_cond_branch(const unsigned int *addr,
 				unsigned long target, int flags);
-void patch_branch(unsigned int *addr, unsigned long target, int flags);
-void patch_instruction(unsigned int *addr, unsigned int instr);
+int patch_branch(unsigned int *addr, unsigned long target, int flags);
+int patch_instruction(unsigned int *addr, unsigned int instr);
 
 int instr_is_relative_branch(unsigned int instr);
 int instr_is_branch_to_addr(const unsigned int *instr, unsigned long addr);
diff --git a/arch/powerpc/include/asm/device.h b/arch/powerpc/include/asm/device.h
index 63d5ca49cece..77e97dd0c15d 100644
--- a/arch/powerpc/include/asm/device.h
+++ b/arch/powerpc/include/asm/device.h
@@ -34,6 +34,9 @@ struct dev_archdata {
 #ifdef CONFIG_EEH
 	struct eeh_dev		*edev;
 #endif
+#ifdef CONFIG_FAIL_IOMMU
+	int fail_iommu;
+#endif
 };
 
 struct pdev_archdata {
diff --git a/arch/powerpc/include/asm/epapr_hcalls.h b/arch/powerpc/include/asm/epapr_hcalls.h
index 976835d8f22e..bf2c06c33871 100644
--- a/arch/powerpc/include/asm/epapr_hcalls.h
+++ b/arch/powerpc/include/asm/epapr_hcalls.h
@@ -153,6 +153,8 @@
 #define EV_HCALL_CLOBBERS2 EV_HCALL_CLOBBERS3, "r5"
 #define EV_HCALL_CLOBBERS1 EV_HCALL_CLOBBERS2, "r4"
 
+extern bool epapr_paravirt_enabled;
+extern u32 epapr_hypercall_start[];
 
 /*
  * We use "uintptr_t" to define a register because it's guaranteed to be a
diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h
index d58fc4e4149c..a43c1473915f 100644
--- a/arch/powerpc/include/asm/exception-64s.h
+++ b/arch/powerpc/include/asm/exception-64s.h
@@ -293,7 +293,7 @@ label##_hv:								\
 
 #define RUNLATCH_ON				\
 BEGIN_FTR_SECTION				\
-	clrrdi	r3,r1,THREAD_SHIFT;		\
+	CURRENT_THREAD_INFO(r3, r1);		\
 	ld	r4,TI_LOCAL_FLAGS(r3);		\
 	andi.	r0,r4,_TLF_RUNLATCH;		\
 	beql	ppc64_runlatch_on_trampoline;	\
@@ -332,7 +332,7 @@ label##_common:							\
 #ifdef CONFIG_PPC_970_NAP
 #define FINISH_NAP				\
 BEGIN_FTR_SECTION				\
-	clrrdi	r11,r1,THREAD_SHIFT;		\
+	CURRENT_THREAD_INFO(r11, r1);		\
 	ld	r9,TI_LOCAL_FLAGS(r11);		\
 	andi.	r10,r9,_TLF_NAPPING;		\
 	bnel	power4_fixup_nap;		\
diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h
index 6eb75b80488c..e45c4947a772 100644
--- a/arch/powerpc/include/asm/hw_irq.h
+++ b/arch/powerpc/include/asm/hw_irq.h
@@ -34,6 +34,8 @@ extern void __replay_interrupt(unsigned int vector);
 
 extern void timer_interrupt(struct pt_regs *);
 extern void performance_monitor_exception(struct pt_regs *regs);
+extern void WatchdogException(struct pt_regs *regs);
+extern void unknown_exception(struct pt_regs *regs);
 
 #ifdef CONFIG_PPC64
 #include <asm/paca.h>
@@ -86,8 +88,8 @@ static inline bool arch_irqs_disabled(void)
 }
 
 #ifdef CONFIG_PPC_BOOK3E
-#define __hard_irq_enable()	asm volatile("wrteei 1" : : : "memory");
-#define __hard_irq_disable()	asm volatile("wrteei 0" : : : "memory");
+#define __hard_irq_enable()	asm volatile("wrteei 1" : : : "memory")
+#define __hard_irq_disable()	asm volatile("wrteei 0" : : : "memory")
 #else
 #define __hard_irq_enable()	__mtmsrd(local_paca->kernel_msr | MSR_EE, 1)
 #define __hard_irq_disable()	__mtmsrd(local_paca->kernel_msr, 1)
@@ -125,6 +127,8 @@ static inline bool arch_irq_disabled_regs(struct pt_regs *regs)
 	return !regs->softe;
 }
 
+extern bool prep_irq_for_idle(void);
+
 #else /* CONFIG_PPC64 */
 
 #define SET_MSR_EE(x)	mtmsr(x)
diff --git a/arch/powerpc/include/asm/immap_qe.h b/arch/powerpc/include/asm/immap_qe.h
index 0edb6842b13d..61e8490786b8 100644
--- a/arch/powerpc/include/asm/immap_qe.h
+++ b/arch/powerpc/include/asm/immap_qe.h
@@ -26,7 +26,9 @@
 struct qe_iram {
 	__be32	iadd;		/* I-RAM Address Register */
 	__be32	idata;		/* I-RAM Data Register */
-	u8	res0[0x78];
+	u8	res0[0x04];
+	__be32	iready;		/* I-RAM Ready Register */
+	u8	res1[0x70];
 } __attribute__ ((packed));
 
 /* QE Interrupt Controller */
diff --git a/arch/powerpc/include/asm/io.h b/arch/powerpc/include/asm/io.h
index a3855b81eada..f94ef4213e9d 100644
--- a/arch/powerpc/include/asm/io.h
+++ b/arch/powerpc/include/asm/io.h
@@ -20,6 +20,14 @@ extern int check_legacy_ioport(unsigned long base_port);
 #define _PNPWRP		0xa79
 #define PNPBIOS_BASE	0xf000
 
+#if defined(CONFIG_PPC64) && defined(CONFIG_PCI)
+extern struct pci_dev *isa_bridge_pcidev;
+/*
+ * has legacy ISA devices ?
+ */
+#define arch_has_dev_port()	(isa_bridge_pcidev != NULL)
+#endif
+
 #include <linux/device.h>
 #include <linux/io.h>
 
diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h
index 957a83f43646..cbfe678e3dbe 100644
--- a/arch/powerpc/include/asm/iommu.h
+++ b/arch/powerpc/include/asm/iommu.h
@@ -53,6 +53,16 @@ static __inline__ __attribute_const__ int get_iommu_order(unsigned long size)
  */
 #define IOMAP_MAX_ORDER		13
 
+#define IOMMU_POOL_HASHBITS	2
+#define IOMMU_NR_POOLS		(1 << IOMMU_POOL_HASHBITS)
+
+struct iommu_pool {
+	unsigned long start;
+	unsigned long end;
+	unsigned long hint;
+	spinlock_t lock;
+} ____cacheline_aligned_in_smp;
+
 struct iommu_table {
 	unsigned long  it_busno;     /* Bus number this table belongs to */
 	unsigned long  it_size;      /* Size of iommu table in entries */
@@ -61,10 +71,10 @@ struct iommu_table {
 	unsigned long  it_index;     /* which iommu table this is */
 	unsigned long  it_type;      /* type: PCI or Virtual Bus */
 	unsigned long  it_blocksize; /* Entries in each block (cacheline) */
-	unsigned long  it_hint;      /* Hint for next alloc */
-	unsigned long  it_largehint; /* Hint for large allocs */
-	unsigned long  it_halfpoint; /* Breaking point for small/large allocs */
-	spinlock_t     it_lock;      /* Protects it_map */
+	unsigned long  poolsize;
+	unsigned long  nr_pools;
+	struct iommu_pool large_pool;
+	struct iommu_pool pools[IOMMU_NR_POOLS];
 	unsigned long *it_map;       /* A simple allocation bitmap for now */
 };
 
diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h
index b0c08b142770..0dd1d86d3e31 100644
--- a/arch/powerpc/include/asm/kvm_book3s_64.h
+++ b/arch/powerpc/include/asm/kvm_book3s_64.h
@@ -36,11 +36,8 @@ static inline void svcpu_put(struct kvmppc_book3s_shadow_vcpu *svcpu)
 #define SPAPR_TCE_SHIFT		12
 
 #ifdef CONFIG_KVM_BOOK3S_64_HV
-/* For now use fixed-size 16MB page table */
-#define HPT_ORDER	24
-#define HPT_NPTEG	(1ul << (HPT_ORDER - 7))	/* 128B per pteg */
-#define HPT_NPTE	(HPT_NPTEG << 3)		/* 8 PTEs per PTEG */
-#define HPT_HASH_MASK	(HPT_NPTEG - 1)
+#define KVM_DEFAULT_HPT_ORDER	24	/* 16MB HPT by default */
+extern int kvm_hpt_order;		/* order of preallocated HPTs */
 #endif
 
 #define VRMA_VSID	0x1ffffffUL	/* 1TB VSID reserved for VRMA */
diff --git a/arch/powerpc/include/asm/kvm_book3s_asm.h b/arch/powerpc/include/asm/kvm_book3s_asm.h
index 88609b23b775..bfcd00c1485d 100644
--- a/arch/powerpc/include/asm/kvm_book3s_asm.h
+++ b/arch/powerpc/include/asm/kvm_book3s_asm.h
@@ -74,6 +74,7 @@ struct kvmppc_host_state {
 	ulong vmhandler;
 	ulong scratch0;
 	ulong scratch1;
+	ulong sprg3;
 	u8 in_guest;
 	u8 restore_hid5;
 	u8 napping;
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index d848cdc49715..50ea12fd7bf5 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -237,6 +237,10 @@ struct kvm_arch {
 	unsigned long vrma_slb_v;
 	int rma_setup_done;
 	int using_mmu_notifiers;
+	u32 hpt_order;
+	atomic_t vcpus_running;
+	unsigned long hpt_npte;
+	unsigned long hpt_mask;
 	spinlock_t slot_phys_lock;
 	unsigned long *slot_phys[KVM_MEM_SLOTS_NUM];
 	int slot_npages[KVM_MEM_SLOTS_NUM];
@@ -414,7 +418,9 @@ struct kvm_vcpu_arch {
 	ulong mcsrr1;
 	ulong mcsr;
 	u32 dec;
+#ifdef CONFIG_BOOKE
 	u32 decar;
+#endif
 	u32 tbl;
 	u32 tbu;
 	u32 tcr;
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index f68c22fa2fce..0124937a23b9 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -119,7 +119,8 @@ extern void kvmppc_core_destroy_mmu(struct kvm_vcpu *vcpu);
 extern int kvmppc_kvm_pv(struct kvm_vcpu *vcpu);
 extern void kvmppc_map_magic(struct kvm_vcpu *vcpu);
 
-extern long kvmppc_alloc_hpt(struct kvm *kvm);
+extern long kvmppc_alloc_hpt(struct kvm *kvm, u32 *htab_orderp);
+extern long kvmppc_alloc_reset_hpt(struct kvm *kvm, u32 *htab_orderp);
 extern void kvmppc_free_hpt(struct kvm *kvm);
 extern long kvmppc_prepare_vrma(struct kvm *kvm,
 				struct kvm_userspace_memory_region *mem);
diff --git a/arch/powerpc/include/asm/mmu.h b/arch/powerpc/include/asm/mmu.h
index f0145522cfba..e8a26db2e8f3 100644
--- a/arch/powerpc/include/asm/mmu.h
+++ b/arch/powerpc/include/asm/mmu.h
@@ -163,12 +163,7 @@ extern u64 ppc64_rma_size;
  * to think about, feedback welcome. --BenH.
  */
 
-/* There are #define as they have to be used in assembly
- *
- * WARNING: If you change this list, make sure to update the array of
- * names currently in arch/powerpc/mm/hugetlbpage.c or bad things will
- * happen
- */
+/* These are #defines as they have to be used in assembly */
 #define MMU_PAGE_4K	0
 #define MMU_PAGE_16K	1
 #define MMU_PAGE_64K	2
diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h
index ac39e6a3b25a..8cccbee61519 100644
--- a/arch/powerpc/include/asm/pci-bridge.h
+++ b/arch/powerpc/include/asm/pci-bridge.h
@@ -30,6 +30,7 @@ struct pci_controller {
 	int first_busno;
 	int last_busno;
 	int self_busno;
+	struct resource busn;
 
 	void __iomem *io_base_virt;
 #ifdef CONFIG_PPC64
diff --git a/arch/powerpc/include/asm/perf_event.h b/arch/powerpc/include/asm/perf_event.h
index 5c16b891d501..0bb23725b1e7 100644
--- a/arch/powerpc/include/asm/perf_event.h
+++ b/arch/powerpc/include/asm/perf_event.h
@@ -26,8 +26,13 @@
 #include <asm/ptrace.h>
 #include <asm/reg.h>
 
+/*
+ * Overload regs->result to specify whether we should use the MSR (result
+ * is zero) or the SIAR (result is non zero).
+ */
 #define perf_arch_fetch_caller_regs(regs, __ip)			\
 	do {							\
+		(regs)->result = 0;				\
 		(regs)->nip = __ip;				\
 		(regs)->gpr[1] = *(unsigned long *)__get_SP();	\
 		asm volatile("mfmsr %0" : "=r" ((regs)->msr));	\
diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h
index d81f99430fe7..4c25319f2fbc 100644
--- a/arch/powerpc/include/asm/ppc-opcode.h
+++ b/arch/powerpc/include/asm/ppc-opcode.h
@@ -15,6 +15,72 @@
 #include <linux/stringify.h>
 #include <asm/asm-compat.h>
 
+#define	__REG_R0	0
+#define	__REG_R1	1
+#define	__REG_R2	2
+#define	__REG_R3	3
+#define	__REG_R4	4
+#define	__REG_R5	5
+#define	__REG_R6	6
+#define	__REG_R7	7
+#define	__REG_R8	8
+#define	__REG_R9	9
+#define	__REG_R10	10
+#define	__REG_R11	11
+#define	__REG_R12	12
+#define	__REG_R13	13
+#define	__REG_R14	14
+#define	__REG_R15	15
+#define	__REG_R16	16
+#define	__REG_R17	17
+#define	__REG_R18	18
+#define	__REG_R19	19
+#define	__REG_R20	20
+#define	__REG_R21	21
+#define	__REG_R22	22
+#define	__REG_R23	23
+#define	__REG_R24	24
+#define	__REG_R25	25
+#define	__REG_R26	26
+#define	__REG_R27	27
+#define	__REG_R28	28
+#define	__REG_R29	29
+#define	__REG_R30	30
+#define	__REG_R31	31
+
+#define	__REGA0_0	0
+#define	__REGA0_R1	1
+#define	__REGA0_R2	2
+#define	__REGA0_R3	3
+#define	__REGA0_R4	4
+#define	__REGA0_R5	5
+#define	__REGA0_R6	6
+#define	__REGA0_R7	7
+#define	__REGA0_R8	8
+#define	__REGA0_R9	9
+#define	__REGA0_R10	10
+#define	__REGA0_R11	11
+#define	__REGA0_R12	12
+#define	__REGA0_R13	13
+#define	__REGA0_R14	14
+#define	__REGA0_R15	15
+#define	__REGA0_R16	16
+#define	__REGA0_R17	17
+#define	__REGA0_R18	18
+#define	__REGA0_R19	19
+#define	__REGA0_R20	20
+#define	__REGA0_R21	21
+#define	__REGA0_R22	22
+#define	__REGA0_R23	23
+#define	__REGA0_R24	24
+#define	__REGA0_R25	25
+#define	__REGA0_R26	26
+#define	__REGA0_R27	27
+#define	__REGA0_R28	28
+#define	__REGA0_R29	29
+#define	__REGA0_R30	30
+#define	__REGA0_R31	31
+
 /* sorted alphabetically */
 #define PPC_INST_DCBA			0x7c0005ec
 #define PPC_INST_DCBA_MASK		0xfc0007fe
@@ -107,12 +173,19 @@
 #define PPC_INST_NEG			0x7c0000d0
 #define PPC_INST_BRANCH			0x48000000
 #define PPC_INST_BRANCH_COND		0x40800000
+#define PPC_INST_LBZCIX			0x7c0006aa
+#define PPC_INST_STBCIX			0x7c0007aa
 
 /* macros to insert fields into opcodes */
-#define __PPC_RA(a)	(((a) & 0x1f) << 16)
-#define __PPC_RB(b)	(((b) & 0x1f) << 11)
-#define __PPC_RS(s)	(((s) & 0x1f) << 21)
-#define __PPC_RT(s)	__PPC_RS(s)
+#define ___PPC_RA(a)	(((a) & 0x1f) << 16)
+#define ___PPC_RB(b)	(((b) & 0x1f) << 11)
+#define ___PPC_RS(s)	(((s) & 0x1f) << 21)
+#define ___PPC_RT(t)	___PPC_RS(t)
+#define __PPC_RA(a)	___PPC_RA(__REG_##a)
+#define __PPC_RA0(a)	___PPC_RA(__REGA0_##a)
+#define __PPC_RB(b)	___PPC_RB(__REG_##b)
+#define __PPC_RS(s)	___PPC_RS(__REG_##s)
+#define __PPC_RT(t)	___PPC_RT(__REG_##t)
 #define __PPC_XA(a)	((((a) & 0x1f) << 16) | (((a) & 0x20) >> 3))
 #define __PPC_XB(b)	((((b) & 0x1f) << 11) | (((b) & 0x20) >> 4))
 #define __PPC_XS(s)	((((s) & 0x1f) << 21) | (((s) & 0x20) >> 5))
@@ -141,13 +214,13 @@
 #define	PPC_DCBZL(a, b)		stringify_in_c(.long PPC_INST_DCBZL | \
 					__PPC_RA(a) | __PPC_RB(b))
 #define PPC_LDARX(t, a, b, eh)	stringify_in_c(.long PPC_INST_LDARX | \
-					__PPC_RT(t) | __PPC_RA(a) | \
-					__PPC_RB(b) | __PPC_EH(eh))
+					___PPC_RT(t) | ___PPC_RA(a) | \
+					___PPC_RB(b) | __PPC_EH(eh))
 #define PPC_LWARX(t, a, b, eh)	stringify_in_c(.long PPC_INST_LWARX | \
-					__PPC_RT(t) | __PPC_RA(a) | \
-					__PPC_RB(b) | __PPC_EH(eh))
+					___PPC_RT(t) | ___PPC_RA(a) | \
+					___PPC_RB(b) | __PPC_EH(eh))
 #define PPC_MSGSND(b)		stringify_in_c(.long PPC_INST_MSGSND | \
-					__PPC_RB(b))
+					___PPC_RB(b))
 #define PPC_POPCNTB(a, s)	stringify_in_c(.long PPC_INST_POPCNTB | \
 					__PPC_RA(a) | __PPC_RS(s))
 #define PPC_POPCNTD(a, s)	stringify_in_c(.long PPC_INST_POPCNTD | \
@@ -158,34 +231,39 @@
 #define PPC_RFDI		stringify_in_c(.long PPC_INST_RFDI)
 #define PPC_RFMCI		stringify_in_c(.long PPC_INST_RFMCI)
 #define PPC_TLBILX(t, a, b)	stringify_in_c(.long PPC_INST_TLBILX | \
-					__PPC_T_TLB(t) | __PPC_RA(a) | __PPC_RB(b))
+					__PPC_T_TLB(t) | __PPC_RA0(a) | __PPC_RB(b))
 #define PPC_TLBILX_ALL(a, b)	PPC_TLBILX(0, a, b)
 #define PPC_TLBILX_PID(a, b)	PPC_TLBILX(1, a, b)
 #define PPC_TLBILX_VA(a, b)	PPC_TLBILX(3, a, b)
 #define PPC_WAIT(w)		stringify_in_c(.long PPC_INST_WAIT | \
 					__PPC_WC(w))
 #define PPC_TLBIE(lp,a) 	stringify_in_c(.long PPC_INST_TLBIE | \
-					       __PPC_RB(a) | __PPC_RS(lp))
+					       ___PPC_RB(a) | ___PPC_RS(lp))
 #define PPC_TLBSRX_DOT(a,b)	stringify_in_c(.long PPC_INST_TLBSRX_DOT | \
-					__PPC_RA(a) | __PPC_RB(b))
+					__PPC_RA0(a) | __PPC_RB(b))
 #define PPC_TLBIVAX(a,b)	stringify_in_c(.long PPC_INST_TLBIVAX | \
-					__PPC_RA(a) | __PPC_RB(b))
+					__PPC_RA0(a) | __PPC_RB(b))
 
 #define PPC_ERATWE(s, a, w)	stringify_in_c(.long PPC_INST_ERATWE | \
 					__PPC_RS(s) | __PPC_RA(a) | __PPC_WS(w))
 #define PPC_ERATRE(s, a, w)	stringify_in_c(.long PPC_INST_ERATRE | \
 					__PPC_RS(s) | __PPC_RA(a) | __PPC_WS(w))
 #define PPC_ERATILX(t, a, b)	stringify_in_c(.long PPC_INST_ERATILX | \
-					__PPC_T_TLB(t) | __PPC_RA(a) | \
+					__PPC_T_TLB(t) | __PPC_RA0(a) | \
 					__PPC_RB(b))
 #define PPC_ERATIVAX(s, a, b)	stringify_in_c(.long PPC_INST_ERATIVAX | \
-					__PPC_RS(s) | __PPC_RA(a) | __PPC_RB(b))
+					__PPC_RS(s) | __PPC_RA0(a) | __PPC_RB(b))
 #define PPC_ERATSX(t, a, w)	stringify_in_c(.long PPC_INST_ERATSX | \
-					__PPC_RS(t) | __PPC_RA(a) | __PPC_RB(b))
+					__PPC_RS(t) | __PPC_RA0(a) | __PPC_RB(b))
 #define PPC_ERATSX_DOT(t, a, w)	stringify_in_c(.long PPC_INST_ERATSX_DOT | \
-					__PPC_RS(t) | __PPC_RA(a) | __PPC_RB(b))
+					__PPC_RS(t) | __PPC_RA0(a) | __PPC_RB(b))
 #define PPC_SLBFEE_DOT(t, b)	stringify_in_c(.long PPC_INST_SLBFEE | \
 					__PPC_RT(t) | __PPC_RB(b))
+/* PASemi instructions */
+#define LBZCIX(t,a,b)		stringify_in_c(.long PPC_INST_LBZCIX | \
+				       __PPC_RT(t) | __PPC_RA(a) | __PPC_RB(b))
+#define STBCIX(s,a,b)		stringify_in_c(.long PPC_INST_STBCIX | \
+				       __PPC_RS(s) | __PPC_RA(a) | __PPC_RB(b))
 
 /*
  * Define what the VSX XX1 form instructions will look like, then add
@@ -194,11 +272,11 @@
 #define VSX_XX1(s, a, b)	(__PPC_XS(s) | __PPC_RA(a) | __PPC_RB(b))
 #define VSX_XX3(t, a, b)	(__PPC_XT(t) | __PPC_XA(a) | __PPC_XB(b))
 #define STXVD2X(s, a, b)	stringify_in_c(.long PPC_INST_STXVD2X | \
-					       VSX_XX1((s), (a), (b)))
+					       VSX_XX1((s), a, b))
 #define LXVD2X(s, a, b)		stringify_in_c(.long PPC_INST_LXVD2X | \
-					       VSX_XX1((s), (a), (b)))
+					       VSX_XX1((s), a, b))
 #define XXLOR(t, a, b)		stringify_in_c(.long PPC_INST_XXLOR | \
-					       VSX_XX3((t), (a), (b)))
+					       VSX_XX3((t), a, b))
 
 #define PPC_NAP			stringify_in_c(.long PPC_INST_NAP)
 #define PPC_SLEEP		stringify_in_c(.long PPC_INST_SLEEP)
diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h
index 15444204a3a1..ea2a86e8ff95 100644
--- a/arch/powerpc/include/asm/ppc_asm.h
+++ b/arch/powerpc/include/asm/ppc_asm.h
@@ -126,26 +126,26 @@ END_FW_FTR_SECTION_IFSET(FW_FEATURE_SPLPAR)
 #define REST_32VRS(n,b,base)	REST_16VRS(n,b,base); REST_16VRS(n+16,b,base)
 
 /* Save the lower 32 VSRs in the thread VSR region */
-#define SAVE_VSR(n,b,base)	li b,THREAD_VSR0+(16*(n));  STXVD2X(n,base,b)
+#define SAVE_VSR(n,b,base)	li b,THREAD_VSR0+(16*(n));  STXVD2X(n,R##base,R##b)
 #define SAVE_2VSRS(n,b,base)	SAVE_VSR(n,b,base); SAVE_VSR(n+1,b,base)
 #define SAVE_4VSRS(n,b,base)	SAVE_2VSRS(n,b,base); SAVE_2VSRS(n+2,b,base)
 #define SAVE_8VSRS(n,b,base)	SAVE_4VSRS(n,b,base); SAVE_4VSRS(n+4,b,base)
 #define SAVE_16VSRS(n,b,base)	SAVE_8VSRS(n,b,base); SAVE_8VSRS(n+8,b,base)
 #define SAVE_32VSRS(n,b,base)	SAVE_16VSRS(n,b,base); SAVE_16VSRS(n+16,b,base)
-#define REST_VSR(n,b,base)	li b,THREAD_VSR0+(16*(n)); LXVD2X(n,base,b)
+#define REST_VSR(n,b,base)	li b,THREAD_VSR0+(16*(n)); LXVD2X(n,R##base,R##b)
 #define REST_2VSRS(n,b,base)	REST_VSR(n,b,base); REST_VSR(n+1,b,base)
 #define REST_4VSRS(n,b,base)	REST_2VSRS(n,b,base); REST_2VSRS(n+2,b,base)
 #define REST_8VSRS(n,b,base)	REST_4VSRS(n,b,base); REST_4VSRS(n+4,b,base)
 #define REST_16VSRS(n,b,base)	REST_8VSRS(n,b,base); REST_8VSRS(n+8,b,base)
 #define REST_32VSRS(n,b,base)	REST_16VSRS(n,b,base); REST_16VSRS(n+16,b,base)
 /* Save the upper 32 VSRs (32-63) in the thread VSX region (0-31) */
-#define SAVE_VSRU(n,b,base)	li b,THREAD_VR0+(16*(n));  STXVD2X(n+32,base,b)
+#define SAVE_VSRU(n,b,base)	li b,THREAD_VR0+(16*(n));  STXVD2X(n+32,R##base,R##b)
 #define SAVE_2VSRSU(n,b,base)	SAVE_VSRU(n,b,base); SAVE_VSRU(n+1,b,base)
 #define SAVE_4VSRSU(n,b,base)	SAVE_2VSRSU(n,b,base); SAVE_2VSRSU(n+2,b,base)
 #define SAVE_8VSRSU(n,b,base)	SAVE_4VSRSU(n,b,base); SAVE_4VSRSU(n+4,b,base)
 #define SAVE_16VSRSU(n,b,base)	SAVE_8VSRSU(n,b,base); SAVE_8VSRSU(n+8,b,base)
 #define SAVE_32VSRSU(n,b,base)	SAVE_16VSRSU(n,b,base); SAVE_16VSRSU(n+16,b,base)
-#define REST_VSRU(n,b,base)	li b,THREAD_VR0+(16*(n)); LXVD2X(n+32,base,b)
+#define REST_VSRU(n,b,base)	li b,THREAD_VR0+(16*(n)); LXVD2X(n+32,R##base,R##b)
 #define REST_2VSRSU(n,b,base)	REST_VSRU(n,b,base); REST_VSRU(n+1,b,base)
 #define REST_4VSRSU(n,b,base)	REST_2VSRSU(n,b,base); REST_2VSRSU(n+2,b,base)
 #define REST_8VSRSU(n,b,base)	REST_4VSRSU(n,b,base); REST_4VSRSU(n+4,b,base)
@@ -178,9 +178,24 @@ END_FW_FTR_SECTION_IFSET(FW_FEATURE_SPLPAR)
 #define HMT_HIGH	or	3,3,3
 #define HMT_EXTRA_HIGH	or	7,7,7		# power7 only
 
+#ifdef CONFIG_PPC64
+#define ULONG_SIZE 	8
+#else
+#define ULONG_SIZE	4
+#endif
+#define __VCPU_GPR(n)	(VCPU_GPRS + (n * ULONG_SIZE))
+#define VCPU_GPR(n)	__VCPU_GPR(__REG_##n)
+
 #ifdef __KERNEL__
 #ifdef CONFIG_PPC64
 
+#define STACKFRAMESIZE 256
+#define __STK_REG(i)   (112 + ((i)-14)*8)
+#define STK_REG(i)     __STK_REG(__REG_##i)
+
+#define __STK_PARAM(i)	(48 + ((i)-3)*8)
+#define STK_PARAM(i)	__STK_PARAM(__REG_##i)
+
 #define XGLUE(a,b) a##b
 #define GLUE(a,b) XGLUE(a,b)
 
@@ -295,14 +310,14 @@ n:
  */
 #ifdef __powerpc64__
 #define LOAD_REG_IMMEDIATE(reg,expr)		\
-	lis     (reg),(expr)@highest;		\
-	ori     (reg),(reg),(expr)@higher;	\
-	rldicr  (reg),(reg),32,31;		\
-	oris    (reg),(reg),(expr)@h;		\
-	ori     (reg),(reg),(expr)@l;
+	lis     reg,(expr)@highest;		\
+	ori     reg,reg,(expr)@higher;	\
+	rldicr  reg,reg,32,31;		\
+	oris    reg,reg,(expr)@h;		\
+	ori     reg,reg,(expr)@l;
 
 #define LOAD_REG_ADDR(reg,name)			\
-	ld	(reg),name@got(r2)
+	ld	reg,name@got(r2)
 
 #define LOAD_REG_ADDRBASE(reg,name)	LOAD_REG_ADDR(reg,name)
 #define ADDROFF(name)			0
@@ -313,12 +328,12 @@ n:
 #else /* 32-bit */
 
 #define LOAD_REG_IMMEDIATE(reg,expr)		\
-	lis	(reg),(expr)@ha;		\
-	addi	(reg),(reg),(expr)@l;
+	lis	reg,(expr)@ha;		\
+	addi	reg,reg,(expr)@l;
 
 #define LOAD_REG_ADDR(reg,name)		LOAD_REG_IMMEDIATE(reg, name)
 
-#define LOAD_REG_ADDRBASE(reg, name)	lis	(reg),name@ha
+#define LOAD_REG_ADDRBASE(reg, name)	lis	reg,name@ha
 #define ADDROFF(name)			name@l
 
 /* offsets for stack frame layout */
@@ -372,9 +387,9 @@ END_FTR_SECTION_IFCLR(CPU_FTR_601)
 #ifdef CONFIG_PPC64
 #define MTOCRF(FXM, RS)			\
 	BEGIN_FTR_SECTION_NESTED(848);	\
-	mtcrf	(FXM), (RS);		\
+	mtcrf	(FXM), RS;		\
 	FTR_SECTION_ELSE_NESTED(848);	\
-	mtocrf (FXM), (RS);		\
+	mtocrf (FXM), RS;		\
 	ALT_FTR_SECTION_END_NESTED_IFCLR(CPU_FTR_NOEXECUTE, 848)
 #endif
 
@@ -463,6 +478,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_601)
 #ifdef CONFIG_PPC_BOOK3S_64
 #define RFI		rfid
 #define MTMSRD(r)	mtmsrd	r
+#define MTMSR_EERI(reg)	mtmsrd	reg,1
 #else
 #define FIX_SRR1(ra, rb)
 #ifndef CONFIG_40x
@@ -471,6 +487,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_601)
 #define RFI		rfi; b .	/* Prevent prefetch past rfi */
 #endif
 #define MTMSRD(r)	mtmsr	r
+#define MTMSR_EERI(reg)	mtmsr	reg
 #define CLR_TOP32(r)
 #endif
 
@@ -490,40 +507,46 @@ END_FTR_SECTION_IFCLR(CPU_FTR_601)
 #define	cr7	7
 
 
-/* General Purpose Registers (GPRs) */
-
-#define	r0	0
-#define	r1	1
-#define	r2	2
-#define	r3	3
-#define	r4	4
-#define	r5	5
-#define	r6	6
-#define	r7	7
-#define	r8	8
-#define	r9	9
-#define	r10	10
-#define	r11	11
-#define	r12	12
-#define	r13	13
-#define	r14	14
-#define	r15	15
-#define	r16	16
-#define	r17	17
-#define	r18	18
-#define	r19	19
-#define	r20	20
-#define	r21	21
-#define	r22	22
-#define	r23	23
-#define	r24	24
-#define	r25	25
-#define	r26	26
-#define	r27	27
-#define	r28	28
-#define	r29	29
-#define	r30	30
-#define	r31	31
+/*
+ * General Purpose Registers (GPRs)
+ *
+ * The lower case r0-r31 should be used in preference to the upper
+ * case R0-R31 as they provide more error checking in the assembler.
+ * Use R0-31 only when really nessesary.
+ */
+
+#define	r0	%r0
+#define	r1	%r1
+#define	r2	%r2
+#define	r3	%r3
+#define	r4	%r4
+#define	r5	%r5
+#define	r6	%r6
+#define	r7	%r7
+#define	r8	%r8
+#define	r9	%r9
+#define	r10	%r10
+#define	r11	%r11
+#define	r12	%r12
+#define	r13	%r13
+#define	r14	%r14
+#define	r15	%r15
+#define	r16	%r16
+#define	r17	%r17
+#define	r18	%r18
+#define	r19	%r19
+#define	r20	%r20
+#define	r21	%r21
+#define	r22	%r22
+#define	r23	%r23
+#define	r24	%r24
+#define	r25	%r25
+#define	r26	%r26
+#define	r27	%r27
+#define	r28	%r28
+#define	r29	%r29
+#define	r30	%r30
+#define	r31	%r31
 
 
 /* Floating Point Registers (FPRs) */
diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index 413a5eaef56c..53b6dfa83344 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -389,10 +389,8 @@ extern int powersave_nap;	/* set if nap mode can be used in idle loop */
 
 #ifdef CONFIG_PSERIES_IDLE
 extern void update_smt_snooze_delay(int snooze);
-extern int pseries_notify_cpuidle_add_cpu(int cpu);
 #else
 static inline void update_smt_snooze_delay(int snooze) {}
-static inline int pseries_notify_cpuidle_add_cpu(int cpu) { return 0; }
 #endif
 
 extern void flush_instruction_cache(void);
diff --git a/arch/powerpc/include/asm/qe.h b/arch/powerpc/include/asm/qe.h
index 5e0b6d511e14..229571a49391 100644
--- a/arch/powerpc/include/asm/qe.h
+++ b/arch/powerpc/include/asm/qe.h
@@ -499,6 +499,7 @@ enum comm_dir {
 /* I-RAM */
 #define QE_IRAM_IADD_AIE	0x80000000	/* Auto Increment Enable */
 #define QE_IRAM_IADD_BADDR	0x00080000	/* Base Address */
+#define QE_IRAM_READY           0x80000000      /* Ready */
 
 /* UPC */
 #define UPGCR_PROTOCOL	0x80000000	/* protocol ul2 or pl2 */
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index f0cb7f461b9d..638608677e2a 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -491,6 +491,7 @@
 #define SPRN_SPRG1	0x111	/* Special Purpose Register General 1 */
 #define SPRN_SPRG2	0x112	/* Special Purpose Register General 2 */
 #define SPRN_SPRG3	0x113	/* Special Purpose Register General 3 */
+#define SPRN_USPRG3	0x103	/* SPRG3 userspace read */
 #define SPRN_SPRG4	0x114	/* Special Purpose Register General 4 */
 #define SPRN_SPRG5	0x115	/* Special Purpose Register General 5 */
 #define SPRN_SPRG6	0x116	/* Special Purpose Register General 6 */
@@ -753,14 +754,14 @@
  * 64-bit server:
  *	- SPRG0 unused (reserved for HV on Power4)
  *	- SPRG2 scratch for exception vectors
- *	- SPRG3 unused (user visible)
+ *	- SPRG3 CPU and NUMA node for VDSO getcpu (user visible)
  *      - HSPRG0 stores PACA in HV mode
  *      - HSPRG1 scratch for "HV" exceptions
  *
  * 64-bit embedded
  *	- SPRG0 generic exception scratch
  *	- SPRG2 TLB exception stack
- *	- SPRG3 unused (user visible)
+ *	- SPRG3 CPU and NUMA node for VDSO getcpu (user visible)
  *	- SPRG4 unused (user visible)
  *	- SPRG6 TLB miss scratch (user visible, sorry !)
  *	- SPRG7 critical exception scratch
@@ -1024,7 +1025,8 @@
 /* Macros for setting and retrieving special purpose registers */
 #ifndef __ASSEMBLY__
 #define mfmsr()		({unsigned long rval; \
-			asm volatile("mfmsr %0" : "=r" (rval)); rval;})
+			asm volatile("mfmsr %0" : "=r" (rval) : \
+						: "memory"); rval;})
 #ifdef CONFIG_PPC_BOOK3S_64
 #define __mtmsrd(v, l)	asm volatile("mtmsrd %0," __stringify(l) \
 				     : : "r" (v) : "memory")
diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h
index 68831e9cf82f..faf93529cbf0 100644
--- a/arch/powerpc/include/asm/thread_info.h
+++ b/arch/powerpc/include/asm/thread_info.h
@@ -22,6 +22,12 @@
 
 #define THREAD_SIZE		(1 << THREAD_SHIFT)
 
+#ifdef CONFIG_PPC64
+#define CURRENT_THREAD_INFO(dest, sp)	clrrdi dest, sp, THREAD_SHIFT
+#else
+#define CURRENT_THREAD_INFO(dest, sp)	rlwinm dest, sp, 0, 0, 31-THREAD_SHIFT
+#endif
+
 #ifndef __ASSEMBLY__
 #include <linux/cache.h>
 #include <asm/processor.h>
diff --git a/arch/powerpc/include/asm/trace.h b/arch/powerpc/include/asm/trace.h
index cbe2297d68b6..5712f06905a9 100644
--- a/arch/powerpc/include/asm/trace.h
+++ b/arch/powerpc/include/asm/trace.h
@@ -8,7 +8,7 @@
 
 struct pt_regs;
 
-TRACE_EVENT(irq_entry,
+DECLARE_EVENT_CLASS(ppc64_interrupt_class,
 
 	TP_PROTO(struct pt_regs *regs),
 
@@ -25,55 +25,32 @@ TRACE_EVENT(irq_entry,
 	TP_printk("pt_regs=%p", __entry->regs)
 );
 
-TRACE_EVENT(irq_exit,
+DEFINE_EVENT(ppc64_interrupt_class, irq_entry,
 
 	TP_PROTO(struct pt_regs *regs),
 
-	TP_ARGS(regs),
-
-	TP_STRUCT__entry(
-		__field(struct pt_regs *, regs)
-	),
-
-	TP_fast_assign(
-		__entry->regs = regs;
-	),
-
-	TP_printk("pt_regs=%p", __entry->regs)
+	TP_ARGS(regs)
 );
 
-TRACE_EVENT(timer_interrupt_entry,
+DEFINE_EVENT(ppc64_interrupt_class, irq_exit,
 
 	TP_PROTO(struct pt_regs *regs),
 
-	TP_ARGS(regs),
-
-	TP_STRUCT__entry(
-		__field(struct pt_regs *, regs)
-	),
-
-	TP_fast_assign(
-		__entry->regs = regs;
-	),
-
-	TP_printk("pt_regs=%p", __entry->regs)
+	TP_ARGS(regs)
 );
 
-TRACE_EVENT(timer_interrupt_exit,
+DEFINE_EVENT(ppc64_interrupt_class, timer_interrupt_entry,
 
 	TP_PROTO(struct pt_regs *regs),
 
-	TP_ARGS(regs),
+	TP_ARGS(regs)
+);
 
-	TP_STRUCT__entry(
-		__field(struct pt_regs *, regs)
-	),
+DEFINE_EVENT(ppc64_interrupt_class, timer_interrupt_exit,
 
-	TP_fast_assign(
-		__entry->regs = regs;
-	),
+	TP_PROTO(struct pt_regs *regs),
 
-	TP_printk("pt_regs=%p", __entry->regs)
+	TP_ARGS(regs)
 );
 
 #ifdef CONFIG_PPC_PSERIES
diff --git a/arch/powerpc/include/asm/vdso.h b/arch/powerpc/include/asm/vdso.h
index dc0419b66f17..50f261bc3e95 100644
--- a/arch/powerpc/include/asm/vdso.h
+++ b/arch/powerpc/include/asm/vdso.h
@@ -22,6 +22,8 @@ extern unsigned long vdso64_rt_sigtramp;
 extern unsigned long vdso32_sigtramp;
 extern unsigned long vdso32_rt_sigtramp;
 
+int __cpuinit vdso_getcpu_init(void);
+
 #else /* __ASSEMBLY__ */
 
 #ifdef __VDSO64__
diff --git a/arch/powerpc/include/asm/vio.h b/arch/powerpc/include/asm/vio.h
index b19adf751dd9..df81cb72d1e0 100644
--- a/arch/powerpc/include/asm/vio.h
+++ b/arch/powerpc/include/asm/vio.h
@@ -44,6 +44,8 @@
  */
 #define VIO_CMO_MIN_ENT 1562624
 
+extern struct bus_type vio_bus_type;
+
 struct iommu_table;
 
 /*
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index 83afacd3ba7b..bb282dd81612 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -128,6 +128,7 @@ ifneq ($(CONFIG_XMON)$(CONFIG_KEXEC),)
 obj-y				+= ppc_save_regs.o
 endif
 
+obj-$(CONFIG_EPAPR_PARAVIRT)	+= epapr_paravirt.o epapr_hcalls.o
 obj-$(CONFIG_KVM_GUEST)		+= kvm.o kvm_emul.o
 
 # Disable GCOV in odd or sensitive code
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 52c7ad78242e..85b05c463fae 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -533,6 +533,7 @@ int main(void)
 	HSTATE_FIELD(HSTATE_VMHANDLER, vmhandler);
 	HSTATE_FIELD(HSTATE_SCRATCH0, scratch0);
 	HSTATE_FIELD(HSTATE_SCRATCH1, scratch1);
+	HSTATE_FIELD(HSTATE_SPRG3, sprg3);
 	HSTATE_FIELD(HSTATE_IN_GUEST, in_guest);
 	HSTATE_FIELD(HSTATE_RESTORE_HID5, restore_hid5);
 	HSTATE_FIELD(HSTATE_NAPPING, napping);
diff --git a/arch/powerpc/kernel/cpu_setup_a2.S b/arch/powerpc/kernel/cpu_setup_a2.S
index ebc62f42a237..61f079e05b61 100644
--- a/arch/powerpc/kernel/cpu_setup_a2.S
+++ b/arch/powerpc/kernel/cpu_setup_a2.S
@@ -100,19 +100,19 @@ _icswx_skip_guest:
 	lis	r4,(MMUCR0_TLBSEL_I|MMUCR0_ECL)@h
 	mtspr	SPRN_MMUCR0, r4
 	li	r4,A2_IERAT_SIZE-1
-	PPC_ERATWE(r4,r4,3)
+	PPC_ERATWE(R4,R4,3)
 
 	/* Now set the D-ERAT watermark to 31 */
 	lis	r4,(MMUCR0_TLBSEL_D|MMUCR0_ECL)@h
 	mtspr	SPRN_MMUCR0, r4
 	li	r4,A2_DERAT_SIZE-1
-	PPC_ERATWE(r4,r4,3)
+	PPC_ERATWE(R4,R4,3)
 
 	/* And invalidate the beast just in case. That won't get rid of
 	 * a bolted entry though it will be in LRU and so will go away eventually
 	 * but let's not bother for now
 	 */
-	PPC_ERATILX(0,0,0)
+	PPC_ERATILX(0,0,R0)
 1:
 	blr
 
diff --git a/arch/powerpc/kernel/dma.c b/arch/powerpc/kernel/dma.c
index b1ec983dcec8..289be751cd75 100644
--- a/arch/powerpc/kernel/dma.c
+++ b/arch/powerpc/kernel/dma.c
@@ -11,6 +11,8 @@
 #include <linux/gfp.h>
 #include <linux/memblock.h>
 #include <linux/export.h>
+#include <linux/pci.h>
+#include <asm/vio.h>
 #include <asm/bug.h>
 #include <asm/abs_addr.h>
 #include <asm/machdep.h>
@@ -205,7 +207,13 @@ EXPORT_SYMBOL_GPL(dma_get_required_mask);
 
 static int __init dma_init(void)
 {
-       dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES);
+	dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES);
+#ifdef CONFIG_PCI
+	dma_debug_add_bus(&pci_bus_type);
+#endif
+#ifdef CONFIG_IBMVIO
+	dma_debug_add_bus(&vio_bus_type);
+#endif
 
        return 0;
 }
diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index ba3aeb4bc06a..5207d5a405e2 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -92,7 +92,7 @@ crit_transfer_to_handler:
 	mfspr	r8,SPRN_SPRG_THREAD
 	lwz	r0,KSP_LIMIT(r8)
 	stw	r0,SAVED_KSP_LIMIT(r11)
-	rlwimi	r0,r1,0,0,(31-THREAD_SHIFT)
+	CURRENT_THREAD_INFO(r0, r1)
 	stw	r0,KSP_LIMIT(r8)
 	/* fall through */
 #endif
@@ -112,7 +112,7 @@ crit_transfer_to_handler:
 	mfspr	r8,SPRN_SPRG_THREAD
 	lwz	r0,KSP_LIMIT(r8)
 	stw	r0,saved_ksp_limit@l(0)
-	rlwimi	r0,r1,0,0,(31-THREAD_SHIFT)
+	CURRENT_THREAD_INFO(r0, r1)
 	stw	r0,KSP_LIMIT(r8)
 	/* fall through */
 #endif
@@ -158,7 +158,7 @@ transfer_to_handler:
 	tophys(r11,r11)
 	addi	r11,r11,global_dbcr0@l
 #ifdef CONFIG_SMP
-	rlwinm	r9,r1,0,0,(31-THREAD_SHIFT)
+	CURRENT_THREAD_INFO(r9, r1)
 	lwz	r9,TI_CPU(r9)
 	slwi	r9,r9,3
 	add	r11,r11,r9
@@ -179,7 +179,7 @@ transfer_to_handler:
 	ble-	stack_ovf		/* then the kernel stack overflowed */
 5:
 #if defined(CONFIG_6xx) || defined(CONFIG_E500)
-	rlwinm	r9,r1,0,0,31-THREAD_SHIFT
+	CURRENT_THREAD_INFO(r9, r1)
 	tophys(r9,r9)			/* check local flags */
 	lwz	r12,TI_LOCAL_FLAGS(r9)
 	mtcrf	0x01,r12
@@ -226,13 +226,7 @@ reenable_mmu:				/* re-enable mmu so we can */
 	stw	r3,16(r1)
 	stw	r4,20(r1)
 	stw	r5,24(r1)
-	andi.	r12,r12,MSR_PR
-	b	11f
 	bl	trace_hardirqs_off
-	b	12f
-11:
-	bl	trace_hardirqs_off
-12:
 	lwz	r5,24(r1)
 	lwz	r4,20(r1)
 	lwz	r3,16(r1)
@@ -333,7 +327,7 @@ _GLOBAL(DoSyscall)
 	mtmsr	r11
 1:
 #endif /* CONFIG_TRACE_IRQFLAGS */
-	rlwinm	r10,r1,0,0,(31-THREAD_SHIFT)	/* current_thread_info() */
+	CURRENT_THREAD_INFO(r10, r1)
 	lwz	r11,TI_FLAGS(r10)
 	andi.	r11,r11,_TIF_SYSCALL_T_OR_A
 	bne-	syscall_dotrace
@@ -354,7 +348,7 @@ ret_from_syscall:
 	bl	do_show_syscall_exit
 #endif
 	mr	r6,r3
-	rlwinm	r12,r1,0,0,(31-THREAD_SHIFT)	/* current_thread_info() */
+	CURRENT_THREAD_INFO(r12, r1)
 	/* disable interrupts so current_thread_info()->flags can't change */
 	LOAD_MSR_KERNEL(r10,MSR_KERNEL)	/* doesn't include MSR_EE */
 	/* Note: We don't bother telling lockdep about it */
@@ -815,7 +809,7 @@ ret_from_except:
 
 user_exc_return:		/* r10 contains MSR_KERNEL here */
 	/* Check current_thread_info()->flags */
-	rlwinm	r9,r1,0,0,(31-THREAD_SHIFT)
+	CURRENT_THREAD_INFO(r9, r1)
 	lwz	r9,TI_FLAGS(r9)
 	andi.	r0,r9,_TIF_USER_WORK_MASK
 	bne	do_work
@@ -835,7 +829,7 @@ restore_user:
 /* N.B. the only way to get here is from the beq following ret_from_except. */
 resume_kernel:
 	/* check current_thread_info->preempt_count */
-	rlwinm	r9,r1,0,0,(31-THREAD_SHIFT)
+	CURRENT_THREAD_INFO(r9, r1)
 	lwz	r0,TI_PREEMPT(r9)
 	cmpwi	0,r0,0		/* if non-zero, just restore regs and return */
 	bne	restore
@@ -852,7 +846,7 @@ resume_kernel:
 	bl	trace_hardirqs_off
 #endif
 1:	bl	preempt_schedule_irq
-	rlwinm	r9,r1,0,0,(31-THREAD_SHIFT)
+	CURRENT_THREAD_INFO(r9, r1)
 	lwz	r3,TI_FLAGS(r9)
 	andi.	r0,r3,_TIF_NEED_RESCHED
 	bne-	1b
@@ -1122,7 +1116,7 @@ ret_from_debug_exc:
 	lwz	r10,SAVED_KSP_LIMIT(r1)
 	stw	r10,KSP_LIMIT(r9)
 	lwz	r9,THREAD_INFO-THREAD(r9)
-	rlwinm	r10,r1,0,0,(31-THREAD_SHIFT)
+	CURRENT_THREAD_INFO(r10, r1)
 	lwz	r10,TI_PREEMPT(r10)
 	stw	r10,TI_PREEMPT(r9)
 	RESTORE_xSRR(SRR0,SRR1);
@@ -1156,7 +1150,7 @@ load_dbcr0:
 	lis	r11,global_dbcr0@ha
 	addi	r11,r11,global_dbcr0@l
 #ifdef CONFIG_SMP
-	rlwinm	r9,r1,0,0,(31-THREAD_SHIFT)
+	CURRENT_THREAD_INFO(r9, r1)
 	lwz	r9,TI_CPU(r9)
 	slwi	r9,r9,3
 	add	r11,r11,r9
@@ -1197,7 +1191,7 @@ recheck:
 	LOAD_MSR_KERNEL(r10,MSR_KERNEL)
 	SYNC
 	MTMSRD(r10)		/* disable interrupts */
-	rlwinm	r9,r1,0,0,(31-THREAD_SHIFT)
+	CURRENT_THREAD_INFO(r9, r1)
 	lwz	r9,TI_FLAGS(r9)
 	andi.	r0,r9,_TIF_NEED_RESCHED
 	bne-	do_resched
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index 5971c85df136..4b01a25e29ef 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -146,7 +146,7 @@ END_FW_FTR_SECTION_IFSET(FW_FEATURE_SPLPAR)
 	REST_2GPRS(7,r1)
 	addi	r9,r1,STACK_FRAME_OVERHEAD
 #endif
-	clrrdi	r11,r1,THREAD_SHIFT
+	CURRENT_THREAD_INFO(r11, r1)
 	ld	r10,TI_FLAGS(r11)
 	andi.	r11,r10,_TIF_SYSCALL_T_OR_A
 	bne-	syscall_dotrace
@@ -181,7 +181,7 @@ syscall_exit:
 	bl	.do_show_syscall_exit
 	ld	r3,RESULT(r1)
 #endif
-	clrrdi	r12,r1,THREAD_SHIFT
+	CURRENT_THREAD_INFO(r12, r1)
 
 	ld	r8,_MSR(r1)
 #ifdef CONFIG_PPC_BOOK3S
@@ -197,7 +197,16 @@ syscall_exit:
 	wrteei	0
 #else
 	ld	r10,PACAKMSR(r13)
-	mtmsrd	r10,1
+	/*
+	 * For performance reasons we clear RI the same time that we
+	 * clear EE. We only need to clear RI just before we restore r13
+	 * below, but batching it with EE saves us one expensive mtmsrd call.
+	 * We have to be careful to restore RI if we branch anywhere from
+	 * here (eg syscall_exit_work).
+	 */
+	li	r9,MSR_RI
+	andc	r11,r10,r9
+	mtmsrd	r11,1
 #endif /* CONFIG_PPC_BOOK3E */
 
 	ld	r9,TI_FLAGS(r12)
@@ -214,17 +223,6 @@ BEGIN_FTR_SECTION
 END_FTR_SECTION_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS)
 	andi.	r6,r8,MSR_PR
 	ld	r4,_LINK(r1)
-	/*
-	 * Clear RI before restoring r13.  If we are returning to
-	 * userspace and we take an exception after restoring r13,
-	 * we end up corrupting the userspace r13 value.
-	 */
-#ifdef CONFIG_PPC_BOOK3S
-	/* No MSR:RI on BookE */
-	li	r12,MSR_RI
-	andc	r11,r10,r12
-	mtmsrd	r11,1			/* clear MSR.RI */
-#endif /* CONFIG_PPC_BOOK3S */
 
 	beq-	1f
 	ACCOUNT_CPU_USER_EXIT(r11, r12)
@@ -262,7 +260,7 @@ syscall_dotrace:
 	ld	r7,GPR7(r1)
 	ld	r8,GPR8(r1)
 	addi	r9,r1,STACK_FRAME_OVERHEAD
-	clrrdi	r10,r1,THREAD_SHIFT
+	CURRENT_THREAD_INFO(r10, r1)
 	ld	r10,TI_FLAGS(r10)
 	b	.Lsyscall_dotrace_cont
 
@@ -271,6 +269,9 @@ syscall_enosys:
 	b	syscall_exit
 	
 syscall_exit_work:
+#ifdef CONFIG_PPC_BOOK3S
+	mtmsrd	r10,1		/* Restore RI */
+#endif
 	/* If TIF_RESTOREALL is set, don't scribble on either r3 or ccr.
 	 If TIF_NOERROR is set, just save r3 as it is. */
 
@@ -499,7 +500,7 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT)
 2:
 #endif /* !CONFIG_PPC_BOOK3S */
 
-	clrrdi	r7,r8,THREAD_SHIFT	/* base of new stack */
+	CURRENT_THREAD_INFO(r7, r8)  /* base of new stack */
 	/* Note: this uses SWITCH_FRAME_SIZE rather than INT_FRAME_SIZE
 	   because we don't need to leave the 288-byte ABI gap at the
 	   top of the kernel stack. */
@@ -558,7 +559,7 @@ _GLOBAL(ret_from_except_lite)
 	mtmsrd	r10,1		  /* Update machine state */
 #endif /* CONFIG_PPC_BOOK3E */
 
-	clrrdi	r9,r1,THREAD_SHIFT	/* current_thread_info() */
+	CURRENT_THREAD_INFO(r9, r1)
 	ld	r3,_MSR(r1)
 	ld	r4,TI_FLAGS(r9)
 	andi.	r3,r3,MSR_PR
@@ -601,7 +602,7 @@ resume_kernel:
 1:	bl	.preempt_schedule_irq
 
 	/* Re-test flags and eventually loop */
-	clrrdi	r9,r1,THREAD_SHIFT
+	CURRENT_THREAD_INFO(r9, r1)
 	ld	r4,TI_FLAGS(r9)
 	andi.	r0,r4,_TIF_NEED_RESCHED
 	bne	1b
diff --git a/arch/powerpc/kernel/epapr_hcalls.S b/arch/powerpc/kernel/epapr_hcalls.S
new file mode 100644
index 000000000000..697b390ebfd8
--- /dev/null
+++ b/arch/powerpc/kernel/epapr_hcalls.S
@@ -0,0 +1,25 @@
+/*
+ * Copyright (C) 2012 Freescale Semiconductor, Inc.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/threads.h>
+#include <asm/reg.h>
+#include <asm/page.h>
+#include <asm/cputable.h>
+#include <asm/thread_info.h>
+#include <asm/ppc_asm.h>
+#include <asm/asm-offsets.h>
+
+/* Hypercall entry point. Will be patched with device tree instructions. */
+.global epapr_hypercall_start
+epapr_hypercall_start:
+	li	r3, -1
+	nop
+	nop
+	nop
+	blr
diff --git a/arch/powerpc/kernel/epapr_paravirt.c b/arch/powerpc/kernel/epapr_paravirt.c
new file mode 100644
index 000000000000..028aeae370b6
--- /dev/null
+++ b/arch/powerpc/kernel/epapr_paravirt.c
@@ -0,0 +1,52 @@
+/*
+ * ePAPR para-virtualization support.
+ *
+ * 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, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+ *
+ * Copyright (C) 2012 Freescale Semiconductor, Inc.
+ */
+
+#include <linux/of.h>
+#include <asm/epapr_hcalls.h>
+#include <asm/cacheflush.h>
+#include <asm/code-patching.h>
+
+bool epapr_paravirt_enabled;
+
+static int __init epapr_paravirt_init(void)
+{
+	struct device_node *hyper_node;
+	const u32 *insts;
+	int len, i;
+
+	hyper_node = of_find_node_by_path("/hypervisor");
+	if (!hyper_node)
+		return -ENODEV;
+
+	insts = of_get_property(hyper_node, "hcall-instructions", &len);
+	if (!insts)
+		return -ENODEV;
+
+	if (len % 4 || len > (4 * 4))
+		return -ENODEV;
+
+	for (i = 0; i < (len / 4); i++)
+		patch_instruction(epapr_hypercall_start + i, insts[i]);
+
+	epapr_paravirt_enabled = true;
+
+	return 0;
+}
+
+early_initcall(epapr_paravirt_init);
diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S
index 7215cc2495df..98be7f0cd227 100644
--- a/arch/powerpc/kernel/exceptions-64e.S
+++ b/arch/powerpc/kernel/exceptions-64e.S
@@ -222,7 +222,7 @@ exc_##n##_bad_stack:							    \
  * interrupts happen before the wait instruction.
  */
 #define CHECK_NAPPING()							\
-	clrrdi	r11,r1,THREAD_SHIFT;					\
+	CURRENT_THREAD_INFO(r11, r1);					\
 	ld	r10,TI_LOCAL_FLAGS(r11);				\
 	andi.	r9,r10,_TLF_NAPPING;					\
 	beq+	1f;							\
@@ -903,7 +903,7 @@ skpinv:	addi	r6,r6,1				/* Increment */
 	bne	1b				/* If not, repeat */
 
 	/* Invalidate all TLBs */
-	PPC_TLBILX_ALL(0,0)
+	PPC_TLBILX_ALL(0,R0)
 	sync
 	isync
 
@@ -961,7 +961,7 @@ skpinv:	addi	r6,r6,1				/* Increment */
 	tlbwe
 
 	/* Invalidate TLB1 */
-	PPC_TLBILX_ALL(0,0)
+	PPC_TLBILX_ALL(0,R0)
 	sync
 	isync
 
@@ -1020,7 +1020,7 @@ skpinv:	addi	r6,r6,1				/* Increment */
 	tlbwe
 
 	/* Invalidate TLB1 */
-	PPC_TLBILX_ALL(0,0)
+	PPC_TLBILX_ALL(0,R0)
 	sync
 	isync
 
@@ -1138,7 +1138,7 @@ a2_tlbinit_after_iprot_flush:
 	tlbwe
 #endif /* CONFIG_PPC_EARLY_DEBUG_WSP */
 
-	PPC_TLBILX(0,0,0)
+	PPC_TLBILX(0,0,R0)
 	sync
 	isync
 
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 1c06d2971545..e894515e77bb 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -239,6 +239,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_REAL_LE)
 	 * out of line to handle them
 	 */
 	. = 0xe00
+hv_exception_trampoline:
 	b	h_data_storage_hv
 	. = 0xe20
 	b	h_instr_storage_hv
@@ -851,7 +852,7 @@ BEGIN_FTR_SECTION
 	bne-	do_ste_alloc		/* If so handle it */
 END_MMU_FTR_SECTION_IFCLR(MMU_FTR_SLB)
 
-	clrrdi	r11,r1,THREAD_SHIFT
+	CURRENT_THREAD_INFO(r11, r1)
 	lwz	r0,TI_PREEMPT(r11)	/* If we're in an "NMI" */
 	andis.	r0,r0,NMI_MASK@h	/* (i.e. an irq when soft-disabled) */
 	bne	77f			/* then don't call hash_page now */
diff --git a/arch/powerpc/kernel/fpu.S b/arch/powerpc/kernel/fpu.S
index de369558bf0a..e0ada05f2df3 100644
--- a/arch/powerpc/kernel/fpu.S
+++ b/arch/powerpc/kernel/fpu.S
@@ -26,7 +26,7 @@
 #include <asm/ptrace.h>
 
 #ifdef CONFIG_VSX
-#define REST_32FPVSRS(n,c,base)						\
+#define __REST_32FPVSRS(n,c,base)					\
 BEGIN_FTR_SECTION							\
 	b	2f;							\
 END_FTR_SECTION_IFSET(CPU_FTR_VSX);					\
@@ -35,7 +35,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX);					\
 2:	REST_32VSRS(n,c,base);						\
 3:
 
-#define SAVE_32FPVSRS(n,c,base)						\
+#define __SAVE_32FPVSRS(n,c,base)					\
 BEGIN_FTR_SECTION							\
 	b	2f;							\
 END_FTR_SECTION_IFSET(CPU_FTR_VSX);					\
@@ -44,9 +44,11 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX);					\
 2:	SAVE_32VSRS(n,c,base);						\
 3:
 #else
-#define REST_32FPVSRS(n,b,base)	REST_32FPRS(n, base)
-#define SAVE_32FPVSRS(n,b,base)	SAVE_32FPRS(n, base)
+#define __REST_32FPVSRS(n,b,base)	REST_32FPRS(n, base)
+#define __SAVE_32FPVSRS(n,b,base)	SAVE_32FPRS(n, base)
 #endif
+#define REST_32FPVSRS(n,c,base) __REST_32FPVSRS(n,__REG_##c,__REG_##base)
+#define SAVE_32FPVSRS(n,c,base) __SAVE_32FPVSRS(n,__REG_##c,__REG_##base)
 
 /*
  * This task wants to use the FPU now.
@@ -79,7 +81,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX)
 	beq	1f
 	toreal(r4)
 	addi	r4,r4,THREAD		/* want last_task_used_math->thread */
-	SAVE_32FPVSRS(0, r5, r4)
+	SAVE_32FPVSRS(0, R5, R4)
 	mffs	fr0
 	stfd	fr0,THREAD_FPSCR(r4)
 	PPC_LL	r5,PT_REGS(r4)
@@ -106,7 +108,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX)
 #endif
 	lfd	fr0,THREAD_FPSCR(r5)
 	MTFSF_L(fr0)
-	REST_32FPVSRS(0, r4, r5)
+	REST_32FPVSRS(0, R4, R5)
 #ifndef CONFIG_SMP
 	subi	r4,r5,THREAD
 	fromreal(r4)
@@ -140,7 +142,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX)
 	addi	r3,r3,THREAD	        /* want THREAD of task */
 	PPC_LL	r5,PT_REGS(r3)
 	PPC_LCMPI	0,r5,0
-	SAVE_32FPVSRS(0, r4 ,r3)
+	SAVE_32FPVSRS(0, R4 ,R3)
 	mffs	fr0
 	stfd	fr0,THREAD_FPSCR(r3)
 	beq	1f
diff --git a/arch/powerpc/kernel/ftrace.c b/arch/powerpc/kernel/ftrace.c
index bf99cfa6bbfe..91b46b7f6f0d 100644
--- a/arch/powerpc/kernel/ftrace.c
+++ b/arch/powerpc/kernel/ftrace.c
@@ -63,11 +63,9 @@ ftrace_modify_code(unsigned long ip, unsigned int old, unsigned int new)
 		return -EINVAL;
 
 	/* replace the text with the new text */
-	if (probe_kernel_write((void *)ip, &new, MCOUNT_INSN_SIZE))
+	if (patch_instruction((unsigned int *)ip, new))
 		return -EPERM;
 
-	flush_icache_range(ip, ip + 8);
-
 	return 0;
 }
 
@@ -212,12 +210,9 @@ __ftrace_make_nop(struct module *mod,
 	 */
 	op = 0x48000008;	/* b +8 */
 
-	if (probe_kernel_write((void *)ip, &op, MCOUNT_INSN_SIZE))
+	if (patch_instruction((unsigned int *)ip, op))
 		return -EPERM;
 
-
-	flush_icache_range(ip, ip + 8);
-
 	return 0;
 }
 
@@ -245,9 +240,9 @@ __ftrace_make_nop(struct module *mod,
 
 	/*
 	 * On PPC32 the trampoline looks like:
-	 *  0x3d, 0x60, 0x00, 0x00  lis r11,sym@ha
-	 *  0x39, 0x6b, 0x00, 0x00  addi r11,r11,sym@l
-	 *  0x7d, 0x69, 0x03, 0xa6  mtctr r11
+	 *  0x3d, 0x80, 0x00, 0x00  lis r12,sym@ha
+	 *  0x39, 0x8c, 0x00, 0x00  addi r12,r12,sym@l
+	 *  0x7d, 0x89, 0x03, 0xa6  mtctr r12
 	 *  0x4e, 0x80, 0x04, 0x20  bctr
 	 */
 
@@ -262,9 +257,9 @@ __ftrace_make_nop(struct module *mod,
 	pr_devel(" %08x %08x ", jmp[0], jmp[1]);
 
 	/* verify that this is what we expect it to be */
-	if (((jmp[0] & 0xffff0000) != 0x3d600000) ||
-	    ((jmp[1] & 0xffff0000) != 0x396b0000) ||
-	    (jmp[2] != 0x7d6903a6) ||
+	if (((jmp[0] & 0xffff0000) != 0x3d800000) ||
+	    ((jmp[1] & 0xffff0000) != 0x398c0000) ||
+	    (jmp[2] != 0x7d8903a6) ||
 	    (jmp[3] != 0x4e800420)) {
 		printk(KERN_ERR "Not a trampoline\n");
 		return -EINVAL;
@@ -286,11 +281,9 @@ __ftrace_make_nop(struct module *mod,
 
 	op = PPC_INST_NOP;
 
-	if (probe_kernel_write((void *)ip, &op, MCOUNT_INSN_SIZE))
+	if (patch_instruction((unsigned int *)ip, op))
 		return -EPERM;
 
-	flush_icache_range(ip, ip + 8);
-
 	return 0;
 }
 #endif /* PPC64 */
@@ -426,11 +419,9 @@ __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 
 	pr_devel("write to %lx\n", rec->ip);
 
-	if (probe_kernel_write((void *)ip, &op, MCOUNT_INSN_SIZE))
+	if (patch_instruction((unsigned int *)ip, op))
 		return -EPERM;
 
-	flush_icache_range(ip, ip + 8);
-
 	return 0;
 }
 #endif /* CONFIG_PPC64 */
@@ -484,6 +475,58 @@ int ftrace_update_ftrace_func(ftrace_func_t func)
 	return ret;
 }
 
+static int __ftrace_replace_code(struct dyn_ftrace *rec, int enable)
+{
+	unsigned long ftrace_addr = (unsigned long)FTRACE_ADDR;
+	int ret;
+
+	ret = ftrace_update_record(rec, enable);
+
+	switch (ret) {
+	case FTRACE_UPDATE_IGNORE:
+		return 0;
+	case FTRACE_UPDATE_MAKE_CALL:
+		return ftrace_make_call(rec, ftrace_addr);
+	case FTRACE_UPDATE_MAKE_NOP:
+		return ftrace_make_nop(NULL, rec, ftrace_addr);
+	}
+
+	return 0;
+}
+
+void ftrace_replace_code(int enable)
+{
+	struct ftrace_rec_iter *iter;
+	struct dyn_ftrace *rec;
+	int ret;
+
+	for (iter = ftrace_rec_iter_start(); iter;
+	     iter = ftrace_rec_iter_next(iter)) {
+		rec = ftrace_rec_iter_record(iter);
+		ret = __ftrace_replace_code(rec, enable);
+		if (ret) {
+			ftrace_bug(ret, rec->ip);
+			return;
+		}
+	}
+}
+
+void arch_ftrace_update_code(int command)
+{
+	if (command & FTRACE_UPDATE_CALLS)
+		ftrace_replace_code(1);
+	else if (command & FTRACE_DISABLE_CALLS)
+		ftrace_replace_code(0);
+
+	if (command & FTRACE_UPDATE_TRACE_FUNC)
+		ftrace_update_ftrace_func(ftrace_trace_function);
+
+	if (command & FTRACE_START_FUNC_RET)
+		ftrace_enable_ftrace_graph_caller();
+	else if (command & FTRACE_STOP_FUNC_RET)
+		ftrace_disable_ftrace_graph_caller();
+}
+
 int __init ftrace_dyn_arch_init(void *data)
 {
 	/* caller expects data to be zero */
diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S
index 1f4434a38608..0f59863c3ade 100644
--- a/arch/powerpc/kernel/head_fsl_booke.S
+++ b/arch/powerpc/kernel/head_fsl_booke.S
@@ -192,7 +192,7 @@ _ENTRY(__early_start)
 	li	r0,0
 	stwu	r0,THREAD_SIZE-STACK_FRAME_OVERHEAD(r1)
 
-	rlwinm  r22,r1,0,0,31-THREAD_SHIFT      /* current thread_info */
+	CURRENT_THREAD_INFO(r22, r1)
 	stw	r24, TI_CPU(r22)
 
 	bl	early_init
@@ -556,8 +556,10 @@ END_FTR_SECTION_IFSET(CPU_FTR_EMB_HV)
 	/* SPE Unavailable */
 	START_EXCEPTION(SPEUnavailable)
 	NORMAL_EXCEPTION_PROLOG(SPE_UNAVAIL)
-	bne	load_up_spe
-	addi	r3,r1,STACK_FRAME_OVERHEAD
+	beq	1f
+	bl	load_up_spe
+	b	fast_exception_return
+1:	addi	r3,r1,STACK_FRAME_OVERHEAD
 	EXC_XFER_EE_LITE(0x2010, KernelSPE)
 #else
 	EXCEPTION(0x2020, SPE_UNAVAIL, SPEUnavailable, \
@@ -778,7 +780,7 @@ tlb_write_entry:
 /* Note that the SPE support is closely modeled after the AltiVec
  * support.  Changes to one are likely to be applicable to the
  * other!  */
-load_up_spe:
+_GLOBAL(load_up_spe)
 /*
  * Disable SPE for the task which had SPE previously,
  * and save its SPE registers in its thread_struct.
@@ -826,20 +828,7 @@ load_up_spe:
 	subi	r4,r5,THREAD
 	stw	r4,last_task_used_spe@l(r3)
 #endif /* !CONFIG_SMP */
-	/* restore registers and return */
-2:	REST_4GPRS(3, r11)
-	lwz	r10,_CCR(r11)
-	REST_GPR(1, r11)
-	mtcr	r10
-	lwz	r10,_LINK(r11)
-	mtlr	r10
-	REST_GPR(10, r11)
-	mtspr	SPRN_SRR1,r9
-	mtspr	SPRN_SRR0,r12
-	REST_GPR(9, r11)
-	REST_GPR(12, r11)
-	lwz	r11,GPR11(r11)
-	rfi
+	blr
 
 /*
  * SPE unavailable trap from kernel - print a message, but let
diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c
index 2bc0584be81c..f3a82dde61db 100644
--- a/arch/powerpc/kernel/hw_breakpoint.c
+++ b/arch/powerpc/kernel/hw_breakpoint.c
@@ -111,7 +111,7 @@ void arch_unregister_hw_breakpoint(struct perf_event *bp)
 	 * and the single_step_dabr_instruction(), then cleanup the breakpoint
 	 * restoration variables to prevent dangling pointers.
 	 */
-	if (bp->ctx->task)
+	if (bp->ctx && bp->ctx->task)
 		bp->ctx->task->thread.last_hit_ubp = NULL;
 }
 
diff --git a/arch/powerpc/kernel/idle_6xx.S b/arch/powerpc/kernel/idle_6xx.S
index 15c611de1ee2..1686916cc7f0 100644
--- a/arch/powerpc/kernel/idle_6xx.S
+++ b/arch/powerpc/kernel/idle_6xx.S
@@ -135,7 +135,7 @@ BEGIN_FTR_SECTION
 	DSSALL
 	sync
 END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
-	rlwinm	r9,r1,0,0,31-THREAD_SHIFT	/* current thread_info */
+	CURRENT_THREAD_INFO(r9, r1)
 	lwz	r8,TI_LOCAL_FLAGS(r9)	/* set napping bit */
 	ori	r8,r8,_TLF_NAPPING	/* so when we take an exception */
 	stw	r8,TI_LOCAL_FLAGS(r9)	/* it will return to our caller */
@@ -158,7 +158,7 @@ _GLOBAL(power_save_ppc32_restore)
 	stw	r9,_NIP(r11)		/* make it do a blr */
 
 #ifdef CONFIG_SMP
-	rlwinm	r12,r11,0,0,31-THREAD_SHIFT
+	CURRENT_THREAD_INFO(r12, r11)
 	lwz	r11,TI_CPU(r12)		/* get cpu number * 4 */
 	slwi	r11,r11,2
 #else
diff --git a/arch/powerpc/kernel/idle_book3e.S b/arch/powerpc/kernel/idle_book3e.S
index ff007b59448d..4c7cb4008585 100644
--- a/arch/powerpc/kernel/idle_book3e.S
+++ b/arch/powerpc/kernel/idle_book3e.S
@@ -60,7 +60,7 @@ _GLOBAL(book3e_idle)
 1:	/* Let's set the _TLF_NAPPING flag so interrupts make us return
 	 * to the right spot
 	*/
-	clrrdi	r11,r1,THREAD_SHIFT
+	CURRENT_THREAD_INFO(r11, r1)
 	ld	r10,TI_LOCAL_FLAGS(r11)
 	ori	r10,r10,_TLF_NAPPING
 	std	r10,TI_LOCAL_FLAGS(r11)
diff --git a/arch/powerpc/kernel/idle_e500.S b/arch/powerpc/kernel/idle_e500.S
index 4f0ab85f3788..15448668988d 100644
--- a/arch/powerpc/kernel/idle_e500.S
+++ b/arch/powerpc/kernel/idle_e500.S
@@ -21,7 +21,7 @@
 	.text
 
 _GLOBAL(e500_idle)
-	rlwinm	r3,r1,0,0,31-THREAD_SHIFT	/* current thread_info */
+	CURRENT_THREAD_INFO(r3, r1)
 	lwz	r4,TI_LOCAL_FLAGS(r3)	/* set napping bit */
 	ori	r4,r4,_TLF_NAPPING	/* so when we take an exception */
 	stw	r4,TI_LOCAL_FLAGS(r3)	/* it will return to our caller */
@@ -96,7 +96,7 @@ _GLOBAL(power_save_ppc32_restore)
 	stw	r9,_NIP(r11)		/* make it do a blr */
 
 #ifdef CONFIG_SMP
-	rlwinm	r12,r1,0,0,31-THREAD_SHIFT
+	CURRENT_THREAD_INFO(r12, r1)
 	lwz	r11,TI_CPU(r12)		/* get cpu number * 4 */
 	slwi	r11,r11,2
 #else
diff --git a/arch/powerpc/kernel/idle_power4.S b/arch/powerpc/kernel/idle_power4.S
index 2c71b0fc9f91..e3edaa189911 100644
--- a/arch/powerpc/kernel/idle_power4.S
+++ b/arch/powerpc/kernel/idle_power4.S
@@ -59,7 +59,7 @@ BEGIN_FTR_SECTION
 	DSSALL
 	sync
 END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
-	clrrdi	r9,r1,THREAD_SHIFT	/* current thread_info */
+	CURRENT_THREAD_INFO(r9, r1)
 	ld	r8,TI_LOCAL_FLAGS(r9)	/* set napping bit */
 	ori	r8,r8,_TLF_NAPPING	/* so when we take an exception */
 	std	r8,TI_LOCAL_FLAGS(r9)	/* it will return to our caller */
diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index 359f078571c7..ff5a6ce027b8 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -33,6 +33,9 @@
 #include <linux/bitmap.h>
 #include <linux/iommu-helper.h>
 #include <linux/crash_dump.h>
+#include <linux/hash.h>
+#include <linux/fault-inject.h>
+#include <linux/pci.h>
 #include <asm/io.h>
 #include <asm/prom.h>
 #include <asm/iommu.h>
@@ -40,6 +43,7 @@
 #include <asm/machdep.h>
 #include <asm/kdump.h>
 #include <asm/fadump.h>
+#include <asm/vio.h>
 
 #define DBG(...)
 
@@ -58,6 +62,114 @@ static int __init setup_iommu(char *str)
 
 __setup("iommu=", setup_iommu);
 
+static DEFINE_PER_CPU(unsigned int, iommu_pool_hash);
+
+/*
+ * We precalculate the hash to avoid doing it on every allocation.
+ *
+ * The hash is important to spread CPUs across all the pools. For example,
+ * on a POWER7 with 4 way SMT we want interrupts on the primary threads and
+ * with 4 pools all primary threads would map to the same pool.
+ */
+static int __init setup_iommu_pool_hash(void)
+{
+	unsigned int i;
+
+	for_each_possible_cpu(i)
+		per_cpu(iommu_pool_hash, i) = hash_32(i, IOMMU_POOL_HASHBITS);
+
+	return 0;
+}
+subsys_initcall(setup_iommu_pool_hash);
+
+#ifdef CONFIG_FAIL_IOMMU
+
+static DECLARE_FAULT_ATTR(fail_iommu);
+
+static int __init setup_fail_iommu(char *str)
+{
+	return setup_fault_attr(&fail_iommu, str);
+}
+__setup("fail_iommu=", setup_fail_iommu);
+
+static bool should_fail_iommu(struct device *dev)
+{
+	return dev->archdata.fail_iommu && should_fail(&fail_iommu, 1);
+}
+
+static int __init fail_iommu_debugfs(void)
+{
+	struct dentry *dir = fault_create_debugfs_attr("fail_iommu",
+						       NULL, &fail_iommu);
+
+	return IS_ERR(dir) ? PTR_ERR(dir) : 0;
+}
+late_initcall(fail_iommu_debugfs);
+
+static ssize_t fail_iommu_show(struct device *dev,
+			       struct device_attribute *attr, char *buf)
+{
+	return sprintf(buf, "%d\n", dev->archdata.fail_iommu);
+}
+
+static ssize_t fail_iommu_store(struct device *dev,
+				struct device_attribute *attr, const char *buf,
+				size_t count)
+{
+	int i;
+
+	if (count > 0 && sscanf(buf, "%d", &i) > 0)
+		dev->archdata.fail_iommu = (i == 0) ? 0 : 1;
+
+	return count;
+}
+
+static DEVICE_ATTR(fail_iommu, S_IRUGO|S_IWUSR, fail_iommu_show,
+		   fail_iommu_store);
+
+static int fail_iommu_bus_notify(struct notifier_block *nb,
+				 unsigned long action, void *data)
+{
+	struct device *dev = data;
+
+	if (action == BUS_NOTIFY_ADD_DEVICE) {
+		if (device_create_file(dev, &dev_attr_fail_iommu))
+			pr_warn("Unable to create IOMMU fault injection sysfs "
+				"entries\n");
+	} else if (action == BUS_NOTIFY_DEL_DEVICE) {
+		device_remove_file(dev, &dev_attr_fail_iommu);
+	}
+
+	return 0;
+}
+
+static struct notifier_block fail_iommu_bus_notifier = {
+	.notifier_call = fail_iommu_bus_notify
+};
+
+static int __init fail_iommu_setup(void)
+{
+#ifdef CONFIG_PCI
+	bus_register_notifier(&pci_bus_type, &fail_iommu_bus_notifier);
+#endif
+#ifdef CONFIG_IBMVIO
+	bus_register_notifier(&vio_bus_type, &fail_iommu_bus_notifier);
+#endif
+
+	return 0;
+}
+/*
+ * Must execute after PCI and VIO subsystem have initialised but before
+ * devices are probed.
+ */
+arch_initcall(fail_iommu_setup);
+#else
+static inline bool should_fail_iommu(struct device *dev)
+{
+	return false;
+}
+#endif
+
 static unsigned long iommu_range_alloc(struct device *dev,
 				       struct iommu_table *tbl,
                                        unsigned long npages,
@@ -71,6 +183,9 @@ static unsigned long iommu_range_alloc(struct device *dev,
 	int pass = 0;
 	unsigned long align_mask;
 	unsigned long boundary_size;
+	unsigned long flags;
+	unsigned int pool_nr;
+	struct iommu_pool *pool;
 
 	align_mask = 0xffffffffffffffffl >> (64 - align_order);
 
@@ -83,36 +198,49 @@ static unsigned long iommu_range_alloc(struct device *dev,
 		return DMA_ERROR_CODE;
 	}
 
-	if (handle && *handle)
-		start = *handle;
+	if (should_fail_iommu(dev))
+		return DMA_ERROR_CODE;
+
+	/*
+	 * We don't need to disable preemption here because any CPU can
+	 * safely use any IOMMU pool.
+	 */
+	pool_nr = __raw_get_cpu_var(iommu_pool_hash) & (tbl->nr_pools - 1);
+
+	if (largealloc)
+		pool = &(tbl->large_pool);
 	else
-		start = largealloc ? tbl->it_largehint : tbl->it_hint;
+		pool = &(tbl->pools[pool_nr]);
 
-	/* Use only half of the table for small allocs (15 pages or less) */
-	limit = largealloc ? tbl->it_size : tbl->it_halfpoint;
+	spin_lock_irqsave(&(pool->lock), flags);
 
-	if (largealloc && start < tbl->it_halfpoint)
-		start = tbl->it_halfpoint;
+again:
+	if ((pass == 0) && handle && *handle)
+		start = *handle;
+	else
+		start = pool->hint;
+
+	limit = pool->end;
 
 	/* The case below can happen if we have a small segment appended
 	 * to a large, or when the previous alloc was at the very end of
 	 * the available space. If so, go back to the initial start.
 	 */
 	if (start >= limit)
-		start = largealloc ? tbl->it_largehint : tbl->it_hint;
-
- again:
+		start = pool->start;
 
 	if (limit + tbl->it_offset > mask) {
 		limit = mask - tbl->it_offset + 1;
 		/* If we're constrained on address range, first try
 		 * at the masked hint to avoid O(n) search complexity,
-		 * but on second pass, start at 0.
+		 * but on second pass, start at 0 in pool 0.
 		 */
-		if ((start & mask) >= limit || pass > 0)
-			start = 0;
-		else
+		if ((start & mask) >= limit || pass > 0) {
+			pool = &(tbl->pools[0]);
+			start = pool->start;
+		} else {
 			start &= mask;
+		}
 	}
 
 	if (dev)
@@ -126,16 +254,25 @@ static unsigned long iommu_range_alloc(struct device *dev,
 			     tbl->it_offset, boundary_size >> IOMMU_PAGE_SHIFT,
 			     align_mask);
 	if (n == -1) {
-		if (likely(pass < 2)) {
-			/* First failure, just rescan the half of the table.
-			 * Second failure, rescan the other half of the table.
-			 */
-			start = (largealloc ^ pass) ? tbl->it_halfpoint : 0;
-			limit = pass ? tbl->it_size : limit;
+		if (likely(pass == 0)) {
+			/* First try the pool from the start */
+			pool->hint = pool->start;
 			pass++;
 			goto again;
+
+		} else if (pass <= tbl->nr_pools) {
+			/* Now try scanning all the other pools */
+			spin_unlock(&(pool->lock));
+			pool_nr = (pool_nr + 1) & (tbl->nr_pools - 1);
+			pool = &tbl->pools[pool_nr];
+			spin_lock(&(pool->lock));
+			pool->hint = pool->start;
+			pass++;
+			goto again;
+
 		} else {
-			/* Third failure, give up */
+			/* Give up */
+			spin_unlock_irqrestore(&(pool->lock), flags);
 			return DMA_ERROR_CODE;
 		}
 	}
@@ -145,10 +282,10 @@ static unsigned long iommu_range_alloc(struct device *dev,
 	/* Bump the hint to a new block for small allocs. */
 	if (largealloc) {
 		/* Don't bump to new block to avoid fragmentation */
-		tbl->it_largehint = end;
+		pool->hint = end;
 	} else {
 		/* Overflow will be taken care of at the next allocation */
-		tbl->it_hint = (end + tbl->it_blocksize - 1) &
+		pool->hint = (end + tbl->it_blocksize - 1) &
 		                ~(tbl->it_blocksize - 1);
 	}
 
@@ -156,6 +293,8 @@ static unsigned long iommu_range_alloc(struct device *dev,
 	if (handle)
 		*handle = end;
 
+	spin_unlock_irqrestore(&(pool->lock), flags);
+
 	return n;
 }
 
@@ -165,18 +304,14 @@ static dma_addr_t iommu_alloc(struct device *dev, struct iommu_table *tbl,
 			      unsigned long mask, unsigned int align_order,
 			      struct dma_attrs *attrs)
 {
-	unsigned long entry, flags;
+	unsigned long entry;
 	dma_addr_t ret = DMA_ERROR_CODE;
 	int build_fail;
 
-	spin_lock_irqsave(&(tbl->it_lock), flags);
-
 	entry = iommu_range_alloc(dev, tbl, npages, NULL, mask, align_order);
 
-	if (unlikely(entry == DMA_ERROR_CODE)) {
-		spin_unlock_irqrestore(&(tbl->it_lock), flags);
+	if (unlikely(entry == DMA_ERROR_CODE))
 		return DMA_ERROR_CODE;
-	}
 
 	entry += tbl->it_offset;	/* Offset into real TCE table */
 	ret = entry << IOMMU_PAGE_SHIFT;	/* Set the return dma address */
@@ -193,8 +328,6 @@ static dma_addr_t iommu_alloc(struct device *dev, struct iommu_table *tbl,
 	 */
 	if (unlikely(build_fail)) {
 		__iommu_free(tbl, ret, npages);
-
-		spin_unlock_irqrestore(&(tbl->it_lock), flags);
 		return DMA_ERROR_CODE;
 	}
 
@@ -202,16 +335,14 @@ static dma_addr_t iommu_alloc(struct device *dev, struct iommu_table *tbl,
 	if (ppc_md.tce_flush)
 		ppc_md.tce_flush(tbl);
 
-	spin_unlock_irqrestore(&(tbl->it_lock), flags);
-
 	/* Make sure updates are seen by hardware */
 	mb();
 
 	return ret;
 }
 
-static void __iommu_free(struct iommu_table *tbl, dma_addr_t dma_addr, 
-			 unsigned int npages)
+static bool iommu_free_check(struct iommu_table *tbl, dma_addr_t dma_addr,
+			     unsigned int npages)
 {
 	unsigned long entry, free_entry;
 
@@ -231,20 +362,57 @@ static void __iommu_free(struct iommu_table *tbl, dma_addr_t dma_addr,
 			printk(KERN_INFO "\tindex     = 0x%llx\n", (u64)tbl->it_index);
 			WARN_ON(1);
 		}
-		return;
+
+		return false;
+	}
+
+	return true;
+}
+
+static struct iommu_pool *get_pool(struct iommu_table *tbl,
+				   unsigned long entry)
+{
+	struct iommu_pool *p;
+	unsigned long largepool_start = tbl->large_pool.start;
+
+	/* The large pool is the last pool at the top of the table */
+	if (entry >= largepool_start) {
+		p = &tbl->large_pool;
+	} else {
+		unsigned int pool_nr = entry / tbl->poolsize;
+
+		BUG_ON(pool_nr > tbl->nr_pools);
+		p = &tbl->pools[pool_nr];
 	}
 
+	return p;
+}
+
+static void __iommu_free(struct iommu_table *tbl, dma_addr_t dma_addr,
+			 unsigned int npages)
+{
+	unsigned long entry, free_entry;
+	unsigned long flags;
+	struct iommu_pool *pool;
+
+	entry = dma_addr >> IOMMU_PAGE_SHIFT;
+	free_entry = entry - tbl->it_offset;
+
+	pool = get_pool(tbl, free_entry);
+
+	if (!iommu_free_check(tbl, dma_addr, npages))
+		return;
+
 	ppc_md.tce_free(tbl, entry, npages);
+
+	spin_lock_irqsave(&(pool->lock), flags);
 	bitmap_clear(tbl->it_map, free_entry, npages);
+	spin_unlock_irqrestore(&(pool->lock), flags);
 }
 
 static void iommu_free(struct iommu_table *tbl, dma_addr_t dma_addr,
 		unsigned int npages)
 {
-	unsigned long flags;
-
-	spin_lock_irqsave(&(tbl->it_lock), flags);
-
 	__iommu_free(tbl, dma_addr, npages);
 
 	/* Make sure TLB cache is flushed if the HW needs it. We do
@@ -253,8 +421,6 @@ static void iommu_free(struct iommu_table *tbl, dma_addr_t dma_addr,
 	 */
 	if (ppc_md.tce_flush)
 		ppc_md.tce_flush(tbl);
-
-	spin_unlock_irqrestore(&(tbl->it_lock), flags);
 }
 
 int iommu_map_sg(struct device *dev, struct iommu_table *tbl,
@@ -263,7 +429,6 @@ int iommu_map_sg(struct device *dev, struct iommu_table *tbl,
 		 struct dma_attrs *attrs)
 {
 	dma_addr_t dma_next = 0, dma_addr;
-	unsigned long flags;
 	struct scatterlist *s, *outs, *segstart;
 	int outcount, incount, i, build_fail = 0;
 	unsigned int align;
@@ -285,8 +450,6 @@ int iommu_map_sg(struct device *dev, struct iommu_table *tbl,
 
 	DBG("sg mapping %d elements:\n", nelems);
 
-	spin_lock_irqsave(&(tbl->it_lock), flags);
-
 	max_seg_size = dma_get_max_seg_size(dev);
 	for_each_sg(sglist, s, nelems, i) {
 		unsigned long vaddr, npages, entry, slen;
@@ -369,8 +532,6 @@ int iommu_map_sg(struct device *dev, struct iommu_table *tbl,
 	if (ppc_md.tce_flush)
 		ppc_md.tce_flush(tbl);
 
-	spin_unlock_irqrestore(&(tbl->it_lock), flags);
-
 	DBG("mapped %d elements:\n", outcount);
 
 	/* For the sake of iommu_unmap_sg, we clear out the length in the
@@ -402,7 +563,6 @@ int iommu_map_sg(struct device *dev, struct iommu_table *tbl,
 		if (s == outs)
 			break;
 	}
-	spin_unlock_irqrestore(&(tbl->it_lock), flags);
 	return 0;
 }
 
@@ -412,15 +572,12 @@ void iommu_unmap_sg(struct iommu_table *tbl, struct scatterlist *sglist,
 		struct dma_attrs *attrs)
 {
 	struct scatterlist *sg;
-	unsigned long flags;
 
 	BUG_ON(direction == DMA_NONE);
 
 	if (!tbl)
 		return;
 
-	spin_lock_irqsave(&(tbl->it_lock), flags);
-
 	sg = sglist;
 	while (nelems--) {
 		unsigned int npages;
@@ -440,8 +597,6 @@ void iommu_unmap_sg(struct iommu_table *tbl, struct scatterlist *sglist,
 	 */
 	if (ppc_md.tce_flush)
 		ppc_md.tce_flush(tbl);
-
-	spin_unlock_irqrestore(&(tbl->it_lock), flags);
 }
 
 static void iommu_table_clear(struct iommu_table *tbl)
@@ -494,9 +649,8 @@ struct iommu_table *iommu_init_table(struct iommu_table *tbl, int nid)
 	unsigned long sz;
 	static int welcomed = 0;
 	struct page *page;
-
-	/* Set aside 1/4 of the table for large allocations. */
-	tbl->it_halfpoint = tbl->it_size * 3 / 4;
+	unsigned int i;
+	struct iommu_pool *p;
 
 	/* number of bytes needed for the bitmap */
 	sz = (tbl->it_size + 7) >> 3;
@@ -515,9 +669,28 @@ struct iommu_table *iommu_init_table(struct iommu_table *tbl, int nid)
 	if (tbl->it_offset == 0)
 		set_bit(0, tbl->it_map);
 
-	tbl->it_hint = 0;
-	tbl->it_largehint = tbl->it_halfpoint;
-	spin_lock_init(&tbl->it_lock);
+	/* We only split the IOMMU table if we have 1GB or more of space */
+	if ((tbl->it_size << IOMMU_PAGE_SHIFT) >= (1UL * 1024 * 1024 * 1024))
+		tbl->nr_pools = IOMMU_NR_POOLS;
+	else
+		tbl->nr_pools = 1;
+
+	/* We reserve the top 1/4 of the table for large allocations */
+	tbl->poolsize = (tbl->it_size * 3 / 4) / tbl->nr_pools;
+
+	for (i = 0; i < tbl->nr_pools; i++) {
+		p = &tbl->pools[i];
+		spin_lock_init(&(p->lock));
+		p->start = tbl->poolsize * i;
+		p->hint = p->start;
+		p->end = p->start + tbl->poolsize;
+	}
+
+	p = &tbl->large_pool;
+	spin_lock_init(&(p->lock));
+	p->start = tbl->poolsize * i;
+	p->hint = p->start;
+	p->end = tbl->it_size;
 
 	iommu_table_clear(tbl);
 
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 1b415027ec0e..1f017bb7a7ce 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -229,7 +229,7 @@ notrace void arch_local_irq_restore(unsigned long en)
 	 */
 	if (unlikely(irq_happened != PACA_IRQ_HARD_DIS))
 		__hard_irq_disable();
-#ifdef CONFIG_TRACE_IRQFLAG
+#ifdef CONFIG_TRACE_IRQFLAGS
 	else {
 		/*
 		 * We should already be hard disabled here. We had bugs
@@ -286,6 +286,52 @@ void notrace restore_interrupts(void)
 		__hard_irq_enable();
 }
 
+/*
+ * This is a helper to use when about to go into idle low-power
+ * when the latter has the side effect of re-enabling interrupts
+ * (such as calling H_CEDE under pHyp).
+ *
+ * You call this function with interrupts soft-disabled (this is
+ * already the case when ppc_md.power_save is called). The function
+ * will return whether to enter power save or just return.
+ *
+ * In the former case, it will have notified lockdep of interrupts
+ * being re-enabled and generally sanitized the lazy irq state,
+ * and in the latter case it will leave with interrupts hard
+ * disabled and marked as such, so the local_irq_enable() call
+ * in cpu_idle() will properly re-enable everything.
+ */
+bool prep_irq_for_idle(void)
+{
+	/*
+	 * First we need to hard disable to ensure no interrupt
+	 * occurs before we effectively enter the low power state
+	 */
+	hard_irq_disable();
+
+	/*
+	 * If anything happened while we were soft-disabled,
+	 * we return now and do not enter the low power state.
+	 */
+	if (lazy_irq_pending())
+		return false;
+
+	/* Tell lockdep we are about to re-enable */
+	trace_hardirqs_on();
+
+	/*
+	 * Mark interrupts as soft-enabled and clear the
+	 * PACA_IRQ_HARD_DIS from the pending mask since we
+	 * are about to hard enable as well as a side effect
+	 * of entering the low power state.
+	 */
+	local_paca->irq_happened &= ~PACA_IRQ_HARD_DIS;
+	local_paca->soft_enabled = 1;
+
+	/* Tell the caller to enter the low power state */
+	return true;
+}
+
 #endif /* CONFIG_PPC64 */
 
 int arch_show_interrupts(struct seq_file *p, int prec)
diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c
index 62bdf2389669..867db1de8949 100644
--- a/arch/powerpc/kernel/kvm.c
+++ b/arch/powerpc/kernel/kvm.c
@@ -31,6 +31,7 @@
 #include <asm/cacheflush.h>
 #include <asm/disassemble.h>
 #include <asm/ppc-opcode.h>
+#include <asm/epapr_hcalls.h>
 
 #define KVM_MAGIC_PAGE		(-4096L)
 #define magic_var(x) KVM_MAGIC_PAGE + offsetof(struct kvm_vcpu_arch_shared, x)
@@ -302,7 +303,7 @@ static void kvm_patch_ins_wrtee(u32 *inst, u32 rt, int imm_one)
 
 	if (imm_one) {
 		p[kvm_emulate_wrtee_reg_offs] =
-			KVM_INST_LI | __PPC_RT(30) | MSR_EE;
+			KVM_INST_LI | __PPC_RT(R30) | MSR_EE;
 	} else {
 		/* Make clobbered registers work too */
 		switch (get_rt(rt)) {
@@ -726,7 +727,7 @@ unsigned long kvm_hypercall(unsigned long *in,
 	unsigned long register r11 asm("r11") = nr;
 	unsigned long register r12 asm("r12");
 
-	asm volatile("bl	kvm_hypercall_start"
+	asm volatile("bl	epapr_hypercall_start"
 		     : "=r"(r0), "=r"(r3), "=r"(r4), "=r"(r5), "=r"(r6),
 		       "=r"(r7), "=r"(r8), "=r"(r9), "=r"(r10), "=r"(r11),
 		       "=r"(r12)
@@ -747,29 +748,6 @@ unsigned long kvm_hypercall(unsigned long *in,
 }
 EXPORT_SYMBOL_GPL(kvm_hypercall);
 
-static int kvm_para_setup(void)
-{
-	extern u32 kvm_hypercall_start;
-	struct device_node *hyper_node;
-	u32 *insts;
-	int len, i;
-
-	hyper_node = of_find_node_by_path("/hypervisor");
-	if (!hyper_node)
-		return -1;
-
-	insts = (u32*)of_get_property(hyper_node, "hcall-instructions", &len);
-	if (len % 4)
-		return -1;
-	if (len > (4 * 4))
-		return -1;
-
-	for (i = 0; i < (len / 4); i++)
-		kvm_patch_ins(&(&kvm_hypercall_start)[i], insts[i]);
-
-	return 0;
-}
-
 static __init void kvm_free_tmp(void)
 {
 	unsigned long start, end;
@@ -791,7 +769,7 @@ static int __init kvm_guest_init(void)
 	if (!kvm_para_available())
 		goto free_tmp;
 
-	if (kvm_para_setup())
+	if (!epapr_paravirt_enabled)
 		goto free_tmp;
 
 	if (kvm_para_has_feature(KVM_FEATURE_MAGIC_PAGE))
diff --git a/arch/powerpc/kernel/kvm_emul.S b/arch/powerpc/kernel/kvm_emul.S
index e291cf3cf954..e100ff324a85 100644
--- a/arch/powerpc/kernel/kvm_emul.S
+++ b/arch/powerpc/kernel/kvm_emul.S
@@ -24,16 +24,6 @@
 #include <asm/page.h>
 #include <asm/asm-offsets.h>
 
-/* Hypercall entry point. Will be patched with device tree instructions. */
-
-.global kvm_hypercall_start
-kvm_hypercall_start:
-	li	r3, -1
-	nop
-	nop
-	nop
-	blr
-
 #define KVM_MAGIC_PAGE		(-4096)
 
 #ifdef CONFIG_64BIT
@@ -132,7 +122,7 @@ kvm_emulate_mtmsrd_len:
 	.long (kvm_emulate_mtmsrd_end - kvm_emulate_mtmsrd) / 4
 
 
-#define MSR_SAFE_BITS (MSR_EE | MSR_CE | MSR_ME | MSR_RI)
+#define MSR_SAFE_BITS (MSR_EE | MSR_RI)
 #define MSR_CRITICAL_BITS ~MSR_SAFE_BITS
 
 .global kvm_emulate_mtmsr
diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S
index 386d57f66f28..407e293aad2f 100644
--- a/arch/powerpc/kernel/misc_32.S
+++ b/arch/powerpc/kernel/misc_32.S
@@ -179,7 +179,7 @@ _GLOBAL(low_choose_750fx_pll)
 	mtspr	SPRN_HID1,r4
 
 	/* Store new HID1 image */
-	rlwinm	r6,r1,0,0,(31-THREAD_SHIFT)
+	CURRENT_THREAD_INFO(r6, r1)
 	lwz	r6,TI_CPU(r6)
 	slwi	r6,r6,2
 	addis	r6,r6,nap_save_hid1@ha
@@ -699,7 +699,7 @@ _GLOBAL(kernel_thread)
 #ifdef CONFIG_SMP
 _GLOBAL(start_secondary_resume)
 	/* Reset stack */
-	rlwinm	r1,r1,0,0,(31-THREAD_SHIFT)	/* current_thread_info() */
+	CURRENT_THREAD_INFO(r1, r1)
 	addi	r1,r1,THREAD_SIZE-STACK_FRAME_OVERHEAD
 	li	r3,0
 	stw	r3,0(r1)		/* Zero the stack frame pointer	*/
diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S
index 616921ef1439..565b78625a32 100644
--- a/arch/powerpc/kernel/misc_64.S
+++ b/arch/powerpc/kernel/misc_64.S
@@ -301,11 +301,6 @@ _GLOBAL(real_writeb)
 
 #ifdef CONFIG_PPC_PASEMI
 
-/* No support in all binutils for these yet, so use defines */
-#define LBZCIX(RT,RA,RB)  .long (0x7c0006aa|(RT<<21)|(RA<<16)|(RB << 11))
-#define STBCIX(RS,RA,RB)  .long (0x7c0007aa|(RS<<21)|(RA<<16)|(RB << 11))
-
-
 _GLOBAL(real_205_readb)
 	mfmsr	r7
 	ori	r0,r7,MSR_DR
@@ -314,7 +309,7 @@ _GLOBAL(real_205_readb)
 	mtmsrd	r0
 	sync
 	isync
-	LBZCIX(r3,0,r3)
+	LBZCIX(R3,R0,R3)
 	isync
 	mtmsrd	r7
 	sync
@@ -329,7 +324,7 @@ _GLOBAL(real_205_writeb)
 	mtmsrd	r0
 	sync
 	isync
-	STBCIX(r3,0,r4)
+	STBCIX(R3,R0,R4)
 	isync
 	mtmsrd	r7
 	sync
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index 886c254fd565..2aa04f29e1de 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -200,11 +200,6 @@ int pcibios_add_platform_entries(struct pci_dev *pdev)
 	return device_create_file(&pdev->dev, &dev_attr_devspec);
 }
 
-char __devinit *pcibios_setup(char *str)
-{
-	return str;
-}
-
 /*
  * Reads the interrupt pin to determine if interrupt is use by card.
  * If the interrupt is used, then gets the interrupt line from the
@@ -1635,6 +1630,11 @@ void __devinit pcibios_scan_phb(struct pci_controller *hose)
 	/* Wire up PHB bus resources */
 	pcibios_setup_phb_resources(hose, &resources);
 
+	hose->busn.start = hose->first_busno;
+	hose->busn.end	 = hose->last_busno;
+	hose->busn.flags = IORESOURCE_BUS;
+	pci_add_resource(&resources, &hose->busn);
+
 	/* Create an empty bus for the toplevel */
 	bus = pci_create_root_bus(hose->parent, hose->first_busno,
 				  hose->ops, hose, &resources);
@@ -1644,7 +1644,6 @@ void __devinit pcibios_scan_phb(struct pci_controller *hose)
 		pci_free_resource_list(&resources);
 		return;
 	}
-	bus->secondary = hose->first_busno;
 	hose->bus = bus;
 
 	/* Get probe mode and perform scan */
@@ -1652,13 +1651,14 @@ void __devinit pcibios_scan_phb(struct pci_controller *hose)
 	if (node && ppc_md.pci_probe_mode)
 		mode = ppc_md.pci_probe_mode(bus);
 	pr_debug("    probe mode: %d\n", mode);
-	if (mode == PCI_PROBE_DEVTREE) {
-		bus->subordinate = hose->last_busno;
+	if (mode == PCI_PROBE_DEVTREE)
 		of_scan_bus(node, bus);
-	}
 
-	if (mode == PCI_PROBE_NORMAL)
-		hose->last_busno = bus->subordinate = pci_scan_child_bus(bus);
+	if (mode == PCI_PROBE_NORMAL) {
+		pci_bus_update_busn_res_end(bus, 255);
+		hose->last_busno = pci_scan_child_bus(bus);
+		pci_bus_update_busn_res_end(bus, hose->last_busno);
+	}
 
 	/* Platform gets a chance to do some global fixups before
 	 * we proceed to resource allocation
diff --git a/arch/powerpc/kernel/pci_64.c b/arch/powerpc/kernel/pci_64.c
index 94a54f61d341..4ff190ff24a0 100644
--- a/arch/powerpc/kernel/pci_64.c
+++ b/arch/powerpc/kernel/pci_64.c
@@ -236,7 +236,7 @@ long sys_pciconfig_iobase(long which, unsigned long in_bus,
 
 	for (ln = pci_root_buses.next; ln != &pci_root_buses; ln = ln->next) {
 		bus = pci_bus_b(ln);
-		if (in_bus >= bus->number && in_bus <= bus->subordinate)
+		if (in_bus >= bus->number && in_bus <= bus->busn_res.end)
 			break;
 		bus = NULL;
 	}
diff --git a/arch/powerpc/kernel/pci_of_scan.c b/arch/powerpc/kernel/pci_of_scan.c
index 89dde171a6fa..30378a19f65d 100644
--- a/arch/powerpc/kernel/pci_of_scan.c
+++ b/arch/powerpc/kernel/pci_of_scan.c
@@ -198,7 +198,6 @@ EXPORT_SYMBOL(of_create_pci_dev);
 
 /**
  * of_scan_pci_bridge - Set up a PCI bridge and scan for child nodes
- * @node: device tree node of bridge
  * @dev: pci_dev structure for the bridge
  *
  * of_scan_bus() calls this routine for each PCI bridge that it finds, and
@@ -240,7 +239,7 @@ void __devinit of_scan_pci_bridge(struct pci_dev *dev)
 	}
 
 	bus->primary = dev->bus->number;
-	bus->subordinate = busrange[1];
+	pci_bus_insert_busn_res(bus, busrange[0], busrange[1]);
 	bus->bridge_ctl = 0;
 
 	/* parse ranges property */
diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index afd4f051f3f2..bdc499c17872 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -720,6 +720,33 @@ static int powerpc_debugfs_init(void)
 arch_initcall(powerpc_debugfs_init);
 #endif
 
+#ifdef CONFIG_BOOKE_WDT
+extern u32 booke_wdt_enabled;
+extern u32 booke_wdt_period;
+
+/* Checks wdt=x and wdt_period=xx command-line option */
+notrace int __init early_parse_wdt(char *p)
+{
+	if (p && strncmp(p, "0", 1) != 0)
+		booke_wdt_enabled = 1;
+
+	return 0;
+}
+early_param("wdt", early_parse_wdt);
+
+int __init early_parse_wdt_period(char *p)
+{
+	unsigned long ret;
+	if (p) {
+		if (!kstrtol(p, 0, &ret))
+			booke_wdt_period = ret;
+	}
+
+	return 0;
+}
+early_param("wdt_period", early_parse_wdt_period);
+#endif	/* CONFIG_BOOKE_WDT */
+
 void ppc_printk_progress(char *s, unsigned short hex)
 {
 	pr_info("%s\n", s);
diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c
index ec8a53fa9e8f..a8f54ecb091f 100644
--- a/arch/powerpc/kernel/setup_32.c
+++ b/arch/powerpc/kernel/setup_32.c
@@ -149,30 +149,6 @@ notrace void __init machine_init(u64 dt_ptr)
 		ppc_md.progress("id mach(): done", 0x200);
 }
 
-#ifdef CONFIG_BOOKE_WDT
-extern u32 booke_wdt_enabled;
-extern u32 booke_wdt_period;
-
-/* Checks wdt=x and wdt_period=xx command-line option */
-notrace int __init early_parse_wdt(char *p)
-{
-	if (p && strncmp(p, "0", 1) != 0)
-	       booke_wdt_enabled = 1;
-
-	return 0;
-}
-early_param("wdt", early_parse_wdt);
-
-int __init early_parse_wdt_period (char *p)
-{
-	if (p)
-		booke_wdt_period = simple_strtoul(p, NULL, 0);
-
-	return 0;
-}
-early_param("wdt_period", early_parse_wdt_period);
-#endif	/* CONFIG_BOOKE_WDT */
-
 /* Checks "l2cr=xxxx" command-line option */
 int __init ppc_setup_l2cr(char *str)
 {
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index e4cb34322de4..0321007086f7 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -48,6 +48,7 @@
 #ifdef CONFIG_PPC64
 #include <asm/paca.h>
 #endif
+#include <asm/vdso.h>
 #include <asm/debug.h>
 
 #ifdef DEBUG
@@ -570,8 +571,9 @@ void __devinit start_secondary(void *unused)
 #ifdef CONFIG_PPC64
 	if (system_state == SYSTEM_RUNNING)
 		vdso_data->processorCount++;
+
+	vdso_getcpu_init();
 #endif
-	ipi_call_lock();
 	notify_cpu_starting(cpu);
 	set_cpu_online(cpu, true);
 	/* Update sibling maps */
@@ -601,7 +603,6 @@ void __devinit start_secondary(void *unused)
 		of_node_put(np);
 	}
 	of_node_put(l2_cache);
-	ipi_call_unlock();
 
 	local_irq_enable();
 
diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c
index 9eb5b9b536a7..b67db22e102d 100644
--- a/arch/powerpc/kernel/vdso.c
+++ b/arch/powerpc/kernel/vdso.c
@@ -706,6 +706,34 @@ static void __init vdso_setup_syscall_map(void)
 	}
 }
 
+#ifdef CONFIG_PPC64
+int __cpuinit vdso_getcpu_init(void)
+{
+	unsigned long cpu, node, val;
+
+	/*
+	 * SPRG3 contains the CPU in the bottom 16 bits and the NUMA node in
+	 * the next 16 bits. The VDSO uses this to implement getcpu().
+	 */
+	cpu = get_cpu();
+	WARN_ON_ONCE(cpu > 0xffff);
+
+	node = cpu_to_node(cpu);
+	WARN_ON_ONCE(node > 0xffff);
+
+	val = (cpu & 0xfff) | ((node & 0xffff) << 16);
+	mtspr(SPRN_SPRG3, val);
+#ifdef CONFIG_KVM_BOOK3S_HANDLER
+	get_paca()->kvm_hstate.sprg3 = val;
+#endif
+
+	put_cpu();
+
+	return 0;
+}
+/* We need to call this before SMP init */
+early_initcall(vdso_getcpu_init);
+#endif
 
 static int __init vdso_init(void)
 {
diff --git a/arch/powerpc/kernel/vdso32/Makefile b/arch/powerpc/kernel/vdso32/Makefile
index 9a7946c41738..53e6c9b979ec 100644
--- a/arch/powerpc/kernel/vdso32/Makefile
+++ b/arch/powerpc/kernel/vdso32/Makefile
@@ -1,7 +1,9 @@
 
 # List of files in the vdso, has to be asm only for now
 
-obj-vdso32 = sigtramp.o gettimeofday.o datapage.o cacheflush.o note.o
+obj-vdso32-$(CONFIG_PPC64) = getcpu.o
+obj-vdso32 = sigtramp.o gettimeofday.o datapage.o cacheflush.o note.o \
+		$(obj-vdso32-y)
 
 # Build rules
 
diff --git a/arch/powerpc/kernel/vdso32/getcpu.S b/arch/powerpc/kernel/vdso32/getcpu.S
new file mode 100644
index 000000000000..47afd08c90f7
--- /dev/null
+++ b/arch/powerpc/kernel/vdso32/getcpu.S
@@ -0,0 +1,45 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ * Copyright (C) IBM Corporation, 2012
+ *
+ * Author: Anton Blanchard <anton@au.ibm.com>
+ */
+#include <asm/ppc_asm.h>
+#include <asm/vdso.h>
+
+	.text
+/*
+ * Exact prototype of getcpu
+ *
+ * int __kernel_getcpu(unsigned *cpu, unsigned *node);
+ *
+ */
+V_FUNCTION_BEGIN(__kernel_getcpu)
+  .cfi_startproc
+	mfspr	r5,SPRN_USPRG3
+	cmpdi	cr0,r3,0
+	cmpdi	cr1,r4,0
+	clrlwi  r6,r5,16
+	rlwinm  r7,r5,16,31-15,31-0
+	beq	cr0,1f
+	stw	r6,0(r3)
+1:	beq	cr1,2f
+	stw	r7,0(r4)
+2:	crclr	cr0*4+so
+	li	r3,0			/* always success */
+	blr
+  .cfi_endproc
+V_FUNCTION_END(__kernel_getcpu)
diff --git a/arch/powerpc/kernel/vdso32/vdso32.lds.S b/arch/powerpc/kernel/vdso32/vdso32.lds.S
index 0546bcd49cd0..43200ba2e570 100644
--- a/arch/powerpc/kernel/vdso32/vdso32.lds.S
+++ b/arch/powerpc/kernel/vdso32/vdso32.lds.S
@@ -147,6 +147,9 @@ VERSION
 		__kernel_sync_dicache_p5;
 		__kernel_sigtramp32;
 		__kernel_sigtramp_rt32;
+#ifdef CONFIG_PPC64
+		__kernel_getcpu;
+#endif
 
 	local: *;
 	};
diff --git a/arch/powerpc/kernel/vdso64/Makefile b/arch/powerpc/kernel/vdso64/Makefile
index 8c500d8622e4..effca9404b17 100644
--- a/arch/powerpc/kernel/vdso64/Makefile
+++ b/arch/powerpc/kernel/vdso64/Makefile
@@ -1,6 +1,6 @@
 # List of files in the vdso, has to be asm only for now
 
-obj-vdso64 = sigtramp.o gettimeofday.o datapage.o cacheflush.o note.o
+obj-vdso64 = sigtramp.o gettimeofday.o datapage.o cacheflush.o note.o getcpu.o
 
 # Build rules
 
diff --git a/arch/powerpc/kernel/vdso64/getcpu.S b/arch/powerpc/kernel/vdso64/getcpu.S
new file mode 100644
index 000000000000..47afd08c90f7
--- /dev/null
+++ b/arch/powerpc/kernel/vdso64/getcpu.S
@@ -0,0 +1,45 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ * Copyright (C) IBM Corporation, 2012
+ *
+ * Author: Anton Blanchard <anton@au.ibm.com>
+ */
+#include <asm/ppc_asm.h>
+#include <asm/vdso.h>
+
+	.text
+/*
+ * Exact prototype of getcpu
+ *
+ * int __kernel_getcpu(unsigned *cpu, unsigned *node);
+ *
+ */
+V_FUNCTION_BEGIN(__kernel_getcpu)
+  .cfi_startproc
+	mfspr	r5,SPRN_USPRG3
+	cmpdi	cr0,r3,0
+	cmpdi	cr1,r4,0
+	clrlwi  r6,r5,16
+	rlwinm  r7,r5,16,31-15,31-0
+	beq	cr0,1f
+	stw	r6,0(r3)
+1:	beq	cr1,2f
+	stw	r7,0(r4)
+2:	crclr	cr0*4+so
+	li	r3,0			/* always success */
+	blr
+  .cfi_endproc
+V_FUNCTION_END(__kernel_getcpu)
diff --git a/arch/powerpc/kernel/vdso64/vdso64.lds.S b/arch/powerpc/kernel/vdso64/vdso64.lds.S
index 0e615404e247..e6c1758f3588 100644
--- a/arch/powerpc/kernel/vdso64/vdso64.lds.S
+++ b/arch/powerpc/kernel/vdso64/vdso64.lds.S
@@ -146,6 +146,7 @@ VERSION
 		__kernel_sync_dicache;
 		__kernel_sync_dicache_p5;
 		__kernel_sigtramp_rt64;
+		__kernel_getcpu;
 
 	local: *;
 	};
diff --git a/arch/powerpc/kernel/vio.c b/arch/powerpc/kernel/vio.c
index 63f72ede4341..3052a931f2b5 100644
--- a/arch/powerpc/kernel/vio.c
+++ b/arch/powerpc/kernel/vio.c
@@ -37,8 +37,6 @@
 #include <asm/page.h>
 #include <asm/hvcall.h>
 
-static struct bus_type vio_bus_type;
-
 static struct vio_dev vio_bus_device  = { /* fake "parent" device */
 	.name = "vio",
 	.type = "",
@@ -625,7 +623,7 @@ struct dma_map_ops vio_dma_mapping_ops = {
  * vio_cmo_set_dev_desired - Set desired entitlement for a device
  *
  * @viodev: struct vio_dev for device to alter
- * @new_desired: new desired entitlement level in bytes
+ * @desired: new desired entitlement level in bytes
  *
  * For use by devices to request a change to their entitlement at runtime or
  * through sysfs.  The desired entitlement level is changed and a balancing
@@ -1262,7 +1260,7 @@ static int vio_bus_remove(struct device *dev)
 
 /**
  * vio_register_driver: - Register a new vio driver
- * @drv:	The vio_driver structure to be registered.
+ * @viodrv:	The vio_driver structure to be registered.
  */
 int __vio_register_driver(struct vio_driver *viodrv, struct module *owner,
 			  const char *mod_name)
@@ -1282,7 +1280,7 @@ EXPORT_SYMBOL(__vio_register_driver);
 
 /**
  * vio_unregister_driver - Remove registration of vio driver.
- * @driver:	The vio_driver struct to be removed form registration
+ * @viodrv:	The vio_driver struct to be removed form registration
  */
 void vio_unregister_driver(struct vio_driver *viodrv)
 {
@@ -1396,21 +1394,27 @@ struct vio_dev *vio_register_device_node(struct device_node *of_node)
 	viodev->name = of_node->name;
 	viodev->dev.of_node = of_node_get(of_node);
 
-	if (firmware_has_feature(FW_FEATURE_CMO))
-		vio_cmo_set_dma_ops(viodev);
-	else
-		set_dma_ops(&viodev->dev, &dma_iommu_ops);
-	set_iommu_table_base(&viodev->dev, vio_build_iommu_table(viodev));
 	set_dev_node(&viodev->dev, of_node_to_nid(of_node));
 
 	/* init generic 'struct device' fields: */
 	viodev->dev.parent = &vio_bus_device.dev;
 	viodev->dev.bus = &vio_bus_type;
 	viodev->dev.release = vio_dev_release;
-        /* needed to ensure proper operation of coherent allocations
-         * later, in case driver doesn't set it explicitly */
-        dma_set_mask(&viodev->dev, DMA_BIT_MASK(64));
-        dma_set_coherent_mask(&viodev->dev, DMA_BIT_MASK(64));
+
+	if (of_get_property(viodev->dev.of_node, "ibm,my-dma-window", NULL)) {
+		if (firmware_has_feature(FW_FEATURE_CMO))
+			vio_cmo_set_dma_ops(viodev);
+		else
+			set_dma_ops(&viodev->dev, &dma_iommu_ops);
+
+		set_iommu_table_base(&viodev->dev,
+				     vio_build_iommu_table(viodev));
+
+		/* needed to ensure proper operation of coherent allocations
+		 * later, in case driver doesn't set it explicitly */
+		dma_set_mask(&viodev->dev, DMA_BIT_MASK(64));
+		dma_set_coherent_mask(&viodev->dev, DMA_BIT_MASK(64));
+	}
 
 	/* register with generic device framework */
 	if (device_register(&viodev->dev)) {
@@ -1490,12 +1494,18 @@ static int __init vio_bus_init(void)
 	if (firmware_has_feature(FW_FEATURE_CMO))
 		vio_cmo_bus_init();
 
+	return 0;
+}
+postcore_initcall(vio_bus_init);
+
+static int __init vio_device_init(void)
+{
 	vio_bus_scan_register_devices("vdevice");
 	vio_bus_scan_register_devices("ibm,platform-facilities");
 
 	return 0;
 }
-__initcall(vio_bus_init);
+device_initcall(vio_device_init);
 
 static ssize_t name_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
@@ -1567,7 +1577,7 @@ static int vio_hotplug(struct device *dev, struct kobj_uevent_env *env)
 	return 0;
 }
 
-static struct bus_type vio_bus_type = {
+struct bus_type vio_bus_type = {
 	.name = "vio",
 	.dev_attrs = vio_dev_attrs,
 	.uevent = vio_hotplug,
diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index 80a577517584..d03eb6f7b058 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -37,56 +37,121 @@
 /* POWER7 has 10-bit LPIDs, PPC970 has 6-bit LPIDs */
 #define MAX_LPID_970	63
 
-long kvmppc_alloc_hpt(struct kvm *kvm)
+/* Power architecture requires HPT is at least 256kB */
+#define PPC_MIN_HPT_ORDER	18
+
+long kvmppc_alloc_hpt(struct kvm *kvm, u32 *htab_orderp)
 {
 	unsigned long hpt;
-	long lpid;
 	struct revmap_entry *rev;
 	struct kvmppc_linear_info *li;
+	long order = kvm_hpt_order;
 
-	/* Allocate guest's hashed page table */
-	li = kvm_alloc_hpt();
-	if (li) {
-		/* using preallocated memory */
-		hpt = (ulong)li->base_virt;
-		kvm->arch.hpt_li = li;
-	} else {
-		/* using dynamic memory */
+	if (htab_orderp) {
+		order = *htab_orderp;
+		if (order < PPC_MIN_HPT_ORDER)
+			order = PPC_MIN_HPT_ORDER;
+	}
+
+	/*
+	 * If the user wants a different size from default,
+	 * try first to allocate it from the kernel page allocator.
+	 */
+	hpt = 0;
+	if (order != kvm_hpt_order) {
 		hpt = __get_free_pages(GFP_KERNEL|__GFP_ZERO|__GFP_REPEAT|
-				       __GFP_NOWARN, HPT_ORDER - PAGE_SHIFT);
+				       __GFP_NOWARN, order - PAGE_SHIFT);
+		if (!hpt)
+			--order;
 	}
 
+	/* Next try to allocate from the preallocated pool */
 	if (!hpt) {
-		pr_err("kvm_alloc_hpt: Couldn't alloc HPT\n");
-		return -ENOMEM;
+		li = kvm_alloc_hpt();
+		if (li) {
+			hpt = (ulong)li->base_virt;
+			kvm->arch.hpt_li = li;
+			order = kvm_hpt_order;
+		}
 	}
+
+	/* Lastly try successively smaller sizes from the page allocator */
+	while (!hpt && order > PPC_MIN_HPT_ORDER) {
+		hpt = __get_free_pages(GFP_KERNEL|__GFP_ZERO|__GFP_REPEAT|
+				       __GFP_NOWARN, order - PAGE_SHIFT);
+		if (!hpt)
+			--order;
+	}
+
+	if (!hpt)
+		return -ENOMEM;
+
 	kvm->arch.hpt_virt = hpt;
+	kvm->arch.hpt_order = order;
+	/* HPTEs are 2**4 bytes long */
+	kvm->arch.hpt_npte = 1ul << (order - 4);
+	/* 128 (2**7) bytes in each HPTEG */
+	kvm->arch.hpt_mask = (1ul << (order - 7)) - 1;
 
 	/* Allocate reverse map array */
-	rev = vmalloc(sizeof(struct revmap_entry) * HPT_NPTE);
+	rev = vmalloc(sizeof(struct revmap_entry) * kvm->arch.hpt_npte);
 	if (!rev) {
 		pr_err("kvmppc_alloc_hpt: Couldn't alloc reverse map array\n");
 		goto out_freehpt;
 	}
 	kvm->arch.revmap = rev;
+	kvm->arch.sdr1 = __pa(hpt) | (order - 18);
 
-	lpid = kvmppc_alloc_lpid();
-	if (lpid < 0)
-		goto out_freeboth;
+	pr_info("KVM guest htab at %lx (order %ld), LPID %x\n",
+		hpt, order, kvm->arch.lpid);
 
-	kvm->arch.sdr1 = __pa(hpt) | (HPT_ORDER - 18);
-	kvm->arch.lpid = lpid;
-
-	pr_info("KVM guest htab at %lx, LPID %lx\n", hpt, lpid);
+	if (htab_orderp)
+		*htab_orderp = order;
 	return 0;
 
- out_freeboth:
-	vfree(rev);
  out_freehpt:
-	free_pages(hpt, HPT_ORDER - PAGE_SHIFT);
+	if (kvm->arch.hpt_li)
+		kvm_release_hpt(kvm->arch.hpt_li);
+	else
+		free_pages(hpt, order - PAGE_SHIFT);
 	return -ENOMEM;
 }
 
+long kvmppc_alloc_reset_hpt(struct kvm *kvm, u32 *htab_orderp)
+{
+	long err = -EBUSY;
+	long order;
+
+	mutex_lock(&kvm->lock);
+	if (kvm->arch.rma_setup_done) {
+		kvm->arch.rma_setup_done = 0;
+		/* order rma_setup_done vs. vcpus_running */
+		smp_mb();
+		if (atomic_read(&kvm->arch.vcpus_running)) {
+			kvm->arch.rma_setup_done = 1;
+			goto out;
+		}
+	}
+	if (kvm->arch.hpt_virt) {
+		order = kvm->arch.hpt_order;
+		/* Set the entire HPT to 0, i.e. invalid HPTEs */
+		memset((void *)kvm->arch.hpt_virt, 0, 1ul << order);
+		/*
+		 * Set the whole last_vcpu array to an invalid vcpu number.
+		 * This ensures that each vcpu will flush its TLB on next entry.
+		 */
+		memset(kvm->arch.last_vcpu, 0xff, sizeof(kvm->arch.last_vcpu));
+		*htab_orderp = order;
+		err = 0;
+	} else {
+		err = kvmppc_alloc_hpt(kvm, htab_orderp);
+		order = *htab_orderp;
+	}
+ out:
+	mutex_unlock(&kvm->lock);
+	return err;
+}
+
 void kvmppc_free_hpt(struct kvm *kvm)
 {
 	kvmppc_free_lpid(kvm->arch.lpid);
@@ -94,7 +159,8 @@ void kvmppc_free_hpt(struct kvm *kvm)
 	if (kvm->arch.hpt_li)
 		kvm_release_hpt(kvm->arch.hpt_li);
 	else
-		free_pages(kvm->arch.hpt_virt, HPT_ORDER - PAGE_SHIFT);
+		free_pages(kvm->arch.hpt_virt,
+			   kvm->arch.hpt_order - PAGE_SHIFT);
 }
 
 /* Bits in first HPTE dword for pagesize 4k, 64k or 16M */
@@ -119,6 +185,7 @@ void kvmppc_map_vrma(struct kvm_vcpu *vcpu, struct kvm_memory_slot *memslot,
 	unsigned long psize;
 	unsigned long hp0, hp1;
 	long ret;
+	struct kvm *kvm = vcpu->kvm;
 
 	psize = 1ul << porder;
 	npages = memslot->npages >> (porder - PAGE_SHIFT);
@@ -127,8 +194,8 @@ void kvmppc_map_vrma(struct kvm_vcpu *vcpu, struct kvm_memory_slot *memslot,
 	if (npages > 1ul << (40 - porder))
 		npages = 1ul << (40 - porder);
 	/* Can't use more than 1 HPTE per HPTEG */
-	if (npages > HPT_NPTEG)
-		npages = HPT_NPTEG;
+	if (npages > kvm->arch.hpt_mask + 1)
+		npages = kvm->arch.hpt_mask + 1;
 
 	hp0 = HPTE_V_1TB_SEG | (VRMA_VSID << (40 - 16)) |
 		HPTE_V_BOLTED | hpte0_pgsize_encoding(psize);
@@ -138,7 +205,7 @@ void kvmppc_map_vrma(struct kvm_vcpu *vcpu, struct kvm_memory_slot *memslot,
 	for (i = 0; i < npages; ++i) {
 		addr = i << porder;
 		/* can't use hpt_hash since va > 64 bits */
-		hash = (i ^ (VRMA_VSID ^ (VRMA_VSID << 25))) & HPT_HASH_MASK;
+		hash = (i ^ (VRMA_VSID ^ (VRMA_VSID << 25))) & kvm->arch.hpt_mask;
 		/*
 		 * We assume that the hash table is empty and no
 		 * vcpus are using it at this stage.  Since we create
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 3abe1b86e583..83e929e66f9d 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -56,7 +56,7 @@
 /* #define EXIT_DEBUG_INT */
 
 static void kvmppc_end_cede(struct kvm_vcpu *vcpu);
-static int kvmppc_hv_setup_rma(struct kvm_vcpu *vcpu);
+static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu);
 
 void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
@@ -1104,11 +1104,15 @@ int kvmppc_vcpu_run(struct kvm_run *run, struct kvm_vcpu *vcpu)
 		return -EINTR;
 	}
 
-	/* On the first time here, set up VRMA or RMA */
+	atomic_inc(&vcpu->kvm->arch.vcpus_running);
+	/* Order vcpus_running vs. rma_setup_done, see kvmppc_alloc_reset_hpt */
+	smp_mb();
+
+	/* On the first time here, set up HTAB and VRMA or RMA */
 	if (!vcpu->kvm->arch.rma_setup_done) {
-		r = kvmppc_hv_setup_rma(vcpu);
+		r = kvmppc_hv_setup_htab_rma(vcpu);
 		if (r)
-			return r;
+			goto out;
 	}
 
 	flush_fp_to_thread(current);
@@ -1126,6 +1130,9 @@ int kvmppc_vcpu_run(struct kvm_run *run, struct kvm_vcpu *vcpu)
 			kvmppc_core_prepare_to_enter(vcpu);
 		}
 	} while (r == RESUME_GUEST);
+
+ out:
+	atomic_dec(&vcpu->kvm->arch.vcpus_running);
 	return r;
 }
 
@@ -1341,7 +1348,7 @@ void kvmppc_core_commit_memory_region(struct kvm *kvm,
 {
 }
 
-static int kvmppc_hv_setup_rma(struct kvm_vcpu *vcpu)
+static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
 {
 	int err = 0;
 	struct kvm *kvm = vcpu->kvm;
@@ -1360,6 +1367,15 @@ static int kvmppc_hv_setup_rma(struct kvm_vcpu *vcpu)
 	if (kvm->arch.rma_setup_done)
 		goto out;	/* another vcpu beat us to it */
 
+	/* Allocate hashed page table (if not done already) and reset it */
+	if (!kvm->arch.hpt_virt) {
+		err = kvmppc_alloc_hpt(kvm, NULL);
+		if (err) {
+			pr_err("KVM: Couldn't alloc HPT\n");
+			goto out;
+		}
+	}
+
 	/* Look up the memslot for guest physical address 0 */
 	memslot = gfn_to_memslot(kvm, 0);
 
@@ -1471,13 +1487,14 @@ static int kvmppc_hv_setup_rma(struct kvm_vcpu *vcpu)
 
 int kvmppc_core_init_vm(struct kvm *kvm)
 {
-	long r;
-	unsigned long lpcr;
+	unsigned long lpcr, lpid;
 
-	/* Allocate hashed page table */
-	r = kvmppc_alloc_hpt(kvm);
-	if (r)
-		return r;
+	/* Allocate the guest's logical partition ID */
+
+	lpid = kvmppc_alloc_lpid();
+	if (lpid < 0)
+		return -ENOMEM;
+	kvm->arch.lpid = lpid;
 
 	INIT_LIST_HEAD(&kvm->arch.spapr_tce_tables);
 
@@ -1487,7 +1504,6 @@ int kvmppc_core_init_vm(struct kvm *kvm)
 
 	if (cpu_has_feature(CPU_FTR_ARCH_201)) {
 		/* PPC970; HID4 is effectively the LPCR */
-		unsigned long lpid = kvm->arch.lpid;
 		kvm->arch.host_lpid = 0;
 		kvm->arch.host_lpcr = lpcr = mfspr(SPRN_HID4);
 		lpcr &= ~((3 << HID4_LPID1_SH) | (0xful << HID4_LPID5_SH));
diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c
index e1b60f56f2a1..fb4eac290fef 100644
--- a/arch/powerpc/kvm/book3s_hv_builtin.c
+++ b/arch/powerpc/kvm/book3s_hv_builtin.c
@@ -25,6 +25,9 @@ static void __init kvm_linear_init_one(ulong size, int count, int type);
 static struct kvmppc_linear_info *kvm_alloc_linear(int type);
 static void kvm_release_linear(struct kvmppc_linear_info *ri);
 
+int kvm_hpt_order = KVM_DEFAULT_HPT_ORDER;
+EXPORT_SYMBOL_GPL(kvm_hpt_order);
+
 /*************** RMA *************/
 
 /*
@@ -209,7 +212,7 @@ static void kvm_release_linear(struct kvmppc_linear_info *ri)
 void __init kvm_linear_init(void)
 {
 	/* HPT */
-	kvm_linear_init_one(1 << HPT_ORDER, kvm_hpt_count, KVM_LINEAR_HPT);
+	kvm_linear_init_one(1 << kvm_hpt_order, kvm_hpt_count, KVM_LINEAR_HPT);
 
 	/* RMA */
 	/* Only do this on PPC970 in HV mode */
diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
index cec4daddbf31..5c70d19494f9 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
@@ -237,7 +237,7 @@ long kvmppc_h_enter(struct kvm_vcpu *vcpu, unsigned long flags,
 
 	/* Find and lock the HPTEG slot to use */
  do_insert:
-	if (pte_index >= HPT_NPTE)
+	if (pte_index >= kvm->arch.hpt_npte)
 		return H_PARAMETER;
 	if (likely((flags & H_EXACT) == 0)) {
 		pte_index &= ~7UL;
@@ -352,7 +352,7 @@ long kvmppc_h_remove(struct kvm_vcpu *vcpu, unsigned long flags,
 	unsigned long v, r, rb;
 	struct revmap_entry *rev;
 
-	if (pte_index >= HPT_NPTE)
+	if (pte_index >= kvm->arch.hpt_npte)
 		return H_PARAMETER;
 	hpte = (unsigned long *)(kvm->arch.hpt_virt + (pte_index << 4));
 	while (!try_lock_hpte(hpte, HPTE_V_HVLOCK))
@@ -419,7 +419,8 @@ long kvmppc_h_bulk_remove(struct kvm_vcpu *vcpu)
 				i = 4;
 				break;
 			}
-			if (req != 1 || flags == 3 || pte_index >= HPT_NPTE) {
+			if (req != 1 || flags == 3 ||
+			    pte_index >= kvm->arch.hpt_npte) {
 				/* parameter error */
 				args[j] = ((0xa0 | flags) << 56) + pte_index;
 				ret = H_PARAMETER;
@@ -521,7 +522,7 @@ long kvmppc_h_protect(struct kvm_vcpu *vcpu, unsigned long flags,
 	struct revmap_entry *rev;
 	unsigned long v, r, rb, mask, bits;
 
-	if (pte_index >= HPT_NPTE)
+	if (pte_index >= kvm->arch.hpt_npte)
 		return H_PARAMETER;
 
 	hpte = (unsigned long *)(kvm->arch.hpt_virt + (pte_index << 4));
@@ -583,7 +584,7 @@ long kvmppc_h_read(struct kvm_vcpu *vcpu, unsigned long flags,
 	int i, n = 1;
 	struct revmap_entry *rev = NULL;
 
-	if (pte_index >= HPT_NPTE)
+	if (pte_index >= kvm->arch.hpt_npte)
 		return H_PARAMETER;
 	if (flags & H_READ_4) {
 		pte_index &= ~3;
@@ -678,7 +679,7 @@ long kvmppc_hv_find_lock_hpte(struct kvm *kvm, gva_t eaddr, unsigned long slb_v,
 		somask = (1UL << 28) - 1;
 		vsid = (slb_v & ~SLB_VSID_B) >> SLB_VSID_SHIFT;
 	}
-	hash = (vsid ^ ((eaddr & somask) >> pshift)) & HPT_HASH_MASK;
+	hash = (vsid ^ ((eaddr & somask) >> pshift)) & kvm->arch.hpt_mask;
 	avpn = slb_v & ~(somask >> 16);	/* also includes B */
 	avpn |= (eaddr & somask) >> 16;
 
@@ -723,7 +724,7 @@ long kvmppc_hv_find_lock_hpte(struct kvm *kvm, gva_t eaddr, unsigned long slb_v,
 		if (val & HPTE_V_SECONDARY)
 			break;
 		val |= HPTE_V_SECONDARY;
-		hash = hash ^ HPT_HASH_MASK;
+		hash = hash ^ kvm->arch.hpt_mask;
 	}
 	return -1;
 }
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index a1044f43becd..5a84c8d3d040 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -72,9 +72,6 @@ _GLOBAL(kvmppc_hv_entry_trampoline)
 	mtsrr1	r6
 	RFI
 
-#define ULONG_SIZE 		8
-#define VCPU_GPR(n)		(VCPU_GPRS + (n * ULONG_SIZE))
-
 /******************************************************************************
  *                                                                            *
  *                               Entry code                                   *
@@ -206,24 +203,24 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
 	/* Load up FP, VMX and VSX registers */
 	bl	kvmppc_load_fp
 
-	ld	r14, VCPU_GPR(r14)(r4)
-	ld	r15, VCPU_GPR(r15)(r4)
-	ld	r16, VCPU_GPR(r16)(r4)
-	ld	r17, VCPU_GPR(r17)(r4)
-	ld	r18, VCPU_GPR(r18)(r4)
-	ld	r19, VCPU_GPR(r19)(r4)
-	ld	r20, VCPU_GPR(r20)(r4)
-	ld	r21, VCPU_GPR(r21)(r4)
-	ld	r22, VCPU_GPR(r22)(r4)
-	ld	r23, VCPU_GPR(r23)(r4)
-	ld	r24, VCPU_GPR(r24)(r4)
-	ld	r25, VCPU_GPR(r25)(r4)
-	ld	r26, VCPU_GPR(r26)(r4)
-	ld	r27, VCPU_GPR(r27)(r4)
-	ld	r28, VCPU_GPR(r28)(r4)
-	ld	r29, VCPU_GPR(r29)(r4)
-	ld	r30, VCPU_GPR(r30)(r4)
-	ld	r31, VCPU_GPR(r31)(r4)
+	ld	r14, VCPU_GPR(R14)(r4)
+	ld	r15, VCPU_GPR(R15)(r4)
+	ld	r16, VCPU_GPR(R16)(r4)
+	ld	r17, VCPU_GPR(R17)(r4)
+	ld	r18, VCPU_GPR(R18)(r4)
+	ld	r19, VCPU_GPR(R19)(r4)
+	ld	r20, VCPU_GPR(R20)(r4)
+	ld	r21, VCPU_GPR(R21)(r4)
+	ld	r22, VCPU_GPR(R22)(r4)
+	ld	r23, VCPU_GPR(R23)(r4)
+	ld	r24, VCPU_GPR(R24)(r4)
+	ld	r25, VCPU_GPR(R25)(r4)
+	ld	r26, VCPU_GPR(R26)(r4)
+	ld	r27, VCPU_GPR(R27)(r4)
+	ld	r28, VCPU_GPR(R28)(r4)
+	ld	r29, VCPU_GPR(R29)(r4)
+	ld	r30, VCPU_GPR(R30)(r4)
+	ld	r31, VCPU_GPR(R31)(r4)
 
 BEGIN_FTR_SECTION
 	/* Switch DSCR to guest value */
@@ -547,21 +544,21 @@ fast_guest_return:
 	mtlr	r5
 	mtcr	r6
 
-	ld	r0, VCPU_GPR(r0)(r4)
-	ld	r1, VCPU_GPR(r1)(r4)
-	ld	r2, VCPU_GPR(r2)(r4)
-	ld	r3, VCPU_GPR(r3)(r4)
-	ld	r5, VCPU_GPR(r5)(r4)
-	ld	r6, VCPU_GPR(r6)(r4)
-	ld	r7, VCPU_GPR(r7)(r4)
-	ld	r8, VCPU_GPR(r8)(r4)
-	ld	r9, VCPU_GPR(r9)(r4)
-	ld	r10, VCPU_GPR(r10)(r4)
-	ld	r11, VCPU_GPR(r11)(r4)
-	ld	r12, VCPU_GPR(r12)(r4)
-	ld	r13, VCPU_GPR(r13)(r4)
-
-	ld	r4, VCPU_GPR(r4)(r4)
+	ld	r0, VCPU_GPR(R0)(r4)
+	ld	r1, VCPU_GPR(R1)(r4)
+	ld	r2, VCPU_GPR(R2)(r4)
+	ld	r3, VCPU_GPR(R3)(r4)
+	ld	r5, VCPU_GPR(R5)(r4)
+	ld	r6, VCPU_GPR(R6)(r4)
+	ld	r7, VCPU_GPR(R7)(r4)
+	ld	r8, VCPU_GPR(R8)(r4)
+	ld	r9, VCPU_GPR(R9)(r4)
+	ld	r10, VCPU_GPR(R10)(r4)
+	ld	r11, VCPU_GPR(R11)(r4)
+	ld	r12, VCPU_GPR(R12)(r4)
+	ld	r13, VCPU_GPR(R13)(r4)
+
+	ld	r4, VCPU_GPR(R4)(r4)
 
 	hrfid
 	b	.
@@ -590,22 +587,22 @@ kvmppc_interrupt:
 
 	/* Save registers */
 
-	std	r0, VCPU_GPR(r0)(r9)
-	std	r1, VCPU_GPR(r1)(r9)
-	std	r2, VCPU_GPR(r2)(r9)
-	std	r3, VCPU_GPR(r3)(r9)
-	std	r4, VCPU_GPR(r4)(r9)
-	std	r5, VCPU_GPR(r5)(r9)
-	std	r6, VCPU_GPR(r6)(r9)
-	std	r7, VCPU_GPR(r7)(r9)
-	std	r8, VCPU_GPR(r8)(r9)
+	std	r0, VCPU_GPR(R0)(r9)
+	std	r1, VCPU_GPR(R1)(r9)
+	std	r2, VCPU_GPR(R2)(r9)
+	std	r3, VCPU_GPR(R3)(r9)
+	std	r4, VCPU_GPR(R4)(r9)
+	std	r5, VCPU_GPR(R5)(r9)
+	std	r6, VCPU_GPR(R6)(r9)
+	std	r7, VCPU_GPR(R7)(r9)
+	std	r8, VCPU_GPR(R8)(r9)
 	ld	r0, HSTATE_HOST_R2(r13)
-	std	r0, VCPU_GPR(r9)(r9)
-	std	r10, VCPU_GPR(r10)(r9)
-	std	r11, VCPU_GPR(r11)(r9)
+	std	r0, VCPU_GPR(R9)(r9)
+	std	r10, VCPU_GPR(R10)(r9)
+	std	r11, VCPU_GPR(R11)(r9)
 	ld	r3, HSTATE_SCRATCH0(r13)
 	lwz	r4, HSTATE_SCRATCH1(r13)
-	std	r3, VCPU_GPR(r12)(r9)
+	std	r3, VCPU_GPR(R12)(r9)
 	stw	r4, VCPU_CR(r9)
 
 	/* Restore R1/R2 so we can handle faults */
@@ -626,7 +623,7 @@ kvmppc_interrupt:
 
 	GET_SCRATCH0(r3)
 	mflr	r4
-	std	r3, VCPU_GPR(r13)(r9)
+	std	r3, VCPU_GPR(R13)(r9)
 	std	r4, VCPU_LR(r9)
 
 	/* Unset guest mode */
@@ -968,24 +965,24 @@ BEGIN_FTR_SECTION
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
 
 	/* Save non-volatile GPRs */
-	std	r14, VCPU_GPR(r14)(r9)
-	std	r15, VCPU_GPR(r15)(r9)
-	std	r16, VCPU_GPR(r16)(r9)
-	std	r17, VCPU_GPR(r17)(r9)
-	std	r18, VCPU_GPR(r18)(r9)
-	std	r19, VCPU_GPR(r19)(r9)
-	std	r20, VCPU_GPR(r20)(r9)
-	std	r21, VCPU_GPR(r21)(r9)
-	std	r22, VCPU_GPR(r22)(r9)
-	std	r23, VCPU_GPR(r23)(r9)
-	std	r24, VCPU_GPR(r24)(r9)
-	std	r25, VCPU_GPR(r25)(r9)
-	std	r26, VCPU_GPR(r26)(r9)
-	std	r27, VCPU_GPR(r27)(r9)
-	std	r28, VCPU_GPR(r28)(r9)
-	std	r29, VCPU_GPR(r29)(r9)
-	std	r30, VCPU_GPR(r30)(r9)
-	std	r31, VCPU_GPR(r31)(r9)
+	std	r14, VCPU_GPR(R14)(r9)
+	std	r15, VCPU_GPR(R15)(r9)
+	std	r16, VCPU_GPR(R16)(r9)
+	std	r17, VCPU_GPR(R17)(r9)
+	std	r18, VCPU_GPR(R18)(r9)
+	std	r19, VCPU_GPR(R19)(r9)
+	std	r20, VCPU_GPR(R20)(r9)
+	std	r21, VCPU_GPR(R21)(r9)
+	std	r22, VCPU_GPR(R22)(r9)
+	std	r23, VCPU_GPR(R23)(r9)
+	std	r24, VCPU_GPR(R24)(r9)
+	std	r25, VCPU_GPR(R25)(r9)
+	std	r26, VCPU_GPR(R26)(r9)
+	std	r27, VCPU_GPR(R27)(r9)
+	std	r28, VCPU_GPR(R28)(r9)
+	std	r29, VCPU_GPR(R29)(r9)
+	std	r30, VCPU_GPR(R30)(r9)
+	std	r31, VCPU_GPR(R31)(r9)
 
 	/* Save SPRGs */
 	mfspr	r3, SPRN_SPRG0
@@ -1067,6 +1064,10 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
 	mtspr	SPRN_DABR,r5
 	mtspr	SPRN_DABRX,r6
 
+	/* Restore SPRG3 */
+	ld	r3,HSTATE_SPRG3(r13)
+	mtspr	SPRN_SPRG3,r3
+
 	/*
 	 * Reload DEC.  HDEC interrupts were disabled when
 	 * we reloaded the host's LPCR value.
@@ -1160,7 +1161,7 @@ kvmppc_hdsi:
 	andi.	r0, r11, MSR_DR		/* data relocation enabled? */
 	beq	3f
 	clrrdi	r0, r4, 28
-	PPC_SLBFEE_DOT(r5, r0)		/* if so, look up SLB */
+	PPC_SLBFEE_DOT(R5, R0)		/* if so, look up SLB */
 	bne	1f			/* if no SLB entry found */
 4:	std	r4, VCPU_FAULT_DAR(r9)
 	stw	r6, VCPU_FAULT_DSISR(r9)
@@ -1234,7 +1235,7 @@ kvmppc_hisi:
 	andi.	r0, r11, MSR_IR		/* instruction relocation enabled? */
 	beq	3f
 	clrrdi	r0, r10, 28
-	PPC_SLBFEE_DOT(r5, r0)		/* if so, look up SLB */
+	PPC_SLBFEE_DOT(R5, R0)		/* if so, look up SLB */
 	bne	1f			/* if no SLB entry found */
 4:
 	/* Search the hash table. */
@@ -1278,7 +1279,7 @@ kvmppc_hisi:
  */
 	.globl	hcall_try_real_mode
 hcall_try_real_mode:
-	ld	r3,VCPU_GPR(r3)(r9)
+	ld	r3,VCPU_GPR(R3)(r9)
 	andi.	r0,r11,MSR_PR
 	bne	hcall_real_cont
 	clrrdi	r3,r3,2
@@ -1291,12 +1292,12 @@ hcall_try_real_mode:
 	add	r3,r3,r4
 	mtctr	r3
 	mr	r3,r9		/* get vcpu pointer */
-	ld	r4,VCPU_GPR(r4)(r9)
+	ld	r4,VCPU_GPR(R4)(r9)
 	bctrl
 	cmpdi	r3,H_TOO_HARD
 	beq	hcall_real_fallback
 	ld	r4,HSTATE_KVM_VCPU(r13)
-	std	r3,VCPU_GPR(r3)(r4)
+	std	r3,VCPU_GPR(R3)(r4)
 	ld	r10,VCPU_PC(r4)
 	ld	r11,VCPU_MSR(r4)
 	b	fast_guest_return
@@ -1424,7 +1425,7 @@ _GLOBAL(kvmppc_h_cede)
 	li	r0,0		/* set trap to 0 to say hcall is handled */
 	stw	r0,VCPU_TRAP(r3)
 	li	r0,H_SUCCESS
-	std	r0,VCPU_GPR(r3)(r3)
+	std	r0,VCPU_GPR(R3)(r3)
 BEGIN_FTR_SECTION
 	b	2f		/* just send it up to host on 970 */
 END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_206)
@@ -1443,7 +1444,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_206)
 	addi	r6,r5,VCORE_NAPPING_THREADS
 31:	lwarx	r4,0,r6
 	or	r4,r4,r0
-	PPC_POPCNTW(r7,r4)
+	PPC_POPCNTW(R7,R4)
 	cmpw	r7,r8
 	bge	2f
 	stwcx.	r4,0,r6
@@ -1464,24 +1465,24 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_206)
  * DAR, DSISR, DABR, DABRX, DSCR, PMCx, MMCRx, SIAR, SDAR.
  */
 	/* Save non-volatile GPRs */
-	std	r14, VCPU_GPR(r14)(r3)
-	std	r15, VCPU_GPR(r15)(r3)
-	std	r16, VCPU_GPR(r16)(r3)
-	std	r17, VCPU_GPR(r17)(r3)
-	std	r18, VCPU_GPR(r18)(r3)
-	std	r19, VCPU_GPR(r19)(r3)
-	std	r20, VCPU_GPR(r20)(r3)
-	std	r21, VCPU_GPR(r21)(r3)
-	std	r22, VCPU_GPR(r22)(r3)
-	std	r23, VCPU_GPR(r23)(r3)
-	std	r24, VCPU_GPR(r24)(r3)
-	std	r25, VCPU_GPR(r25)(r3)
-	std	r26, VCPU_GPR(r26)(r3)
-	std	r27, VCPU_GPR(r27)(r3)
-	std	r28, VCPU_GPR(r28)(r3)
-	std	r29, VCPU_GPR(r29)(r3)
-	std	r30, VCPU_GPR(r30)(r3)
-	std	r31, VCPU_GPR(r31)(r3)
+	std	r14, VCPU_GPR(R14)(r3)
+	std	r15, VCPU_GPR(R15)(r3)
+	std	r16, VCPU_GPR(R16)(r3)
+	std	r17, VCPU_GPR(R17)(r3)
+	std	r18, VCPU_GPR(R18)(r3)
+	std	r19, VCPU_GPR(R19)(r3)
+	std	r20, VCPU_GPR(R20)(r3)
+	std	r21, VCPU_GPR(R21)(r3)
+	std	r22, VCPU_GPR(R22)(r3)
+	std	r23, VCPU_GPR(R23)(r3)
+	std	r24, VCPU_GPR(R24)(r3)
+	std	r25, VCPU_GPR(R25)(r3)
+	std	r26, VCPU_GPR(R26)(r3)
+	std	r27, VCPU_GPR(R27)(r3)
+	std	r28, VCPU_GPR(R28)(r3)
+	std	r29, VCPU_GPR(R29)(r3)
+	std	r30, VCPU_GPR(R30)(r3)
+	std	r31, VCPU_GPR(R31)(r3)
 
 	/* save FP state */
 	bl	.kvmppc_save_fp
@@ -1513,24 +1514,24 @@ kvm_end_cede:
 	bl	kvmppc_load_fp
 
 	/* Load NV GPRS */
-	ld	r14, VCPU_GPR(r14)(r4)
-	ld	r15, VCPU_GPR(r15)(r4)
-	ld	r16, VCPU_GPR(r16)(r4)
-	ld	r17, VCPU_GPR(r17)(r4)
-	ld	r18, VCPU_GPR(r18)(r4)
-	ld	r19, VCPU_GPR(r19)(r4)
-	ld	r20, VCPU_GPR(r20)(r4)
-	ld	r21, VCPU_GPR(r21)(r4)
-	ld	r22, VCPU_GPR(r22)(r4)
-	ld	r23, VCPU_GPR(r23)(r4)
-	ld	r24, VCPU_GPR(r24)(r4)
-	ld	r25, VCPU_GPR(r25)(r4)
-	ld	r26, VCPU_GPR(r26)(r4)
-	ld	r27, VCPU_GPR(r27)(r4)
-	ld	r28, VCPU_GPR(r28)(r4)
-	ld	r29, VCPU_GPR(r29)(r4)
-	ld	r30, VCPU_GPR(r30)(r4)
-	ld	r31, VCPU_GPR(r31)(r4)
+	ld	r14, VCPU_GPR(R14)(r4)
+	ld	r15, VCPU_GPR(R15)(r4)
+	ld	r16, VCPU_GPR(R16)(r4)
+	ld	r17, VCPU_GPR(R17)(r4)
+	ld	r18, VCPU_GPR(R18)(r4)
+	ld	r19, VCPU_GPR(R19)(r4)
+	ld	r20, VCPU_GPR(R20)(r4)
+	ld	r21, VCPU_GPR(R21)(r4)
+	ld	r22, VCPU_GPR(R22)(r4)
+	ld	r23, VCPU_GPR(R23)(r4)
+	ld	r24, VCPU_GPR(R24)(r4)
+	ld	r25, VCPU_GPR(R25)(r4)
+	ld	r26, VCPU_GPR(R26)(r4)
+	ld	r27, VCPU_GPR(R27)(r4)
+	ld	r28, VCPU_GPR(R28)(r4)
+	ld	r29, VCPU_GPR(R29)(r4)
+	ld	r30, VCPU_GPR(R30)(r4)
+	ld	r31, VCPU_GPR(R31)(r4)
 
 	/* clear our bit in vcore->napping_threads */
 33:	ld	r5,HSTATE_KVM_VCORE(r13)
@@ -1649,7 +1650,7 @@ BEGIN_FTR_SECTION
 	reg = 0
 	.rept	32
 	li	r6,reg*16+VCPU_VSRS
-	STXVD2X(reg,r6,r3)
+	STXVD2X(reg,R6,R3)
 	reg = reg + 1
 	.endr
 FTR_SECTION_ELSE
@@ -1711,7 +1712,7 @@ BEGIN_FTR_SECTION
 	reg = 0
 	.rept	32
 	li	r7,reg*16+VCPU_VSRS
-	LXVD2X(reg,r7,r4)
+	LXVD2X(reg,R7,R4)
 	reg = reg + 1
 	.endr
 FTR_SECTION_ELSE
diff --git a/arch/powerpc/kvm/book3s_interrupts.S b/arch/powerpc/kvm/book3s_interrupts.S
index 3e35383bdb21..48cbbf862958 100644
--- a/arch/powerpc/kvm/book3s_interrupts.S
+++ b/arch/powerpc/kvm/book3s_interrupts.S
@@ -25,38 +25,30 @@
 #include <asm/exception-64s.h>
 
 #if defined(CONFIG_PPC_BOOK3S_64)
-
-#define ULONG_SIZE 		8
 #define FUNC(name) 		GLUE(.,name)
-
 #elif defined(CONFIG_PPC_BOOK3S_32)
-
-#define ULONG_SIZE              4
 #define FUNC(name)		name
-
 #endif /* CONFIG_PPC_BOOK3S_XX */
 
-
-#define VCPU_GPR(n)		(VCPU_GPRS + (n * ULONG_SIZE))
 #define VCPU_LOAD_NVGPRS(vcpu) \
-	PPC_LL	r14, VCPU_GPR(r14)(vcpu); \
-	PPC_LL	r15, VCPU_GPR(r15)(vcpu); \
-	PPC_LL	r16, VCPU_GPR(r16)(vcpu); \
-	PPC_LL	r17, VCPU_GPR(r17)(vcpu); \
-	PPC_LL	r18, VCPU_GPR(r18)(vcpu); \
-	PPC_LL	r19, VCPU_GPR(r19)(vcpu); \
-	PPC_LL	r20, VCPU_GPR(r20)(vcpu); \
-	PPC_LL	r21, VCPU_GPR(r21)(vcpu); \
-	PPC_LL	r22, VCPU_GPR(r22)(vcpu); \
-	PPC_LL	r23, VCPU_GPR(r23)(vcpu); \
-	PPC_LL	r24, VCPU_GPR(r24)(vcpu); \
-	PPC_LL	r25, VCPU_GPR(r25)(vcpu); \
-	PPC_LL	r26, VCPU_GPR(r26)(vcpu); \
-	PPC_LL	r27, VCPU_GPR(r27)(vcpu); \
-	PPC_LL	r28, VCPU_GPR(r28)(vcpu); \
-	PPC_LL	r29, VCPU_GPR(r29)(vcpu); \
-	PPC_LL	r30, VCPU_GPR(r30)(vcpu); \
-	PPC_LL	r31, VCPU_GPR(r31)(vcpu); \
+	PPC_LL	r14, VCPU_GPR(R14)(vcpu); \
+	PPC_LL	r15, VCPU_GPR(R15)(vcpu); \
+	PPC_LL	r16, VCPU_GPR(R16)(vcpu); \
+	PPC_LL	r17, VCPU_GPR(R17)(vcpu); \
+	PPC_LL	r18, VCPU_GPR(R18)(vcpu); \
+	PPC_LL	r19, VCPU_GPR(R19)(vcpu); \
+	PPC_LL	r20, VCPU_GPR(R20)(vcpu); \
+	PPC_LL	r21, VCPU_GPR(R21)(vcpu); \
+	PPC_LL	r22, VCPU_GPR(R22)(vcpu); \
+	PPC_LL	r23, VCPU_GPR(R23)(vcpu); \
+	PPC_LL	r24, VCPU_GPR(R24)(vcpu); \
+	PPC_LL	r25, VCPU_GPR(R25)(vcpu); \
+	PPC_LL	r26, VCPU_GPR(R26)(vcpu); \
+	PPC_LL	r27, VCPU_GPR(R27)(vcpu); \
+	PPC_LL	r28, VCPU_GPR(R28)(vcpu); \
+	PPC_LL	r29, VCPU_GPR(R29)(vcpu); \
+	PPC_LL	r30, VCPU_GPR(R30)(vcpu); \
+	PPC_LL	r31, VCPU_GPR(R31)(vcpu); \
 
 /*****************************************************************************
  *                                                                           *
@@ -131,24 +123,24 @@ kvmppc_handler_highmem:
 	/* R7 = vcpu */
 	PPC_LL	r7, GPR4(r1)
 
-	PPC_STL	r14, VCPU_GPR(r14)(r7)
-	PPC_STL	r15, VCPU_GPR(r15)(r7)
-	PPC_STL	r16, VCPU_GPR(r16)(r7)
-	PPC_STL	r17, VCPU_GPR(r17)(r7)
-	PPC_STL	r18, VCPU_GPR(r18)(r7)
-	PPC_STL	r19, VCPU_GPR(r19)(r7)
-	PPC_STL	r20, VCPU_GPR(r20)(r7)
-	PPC_STL	r21, VCPU_GPR(r21)(r7)
-	PPC_STL	r22, VCPU_GPR(r22)(r7)
-	PPC_STL	r23, VCPU_GPR(r23)(r7)
-	PPC_STL	r24, VCPU_GPR(r24)(r7)
-	PPC_STL	r25, VCPU_GPR(r25)(r7)
-	PPC_STL	r26, VCPU_GPR(r26)(r7)
-	PPC_STL	r27, VCPU_GPR(r27)(r7)
-	PPC_STL	r28, VCPU_GPR(r28)(r7)
-	PPC_STL	r29, VCPU_GPR(r29)(r7)
-	PPC_STL	r30, VCPU_GPR(r30)(r7)
-	PPC_STL	r31, VCPU_GPR(r31)(r7)
+	PPC_STL	r14, VCPU_GPR(R14)(r7)
+	PPC_STL	r15, VCPU_GPR(R15)(r7)
+	PPC_STL	r16, VCPU_GPR(R16)(r7)
+	PPC_STL	r17, VCPU_GPR(R17)(r7)
+	PPC_STL	r18, VCPU_GPR(R18)(r7)
+	PPC_STL	r19, VCPU_GPR(R19)(r7)
+	PPC_STL	r20, VCPU_GPR(R20)(r7)
+	PPC_STL	r21, VCPU_GPR(R21)(r7)
+	PPC_STL	r22, VCPU_GPR(R22)(r7)
+	PPC_STL	r23, VCPU_GPR(R23)(r7)
+	PPC_STL	r24, VCPU_GPR(R24)(r7)
+	PPC_STL	r25, VCPU_GPR(R25)(r7)
+	PPC_STL	r26, VCPU_GPR(R26)(r7)
+	PPC_STL	r27, VCPU_GPR(R27)(r7)
+	PPC_STL	r28, VCPU_GPR(R28)(r7)
+	PPC_STL	r29, VCPU_GPR(R29)(r7)
+	PPC_STL	r30, VCPU_GPR(R30)(r7)
+	PPC_STL	r31, VCPU_GPR(R31)(r7)
 
 	/* Pass the exit number as 3rd argument to kvmppc_handle_exit */
 	mr	r5, r12
diff --git a/arch/powerpc/kvm/book3s_pr_papr.c b/arch/powerpc/kvm/book3s_pr_papr.c
index 3ff9013d6e79..ee02b30878ed 100644
--- a/arch/powerpc/kvm/book3s_pr_papr.c
+++ b/arch/powerpc/kvm/book3s_pr_papr.c
@@ -241,6 +241,7 @@ int kvmppc_h_pr(struct kvm_vcpu *vcpu, unsigned long cmd)
 	case H_PUT_TCE:
 		return kvmppc_h_pr_put_tce(vcpu);
 	case H_CEDE:
+		vcpu->arch.shared->msr |= MSR_EE;
 		kvm_vcpu_block(vcpu);
 		clear_bit(KVM_REQ_UNHALT, &vcpu->requests);
 		vcpu->stat.halt_wakeup++;
diff --git a/arch/powerpc/kvm/book3s_rmhandlers.S b/arch/powerpc/kvm/book3s_rmhandlers.S
index 34187585c507..ab523f3c1731 100644
--- a/arch/powerpc/kvm/book3s_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_rmhandlers.S
@@ -37,7 +37,6 @@
 #if defined(CONFIG_PPC_BOOK3S_64)
 
 #define FUNC(name) 		GLUE(.,name)
-#define MTMSR_EERI(reg)		mtmsrd	(reg),1
 
 	.globl	kvmppc_skip_interrupt
 kvmppc_skip_interrupt:
diff --git a/arch/powerpc/kvm/book3s_segment.S b/arch/powerpc/kvm/book3s_segment.S
index 798491a268b3..1abe4788191a 100644
--- a/arch/powerpc/kvm/book3s_segment.S
+++ b/arch/powerpc/kvm/book3s_segment.S
@@ -23,7 +23,6 @@
 
 #define GET_SHADOW_VCPU(reg)    \
 	mr	reg, r13
-#define MTMSR_EERI(reg)		mtmsrd	(reg),1
 
 #elif defined(CONFIG_PPC_BOOK3S_32)
 
@@ -31,7 +30,6 @@
 	tophys(reg, r2);       			\
 	lwz     reg, (THREAD + THREAD_KVM_SVCPU)(reg);	\
 	tophys(reg, reg)
-#define MTMSR_EERI(reg)		mtmsr	(reg)
 
 #endif
 
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index 72f13f4a06e0..d25a097c852b 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -612,6 +612,12 @@ static void kvmppc_fill_pt_regs(struct pt_regs *regs)
 	regs->link = lr;
 }
 
+/*
+ * For interrupts needed to be handled by host interrupt handlers,
+ * corresponding host handler are called from here in similar way
+ * (but not exact) as they are called from low level handler
+ * (such as from arch/powerpc/kernel/head_fsl_booke.S).
+ */
 static void kvmppc_restart_interrupt(struct kvm_vcpu *vcpu,
 				     unsigned int exit_nr)
 {
@@ -639,6 +645,17 @@ static void kvmppc_restart_interrupt(struct kvm_vcpu *vcpu,
 		kvmppc_fill_pt_regs(&regs);
 		performance_monitor_exception(&regs);
 		break;
+	case BOOKE_INTERRUPT_WATCHDOG:
+		kvmppc_fill_pt_regs(&regs);
+#ifdef CONFIG_BOOKE_WDT
+		WatchdogException(&regs);
+#else
+		unknown_exception(&regs);
+#endif
+		break;
+	case BOOKE_INTERRUPT_CRITICAL:
+		unknown_exception(&regs);
+		break;
 	}
 }
 
@@ -683,6 +700,10 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		r = RESUME_GUEST;
 		break;
 
+	case BOOKE_INTERRUPT_WATCHDOG:
+		r = RESUME_GUEST;
+		break;
+
 	case BOOKE_INTERRUPT_DOORBELL:
 		kvmppc_account_exit(vcpu, DBELL_EXITS);
 		r = RESUME_GUEST;
@@ -1267,6 +1288,11 @@ void kvmppc_decrementer_func(unsigned long data)
 {
 	struct kvm_vcpu *vcpu = (struct kvm_vcpu *)data;
 
+	if (vcpu->arch.tcr & TCR_ARE) {
+		vcpu->arch.dec = vcpu->arch.decar;
+		kvmppc_emulate_dec(vcpu);
+	}
+
 	kvmppc_set_tsr_bits(vcpu, TSR_DIS);
 }
 
diff --git a/arch/powerpc/kvm/booke_emulate.c b/arch/powerpc/kvm/booke_emulate.c
index 6c76397f2af4..12834bb608ab 100644
--- a/arch/powerpc/kvm/booke_emulate.c
+++ b/arch/powerpc/kvm/booke_emulate.c
@@ -24,6 +24,7 @@
 #include "booke.h"
 
 #define OP_19_XOP_RFI     50
+#define OP_19_XOP_RFCI    51
 
 #define OP_31_XOP_MFMSR   83
 #define OP_31_XOP_WRTEE   131
@@ -36,6 +37,12 @@ static void kvmppc_emul_rfi(struct kvm_vcpu *vcpu)
 	kvmppc_set_msr(vcpu, vcpu->arch.shared->srr1);
 }
 
+static void kvmppc_emul_rfci(struct kvm_vcpu *vcpu)
+{
+	vcpu->arch.pc = vcpu->arch.csrr0;
+	kvmppc_set_msr(vcpu, vcpu->arch.csrr1);
+}
+
 int kvmppc_booke_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
                             unsigned int inst, int *advance)
 {
@@ -52,6 +59,12 @@ int kvmppc_booke_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			*advance = 0;
 			break;
 
+		case OP_19_XOP_RFCI:
+			kvmppc_emul_rfci(vcpu);
+			kvmppc_set_exit_type(vcpu, EMULATED_RFCI_EXITS);
+			*advance = 0;
+			break;
+
 		default:
 			emulated = EMULATE_FAIL;
 			break;
@@ -113,6 +126,12 @@ int kvmppc_booke_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, ulong spr_val)
 	case SPRN_ESR:
 		vcpu->arch.shared->esr = spr_val;
 		break;
+	case SPRN_CSRR0:
+		vcpu->arch.csrr0 = spr_val;
+		break;
+	case SPRN_CSRR1:
+		vcpu->arch.csrr1 = spr_val;
+		break;
 	case SPRN_DBCR0:
 		vcpu->arch.dbcr0 = spr_val;
 		break;
@@ -129,6 +148,9 @@ int kvmppc_booke_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, ulong spr_val)
 		kvmppc_set_tcr(vcpu, spr_val);
 		break;
 
+	case SPRN_DECAR:
+		vcpu->arch.decar = spr_val;
+		break;
 	/*
 	 * Note: SPRG4-7 are user-readable.
 	 * These values are loaded into the real SPRGs when resuming the
@@ -229,6 +251,12 @@ int kvmppc_booke_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, ulong *spr_val)
 	case SPRN_ESR:
 		*spr_val = vcpu->arch.shared->esr;
 		break;
+	case SPRN_CSRR0:
+		*spr_val = vcpu->arch.csrr0;
+		break;
+	case SPRN_CSRR1:
+		*spr_val = vcpu->arch.csrr1;
+		break;
 	case SPRN_DBCR0:
 		*spr_val = vcpu->arch.dbcr0;
 		break;
diff --git a/arch/powerpc/kvm/booke_interrupts.S b/arch/powerpc/kvm/booke_interrupts.S
index 8feec2ff3928..bb46b32f9813 100644
--- a/arch/powerpc/kvm/booke_interrupts.S
+++ b/arch/powerpc/kvm/booke_interrupts.S
@@ -25,8 +25,6 @@
 #include <asm/page.h>
 #include <asm/asm-offsets.h>
 
-#define VCPU_GPR(n)     (VCPU_GPRS + (n * 4))
-
 /* The host stack layout: */
 #define HOST_R1         0 /* Implied by stwu. */
 #define HOST_CALLEE_LR  4
@@ -36,8 +34,9 @@
 #define HOST_R2         12
 #define HOST_CR         16
 #define HOST_NV_GPRS    20
-#define HOST_NV_GPR(n)  (HOST_NV_GPRS + ((n - 14) * 4))
-#define HOST_MIN_STACK_SIZE (HOST_NV_GPR(31) + 4)
+#define __HOST_NV_GPR(n)  (HOST_NV_GPRS + ((n - 14) * 4))
+#define HOST_NV_GPR(n)  __HOST_NV_GPR(__REG_##n)
+#define HOST_MIN_STACK_SIZE (HOST_NV_GPR(R31) + 4)
 #define HOST_STACK_SIZE (((HOST_MIN_STACK_SIZE + 15) / 16) * 16) /* Align. */
 #define HOST_STACK_LR   (HOST_STACK_SIZE + 4) /* In caller stack frame. */
 
@@ -53,16 +52,21 @@
                        (1<<BOOKE_INTERRUPT_PROGRAM) | \
                        (1<<BOOKE_INTERRUPT_DTLB_MISS))
 
-.macro KVM_HANDLER ivor_nr
+.macro KVM_HANDLER ivor_nr scratch srr0
 _GLOBAL(kvmppc_handler_\ivor_nr)
 	/* Get pointer to vcpu and record exit number. */
-	mtspr	SPRN_SPRG_WSCRATCH0, r4
+	mtspr	\scratch , r4
 	mfspr	r4, SPRN_SPRG_RVCPU
-	stw	r5, VCPU_GPR(r5)(r4)
-	stw	r6, VCPU_GPR(r6)(r4)
+	stw	r3, VCPU_GPR(R3)(r4)
+	stw	r5, VCPU_GPR(R5)(r4)
+	stw	r6, VCPU_GPR(R6)(r4)
+	mfspr	r3, \scratch
 	mfctr	r5
-	lis	r6, kvmppc_resume_host@h
+	stw	r3, VCPU_GPR(R4)(r4)
 	stw	r5, VCPU_CTR(r4)
+	mfspr	r3, \srr0
+	lis	r6, kvmppc_resume_host@h
+	stw	r3, VCPU_PC(r4)
 	li	r5, \ivor_nr
 	ori	r6, r6, kvmppc_resume_host@l
 	mtctr	r6
@@ -70,42 +74,40 @@ _GLOBAL(kvmppc_handler_\ivor_nr)
 .endm
 
 _GLOBAL(kvmppc_handlers_start)
-KVM_HANDLER BOOKE_INTERRUPT_CRITICAL
-KVM_HANDLER BOOKE_INTERRUPT_MACHINE_CHECK
-KVM_HANDLER BOOKE_INTERRUPT_DATA_STORAGE
-KVM_HANDLER BOOKE_INTERRUPT_INST_STORAGE
-KVM_HANDLER BOOKE_INTERRUPT_EXTERNAL
-KVM_HANDLER BOOKE_INTERRUPT_ALIGNMENT
-KVM_HANDLER BOOKE_INTERRUPT_PROGRAM
-KVM_HANDLER BOOKE_INTERRUPT_FP_UNAVAIL
-KVM_HANDLER BOOKE_INTERRUPT_SYSCALL
-KVM_HANDLER BOOKE_INTERRUPT_AP_UNAVAIL
-KVM_HANDLER BOOKE_INTERRUPT_DECREMENTER
-KVM_HANDLER BOOKE_INTERRUPT_FIT
-KVM_HANDLER BOOKE_INTERRUPT_WATCHDOG
-KVM_HANDLER BOOKE_INTERRUPT_DTLB_MISS
-KVM_HANDLER BOOKE_INTERRUPT_ITLB_MISS
-KVM_HANDLER BOOKE_INTERRUPT_DEBUG
-KVM_HANDLER BOOKE_INTERRUPT_SPE_UNAVAIL
-KVM_HANDLER BOOKE_INTERRUPT_SPE_FP_DATA
-KVM_HANDLER BOOKE_INTERRUPT_SPE_FP_ROUND
+KVM_HANDLER BOOKE_INTERRUPT_CRITICAL SPRN_SPRG_RSCRATCH_CRIT SPRN_CSRR0
+KVM_HANDLER BOOKE_INTERRUPT_MACHINE_CHECK  SPRN_SPRG_RSCRATCH_MC SPRN_MCSRR0
+KVM_HANDLER BOOKE_INTERRUPT_DATA_STORAGE SPRN_SPRG_RSCRATCH0 SPRN_SRR0
+KVM_HANDLER BOOKE_INTERRUPT_INST_STORAGE SPRN_SPRG_RSCRATCH0 SPRN_SRR0
+KVM_HANDLER BOOKE_INTERRUPT_EXTERNAL SPRN_SPRG_RSCRATCH0 SPRN_SRR0
+KVM_HANDLER BOOKE_INTERRUPT_ALIGNMENT SPRN_SPRG_RSCRATCH0 SPRN_SRR0
+KVM_HANDLER BOOKE_INTERRUPT_PROGRAM SPRN_SPRG_RSCRATCH0 SPRN_SRR0
+KVM_HANDLER BOOKE_INTERRUPT_FP_UNAVAIL SPRN_SPRG_RSCRATCH0 SPRN_SRR0
+KVM_HANDLER BOOKE_INTERRUPT_SYSCALL SPRN_SPRG_RSCRATCH0 SPRN_SRR0
+KVM_HANDLER BOOKE_INTERRUPT_AP_UNAVAIL SPRN_SPRG_RSCRATCH0 SPRN_SRR0
+KVM_HANDLER BOOKE_INTERRUPT_DECREMENTER SPRN_SPRG_RSCRATCH0 SPRN_SRR0
+KVM_HANDLER BOOKE_INTERRUPT_FIT SPRN_SPRG_RSCRATCH0 SPRN_SRR0
+KVM_HANDLER BOOKE_INTERRUPT_WATCHDOG SPRN_SPRG_RSCRATCH_CRIT SPRN_CSRR0
+KVM_HANDLER BOOKE_INTERRUPT_DTLB_MISS SPRN_SPRG_RSCRATCH0 SPRN_SRR0
+KVM_HANDLER BOOKE_INTERRUPT_ITLB_MISS SPRN_SPRG_RSCRATCH0 SPRN_SRR0
+KVM_HANDLER BOOKE_INTERRUPT_DEBUG SPRN_SPRG_RSCRATCH_CRIT SPRN_CSRR0
+KVM_HANDLER BOOKE_INTERRUPT_SPE_UNAVAIL SPRN_SPRG_RSCRATCH0 SPRN_SRR0
+KVM_HANDLER BOOKE_INTERRUPT_SPE_FP_DATA SPRN_SPRG_RSCRATCH0 SPRN_SRR0
+KVM_HANDLER BOOKE_INTERRUPT_SPE_FP_ROUND SPRN_SPRG_RSCRATCH0 SPRN_SRR0
 
 _GLOBAL(kvmppc_handler_len)
 	.long kvmppc_handler_1 - kvmppc_handler_0
 
-
 /* Registers:
  *  SPRG_SCRATCH0: guest r4
  *  r4: vcpu pointer
  *  r5: KVM exit number
  */
 _GLOBAL(kvmppc_resume_host)
-	stw	r3, VCPU_GPR(r3)(r4)
 	mfcr	r3
 	stw	r3, VCPU_CR(r4)
-	stw	r7, VCPU_GPR(r7)(r4)
-	stw	r8, VCPU_GPR(r8)(r4)
-	stw	r9, VCPU_GPR(r9)(r4)
+	stw	r7, VCPU_GPR(R7)(r4)
+	stw	r8, VCPU_GPR(R8)(r4)
+	stw	r9, VCPU_GPR(R9)(r4)
 
 	li	r6, 1
 	slw	r6, r6, r5
@@ -135,23 +137,23 @@ _GLOBAL(kvmppc_resume_host)
 	isync
 	stw	r9, VCPU_LAST_INST(r4)
 
-	stw	r15, VCPU_GPR(r15)(r4)
-	stw	r16, VCPU_GPR(r16)(r4)
-	stw	r17, VCPU_GPR(r17)(r4)
-	stw	r18, VCPU_GPR(r18)(r4)
-	stw	r19, VCPU_GPR(r19)(r4)
-	stw	r20, VCPU_GPR(r20)(r4)
-	stw	r21, VCPU_GPR(r21)(r4)
-	stw	r22, VCPU_GPR(r22)(r4)
-	stw	r23, VCPU_GPR(r23)(r4)
-	stw	r24, VCPU_GPR(r24)(r4)
-	stw	r25, VCPU_GPR(r25)(r4)
-	stw	r26, VCPU_GPR(r26)(r4)
-	stw	r27, VCPU_GPR(r27)(r4)
-	stw	r28, VCPU_GPR(r28)(r4)
-	stw	r29, VCPU_GPR(r29)(r4)
-	stw	r30, VCPU_GPR(r30)(r4)
-	stw	r31, VCPU_GPR(r31)(r4)
+	stw	r15, VCPU_GPR(R15)(r4)
+	stw	r16, VCPU_GPR(R16)(r4)
+	stw	r17, VCPU_GPR(R17)(r4)
+	stw	r18, VCPU_GPR(R18)(r4)
+	stw	r19, VCPU_GPR(R19)(r4)
+	stw	r20, VCPU_GPR(R20)(r4)
+	stw	r21, VCPU_GPR(R21)(r4)
+	stw	r22, VCPU_GPR(R22)(r4)
+	stw	r23, VCPU_GPR(R23)(r4)
+	stw	r24, VCPU_GPR(R24)(r4)
+	stw	r25, VCPU_GPR(R25)(r4)
+	stw	r26, VCPU_GPR(R26)(r4)
+	stw	r27, VCPU_GPR(R27)(r4)
+	stw	r28, VCPU_GPR(R28)(r4)
+	stw	r29, VCPU_GPR(R29)(r4)
+	stw	r30, VCPU_GPR(R30)(r4)
+	stw	r31, VCPU_GPR(R31)(r4)
 ..skip_inst_copy:
 
 	/* Also grab DEAR and ESR before the host can clobber them. */
@@ -169,22 +171,18 @@ _GLOBAL(kvmppc_resume_host)
 ..skip_esr:
 
 	/* Save remaining volatile guest register state to vcpu. */
-	stw	r0, VCPU_GPR(r0)(r4)
-	stw	r1, VCPU_GPR(r1)(r4)
-	stw	r2, VCPU_GPR(r2)(r4)
-	stw	r10, VCPU_GPR(r10)(r4)
-	stw	r11, VCPU_GPR(r11)(r4)
-	stw	r12, VCPU_GPR(r12)(r4)
-	stw	r13, VCPU_GPR(r13)(r4)
-	stw	r14, VCPU_GPR(r14)(r4) /* We need a NV GPR below. */
+	stw	r0, VCPU_GPR(R0)(r4)
+	stw	r1, VCPU_GPR(R1)(r4)
+	stw	r2, VCPU_GPR(R2)(r4)
+	stw	r10, VCPU_GPR(R10)(r4)
+	stw	r11, VCPU_GPR(R11)(r4)
+	stw	r12, VCPU_GPR(R12)(r4)
+	stw	r13, VCPU_GPR(R13)(r4)
+	stw	r14, VCPU_GPR(R14)(r4) /* We need a NV GPR below. */
 	mflr	r3
 	stw	r3, VCPU_LR(r4)
 	mfxer	r3
 	stw	r3, VCPU_XER(r4)
-	mfspr	r3, SPRN_SPRG_RSCRATCH0
-	stw	r3, VCPU_GPR(r4)(r4)
-	mfspr	r3, SPRN_SRR0
-	stw	r3, VCPU_PC(r4)
 
 	/* Restore host stack pointer and PID before IVPR, since the host
 	 * exception handlers use them. */
@@ -214,28 +212,28 @@ _GLOBAL(kvmppc_resume_host)
 
 	/* Restore vcpu pointer and the nonvolatiles we used. */
 	mr	r4, r14
-	lwz	r14, VCPU_GPR(r14)(r4)
+	lwz	r14, VCPU_GPR(R14)(r4)
 
 	/* Sometimes instruction emulation must restore complete GPR state. */
 	andi.	r5, r3, RESUME_FLAG_NV
 	beq	..skip_nv_load
-	lwz	r15, VCPU_GPR(r15)(r4)
-	lwz	r16, VCPU_GPR(r16)(r4)
-	lwz	r17, VCPU_GPR(r17)(r4)
-	lwz	r18, VCPU_GPR(r18)(r4)
-	lwz	r19, VCPU_GPR(r19)(r4)
-	lwz	r20, VCPU_GPR(r20)(r4)
-	lwz	r21, VCPU_GPR(r21)(r4)
-	lwz	r22, VCPU_GPR(r22)(r4)
-	lwz	r23, VCPU_GPR(r23)(r4)
-	lwz	r24, VCPU_GPR(r24)(r4)
-	lwz	r25, VCPU_GPR(r25)(r4)
-	lwz	r26, VCPU_GPR(r26)(r4)
-	lwz	r27, VCPU_GPR(r27)(r4)
-	lwz	r28, VCPU_GPR(r28)(r4)
-	lwz	r29, VCPU_GPR(r29)(r4)
-	lwz	r30, VCPU_GPR(r30)(r4)
-	lwz	r31, VCPU_GPR(r31)(r4)
+	lwz	r15, VCPU_GPR(R15)(r4)
+	lwz	r16, VCPU_GPR(R16)(r4)
+	lwz	r17, VCPU_GPR(R17)(r4)
+	lwz	r18, VCPU_GPR(R18)(r4)
+	lwz	r19, VCPU_GPR(R19)(r4)
+	lwz	r20, VCPU_GPR(R20)(r4)
+	lwz	r21, VCPU_GPR(R21)(r4)
+	lwz	r22, VCPU_GPR(R22)(r4)
+	lwz	r23, VCPU_GPR(R23)(r4)
+	lwz	r24, VCPU_GPR(R24)(r4)
+	lwz	r25, VCPU_GPR(R25)(r4)
+	lwz	r26, VCPU_GPR(R26)(r4)
+	lwz	r27, VCPU_GPR(R27)(r4)
+	lwz	r28, VCPU_GPR(R28)(r4)
+	lwz	r29, VCPU_GPR(R29)(r4)
+	lwz	r30, VCPU_GPR(R30)(r4)
+	lwz	r31, VCPU_GPR(R31)(r4)
 ..skip_nv_load:
 
 	/* Should we return to the guest? */
@@ -257,43 +255,43 @@ heavyweight_exit:
 
 	/* We already saved guest volatile register state; now save the
 	 * non-volatiles. */
-	stw	r15, VCPU_GPR(r15)(r4)
-	stw	r16, VCPU_GPR(r16)(r4)
-	stw	r17, VCPU_GPR(r17)(r4)
-	stw	r18, VCPU_GPR(r18)(r4)
-	stw	r19, VCPU_GPR(r19)(r4)
-	stw	r20, VCPU_GPR(r20)(r4)
-	stw	r21, VCPU_GPR(r21)(r4)
-	stw	r22, VCPU_GPR(r22)(r4)
-	stw	r23, VCPU_GPR(r23)(r4)
-	stw	r24, VCPU_GPR(r24)(r4)
-	stw	r25, VCPU_GPR(r25)(r4)
-	stw	r26, VCPU_GPR(r26)(r4)
-	stw	r27, VCPU_GPR(r27)(r4)
-	stw	r28, VCPU_GPR(r28)(r4)
-	stw	r29, VCPU_GPR(r29)(r4)
-	stw	r30, VCPU_GPR(r30)(r4)
-	stw	r31, VCPU_GPR(r31)(r4)
+	stw	r15, VCPU_GPR(R15)(r4)
+	stw	r16, VCPU_GPR(R16)(r4)
+	stw	r17, VCPU_GPR(R17)(r4)
+	stw	r18, VCPU_GPR(R18)(r4)
+	stw	r19, VCPU_GPR(R19)(r4)
+	stw	r20, VCPU_GPR(R20)(r4)
+	stw	r21, VCPU_GPR(R21)(r4)
+	stw	r22, VCPU_GPR(R22)(r4)
+	stw	r23, VCPU_GPR(R23)(r4)
+	stw	r24, VCPU_GPR(R24)(r4)
+	stw	r25, VCPU_GPR(R25)(r4)
+	stw	r26, VCPU_GPR(R26)(r4)
+	stw	r27, VCPU_GPR(R27)(r4)
+	stw	r28, VCPU_GPR(R28)(r4)
+	stw	r29, VCPU_GPR(R29)(r4)
+	stw	r30, VCPU_GPR(R30)(r4)
+	stw	r31, VCPU_GPR(R31)(r4)
 
 	/* Load host non-volatile register state from host stack. */
-	lwz	r14, HOST_NV_GPR(r14)(r1)
-	lwz	r15, HOST_NV_GPR(r15)(r1)
-	lwz	r16, HOST_NV_GPR(r16)(r1)
-	lwz	r17, HOST_NV_GPR(r17)(r1)
-	lwz	r18, HOST_NV_GPR(r18)(r1)
-	lwz	r19, HOST_NV_GPR(r19)(r1)
-	lwz	r20, HOST_NV_GPR(r20)(r1)
-	lwz	r21, HOST_NV_GPR(r21)(r1)
-	lwz	r22, HOST_NV_GPR(r22)(r1)
-	lwz	r23, HOST_NV_GPR(r23)(r1)
-	lwz	r24, HOST_NV_GPR(r24)(r1)
-	lwz	r25, HOST_NV_GPR(r25)(r1)
-	lwz	r26, HOST_NV_GPR(r26)(r1)
-	lwz	r27, HOST_NV_GPR(r27)(r1)
-	lwz	r28, HOST_NV_GPR(r28)(r1)
-	lwz	r29, HOST_NV_GPR(r29)(r1)
-	lwz	r30, HOST_NV_GPR(r30)(r1)
-	lwz	r31, HOST_NV_GPR(r31)(r1)
+	lwz	r14, HOST_NV_GPR(R14)(r1)
+	lwz	r15, HOST_NV_GPR(R15)(r1)
+	lwz	r16, HOST_NV_GPR(R16)(r1)
+	lwz	r17, HOST_NV_GPR(R17)(r1)
+	lwz	r18, HOST_NV_GPR(R18)(r1)
+	lwz	r19, HOST_NV_GPR(R19)(r1)
+	lwz	r20, HOST_NV_GPR(R20)(r1)
+	lwz	r21, HOST_NV_GPR(R21)(r1)
+	lwz	r22, HOST_NV_GPR(R22)(r1)
+	lwz	r23, HOST_NV_GPR(R23)(r1)
+	lwz	r24, HOST_NV_GPR(R24)(r1)
+	lwz	r25, HOST_NV_GPR(R25)(r1)
+	lwz	r26, HOST_NV_GPR(R26)(r1)
+	lwz	r27, HOST_NV_GPR(R27)(r1)
+	lwz	r28, HOST_NV_GPR(R28)(r1)
+	lwz	r29, HOST_NV_GPR(R29)(r1)
+	lwz	r30, HOST_NV_GPR(R30)(r1)
+	lwz	r31, HOST_NV_GPR(R31)(r1)
 
 	/* Return to kvm_vcpu_run(). */
 	lwz	r4, HOST_STACK_LR(r1)
@@ -321,44 +319,44 @@ _GLOBAL(__kvmppc_vcpu_run)
 	stw	r5, HOST_CR(r1)
 
 	/* Save host non-volatile register state to stack. */
-	stw	r14, HOST_NV_GPR(r14)(r1)
-	stw	r15, HOST_NV_GPR(r15)(r1)
-	stw	r16, HOST_NV_GPR(r16)(r1)
-	stw	r17, HOST_NV_GPR(r17)(r1)
-	stw	r18, HOST_NV_GPR(r18)(r1)
-	stw	r19, HOST_NV_GPR(r19)(r1)
-	stw	r20, HOST_NV_GPR(r20)(r1)
-	stw	r21, HOST_NV_GPR(r21)(r1)
-	stw	r22, HOST_NV_GPR(r22)(r1)
-	stw	r23, HOST_NV_GPR(r23)(r1)
-	stw	r24, HOST_NV_GPR(r24)(r1)
-	stw	r25, HOST_NV_GPR(r25)(r1)
-	stw	r26, HOST_NV_GPR(r26)(r1)
-	stw	r27, HOST_NV_GPR(r27)(r1)
-	stw	r28, HOST_NV_GPR(r28)(r1)
-	stw	r29, HOST_NV_GPR(r29)(r1)
-	stw	r30, HOST_NV_GPR(r30)(r1)
-	stw	r31, HOST_NV_GPR(r31)(r1)
+	stw	r14, HOST_NV_GPR(R14)(r1)
+	stw	r15, HOST_NV_GPR(R15)(r1)
+	stw	r16, HOST_NV_GPR(R16)(r1)
+	stw	r17, HOST_NV_GPR(R17)(r1)
+	stw	r18, HOST_NV_GPR(R18)(r1)
+	stw	r19, HOST_NV_GPR(R19)(r1)
+	stw	r20, HOST_NV_GPR(R20)(r1)
+	stw	r21, HOST_NV_GPR(R21)(r1)
+	stw	r22, HOST_NV_GPR(R22)(r1)
+	stw	r23, HOST_NV_GPR(R23)(r1)
+	stw	r24, HOST_NV_GPR(R24)(r1)
+	stw	r25, HOST_NV_GPR(R25)(r1)
+	stw	r26, HOST_NV_GPR(R26)(r1)
+	stw	r27, HOST_NV_GPR(R27)(r1)
+	stw	r28, HOST_NV_GPR(R28)(r1)
+	stw	r29, HOST_NV_GPR(R29)(r1)
+	stw	r30, HOST_NV_GPR(R30)(r1)
+	stw	r31, HOST_NV_GPR(R31)(r1)
 
 	/* Load guest non-volatiles. */
-	lwz	r14, VCPU_GPR(r14)(r4)
-	lwz	r15, VCPU_GPR(r15)(r4)
-	lwz	r16, VCPU_GPR(r16)(r4)
-	lwz	r17, VCPU_GPR(r17)(r4)
-	lwz	r18, VCPU_GPR(r18)(r4)
-	lwz	r19, VCPU_GPR(r19)(r4)
-	lwz	r20, VCPU_GPR(r20)(r4)
-	lwz	r21, VCPU_GPR(r21)(r4)
-	lwz	r22, VCPU_GPR(r22)(r4)
-	lwz	r23, VCPU_GPR(r23)(r4)
-	lwz	r24, VCPU_GPR(r24)(r4)
-	lwz	r25, VCPU_GPR(r25)(r4)
-	lwz	r26, VCPU_GPR(r26)(r4)
-	lwz	r27, VCPU_GPR(r27)(r4)
-	lwz	r28, VCPU_GPR(r28)(r4)
-	lwz	r29, VCPU_GPR(r29)(r4)
-	lwz	r30, VCPU_GPR(r30)(r4)
-	lwz	r31, VCPU_GPR(r31)(r4)
+	lwz	r14, VCPU_GPR(R14)(r4)
+	lwz	r15, VCPU_GPR(R15)(r4)
+	lwz	r16, VCPU_GPR(R16)(r4)
+	lwz	r17, VCPU_GPR(R17)(r4)
+	lwz	r18, VCPU_GPR(R18)(r4)
+	lwz	r19, VCPU_GPR(R19)(r4)
+	lwz	r20, VCPU_GPR(R20)(r4)
+	lwz	r21, VCPU_GPR(R21)(r4)
+	lwz	r22, VCPU_GPR(R22)(r4)
+	lwz	r23, VCPU_GPR(R23)(r4)
+	lwz	r24, VCPU_GPR(R24)(r4)
+	lwz	r25, VCPU_GPR(R25)(r4)
+	lwz	r26, VCPU_GPR(R26)(r4)
+	lwz	r27, VCPU_GPR(R27)(r4)
+	lwz	r28, VCPU_GPR(R28)(r4)
+	lwz	r29, VCPU_GPR(R29)(r4)
+	lwz	r30, VCPU_GPR(R30)(r4)
+	lwz	r31, VCPU_GPR(R31)(r4)
 
 #ifdef CONFIG_SPE
 	/* save host SPEFSCR and load guest SPEFSCR */
@@ -386,13 +384,13 @@ lightweight_exit:
 #endif
 
 	/* Load some guest volatiles. */
-	lwz	r0, VCPU_GPR(r0)(r4)
-	lwz	r2, VCPU_GPR(r2)(r4)
-	lwz	r9, VCPU_GPR(r9)(r4)
-	lwz	r10, VCPU_GPR(r10)(r4)
-	lwz	r11, VCPU_GPR(r11)(r4)
-	lwz	r12, VCPU_GPR(r12)(r4)
-	lwz	r13, VCPU_GPR(r13)(r4)
+	lwz	r0, VCPU_GPR(R0)(r4)
+	lwz	r2, VCPU_GPR(R2)(r4)
+	lwz	r9, VCPU_GPR(R9)(r4)
+	lwz	r10, VCPU_GPR(R10)(r4)
+	lwz	r11, VCPU_GPR(R11)(r4)
+	lwz	r12, VCPU_GPR(R12)(r4)
+	lwz	r13, VCPU_GPR(R13)(r4)
 	lwz	r3, VCPU_LR(r4)
 	mtlr	r3
 	lwz	r3, VCPU_XER(r4)
@@ -411,7 +409,7 @@ lightweight_exit:
 
 	/* Can't switch the stack pointer until after IVPR is switched,
 	 * because host interrupt handlers would get confused. */
-	lwz	r1, VCPU_GPR(r1)(r4)
+	lwz	r1, VCPU_GPR(R1)(r4)
 
 	/*
 	 * Host interrupt handlers may have clobbered these
@@ -449,10 +447,10 @@ lightweight_exit:
 	mtcr	r5
 	mtsrr0	r6
 	mtsrr1	r7
-	lwz	r5, VCPU_GPR(r5)(r4)
-	lwz	r6, VCPU_GPR(r6)(r4)
-	lwz	r7, VCPU_GPR(r7)(r4)
-	lwz	r8, VCPU_GPR(r8)(r4)
+	lwz	r5, VCPU_GPR(R5)(r4)
+	lwz	r6, VCPU_GPR(R6)(r4)
+	lwz	r7, VCPU_GPR(R7)(r4)
+	lwz	r8, VCPU_GPR(R8)(r4)
 
 	/* Clear any debug events which occurred since we disabled MSR[DE].
 	 * XXX This gives us a 3-instruction window in which a breakpoint
@@ -461,8 +459,8 @@ lightweight_exit:
 	ori	r3, r3, 0xffff
 	mtspr	SPRN_DBSR, r3
 
-	lwz	r3, VCPU_GPR(r3)(r4)
-	lwz	r4, VCPU_GPR(r4)(r4)
+	lwz	r3, VCPU_GPR(R3)(r4)
+	lwz	r4, VCPU_GPR(R4)(r4)
 	rfi
 
 #ifdef CONFIG_SPE
diff --git a/arch/powerpc/kvm/bookehv_interrupts.S b/arch/powerpc/kvm/bookehv_interrupts.S
index 6048a00515d7..d28c2d43ac1b 100644
--- a/arch/powerpc/kvm/bookehv_interrupts.S
+++ b/arch/powerpc/kvm/bookehv_interrupts.S
@@ -37,7 +37,6 @@
 
 #define LONGBYTES		(BITS_PER_LONG / 8)
 
-#define VCPU_GPR(n)     	(VCPU_GPRS + (n * LONGBYTES))
 #define VCPU_GUEST_SPRG(n)	(VCPU_GUEST_SPRGS + (n * LONGBYTES))
 
 /* The host stack layout: */
@@ -67,15 +66,15 @@
  */
 .macro kvm_handler_common intno, srr0, flags
 	/* Restore host stack pointer */
-	PPC_STL	r1, VCPU_GPR(r1)(r4)
-	PPC_STL	r2, VCPU_GPR(r2)(r4)
+	PPC_STL	r1, VCPU_GPR(R1)(r4)
+	PPC_STL	r2, VCPU_GPR(R2)(r4)
 	PPC_LL	r1, VCPU_HOST_STACK(r4)
 	PPC_LL	r2, HOST_R2(r1)
 
 	mfspr	r10, SPRN_PID
 	lwz	r8, VCPU_HOST_PID(r4)
 	PPC_LL	r11, VCPU_SHARED(r4)
-	PPC_STL	r14, VCPU_GPR(r14)(r4) /* We need a non-volatile GPR. */
+	PPC_STL	r14, VCPU_GPR(R14)(r4) /* We need a non-volatile GPR. */
 	li	r14, \intno
 
 	stw	r10, VCPU_GUEST_PID(r4)
@@ -137,35 +136,31 @@
 	 */
 
 	mfspr	r3, SPRN_EPLC	/* will already have correct ELPID and EGS */
-	PPC_STL	r15, VCPU_GPR(r15)(r4)
-	PPC_STL	r16, VCPU_GPR(r16)(r4)
-	PPC_STL	r17, VCPU_GPR(r17)(r4)
-	PPC_STL	r18, VCPU_GPR(r18)(r4)
-	PPC_STL	r19, VCPU_GPR(r19)(r4)
+	PPC_STL	r15, VCPU_GPR(R15)(r4)
+	PPC_STL	r16, VCPU_GPR(R16)(r4)
+	PPC_STL	r17, VCPU_GPR(R17)(r4)
+	PPC_STL	r18, VCPU_GPR(R18)(r4)
+	PPC_STL	r19, VCPU_GPR(R19)(r4)
 	mr	r8, r3
-	PPC_STL	r20, VCPU_GPR(r20)(r4)
+	PPC_STL	r20, VCPU_GPR(R20)(r4)
 	rlwimi	r8, r6, EPC_EAS_SHIFT - MSR_IR_LG, EPC_EAS
-	PPC_STL	r21, VCPU_GPR(r21)(r4)
+	PPC_STL	r21, VCPU_GPR(R21)(r4)
 	rlwimi	r8, r6, EPC_EPR_SHIFT - MSR_PR_LG, EPC_EPR
-	PPC_STL	r22, VCPU_GPR(r22)(r4)
+	PPC_STL	r22, VCPU_GPR(R22)(r4)
 	rlwimi	r8, r10, EPC_EPID_SHIFT, EPC_EPID
-	PPC_STL	r23, VCPU_GPR(r23)(r4)
-	PPC_STL	r24, VCPU_GPR(r24)(r4)
-	PPC_STL	r25, VCPU_GPR(r25)(r4)
-	PPC_STL	r26, VCPU_GPR(r26)(r4)
-	PPC_STL	r27, VCPU_GPR(r27)(r4)
-	PPC_STL	r28, VCPU_GPR(r28)(r4)
-	PPC_STL	r29, VCPU_GPR(r29)(r4)
-	PPC_STL	r30, VCPU_GPR(r30)(r4)
-	PPC_STL	r31, VCPU_GPR(r31)(r4)
+	PPC_STL	r23, VCPU_GPR(R23)(r4)
+	PPC_STL	r24, VCPU_GPR(R24)(r4)
+	PPC_STL	r25, VCPU_GPR(R25)(r4)
+	PPC_STL	r26, VCPU_GPR(R26)(r4)
+	PPC_STL	r27, VCPU_GPR(R27)(r4)
+	PPC_STL	r28, VCPU_GPR(R28)(r4)
+	PPC_STL	r29, VCPU_GPR(R29)(r4)
+	PPC_STL	r30, VCPU_GPR(R30)(r4)
+	PPC_STL	r31, VCPU_GPR(R31)(r4)
 	mtspr	SPRN_EPLC, r8
 
 	/* disable preemption, so we are sure we hit the fixup handler */
-#ifdef CONFIG_PPC64
-	clrrdi	r8,r1,THREAD_SHIFT
-#else
-	rlwinm	r8,r1,0,0,31-THREAD_SHIFT       /* current thread_info */
-#endif
+	CURRENT_THREAD_INFO(r8, r1)
 	li	r7, 1
 	stw	r7, TI_PREEMPT(r8)
 
@@ -211,24 +206,24 @@
 .macro kvm_handler intno srr0, srr1, flags
 _GLOBAL(kvmppc_handler_\intno\()_\srr1)
 	GET_VCPU(r11, r10)
-	PPC_STL r3, VCPU_GPR(r3)(r11)
+	PPC_STL r3, VCPU_GPR(R3)(r11)
 	mfspr	r3, SPRN_SPRG_RSCRATCH0
-	PPC_STL	r4, VCPU_GPR(r4)(r11)
+	PPC_STL	r4, VCPU_GPR(R4)(r11)
 	PPC_LL	r4, THREAD_NORMSAVE(0)(r10)
-	PPC_STL	r5, VCPU_GPR(r5)(r11)
+	PPC_STL	r5, VCPU_GPR(R5)(r11)
 	stw	r13, VCPU_CR(r11)
 	mfspr	r5, \srr0
-	PPC_STL	r3, VCPU_GPR(r10)(r11)
+	PPC_STL	r3, VCPU_GPR(R10)(r11)
 	PPC_LL	r3, THREAD_NORMSAVE(2)(r10)
-	PPC_STL	r6, VCPU_GPR(r6)(r11)
-	PPC_STL	r4, VCPU_GPR(r11)(r11)
+	PPC_STL	r6, VCPU_GPR(R6)(r11)
+	PPC_STL	r4, VCPU_GPR(R11)(r11)
 	mfspr	r6, \srr1
-	PPC_STL	r7, VCPU_GPR(r7)(r11)
-	PPC_STL	r8, VCPU_GPR(r8)(r11)
-	PPC_STL	r9, VCPU_GPR(r9)(r11)
-	PPC_STL r3, VCPU_GPR(r13)(r11)
+	PPC_STL	r7, VCPU_GPR(R7)(r11)
+	PPC_STL	r8, VCPU_GPR(R8)(r11)
+	PPC_STL	r9, VCPU_GPR(R9)(r11)
+	PPC_STL r3, VCPU_GPR(R13)(r11)
 	mfctr	r7
-	PPC_STL	r12, VCPU_GPR(r12)(r11)
+	PPC_STL	r12, VCPU_GPR(R12)(r11)
 	PPC_STL	r7, VCPU_CTR(r11)
 	mr	r4, r11
 	kvm_handler_common \intno, \srr0, \flags
@@ -238,25 +233,25 @@ _GLOBAL(kvmppc_handler_\intno\()_\srr1)
 _GLOBAL(kvmppc_handler_\intno\()_\srr1)
 	mfspr	r10, SPRN_SPRG_THREAD
 	GET_VCPU(r11, r10)
-	PPC_STL r3, VCPU_GPR(r3)(r11)
+	PPC_STL r3, VCPU_GPR(R3)(r11)
 	mfspr	r3, \scratch
-	PPC_STL	r4, VCPU_GPR(r4)(r11)
+	PPC_STL	r4, VCPU_GPR(R4)(r11)
 	PPC_LL	r4, GPR9(r8)
-	PPC_STL	r5, VCPU_GPR(r5)(r11)
+	PPC_STL	r5, VCPU_GPR(R5)(r11)
 	stw	r9, VCPU_CR(r11)
 	mfspr	r5, \srr0
-	PPC_STL	r3, VCPU_GPR(r8)(r11)
+	PPC_STL	r3, VCPU_GPR(R8)(r11)
 	PPC_LL	r3, GPR10(r8)
-	PPC_STL	r6, VCPU_GPR(r6)(r11)
-	PPC_STL	r4, VCPU_GPR(r9)(r11)
+	PPC_STL	r6, VCPU_GPR(R6)(r11)
+	PPC_STL	r4, VCPU_GPR(R9)(r11)
 	mfspr	r6, \srr1
 	PPC_LL	r4, GPR11(r8)
-	PPC_STL	r7, VCPU_GPR(r7)(r11)
-	PPC_STL r3, VCPU_GPR(r10)(r11)
+	PPC_STL	r7, VCPU_GPR(R7)(r11)
+	PPC_STL r3, VCPU_GPR(R10)(r11)
 	mfctr	r7
-	PPC_STL	r12, VCPU_GPR(r12)(r11)
-	PPC_STL r13, VCPU_GPR(r13)(r11)
-	PPC_STL	r4, VCPU_GPR(r11)(r11)
+	PPC_STL	r12, VCPU_GPR(R12)(r11)
+	PPC_STL r13, VCPU_GPR(R13)(r11)
+	PPC_STL	r4, VCPU_GPR(R11)(r11)
 	PPC_STL	r7, VCPU_CTR(r11)
 	mr	r4, r11
 	kvm_handler_common \intno, \srr0, \flags
@@ -267,7 +262,7 @@ kvm_lvl_handler BOOKE_INTERRUPT_CRITICAL, \
 kvm_lvl_handler BOOKE_INTERRUPT_MACHINE_CHECK, \
 	SPRN_SPRG_RSCRATCH_MC, SPRN_MCSRR0, SPRN_MCSRR1, 0
 kvm_handler BOOKE_INTERRUPT_DATA_STORAGE, \
-	SPRN_SRR0, SPRN_SRR1, (NEED_EMU | NEED_DEAR)
+	SPRN_SRR0, SPRN_SRR1, (NEED_EMU | NEED_DEAR | NEED_ESR)
 kvm_handler BOOKE_INTERRUPT_INST_STORAGE, SPRN_SRR0, SPRN_SRR1, NEED_ESR
 kvm_handler BOOKE_INTERRUPT_EXTERNAL, SPRN_SRR0, SPRN_SRR1, 0
 kvm_handler BOOKE_INTERRUPT_ALIGNMENT, \
@@ -310,7 +305,7 @@ kvm_lvl_handler BOOKE_INTERRUPT_DEBUG, \
 _GLOBAL(kvmppc_resume_host)
 	/* Save remaining volatile guest register state to vcpu. */
 	mfspr	r3, SPRN_VRSAVE
-	PPC_STL	r0, VCPU_GPR(r0)(r4)
+	PPC_STL	r0, VCPU_GPR(R0)(r4)
 	mflr	r5
 	mfspr	r6, SPRN_SPRG4
 	PPC_STL	r5, VCPU_LR(r4)
@@ -358,27 +353,27 @@ _GLOBAL(kvmppc_resume_host)
 
 	/* Restore vcpu pointer and the nonvolatiles we used. */
 	mr	r4, r14
-	PPC_LL	r14, VCPU_GPR(r14)(r4)
+	PPC_LL	r14, VCPU_GPR(R14)(r4)
 
 	andi.	r5, r3, RESUME_FLAG_NV
 	beq	skip_nv_load
-	PPC_LL	r15, VCPU_GPR(r15)(r4)
-	PPC_LL	r16, VCPU_GPR(r16)(r4)
-	PPC_LL	r17, VCPU_GPR(r17)(r4)
-	PPC_LL	r18, VCPU_GPR(r18)(r4)
-	PPC_LL	r19, VCPU_GPR(r19)(r4)
-	PPC_LL	r20, VCPU_GPR(r20)(r4)
-	PPC_LL	r21, VCPU_GPR(r21)(r4)
-	PPC_LL	r22, VCPU_GPR(r22)(r4)
-	PPC_LL	r23, VCPU_GPR(r23)(r4)
-	PPC_LL	r24, VCPU_GPR(r24)(r4)
-	PPC_LL	r25, VCPU_GPR(r25)(r4)
-	PPC_LL	r26, VCPU_GPR(r26)(r4)
-	PPC_LL	r27, VCPU_GPR(r27)(r4)
-	PPC_LL	r28, VCPU_GPR(r28)(r4)
-	PPC_LL	r29, VCPU_GPR(r29)(r4)
-	PPC_LL	r30, VCPU_GPR(r30)(r4)
-	PPC_LL	r31, VCPU_GPR(r31)(r4)
+	PPC_LL	r15, VCPU_GPR(R15)(r4)
+	PPC_LL	r16, VCPU_GPR(R16)(r4)
+	PPC_LL	r17, VCPU_GPR(R17)(r4)
+	PPC_LL	r18, VCPU_GPR(R18)(r4)
+	PPC_LL	r19, VCPU_GPR(R19)(r4)
+	PPC_LL	r20, VCPU_GPR(R20)(r4)
+	PPC_LL	r21, VCPU_GPR(R21)(r4)
+	PPC_LL	r22, VCPU_GPR(R22)(r4)
+	PPC_LL	r23, VCPU_GPR(R23)(r4)
+	PPC_LL	r24, VCPU_GPR(R24)(r4)
+	PPC_LL	r25, VCPU_GPR(R25)(r4)
+	PPC_LL	r26, VCPU_GPR(R26)(r4)
+	PPC_LL	r27, VCPU_GPR(R27)(r4)
+	PPC_LL	r28, VCPU_GPR(R28)(r4)
+	PPC_LL	r29, VCPU_GPR(R29)(r4)
+	PPC_LL	r30, VCPU_GPR(R30)(r4)
+	PPC_LL	r31, VCPU_GPR(R31)(r4)
 skip_nv_load:
 	/* Should we return to the guest? */
 	andi.	r5, r3, RESUME_FLAG_HOST
@@ -396,23 +391,23 @@ heavyweight_exit:
 	 * non-volatiles.
 	 */
 
-	PPC_STL	r15, VCPU_GPR(r15)(r4)
-	PPC_STL	r16, VCPU_GPR(r16)(r4)
-	PPC_STL	r17, VCPU_GPR(r17)(r4)
-	PPC_STL	r18, VCPU_GPR(r18)(r4)
-	PPC_STL	r19, VCPU_GPR(r19)(r4)
-	PPC_STL	r20, VCPU_GPR(r20)(r4)
-	PPC_STL	r21, VCPU_GPR(r21)(r4)
-	PPC_STL	r22, VCPU_GPR(r22)(r4)
-	PPC_STL	r23, VCPU_GPR(r23)(r4)
-	PPC_STL	r24, VCPU_GPR(r24)(r4)
-	PPC_STL	r25, VCPU_GPR(r25)(r4)
-	PPC_STL	r26, VCPU_GPR(r26)(r4)
-	PPC_STL	r27, VCPU_GPR(r27)(r4)
-	PPC_STL	r28, VCPU_GPR(r28)(r4)
-	PPC_STL	r29, VCPU_GPR(r29)(r4)
-	PPC_STL	r30, VCPU_GPR(r30)(r4)
-	PPC_STL	r31, VCPU_GPR(r31)(r4)
+	PPC_STL	r15, VCPU_GPR(R15)(r4)
+	PPC_STL	r16, VCPU_GPR(R16)(r4)
+	PPC_STL	r17, VCPU_GPR(R17)(r4)
+	PPC_STL	r18, VCPU_GPR(R18)(r4)
+	PPC_STL	r19, VCPU_GPR(R19)(r4)
+	PPC_STL	r20, VCPU_GPR(R20)(r4)
+	PPC_STL	r21, VCPU_GPR(R21)(r4)
+	PPC_STL	r22, VCPU_GPR(R22)(r4)
+	PPC_STL	r23, VCPU_GPR(R23)(r4)
+	PPC_STL	r24, VCPU_GPR(R24)(r4)
+	PPC_STL	r25, VCPU_GPR(R25)(r4)
+	PPC_STL	r26, VCPU_GPR(R26)(r4)
+	PPC_STL	r27, VCPU_GPR(R27)(r4)
+	PPC_STL	r28, VCPU_GPR(R28)(r4)
+	PPC_STL	r29, VCPU_GPR(R29)(r4)
+	PPC_STL	r30, VCPU_GPR(R30)(r4)
+	PPC_STL	r31, VCPU_GPR(R31)(r4)
 
 	/* Load host non-volatile register state from host stack. */
 	PPC_LL	r14, HOST_NV_GPR(r14)(r1)
@@ -478,24 +473,24 @@ _GLOBAL(__kvmppc_vcpu_run)
 	PPC_STL	r31, HOST_NV_GPR(r31)(r1)
 
 	/* Load guest non-volatiles. */
-	PPC_LL	r14, VCPU_GPR(r14)(r4)
-	PPC_LL	r15, VCPU_GPR(r15)(r4)
-	PPC_LL	r16, VCPU_GPR(r16)(r4)
-	PPC_LL	r17, VCPU_GPR(r17)(r4)
-	PPC_LL	r18, VCPU_GPR(r18)(r4)
-	PPC_LL	r19, VCPU_GPR(r19)(r4)
-	PPC_LL	r20, VCPU_GPR(r20)(r4)
-	PPC_LL	r21, VCPU_GPR(r21)(r4)
-	PPC_LL	r22, VCPU_GPR(r22)(r4)
-	PPC_LL	r23, VCPU_GPR(r23)(r4)
-	PPC_LL	r24, VCPU_GPR(r24)(r4)
-	PPC_LL	r25, VCPU_GPR(r25)(r4)
-	PPC_LL	r26, VCPU_GPR(r26)(r4)
-	PPC_LL	r27, VCPU_GPR(r27)(r4)
-	PPC_LL	r28, VCPU_GPR(r28)(r4)
-	PPC_LL	r29, VCPU_GPR(r29)(r4)
-	PPC_LL	r30, VCPU_GPR(r30)(r4)
-	PPC_LL	r31, VCPU_GPR(r31)(r4)
+	PPC_LL	r14, VCPU_GPR(R14)(r4)
+	PPC_LL	r15, VCPU_GPR(R15)(r4)
+	PPC_LL	r16, VCPU_GPR(R16)(r4)
+	PPC_LL	r17, VCPU_GPR(R17)(r4)
+	PPC_LL	r18, VCPU_GPR(R18)(r4)
+	PPC_LL	r19, VCPU_GPR(R19)(r4)
+	PPC_LL	r20, VCPU_GPR(R20)(r4)
+	PPC_LL	r21, VCPU_GPR(R21)(r4)
+	PPC_LL	r22, VCPU_GPR(R22)(r4)
+	PPC_LL	r23, VCPU_GPR(R23)(r4)
+	PPC_LL	r24, VCPU_GPR(R24)(r4)
+	PPC_LL	r25, VCPU_GPR(R25)(r4)
+	PPC_LL	r26, VCPU_GPR(R26)(r4)
+	PPC_LL	r27, VCPU_GPR(R27)(r4)
+	PPC_LL	r28, VCPU_GPR(R28)(r4)
+	PPC_LL	r29, VCPU_GPR(R29)(r4)
+	PPC_LL	r30, VCPU_GPR(R30)(r4)
+	PPC_LL	r31, VCPU_GPR(R31)(r4)
 
 
 lightweight_exit:
@@ -554,13 +549,13 @@ lightweight_exit:
 	lwz	r7, VCPU_CR(r4)
 	PPC_LL	r8, VCPU_PC(r4)
 	PPC_LD(r9, VCPU_SHARED_MSR, r11)
-	PPC_LL	r0, VCPU_GPR(r0)(r4)
-	PPC_LL	r1, VCPU_GPR(r1)(r4)
-	PPC_LL	r2, VCPU_GPR(r2)(r4)
-	PPC_LL	r10, VCPU_GPR(r10)(r4)
-	PPC_LL	r11, VCPU_GPR(r11)(r4)
-	PPC_LL	r12, VCPU_GPR(r12)(r4)
-	PPC_LL	r13, VCPU_GPR(r13)(r4)
+	PPC_LL	r0, VCPU_GPR(R0)(r4)
+	PPC_LL	r1, VCPU_GPR(R1)(r4)
+	PPC_LL	r2, VCPU_GPR(R2)(r4)
+	PPC_LL	r10, VCPU_GPR(R10)(r4)
+	PPC_LL	r11, VCPU_GPR(R11)(r4)
+	PPC_LL	r12, VCPU_GPR(R12)(r4)
+	PPC_LL	r13, VCPU_GPR(R13)(r4)
 	mtlr	r3
 	mtxer	r5
 	mtctr	r6
@@ -586,12 +581,12 @@ lightweight_exit:
 	mtcr	r7
 
 	/* Finish loading guest volatiles and jump to guest. */
-	PPC_LL	r5, VCPU_GPR(r5)(r4)
-	PPC_LL	r6, VCPU_GPR(r6)(r4)
-	PPC_LL	r7, VCPU_GPR(r7)(r4)
-	PPC_LL	r8, VCPU_GPR(r8)(r4)
-	PPC_LL	r9, VCPU_GPR(r9)(r4)
-
-	PPC_LL	r3, VCPU_GPR(r3)(r4)
-	PPC_LL	r4, VCPU_GPR(r4)(r4)
+	PPC_LL	r5, VCPU_GPR(R5)(r4)
+	PPC_LL	r6, VCPU_GPR(R6)(r4)
+	PPC_LL	r7, VCPU_GPR(R7)(r4)
+	PPC_LL	r8, VCPU_GPR(R8)(r4)
+	PPC_LL	r9, VCPU_GPR(R9)(r4)
+
+	PPC_LL	r3, VCPU_GPR(R3)(r4)
+	PPC_LL	r4, VCPU_GPR(R4)(r4)
 	rfi
diff --git a/arch/powerpc/kvm/e500_emulate.c b/arch/powerpc/kvm/e500_emulate.c
index 8b99e076dc81..e04b0ef55ce0 100644
--- a/arch/powerpc/kvm/e500_emulate.c
+++ b/arch/powerpc/kvm/e500_emulate.c
@@ -269,6 +269,9 @@ int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, ulong *spr_val)
 		*spr_val = vcpu->arch.shared->mas7_3 >> 32;
 		break;
 #endif
+	case SPRN_DECAR:
+		*spr_val = vcpu->arch.decar;
+		break;
 	case SPRN_TLB0CFG:
 		*spr_val = vcpu->arch.tlbcfg[0];
 		break;
diff --git a/arch/powerpc/kvm/e500mc.c b/arch/powerpc/kvm/e500mc.c
index fe6c1de6b701..1f89d26e65fb 100644
--- a/arch/powerpc/kvm/e500mc.c
+++ b/arch/powerpc/kvm/e500mc.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2010 Freescale Semiconductor, Inc. All rights reserved.
+ * Copyright (C) 2010,2012 Freescale Semiconductor, Inc. All rights reserved.
  *
  * Author: Varun Sethi, <varun.sethi@freescale.com>
  *
@@ -57,7 +57,8 @@ void kvmppc_e500_tlbil_one(struct kvmppc_vcpu_e500 *vcpu_e500,
 			   struct kvm_book3e_206_tlb_entry *gtlbe)
 {
 	unsigned int tid, ts;
-	u32 val, eaddr, lpid;
+	gva_t eaddr;
+	u32 val, lpid;
 	unsigned long flags;
 
 	ts = get_tlb_ts(gtlbe);
@@ -183,6 +184,9 @@ int kvmppc_core_vcpu_setup(struct kvm_vcpu *vcpu)
 
 	vcpu->arch.shadow_epcr = SPRN_EPCR_DSIGS | SPRN_EPCR_DGTMI | \
 				 SPRN_EPCR_DUVD;
+#ifdef CONFIG_64BIT
+	vcpu->arch.shadow_epcr |= SPRN_EPCR_ICM;
+#endif
 	vcpu->arch.shadow_msrp = MSRP_UCLEP | MSRP_DEP | MSRP_PMMP;
 	vcpu->arch.eplc = EPC_EGS | (vcpu->kvm->arch.lpid << EPC_ELPID_SHIFT);
 	vcpu->arch.epsc = vcpu->arch.eplc;
diff --git a/arch/powerpc/kvm/emulate.c b/arch/powerpc/kvm/emulate.c
index f90e86dea7a2..ee04abaefe23 100644
--- a/arch/powerpc/kvm/emulate.c
+++ b/arch/powerpc/kvm/emulate.c
@@ -59,11 +59,13 @@
 #define OP_31_XOP_STHBRX    918
 
 #define OP_LWZ  32
+#define OP_LD   58
 #define OP_LWZU 33
 #define OP_LBZ  34
 #define OP_LBZU 35
 #define OP_STW  36
 #define OP_STWU 37
+#define OP_STD  62
 #define OP_STB  38
 #define OP_STBU 39
 #define OP_LHZ  40
@@ -392,6 +394,12 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 		emulated = kvmppc_handle_load(run, vcpu, rt, 4, 1);
 		break;
 
+	/* TBD: Add support for other 64 bit load variants like ldu, ldux, ldx etc. */
+	case OP_LD:
+		rt = get_rt(inst);
+		emulated = kvmppc_handle_load(run, vcpu, rt, 8, 1);
+		break;
+
 	case OP_LWZU:
 		emulated = kvmppc_handle_load(run, vcpu, rt, 4, 1);
 		kvmppc_set_gpr(vcpu, ra, vcpu->arch.vaddr_accessed);
@@ -412,6 +420,14 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 		                               4, 1);
 		break;
 
+	/* TBD: Add support for other 64 bit store variants like stdu, stdux, stdx etc. */
+	case OP_STD:
+		rs = get_rs(inst);
+		emulated = kvmppc_handle_store(run, vcpu,
+					       kvmppc_get_gpr(vcpu, rs),
+		                               8, 1);
+		break;
+
 	case OP_STWU:
 		emulated = kvmppc_handle_store(run, vcpu,
 					       kvmppc_get_gpr(vcpu, rs),
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 1493c8de947b..87f4dc886076 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -246,6 +246,7 @@ int kvm_dev_ioctl_check_extension(long ext)
 #endif
 #ifdef CONFIG_PPC_BOOK3S_64
 	case KVM_CAP_SPAPR_TCE:
+	case KVM_CAP_PPC_ALLOC_HTAB:
 		r = 1;
 		break;
 #endif /* CONFIG_PPC_BOOK3S_64 */
@@ -802,6 +803,23 @@ long kvm_arch_vm_ioctl(struct file *filp,
 			r = -EFAULT;
 		break;
 	}
+
+	case KVM_PPC_ALLOCATE_HTAB: {
+		struct kvm *kvm = filp->private_data;
+		u32 htab_order;
+
+		r = -EFAULT;
+		if (get_user(htab_order, (u32 __user *)argp))
+			break;
+		r = kvmppc_alloc_reset_hpt(kvm, &htab_order);
+		if (r)
+			break;
+		r = -EFAULT;
+		if (put_user(htab_order, (u32 __user *)argp))
+			break;
+		r = 0;
+		break;
+	}
 #endif /* CONFIG_KVM_BOOK3S_64_HV */
 
 #ifdef CONFIG_PPC_BOOK3S_64
diff --git a/arch/powerpc/lib/Makefile b/arch/powerpc/lib/Makefile
index 7735a2c2e6d9..746e0c895cd7 100644
--- a/arch/powerpc/lib/Makefile
+++ b/arch/powerpc/lib/Makefile
@@ -17,14 +17,15 @@ obj-$(CONFIG_HAS_IOMEM)	+= devres.o
 obj-$(CONFIG_PPC64)	+= copypage_64.o copyuser_64.o \
 			   memcpy_64.o usercopy_64.o mem_64.o string.o \
 			   checksum_wrappers_64.o hweight_64.o \
-			   copyuser_power7.o
+			   copyuser_power7.o string_64.o copypage_power7.o \
+			   memcpy_power7.o
 obj-$(CONFIG_XMON)	+= sstep.o ldstfp.o
 obj-$(CONFIG_KPROBES)	+= sstep.o ldstfp.o
 obj-$(CONFIG_HAVE_HW_BREAKPOINT)	+= sstep.o ldstfp.o
 
 ifeq ($(CONFIG_PPC64),y)
 obj-$(CONFIG_SMP)	+= locks.o
-obj-$(CONFIG_ALTIVEC)	+= copyuser_power7_vmx.o
+obj-$(CONFIG_ALTIVEC)	+= vmx-helper.o
 endif
 
 obj-$(CONFIG_PPC_LIB_RHEAP) += rheap.o
diff --git a/arch/powerpc/lib/checksum_64.S b/arch/powerpc/lib/checksum_64.S
index 18245af38aea..167f72555d60 100644
--- a/arch/powerpc/lib/checksum_64.S
+++ b/arch/powerpc/lib/checksum_64.S
@@ -65,9 +65,6 @@ _GLOBAL(csum_tcpudp_magic)
 	srwi	r3,r3,16
 	blr
 
-#define STACKFRAMESIZE 256
-#define STK_REG(i)	(112 + ((i)-14)*8)
-
 /*
  * Computes the checksum of a memory block at buff, length len,
  * and adds in "sum" (32-bit).
@@ -114,9 +111,9 @@ _GLOBAL(csum_partial)
 	mtctr	r6
 
 	stdu	r1,-STACKFRAMESIZE(r1)
-	std	r14,STK_REG(r14)(r1)
-	std	r15,STK_REG(r15)(r1)
-	std	r16,STK_REG(r16)(r1)
+	std	r14,STK_REG(R14)(r1)
+	std	r15,STK_REG(R15)(r1)
+	std	r16,STK_REG(R16)(r1)
 
 	ld	r6,0(r3)
 	ld	r9,8(r3)
@@ -175,9 +172,9 @@ _GLOBAL(csum_partial)
 	adde	r0,r0,r15
 	adde	r0,r0,r16
 
-	ld	r14,STK_REG(r14)(r1)
-	ld	r15,STK_REG(r15)(r1)
-	ld	r16,STK_REG(r16)(r1)
+	ld	r14,STK_REG(R14)(r1)
+	ld	r15,STK_REG(R15)(r1)
+	ld	r16,STK_REG(R16)(r1)
 	addi	r1,r1,STACKFRAMESIZE
 
 	andi.	r4,r4,63
@@ -299,9 +296,9 @@ dest;	sth	r6,0(r4)
 	mtctr	r6
 
 	stdu	r1,-STACKFRAMESIZE(r1)
-	std	r14,STK_REG(r14)(r1)
-	std	r15,STK_REG(r15)(r1)
-	std	r16,STK_REG(r16)(r1)
+	std	r14,STK_REG(R14)(r1)
+	std	r15,STK_REG(R15)(r1)
+	std	r16,STK_REG(R16)(r1)
 
 source;	ld	r6,0(r3)
 source;	ld	r9,8(r3)
@@ -382,9 +379,9 @@ dest;	std	r16,56(r4)
 	adde	r0,r0,r15
 	adde	r0,r0,r16
 
-	ld	r14,STK_REG(r14)(r1)
-	ld	r15,STK_REG(r15)(r1)
-	ld	r16,STK_REG(r16)(r1)
+	ld	r14,STK_REG(R14)(r1)
+	ld	r15,STK_REG(R15)(r1)
+	ld	r16,STK_REG(R16)(r1)
 	addi	r1,r1,STACKFRAMESIZE
 
 	andi.	r5,r5,63
diff --git a/arch/powerpc/lib/code-patching.c b/arch/powerpc/lib/code-patching.c
index 7c975d43e3f3..dd223b3eb333 100644
--- a/arch/powerpc/lib/code-patching.c
+++ b/arch/powerpc/lib/code-patching.c
@@ -13,17 +13,23 @@
 #include <linux/mm.h>
 #include <asm/page.h>
 #include <asm/code-patching.h>
+#include <asm/uaccess.h>
 
 
-void patch_instruction(unsigned int *addr, unsigned int instr)
+int patch_instruction(unsigned int *addr, unsigned int instr)
 {
-	*addr = instr;
+	int err;
+
+	err = __put_user(instr, addr);
+	if (err)
+		return err;
 	asm ("dcbst 0, %0; sync; icbi 0,%0; sync; isync" : : "r" (addr));
+	return 0;
 }
 
-void patch_branch(unsigned int *addr, unsigned long target, int flags)
+int patch_branch(unsigned int *addr, unsigned long target, int flags)
 {
-	patch_instruction(addr, create_branch(addr, target, flags));
+	return patch_instruction(addr, create_branch(addr, target, flags));
 }
 
 unsigned int create_branch(const unsigned int *addr,
diff --git a/arch/powerpc/lib/copypage_64.S b/arch/powerpc/lib/copypage_64.S
index 53dcb6b1b708..9f9434a85264 100644
--- a/arch/powerpc/lib/copypage_64.S
+++ b/arch/powerpc/lib/copypage_64.S
@@ -17,7 +17,11 @@ PPC64_CACHES:
         .section        ".text"
 
 _GLOBAL(copy_page)
+BEGIN_FTR_SECTION
 	lis	r5,PAGE_SIZE@h
+FTR_SECTION_ELSE
+	b	.copypage_power7
+ALT_FTR_SECTION_END_IFCLR(CPU_FTR_VMX_COPY)
 	ori	r5,r5,PAGE_SIZE@l
 BEGIN_FTR_SECTION
 	ld      r10,PPC64_CACHES@toc(r2)
diff --git a/arch/powerpc/lib/copypage_power7.S b/arch/powerpc/lib/copypage_power7.S
new file mode 100644
index 000000000000..0ef75bf0695c
--- /dev/null
+++ b/arch/powerpc/lib/copypage_power7.S
@@ -0,0 +1,165 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ * Copyright (C) IBM Corporation, 2012
+ *
+ * Author: Anton Blanchard <anton@au.ibm.com>
+ */
+#include <asm/page.h>
+#include <asm/ppc_asm.h>
+
+_GLOBAL(copypage_power7)
+	/*
+	 * We prefetch both the source and destination using enhanced touch
+	 * instructions. We use a stream ID of 0 for the load side and
+	 * 1 for the store side. Since source and destination are page
+	 * aligned we don't need to clear the bottom 7 bits of either
+	 * address.
+	 */
+	ori	r9,r3,1		/* stream=1 */
+
+#ifdef CONFIG_PPC_64K_PAGES
+	lis	r7,0x0E01	/* depth=7, units=512 */
+#else
+	lis	r7,0x0E00	/* depth=7 */
+	ori	r7,r7,0x1000	/* units=32 */
+#endif
+	ori	r10,r7,1	/* stream=1 */
+
+	lis	r8,0x8000	/* GO=1 */
+	clrldi	r8,r8,32
+
+.machine push
+.machine "power4"
+	dcbt	r0,r4,0b01000
+	dcbt	r0,r7,0b01010
+	dcbtst	r0,r9,0b01000
+	dcbtst	r0,r10,0b01010
+	eieio
+	dcbt	r0,r8,0b01010	/* GO */
+.machine pop
+
+#ifdef CONFIG_ALTIVEC
+	mflr	r0
+	std	r3,48(r1)
+	std	r4,56(r1)
+	std	r0,16(r1)
+	stdu	r1,-STACKFRAMESIZE(r1)
+	bl	.enter_vmx_copy
+	cmpwi	r3,0
+	ld	r0,STACKFRAMESIZE+16(r1)
+	ld	r3,STACKFRAMESIZE+48(r1)
+	ld	r4,STACKFRAMESIZE+56(r1)
+	mtlr	r0
+
+	li	r0,(PAGE_SIZE/128)
+	mtctr	r0
+
+	beq	.Lnonvmx_copy
+
+	addi	r1,r1,STACKFRAMESIZE
+
+	li	r6,16
+	li	r7,32
+	li	r8,48
+	li	r9,64
+	li	r10,80
+	li	r11,96
+	li	r12,112
+
+	.align	5
+1:	lvx	vr7,r0,r4
+	lvx	vr6,r4,r6
+	lvx	vr5,r4,r7
+	lvx	vr4,r4,r8
+	lvx	vr3,r4,r9
+	lvx	vr2,r4,r10
+	lvx	vr1,r4,r11
+	lvx	vr0,r4,r12
+	addi	r4,r4,128
+	stvx	vr7,r0,r3
+	stvx	vr6,r3,r6
+	stvx	vr5,r3,r7
+	stvx	vr4,r3,r8
+	stvx	vr3,r3,r9
+	stvx	vr2,r3,r10
+	stvx	vr1,r3,r11
+	stvx	vr0,r3,r12
+	addi	r3,r3,128
+	bdnz	1b
+
+	b	.exit_vmx_copy		/* tail call optimise */
+
+#else
+	li	r0,(PAGE_SIZE/128)
+	mtctr	r0
+
+	stdu	r1,-STACKFRAMESIZE(r1)
+#endif
+
+.Lnonvmx_copy:
+	std	r14,STK_REG(R14)(r1)
+	std	r15,STK_REG(R15)(r1)
+	std	r16,STK_REG(R16)(r1)
+	std	r17,STK_REG(R17)(r1)
+	std	r18,STK_REG(R18)(r1)
+	std	r19,STK_REG(R19)(r1)
+	std	r20,STK_REG(R20)(r1)
+
+1:	ld	r0,0(r4)
+	ld	r5,8(r4)
+	ld	r6,16(r4)
+	ld	r7,24(r4)
+	ld	r8,32(r4)
+	ld	r9,40(r4)
+	ld	r10,48(r4)
+	ld	r11,56(r4)
+	ld	r12,64(r4)
+	ld	r14,72(r4)
+	ld	r15,80(r4)
+	ld	r16,88(r4)
+	ld	r17,96(r4)
+	ld	r18,104(r4)
+	ld	r19,112(r4)
+	ld	r20,120(r4)
+	addi	r4,r4,128
+	std	r0,0(r3)
+	std	r5,8(r3)
+	std	r6,16(r3)
+	std	r7,24(r3)
+	std	r8,32(r3)
+	std	r9,40(r3)
+	std	r10,48(r3)
+	std	r11,56(r3)
+	std	r12,64(r3)
+	std	r14,72(r3)
+	std	r15,80(r3)
+	std	r16,88(r3)
+	std	r17,96(r3)
+	std	r18,104(r3)
+	std	r19,112(r3)
+	std	r20,120(r3)
+	addi	r3,r3,128
+	bdnz	1b
+
+	ld	r14,STK_REG(R14)(r1)
+	ld	r15,STK_REG(R15)(r1)
+	ld	r16,STK_REG(R16)(r1)
+	ld	r17,STK_REG(R17)(r1)
+	ld	r18,STK_REG(R18)(r1)
+	ld	r19,STK_REG(R19)(r1)
+	ld	r20,STK_REG(R20)(r1)
+	addi	r1,r1,STACKFRAMESIZE
+	blr
diff --git a/arch/powerpc/lib/copyuser_power7.S b/arch/powerpc/lib/copyuser_power7.S
index 497db7b23bb1..f9ede7c6606e 100644
--- a/arch/powerpc/lib/copyuser_power7.S
+++ b/arch/powerpc/lib/copyuser_power7.S
@@ -19,9 +19,6 @@
  */
 #include <asm/ppc_asm.h>
 
-#define STACKFRAMESIZE	256
-#define STK_REG(i)	(112 + ((i)-14)*8)
-
 	.macro err1
 100:
 	.section __ex_table,"a"
@@ -57,26 +54,26 @@
 
 
 .Ldo_err4:
-	ld	r16,STK_REG(r16)(r1)
-	ld	r15,STK_REG(r15)(r1)
-	ld	r14,STK_REG(r14)(r1)
+	ld	r16,STK_REG(R16)(r1)
+	ld	r15,STK_REG(R15)(r1)
+	ld	r14,STK_REG(R14)(r1)
 .Ldo_err3:
-	bl	.exit_vmx_copy
+	bl	.exit_vmx_usercopy
 	ld	r0,STACKFRAMESIZE+16(r1)
 	mtlr	r0
 	b	.Lexit
 #endif /* CONFIG_ALTIVEC */
 
 .Ldo_err2:
-	ld	r22,STK_REG(r22)(r1)
-	ld	r21,STK_REG(r21)(r1)
-	ld	r20,STK_REG(r20)(r1)
-	ld	r19,STK_REG(r19)(r1)
-	ld	r18,STK_REG(r18)(r1)
-	ld	r17,STK_REG(r17)(r1)
-	ld	r16,STK_REG(r16)(r1)
-	ld	r15,STK_REG(r15)(r1)
-	ld	r14,STK_REG(r14)(r1)
+	ld	r22,STK_REG(R22)(r1)
+	ld	r21,STK_REG(R21)(r1)
+	ld	r20,STK_REG(R20)(r1)
+	ld	r19,STK_REG(R19)(r1)
+	ld	r18,STK_REG(R18)(r1)
+	ld	r17,STK_REG(R17)(r1)
+	ld	r16,STK_REG(R16)(r1)
+	ld	r15,STK_REG(R15)(r1)
+	ld	r14,STK_REG(R14)(r1)
 .Lexit:
 	addi	r1,r1,STACKFRAMESIZE
 .Ldo_err1:
@@ -137,15 +134,15 @@ err1;	stw	r0,0(r3)
 
 	mflr	r0
 	stdu	r1,-STACKFRAMESIZE(r1)
-	std	r14,STK_REG(r14)(r1)
-	std	r15,STK_REG(r15)(r1)
-	std	r16,STK_REG(r16)(r1)
-	std	r17,STK_REG(r17)(r1)
-	std	r18,STK_REG(r18)(r1)
-	std	r19,STK_REG(r19)(r1)
-	std	r20,STK_REG(r20)(r1)
-	std	r21,STK_REG(r21)(r1)
-	std	r22,STK_REG(r22)(r1)
+	std	r14,STK_REG(R14)(r1)
+	std	r15,STK_REG(R15)(r1)
+	std	r16,STK_REG(R16)(r1)
+	std	r17,STK_REG(R17)(r1)
+	std	r18,STK_REG(R18)(r1)
+	std	r19,STK_REG(R19)(r1)
+	std	r20,STK_REG(R20)(r1)
+	std	r21,STK_REG(R21)(r1)
+	std	r22,STK_REG(R22)(r1)
 	std	r0,STACKFRAMESIZE+16(r1)
 
 	srdi	r6,r5,7
@@ -192,15 +189,15 @@ err2;	std	r21,120(r3)
 
 	clrldi	r5,r5,(64-7)
 
-	ld	r14,STK_REG(r14)(r1)
-	ld	r15,STK_REG(r15)(r1)
-	ld	r16,STK_REG(r16)(r1)
-	ld	r17,STK_REG(r17)(r1)
-	ld	r18,STK_REG(r18)(r1)
-	ld	r19,STK_REG(r19)(r1)
-	ld	r20,STK_REG(r20)(r1)
-	ld	r21,STK_REG(r21)(r1)
-	ld	r22,STK_REG(r22)(r1)
+	ld	r14,STK_REG(R14)(r1)
+	ld	r15,STK_REG(R15)(r1)
+	ld	r16,STK_REG(R16)(r1)
+	ld	r17,STK_REG(R17)(r1)
+	ld	r18,STK_REG(R18)(r1)
+	ld	r19,STK_REG(R19)(r1)
+	ld	r20,STK_REG(R20)(r1)
+	ld	r21,STK_REG(R21)(r1)
+	ld	r22,STK_REG(R22)(r1)
 	addi	r1,r1,STACKFRAMESIZE
 
 	/* Up to 127B to go */
@@ -290,7 +287,7 @@ err1;	stb	r0,0(r3)
 	mflr	r0
 	std	r0,16(r1)
 	stdu	r1,-STACKFRAMESIZE(r1)
-	bl	.enter_vmx_copy
+	bl	.enter_vmx_usercopy
 	cmpwi	r3,0
 	ld	r0,STACKFRAMESIZE+16(r1)
 	ld	r3,STACKFRAMESIZE+48(r1)
@@ -298,6 +295,68 @@ err1;	stb	r0,0(r3)
 	ld	r5,STACKFRAMESIZE+64(r1)
 	mtlr	r0
 
+	/*
+	 * We prefetch both the source and destination using enhanced touch
+	 * instructions. We use a stream ID of 0 for the load side and
+	 * 1 for the store side.
+	 */
+	clrrdi	r6,r4,7
+	clrrdi	r9,r3,7
+	ori	r9,r9,1		/* stream=1 */
+
+	srdi	r7,r5,7		/* length in cachelines, capped at 0x3FF */
+	cmpldi	r7,0x3FF
+	ble	1f
+	li	r7,0x3FF
+1:	lis	r0,0x0E00	/* depth=7 */
+	sldi	r7,r7,7
+	or	r7,r7,r0
+	ori	r10,r7,1	/* stream=1 */
+
+	lis	r8,0x8000	/* GO=1 */
+	clrldi	r8,r8,32
+
+.machine push
+.machine "power4"
+	dcbt	r0,r6,0b01000
+	dcbt	r0,r7,0b01010
+	dcbtst	r0,r9,0b01000
+	dcbtst	r0,r10,0b01010
+	eieio
+	dcbt	r0,r8,0b01010	/* GO */
+.machine pop
+
+	/*
+	 * We prefetch both the source and destination using enhanced touch
+	 * instructions. We use a stream ID of 0 for the load side and
+	 * 1 for the store side.
+	 */
+	clrrdi	r6,r4,7
+	clrrdi	r9,r3,7
+	ori	r9,r9,1		/* stream=1 */
+
+	srdi	r7,r5,7		/* length in cachelines, capped at 0x3FF */
+	cmpldi	cr1,r7,0x3FF
+	ble	cr1,1f
+	li	r7,0x3FF
+1:	lis	r0,0x0E00	/* depth=7 */
+	sldi	r7,r7,7
+	or	r7,r7,r0
+	ori	r10,r7,1	/* stream=1 */
+
+	lis	r8,0x8000	/* GO=1 */
+	clrldi	r8,r8,32
+
+.machine push
+.machine "power4"
+	dcbt	r0,r6,0b01000
+	dcbt	r0,r7,0b01010
+	dcbtst	r0,r9,0b01000
+	dcbtst	r0,r10,0b01010
+	eieio
+	dcbt	r0,r8,0b01010	/* GO */
+.machine pop
+
 	beq	.Lunwind_stack_nonvmx_copy
 
 	/*
@@ -378,9 +437,9 @@ err3;	stvx	vr0,r3,r11
 7:	sub	r5,r5,r6
 	srdi	r6,r5,7
 
-	std	r14,STK_REG(r14)(r1)
-	std	r15,STK_REG(r15)(r1)
-	std	r16,STK_REG(r16)(r1)
+	std	r14,STK_REG(R14)(r1)
+	std	r15,STK_REG(R15)(r1)
+	std	r16,STK_REG(R16)(r1)
 
 	li	r12,64
 	li	r14,80
@@ -415,9 +474,9 @@ err4;	stvx	vr0,r3,r16
 	addi	r3,r3,128
 	bdnz	8b
 
-	ld	r14,STK_REG(r14)(r1)
-	ld	r15,STK_REG(r15)(r1)
-	ld	r16,STK_REG(r16)(r1)
+	ld	r14,STK_REG(R14)(r1)
+	ld	r15,STK_REG(R15)(r1)
+	ld	r16,STK_REG(R16)(r1)
 
 	/* Up to 127B to go */
 	clrldi	r5,r5,(64-7)
@@ -476,7 +535,7 @@ err3;	lbz	r0,0(r4)
 err3;	stb	r0,0(r3)
 
 15:	addi	r1,r1,STACKFRAMESIZE
-	b	.exit_vmx_copy		/* tail call optimise */
+	b	.exit_vmx_usercopy	/* tail call optimise */
 
 .Lvmx_unaligned_copy:
 	/* Get the destination 16B aligned */
@@ -563,9 +622,9 @@ err3;	stvx	vr11,r3,r11
 7:	sub	r5,r5,r6
 	srdi	r6,r5,7
 
-	std	r14,STK_REG(r14)(r1)
-	std	r15,STK_REG(r15)(r1)
-	std	r16,STK_REG(r16)(r1)
+	std	r14,STK_REG(R14)(r1)
+	std	r15,STK_REG(R15)(r1)
+	std	r16,STK_REG(R16)(r1)
 
 	li	r12,64
 	li	r14,80
@@ -608,9 +667,9 @@ err4;	stvx	vr15,r3,r16
 	addi	r3,r3,128
 	bdnz	8b
 
-	ld	r14,STK_REG(r14)(r1)
-	ld	r15,STK_REG(r15)(r1)
-	ld	r16,STK_REG(r16)(r1)
+	ld	r14,STK_REG(R14)(r1)
+	ld	r15,STK_REG(R15)(r1)
+	ld	r16,STK_REG(R16)(r1)
 
 	/* Up to 127B to go */
 	clrldi	r5,r5,(64-7)
@@ -679,5 +738,5 @@ err3;	lbz	r0,0(r4)
 err3;	stb	r0,0(r3)
 
 15:	addi	r1,r1,STACKFRAMESIZE
-	b	.exit_vmx_copy		/* tail call optimise */
+	b	.exit_vmx_usercopy	/* tail call optimise */
 #endif /* CONFiG_ALTIVEC */
diff --git a/arch/powerpc/lib/crtsavres.S b/arch/powerpc/lib/crtsavres.S
index 1c893f05d224..b2c68ce139ae 100644
--- a/arch/powerpc/lib/crtsavres.S
+++ b/arch/powerpc/lib/crtsavres.S
@@ -41,12 +41,13 @@
 #include <asm/ppc_asm.h>
 
 	.file	"crtsavres.S"
-	.section ".text"
 
 #ifdef CONFIG_CC_OPTIMIZE_FOR_SIZE
 
 #ifndef CONFIG_PPC64
 
+	.section ".text"
+
 /* Routines for saving integer registers, called by the compiler.  */
 /* Called with r11 pointing to the stack header word of the caller of the */
 /* function, just beyond the end of the integer save area.  */
@@ -232,6 +233,8 @@ _GLOBAL(_rest32gpr_31_x)
 
 #else /* CONFIG_PPC64 */
 
+	.section ".text.save.restore","ax",@progbits
+
 .globl	_savegpr0_14
 _savegpr0_14:
 	std	r14,-144(r1)
diff --git a/arch/powerpc/lib/hweight_64.S b/arch/powerpc/lib/hweight_64.S
index fda27868cf8c..9b96ff2ecd4d 100644
--- a/arch/powerpc/lib/hweight_64.S
+++ b/arch/powerpc/lib/hweight_64.S
@@ -28,7 +28,7 @@ BEGIN_FTR_SECTION
 	nop
 	nop
 FTR_SECTION_ELSE
-	PPC_POPCNTB(r3,r3)
+	PPC_POPCNTB(R3,R3)
 	clrldi	r3,r3,64-8
 	blr
 ALT_FTR_SECTION_END_IFCLR(CPU_FTR_POPCNTB)
@@ -42,14 +42,14 @@ BEGIN_FTR_SECTION
 	nop
 FTR_SECTION_ELSE
   BEGIN_FTR_SECTION_NESTED(50)
-	PPC_POPCNTB(r3,r3)
+	PPC_POPCNTB(R3,R3)
 	srdi	r4,r3,8
 	add	r3,r4,r3
 	clrldi	r3,r3,64-8
 	blr
   FTR_SECTION_ELSE_NESTED(50)
 	clrlwi  r3,r3,16
-	PPC_POPCNTW(r3,r3)
+	PPC_POPCNTW(R3,R3)
 	clrldi	r3,r3,64-8
 	blr
   ALT_FTR_SECTION_END_NESTED_IFCLR(CPU_FTR_POPCNTD, 50)
@@ -66,7 +66,7 @@ BEGIN_FTR_SECTION
 	nop
 FTR_SECTION_ELSE
   BEGIN_FTR_SECTION_NESTED(51)
-	PPC_POPCNTB(r3,r3)
+	PPC_POPCNTB(R3,R3)
 	srdi	r4,r3,16
 	add	r3,r4,r3
 	srdi	r4,r3,8
@@ -74,7 +74,7 @@ FTR_SECTION_ELSE
 	clrldi	r3,r3,64-8
 	blr
   FTR_SECTION_ELSE_NESTED(51)
-	PPC_POPCNTW(r3,r3)
+	PPC_POPCNTW(R3,R3)
 	clrldi	r3,r3,64-8
 	blr
   ALT_FTR_SECTION_END_NESTED_IFCLR(CPU_FTR_POPCNTD, 51)
@@ -93,7 +93,7 @@ BEGIN_FTR_SECTION
 	nop
 FTR_SECTION_ELSE
   BEGIN_FTR_SECTION_NESTED(52)
-	PPC_POPCNTB(r3,r3)
+	PPC_POPCNTB(R3,R3)
 	srdi	r4,r3,32
 	add	r3,r4,r3
 	srdi	r4,r3,16
@@ -103,7 +103,7 @@ FTR_SECTION_ELSE
 	clrldi	r3,r3,64-8
 	blr
   FTR_SECTION_ELSE_NESTED(52)
-	PPC_POPCNTD(r3,r3)
+	PPC_POPCNTD(R3,R3)
 	clrldi	r3,r3,64-8
 	blr
   ALT_FTR_SECTION_END_NESTED_IFCLR(CPU_FTR_POPCNTD, 52)
diff --git a/arch/powerpc/lib/ldstfp.S b/arch/powerpc/lib/ldstfp.S
index 6a85380520b6..85aec08ab234 100644
--- a/arch/powerpc/lib/ldstfp.S
+++ b/arch/powerpc/lib/ldstfp.S
@@ -330,13 +330,13 @@ _GLOBAL(do_lxvd2x)
 	MTMSRD(r7)
 	isync
 	beq	cr7,1f
-	STXVD2X(0,r1,r8)
+	STXVD2X(0,R1,R8)
 1:	li	r9,-EFAULT
-2:	LXVD2X(0,0,r4)
+2:	LXVD2X(0,R0,R4)
 	li	r9,0
 3:	beq	cr7,4f
 	bl	put_vsr
-	LXVD2X(0,r1,r8)
+	LXVD2X(0,R1,R8)
 4:	PPC_LL	r0,STKFRM+PPC_LR_STKOFF(r1)
 	mtlr	r0
 	MTMSRD(r6)
@@ -358,13 +358,13 @@ _GLOBAL(do_stxvd2x)
 	MTMSRD(r7)
 	isync
 	beq	cr7,1f
-	STXVD2X(0,r1,r8)
+	STXVD2X(0,R1,R8)
 	bl	get_vsr
 1:	li	r9,-EFAULT
-2:	STXVD2X(0,0,r4)
+2:	STXVD2X(0,R0,R4)
 	li	r9,0
 3:	beq	cr7,4f
-	LXVD2X(0,r1,r8)
+	LXVD2X(0,R1,R8)
 4:	PPC_LL	r0,STKFRM+PPC_LR_STKOFF(r1)
 	mtlr	r0
 	MTMSRD(r6)
diff --git a/arch/powerpc/lib/memcpy_64.S b/arch/powerpc/lib/memcpy_64.S
index 82fea3963e15..d2bbbc8d7dc0 100644
--- a/arch/powerpc/lib/memcpy_64.S
+++ b/arch/powerpc/lib/memcpy_64.S
@@ -11,7 +11,11 @@
 
 	.align	7
 _GLOBAL(memcpy)
+BEGIN_FTR_SECTION
 	std	r3,48(r1)	/* save destination pointer for return value */
+FTR_SECTION_ELSE
+	b	memcpy_power7
+ALT_FTR_SECTION_END_IFCLR(CPU_FTR_VMX_COPY)
 	PPC_MTOCRF(0x01,r5)
 	cmpldi	cr1,r5,16
 	neg	r6,r3		# LS 3 bits = # bytes to 8-byte dest bdry
diff --git a/arch/powerpc/lib/memcpy_power7.S b/arch/powerpc/lib/memcpy_power7.S
new file mode 100644
index 000000000000..0efdc51bc716
--- /dev/null
+++ b/arch/powerpc/lib/memcpy_power7.S
@@ -0,0 +1,647 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ * Copyright (C) IBM Corporation, 2012
+ *
+ * Author: Anton Blanchard <anton@au.ibm.com>
+ */
+#include <asm/ppc_asm.h>
+
+_GLOBAL(memcpy_power7)
+#ifdef CONFIG_ALTIVEC
+	cmpldi	r5,16
+	cmpldi	cr1,r5,4096
+
+	std	r3,48(r1)
+
+	blt	.Lshort_copy
+	bgt	cr1,.Lvmx_copy
+#else
+	cmpldi	r5,16
+
+	std	r3,48(r1)
+
+	blt	.Lshort_copy
+#endif
+
+.Lnonvmx_copy:
+	/* Get the source 8B aligned */
+	neg	r6,r4
+	mtocrf	0x01,r6
+	clrldi	r6,r6,(64-3)
+
+	bf	cr7*4+3,1f
+	lbz	r0,0(r4)
+	addi	r4,r4,1
+	stb	r0,0(r3)
+	addi	r3,r3,1
+
+1:	bf	cr7*4+2,2f
+	lhz	r0,0(r4)
+	addi	r4,r4,2
+	sth	r0,0(r3)
+	addi	r3,r3,2
+
+2:	bf	cr7*4+1,3f
+	lwz	r0,0(r4)
+	addi	r4,r4,4
+	stw	r0,0(r3)
+	addi	r3,r3,4
+
+3:	sub	r5,r5,r6
+	cmpldi	r5,128
+	blt	5f
+
+	mflr	r0
+	stdu	r1,-STACKFRAMESIZE(r1)
+	std	r14,STK_REG(R14)(r1)
+	std	r15,STK_REG(R15)(r1)
+	std	r16,STK_REG(R16)(r1)
+	std	r17,STK_REG(R17)(r1)
+	std	r18,STK_REG(R18)(r1)
+	std	r19,STK_REG(R19)(r1)
+	std	r20,STK_REG(R20)(r1)
+	std	r21,STK_REG(R21)(r1)
+	std	r22,STK_REG(R22)(r1)
+	std	r0,STACKFRAMESIZE+16(r1)
+
+	srdi	r6,r5,7
+	mtctr	r6
+
+	/* Now do cacheline (128B) sized loads and stores. */
+	.align	5
+4:
+	ld	r0,0(r4)
+	ld	r6,8(r4)
+	ld	r7,16(r4)
+	ld	r8,24(r4)
+	ld	r9,32(r4)
+	ld	r10,40(r4)
+	ld	r11,48(r4)
+	ld	r12,56(r4)
+	ld	r14,64(r4)
+	ld	r15,72(r4)
+	ld	r16,80(r4)
+	ld	r17,88(r4)
+	ld	r18,96(r4)
+	ld	r19,104(r4)
+	ld	r20,112(r4)
+	ld	r21,120(r4)
+	addi	r4,r4,128
+	std	r0,0(r3)
+	std	r6,8(r3)
+	std	r7,16(r3)
+	std	r8,24(r3)
+	std	r9,32(r3)
+	std	r10,40(r3)
+	std	r11,48(r3)
+	std	r12,56(r3)
+	std	r14,64(r3)
+	std	r15,72(r3)
+	std	r16,80(r3)
+	std	r17,88(r3)
+	std	r18,96(r3)
+	std	r19,104(r3)
+	std	r20,112(r3)
+	std	r21,120(r3)
+	addi	r3,r3,128
+	bdnz	4b
+
+	clrldi	r5,r5,(64-7)
+
+	ld	r14,STK_REG(R14)(r1)
+	ld	r15,STK_REG(R15)(r1)
+	ld	r16,STK_REG(R16)(r1)
+	ld	r17,STK_REG(R17)(r1)
+	ld	r18,STK_REG(R18)(r1)
+	ld	r19,STK_REG(R19)(r1)
+	ld	r20,STK_REG(R20)(r1)
+	ld	r21,STK_REG(R21)(r1)
+	ld	r22,STK_REG(R22)(r1)
+	addi	r1,r1,STACKFRAMESIZE
+
+	/* Up to 127B to go */
+5:	srdi	r6,r5,4
+	mtocrf	0x01,r6
+
+6:	bf	cr7*4+1,7f
+	ld	r0,0(r4)
+	ld	r6,8(r4)
+	ld	r7,16(r4)
+	ld	r8,24(r4)
+	ld	r9,32(r4)
+	ld	r10,40(r4)
+	ld	r11,48(r4)
+	ld	r12,56(r4)
+	addi	r4,r4,64
+	std	r0,0(r3)
+	std	r6,8(r3)
+	std	r7,16(r3)
+	std	r8,24(r3)
+	std	r9,32(r3)
+	std	r10,40(r3)
+	std	r11,48(r3)
+	std	r12,56(r3)
+	addi	r3,r3,64
+
+	/* Up to 63B to go */
+7:	bf	cr7*4+2,8f
+	ld	r0,0(r4)
+	ld	r6,8(r4)
+	ld	r7,16(r4)
+	ld	r8,24(r4)
+	addi	r4,r4,32
+	std	r0,0(r3)
+	std	r6,8(r3)
+	std	r7,16(r3)
+	std	r8,24(r3)
+	addi	r3,r3,32
+
+	/* Up to 31B to go */
+8:	bf	cr7*4+3,9f
+	ld	r0,0(r4)
+	ld	r6,8(r4)
+	addi	r4,r4,16
+	std	r0,0(r3)
+	std	r6,8(r3)
+	addi	r3,r3,16
+
+9:	clrldi	r5,r5,(64-4)
+
+	/* Up to 15B to go */
+.Lshort_copy:
+	mtocrf	0x01,r5
+	bf	cr7*4+0,12f
+	lwz	r0,0(r4)	/* Less chance of a reject with word ops */
+	lwz	r6,4(r4)
+	addi	r4,r4,8
+	stw	r0,0(r3)
+	stw	r6,4(r3)
+	addi	r3,r3,8
+
+12:	bf	cr7*4+1,13f
+	lwz	r0,0(r4)
+	addi	r4,r4,4
+	stw	r0,0(r3)
+	addi	r3,r3,4
+
+13:	bf	cr7*4+2,14f
+	lhz	r0,0(r4)
+	addi	r4,r4,2
+	sth	r0,0(r3)
+	addi	r3,r3,2
+
+14:	bf	cr7*4+3,15f
+	lbz	r0,0(r4)
+	stb	r0,0(r3)
+
+15:	ld	r3,48(r1)
+	blr
+
+.Lunwind_stack_nonvmx_copy:
+	addi	r1,r1,STACKFRAMESIZE
+	b	.Lnonvmx_copy
+
+#ifdef CONFIG_ALTIVEC
+.Lvmx_copy:
+	mflr	r0
+	std	r4,56(r1)
+	std	r5,64(r1)
+	std	r0,16(r1)
+	stdu	r1,-STACKFRAMESIZE(r1)
+	bl	.enter_vmx_copy
+	cmpwi	r3,0
+	ld	r0,STACKFRAMESIZE+16(r1)
+	ld	r3,STACKFRAMESIZE+48(r1)
+	ld	r4,STACKFRAMESIZE+56(r1)
+	ld	r5,STACKFRAMESIZE+64(r1)
+	mtlr	r0
+
+	/*
+	 * We prefetch both the source and destination using enhanced touch
+	 * instructions. We use a stream ID of 0 for the load side and
+	 * 1 for the store side.
+	 */
+	clrrdi	r6,r4,7
+	clrrdi	r9,r3,7
+	ori	r9,r9,1		/* stream=1 */
+
+	srdi	r7,r5,7		/* length in cachelines, capped at 0x3FF */
+	cmpldi	cr1,r7,0x3FF
+	ble	cr1,1f
+	li	r7,0x3FF
+1:	lis	r0,0x0E00	/* depth=7 */
+	sldi	r7,r7,7
+	or	r7,r7,r0
+	ori	r10,r7,1	/* stream=1 */
+
+	lis	r8,0x8000	/* GO=1 */
+	clrldi	r8,r8,32
+
+.machine push
+.machine "power4"
+	dcbt	r0,r6,0b01000
+	dcbt	r0,r7,0b01010
+	dcbtst	r0,r9,0b01000
+	dcbtst	r0,r10,0b01010
+	eieio
+	dcbt	r0,r8,0b01010	/* GO */
+.machine pop
+
+	beq	.Lunwind_stack_nonvmx_copy
+
+	/*
+	 * If source and destination are not relatively aligned we use a
+	 * slower permute loop.
+	 */
+	xor	r6,r4,r3
+	rldicl.	r6,r6,0,(64-4)
+	bne	.Lvmx_unaligned_copy
+
+	/* Get the destination 16B aligned */
+	neg	r6,r3
+	mtocrf	0x01,r6
+	clrldi	r6,r6,(64-4)
+
+	bf	cr7*4+3,1f
+	lbz	r0,0(r4)
+	addi	r4,r4,1
+	stb	r0,0(r3)
+	addi	r3,r3,1
+
+1:	bf	cr7*4+2,2f
+	lhz	r0,0(r4)
+	addi	r4,r4,2
+	sth	r0,0(r3)
+	addi	r3,r3,2
+
+2:	bf	cr7*4+1,3f
+	lwz	r0,0(r4)
+	addi	r4,r4,4
+	stw	r0,0(r3)
+	addi	r3,r3,4
+
+3:	bf	cr7*4+0,4f
+	ld	r0,0(r4)
+	addi	r4,r4,8
+	std	r0,0(r3)
+	addi	r3,r3,8
+
+4:	sub	r5,r5,r6
+
+	/* Get the desination 128B aligned */
+	neg	r6,r3
+	srdi	r7,r6,4
+	mtocrf	0x01,r7
+	clrldi	r6,r6,(64-7)
+
+	li	r9,16
+	li	r10,32
+	li	r11,48
+
+	bf	cr7*4+3,5f
+	lvx	vr1,r0,r4
+	addi	r4,r4,16
+	stvx	vr1,r0,r3
+	addi	r3,r3,16
+
+5:	bf	cr7*4+2,6f
+	lvx	vr1,r0,r4
+	lvx	vr0,r4,r9
+	addi	r4,r4,32
+	stvx	vr1,r0,r3
+	stvx	vr0,r3,r9
+	addi	r3,r3,32
+
+6:	bf	cr7*4+1,7f
+	lvx	vr3,r0,r4
+	lvx	vr2,r4,r9
+	lvx	vr1,r4,r10
+	lvx	vr0,r4,r11
+	addi	r4,r4,64
+	stvx	vr3,r0,r3
+	stvx	vr2,r3,r9
+	stvx	vr1,r3,r10
+	stvx	vr0,r3,r11
+	addi	r3,r3,64
+
+7:	sub	r5,r5,r6
+	srdi	r6,r5,7
+
+	std	r14,STK_REG(R14)(r1)
+	std	r15,STK_REG(R15)(r1)
+	std	r16,STK_REG(R16)(r1)
+
+	li	r12,64
+	li	r14,80
+	li	r15,96
+	li	r16,112
+
+	mtctr	r6
+
+	/*
+	 * Now do cacheline sized loads and stores. By this stage the
+	 * cacheline stores are also cacheline aligned.
+	 */
+	.align	5
+8:
+	lvx	vr7,r0,r4
+	lvx	vr6,r4,r9
+	lvx	vr5,r4,r10
+	lvx	vr4,r4,r11
+	lvx	vr3,r4,r12
+	lvx	vr2,r4,r14
+	lvx	vr1,r4,r15
+	lvx	vr0,r4,r16
+	addi	r4,r4,128
+	stvx	vr7,r0,r3
+	stvx	vr6,r3,r9
+	stvx	vr5,r3,r10
+	stvx	vr4,r3,r11
+	stvx	vr3,r3,r12
+	stvx	vr2,r3,r14
+	stvx	vr1,r3,r15
+	stvx	vr0,r3,r16
+	addi	r3,r3,128
+	bdnz	8b
+
+	ld	r14,STK_REG(R14)(r1)
+	ld	r15,STK_REG(R15)(r1)
+	ld	r16,STK_REG(R16)(r1)
+
+	/* Up to 127B to go */
+	clrldi	r5,r5,(64-7)
+	srdi	r6,r5,4
+	mtocrf	0x01,r6
+
+	bf	cr7*4+1,9f
+	lvx	vr3,r0,r4
+	lvx	vr2,r4,r9
+	lvx	vr1,r4,r10
+	lvx	vr0,r4,r11
+	addi	r4,r4,64
+	stvx	vr3,r0,r3
+	stvx	vr2,r3,r9
+	stvx	vr1,r3,r10
+	stvx	vr0,r3,r11
+	addi	r3,r3,64
+
+9:	bf	cr7*4+2,10f
+	lvx	vr1,r0,r4
+	lvx	vr0,r4,r9
+	addi	r4,r4,32
+	stvx	vr1,r0,r3
+	stvx	vr0,r3,r9
+	addi	r3,r3,32
+
+10:	bf	cr7*4+3,11f
+	lvx	vr1,r0,r4
+	addi	r4,r4,16
+	stvx	vr1,r0,r3
+	addi	r3,r3,16
+
+	/* Up to 15B to go */
+11:	clrldi	r5,r5,(64-4)
+	mtocrf	0x01,r5
+	bf	cr7*4+0,12f
+	ld	r0,0(r4)
+	addi	r4,r4,8
+	std	r0,0(r3)
+	addi	r3,r3,8
+
+12:	bf	cr7*4+1,13f
+	lwz	r0,0(r4)
+	addi	r4,r4,4
+	stw	r0,0(r3)
+	addi	r3,r3,4
+
+13:	bf	cr7*4+2,14f
+	lhz	r0,0(r4)
+	addi	r4,r4,2
+	sth	r0,0(r3)
+	addi	r3,r3,2
+
+14:	bf	cr7*4+3,15f
+	lbz	r0,0(r4)
+	stb	r0,0(r3)
+
+15:	addi	r1,r1,STACKFRAMESIZE
+	ld	r3,48(r1)
+	b	.exit_vmx_copy		/* tail call optimise */
+
+.Lvmx_unaligned_copy:
+	/* Get the destination 16B aligned */
+	neg	r6,r3
+	mtocrf	0x01,r6
+	clrldi	r6,r6,(64-4)
+
+	bf	cr7*4+3,1f
+	lbz	r0,0(r4)
+	addi	r4,r4,1
+	stb	r0,0(r3)
+	addi	r3,r3,1
+
+1:	bf	cr7*4+2,2f
+	lhz	r0,0(r4)
+	addi	r4,r4,2
+	sth	r0,0(r3)
+	addi	r3,r3,2
+
+2:	bf	cr7*4+1,3f
+	lwz	r0,0(r4)
+	addi	r4,r4,4
+	stw	r0,0(r3)
+	addi	r3,r3,4
+
+3:	bf	cr7*4+0,4f
+	lwz	r0,0(r4)	/* Less chance of a reject with word ops */
+	lwz	r7,4(r4)
+	addi	r4,r4,8
+	stw	r0,0(r3)
+	stw	r7,4(r3)
+	addi	r3,r3,8
+
+4:	sub	r5,r5,r6
+
+	/* Get the desination 128B aligned */
+	neg	r6,r3
+	srdi	r7,r6,4
+	mtocrf	0x01,r7
+	clrldi	r6,r6,(64-7)
+
+	li	r9,16
+	li	r10,32
+	li	r11,48
+
+	lvsl	vr16,0,r4	/* Setup permute control vector */
+	lvx	vr0,0,r4
+	addi	r4,r4,16
+
+	bf	cr7*4+3,5f
+	lvx	vr1,r0,r4
+	vperm	vr8,vr0,vr1,vr16
+	addi	r4,r4,16
+	stvx	vr8,r0,r3
+	addi	r3,r3,16
+	vor	vr0,vr1,vr1
+
+5:	bf	cr7*4+2,6f
+	lvx	vr1,r0,r4
+	vperm	vr8,vr0,vr1,vr16
+	lvx	vr0,r4,r9
+	vperm	vr9,vr1,vr0,vr16
+	addi	r4,r4,32
+	stvx	vr8,r0,r3
+	stvx	vr9,r3,r9
+	addi	r3,r3,32
+
+6:	bf	cr7*4+1,7f
+	lvx	vr3,r0,r4
+	vperm	vr8,vr0,vr3,vr16
+	lvx	vr2,r4,r9
+	vperm	vr9,vr3,vr2,vr16
+	lvx	vr1,r4,r10
+	vperm	vr10,vr2,vr1,vr16
+	lvx	vr0,r4,r11
+	vperm	vr11,vr1,vr0,vr16
+	addi	r4,r4,64
+	stvx	vr8,r0,r3
+	stvx	vr9,r3,r9
+	stvx	vr10,r3,r10
+	stvx	vr11,r3,r11
+	addi	r3,r3,64
+
+7:	sub	r5,r5,r6
+	srdi	r6,r5,7
+
+	std	r14,STK_REG(R14)(r1)
+	std	r15,STK_REG(R15)(r1)
+	std	r16,STK_REG(R16)(r1)
+
+	li	r12,64
+	li	r14,80
+	li	r15,96
+	li	r16,112
+
+	mtctr	r6
+
+	/*
+	 * Now do cacheline sized loads and stores. By this stage the
+	 * cacheline stores are also cacheline aligned.
+	 */
+	.align	5
+8:
+	lvx	vr7,r0,r4
+	vperm	vr8,vr0,vr7,vr16
+	lvx	vr6,r4,r9
+	vperm	vr9,vr7,vr6,vr16
+	lvx	vr5,r4,r10
+	vperm	vr10,vr6,vr5,vr16
+	lvx	vr4,r4,r11
+	vperm	vr11,vr5,vr4,vr16
+	lvx	vr3,r4,r12
+	vperm	vr12,vr4,vr3,vr16
+	lvx	vr2,r4,r14
+	vperm	vr13,vr3,vr2,vr16
+	lvx	vr1,r4,r15
+	vperm	vr14,vr2,vr1,vr16
+	lvx	vr0,r4,r16
+	vperm	vr15,vr1,vr0,vr16
+	addi	r4,r4,128
+	stvx	vr8,r0,r3
+	stvx	vr9,r3,r9
+	stvx	vr10,r3,r10
+	stvx	vr11,r3,r11
+	stvx	vr12,r3,r12
+	stvx	vr13,r3,r14
+	stvx	vr14,r3,r15
+	stvx	vr15,r3,r16
+	addi	r3,r3,128
+	bdnz	8b
+
+	ld	r14,STK_REG(R14)(r1)
+	ld	r15,STK_REG(R15)(r1)
+	ld	r16,STK_REG(R16)(r1)
+
+	/* Up to 127B to go */
+	clrldi	r5,r5,(64-7)
+	srdi	r6,r5,4
+	mtocrf	0x01,r6
+
+	bf	cr7*4+1,9f
+	lvx	vr3,r0,r4
+	vperm	vr8,vr0,vr3,vr16
+	lvx	vr2,r4,r9
+	vperm	vr9,vr3,vr2,vr16
+	lvx	vr1,r4,r10
+	vperm	vr10,vr2,vr1,vr16
+	lvx	vr0,r4,r11
+	vperm	vr11,vr1,vr0,vr16
+	addi	r4,r4,64
+	stvx	vr8,r0,r3
+	stvx	vr9,r3,r9
+	stvx	vr10,r3,r10
+	stvx	vr11,r3,r11
+	addi	r3,r3,64
+
+9:	bf	cr7*4+2,10f
+	lvx	vr1,r0,r4
+	vperm	vr8,vr0,vr1,vr16
+	lvx	vr0,r4,r9
+	vperm	vr9,vr1,vr0,vr16
+	addi	r4,r4,32
+	stvx	vr8,r0,r3
+	stvx	vr9,r3,r9
+	addi	r3,r3,32
+
+10:	bf	cr7*4+3,11f
+	lvx	vr1,r0,r4
+	vperm	vr8,vr0,vr1,vr16
+	addi	r4,r4,16
+	stvx	vr8,r0,r3
+	addi	r3,r3,16
+
+	/* Up to 15B to go */
+11:	clrldi	r5,r5,(64-4)
+	addi	r4,r4,-16	/* Unwind the +16 load offset */
+	mtocrf	0x01,r5
+	bf	cr7*4+0,12f
+	lwz	r0,0(r4)	/* Less chance of a reject with word ops */
+	lwz	r6,4(r4)
+	addi	r4,r4,8
+	stw	r0,0(r3)
+	stw	r6,4(r3)
+	addi	r3,r3,8
+
+12:	bf	cr7*4+1,13f
+	lwz	r0,0(r4)
+	addi	r4,r4,4
+	stw	r0,0(r3)
+	addi	r3,r3,4
+
+13:	bf	cr7*4+2,14f
+	lhz	r0,0(r4)
+	addi	r4,r4,2
+	sth	r0,0(r3)
+	addi	r3,r3,2
+
+14:	bf	cr7*4+3,15f
+	lbz	r0,0(r4)
+	stb	r0,0(r3)
+
+15:	addi	r1,r1,STACKFRAMESIZE
+	ld	r3,48(r1)
+	b	.exit_vmx_copy		/* tail call optimise */
+#endif /* CONFiG_ALTIVEC */
diff --git a/arch/powerpc/lib/string.S b/arch/powerpc/lib/string.S
index 093d6316435c..1b5a0a09d609 100644
--- a/arch/powerpc/lib/string.S
+++ b/arch/powerpc/lib/string.S
@@ -119,6 +119,7 @@ _GLOBAL(memchr)
 2:	li	r3,0
 	blr
 
+#ifdef CONFIG_PPC32
 _GLOBAL(__clear_user)
 	addi	r6,r3,-4
 	li	r3,0
@@ -160,3 +161,4 @@ _GLOBAL(__clear_user)
 	PPC_LONG	1b,91b
 	PPC_LONG	8b,92b
 	.text
+#endif
diff --git a/arch/powerpc/lib/string_64.S b/arch/powerpc/lib/string_64.S
new file mode 100644
index 000000000000..3b1e48049faf
--- /dev/null
+++ b/arch/powerpc/lib/string_64.S
@@ -0,0 +1,202 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ * Copyright (C) IBM Corporation, 2012
+ *
+ * Author: Anton Blanchard <anton@au.ibm.com>
+ */
+
+#include <asm/ppc_asm.h>
+#include <asm/asm-offsets.h>
+
+	.section	".toc","aw"
+PPC64_CACHES:
+	.tc		ppc64_caches[TC],ppc64_caches
+	.section	".text"
+
+/**
+ * __clear_user: - Zero a block of memory in user space, with less checking.
+ * @to:   Destination address, in user space.
+ * @n:    Number of bytes to zero.
+ *
+ * Zero a block of memory in user space.  Caller must check
+ * the specified block with access_ok() before calling this function.
+ *
+ * Returns number of bytes that could not be cleared.
+ * On success, this will be zero.
+ */
+
+	.macro err1
+100:
+	.section __ex_table,"a"
+	.align 3
+	.llong 100b,.Ldo_err1
+	.previous
+	.endm
+
+	.macro err2
+200:
+	.section __ex_table,"a"
+	.align 3
+	.llong 200b,.Ldo_err2
+	.previous
+	.endm
+
+	.macro err3
+300:
+	.section __ex_table,"a"
+	.align 3
+	.llong 300b,.Ldo_err3
+	.previous
+	.endm
+
+.Ldo_err1:
+	mr	r3,r8
+
+.Ldo_err2:
+	mtctr	r4
+1:
+err3;	stb	r0,0(r3)
+	addi	r3,r3,1
+	addi	r4,r4,-1
+	bdnz	1b
+
+.Ldo_err3:
+	mr	r3,r4
+	blr
+
+_GLOBAL(__clear_user)
+	cmpdi	r4,32
+	neg	r6,r3
+	li	r0,0
+	blt	.Lshort_clear
+	mr	r8,r3
+	mtocrf	0x01,r6
+	clrldi	r6,r6,(64-3)
+
+	/* Get the destination 8 byte aligned */
+	bf	cr7*4+3,1f
+err1;	stb	r0,0(r3)
+	addi	r3,r3,1
+
+1:	bf	cr7*4+2,2f
+err1;	sth	r0,0(r3)
+	addi	r3,r3,2
+
+2:	bf	cr7*4+1,3f
+err1;	stw	r0,0(r3)
+	addi	r3,r3,4
+
+3:	sub	r4,r4,r6
+
+	cmpdi	r4,32
+	cmpdi	cr1,r4,512
+	blt	.Lshort_clear
+	bgt	cr1,.Llong_clear
+
+.Lmedium_clear:
+	srdi	r6,r4,5
+	mtctr	r6
+
+	/* Do 32 byte chunks */
+4:
+err2;	std	r0,0(r3)
+err2;	std	r0,8(r3)
+err2;	std	r0,16(r3)
+err2;	std	r0,24(r3)
+	addi	r3,r3,32
+	addi	r4,r4,-32
+	bdnz	4b
+
+.Lshort_clear:
+	/* up to 31 bytes to go */
+	cmpdi	r4,16
+	blt	6f
+err2;	std	r0,0(r3)
+err2;	std	r0,8(r3)
+	addi	r3,r3,16
+	addi	r4,r4,-16
+
+	/* Up to 15 bytes to go */
+6:	mr	r8,r3
+	clrldi	r4,r4,(64-4)
+	mtocrf	0x01,r4
+	bf	cr7*4+0,7f
+err1;	std	r0,0(r3)
+	addi	r3,r3,8
+
+7:	bf	cr7*4+1,8f
+err1;	stw	r0,0(r3)
+	addi	r3,r3,4
+
+8:	bf	cr7*4+2,9f
+err1;	sth	r0,0(r3)
+	addi	r3,r3,2
+
+9:	bf	cr7*4+3,10f
+err1;	stb	r0,0(r3)
+
+10:	li	r3,0
+	blr
+
+.Llong_clear:
+	ld	r5,PPC64_CACHES@toc(r2)
+
+	bf	cr7*4+0,11f
+err2;	std	r0,0(r3)
+	addi	r3,r3,8
+	addi	r4,r4,-8
+
+	/* Destination is 16 byte aligned, need to get it cacheline aligned */
+11:	lwz	r7,DCACHEL1LOGLINESIZE(r5)
+	lwz	r9,DCACHEL1LINESIZE(r5)
+
+	/*
+	 * With worst case alignment the long clear loop takes a minimum
+	 * of 1 byte less than 2 cachelines.
+	 */
+	sldi	r10,r9,2
+	cmpd	r4,r10
+	blt	.Lmedium_clear
+
+	neg	r6,r3
+	addi	r10,r9,-1
+	and.	r5,r6,r10
+	beq	13f
+
+	srdi	r6,r5,4
+	mtctr	r6
+	mr	r8,r3
+12:
+err1;	std	r0,0(r3)
+err1;	std	r0,8(r3)
+	addi	r3,r3,16
+	bdnz	12b
+
+	sub	r4,r4,r5
+
+13:	srd	r6,r4,r7
+	mtctr	r6
+	mr	r8,r3
+14:
+err1;	dcbz	r0,r3
+	add	r3,r3,r9
+	bdnz	14b
+
+	and	r4,r4,r10
+
+	cmpdi	r4,32
+	blt	.Lshort_clear
+	b	.Lmedium_clear
diff --git a/arch/powerpc/lib/copyuser_power7_vmx.c b/arch/powerpc/lib/vmx-helper.c
index bf2654f2b68e..3cf529ceec5b 100644
--- a/arch/powerpc/lib/copyuser_power7_vmx.c
+++ b/arch/powerpc/lib/vmx-helper.c
@@ -22,7 +22,7 @@
 #include <linux/hardirq.h>
 #include <asm/switch_to.h>
 
-int enter_vmx_copy(void)
+int enter_vmx_usercopy(void)
 {
 	if (in_interrupt())
 		return 0;
@@ -44,8 +44,31 @@ int enter_vmx_copy(void)
  * This function must return 0 because we tail call optimise when calling
  * from __copy_tofrom_user_power7 which returns 0 on success.
  */
-int exit_vmx_copy(void)
+int exit_vmx_usercopy(void)
 {
 	pagefault_enable();
 	return 0;
 }
+
+int enter_vmx_copy(void)
+{
+	if (in_interrupt())
+		return 0;
+
+	preempt_disable();
+
+	enable_kernel_altivec();
+
+	return 1;
+}
+
+/*
+ * All calls to this function will be optimised into tail calls. We are
+ * passed a pointer to the destination which we return as required by a
+ * memcpy implementation.
+ */
+void *exit_vmx_copy(void *dest)
+{
+	preempt_enable();
+	return dest;
+}
diff --git a/arch/powerpc/mm/hash_low_32.S b/arch/powerpc/mm/hash_low_32.S
index b13d58932bf6..115347f74ce5 100644
--- a/arch/powerpc/mm/hash_low_32.S
+++ b/arch/powerpc/mm/hash_low_32.S
@@ -184,7 +184,7 @@ _GLOBAL(add_hash_page)
 	add	r3,r3,r0		/* note create_hpte trims to 24 bits */
 
 #ifdef CONFIG_SMP
-	rlwinm	r8,r1,0,0,(31-THREAD_SHIFT) /* use cpu number to make tag */
+	CURRENT_THREAD_INFO(r8, r1)	/* use cpu number to make tag */
 	lwz	r8,TI_CPU(r8)		/* to go in mmu_hash_lock */
 	oris	r8,r8,12
 #endif /* CONFIG_SMP */
@@ -545,7 +545,7 @@ _GLOBAL(flush_hash_pages)
 #ifdef CONFIG_SMP
 	addis	r9,r7,mmu_hash_lock@ha
 	addi	r9,r9,mmu_hash_lock@l
-	rlwinm	r8,r1,0,0,(31-THREAD_SHIFT)
+	CURRENT_THREAD_INFO(r8, r1)
 	add	r8,r8,r7
 	lwz	r8,TI_CPU(r8)
 	oris	r8,r8,9
@@ -639,7 +639,7 @@ _GLOBAL(flush_hash_patch_B)
  */
 _GLOBAL(_tlbie)
 #ifdef CONFIG_SMP
-	rlwinm	r8,r1,0,0,(31-THREAD_SHIFT)
+	CURRENT_THREAD_INFO(r8, r1)
 	lwz	r8,TI_CPU(r8)
 	oris	r8,r8,11
 	mfmsr	r10
@@ -677,7 +677,7 @@ _GLOBAL(_tlbie)
  */
 _GLOBAL(_tlbia)
 #if defined(CONFIG_SMP)
-	rlwinm	r8,r1,0,0,(31-THREAD_SHIFT)
+	CURRENT_THREAD_INFO(r8, r1)
 	lwz	r8,TI_CPU(r8)
 	oris	r8,r8,10
 	mfmsr	r10
diff --git a/arch/powerpc/mm/hash_low_64.S b/arch/powerpc/mm/hash_low_64.S
index a242b5d7cbe4..602aeb06d298 100644
--- a/arch/powerpc/mm/hash_low_64.S
+++ b/arch/powerpc/mm/hash_low_64.S
@@ -34,14 +34,6 @@
  *         |   CR save area			(SP + 8)
  * SP ---> +-- Back chain			(SP + 0)
  */
-#define STACKFRAMESIZE	256
-
-/* Save parameters offsets */
-#define STK_PARM(i)	(STACKFRAMESIZE + 48 + ((i)-3)*8)
-
-/* Save non-volatile offsets */
-#define STK_REG(i)	(112 + ((i)-14)*8)
-
 
 #ifndef CONFIG_PPC_64K_PAGES
 
@@ -64,9 +56,9 @@ _GLOBAL(__hash_page_4K)
 	std	r0,16(r1)
 	stdu	r1,-STACKFRAMESIZE(r1)
 	/* Save all params that we need after a function call */
-	std	r6,STK_PARM(r6)(r1)
-	std	r8,STK_PARM(r8)(r1)
-	std	r9,STK_PARM(r9)(r1)
+	std	r6,STK_PARAM(R6)(r1)
+	std	r8,STK_PARAM(R8)(r1)
+	std	r9,STK_PARAM(R9)(r1)
 	
 	/* Save non-volatile registers.
 	 * r31 will hold "old PTE"
@@ -75,11 +67,11 @@ _GLOBAL(__hash_page_4K)
 	 * r28 is a hash value
 	 * r27 is hashtab mask (maybe dynamic patched instead ?)
 	 */
-	std	r27,STK_REG(r27)(r1)
-	std	r28,STK_REG(r28)(r1)
-	std	r29,STK_REG(r29)(r1)
-	std	r30,STK_REG(r30)(r1)
-	std	r31,STK_REG(r31)(r1)
+	std	r27,STK_REG(R27)(r1)
+	std	r28,STK_REG(R28)(r1)
+	std	r29,STK_REG(R29)(r1)
+	std	r30,STK_REG(R30)(r1)
+	std	r31,STK_REG(R31)(r1)
 	
 	/* Step 1:
 	 *
@@ -162,7 +154,7 @@ END_FTR_SECTION(CPU_FTR_NOEXECUTE|CPU_FTR_COHERENT_ICACHE, CPU_FTR_NOEXECUTE)
 	/* At this point, r3 contains new PP bits, save them in
 	 * place of "access" in the param area (sic)
 	 */
-	std	r3,STK_PARM(r4)(r1)
+	std	r3,STK_PARAM(R4)(r1)
 
 	/* Get htab_hash_mask */
 	ld	r4,htab_hash_mask@got(2)
@@ -192,11 +184,11 @@ htab_insert_pte:
 	rldicr	r3,r0,3,63-3		/* r3 = (hash & mask) << 3 */
 
 	/* Call ppc_md.hpte_insert */
-	ld	r6,STK_PARM(r4)(r1)	/* Retrieve new pp bits */
+	ld	r6,STK_PARAM(R4)(r1)	/* Retrieve new pp bits */
 	mr	r4,r29			/* Retrieve va */
 	li	r7,0			/* !bolted, !secondary */
 	li	r8,MMU_PAGE_4K		/* page size */
-	ld	r9,STK_PARM(r9)(r1)	/* segment size */
+	ld	r9,STK_PARAM(R9)(r1)	/* segment size */
 _GLOBAL(htab_call_hpte_insert1)
 	bl	.			/* Patched by htab_finish_init() */
 	cmpdi	0,r3,0
@@ -215,11 +207,11 @@ _GLOBAL(htab_call_hpte_insert1)
 	rldicr	r3,r0,3,63-3	/* r0 = (~hash & mask) << 3 */
 	
 	/* Call ppc_md.hpte_insert */
-	ld	r6,STK_PARM(r4)(r1)	/* Retrieve new pp bits */
+	ld	r6,STK_PARAM(R4)(r1)	/* Retrieve new pp bits */
 	mr	r4,r29			/* Retrieve va */
 	li	r7,HPTE_V_SECONDARY	/* !bolted, secondary */
 	li	r8,MMU_PAGE_4K		/* page size */
-	ld	r9,STK_PARM(r9)(r1)	/* segment size */
+	ld	r9,STK_PARAM(R9)(r1)	/* segment size */
 _GLOBAL(htab_call_hpte_insert2)
 	bl	.			/* Patched by htab_finish_init() */
 	cmpdi	0,r3,0
@@ -255,15 +247,15 @@ htab_pte_insert_ok:
 	 * (maybe add eieio may be good still ?)
 	 */
 htab_write_out_pte:
-	ld	r6,STK_PARM(r6)(r1)
+	ld	r6,STK_PARAM(R6)(r1)
 	std	r30,0(r6)
 	li	r3, 0
 htab_bail:
-	ld	r27,STK_REG(r27)(r1)
-	ld	r28,STK_REG(r28)(r1)
-	ld	r29,STK_REG(r29)(r1)
-	ld      r30,STK_REG(r30)(r1)
-	ld      r31,STK_REG(r31)(r1)
+	ld	r27,STK_REG(R27)(r1)
+	ld	r28,STK_REG(R28)(r1)
+	ld	r29,STK_REG(R29)(r1)
+	ld      r30,STK_REG(R30)(r1)
+	ld      r31,STK_REG(R31)(r1)
 	addi    r1,r1,STACKFRAMESIZE
 	ld      r0,16(r1)
 	mtlr    r0
@@ -288,8 +280,8 @@ htab_modify_pte:
 	/* Call ppc_md.hpte_updatepp */
 	mr	r5,r29			/* va */
 	li	r6,MMU_PAGE_4K		/* page size */
-	ld	r7,STK_PARM(r9)(r1)	/* segment size */
-	ld	r8,STK_PARM(r8)(r1)	/* get "local" param */
+	ld	r7,STK_PARAM(R9)(r1)	/* segment size */
+	ld	r8,STK_PARAM(R8)(r1)	/* get "local" param */
 _GLOBAL(htab_call_hpte_updatepp)
 	bl	.			/* Patched by htab_finish_init() */
 
@@ -312,7 +304,7 @@ htab_wrong_access:
 
 htab_pte_insert_failure:
 	/* Bail out restoring old PTE */
-	ld	r6,STK_PARM(r6)(r1)
+	ld	r6,STK_PARAM(R6)(r1)
 	std	r31,0(r6)
 	li	r3,-1
 	b	htab_bail
@@ -340,9 +332,9 @@ _GLOBAL(__hash_page_4K)
 	std	r0,16(r1)
 	stdu	r1,-STACKFRAMESIZE(r1)
 	/* Save all params that we need after a function call */
-	std	r6,STK_PARM(r6)(r1)
-	std	r8,STK_PARM(r8)(r1)
-	std	r9,STK_PARM(r9)(r1)
+	std	r6,STK_PARAM(R6)(r1)
+	std	r8,STK_PARAM(R8)(r1)
+	std	r9,STK_PARAM(R9)(r1)
 
 	/* Save non-volatile registers.
 	 * r31 will hold "old PTE"
@@ -353,13 +345,13 @@ _GLOBAL(__hash_page_4K)
 	 * r26 is the hidx mask
 	 * r25 is the index in combo page
 	 */
-	std	r25,STK_REG(r25)(r1)
-	std	r26,STK_REG(r26)(r1)
-	std	r27,STK_REG(r27)(r1)
-	std	r28,STK_REG(r28)(r1)
-	std	r29,STK_REG(r29)(r1)
-	std	r30,STK_REG(r30)(r1)
-	std	r31,STK_REG(r31)(r1)
+	std	r25,STK_REG(R25)(r1)
+	std	r26,STK_REG(R26)(r1)
+	std	r27,STK_REG(R27)(r1)
+	std	r28,STK_REG(R28)(r1)
+	std	r29,STK_REG(R29)(r1)
+	std	r30,STK_REG(R30)(r1)
+	std	r31,STK_REG(R31)(r1)
 
 	/* Step 1:
 	 *
@@ -452,7 +444,7 @@ END_FTR_SECTION(CPU_FTR_NOEXECUTE|CPU_FTR_COHERENT_ICACHE, CPU_FTR_NOEXECUTE)
 	/* At this point, r3 contains new PP bits, save them in
 	 * place of "access" in the param area (sic)
 	 */
-	std	r3,STK_PARM(r4)(r1)
+	std	r3,STK_PARAM(R4)(r1)
 
 	/* Get htab_hash_mask */
 	ld	r4,htab_hash_mask@got(2)
@@ -473,7 +465,7 @@ END_FTR_SECTION(CPU_FTR_NOEXECUTE|CPU_FTR_COHERENT_ICACHE, CPU_FTR_NOEXECUTE)
 	andis.	r0,r31,_PAGE_COMBO@h
 	beq	htab_inval_old_hpte
 
-	ld	r6,STK_PARM(r6)(r1)
+	ld	r6,STK_PARAM(R6)(r1)
 	ori	r26,r6,0x8000		/* Load the hidx mask */
 	ld	r26,0(r26)
 	addi	r5,r25,36		/* Check actual HPTE_SUB bit, this */
@@ -495,11 +487,11 @@ htab_special_pfn:
 	rldicr	r3,r0,3,63-3		/* r0 = (hash & mask) << 3 */
 
 	/* Call ppc_md.hpte_insert */
-	ld	r6,STK_PARM(r4)(r1)	/* Retrieve new pp bits */
+	ld	r6,STK_PARAM(R4)(r1)	/* Retrieve new pp bits */
 	mr	r4,r29			/* Retrieve va */
 	li	r7,0			/* !bolted, !secondary */
 	li	r8,MMU_PAGE_4K		/* page size */
-	ld	r9,STK_PARM(r9)(r1)	/* segment size */
+	ld	r9,STK_PARAM(R9)(r1)	/* segment size */
 _GLOBAL(htab_call_hpte_insert1)
 	bl	.			/* patched by htab_finish_init() */
 	cmpdi	0,r3,0
@@ -522,11 +514,11 @@ _GLOBAL(htab_call_hpte_insert1)
 	rldicr	r3,r0,3,63-3		/* r0 = (~hash & mask) << 3 */
 
 	/* Call ppc_md.hpte_insert */
-	ld	r6,STK_PARM(r4)(r1)	/* Retrieve new pp bits */
+	ld	r6,STK_PARAM(R4)(r1)	/* Retrieve new pp bits */
 	mr	r4,r29			/* Retrieve va */
 	li	r7,HPTE_V_SECONDARY	/* !bolted, secondary */
 	li	r8,MMU_PAGE_4K		/* page size */
-	ld	r9,STK_PARM(r9)(r1)	/* segment size */
+	ld	r9,STK_PARAM(R9)(r1)	/* segment size */
 _GLOBAL(htab_call_hpte_insert2)
 	bl	.			/* patched by htab_finish_init() */
 	cmpdi	0,r3,0
@@ -559,8 +551,8 @@ htab_inval_old_hpte:
 	mr	r4,r31			/* PTE.pte */
 	li	r5,0			/* PTE.hidx */
 	li	r6,MMU_PAGE_64K		/* psize */
-	ld	r7,STK_PARM(r9)(r1)	/* ssize */
-	ld	r8,STK_PARM(r8)(r1)	/* local */
+	ld	r7,STK_PARAM(R9)(r1)	/* ssize */
+	ld	r8,STK_PARAM(R8)(r1)	/* local */
 	bl	.flush_hash_page
 	/* Clear out _PAGE_HPTE_SUB bits in the new linux PTE */
 	lis	r0,_PAGE_HPTE_SUB@h
@@ -576,7 +568,7 @@ htab_pte_insert_ok:
 	/* Insert slot number & secondary bit in PTE second half,
 	 * clear _PAGE_BUSY and set approriate HPTE slot bit
 	 */
-	ld	r6,STK_PARM(r6)(r1)
+	ld	r6,STK_PARAM(R6)(r1)
 	li	r0,_PAGE_BUSY
 	andc	r30,r30,r0
 	/* HPTE SUB bit */
@@ -597,13 +589,13 @@ htab_pte_insert_ok:
 	std	r30,0(r6)
 	li	r3, 0
 htab_bail:
-	ld	r25,STK_REG(r25)(r1)
-	ld	r26,STK_REG(r26)(r1)
-	ld	r27,STK_REG(r27)(r1)
-	ld	r28,STK_REG(r28)(r1)
-	ld	r29,STK_REG(r29)(r1)
-	ld      r30,STK_REG(r30)(r1)
-	ld      r31,STK_REG(r31)(r1)
+	ld	r25,STK_REG(R25)(r1)
+	ld	r26,STK_REG(R26)(r1)
+	ld	r27,STK_REG(R27)(r1)
+	ld	r28,STK_REG(R28)(r1)
+	ld	r29,STK_REG(R29)(r1)
+	ld      r30,STK_REG(R30)(r1)
+	ld      r31,STK_REG(R31)(r1)
 	addi    r1,r1,STACKFRAMESIZE
 	ld      r0,16(r1)
 	mtlr    r0
@@ -630,8 +622,8 @@ htab_modify_pte:
 	/* Call ppc_md.hpte_updatepp */
 	mr	r5,r29			/* va */
 	li	r6,MMU_PAGE_4K		/* page size */
-	ld	r7,STK_PARM(r9)(r1)	/* segment size */
-	ld	r8,STK_PARM(r8)(r1)	/* get "local" param */
+	ld	r7,STK_PARAM(R9)(r1)	/* segment size */
+	ld	r8,STK_PARAM(R8)(r1)	/* get "local" param */
 _GLOBAL(htab_call_hpte_updatepp)
 	bl	.			/* patched by htab_finish_init() */
 
@@ -644,7 +636,7 @@ _GLOBAL(htab_call_hpte_updatepp)
 	/* Clear the BUSY bit and Write out the PTE */
 	li	r0,_PAGE_BUSY
 	andc	r30,r30,r0
-	ld	r6,STK_PARM(r6)(r1)
+	ld	r6,STK_PARAM(R6)(r1)
 	std	r30,0(r6)
 	li	r3,0
 	b	htab_bail
@@ -657,7 +649,7 @@ htab_wrong_access:
 
 htab_pte_insert_failure:
 	/* Bail out restoring old PTE */
-	ld	r6,STK_PARM(r6)(r1)
+	ld	r6,STK_PARAM(R6)(r1)
 	std	r31,0(r6)
 	li	r3,-1
 	b	htab_bail
@@ -677,9 +669,9 @@ _GLOBAL(__hash_page_64K)
 	std	r0,16(r1)
 	stdu	r1,-STACKFRAMESIZE(r1)
 	/* Save all params that we need after a function call */
-	std	r6,STK_PARM(r6)(r1)
-	std	r8,STK_PARM(r8)(r1)
-	std	r9,STK_PARM(r9)(r1)
+	std	r6,STK_PARAM(R6)(r1)
+	std	r8,STK_PARAM(R8)(r1)
+	std	r9,STK_PARAM(R9)(r1)
 
 	/* Save non-volatile registers.
 	 * r31 will hold "old PTE"
@@ -688,11 +680,11 @@ _GLOBAL(__hash_page_64K)
 	 * r28 is a hash value
 	 * r27 is hashtab mask (maybe dynamic patched instead ?)
 	 */
-	std	r27,STK_REG(r27)(r1)
-	std	r28,STK_REG(r28)(r1)
-	std	r29,STK_REG(r29)(r1)
-	std	r30,STK_REG(r30)(r1)
-	std	r31,STK_REG(r31)(r1)
+	std	r27,STK_REG(R27)(r1)
+	std	r28,STK_REG(R28)(r1)
+	std	r29,STK_REG(R29)(r1)
+	std	r30,STK_REG(R30)(r1)
+	std	r31,STK_REG(R31)(r1)
 
 	/* Step 1:
 	 *
@@ -780,7 +772,7 @@ END_FTR_SECTION(CPU_FTR_NOEXECUTE|CPU_FTR_COHERENT_ICACHE, CPU_FTR_NOEXECUTE)
 	/* At this point, r3 contains new PP bits, save them in
 	 * place of "access" in the param area (sic)
 	 */
-	std	r3,STK_PARM(r4)(r1)
+	std	r3,STK_PARAM(R4)(r1)
 
 	/* Get htab_hash_mask */
 	ld	r4,htab_hash_mask@got(2)
@@ -813,11 +805,11 @@ ht64_insert_pte:
 	rldicr	r3,r0,3,63-3	/* r0 = (hash & mask) << 3 */
 
 	/* Call ppc_md.hpte_insert */
-	ld	r6,STK_PARM(r4)(r1)	/* Retrieve new pp bits */
+	ld	r6,STK_PARAM(R4)(r1)	/* Retrieve new pp bits */
 	mr	r4,r29			/* Retrieve va */
 	li	r7,0			/* !bolted, !secondary */
 	li	r8,MMU_PAGE_64K
-	ld	r9,STK_PARM(r9)(r1)	/* segment size */
+	ld	r9,STK_PARAM(R9)(r1)	/* segment size */
 _GLOBAL(ht64_call_hpte_insert1)
 	bl	.			/* patched by htab_finish_init() */
 	cmpdi	0,r3,0
@@ -836,11 +828,11 @@ _GLOBAL(ht64_call_hpte_insert1)
 	rldicr	r3,r0,3,63-3	/* r0 = (~hash & mask) << 3 */
 
 	/* Call ppc_md.hpte_insert */
-	ld	r6,STK_PARM(r4)(r1)	/* Retrieve new pp bits */
+	ld	r6,STK_PARAM(R4)(r1)	/* Retrieve new pp bits */
 	mr	r4,r29			/* Retrieve va */
 	li	r7,HPTE_V_SECONDARY	/* !bolted, secondary */
 	li	r8,MMU_PAGE_64K
-	ld	r9,STK_PARM(r9)(r1)	/* segment size */
+	ld	r9,STK_PARAM(R9)(r1)	/* segment size */
 _GLOBAL(ht64_call_hpte_insert2)
 	bl	.			/* patched by htab_finish_init() */
 	cmpdi	0,r3,0
@@ -876,15 +868,15 @@ ht64_pte_insert_ok:
 	 * (maybe add eieio may be good still ?)
 	 */
 ht64_write_out_pte:
-	ld	r6,STK_PARM(r6)(r1)
+	ld	r6,STK_PARAM(R6)(r1)
 	std	r30,0(r6)
 	li	r3, 0
 ht64_bail:
-	ld	r27,STK_REG(r27)(r1)
-	ld	r28,STK_REG(r28)(r1)
-	ld	r29,STK_REG(r29)(r1)
-	ld      r30,STK_REG(r30)(r1)
-	ld      r31,STK_REG(r31)(r1)
+	ld	r27,STK_REG(R27)(r1)
+	ld	r28,STK_REG(R28)(r1)
+	ld	r29,STK_REG(R29)(r1)
+	ld      r30,STK_REG(R30)(r1)
+	ld      r31,STK_REG(R31)(r1)
 	addi    r1,r1,STACKFRAMESIZE
 	ld      r0,16(r1)
 	mtlr    r0
@@ -909,8 +901,8 @@ ht64_modify_pte:
 	/* Call ppc_md.hpte_updatepp */
 	mr	r5,r29			/* va */
 	li	r6,MMU_PAGE_64K
-	ld	r7,STK_PARM(r9)(r1)	/* segment size */
-	ld	r8,STK_PARM(r8)(r1)	/* get "local" param */
+	ld	r7,STK_PARAM(R9)(r1)	/* segment size */
+	ld	r8,STK_PARAM(R8)(r1)	/* get "local" param */
 _GLOBAL(ht64_call_hpte_updatepp)
 	bl	.			/* patched by htab_finish_init() */
 
@@ -933,7 +925,7 @@ ht64_wrong_access:
 
 ht64_pte_insert_failure:
 	/* Bail out restoring old PTE */
-	ld	r6,STK_PARM(r6)(r1)
+	ld	r6,STK_PARAM(R6)(r1)
 	std	r31,0(r6)
 	li	r3,-1
 	b	ht64_bail
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 6e8f677f5646..39b159751c35 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -340,6 +340,8 @@ static int __init find_min_common_depth(void)
 				dbg("Using form 1 affinity\n");
 				form1_affinity = 1;
 			}
+
+			of_node_put(chosen);
 		}
 	}
 
@@ -639,7 +641,7 @@ static void __init parse_drconf_memory(struct device_node *memory)
 	unsigned int n, rc, ranges, is_kexec_kdump = 0;
 	unsigned long lmb_size, base, size, sz;
 	int nid;
-	struct assoc_arrays aa;
+	struct assoc_arrays aa = { .arrays = NULL };
 
 	n = of_get_drconf_memory(memory, &dm);
 	if (!n)
diff --git a/arch/powerpc/mm/tlb_low_64e.S b/arch/powerpc/mm/tlb_low_64e.S
index ff672bd8fea9..f09d48e3268d 100644
--- a/arch/powerpc/mm/tlb_low_64e.S
+++ b/arch/powerpc/mm/tlb_low_64e.S
@@ -126,7 +126,7 @@ BEGIN_MMU_FTR_SECTION
 	/* Set the TLB reservation and search for existing entry. Then load
 	 * the entry.
 	 */
-	PPC_TLBSRX_DOT(0,r16)
+	PPC_TLBSRX_DOT(0,R16)
 	ldx	r14,r14,r15		/* grab pgd entry */
 	beq	normal_tlb_miss_done	/* tlb exists already, bail */
 MMU_FTR_SECTION_ELSE
@@ -395,7 +395,7 @@ BEGIN_MMU_FTR_SECTION
 	/* Set the TLB reservation and search for existing entry. Then load
 	 * the entry.
 	 */
-	PPC_TLBSRX_DOT(0,r16)
+	PPC_TLBSRX_DOT(0,R16)
 	ld	r14,0(r10)
 	beq	normal_tlb_miss_done
 MMU_FTR_SECTION_ELSE
@@ -528,7 +528,7 @@ BEGIN_MMU_FTR_SECTION
 	/* Search if we already have a TLB entry for that virtual address, and
 	 * if we do, bail out.
 	 */
-	PPC_TLBSRX_DOT(0,r16)
+	PPC_TLBSRX_DOT(0,R16)
 	beq	virt_page_table_tlb_miss_done
 END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_TLBRSRV)
 
@@ -779,7 +779,7 @@ htw_tlb_miss:
 	 *
 	 * MAS1:IND should be already set based on MAS4
 	 */
-	PPC_TLBSRX_DOT(0,r16)
+	PPC_TLBSRX_DOT(0,R16)
 	beq	htw_tlb_miss_done
 
 	/* Now, we need to walk the page tables. First check if we are in
@@ -919,7 +919,7 @@ tlb_load_linear:
 	mtspr	SPRN_MAS1,r15
 
 	/* Already somebody there ? */
-	PPC_TLBSRX_DOT(0,r16)
+	PPC_TLBSRX_DOT(0,R16)
 	beq	tlb_load_linear_done
 
 	/* Now we build the remaining MAS. MAS0 and 2 should be fine
diff --git a/arch/powerpc/mm/tlb_nohash_low.S b/arch/powerpc/mm/tlb_nohash_low.S
index 7c63c0ed4f1b..fab919fd1384 100644
--- a/arch/powerpc/mm/tlb_nohash_low.S
+++ b/arch/powerpc/mm/tlb_nohash_low.S
@@ -266,7 +266,7 @@ BEGIN_MMU_FTR_SECTION
 	andi.	r3,r3,MMUCSR0_TLBFI@l
 	bne	1b
 MMU_FTR_SECTION_ELSE
-	PPC_TLBILX_ALL(0,0)
+	PPC_TLBILX_ALL(0,R0)
 ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_USE_TLBILX)
 	msync
 	isync
@@ -279,7 +279,7 @@ BEGIN_MMU_FTR_SECTION
 	wrteei	0
 	mfspr	r4,SPRN_MAS6	/* save MAS6 */
 	mtspr	SPRN_MAS6,r3
-	PPC_TLBILX_PID(0,0)
+	PPC_TLBILX_PID(0,R0)
 	mtspr	SPRN_MAS6,r4	/* restore MAS6 */
 	wrtee	r10
 MMU_FTR_SECTION_ELSE
@@ -313,7 +313,7 @@ BEGIN_MMU_FTR_SECTION
 	mtspr	SPRN_MAS1,r4
 	tlbwe
 MMU_FTR_SECTION_ELSE
-	PPC_TLBILX_VA(0,r3)
+	PPC_TLBILX_VA(0,R3)
 ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_USE_TLBILX)
 	msync
 	isync
@@ -331,7 +331,7 @@ _GLOBAL(_tlbil_pid)
 	mfmsr	r10
 	wrteei	0
 	mtspr	SPRN_MAS6,r4
-	PPC_TLBILX_PID(0,0)
+	PPC_TLBILX_PID(0,R0)
 	wrtee	r10
 	msync
 	isync
@@ -343,14 +343,14 @@ _GLOBAL(_tlbil_pid_noind)
 	ori	r4,r4,MAS6_SIND
 	wrteei	0
 	mtspr	SPRN_MAS6,r4
-	PPC_TLBILX_PID(0,0)
+	PPC_TLBILX_PID(0,R0)
 	wrtee	r10
 	msync
 	isync
 	blr
 
 _GLOBAL(_tlbil_all)
-	PPC_TLBILX_ALL(0,0)
+	PPC_TLBILX_ALL(0,R0)
 	msync
 	isync
 	blr
@@ -364,7 +364,7 @@ _GLOBAL(_tlbil_va)
 	beq	1f
 	rlwimi	r4,r6,MAS6_SIND_SHIFT,MAS6_SIND
 1:	mtspr	SPRN_MAS6,r4		/* assume AS=0 for now */
-	PPC_TLBILX_VA(0,r3)
+	PPC_TLBILX_VA(0,R3)
 	msync
 	isync
 	wrtee	r10
@@ -379,7 +379,7 @@ _GLOBAL(_tlbivax_bcast)
 	beq	1f
 	rlwimi	r4,r6,MAS6_SIND_SHIFT,MAS6_SIND
 1:	mtspr	SPRN_MAS6,r4		/* assume AS=0 for now */
-	PPC_TLBIVAX(0,r3)
+	PPC_TLBIVAX(0,R3)
 	eieio
 	tlbsync
 	sync
diff --git a/arch/powerpc/net/bpf_jit.h b/arch/powerpc/net/bpf_jit.h
index 5c3cf2d04e41..1fc8109bf2f9 100644
--- a/arch/powerpc/net/bpf_jit.h
+++ b/arch/powerpc/net/bpf_jit.h
@@ -75,23 +75,23 @@ DECLARE_LOAD_FUNC(sk_load_byte_msh);
 #define PPC_NOP()		EMIT(PPC_INST_NOP)
 #define PPC_BLR()		EMIT(PPC_INST_BLR)
 #define PPC_BLRL()		EMIT(PPC_INST_BLRL)
-#define PPC_MTLR(r)		EMIT(PPC_INST_MTLR | __PPC_RT(r))
-#define PPC_ADDI(d, a, i)	EMIT(PPC_INST_ADDI | __PPC_RT(d) |	      \
-				     __PPC_RA(a) | IMM_L(i))
+#define PPC_MTLR(r)		EMIT(PPC_INST_MTLR | ___PPC_RT(r))
+#define PPC_ADDI(d, a, i)	EMIT(PPC_INST_ADDI | ___PPC_RT(d) |	      \
+				     ___PPC_RA(a) | IMM_L(i))
 #define PPC_MR(d, a)		PPC_OR(d, a, a)
 #define PPC_LI(r, i)		PPC_ADDI(r, 0, i)
 #define PPC_ADDIS(d, a, i)	EMIT(PPC_INST_ADDIS |			      \
-				     __PPC_RS(d) | __PPC_RA(a) | IMM_L(i))
+				     ___PPC_RS(d) | ___PPC_RA(a) | IMM_L(i))
 #define PPC_LIS(r, i)		PPC_ADDIS(r, 0, i)
-#define PPC_STD(r, base, i)	EMIT(PPC_INST_STD | __PPC_RS(r) |	      \
-				     __PPC_RA(base) | ((i) & 0xfffc))
-
-#define PPC_LD(r, base, i)	EMIT(PPC_INST_LD | __PPC_RT(r) |	      \
-				     __PPC_RA(base) | IMM_L(i))
-#define PPC_LWZ(r, base, i)	EMIT(PPC_INST_LWZ | __PPC_RT(r) |	      \
-				     __PPC_RA(base) | IMM_L(i))
-#define PPC_LHZ(r, base, i)	EMIT(PPC_INST_LHZ | __PPC_RT(r) |	      \
-				     __PPC_RA(base) | IMM_L(i))
+#define PPC_STD(r, base, i)	EMIT(PPC_INST_STD | ___PPC_RS(r) |	      \
+				     ___PPC_RA(base) | ((i) & 0xfffc))
+
+#define PPC_LD(r, base, i)	EMIT(PPC_INST_LD | ___PPC_RT(r) |	      \
+				     ___PPC_RA(base) | IMM_L(i))
+#define PPC_LWZ(r, base, i)	EMIT(PPC_INST_LWZ | ___PPC_RT(r) |	      \
+				     ___PPC_RA(base) | IMM_L(i))
+#define PPC_LHZ(r, base, i)	EMIT(PPC_INST_LHZ | ___PPC_RT(r) |	      \
+				     ___PPC_RA(base) | IMM_L(i))
 /* Convenience helpers for the above with 'far' offsets: */
 #define PPC_LD_OFFS(r, base, i) do { if ((i) < 32768) PPC_LD(r, base, i);     \
 		else {	PPC_ADDIS(r, base, IMM_HA(i));			      \
@@ -105,52 +105,52 @@ DECLARE_LOAD_FUNC(sk_load_byte_msh);
 		else {	PPC_ADDIS(r, base, IMM_HA(i));			      \
 			PPC_LHZ(r, r, IMM_L(i)); } } while(0)
 
-#define PPC_CMPWI(a, i)		EMIT(PPC_INST_CMPWI | __PPC_RA(a) | IMM_L(i))
-#define PPC_CMPDI(a, i)		EMIT(PPC_INST_CMPDI | __PPC_RA(a) | IMM_L(i))
-#define PPC_CMPLWI(a, i)	EMIT(PPC_INST_CMPLWI | __PPC_RA(a) | IMM_L(i))
-#define PPC_CMPLW(a, b)		EMIT(PPC_INST_CMPLW | __PPC_RA(a) | __PPC_RB(b))
-
-#define PPC_SUB(d, a, b)	EMIT(PPC_INST_SUB | __PPC_RT(d) |	      \
-				     __PPC_RB(a) | __PPC_RA(b))
-#define PPC_ADD(d, a, b)	EMIT(PPC_INST_ADD | __PPC_RT(d) |	      \
-				     __PPC_RA(a) | __PPC_RB(b))
-#define PPC_MUL(d, a, b)	EMIT(PPC_INST_MULLW | __PPC_RT(d) |	      \
-				     __PPC_RA(a) | __PPC_RB(b))
-#define PPC_MULHWU(d, a, b)	EMIT(PPC_INST_MULHWU | __PPC_RT(d) |	      \
-				     __PPC_RA(a) | __PPC_RB(b))
-#define PPC_MULI(d, a, i)	EMIT(PPC_INST_MULLI | __PPC_RT(d) |	      \
-				     __PPC_RA(a) | IMM_L(i))
-#define PPC_DIVWU(d, a, b)	EMIT(PPC_INST_DIVWU | __PPC_RT(d) |	      \
-				     __PPC_RA(a) | __PPC_RB(b))
-#define PPC_AND(d, a, b)	EMIT(PPC_INST_AND | __PPC_RA(d) |	      \
-				     __PPC_RS(a) | __PPC_RB(b))
-#define PPC_ANDI(d, a, i)	EMIT(PPC_INST_ANDI | __PPC_RA(d) |	      \
-				     __PPC_RS(a) | IMM_L(i))
-#define PPC_AND_DOT(d, a, b)	EMIT(PPC_INST_ANDDOT | __PPC_RA(d) |	      \
-				     __PPC_RS(a) | __PPC_RB(b))
-#define PPC_OR(d, a, b)		EMIT(PPC_INST_OR | __PPC_RA(d) |	      \
-				     __PPC_RS(a) | __PPC_RB(b))
-#define PPC_ORI(d, a, i)	EMIT(PPC_INST_ORI | __PPC_RA(d) |	      \
-				     __PPC_RS(a) | IMM_L(i))
-#define PPC_ORIS(d, a, i)	EMIT(PPC_INST_ORIS | __PPC_RA(d) |	      \
-				     __PPC_RS(a) | IMM_L(i))
-#define PPC_SLW(d, a, s)	EMIT(PPC_INST_SLW | __PPC_RA(d) |	      \
-				     __PPC_RS(a) | __PPC_RB(s))
-#define PPC_SRW(d, a, s)	EMIT(PPC_INST_SRW | __PPC_RA(d) |	      \
-				     __PPC_RS(a) | __PPC_RB(s))
+#define PPC_CMPWI(a, i)		EMIT(PPC_INST_CMPWI | ___PPC_RA(a) | IMM_L(i))
+#define PPC_CMPDI(a, i)		EMIT(PPC_INST_CMPDI | ___PPC_RA(a) | IMM_L(i))
+#define PPC_CMPLWI(a, i)	EMIT(PPC_INST_CMPLWI | ___PPC_RA(a) | IMM_L(i))
+#define PPC_CMPLW(a, b)		EMIT(PPC_INST_CMPLW | ___PPC_RA(a) | ___PPC_RB(b))
+
+#define PPC_SUB(d, a, b)	EMIT(PPC_INST_SUB | ___PPC_RT(d) |	      \
+				     ___PPC_RB(a) | ___PPC_RA(b))
+#define PPC_ADD(d, a, b)	EMIT(PPC_INST_ADD | ___PPC_RT(d) |	      \
+				     ___PPC_RA(a) | ___PPC_RB(b))
+#define PPC_MUL(d, a, b)	EMIT(PPC_INST_MULLW | ___PPC_RT(d) |	      \
+				     ___PPC_RA(a) | ___PPC_RB(b))
+#define PPC_MULHWU(d, a, b)	EMIT(PPC_INST_MULHWU | ___PPC_RT(d) |	      \
+				     ___PPC_RA(a) | ___PPC_RB(b))
+#define PPC_MULI(d, a, i)	EMIT(PPC_INST_MULLI | ___PPC_RT(d) |	      \
+				     ___PPC_RA(a) | IMM_L(i))
+#define PPC_DIVWU(d, a, b)	EMIT(PPC_INST_DIVWU | ___PPC_RT(d) |	      \
+				     ___PPC_RA(a) | ___PPC_RB(b))
+#define PPC_AND(d, a, b)	EMIT(PPC_INST_AND | ___PPC_RA(d) |	      \
+				     ___PPC_RS(a) | ___PPC_RB(b))
+#define PPC_ANDI(d, a, i)	EMIT(PPC_INST_ANDI | ___PPC_RA(d) |	      \
+				     ___PPC_RS(a) | IMM_L(i))
+#define PPC_AND_DOT(d, a, b)	EMIT(PPC_INST_ANDDOT | ___PPC_RA(d) |	      \
+				     ___PPC_RS(a) | ___PPC_RB(b))
+#define PPC_OR(d, a, b)		EMIT(PPC_INST_OR | ___PPC_RA(d) |	      \
+				     ___PPC_RS(a) | ___PPC_RB(b))
+#define PPC_ORI(d, a, i)	EMIT(PPC_INST_ORI | ___PPC_RA(d) |	      \
+				     ___PPC_RS(a) | IMM_L(i))
+#define PPC_ORIS(d, a, i)	EMIT(PPC_INST_ORIS | ___PPC_RA(d) |	      \
+				     ___PPC_RS(a) | IMM_L(i))
+#define PPC_SLW(d, a, s)	EMIT(PPC_INST_SLW | ___PPC_RA(d) |	      \
+				     ___PPC_RS(a) | ___PPC_RB(s))
+#define PPC_SRW(d, a, s)	EMIT(PPC_INST_SRW | ___PPC_RA(d) |	      \
+				     ___PPC_RS(a) | ___PPC_RB(s))
 /* slwi = rlwinm Rx, Ry, n, 0, 31-n */
-#define PPC_SLWI(d, a, i)	EMIT(PPC_INST_RLWINM | __PPC_RA(d) |	      \
-				     __PPC_RS(a) | __PPC_SH(i) |	      \
+#define PPC_SLWI(d, a, i)	EMIT(PPC_INST_RLWINM | ___PPC_RA(d) |	      \
+				     ___PPC_RS(a) | __PPC_SH(i) |	      \
 				     __PPC_MB(0) | __PPC_ME(31-(i)))
 /* srwi = rlwinm Rx, Ry, 32-n, n, 31 */
-#define PPC_SRWI(d, a, i)	EMIT(PPC_INST_RLWINM | __PPC_RA(d) |	      \
-				     __PPC_RS(a) | __PPC_SH(32-(i)) |	      \
+#define PPC_SRWI(d, a, i)	EMIT(PPC_INST_RLWINM | ___PPC_RA(d) |	      \
+				     ___PPC_RS(a) | __PPC_SH(32-(i)) |	      \
 				     __PPC_MB(i) | __PPC_ME(31))
 /* sldi = rldicr Rx, Ry, n, 63-n */
-#define PPC_SLDI(d, a, i)	EMIT(PPC_INST_RLDICR | __PPC_RA(d) |	      \
-				     __PPC_RS(a) | __PPC_SH(i) |	      \
+#define PPC_SLDI(d, a, i)	EMIT(PPC_INST_RLDICR | ___PPC_RA(d) |	      \
+				     ___PPC_RS(a) | __PPC_SH(i) |	      \
 				     __PPC_MB(63-(i)) | (((i) & 0x20) >> 4))
-#define PPC_NEG(d, a)		EMIT(PPC_INST_NEG | __PPC_RT(d) | __PPC_RA(a))
+#define PPC_NEG(d, a)		EMIT(PPC_INST_NEG | ___PPC_RT(d) | ___PPC_RA(a))
 
 /* Long jump; (unconditional 'branch') */
 #define PPC_JMP(dest)		EMIT(PPC_INST_BRANCH |			      \
diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c
index 2dc8b1484845..dd1130642d07 100644
--- a/arch/powerpc/net/bpf_jit_comp.c
+++ b/arch/powerpc/net/bpf_jit_comp.c
@@ -39,7 +39,7 @@ static void bpf_jit_build_prologue(struct sk_filter *fp, u32 *image,
 		/* Make stackframe */
 		if (ctx->seen & SEEN_DATAREF) {
 			/* If we call any helpers (for loads), save LR */
-			EMIT(PPC_INST_MFLR | __PPC_RT(0));
+			EMIT(PPC_INST_MFLR | __PPC_RT(R0));
 			PPC_STD(0, 1, 16);
 
 			/* Back up non-volatile regs. */
@@ -56,7 +56,7 @@ static void bpf_jit_build_prologue(struct sk_filter *fp, u32 *image,
 					PPC_STD(i, 1, -(8*(32-i)));
 			}
 		}
-		EMIT(PPC_INST_STDU | __PPC_RS(1) | __PPC_RA(1) |
+		EMIT(PPC_INST_STDU | __PPC_RS(R1) | __PPC_RA(R1) |
 		     (-BPF_PPC_STACKFRAME & 0xfffc));
 	}
 
diff --git a/arch/powerpc/perf/callchain.c b/arch/powerpc/perf/callchain.c
index e8a18d1cc7c9..74d1e780748b 100644
--- a/arch/powerpc/perf/callchain.c
+++ b/arch/powerpc/perf/callchain.c
@@ -57,7 +57,7 @@ perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs)
 
 	lr = regs->link;
 	sp = regs->gpr[1];
-	perf_callchain_store(entry, regs->nip);
+	perf_callchain_store(entry, perf_instruction_pointer(regs));
 
 	if (!validate_sp(sp, current, STACK_FRAME_OVERHEAD))
 		return;
@@ -238,7 +238,7 @@ static void perf_callchain_user_64(struct perf_callchain_entry *entry,
 	struct signal_frame_64 __user *sigframe;
 	unsigned long __user *fp, *uregs;
 
-	next_ip = regs->nip;
+	next_ip = perf_instruction_pointer(regs);
 	lr = regs->link;
 	sp = regs->gpr[1];
 	perf_callchain_store(entry, next_ip);
@@ -444,7 +444,7 @@ static void perf_callchain_user_32(struct perf_callchain_entry *entry,
 	long level = 0;
 	unsigned int __user *fp, *uregs;
 
-	next_ip = regs->nip;
+	next_ip = perf_instruction_pointer(regs);
 	lr = regs->link;
 	sp = regs->gpr[1];
 	perf_callchain_store(entry, next_ip);
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index 8f84bcba18da..77b49ddda9d3 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -73,7 +73,10 @@ static inline u32 perf_get_misc_flags(struct pt_regs *regs)
 {
 	return 0;
 }
-static inline void perf_read_regs(struct pt_regs *regs) { }
+static inline void perf_read_regs(struct pt_regs *regs)
+{
+	regs->result = 0;
+}
 static inline int perf_intr_is_nmi(struct pt_regs *regs)
 {
 	return 0;
@@ -116,6 +119,26 @@ static inline void perf_get_data_addr(struct pt_regs *regs, u64 *addrp)
 		*addrp = mfspr(SPRN_SDAR);
 }
 
+static bool mmcra_sihv(unsigned long mmcra)
+{
+	unsigned long sihv = MMCRA_SIHV;
+
+	if (ppmu->flags & PPMU_ALT_SIPR)
+		sihv = POWER6_MMCRA_SIHV;
+
+	return !!(mmcra & sihv);
+}
+
+static bool mmcra_sipr(unsigned long mmcra)
+{
+	unsigned long sipr = MMCRA_SIPR;
+
+	if (ppmu->flags & PPMU_ALT_SIPR)
+		sipr = POWER6_MMCRA_SIPR;
+
+	return !!(mmcra & sipr);
+}
+
 static inline u32 perf_flags_from_msr(struct pt_regs *regs)
 {
 	if (regs->msr & MSR_PR)
@@ -128,19 +151,9 @@ static inline u32 perf_flags_from_msr(struct pt_regs *regs)
 static inline u32 perf_get_misc_flags(struct pt_regs *regs)
 {
 	unsigned long mmcra = regs->dsisr;
-	unsigned long sihv = MMCRA_SIHV;
-	unsigned long sipr = MMCRA_SIPR;
+	unsigned long use_siar = regs->result;
 
-	/* Not a PMU interrupt: Make up flags from regs->msr */
-	if (TRAP(regs) != 0xf00)
-		return perf_flags_from_msr(regs);
-
-	/*
-	 * If we don't support continuous sampling and this
-	 * is not a marked event, same deal
-	 */
-	if ((ppmu->flags & PPMU_NO_CONT_SAMPLING) &&
-	    !(mmcra & MMCRA_SAMPLE_ENABLE))
+	if (!use_siar)
 		return perf_flags_from_msr(regs);
 
 	/*
@@ -156,15 +169,10 @@ static inline u32 perf_get_misc_flags(struct pt_regs *regs)
 		return PERF_RECORD_MISC_USER;
 	}
 
-	if (ppmu->flags & PPMU_ALT_SIPR) {
-		sihv = POWER6_MMCRA_SIHV;
-		sipr = POWER6_MMCRA_SIPR;
-	}
-
 	/* PR has priority over HV, so order below is important */
-	if (mmcra & sipr)
+	if (mmcra_sipr(mmcra))
 		return PERF_RECORD_MISC_USER;
-	if ((mmcra & sihv) && (freeze_events_kernel != MMCR0_FCHV))
+	if (mmcra_sihv(mmcra) && (freeze_events_kernel != MMCR0_FCHV))
 		return PERF_RECORD_MISC_HYPERVISOR;
 	return PERF_RECORD_MISC_KERNEL;
 }
@@ -172,10 +180,45 @@ static inline u32 perf_get_misc_flags(struct pt_regs *regs)
 /*
  * Overload regs->dsisr to store MMCRA so we only need to read it once
  * on each interrupt.
+ * Overload regs->result to specify whether we should use the MSR (result
+ * is zero) or the SIAR (result is non zero).
  */
 static inline void perf_read_regs(struct pt_regs *regs)
 {
-	regs->dsisr = mfspr(SPRN_MMCRA);
+	unsigned long mmcra = mfspr(SPRN_MMCRA);
+	int marked = mmcra & MMCRA_SAMPLE_ENABLE;
+	int use_siar;
+
+	/*
+	 * If this isn't a PMU exception (eg a software event) the SIAR is
+	 * not valid. Use pt_regs.
+	 *
+	 * If it is a marked event use the SIAR.
+	 *
+	 * If the PMU doesn't update the SIAR for non marked events use
+	 * pt_regs.
+	 *
+	 * If the PMU has HV/PR flags then check to see if they
+	 * place the exception in userspace. If so, use pt_regs. In
+	 * continuous sampling mode the SIAR and the PMU exception are
+	 * not synchronised, so they may be many instructions apart.
+	 * This can result in confusing backtraces. We still want
+	 * hypervisor samples as well as samples in the kernel with
+	 * interrupts off hence the userspace check.
+	 */
+	if (TRAP(regs) != 0xf00)
+		use_siar = 0;
+	else if (marked)
+		use_siar = 1;
+	else if ((ppmu->flags & PPMU_NO_CONT_SAMPLING))
+		use_siar = 0;
+	else if (!(ppmu->flags & PPMU_NO_SIPR) && mmcra_sipr(mmcra))
+		use_siar = 0;
+	else
+		use_siar = 1;
+
+	regs->dsisr = mmcra;
+	regs->result = use_siar;
 }
 
 /*
@@ -1329,18 +1372,12 @@ unsigned long perf_misc_flags(struct pt_regs *regs)
  */
 unsigned long perf_instruction_pointer(struct pt_regs *regs)
 {
-	unsigned long mmcra = regs->dsisr;
+	unsigned long use_siar = regs->result;
 
-	/* Not a PMU interrupt */
-	if (TRAP(regs) != 0xf00)
-		return regs->nip;
-
-	/* Processor doesn't support sampling non marked events */
-	if ((ppmu->flags & PPMU_NO_CONT_SAMPLING) &&
-	    !(mmcra & MMCRA_SAMPLE_ENABLE))
+	if (use_siar)
+		return mfspr(SPRN_SIAR) + perf_ip_adjust(regs);
+	else
 		return regs->nip;
-
-	return mfspr(SPRN_SIAR) + perf_ip_adjust(regs);
 }
 
 static bool pmc_overflow(unsigned long val)
diff --git a/arch/powerpc/platforms/44x/currituck.c b/arch/powerpc/platforms/44x/currituck.c
index 583e67fee37e..9f6c33d63a42 100644
--- a/arch/powerpc/platforms/44x/currituck.c
+++ b/arch/powerpc/platforms/44x/currituck.c
@@ -160,7 +160,7 @@ static void __init ppc47x_setup_arch(void)
 	/* No need to check the DMA config as we /know/ our windows are all of
  	 * RAM.  Lets hope that doesn't change */
 #ifdef CONFIG_SWIOTLB
-	if (memblock_end_of_DRAM() > 0xffffffff) {
+	if ((memblock_end_of_DRAM() - 1) > 0xffffffff) {
 		ppc_swiotlb_enable = 1;
 		set_pci_dma_ops(&swiotlb_dma_ops);
 		ppc_md.pci_dma_dev_setup = pci_dma_dev_setup_swiotlb;
diff --git a/arch/powerpc/platforms/82xx/km82xx.c b/arch/powerpc/platforms/82xx/km82xx.c
index 3661bcdc326a..cf964e19573a 100644
--- a/arch/powerpc/platforms/82xx/km82xx.c
+++ b/arch/powerpc/platforms/82xx/km82xx.c
@@ -128,6 +128,11 @@ static __initdata struct cpm_pin km82xx_pins[] = {
 	{3, 23, CPM_PIN_OUTPUT | CPM_PIN_PRIMARY}, /* TXP */
 	{3, 24, CPM_PIN_OUTPUT | CPM_PIN_PRIMARY}, /* TXN */
 	{3, 25, CPM_PIN_INPUT  | CPM_PIN_PRIMARY}, /* RXD */
+
+	/* SPI */
+	{3, 16, CPM_PIN_INPUT | CPM_PIN_SECONDARY},/* SPI_MISO PD16 */
+	{3, 17, CPM_PIN_INPUT | CPM_PIN_SECONDARY},/* SPI_MOSI PD17 */
+	{3, 18, CPM_PIN_INPUT | CPM_PIN_SECONDARY},/* SPI_CLK PD18 */
 };
 
 static void __init init_ioports(void)
diff --git a/arch/powerpc/platforms/83xx/km83xx.c b/arch/powerpc/platforms/83xx/km83xx.c
index a266ba876863..89923d723349 100644
--- a/arch/powerpc/platforms/83xx/km83xx.c
+++ b/arch/powerpc/platforms/83xx/km83xx.c
@@ -3,7 +3,7 @@
  * Author: Heiko Schocher <hs@denx.de>
  *
  * Description:
- * Keymile KMETER1 board specific routines.
+ * Keymile 83xx platform specific routines.
  *
  * 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
@@ -70,54 +70,88 @@ static void __init mpc83xx_km_setup_arch(void)
 		for_each_node_by_name(np, "spi")
 			par_io_of_config(np);
 
-		for (np = NULL; (np = of_find_node_by_name(np, "ucc")) != NULL;)
+		for_each_node_by_name(np, "ucc")
 			par_io_of_config(np);
 	}
 
 	np = of_find_compatible_node(NULL, "network", "ucc_geth");
 	if (np != NULL) {
-		uint svid;
+		/*
+		 * handle mpc8360E Erratum QE_ENET10:
+		 * RGMII AC values do not meet the specification
+		 */
+		uint svid = mfspr(SPRN_SVR);
+		struct	device_node *np_par;
+		struct	resource res;
+		void	__iomem *base;
+		int	ret;
+
+		np_par = of_find_node_by_name(NULL, "par_io");
+		if (np_par == NULL) {
+			printk(KERN_WARNING "%s couldn;t find par_io node\n",
+				__func__);
+			return;
+		}
+		/* Map Parallel I/O ports registers */
+		ret = of_address_to_resource(np_par, 0, &res);
+		if (ret) {
+			printk(KERN_WARNING "%s couldn;t map par_io registers\n",
+				__func__);
+			return;
+		}
+
+		base = ioremap(res.start, res.end - res.start + 1);
+
+		/*
+		 * set output delay adjustments to default values according
+		 * table 5 in Errata Rev. 5, 9/2011:
+		 *
+		 * write 0b01 to UCC1 bits 18:19
+		 * write 0b01 to UCC2 option 1 bits 4:5
+		 * write 0b01 to UCC2 option 2 bits 16:17
+		 */
+		clrsetbits_be32((base + 0xa8), 0x0c00f000, 0x04005000);
+
+		/*
+		 * set output delay adjustments to default values according
+		 * table 3-13 in Reference Manual Rev.3 05/2010:
+		 *
+		 * write 0b01 to UCC2 option 2 bits 16:17
+		 * write 0b0101 to UCC1 bits 20:23
+		 * write 0b0101 to UCC2 option 1 bits 24:27
+		 */
+		clrsetbits_be32((base + 0xac), 0x0000cff0, 0x00004550);
 
-		/* handle mpc8360ea rev.2.1 erratum 2: RGMII Timing */
-		svid = mfspr(SPRN_SVR);
 		if (SVR_REV(svid) == 0x0021) {
-			struct	device_node *np_par;
-			struct	resource res;
-			void	__iomem *base;
-			int	ret;
-
-			np_par = of_find_node_by_name(NULL, "par_io");
-			if (np_par == NULL) {
-				printk(KERN_WARNING "%s couldn;t find par_io node\n",
-					__func__);
-				return;
-			}
-			/* Map Parallel I/O ports registers */
-			ret = of_address_to_resource(np_par, 0, &res);
-			if (ret) {
-				printk(KERN_WARNING "%s couldn;t map par_io registers\n",
-					__func__);
-				return;
-			}
-			base = ioremap(res.start, resource_size(&res));
+			/*
+			 * UCC2 option 1: write 0b1010 to bits 24:27
+			 * at address IMMRBAR+0x14AC
+			 */
+			clrsetbits_be32((base + 0xac), 0x000000f0, 0x000000a0);
+		} else if (SVR_REV(svid) == 0x0020) {
+			/*
+			 * UCC1: write 0b11 to bits 18:19
+			 * at address IMMRBAR+0x14A8
+			 */
+			setbits32((base + 0xa8), 0x00003000);
 
 			/*
-			 * IMMR + 0x14A8[4:5] = 11 (clk delay for UCC 2)
-			 * IMMR + 0x14A8[18:19] = 11 (clk delay for UCC 1)
+			 * UCC2 option 1: write 0b11 to bits 4:5
+			 * at address IMMRBAR+0x14A8
 			 */
-			setbits32((base + 0xa8), 0x0c003000);
+			setbits32((base + 0xa8), 0x0c000000);
 
 			/*
-			 * IMMR + 0x14AC[20:27] = 10101010
-			 * (data delay for both UCC's)
+			 * UCC2 option 2: write 0b11 to bits 16:17
+			 * at address IMMRBAR+0x14AC
 			 */
-			clrsetbits_be32((base + 0xac), 0xff0, 0xaa0);
-			iounmap(base);
-			of_node_put(np_par);
+			setbits32((base + 0xac), 0x0000c000);
 		}
+		iounmap(base);
+		of_node_put(np_par);
 		of_node_put(np);
 	}
-#endif				/* CONFIG_QUICC_ENGINE */
+#endif	/* CONFIG_QUICC_ENGINE */
 }
 
 machine_device_initcall(mpc83xx_km, mpc83xx_declare_of_platform_devices);
diff --git a/arch/powerpc/platforms/85xx/Kconfig b/arch/powerpc/platforms/85xx/Kconfig
index f000d81c4e31..159c01e91463 100644
--- a/arch/powerpc/platforms/85xx/Kconfig
+++ b/arch/powerpc/platforms/85xx/Kconfig
@@ -23,6 +23,15 @@ config FSL_85XX_CACHE_SRAM
 	  cache-sram-size and cache-sram-offset kernel boot
 	  parameters should be passed when this option is enabled.
 
+config BSC9131_RDB
+	bool "Freescale BSC9131RDB"
+	select DEFAULT_UIMAGE
+	help
+	  This option enables support for the Freescale BSC9131RDB board.
+	  The BSC9131 is a heterogeneous SoC containing an e500v2 powerpc and a
+	  StarCore SC3850 DSP
+	  Manufacturer : Freescale Semiconductor, Inc
+
 config MPC8540_ADS
 	bool "Freescale MPC8540 ADS"
 	select DEFAULT_UIMAGE
@@ -175,12 +184,6 @@ config SBC8548
 	help
 	  This option enables support for the Wind River SBC8548 board
 
-config SBC8560
-	bool "Wind River SBC8560"
-	select DEFAULT_UIMAGE
-	help
-	  This option enables support for the Wind River SBC8560 board
-
 config GE_IMP3A
 	bool "GE Intelligent Platforms IMP3A"
 	select DEFAULT_UIMAGE
@@ -222,18 +225,6 @@ config P3041_DS
 	help
 	  This option enables support for the P3041 DS board
 
-config P3060_QDS
-	bool "Freescale P3060 QDS"
-	select DEFAULT_UIMAGE
-	select PPC_E500MC
-	select PHYS_64BIT
-	select SWIOTLB
-	select GPIO_MPC8XXX
-	select HAS_RAPIDIO
-	select PPC_EPAPR_HV_PIC
-	help
-	  This option enables support for the P3060 QDS board
-
 config P4080_DS
 	bool "Freescale P4080 DS"
 	select DEFAULT_UIMAGE
@@ -263,6 +254,22 @@ config P5020_DS
 	help
 	  This option enables support for the P5020 DS board
 
+config PPC_QEMU_E500
+	bool "QEMU generic e500 platform"
+	depends on EXPERIMENTAL
+	select DEFAULT_UIMAGE
+	help
+	  This option enables support for running as a QEMU guest using
+	  QEMU's generic e500 machine.  This is not required if you're
+	  using a QEMU machine that targets a specific board, such as
+	  mpc8544ds.
+
+	  Unlike most e500 boards that target a specific CPU, this
+	  platform works with any e500-family CPU that QEMU supports.
+	  Thus, you'll need to make sure CONFIG_PPC_E500MC is set or
+	  unset based on the emulated CPU (or actual host CPU in the case
+	  of KVM).
+
 endif # FSL_SOC_BOOKE
 
 config TQM85xx
diff --git a/arch/powerpc/platforms/85xx/Makefile b/arch/powerpc/platforms/85xx/Makefile
index 2125d4ca068a..3dfe81175036 100644
--- a/arch/powerpc/platforms/85xx/Makefile
+++ b/arch/powerpc/platforms/85xx/Makefile
@@ -5,6 +5,7 @@ obj-$(CONFIG_SMP) += smp.o
 
 obj-y += common.o
 
+obj-$(CONFIG_BSC9131_RDB) += bsc913x_rdb.o
 obj-$(CONFIG_MPC8540_ADS) += mpc85xx_ads.o
 obj-$(CONFIG_MPC8560_ADS) += mpc85xx_ads.o
 obj-$(CONFIG_MPC85xx_CDS) += mpc85xx_cds.o
@@ -17,14 +18,13 @@ obj-$(CONFIG_P1022_DS)    += p1022_ds.o
 obj-$(CONFIG_P1023_RDS)   += p1023_rds.o
 obj-$(CONFIG_P2041_RDB)   += p2041_rdb.o corenet_ds.o
 obj-$(CONFIG_P3041_DS)    += p3041_ds.o corenet_ds.o
-obj-$(CONFIG_P3060_QDS)   += p3060_qds.o corenet_ds.o
 obj-$(CONFIG_P4080_DS)    += p4080_ds.o corenet_ds.o
 obj-$(CONFIG_P5020_DS)    += p5020_ds.o corenet_ds.o
 obj-$(CONFIG_STX_GP3)	  += stx_gp3.o
 obj-$(CONFIG_TQM85xx)	  += tqm85xx.o
-obj-$(CONFIG_SBC8560)     += sbc8560.o
 obj-$(CONFIG_SBC8548)     += sbc8548.o
 obj-$(CONFIG_SOCRATES)    += socrates.o socrates_fpga_pic.o
 obj-$(CONFIG_KSI8560)	  += ksi8560.o
 obj-$(CONFIG_XES_MPC85xx) += xes_mpc85xx.o
 obj-$(CONFIG_GE_IMP3A)	  += ge_imp3a.o
+obj-$(CONFIG_PPC_QEMU_E500) += qemu_e500.o
diff --git a/arch/powerpc/platforms/85xx/bsc913x_rdb.c b/arch/powerpc/platforms/85xx/bsc913x_rdb.c
new file mode 100644
index 000000000000..9d57bedb940c
--- /dev/null
+++ b/arch/powerpc/platforms/85xx/bsc913x_rdb.c
@@ -0,0 +1,67 @@
+/*
+ * BSC913xRDB Board Setup
+ *
+ * Author: Priyanka Jain <Priyanka.Jain@freescale.com>
+ *
+ * Copyright 2011-2012 Freescale Semiconductor Inc.
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ */
+
+#include <linux/of_platform.h>
+#include <linux/pci.h>
+#include <asm/mpic.h>
+#include <sysdev/fsl_soc.h>
+#include <asm/udbg.h>
+
+#include "mpc85xx.h"
+
+void __init bsc913x_rdb_pic_init(void)
+{
+	struct mpic *mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN |
+	  MPIC_SINGLE_DEST_CPU,
+	  0, 256, " OpenPIC  ");
+
+	if (!mpic)
+		pr_err("bsc913x: Failed to allocate MPIC structure\n");
+	else
+		mpic_init(mpic);
+}
+
+/*
+ * Setup the architecture
+ */
+static void __init bsc913x_rdb_setup_arch(void)
+{
+	if (ppc_md.progress)
+		ppc_md.progress("bsc913x_rdb_setup_arch()", 0);
+
+	pr_info("bsc913x board from Freescale Semiconductor\n");
+}
+
+machine_device_initcall(bsc9131_rdb, mpc85xx_common_publish_devices);
+
+/*
+ * Called very early, device-tree isn't unflattened
+ */
+
+static int __init bsc9131_rdb_probe(void)
+{
+	unsigned long root = of_get_flat_dt_root();
+
+	return of_flat_dt_is_compatible(root, "fsl,bsc9131rdb");
+}
+
+define_machine(bsc9131_rdb) {
+	.name			= "BSC9131 RDB",
+	.probe			= bsc9131_rdb_probe,
+	.setup_arch		= bsc913x_rdb_setup_arch,
+	.init_IRQ		= bsc913x_rdb_pic_init,
+	.get_irq		= mpic_get_irq,
+	.restart		= fsl_rstcr_restart,
+	.calibrate_decr		= generic_calibrate_decr,
+	.progress		= udbg_progress,
+};
diff --git a/arch/powerpc/platforms/85xx/corenet_ds.c b/arch/powerpc/platforms/85xx/corenet_ds.c
index dd3617c531d7..925b02874233 100644
--- a/arch/powerpc/platforms/85xx/corenet_ds.c
+++ b/arch/powerpc/platforms/85xx/corenet_ds.c
@@ -77,7 +77,7 @@ void __init corenet_ds_setup_arch(void)
 #endif
 
 #ifdef CONFIG_SWIOTLB
-	if (memblock_end_of_DRAM() > max) {
+	if ((memblock_end_of_DRAM() - 1) > max) {
 		ppc_swiotlb_enable = 1;
 		set_pci_dma_ops(&swiotlb_dma_ops);
 		ppc_md.pci_dma_dev_setup = pci_dma_dev_setup_swiotlb;
diff --git a/arch/powerpc/platforms/85xx/ge_imp3a.c b/arch/powerpc/platforms/85xx/ge_imp3a.c
index 18014629416d..b6a728b0a8ca 100644
--- a/arch/powerpc/platforms/85xx/ge_imp3a.c
+++ b/arch/powerpc/platforms/85xx/ge_imp3a.c
@@ -125,7 +125,7 @@ static void __init ge_imp3a_setup_arch(void)
 	mpc85xx_smp_init();
 
 #ifdef CONFIG_SWIOTLB
-	if (memblock_end_of_DRAM() > max) {
+	if ((memblock_end_of_DRAM() - 1) > max) {
 		ppc_swiotlb_enable = 1;
 		set_pci_dma_ops(&swiotlb_dma_ops);
 		ppc_md.pci_dma_dev_setup = pci_dma_dev_setup_swiotlb;
diff --git a/arch/powerpc/platforms/85xx/mpc8536_ds.c b/arch/powerpc/platforms/85xx/mpc8536_ds.c
index 585bd22b1406..767c7cf18a9c 100644
--- a/arch/powerpc/platforms/85xx/mpc8536_ds.c
+++ b/arch/powerpc/platforms/85xx/mpc8536_ds.c
@@ -75,7 +75,7 @@ static void __init mpc8536_ds_setup_arch(void)
 #endif
 
 #ifdef CONFIG_SWIOTLB
-	if (memblock_end_of_DRAM() > max) {
+	if ((memblock_end_of_DRAM() - 1) > max) {
 		ppc_swiotlb_enable = 1;
 		set_pci_dma_ops(&swiotlb_dma_ops);
 		ppc_md.pci_dma_dev_setup = pci_dma_dev_setup_swiotlb;
diff --git a/arch/powerpc/platforms/85xx/mpc85xx_ds.c b/arch/powerpc/platforms/85xx/mpc85xx_ds.c
index 1fd91e9e0ffb..6d3265fe7718 100644
--- a/arch/powerpc/platforms/85xx/mpc85xx_ds.c
+++ b/arch/powerpc/platforms/85xx/mpc85xx_ds.c
@@ -114,71 +114,53 @@ void __init mpc85xx_ds_pic_init(void)
 }
 
 #ifdef CONFIG_PCI
-static int primary_phb_addr;
 extern int uli_exclude_device(struct pci_controller *hose,
 				u_char bus, u_char devfn);
 
+static struct device_node *pci_with_uli;
+
 static int mpc85xx_exclude_device(struct pci_controller *hose,
 				   u_char bus, u_char devfn)
 {
-	struct device_node* node;
-	struct resource rsrc;
-
-	node = hose->dn;
-	of_address_to_resource(node, 0, &rsrc);
-
-	if ((rsrc.start & 0xfffff) == primary_phb_addr) {
+	if (hose->dn == pci_with_uli)
 		return uli_exclude_device(hose, bus, devfn);
-	}
 
 	return PCIBIOS_SUCCESSFUL;
 }
 #endif	/* CONFIG_PCI */
 
-/*
- * Setup the architecture
- */
-static void __init mpc85xx_ds_setup_arch(void)
+static void __init mpc85xx_ds_pci_init(void)
 {
 #ifdef CONFIG_PCI
-	struct device_node *np;
-	struct pci_controller *hose;
-#endif
-	dma_addr_t max = 0xffffffff;
+	struct device_node *node;
 
-	if (ppc_md.progress)
-		ppc_md.progress("mpc85xx_ds_setup_arch()", 0);
+	fsl_pci_init();
 
-#ifdef CONFIG_PCI
-	for_each_node_by_type(np, "pci") {
-		if (of_device_is_compatible(np, "fsl,mpc8540-pci") ||
-		    of_device_is_compatible(np, "fsl,mpc8548-pcie") ||
-		    of_device_is_compatible(np, "fsl,p2020-pcie")) {
-			struct resource rsrc;
-			of_address_to_resource(np, 0, &rsrc);
-			if ((rsrc.start & 0xfffff) == primary_phb_addr)
-				fsl_add_bridge(np, 1);
-			else
-				fsl_add_bridge(np, 0);
-
-			hose = pci_find_hose_for_OF_device(np);
-			max = min(max, hose->dma_window_base_cur +
-					hose->dma_window_size);
+	/* See if we have a ULI under the primary */
+
+	node = of_find_node_by_name(NULL, "uli1575");
+	while ((pci_with_uli = of_get_parent(node))) {
+		of_node_put(node);
+		node = pci_with_uli;
+
+		if (pci_with_uli == fsl_pci_primary) {
+			ppc_md.pci_exclude_device = mpc85xx_exclude_device;
+			break;
 		}
 	}
-
-	ppc_md.pci_exclude_device = mpc85xx_exclude_device;
 #endif
+}
 
-	mpc85xx_smp_init();
+/*
+ * Setup the architecture
+ */
+static void __init mpc85xx_ds_setup_arch(void)
+{
+	if (ppc_md.progress)
+		ppc_md.progress("mpc85xx_ds_setup_arch()", 0);
 
-#ifdef CONFIG_SWIOTLB
-	if (memblock_end_of_DRAM() > max) {
-		ppc_swiotlb_enable = 1;
-		set_pci_dma_ops(&swiotlb_dma_ops);
-		ppc_md.pci_dma_dev_setup = pci_dma_dev_setup_swiotlb;
-	}
-#endif
+	mpc85xx_ds_pci_init();
+	mpc85xx_smp_init();
 
 	printk("MPC85xx DS board from Freescale Semiconductor\n");
 }
@@ -190,14 +172,7 @@ static int __init mpc8544_ds_probe(void)
 {
 	unsigned long root = of_get_flat_dt_root();
 
-	if (of_flat_dt_is_compatible(root, "MPC8544DS")) {
-#ifdef CONFIG_PCI
-		primary_phb_addr = 0xb000;
-#endif
-		return 1;
-	}
-
-	return 0;
+	return !!of_flat_dt_is_compatible(root, "MPC8544DS");
 }
 
 machine_device_initcall(mpc8544_ds, mpc85xx_common_publish_devices);
@@ -215,14 +190,7 @@ static int __init mpc8572_ds_probe(void)
 {
 	unsigned long root = of_get_flat_dt_root();
 
-	if (of_flat_dt_is_compatible(root, "fsl,MPC8572DS")) {
-#ifdef CONFIG_PCI
-		primary_phb_addr = 0x8000;
-#endif
-		return 1;
-	}
-
-	return 0;
+	return !!of_flat_dt_is_compatible(root, "fsl,MPC8572DS");
 }
 
 /*
@@ -232,14 +200,7 @@ static int __init p2020_ds_probe(void)
 {
 	unsigned long root = of_get_flat_dt_root();
 
-	if (of_flat_dt_is_compatible(root, "fsl,P2020DS")) {
-#ifdef CONFIG_PCI
-		primary_phb_addr = 0x9000;
-#endif
-		return 1;
-	}
-
-	return 0;
+	return !!of_flat_dt_is_compatible(root, "fsl,P2020DS");
 }
 
 define_machine(mpc8544_ds) {
diff --git a/arch/powerpc/platforms/85xx/mpc85xx_mds.c b/arch/powerpc/platforms/85xx/mpc85xx_mds.c
index d208ebccb91c..8e4b094c553b 100644
--- a/arch/powerpc/platforms/85xx/mpc85xx_mds.c
+++ b/arch/powerpc/platforms/85xx/mpc85xx_mds.c
@@ -359,7 +359,7 @@ static void __init mpc85xx_mds_setup_arch(void)
 	mpc85xx_mds_qe_init();
 
 #ifdef CONFIG_SWIOTLB
-	if (memblock_end_of_DRAM() > max) {
+	if ((memblock_end_of_DRAM() - 1) > max) {
 		ppc_swiotlb_enable = 1;
 		set_pci_dma_ops(&swiotlb_dma_ops);
 		ppc_md.pci_dma_dev_setup = pci_dma_dev_setup_swiotlb;
diff --git a/arch/powerpc/platforms/85xx/mpc85xx_rdb.c b/arch/powerpc/platforms/85xx/mpc85xx_rdb.c
index 313fce4f5574..1910fdcb75b2 100644
--- a/arch/powerpc/platforms/85xx/mpc85xx_rdb.c
+++ b/arch/powerpc/platforms/85xx/mpc85xx_rdb.c
@@ -169,6 +169,7 @@ machine_device_initcall(p1020_rdb_pc, mpc85xx_common_publish_devices);
 machine_device_initcall(p1020_utm_pc, mpc85xx_common_publish_devices);
 machine_device_initcall(p1021_rdb_pc, mpc85xx_common_publish_devices);
 machine_device_initcall(p1025_rdb, mpc85xx_common_publish_devices);
+machine_device_initcall(p1024_rdb, mpc85xx_common_publish_devices);
 
 /*
  * Called very early, device-tree isn't unflattened
@@ -237,6 +238,13 @@ static int __init p1020_utm_pc_probe(void)
 	return of_flat_dt_is_compatible(root, "fsl,P1020UTM-PC");
 }
 
+static int __init p1024_rdb_probe(void)
+{
+	unsigned long root = of_get_flat_dt_root();
+
+	return of_flat_dt_is_compatible(root, "fsl,P1024RDB");
+}
+
 define_machine(p2020_rdb) {
 	.name			= "P2020 RDB",
 	.probe			= p2020_rdb_probe,
@@ -348,3 +356,17 @@ define_machine(p1020_rdb_pc) {
 	.calibrate_decr		= generic_calibrate_decr,
 	.progress		= udbg_progress,
 };
+
+define_machine(p1024_rdb) {
+	.name			= "P1024 RDB",
+	.probe			= p1024_rdb_probe,
+	.setup_arch		= mpc85xx_rdb_setup_arch,
+	.init_IRQ		= mpc85xx_rdb_pic_init,
+#ifdef CONFIG_PCI
+	.pcibios_fixup_bus	= fsl_pcibios_fixup_bus,
+#endif
+	.get_irq		= mpic_get_irq,
+	.restart		= fsl_rstcr_restart,
+	.calibrate_decr		= generic_calibrate_decr,
+	.progress		= udbg_progress,
+};
diff --git a/arch/powerpc/platforms/85xx/p1022_ds.c b/arch/powerpc/platforms/85xx/p1022_ds.c
index f700c81a1321..89ee02c54561 100644
--- a/arch/powerpc/platforms/85xx/p1022_ds.c
+++ b/arch/powerpc/platforms/85xx/p1022_ds.c
@@ -27,6 +27,7 @@
 #include <sysdev/fsl_pci.h>
 #include <asm/udbg.h>
 #include <asm/fsl_guts.h>
+#include <asm/fsl_lbc.h>
 #include "smp.h"
 
 #include "mpc85xx.h"
@@ -142,17 +143,73 @@ static void p1022ds_set_gamma_table(enum fsl_diu_monitor_port port,
 {
 }
 
+struct fsl_law {
+	u32	lawbar;
+	u32	reserved1;
+	u32	lawar;
+	u32	reserved[5];
+};
+
+#define LAWBAR_MASK	0x00F00000
+#define LAWBAR_SHIFT	12
+
+#define LAWAR_EN	0x80000000
+#define LAWAR_TGT_MASK	0x01F00000
+#define LAW_TRGT_IF_LBC	(0x04 << 20)
+
+#define LAWAR_MASK	(LAWAR_EN | LAWAR_TGT_MASK)
+#define LAWAR_MATCH	(LAWAR_EN | LAW_TRGT_IF_LBC)
+
+#define BR_BA		0xFFFF8000
+
+/*
+ * Map a BRx value to a physical address
+ *
+ * The localbus BRx registers only store the lower 32 bits of the address.  To
+ * obtain the upper four bits, we need to scan the LAW table.  The entry which
+ * maps to the localbus will contain the upper four bits.
+ */
+static phys_addr_t lbc_br_to_phys(const void *ecm, unsigned int count, u32 br)
+{
+#ifndef CONFIG_PHYS_64BIT
+	/*
+	 * If we only have 32-bit addressing, then the BRx address *is* the
+	 * physical address.
+	 */
+	return br & BR_BA;
+#else
+	const struct fsl_law *law = ecm + 0xc08;
+	unsigned int i;
+
+	for (i = 0; i < count; i++) {
+		u64 lawbar = in_be32(&law[i].lawbar);
+		u32 lawar = in_be32(&law[i].lawar);
+
+		if ((lawar & LAWAR_MASK) == LAWAR_MATCH)
+			/* Extract the upper four bits */
+			return (br & BR_BA) | ((lawbar & LAWBAR_MASK) << 12);
+	}
+
+	return 0;
+#endif
+}
+
 /**
  * p1022ds_set_monitor_port: switch the output to a different monitor port
- *
  */
 static void p1022ds_set_monitor_port(enum fsl_diu_monitor_port port)
 {
 	struct device_node *guts_node;
-	struct device_node *indirect_node = NULL;
+	struct device_node *lbc_node = NULL;
+	struct device_node *law_node = NULL;
 	struct ccsr_guts __iomem *guts;
+	struct fsl_lbc_regs *lbc = NULL;
+	void *ecm = NULL;
 	u8 __iomem *lbc_lcs0_ba = NULL;
 	u8 __iomem *lbc_lcs1_ba = NULL;
+	phys_addr_t cs0_addr, cs1_addr;
+	const __be32 *iprop;
+	unsigned int num_laws;
 	u8 b;
 
 	/* Map the global utilities registers. */
@@ -168,24 +225,42 @@ static void p1022ds_set_monitor_port(enum fsl_diu_monitor_port port)
 		goto exit;
 	}
 
-	indirect_node = of_find_compatible_node(NULL, NULL,
-					     "fsl,p1022ds-indirect-pixis");
-	if (!indirect_node) {
-		pr_err("p1022ds: missing pixis indirect mode node\n");
+	lbc_node = of_find_compatible_node(NULL, NULL, "fsl,p1022-elbc");
+	if (!lbc_node) {
+		pr_err("p1022ds: missing localbus node\n");
+		goto exit;
+	}
+
+	lbc = of_iomap(lbc_node, 0);
+	if (!lbc) {
+		pr_err("p1022ds: could not map localbus node\n");
+		goto exit;
+	}
+
+	law_node = of_find_compatible_node(NULL, NULL, "fsl,ecm-law");
+	if (!law_node) {
+		pr_err("p1022ds: missing local access window node\n");
 		goto exit;
 	}
 
-	lbc_lcs0_ba = of_iomap(indirect_node, 0);
-	if (!lbc_lcs0_ba) {
-		pr_err("p1022ds: could not map localbus chip select 0\n");
+	ecm = of_iomap(law_node, 0);
+	if (!ecm) {
+		pr_err("p1022ds: could not map local access window node\n");
 		goto exit;
 	}
 
-	lbc_lcs1_ba = of_iomap(indirect_node, 1);
-	if (!lbc_lcs1_ba) {
-		pr_err("p1022ds: could not map localbus chip select 1\n");
+	iprop = of_get_property(law_node, "fsl,num-laws", 0);
+	if (!iprop) {
+		pr_err("p1022ds: LAW node is missing fsl,num-laws property\n");
 		goto exit;
 	}
+	num_laws = be32_to_cpup(iprop);
+
+	cs0_addr = lbc_br_to_phys(ecm, num_laws, in_be32(&lbc->bank[0].br));
+	cs1_addr = lbc_br_to_phys(ecm, num_laws, in_be32(&lbc->bank[1].br));
+
+	lbc_lcs0_ba = ioremap(cs0_addr, 1);
+	lbc_lcs1_ba = ioremap(cs1_addr, 1);
 
 	/* Make sure we're in indirect mode first. */
 	if ((in_be32(&guts->pmuxcr) & PMUXCR_ELBCDIU_MASK) !=
@@ -254,10 +329,15 @@ exit:
 		iounmap(lbc_lcs1_ba);
 	if (lbc_lcs0_ba)
 		iounmap(lbc_lcs0_ba);
+	if (lbc)
+		iounmap(lbc);
+	if (ecm)
+		iounmap(ecm);
 	if (guts)
 		iounmap(guts);
 
-	of_node_put(indirect_node);
+	of_node_put(law_node);
+	of_node_put(lbc_node);
 	of_node_put(guts_node);
 }
 
@@ -348,13 +428,7 @@ void __init p1022_ds_pic_init(void)
  */
 static void __init disable_one_node(struct device_node *np, struct property *new)
 {
-	struct property *old;
-
-	old = of_find_property(np, new->name, NULL);
-	if (old)
-		prom_update_property(np, new, old);
-	else
-		prom_add_property(np, new);
+	prom_update_property(np, new);
 }
 
 /* TRUE if there is a "video=fslfb" command-line parameter. */
@@ -450,7 +524,7 @@ static void __init p1022_ds_setup_arch(void)
 	mpc85xx_smp_init();
 
 #ifdef CONFIG_SWIOTLB
-	if (memblock_end_of_DRAM() > max) {
+	if ((memblock_end_of_DRAM() - 1) > max) {
 		ppc_swiotlb_enable = 1;
 		set_pci_dma_ops(&swiotlb_dma_ops);
 		ppc_md.pci_dma_dev_setup = pci_dma_dev_setup_swiotlb;
diff --git a/arch/powerpc/platforms/85xx/p3060_qds.c b/arch/powerpc/platforms/85xx/p3060_qds.c
deleted file mode 100644
index 081cf4ac1881..000000000000
--- a/arch/powerpc/platforms/85xx/p3060_qds.c
+++ /dev/null
@@ -1,77 +0,0 @@
-/*
- * P3060 QDS Setup
- *
- * Copyright 2011 Freescale Semiconductor Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- */
-
-#include <linux/kernel.h>
-#include <linux/interrupt.h>
-#include <linux/phy.h>
-#include <asm/machdep.h>
-#include <asm/udbg.h>
-#include <asm/mpic.h>
-#include <linux/of_platform.h>
-#include <sysdev/fsl_soc.h>
-#include <sysdev/fsl_pci.h>
-#include <asm/ehv_pic.h>
-#include "corenet_ds.h"
-
-/*
- * Called very early, device-tree isn't unflattened
- */
-static int __init p3060_qds_probe(void)
-{
-	unsigned long root = of_get_flat_dt_root();
-#ifdef CONFIG_SMP
-	extern struct smp_ops_t smp_85xx_ops;
-#endif
-
-	if (of_flat_dt_is_compatible(root, "fsl,P3060QDS"))
-		return 1;
-
-	/* Check if we're running under the Freescale hypervisor */
-	if (of_flat_dt_is_compatible(root, "fsl,P3060QDS-hv")) {
-		ppc_md.init_IRQ = ehv_pic_init;
-		ppc_md.get_irq = ehv_pic_get_irq;
-		ppc_md.restart = fsl_hv_restart;
-		ppc_md.power_off = fsl_hv_halt;
-		ppc_md.halt = fsl_hv_halt;
-#ifdef CONFIG_SMP
-		/*
-		 * Disable the timebase sync operations because we can't write
-		 * to the timebase registers under the hypervisor.
-		 */
-		smp_85xx_ops.give_timebase = NULL;
-		smp_85xx_ops.take_timebase = NULL;
-#endif
-		return 1;
-	}
-
-	return 0;
-}
-
-define_machine(p3060_qds) {
-	.name			= "P3060 QDS",
-	.probe			= p3060_qds_probe,
-	.setup_arch		= corenet_ds_setup_arch,
-	.init_IRQ		= corenet_ds_pic_init,
-#ifdef CONFIG_PCI
-	.pcibios_fixup_bus	= fsl_pcibios_fixup_bus,
-#endif
-	.get_irq		= mpic_get_coreint_irq,
-	.restart		= fsl_rstcr_restart,
-	.calibrate_decr		= generic_calibrate_decr,
-	.progress		= udbg_progress,
-	.power_save		= e500_idle,
-};
-
-machine_device_initcall(p3060_qds, corenet_ds_publish_devices);
-
-#ifdef CONFIG_SWIOTLB
-machine_arch_initcall(p3060_qds, swiotlb_setup_bus_notifier);
-#endif
diff --git a/arch/powerpc/platforms/85xx/qemu_e500.c b/arch/powerpc/platforms/85xx/qemu_e500.c
new file mode 100644
index 000000000000..95a2e53af71b
--- /dev/null
+++ b/arch/powerpc/platforms/85xx/qemu_e500.c
@@ -0,0 +1,72 @@
+/*
+ * Paravirt target for a generic QEMU e500 machine
+ *
+ * This is intended to be a flexible device-tree-driven platform, not fixed
+ * to a particular piece of hardware or a particular spec of virtual hardware,
+ * beyond the assumption of an e500-family CPU.  Some things are still hardcoded
+ * here, such as MPIC, but this is a limitation of the current code rather than
+ * an interface contract with QEMU.
+ *
+ * Copyright 2012 Freescale Semiconductor Inc.
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/of_fdt.h>
+#include <asm/machdep.h>
+#include <asm/time.h>
+#include <asm/udbg.h>
+#include <asm/mpic.h>
+#include <sysdev/fsl_soc.h>
+#include <sysdev/fsl_pci.h>
+#include "smp.h"
+#include "mpc85xx.h"
+
+void __init qemu_e500_pic_init(void)
+{
+	struct mpic *mpic;
+
+	mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN | MPIC_SINGLE_DEST_CPU,
+			0, 256, " OpenPIC  ");
+
+	BUG_ON(mpic == NULL);
+	mpic_init(mpic);
+}
+
+static void __init qemu_e500_setup_arch(void)
+{
+	ppc_md.progress("qemu_e500_setup_arch()", 0);
+
+	fsl_pci_init();
+	mpc85xx_smp_init();
+}
+
+/*
+ * Called very early, device-tree isn't unflattened
+ */
+static int __init qemu_e500_probe(void)
+{
+	unsigned long root = of_get_flat_dt_root();
+
+	return !!of_flat_dt_is_compatible(root, "fsl,qemu-e500");
+}
+
+machine_device_initcall(qemu_e500, mpc85xx_common_publish_devices);
+
+define_machine(qemu_e500) {
+	.name			= "QEMU e500",
+	.probe			= qemu_e500_probe,
+	.setup_arch		= qemu_e500_setup_arch,
+	.init_IRQ		= qemu_e500_pic_init,
+#ifdef CONFIG_PCI
+	.pcibios_fixup_bus	= fsl_pcibios_fixup_bus,
+#endif
+	.get_irq		= mpic_get_irq,
+	.restart		= fsl_rstcr_restart,
+	.calibrate_decr		= generic_calibrate_decr,
+	.progress		= udbg_progress,
+};
diff --git a/arch/powerpc/platforms/85xx/sbc8560.c b/arch/powerpc/platforms/85xx/sbc8560.c
deleted file mode 100644
index b1be632ede43..000000000000
--- a/arch/powerpc/platforms/85xx/sbc8560.c
+++ /dev/null
@@ -1,254 +0,0 @@
-/*
- * Wind River SBC8560 setup and early boot code.
- *
- * Copyright 2007 Wind River Systems Inc.
- *
- * By Paul Gortmaker (see MAINTAINERS for contact information)
- *
- * Based largely on the MPC8560ADS support - Copyright 2005 Freescale Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- */
-
-#include <linux/stddef.h>
-#include <linux/kernel.h>
-#include <linux/pci.h>
-#include <linux/kdev_t.h>
-#include <linux/delay.h>
-#include <linux/seq_file.h>
-#include <linux/of_platform.h>
-
-#include <asm/time.h>
-#include <asm/machdep.h>
-#include <asm/pci-bridge.h>
-#include <asm/mpic.h>
-#include <mm/mmu_decl.h>
-#include <asm/udbg.h>
-
-#include <sysdev/fsl_soc.h>
-#include <sysdev/fsl_pci.h>
-
-#include "mpc85xx.h"
-
-#ifdef CONFIG_CPM2
-#include <asm/cpm2.h>
-#include <sysdev/cpm2_pic.h>
-#endif
-
-static void __init sbc8560_pic_init(void)
-{
-	struct mpic *mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN,
-			0, 256, " OpenPIC  ");
-	BUG_ON(mpic == NULL);
-	mpic_init(mpic);
-
-	mpc85xx_cpm2_pic_init();
-}
-
-/*
- * Setup the architecture
- */
-#ifdef CONFIG_CPM2
-struct cpm_pin {
-	int port, pin, flags;
-};
-
-static const struct cpm_pin sbc8560_pins[] = {
-	/* SCC1 */
-	{3, 29, CPM_PIN_OUTPUT | CPM_PIN_PRIMARY},
-	{3, 30, CPM_PIN_OUTPUT | CPM_PIN_SECONDARY},
-	{3, 31, CPM_PIN_INPUT | CPM_PIN_PRIMARY},
-
-	/* SCC2 */
-	{3, 26, CPM_PIN_OUTPUT | CPM_PIN_PRIMARY},
-	{3, 27, CPM_PIN_OUTPUT | CPM_PIN_PRIMARY},
-	{3, 28, CPM_PIN_INPUT | CPM_PIN_PRIMARY},
-
-	/* FCC2 */
-	{1, 18, CPM_PIN_INPUT | CPM_PIN_PRIMARY},
-	{1, 19, CPM_PIN_INPUT | CPM_PIN_PRIMARY},
-	{1, 20, CPM_PIN_INPUT | CPM_PIN_PRIMARY},
-	{1, 21, CPM_PIN_INPUT | CPM_PIN_PRIMARY},
-	{1, 22, CPM_PIN_OUTPUT | CPM_PIN_PRIMARY},
-	{1, 23, CPM_PIN_OUTPUT | CPM_PIN_PRIMARY},
-	{1, 24, CPM_PIN_OUTPUT | CPM_PIN_PRIMARY},
-	{1, 25, CPM_PIN_OUTPUT | CPM_PIN_PRIMARY},
-	{1, 26, CPM_PIN_INPUT | CPM_PIN_PRIMARY},
-	{1, 27, CPM_PIN_INPUT | CPM_PIN_PRIMARY},
-	{1, 28, CPM_PIN_INPUT | CPM_PIN_PRIMARY},
-	{1, 29, CPM_PIN_OUTPUT | CPM_PIN_SECONDARY},
-	{1, 30, CPM_PIN_INPUT | CPM_PIN_PRIMARY},
-	{1, 31, CPM_PIN_OUTPUT | CPM_PIN_PRIMARY},
-	{2, 18, CPM_PIN_INPUT | CPM_PIN_PRIMARY}, /* CLK14 */
-	{2, 19, CPM_PIN_INPUT | CPM_PIN_PRIMARY}, /* CLK13 */
-
-	/* FCC3 */
-	{1, 4, CPM_PIN_OUTPUT | CPM_PIN_PRIMARY},
-	{1, 5, CPM_PIN_OUTPUT | CPM_PIN_PRIMARY},
-	{1, 6, CPM_PIN_OUTPUT | CPM_PIN_PRIMARY},
-	{1, 7, CPM_PIN_OUTPUT | CPM_PIN_PRIMARY},
-	{1, 8, CPM_PIN_INPUT | CPM_PIN_PRIMARY},
-	{1, 9, CPM_PIN_INPUT | CPM_PIN_PRIMARY},
-	{1, 10, CPM_PIN_INPUT | CPM_PIN_PRIMARY},
-	{1, 11, CPM_PIN_INPUT | CPM_PIN_PRIMARY},
-	{1, 12, CPM_PIN_INPUT | CPM_PIN_PRIMARY},
-	{1, 13, CPM_PIN_INPUT | CPM_PIN_PRIMARY},
-	{1, 14, CPM_PIN_OUTPUT | CPM_PIN_PRIMARY},
-	{1, 15, CPM_PIN_OUTPUT | CPM_PIN_PRIMARY},
-	{1, 16, CPM_PIN_INPUT | CPM_PIN_PRIMARY},
-	{1, 17, CPM_PIN_INPUT | CPM_PIN_PRIMARY},
-	{2, 16, CPM_PIN_INPUT | CPM_PIN_SECONDARY}, /* CLK16 */
-	{2, 17, CPM_PIN_INPUT | CPM_PIN_SECONDARY}, /* CLK15 */
-};
-
-static void __init init_ioports(void)
-{
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(sbc8560_pins); i++) {
-		const struct cpm_pin *pin = &sbc8560_pins[i];
-		cpm2_set_pin(pin->port, pin->pin, pin->flags);
-	}
-
-	cpm2_clk_setup(CPM_CLK_SCC1, CPM_BRG1, CPM_CLK_RX);
-	cpm2_clk_setup(CPM_CLK_SCC1, CPM_BRG1, CPM_CLK_TX);
-	cpm2_clk_setup(CPM_CLK_SCC2, CPM_BRG2, CPM_CLK_RX);
-	cpm2_clk_setup(CPM_CLK_SCC2, CPM_BRG2, CPM_CLK_TX);
-	cpm2_clk_setup(CPM_CLK_FCC2, CPM_CLK13, CPM_CLK_RX);
-	cpm2_clk_setup(CPM_CLK_FCC2, CPM_CLK14, CPM_CLK_TX);
-	cpm2_clk_setup(CPM_CLK_FCC3, CPM_CLK15, CPM_CLK_RX);
-	cpm2_clk_setup(CPM_CLK_FCC3, CPM_CLK16, CPM_CLK_TX);
-}
-#endif
-
-static void __init sbc8560_setup_arch(void)
-{
-#ifdef CONFIG_PCI
-	struct device_node *np;
-#endif
-
-	if (ppc_md.progress)
-		ppc_md.progress("sbc8560_setup_arch()", 0);
-
-#ifdef CONFIG_CPM2
-	cpm2_reset();
-	init_ioports();
-#endif
-
-#ifdef CONFIG_PCI
-	for_each_compatible_node(np, "pci", "fsl,mpc8540-pci")
-		fsl_add_bridge(np, 1);
-#endif
-}
-
-static void sbc8560_show_cpuinfo(struct seq_file *m)
-{
-	uint pvid, svid, phid1;
-
-	pvid = mfspr(SPRN_PVR);
-	svid = mfspr(SPRN_SVR);
-
-	seq_printf(m, "Vendor\t\t: Wind River\n");
-	seq_printf(m, "PVR\t\t: 0x%x\n", pvid);
-	seq_printf(m, "SVR\t\t: 0x%x\n", svid);
-
-	/* Display cpu Pll setting */
-	phid1 = mfspr(SPRN_HID1);
-	seq_printf(m, "PLL setting\t: 0x%x\n", ((phid1 >> 24) & 0x3f));
-}
-
-machine_device_initcall(sbc8560, mpc85xx_common_publish_devices);
-
-/*
- * Called very early, device-tree isn't unflattened
- */
-static int __init sbc8560_probe(void)
-{
-        unsigned long root = of_get_flat_dt_root();
-
-        return of_flat_dt_is_compatible(root, "SBC8560");
-}
-
-#ifdef CONFIG_RTC_DRV_M48T59
-static int __init sbc8560_rtc_init(void)
-{
-	struct device_node *np;
-	struct resource res;
-	struct platform_device *rtc_dev;
-
-	np = of_find_compatible_node(NULL, NULL, "m48t59");
-	if (np == NULL) {
-		printk("No RTC in DTB. Has it been eaten by wild dogs?\n");
-		return -ENODEV;
-	}
-
-	of_address_to_resource(np, 0, &res);
-	of_node_put(np);
-
-	printk("Found RTC (m48t59) at i/o 0x%x\n", res.start);
-
-	rtc_dev = platform_device_register_simple("rtc-m48t59", 0, &res, 1);
-
-	if (IS_ERR(rtc_dev)) {
-		printk("Registering sbc8560 RTC device failed\n");
-		return PTR_ERR(rtc_dev);
-	}
-
-	return 0;
-}
-
-arch_initcall(sbc8560_rtc_init);
-
-#endif	/* M48T59 */
-
-static __u8 __iomem *brstcr;
-
-static int __init sbc8560_bdrstcr_init(void)
-{
-	struct device_node *np;
-	struct resource res;
-
-	np = of_find_compatible_node(NULL, NULL, "wrs,sbc8560-brstcr");
-	if (np == NULL) {
-		printk(KERN_WARNING "sbc8560: No board specific RSTCR in DTB.\n");
-		return -ENODEV;
-	}
-
-	of_address_to_resource(np, 0, &res);
-
-	printk(KERN_INFO "sbc8560: Found BRSTCR at %pR\n", &res);
-
-	brstcr = ioremap(res.start, resource_size(&res));
-	if(!brstcr)
-		printk(KERN_WARNING "sbc8560: ioremap of brstcr failed.\n");
-
-	of_node_put(np);
-
-	return 0;
-}
-
-arch_initcall(sbc8560_bdrstcr_init);
-
-void sbc8560_rstcr_restart(char * cmd)
-{
-	local_irq_disable();
-	if(brstcr)
-		clrbits8(brstcr, 0x80);
-
-	while(1);
-}
-
-define_machine(sbc8560) {
-	.name			= "SBC8560",
-	.probe			= sbc8560_probe,
-	.setup_arch		= sbc8560_setup_arch,
-	.init_IRQ		= sbc8560_pic_init,
-	.show_cpuinfo		= sbc8560_show_cpuinfo,
-	.get_irq		= mpic_get_irq,
-	.restart		= sbc8560_rstcr_restart,
-	.calibrate_decr		= generic_calibrate_decr,
-	.progress		= udbg_progress,
-};
diff --git a/arch/powerpc/platforms/85xx/tqm85xx.c b/arch/powerpc/platforms/85xx/tqm85xx.c
index 4d786c25d3e5..3e70a2035e53 100644
--- a/arch/powerpc/platforms/85xx/tqm85xx.c
+++ b/arch/powerpc/platforms/85xx/tqm85xx.c
@@ -102,7 +102,7 @@ static void tqm85xx_show_cpuinfo(struct seq_file *m)
 	seq_printf(m, "PLL setting\t: 0x%x\n", ((phid1 >> 24) & 0x3f));
 }
 
-static void __init tqm85xx_ti1520_fixup(struct pci_dev *pdev)
+static void __devinit tqm85xx_ti1520_fixup(struct pci_dev *pdev)
 {
 	unsigned int val;
 
diff --git a/arch/powerpc/platforms/86xx/gef_ppc9a.c b/arch/powerpc/platforms/86xx/gef_ppc9a.c
index 1fca663f1b25..563aafa8629c 100644
--- a/arch/powerpc/platforms/86xx/gef_ppc9a.c
+++ b/arch/powerpc/platforms/86xx/gef_ppc9a.c
@@ -164,7 +164,7 @@ static void gef_ppc9a_show_cpuinfo(struct seq_file *m)
 		gef_ppc9a_get_vme_is_syscon() ? "yes" : "no");
 }
 
-static void __init gef_ppc9a_nec_fixup(struct pci_dev *pdev)
+static void __devinit gef_ppc9a_nec_fixup(struct pci_dev *pdev)
 {
 	unsigned int val;
 
diff --git a/arch/powerpc/platforms/86xx/gef_sbc310.c b/arch/powerpc/platforms/86xx/gef_sbc310.c
index 14e0e576bcbd..cc6a91ae0889 100644
--- a/arch/powerpc/platforms/86xx/gef_sbc310.c
+++ b/arch/powerpc/platforms/86xx/gef_sbc310.c
@@ -152,7 +152,7 @@ static void gef_sbc310_show_cpuinfo(struct seq_file *m)
 
 }
 
-static void __init gef_sbc310_nec_fixup(struct pci_dev *pdev)
+static void __devinit gef_sbc310_nec_fixup(struct pci_dev *pdev)
 {
 	unsigned int val;
 
diff --git a/arch/powerpc/platforms/86xx/gef_sbc610.c b/arch/powerpc/platforms/86xx/gef_sbc610.c
index 1638f43599f0..aead6b337f4a 100644
--- a/arch/powerpc/platforms/86xx/gef_sbc610.c
+++ b/arch/powerpc/platforms/86xx/gef_sbc610.c
@@ -141,7 +141,7 @@ static void gef_sbc610_show_cpuinfo(struct seq_file *m)
 	seq_printf(m, "SVR\t\t: 0x%x\n", svid);
 }
 
-static void __init gef_sbc610_nec_fixup(struct pci_dev *pdev)
+static void __devinit gef_sbc610_nec_fixup(struct pci_dev *pdev)
 {
 	unsigned int val;
 
diff --git a/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c b/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c
index 3755e61d7ecf..817245bc0219 100644
--- a/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c
+++ b/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c
@@ -102,7 +102,7 @@ mpc86xx_hpcn_setup_arch(void)
 #endif
 
 #ifdef CONFIG_SWIOTLB
-	if (memblock_end_of_DRAM() > max) {
+	if ((memblock_end_of_DRAM() - 1) > max) {
 		ppc_swiotlb_enable = 1;
 		set_pci_dma_ops(&swiotlb_dma_ops);
 		ppc_md.pci_dma_dev_setup = pci_dma_dev_setup_swiotlb;
diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig
index a35ca44ade66..e7a896acd982 100644
--- a/arch/powerpc/platforms/Kconfig
+++ b/arch/powerpc/platforms/Kconfig
@@ -25,6 +25,7 @@ source "arch/powerpc/platforms/wsp/Kconfig"
 config KVM_GUEST
 	bool "KVM Guest support"
 	default n
+	select EPAPR_PARAVIRT
 	---help---
 	  This option enables various optimizations for running under the KVM
 	  hypervisor. Overhead for the kernel when not running inside KVM should
@@ -32,6 +33,14 @@ config KVM_GUEST
 
 	  In case of doubt, say Y
 
+config EPAPR_PARAVIRT
+	bool "ePAPR para-virtualization support"
+	default n
+	help
+	  Enables ePAPR para-virtualization support for guests.
+
+	  In case of doubt, say Y
+
 config PPC_NATIVE
 	bool
 	depends on 6xx || PPC64
diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype
index 61c9550819a2..30fd01de6bed 100644
--- a/arch/powerpc/platforms/Kconfig.cputype
+++ b/arch/powerpc/platforms/Kconfig.cputype
@@ -159,6 +159,10 @@ config PPC_E500MC
 	bool "e500mc Support"
 	select PPC_FPU
 	depends on E500
+	help
+	  This must be enabled for running on e500mc (and derivatives
+	  such as e5500/e6500), and must be disabled for running on
+	  e500v1 or e500v2.
 
 config PPC_FPU
 	bool
diff --git a/arch/powerpc/platforms/cell/beat_hvCall.S b/arch/powerpc/platforms/cell/beat_hvCall.S
index 74c817448948..96c801907126 100644
--- a/arch/powerpc/platforms/cell/beat_hvCall.S
+++ b/arch/powerpc/platforms/cell/beat_hvCall.S
@@ -22,8 +22,6 @@
 
 #include <asm/ppc_asm.h>
 
-#define	STK_PARM(i)	(48 + ((i)-3)*8)
-
 /* Not implemented on Beat, now */
 #define	HCALL_INST_PRECALL
 #define	HCALL_INST_POSTCALL
@@ -74,7 +72,7 @@ _GLOBAL(beat_hcall_norets8)
 	mr	r6,r7
 	mr	r7,r8
 	mr	r8,r9
-	ld	r10,STK_PARM(r10)(r1)
+	ld	r10,STK_PARAM(R10)(r1)
 
 	HVSC				/* invoke the hypervisor */
 
@@ -94,7 +92,7 @@ _GLOBAL(beat_hcall1)
 
 	HCALL_INST_PRECALL
 
-	std	r4,STK_PARM(r4)(r1)	/* save ret buffer */
+	std	r4,STK_PARAM(R4)(r1)	/* save ret buffer */
 
 	mr	r11,r3
 	mr	r3,r5
@@ -108,7 +106,7 @@ _GLOBAL(beat_hcall1)
 
 	HCALL_INST_POSTCALL
 
-	ld	r12,STK_PARM(r4)(r1)
+	ld	r12,STK_PARAM(R4)(r1)
 	std	r4,  0(r12)
 
 	lwz	r0,8(r1)
@@ -125,7 +123,7 @@ _GLOBAL(beat_hcall2)
 
 	HCALL_INST_PRECALL
 
-	std	r4,STK_PARM(r4)(r1)	/* save ret buffer */
+	std	r4,STK_PARAM(R4)(r1)	/* save ret buffer */
 
 	mr	r11,r3
 	mr	r3,r5
@@ -139,7 +137,7 @@ _GLOBAL(beat_hcall2)
 
 	HCALL_INST_POSTCALL
 
-	ld	r12,STK_PARM(r4)(r1)
+	ld	r12,STK_PARAM(R4)(r1)
 	std	r4,  0(r12)
 	std	r5,  8(r12)
 
@@ -157,7 +155,7 @@ _GLOBAL(beat_hcall3)
 
 	HCALL_INST_PRECALL
 
-	std	r4,STK_PARM(r4)(r1)	/* save ret buffer */
+	std	r4,STK_PARAM(R4)(r1)	/* save ret buffer */
 
 	mr	r11,r3
 	mr	r3,r5
@@ -171,7 +169,7 @@ _GLOBAL(beat_hcall3)
 
 	HCALL_INST_POSTCALL
 
-	ld	r12,STK_PARM(r4)(r1)
+	ld	r12,STK_PARAM(R4)(r1)
 	std	r4,  0(r12)
 	std	r5,  8(r12)
 	std	r6, 16(r12)
@@ -190,7 +188,7 @@ _GLOBAL(beat_hcall4)
 
 	HCALL_INST_PRECALL
 
-	std	r4,STK_PARM(r4)(r1)	/* save ret buffer */
+	std	r4,STK_PARAM(R4)(r1)	/* save ret buffer */
 
 	mr	r11,r3
 	mr	r3,r5
@@ -204,7 +202,7 @@ _GLOBAL(beat_hcall4)
 
 	HCALL_INST_POSTCALL
 
-	ld	r12,STK_PARM(r4)(r1)
+	ld	r12,STK_PARAM(R4)(r1)
 	std	r4,  0(r12)
 	std	r5,  8(r12)
 	std	r6, 16(r12)
@@ -224,7 +222,7 @@ _GLOBAL(beat_hcall5)
 
 	HCALL_INST_PRECALL
 
-	std	r4,STK_PARM(r4)(r1)	/* save ret buffer */
+	std	r4,STK_PARAM(R4)(r1)	/* save ret buffer */
 
 	mr	r11,r3
 	mr	r3,r5
@@ -238,7 +236,7 @@ _GLOBAL(beat_hcall5)
 
 	HCALL_INST_POSTCALL
 
-	ld	r12,STK_PARM(r4)(r1)
+	ld	r12,STK_PARAM(R4)(r1)
 	std	r4,  0(r12)
 	std	r5,  8(r12)
 	std	r6, 16(r12)
@@ -259,7 +257,7 @@ _GLOBAL(beat_hcall6)
 
 	HCALL_INST_PRECALL
 
-	std	r4,STK_PARM(r4)(r1)	/* save ret buffer */
+	std	r4,STK_PARAM(R4)(r1)	/* save ret buffer */
 
 	mr	r11,r3
 	mr	r3,r5
@@ -273,7 +271,7 @@ _GLOBAL(beat_hcall6)
 
 	HCALL_INST_POSTCALL
 
-	ld	r12,STK_PARM(r4)(r1)
+	ld	r12,STK_PARAM(R4)(r1)
 	std	r4,  0(r12)
 	std	r5,  8(r12)
 	std	r6, 16(r12)
diff --git a/arch/powerpc/platforms/cell/iommu.c b/arch/powerpc/platforms/cell/iommu.c
index b6732004c882..dca213666747 100644
--- a/arch/powerpc/platforms/cell/iommu.c
+++ b/arch/powerpc/platforms/cell/iommu.c
@@ -518,7 +518,6 @@ cell_iommu_setup_window(struct cbe_iommu *iommu, struct device_node *np,
 	__set_bit(0, window->table.it_map);
 	tce_build_cell(&window->table, window->table.it_offset, 1,
 		       (unsigned long)iommu->pad_page, DMA_TO_DEVICE, NULL);
-	window->table.it_hint = window->table.it_blocksize;
 
 	return window;
 }
diff --git a/arch/powerpc/platforms/cell/pervasive.c b/arch/powerpc/platforms/cell/pervasive.c
index efdacc829576..d17e98bc0c10 100644
--- a/arch/powerpc/platforms/cell/pervasive.c
+++ b/arch/powerpc/platforms/cell/pervasive.c
@@ -42,11 +42,9 @@ static void cbe_power_save(void)
 {
 	unsigned long ctrl, thread_switch_control;
 
-	/*
-	 * We need to hard disable interrupts, the local_irq_enable() done by
-	 * our caller upon return will hard re-enable.
-	 */
-	hard_irq_disable();
+	/* Ensure our interrupt state is properly tracked */
+	if (!prep_irq_for_idle())
+		return;
 
 	ctrl = mfspr(SPRN_CTRLF);
 
@@ -81,6 +79,9 @@ static void cbe_power_save(void)
 	 */
 	ctrl &= ~(CTRL_RUNLATCH | CTRL_TE);
 	mtspr(SPRN_CTRLT, ctrl);
+
+	/* Re-enable interrupts in MSR */
+	__hard_irq_enable();
 }
 
 static int cbe_system_reset_exception(struct pt_regs *regs)
diff --git a/arch/powerpc/platforms/cell/spufs/inode.c b/arch/powerpc/platforms/cell/spufs/inode.c
index 66519d263da7..d544d7816df3 100644
--- a/arch/powerpc/platforms/cell/spufs/inode.c
+++ b/arch/powerpc/platforms/cell/spufs/inode.c
@@ -317,28 +317,23 @@ out:
 	return ret;
 }
 
-static int spufs_context_open(struct dentry *dentry, struct vfsmount *mnt)
+static int spufs_context_open(struct path *path)
 {
 	int ret;
 	struct file *filp;
 
 	ret = get_unused_fd();
-	if (ret < 0) {
-		dput(dentry);
-		mntput(mnt);
-		goto out;
-	}
+	if (ret < 0)
+		return ret;
 
-	filp = dentry_open(dentry, mnt, O_RDONLY, current_cred());
+	filp = dentry_open(path, O_RDONLY, current_cred());
 	if (IS_ERR(filp)) {
 		put_unused_fd(ret);
-		ret = PTR_ERR(filp);
-		goto out;
+		return PTR_ERR(filp);
 	}
 
 	filp->f_op = &spufs_context_fops;
 	fd_install(ret, filp);
-out:
 	return ret;
 }
 
@@ -453,6 +448,7 @@ spufs_create_context(struct inode *inode, struct dentry *dentry,
 	int affinity;
 	struct spu_gang *gang;
 	struct spu_context *neighbor;
+	struct path path = {.mnt = mnt, .dentry = dentry};
 
 	ret = -EPERM;
 	if ((flags & SPU_CREATE_NOSCHED) &&
@@ -495,11 +491,7 @@ spufs_create_context(struct inode *inode, struct dentry *dentry,
 			put_spu_context(neighbor);
 	}
 
-	/*
-	 * get references for dget and mntget, will be released
-	 * in error path of *_open().
-	 */
-	ret = spufs_context_open(dget(dentry), mntget(mnt));
+	ret = spufs_context_open(&path);
 	if (ret < 0) {
 		WARN_ON(spufs_rmdir(inode, dentry));
 		if (affinity)
@@ -556,28 +548,27 @@ out:
 	return ret;
 }
 
-static int spufs_gang_open(struct dentry *dentry, struct vfsmount *mnt)
+static int spufs_gang_open(struct path *path)
 {
 	int ret;
 	struct file *filp;
 
 	ret = get_unused_fd();
-	if (ret < 0) {
-		dput(dentry);
-		mntput(mnt);
-		goto out;
-	}
+	if (ret < 0)
+		return ret;
 
-	filp = dentry_open(dentry, mnt, O_RDONLY, current_cred());
+	/*
+	 * get references for dget and mntget, will be released
+	 * in error path of *_open().
+	 */
+	filp = dentry_open(path, O_RDONLY, current_cred());
 	if (IS_ERR(filp)) {
 		put_unused_fd(ret);
-		ret = PTR_ERR(filp);
-		goto out;
+		return PTR_ERR(filp);
 	}
 
 	filp->f_op = &simple_dir_operations;
 	fd_install(ret, filp);
-out:
 	return ret;
 }
 
@@ -585,17 +576,14 @@ static int spufs_create_gang(struct inode *inode,
 			struct dentry *dentry,
 			struct vfsmount *mnt, umode_t mode)
 {
+	struct path path = {.mnt = mnt, .dentry = dentry};
 	int ret;
 
 	ret = spufs_mkgang(inode, dentry, mode & S_IRWXUGO);
 	if (ret)
 		goto out;
 
-	/*
-	 * get references for dget and mntget, will be released
-	 * in error path of *_open().
-	 */
-	ret = spufs_gang_open(dget(dentry), mntget(mnt));
+	ret = spufs_gang_open(&path);
 	if (ret < 0) {
 		int err = simple_rmdir(inode, dentry);
 		WARN_ON(err);
diff --git a/arch/powerpc/platforms/powernv/opal-takeover.S b/arch/powerpc/platforms/powernv/opal-takeover.S
index 77b48b2b9309..3cd262897c27 100644
--- a/arch/powerpc/platforms/powernv/opal-takeover.S
+++ b/arch/powerpc/platforms/powernv/opal-takeover.S
@@ -14,8 +14,6 @@
 #include <asm/asm-offsets.h>
 #include <asm/opal.h>
 
-#define STK_PARAM(i)	(48 + ((i)-3)*8)
-
 #define H_HAL_TAKEOVER			0x5124
 #define H_HAL_TAKEOVER_QUERY_MAGIC	-1
 
@@ -23,14 +21,14 @@
 _GLOBAL(opal_query_takeover)
 	mfcr	r0
 	stw	r0,8(r1)
-	std	r3,STK_PARAM(r3)(r1)
-	std	r4,STK_PARAM(r4)(r1)
+	std	r3,STK_PARAM(R3)(r1)
+	std	r4,STK_PARAM(R4)(r1)
 	li	r3,H_HAL_TAKEOVER
 	li	r4,H_HAL_TAKEOVER_QUERY_MAGIC
 	HVSC
-	ld	r10,STK_PARAM(r3)(r1)
+	ld	r10,STK_PARAM(R3)(r1)
 	std	r4,0(r10)
-	ld	r10,STK_PARAM(r4)(r1)
+	ld	r10,STK_PARAM(R4)(r1)
 	std	r5,0(r10)
 	lwz	r0,8(r1)
 	mtcrf	0xff,r0
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index fbdd74dac3ac..9cda6a1ad0cf 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -589,7 +589,7 @@ static int __devinit pnv_ioda_configure_pe(struct pnv_phb *phb,
 		dcomp = OPAL_IGNORE_RID_DEVICE_NUMBER;
 		fcomp = OPAL_IGNORE_RID_FUNCTION_NUMBER;
 		parent = pe->pbus->self;
-		count = pe->pbus->subordinate - pe->pbus->secondary + 1;
+		count = pe->pbus->busn_res.end - pe->pbus->busn_res.start + 1;
 		switch(count) {
 		case  1: bcomp = OpalPciBusAll;		break;
 		case  2: bcomp = OpalPciBus7Bits;	break;
@@ -816,11 +816,11 @@ static void __devinit pnv_ioda_setup_bus_PE(struct pci_dev *dev,
 	pe->pdev = NULL;
 	pe->tce32_seg = -1;
 	pe->mve_number = -1;
-	pe->rid = bus->secondary << 8;
+	pe->rid = bus->busn_res.start << 8;
 	pe->dma_weight = 0;
 
-	pe_info(pe, "Secondary busses %d..%d associated with PE\n",
-		bus->secondary, bus->subordinate);
+	pe_info(pe, "Secondary busses %pR associated with PE\n",
+		&bus->busn_res);
 
 	if (pnv_ioda_configure_pe(phb, pe)) {
 		/* XXX What do we do here ? */
diff --git a/arch/powerpc/platforms/pseries/eeh_event.c b/arch/powerpc/platforms/pseries/eeh_event.c
index 4cb375c0f8d1..fb506317ebb0 100644
--- a/arch/powerpc/platforms/pseries/eeh_event.c
+++ b/arch/powerpc/platforms/pseries/eeh_event.c
@@ -85,8 +85,10 @@ static int eeh_event_handler(void * dummy)
 	set_current_state(TASK_INTERRUPTIBLE);	/* Don't add to load average */
 	edev = handle_eeh_events(event);
 
-	eeh_clear_slot(eeh_dev_to_of_node(edev), EEH_MODE_RECOVERING);
-	pci_dev_put(edev->pdev);
+	if (edev) {
+		eeh_clear_slot(eeh_dev_to_of_node(edev), EEH_MODE_RECOVERING);
+		pci_dev_put(edev->pdev);
+	}
 
 	kfree(event);
 	mutex_unlock(&eeh_event_mutex);
diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c
index 8752f79a6af8..c33360ec4f4f 100644
--- a/arch/powerpc/platforms/pseries/eeh_pseries.c
+++ b/arch/powerpc/platforms/pseries/eeh_pseries.c
@@ -81,7 +81,7 @@ static int pseries_eeh_init(void)
 	ibm_get_config_addr_info2	= rtas_token("ibm,get-config-addr-info2");
 	ibm_get_config_addr_info	= rtas_token("ibm,get-config-addr-info");
 	ibm_configure_pe		= rtas_token("ibm,configure-pe");
-	ibm_configure_bridge		= rtas_token ("ibm,configure-bridge");
+	ibm_configure_bridge		= rtas_token("ibm,configure-bridge");
 
 	/* necessary sanity check */
 	if (ibm_set_eeh_option == RTAS_UNKNOWN_SERVICE) {
@@ -89,7 +89,7 @@ static int pseries_eeh_init(void)
 			__func__);
 		return -EINVAL;
 	} else if (ibm_set_slot_reset == RTAS_UNKNOWN_SERVICE) {
-		pr_warning("%s: RTAS service <ibm, set-slot-reset> invalid\n",
+		pr_warning("%s: RTAS service <ibm,set-slot-reset> invalid\n",
 			__func__);
 		return -EINVAL;
 	} else if (ibm_read_slot_reset_state2 == RTAS_UNKNOWN_SERVICE &&
diff --git a/arch/powerpc/platforms/pseries/hvCall.S b/arch/powerpc/platforms/pseries/hvCall.S
index 3ce73d0052b1..444fe7759e55 100644
--- a/arch/powerpc/platforms/pseries/hvCall.S
+++ b/arch/powerpc/platforms/pseries/hvCall.S
@@ -13,8 +13,6 @@
 #include <asm/asm-offsets.h>
 #include <asm/ptrace.h>
 	
-#define STK_PARM(i)     (48 + ((i)-3)*8)
-
 #ifdef CONFIG_TRACEPOINTS
 
 	.section	".toc","aw"
@@ -26,7 +24,7 @@ hcall_tracepoint_refcount:
 	.section	".text"
 
 /*
- * precall must preserve all registers.  use unused STK_PARM()
+ * precall must preserve all registers.  use unused STK_PARAM()
  * areas to save snapshots and opcode. We branch around this
  * in early init (eg when populating the MMU hashtable) by using an
  * unconditional cpu feature.
@@ -40,28 +38,28 @@ END_FTR_SECTION(0, 1);						\
 	cmpdi	r12,0;						\
 	beq+	1f;						\
 	mflr	r0;						\
-	std	r3,STK_PARM(r3)(r1);				\
-	std	r4,STK_PARM(r4)(r1);				\
-	std	r5,STK_PARM(r5)(r1);				\
-	std	r6,STK_PARM(r6)(r1);				\
-	std	r7,STK_PARM(r7)(r1);				\
-	std	r8,STK_PARM(r8)(r1);				\
-	std	r9,STK_PARM(r9)(r1);				\
-	std	r10,STK_PARM(r10)(r1);				\
+	std	r3,STK_PARAM(R3)(r1);				\
+	std	r4,STK_PARAM(R4)(r1);				\
+	std	r5,STK_PARAM(R5)(r1);				\
+	std	r6,STK_PARAM(R6)(r1);				\
+	std	r7,STK_PARAM(R7)(r1);				\
+	std	r8,STK_PARAM(R8)(r1);				\
+	std	r9,STK_PARAM(R9)(r1);				\
+	std	r10,STK_PARAM(R10)(r1);				\
 	std	r0,16(r1);					\
-	addi	r4,r1,STK_PARM(FIRST_REG);			\
+	addi	r4,r1,STK_PARAM(FIRST_REG);			\
 	stdu	r1,-STACK_FRAME_OVERHEAD(r1);			\
 	bl	.__trace_hcall_entry;				\
 	addi	r1,r1,STACK_FRAME_OVERHEAD;			\
 	ld	r0,16(r1);					\
-	ld	r3,STK_PARM(r3)(r1);				\
-	ld	r4,STK_PARM(r4)(r1);				\
-	ld	r5,STK_PARM(r5)(r1);				\
-	ld	r6,STK_PARM(r6)(r1);				\
-	ld	r7,STK_PARM(r7)(r1);				\
-	ld	r8,STK_PARM(r8)(r1);				\
-	ld	r9,STK_PARM(r9)(r1);				\
-	ld	r10,STK_PARM(r10)(r1);				\
+	ld	r3,STK_PARAM(R3)(r1);				\
+	ld	r4,STK_PARAM(R4)(r1);				\
+	ld	r5,STK_PARAM(R5)(r1);				\
+	ld	r6,STK_PARAM(R6)(r1);				\
+	ld	r7,STK_PARAM(R7)(r1);				\
+	ld	r8,STK_PARAM(R8)(r1);				\
+	ld	r9,STK_PARAM(R9)(r1);				\
+	ld	r10,STK_PARAM(R10)(r1);				\
 	mtlr	r0;						\
 1:
 
@@ -79,8 +77,8 @@ END_FTR_SECTION(0, 1);						\
 	cmpdi	r12,0;						\
 	beq+	1f;						\
 	mflr	r0;						\
-	ld	r6,STK_PARM(r3)(r1);				\
-	std	r3,STK_PARM(r3)(r1);				\
+	ld	r6,STK_PARAM(R3)(r1);				\
+	std	r3,STK_PARAM(R3)(r1);				\
 	mr	r4,r3;						\
 	mr	r3,r6;						\
 	std	r0,16(r1);					\
@@ -88,7 +86,7 @@ END_FTR_SECTION(0, 1);						\
 	bl	.__trace_hcall_exit;				\
 	addi	r1,r1,STACK_FRAME_OVERHEAD;			\
 	ld	r0,16(r1);					\
-	ld	r3,STK_PARM(r3)(r1);				\
+	ld	r3,STK_PARAM(R3)(r1);				\
 	mtlr	r0;						\
 1:
 
@@ -114,7 +112,7 @@ _GLOBAL(plpar_hcall_norets)
 	mfcr	r0
 	stw	r0,8(r1)
 
-	HCALL_INST_PRECALL(r4)
+	HCALL_INST_PRECALL(R4)
 
 	HVSC				/* invoke the hypervisor */
 
@@ -130,9 +128,9 @@ _GLOBAL(plpar_hcall)
 	mfcr	r0
 	stw	r0,8(r1)
 
-	HCALL_INST_PRECALL(r5)
+	HCALL_INST_PRECALL(R5)
 
-	std     r4,STK_PARM(r4)(r1)     /* Save ret buffer */
+	std     r4,STK_PARAM(R4)(r1)     /* Save ret buffer */
 
 	mr	r4,r5
 	mr	r5,r6
@@ -143,7 +141,7 @@ _GLOBAL(plpar_hcall)
 
 	HVSC				/* invoke the hypervisor */
 
-	ld	r12,STK_PARM(r4)(r1)
+	ld	r12,STK_PARAM(R4)(r1)
 	std	r4,  0(r12)
 	std	r5,  8(r12)
 	std	r6, 16(r12)
@@ -168,7 +166,7 @@ _GLOBAL(plpar_hcall_raw)
 	mfcr	r0
 	stw	r0,8(r1)
 
-	std     r4,STK_PARM(r4)(r1)     /* Save ret buffer */
+	std     r4,STK_PARAM(R4)(r1)     /* Save ret buffer */
 
 	mr	r4,r5
 	mr	r5,r6
@@ -179,7 +177,7 @@ _GLOBAL(plpar_hcall_raw)
 
 	HVSC				/* invoke the hypervisor */
 
-	ld	r12,STK_PARM(r4)(r1)
+	ld	r12,STK_PARAM(R4)(r1)
 	std	r4,  0(r12)
 	std	r5,  8(r12)
 	std	r6, 16(r12)
@@ -196,9 +194,9 @@ _GLOBAL(plpar_hcall9)
 	mfcr	r0
 	stw	r0,8(r1)
 
-	HCALL_INST_PRECALL(r5)
+	HCALL_INST_PRECALL(R5)
 
-	std     r4,STK_PARM(r4)(r1)     /* Save ret buffer */
+	std     r4,STK_PARAM(R4)(r1)     /* Save ret buffer */
 
 	mr	r4,r5
 	mr	r5,r6
@@ -206,14 +204,14 @@ _GLOBAL(plpar_hcall9)
 	mr	r7,r8
 	mr	r8,r9
 	mr	r9,r10
-	ld	r10,STK_PARM(r11)(r1)	 /* put arg7 in R10 */
-	ld	r11,STK_PARM(r12)(r1)	 /* put arg8 in R11 */
-	ld	r12,STK_PARM(r13)(r1)    /* put arg9 in R12 */
+	ld	r10,STK_PARAM(R11)(r1)	 /* put arg7 in R10 */
+	ld	r11,STK_PARAM(R12)(r1)	 /* put arg8 in R11 */
+	ld	r12,STK_PARAM(R13)(r1)    /* put arg9 in R12 */
 
 	HVSC				/* invoke the hypervisor */
 
 	mr	r0,r12
-	ld	r12,STK_PARM(r4)(r1)
+	ld	r12,STK_PARAM(R4)(r1)
 	std	r4,  0(r12)
 	std	r5,  8(r12)
 	std	r6, 16(r12)
@@ -238,7 +236,7 @@ _GLOBAL(plpar_hcall9_raw)
 	mfcr	r0
 	stw	r0,8(r1)
 
-	std     r4,STK_PARM(r4)(r1)     /* Save ret buffer */
+	std     r4,STK_PARAM(R4)(r1)     /* Save ret buffer */
 
 	mr	r4,r5
 	mr	r5,r6
@@ -246,14 +244,14 @@ _GLOBAL(plpar_hcall9_raw)
 	mr	r7,r8
 	mr	r8,r9
 	mr	r9,r10
-	ld	r10,STK_PARM(r11)(r1)	 /* put arg7 in R10 */
-	ld	r11,STK_PARM(r12)(r1)	 /* put arg8 in R11 */
-	ld	r12,STK_PARM(r13)(r1)    /* put arg9 in R12 */
+	ld	r10,STK_PARAM(R11)(r1)	 /* put arg7 in R10 */
+	ld	r11,STK_PARAM(R12)(r1)	 /* put arg8 in R11 */
+	ld	r12,STK_PARAM(R13)(r1)    /* put arg9 in R12 */
 
 	HVSC				/* invoke the hypervisor */
 
 	mr	r0,r12
-	ld	r12,STK_PARM(r4)(r1)
+	ld	r12,STK_PARAM(R4)(r1)
 	std	r4,  0(r12)
 	std	r5,  8(r12)
 	std	r6, 16(r12)
diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index 6b58a395dff6..bca220f2873c 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -192,12 +192,15 @@ static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum,
 	long l, limit;
 	long tcenum_start = tcenum, npages_start = npages;
 	int ret = 0;
+	unsigned long flags;
 
 	if (npages == 1) {
 		return tce_build_pSeriesLP(tbl, tcenum, npages, uaddr,
 		                           direction, attrs);
 	}
 
+	local_irq_save(flags);	/* to protect tcep and the page behind it */
+
 	tcep = __get_cpu_var(tce_page);
 
 	/* This is safe to do since interrupts are off when we're called
@@ -207,6 +210,7 @@ static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum,
 		tcep = (u64 *)__get_free_page(GFP_ATOMIC);
 		/* If allocation fails, fall back to the loop implementation */
 		if (!tcep) {
+			local_irq_restore(flags);
 			return tce_build_pSeriesLP(tbl, tcenum, npages, uaddr,
 					    direction, attrs);
 		}
@@ -240,6 +244,8 @@ static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum,
 		tcenum += limit;
 	} while (npages > 0 && !rc);
 
+	local_irq_restore(flags);
+
 	if (unlikely(rc == H_NOT_ENOUGH_RESOURCES)) {
 		ret = (int)rc;
 		tce_freemulti_pSeriesLP(tbl, tcenum_start,
@@ -707,6 +713,21 @@ static int __init disable_ddw_setup(char *str)
 
 early_param("disable_ddw", disable_ddw_setup);
 
+static inline void __remove_ddw(struct device_node *np, const u32 *ddw_avail, u64 liobn)
+{
+	int ret;
+
+	ret = rtas_call(ddw_avail[2], 1, 1, NULL, liobn);
+	if (ret)
+		pr_warning("%s: failed to remove DMA window: rtas returned "
+			"%d to ibm,remove-pe-dma-window(%x) %llx\n",
+			np->full_name, ret, ddw_avail[2], liobn);
+	else
+		pr_debug("%s: successfully removed DMA window: rtas returned "
+			"%d to ibm,remove-pe-dma-window(%x) %llx\n",
+			np->full_name, ret, ddw_avail[2], liobn);
+}
+
 static void remove_ddw(struct device_node *np)
 {
 	struct dynamic_dma_window_prop *dwp;
@@ -736,15 +757,7 @@ static void remove_ddw(struct device_node *np)
 		pr_debug("%s successfully cleared tces in window.\n",
 			 np->full_name);
 
-	ret = rtas_call(ddw_avail[2], 1, 1, NULL, liobn);
-	if (ret)
-		pr_warning("%s: failed to remove direct window: rtas returned "
-			"%d to ibm,remove-pe-dma-window(%x) %llx\n",
-			np->full_name, ret, ddw_avail[2], liobn);
-	else
-		pr_debug("%s: successfully removed direct window: rtas returned "
-			"%d to ibm,remove-pe-dma-window(%x) %llx\n",
-			np->full_name, ret, ddw_avail[2], liobn);
+	__remove_ddw(np, ddw_avail, liobn);
 
 delprop:
 	ret = prom_remove_property(np, win64);
@@ -869,6 +882,35 @@ static int create_ddw(struct pci_dev *dev, const u32 *ddw_avail,
 	return ret;
 }
 
+static void restore_default_window(struct pci_dev *dev,
+				u32 ddw_restore_token, unsigned long liobn)
+{
+	struct eeh_dev *edev;
+	u32 cfg_addr;
+	u64 buid;
+	int ret;
+
+	/*
+	 * Get the config address and phb buid of the PE window.
+	 * Rely on eeh to retrieve this for us.
+	 * Retrieve them from the pci device, not the node with the
+	 * dma-window property
+	 */
+	edev = pci_dev_to_eeh_dev(dev);
+	cfg_addr = edev->config_addr;
+	if (edev->pe_config_addr)
+		cfg_addr = edev->pe_config_addr;
+	buid = edev->phb->buid;
+
+	do {
+		ret = rtas_call(ddw_restore_token, 3, 1, NULL, cfg_addr,
+					BUID_HI(buid), BUID_LO(buid));
+	} while (rtas_busy_delay(ret));
+	dev_info(&dev->dev,
+		"ibm,reset-pe-dma-windows(%x) %x %x %x returned %d\n",
+		 ddw_restore_token, cfg_addr, BUID_HI(buid), BUID_LO(buid), ret);
+}
+
 /*
  * If the PE supports dynamic dma windows, and there is space for a table
  * that can map all pages in a linear offset, then setup such a table,
@@ -889,9 +931,13 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 	u64 dma_addr, max_addr;
 	struct device_node *dn;
 	const u32 *uninitialized_var(ddw_avail);
+	const u32 *uninitialized_var(ddw_extensions);
+	u32 ddw_restore_token = 0;
 	struct direct_window *window;
 	struct property *win64;
 	struct dynamic_dma_window_prop *ddwprop;
+	const void *dma_window = NULL;
+	unsigned long liobn, offset, size;
 
 	mutex_lock(&direct_window_init_mutex);
 
@@ -911,7 +957,40 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 	if (!ddw_avail || len < 3 * sizeof(u32))
 		goto out_unlock;
 
-       /*
+	/*
+	 * the extensions property is only required to exist in certain
+	 * levels of firmware and later
+	 * the ibm,ddw-extensions property is a list with the first
+	 * element containing the number of extensions and each
+	 * subsequent entry is a value corresponding to that extension
+	 */
+	ddw_extensions = of_get_property(pdn, "ibm,ddw-extensions", &len);
+	if (ddw_extensions) {
+		/*
+		 * each new defined extension length should be added to
+		 * the top of the switch so the "earlier" entries also
+		 * get picked up
+		 */
+		switch (ddw_extensions[0]) {
+			/* ibm,reset-pe-dma-windows */
+			case 1:
+				ddw_restore_token = ddw_extensions[1];
+				break;
+		}
+	}
+
+	/*
+	 * Only remove the existing DMA window if we can restore back to
+	 * the default state. Removing the existing window maximizes the
+	 * resources available to firmware for dynamic window creation.
+	 */
+	if (ddw_restore_token) {
+		dma_window = of_get_property(pdn, "ibm,dma-window", NULL);
+		of_parse_dma_window(pdn, dma_window, &liobn, &offset, &size);
+		__remove_ddw(pdn, ddw_avail, liobn);
+	}
+
+	/*
 	 * Query if there is a second window of size to map the
 	 * whole partition.  Query returns number of windows, largest
 	 * block assigned to PE (partition endpoint), and two bitmasks
@@ -920,7 +999,7 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 	dn = pci_device_to_OF_node(dev);
 	ret = query_ddw(dev, ddw_avail, &query);
 	if (ret != 0)
-		goto out_unlock;
+		goto out_restore_window;
 
 	if (query.windows_available == 0) {
 		/*
@@ -929,7 +1008,7 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 		 * trading in for a larger page size.
 		 */
 		dev_dbg(&dev->dev, "no free dynamic windows");
-		goto out_unlock;
+		goto out_restore_window;
 	}
 	if (query.page_size & 4) {
 		page_shift = 24; /* 16MB */
@@ -940,7 +1019,7 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 	} else {
 		dev_dbg(&dev->dev, "no supported direct page size in mask %x",
 			  query.page_size);
-		goto out_unlock;
+		goto out_restore_window;
 	}
 	/* verify the window * number of ptes will map the partition */
 	/* check largest block * page size > max memory hotplug addr */
@@ -949,14 +1028,14 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn)
 		dev_dbg(&dev->dev, "can't map partiton max 0x%llx with %u "
 			  "%llu-sized pages\n", max_addr,  query.largest_available_block,
 			  1ULL << page_shift);
-		goto out_unlock;
+		goto out_restore_window;
 	}
 	len = order_base_2(max_addr);
 	win64 = kzalloc(sizeof(struct property), GFP_KERNEL);
 	if (!win64) {
 		dev_info(&dev->dev,
 			"couldn't allocate property for 64bit dma window\n");
-		goto out_unlock;
+		goto out_restore_window;
 	}
 	win64->name = kstrdup(DIRECT64_PROPNAME, GFP_KERNEL);
 	win64->value = ddwprop = kmalloc(sizeof(*ddwprop), GFP_KERNEL);
@@ -1018,6 +1097,10 @@ out_free_prop:
 	kfree(win64->value);
 	kfree(win64);
 
+out_restore_window:
+	if (ddw_restore_token)
+		restore_default_window(dev, ddw_restore_token, liobn);
+
 out_unlock:
 	mutex_unlock(&direct_window_init_mutex);
 	return dma_addr;
diff --git a/arch/powerpc/platforms/pseries/mobility.c b/arch/powerpc/platforms/pseries/mobility.c
index 029a562af373..dd30b12edfe4 100644
--- a/arch/powerpc/platforms/pseries/mobility.c
+++ b/arch/powerpc/platforms/pseries/mobility.c
@@ -67,7 +67,6 @@ static int update_dt_property(struct device_node *dn, struct property **prop,
 			      const char *name, u32 vd, char *value)
 {
 	struct property *new_prop = *prop;
-	struct property *old_prop;
 	int more = 0;
 
 	/* A negative 'vd' value indicates that only part of the new property
@@ -117,12 +116,7 @@ static int update_dt_property(struct device_node *dn, struct property **prop,
 	}
 
 	if (!more) {
-		old_prop = of_find_property(dn, new_prop->name, NULL);
-		if (old_prop)
-			prom_update_property(dn, new_prop, old_prop);
-		else
-			prom_add_property(dn, new_prop);
-
+		prom_update_property(dn, new_prop);
 		new_prop = NULL;
 	}
 
diff --git a/arch/powerpc/platforms/pseries/pci_dlpar.c b/arch/powerpc/platforms/pseries/pci_dlpar.c
index 8b7bafa489c2..3ccebc83dc02 100644
--- a/arch/powerpc/platforms/pseries/pci_dlpar.c
+++ b/arch/powerpc/platforms/pseries/pci_dlpar.c
@@ -121,7 +121,7 @@ void pcibios_add_pci_devices(struct pci_bus * bus)
 		if (!num)
 			return;
 		pcibios_setup_bus_devices(bus);
-		max = bus->secondary;
+		max = bus->busn_res.start;
 		for (pass=0; pass < 2; pass++)
 			list_for_each_entry(dev, &bus->devices, bus_list) {
 			if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE ||
diff --git a/arch/powerpc/platforms/pseries/processor_idle.c b/arch/powerpc/platforms/pseries/processor_idle.c
index e61483e8e960..455760b1fe6e 100644
--- a/arch/powerpc/platforms/pseries/processor_idle.c
+++ b/arch/powerpc/platforms/pseries/processor_idle.c
@@ -11,6 +11,7 @@
 #include <linux/moduleparam.h>
 #include <linux/cpuidle.h>
 #include <linux/cpu.h>
+#include <linux/notifier.h>
 
 #include <asm/paca.h>
 #include <asm/reg.h>
@@ -99,15 +100,18 @@ out:
 static void check_and_cede_processor(void)
 {
 	/*
-	 * Interrupts are soft-disabled at this point,
-	 * but not hard disabled. So an interrupt might have
-	 * occurred before entering NAP, and would be potentially
-	 * lost (edge events, decrementer events, etc...) unless
-	 * we first hard disable then check.
+	 * Ensure our interrupt state is properly tracked,
+	 * also checks if no interrupt has occurred while we
+	 * were soft-disabled
 	 */
-	hard_irq_disable();
-	if (!lazy_irq_pending())
+	if (prep_irq_for_idle()) {
 		cede_processor();
+#ifdef CONFIG_TRACE_IRQFLAGS
+		/* Ensure that H_CEDE returns with IRQs on */
+		if (WARN_ON(!(mfmsr() & MSR_EE)))
+			__hard_irq_enable();
+#endif
+	}
 }
 
 static int dedicated_cede_loop(struct cpuidle_device *dev,
@@ -186,17 +190,40 @@ static struct cpuidle_state shared_states[MAX_IDLE_STATE_COUNT] = {
 		.enter = &shared_cede_loop },
 };
 
-int pseries_notify_cpuidle_add_cpu(int cpu)
+static int pseries_cpuidle_add_cpu_notifier(struct notifier_block *n,
+			unsigned long action, void *hcpu)
 {
+	int hotcpu = (unsigned long)hcpu;
 	struct cpuidle_device *dev =
-			per_cpu_ptr(pseries_cpuidle_devices, cpu);
+			per_cpu_ptr(pseries_cpuidle_devices, hotcpu);
+
 	if (dev && cpuidle_get_driver()) {
-		cpuidle_disable_device(dev);
-		cpuidle_enable_device(dev);
+		switch (action) {
+		case CPU_ONLINE:
+		case CPU_ONLINE_FROZEN:
+			cpuidle_pause_and_lock();
+			cpuidle_enable_device(dev);
+			cpuidle_resume_and_unlock();
+			break;
+
+		case CPU_DEAD:
+		case CPU_DEAD_FROZEN:
+			cpuidle_pause_and_lock();
+			cpuidle_disable_device(dev);
+			cpuidle_resume_and_unlock();
+			break;
+
+		default:
+			return NOTIFY_DONE;
+		}
 	}
-	return 0;
+	return NOTIFY_OK;
 }
 
+static struct notifier_block setup_hotplug_notifier = {
+	.notifier_call = pseries_cpuidle_add_cpu_notifier,
+};
+
 /*
  * pseries_cpuidle_driver_init()
  */
@@ -321,6 +348,7 @@ static int __init pseries_processor_idle_init(void)
 		return retval;
 	}
 
+	register_cpu_notifier(&setup_hotplug_notifier);
 	printk(KERN_DEBUG "pseries_idle_driver registered\n");
 
 	return 0;
@@ -329,6 +357,7 @@ static int __init pseries_processor_idle_init(void)
 static void __exit pseries_processor_idle_exit(void)
 {
 
+	unregister_cpu_notifier(&setup_hotplug_notifier);
 	pseries_idle_devices_uninit();
 	cpuidle_unregister_driver(&pseries_idle_driver);
 
diff --git a/arch/powerpc/platforms/pseries/reconfig.c b/arch/powerpc/platforms/pseries/reconfig.c
index 7b3bf76ef834..39f71fba9b38 100644
--- a/arch/powerpc/platforms/pseries/reconfig.c
+++ b/arch/powerpc/platforms/pseries/reconfig.c
@@ -432,7 +432,7 @@ static int do_update_property(char *buf, size_t bufsize)
 	unsigned char *value;
 	char *name, *end, *next_prop;
 	int rc, length;
-	struct property *newprop, *oldprop;
+	struct property *newprop;
 	buf = parse_node(buf, bufsize, &np);
 	end = buf + bufsize;
 
@@ -443,6 +443,9 @@ static int do_update_property(char *buf, size_t bufsize)
 	if (!next_prop)
 		return -EINVAL;
 
+	if (!strlen(name))
+		return -ENODEV;
+
 	newprop = new_property(name, length, value, NULL);
 	if (!newprop)
 		return -ENOMEM;
@@ -450,18 +453,11 @@ static int do_update_property(char *buf, size_t bufsize)
 	if (!strcmp(name, "slb-size") || !strcmp(name, "ibm,slb-size"))
 		slb_set_size(*(int *)value);
 
-	oldprop = of_find_property(np, name,NULL);
-	if (!oldprop) {
-		if (strlen(name))
-			return prom_add_property(np, newprop);
-		return -ENODEV;
-	}
-
 	upd_value.node = np;
 	upd_value.property = newprop;
 	pSeries_reconfig_notify(PSERIES_UPDATE_PROPERTY, &upd_value);
 
-	rc = prom_update_property(np, newprop, oldprop);
+	rc = prom_update_property(np, newprop);
 	if (rc)
 		return rc;
 
@@ -486,7 +482,7 @@ static int do_update_property(char *buf, size_t bufsize)
 
 		rc = pSeries_reconfig_notify(action, value);
 		if (rc) {
-			prom_update_property(np, oldprop, newprop);
+			prom_update_property(np, newprop);
 			return rc;
 		}
 	}
diff --git a/arch/powerpc/platforms/pseries/smp.c b/arch/powerpc/platforms/pseries/smp.c
index e16bb8d48550..71706bc34a0d 100644
--- a/arch/powerpc/platforms/pseries/smp.c
+++ b/arch/powerpc/platforms/pseries/smp.c
@@ -147,7 +147,6 @@ static void __devinit smp_xics_setup_cpu(int cpu)
 	set_cpu_current_state(cpu, CPU_STATE_ONLINE);
 	set_default_offline_state(cpu);
 #endif
-	pseries_notify_cpuidle_add_cpu(cpu);
 }
 
 static int __devinit smp_pSeries_kick_cpu(int nr)
diff --git a/arch/powerpc/sysdev/6xx-suspend.S b/arch/powerpc/sysdev/6xx-suspend.S
index 21cda085d926..cf48e9cb2575 100644
--- a/arch/powerpc/sysdev/6xx-suspend.S
+++ b/arch/powerpc/sysdev/6xx-suspend.S
@@ -29,7 +29,7 @@ _GLOBAL(mpc6xx_enter_standby)
 	ori	r5, r5, ret_from_standby@l
 	mtlr	r5
 
-	rlwinm	r5, r1, 0, 0, 31-THREAD_SHIFT
+	CURRENT_THREAD_INFO(r5, r1)
 	lwz	r6, TI_LOCAL_FLAGS(r5)
 	ori	r6, r6, _TLF_SLEEPING
 	stw	r6, TI_LOCAL_FLAGS(r5)
diff --git a/arch/powerpc/sysdev/fsl_pci.c b/arch/powerpc/sysdev/fsl_pci.c
index 6073288fed29..a7b2a600d0a4 100644
--- a/arch/powerpc/sysdev/fsl_pci.c
+++ b/arch/powerpc/sysdev/fsl_pci.c
@@ -1,7 +1,7 @@
 /*
  * MPC83xx/85xx/86xx PCI/PCIE support routing.
  *
- * Copyright 2007-2011 Freescale Semiconductor, Inc.
+ * Copyright 2007-2012 Freescale Semiconductor, Inc.
  * Copyright 2008-2009 MontaVista Software, Inc.
  *
  * Initial author: Xianghua Xiao <x.xiao@freescale.com>
@@ -36,7 +36,7 @@
 
 static int fsl_pcie_bus_fixup, is_mpc83xx_pci;
 
-static void __init quirk_fsl_pcie_header(struct pci_dev *dev)
+static void __devinit quirk_fsl_pcie_header(struct pci_dev *dev)
 {
 	u8 progif;
 
@@ -807,3 +807,72 @@ u64 fsl_pci_immrbar_base(struct pci_controller *hose)
 
 	return 0;
 }
+
+#if defined(CONFIG_FSL_SOC_BOOKE) || defined(CONFIG_PPC_86xx)
+static const struct of_device_id pci_ids[] = {
+	{ .compatible = "fsl,mpc8540-pci", },
+	{ .compatible = "fsl,mpc8548-pcie", },
+	{ .compatible = "fsl,mpc8610-pci", },
+	{ .compatible = "fsl,mpc8641-pcie", },
+	{ .compatible = "fsl,p1022-pcie", },
+	{ .compatible = "fsl,p1010-pcie", },
+	{ .compatible = "fsl,p1023-pcie", },
+	{ .compatible = "fsl,p4080-pcie", },
+	{ .compatible = "fsl,qoriq-pcie-v2.3", },
+	{ .compatible = "fsl,qoriq-pcie-v2.2", },
+	{},
+};
+
+struct device_node *fsl_pci_primary;
+
+void __devinit fsl_pci_init(void)
+{
+	struct device_node *node;
+	struct pci_controller *hose;
+	dma_addr_t max = 0xffffffff;
+
+	/* Callers can specify the primary bus using other means. */
+	if (!fsl_pci_primary) {
+		/* If a PCI host bridge contains an ISA node, it's primary. */
+		node = of_find_node_by_type(NULL, "isa");
+		while ((fsl_pci_primary = of_get_parent(node))) {
+			of_node_put(node);
+			node = fsl_pci_primary;
+
+			if (of_match_node(pci_ids, node))
+				break;
+		}
+	}
+
+	node = NULL;
+	for_each_node_by_type(node, "pci") {
+		if (of_match_node(pci_ids, node)) {
+			/*
+			 * If there's no PCI host bridge with ISA, arbitrarily
+			 * designate one as primary.  This can go away once
+			 * various bugs with primary-less systems are fixed.
+			 */
+			if (!fsl_pci_primary)
+				fsl_pci_primary = node;
+
+			fsl_add_bridge(node, fsl_pci_primary == node);
+			hose = pci_find_hose_for_OF_device(node);
+			max = min(max, hose->dma_window_base_cur +
+					hose->dma_window_size);
+		}
+	}
+
+#ifdef CONFIG_SWIOTLB
+	/*
+	 * if we couldn't map all of DRAM via the dma windows
+	 * we need SWIOTLB to handle buffers located outside of
+	 * dma capable memory region
+	 */
+	if (memblock_end_of_DRAM() - 1 > max) {
+		ppc_swiotlb_enable = 1;
+		set_pci_dma_ops(&swiotlb_dma_ops);
+		ppc_md.pci_dma_dev_setup = pci_dma_dev_setup_swiotlb;
+	}
+#endif
+}
+#endif
diff --git a/arch/powerpc/sysdev/fsl_pci.h b/arch/powerpc/sysdev/fsl_pci.h
index a39ed5cc2c5a..baa0fd18289f 100644
--- a/arch/powerpc/sysdev/fsl_pci.h
+++ b/arch/powerpc/sysdev/fsl_pci.h
@@ -93,5 +93,13 @@ extern void fsl_pcibios_fixup_bus(struct pci_bus *bus);
 extern int mpc83xx_add_bridge(struct device_node *dev);
 u64 fsl_pci_immrbar_base(struct pci_controller *hose);
 
+extern struct device_node *fsl_pci_primary;
+
+#ifdef CONFIG_FSL_PCI
+void fsl_pci_init(void);
+#else
+static inline void fsl_pci_init(void) {}
+#endif
+
 #endif /* __POWERPC_FSL_PCI_H */
 #endif /* __KERNEL__ */
diff --git a/arch/powerpc/sysdev/mpic.c b/arch/powerpc/sysdev/mpic.c
index 395af1347749..bfc6211e5422 100644
--- a/arch/powerpc/sysdev/mpic.c
+++ b/arch/powerpc/sysdev/mpic.c
@@ -1211,7 +1211,7 @@ struct mpic * __init mpic_alloc(struct device_node *node,
 	if (of_get_property(node, "single-cpu-affinity", NULL))
 		flags |= MPIC_SINGLE_DEST_CPU;
 	if (of_device_is_compatible(node, "fsl,mpic"))
-		flags |= MPIC_FSL;
+		flags |= MPIC_FSL | MPIC_LARGE_VECTORS;
 
 	mpic = kzalloc(sizeof(struct mpic), GFP_KERNEL);
 	if (mpic == NULL)
@@ -1376,7 +1376,7 @@ struct mpic * __init mpic_alloc(struct device_node *node,
 	mpic->isu_mask = (1 << mpic->isu_shift) - 1;
 
 	mpic->irqhost = irq_domain_add_linear(mpic->node,
-				       last_irq + 1,
+				       intvec_top,
 				       &mpic_host_ops, mpic);
 
 	/*
diff --git a/arch/powerpc/sysdev/mv64x60_pci.c b/arch/powerpc/sysdev/mv64x60_pci.c
index b0037cefaada..364b14d4754b 100644
--- a/arch/powerpc/sysdev/mv64x60_pci.c
+++ b/arch/powerpc/sysdev/mv64x60_pci.c
@@ -104,7 +104,7 @@ subsys_initcall(mv64x60_sysfs_init);
 
 #endif /* CONFIG_SYSFS */
 
-static void __init mv64x60_pci_fixup_early(struct pci_dev *dev)
+static void __devinit mv64x60_pci_fixup_early(struct pci_dev *dev)
 {
 	/*
 	 * Set the host bridge hdr_type to an invalid value so that
diff --git a/arch/powerpc/sysdev/qe_lib/qe.c b/arch/powerpc/sysdev/qe_lib/qe.c
index 818e763f8265..b04367529729 100644
--- a/arch/powerpc/sysdev/qe_lib/qe.c
+++ b/arch/powerpc/sysdev/qe_lib/qe.c
@@ -395,6 +395,9 @@ static void qe_upload_microcode(const void *base,
 
 	for (i = 0; i < be32_to_cpu(ucode->count); i++)
 		out_be32(&qe_immr->iram.idata, be32_to_cpu(code[i]));
+	
+	/* Set I-RAM Ready Register */
+	out_be32(&qe_immr->iram.iready, be32_to_cpu(QE_IRAM_READY));
 }
 
 /*