Merge branch 'master' into for-next

Sync with Linus tree to have 157550ff ("mtd: add GPMI-NAND driver
in the config and Makefile") as I have patch depending on that one.

385 files changed, 10114 insertions, 2215 deletions

diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 6926b61acfea..b177caa56d95 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -323,7 +323,7 @@ config SWIOTLB
 
 config HOTPLUG_CPU
         bool "Support for enabling/disabling CPUs"
-        depends on SMP && HOTPLUG && EXPERIMENTAL && (PPC_PSERIES || PPC_PMAC)
+        depends on SMP && HOTPLUG && EXPERIMENTAL && (PPC_PSERIES || PPC_PMAC || PPC_POWERNV)
         ---help---
           Say Y here to be able to disable and re-enable individual
           CPUs at runtime on SMP machines.
@@ -345,7 +345,7 @@ config ARCH_ENABLE_MEMORY_HOTREMOVE
 
 config KEXEC
         bool "kexec system call (EXPERIMENTAL)"
-        depends on (PPC_BOOK3S || FSL_BOOKE) && EXPERIMENTAL
+        depends on (PPC_BOOK3S || FSL_BOOKE || (44x && !SMP && !47x)) && EXPERIMENTAL
         help
           kexec is a system call that implements the ability to shutdown your
           current kernel, and to start another kernel.  It is like a reboot
@@ -379,10 +379,6 @@ config PHYP_DUMP
 
           If unsure, say "N"
 
-config PPCBUG_NVRAM
-        bool "Enable reading PPCBUG NVRAM during boot" if PPLUS || LOPEC
-        default y if PPC_PREP
-
 config IRQ_ALL_CPUS
         bool "Distribute interrupts on all CPUs by default"
         depends on SMP && !MV64360
@@ -429,8 +425,7 @@ config ARCH_POPULATES_NODE_MAP
         def_bool y
 
 config SYS_SUPPORTS_HUGETLBFS
-       def_bool y
-       depends on PPC_BOOK3S_64
+        bool
 
 source "mm/Kconfig"
 
@@ -656,6 +651,8 @@ config SBUS
 
 config FSL_SOC
         bool
+        select HAVE_CAN_FLEXCAN if NET && CAN
+        select PPC_CLOCK if CAN_FLEXCAN
 
 config FSL_PCI
         bool
@@ -744,24 +741,6 @@ config 8260_PCI9
         depends on PCI_8260 && !8272
         default y
 
-choice
-        prompt "IDMA channel for PCI 9 workaround"
-        depends on 8260_PCI9
-
-config 8260_PCI9_IDMA1
-        bool "IDMA1"
-
-config 8260_PCI9_IDMA2
-        bool "IDMA2"
-
-config 8260_PCI9_IDMA3
-        bool "IDMA3"
-
-config 8260_PCI9_IDMA4
-        bool "IDMA4"
-
-endchoice
-
 source "drivers/pci/pcie/Kconfig"
 
 source "drivers/pci/Kconfig"
diff --git a/arch/powerpc/Kconfig.debug b/arch/powerpc/Kconfig.debug
index 067cb8480747..1b8a9c905cf7 100644
--- a/arch/powerpc/Kconfig.debug
+++ b/arch/powerpc/Kconfig.debug
@@ -141,9 +141,6 @@ config BOOTX_TEXT
 
 config PPC_EARLY_DEBUG
         bool "Early debugging (dangerous)"
-        # PPC_EARLY_DEBUG on 440 leaves AS=1 mappings above the TLB high water
-        # mark, which doesn't work with current 440 KVM.
-        depends on !KVM
         help
           Say Y to enable some early debugging facilities that may be available
           for your processor/board combination. Those facilities are hacks
@@ -222,7 +219,9 @@ config PPC_EARLY_DEBUG_BEAT
 
 config PPC_EARLY_DEBUG_44x
         bool "Early serial debugging for IBM/AMCC 44x CPUs"
-        depends on 44x
+        # PPC_EARLY_DEBUG on 440 leaves AS=1 mappings above the TLB high water
+        # mark, which doesn't work with current 440 KVM.
+        depends on 44x && !KVM
         help
           Select this to enable early debugging for IBM 44x chips via the
           inbuilt serial port.  If you enable this, ensure you set
@@ -258,8 +257,35 @@ config PPC_EARLY_DEBUG_WSP
         depends on PPC_WSP
         select PPC_UDBG_16550
 
+config PPC_EARLY_DEBUG_PS3GELIC
+        bool "Early debugging through the PS3 Ethernet port"
+        depends on PPC_PS3
+        select PS3GELIC_UDBG
+        help
+          Select this to enable early debugging for the PlayStation3 via
+          UDP broadcasts sent out through the Ethernet port.
+
+config PPC_EARLY_DEBUG_OPAL_RAW
+        bool "OPAL raw console"
+        depends on HVC_OPAL
+        help
+          Select this to enable early debugging for the PowerNV platform
+          using a "raw" console
+
+config PPC_EARLY_DEBUG_OPAL_HVSI
+        bool "OPAL hvsi console"
+        depends on HVC_OPAL
+        help
+          Select this to enable early debugging for the PowerNV platform
+          using an "hvsi" console
+
 endchoice
 
+config PPC_EARLY_DEBUG_OPAL
+        def_bool y
+        depends on PPC_EARLY_DEBUG_OPAL_RAW || PPC_EARLY_DEBUG_OPAL_HVSI
+
+
 config PPC_EARLY_DEBUG_HVSI_VTERMNO
         hex "vterm number to use with early debug HVSI"
         depends on PPC_EARLY_DEBUG_LPAR_HVSI
@@ -268,6 +294,18 @@ config PPC_EARLY_DEBUG_HVSI_VTERMNO
           You probably want 0x30000000 for your first serial port and
           0x30000001 for your second one
 
+config PPC_EARLY_DEBUG_OPAL_VTERMNO
+        hex "vterm number to use with OPAL early debug"
+        depends on PPC_EARLY_DEBUG_OPAL
+        default "0"
+        help
+          This correspond to which /dev/hvcN you want to use for early
+          debug.
+
+          On OPAL v1 (takeover) this should always be 0
+          On OPAL v2, this will be 0 for network console and 1 or 2 for
+          the machine built-in serial ports.
+
 config PPC_EARLY_DEBUG_44x_PHYSLOW
         hex "Low 32 bits of early debug UART physical address"
         depends on PPC_EARLY_DEBUG_44x
diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile
index c26200b40a47..72ee8c1fba48 100644
--- a/arch/powerpc/boot/Makefile
+++ b/arch/powerpc/boot/Makefile
@@ -58,7 +58,7 @@ $(addprefix $(obj)/,$(zlib) cuboot-c2k.o gunzip_util.o main.o prpmc2800.o): \
 libfdt       := fdt.c fdt_ro.c fdt_wip.c fdt_sw.c fdt_rw.c fdt_strerror.c
 libfdtheader := fdt.h libfdt.h libfdt_internal.h
 
-$(addprefix $(obj)/,$(libfdt) libfdt-wrapper.o simpleboot.o): \
+$(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 \
@@ -171,6 +171,7 @@ quiet_cmd_wrap	= WRAP    $@
                 $(if $3, -s $3)$(if $4, -d $4)$(if $5, -i $5) vmlinux
 
 image-$(CONFIG_PPC_PSERIES)             += zImage.pseries
+image-$(CONFIG_PPC_POWERNV)             += zImage.pseries
 image-$(CONFIG_PPC_MAPLE)               += zImage.maple
 image-$(CONFIG_PPC_IBM_CELL_BLADE)      += zImage.pseries
 image-$(CONFIG_PPC_PS3)                 += dtbImage.ps3
diff --git a/arch/powerpc/boot/dts/charon.dts b/arch/powerpc/boot/dts/charon.dts
new file mode 100644
index 000000000000..0e00e508eaa6
--- /dev/null
+++ b/arch/powerpc/boot/dts/charon.dts
@@ -0,0 +1,236 @@
+/*
+ * charon board Device Tree Source
+ *
+ * Copyright (C) 2007 Semihalf
+ * Marian Balakowicz <m8@semihalf.com>
+ *
+ * Copyright (C) 2010 DENX Software Engineering GmbH
+ * Heiko Schocher <hs@denx.de>
+ *
+ * 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 = "anon,charon";
+        compatible = "anon,charon";
+        #address-cells = <1>;
+        #size-cells = <1>;
+        interrupt-parent = <&mpc5200_pic>;
+
+        cpus {
+                #address-cells = <1>;
+                #size-cells = <0>;
+
+                PowerPC,5200@0 {
+                        device_type = "cpu";
+                        reg = <0>;
+                        d-cache-line-size = <32>;
+                        i-cache-line-size = <32>;
+                        d-cache-size = <0x4000>;        // L1, 16K
+                        i-cache-size = <0x4000>;        // L1, 16K
+                        timebase-frequency = <0>;       // from bootloader
+                        bus-frequency = <0>;            // from bootloader
+                        clock-frequency = <0>;          // from bootloader
+                };
+        };
+
+        memory {
+                device_type = "memory";
+                reg = <0x00000000 0x08000000>;  // 128MB
+        };
+
+        soc5200@f0000000 {
+                #address-cells = <1>;
+                #size-cells = <1>;
+                compatible = "fsl,mpc5200-immr";
+                ranges = <0 0xf0000000 0x0000c000>;
+                reg = <0xf0000000 0x00000100>;
+                bus-frequency = <0>;            // from bootloader
+                system-frequency = <0>;         // from bootloader
+
+                cdm@200 {
+                        compatible = "fsl,mpc5200-cdm";
+                        reg = <0x200 0x38>;
+                };
+
+                mpc5200_pic: interrupt-controller@500 {
+                        // 5200 interrupts are encoded into two levels;
+                        interrupt-controller;
+                        #interrupt-cells = <3>;
+                        compatible = "fsl,mpc5200-pic";
+                        reg = <0x500 0x80>;
+                };
+
+                timer@600 {     // General Purpose Timer
+                        compatible = "fsl,mpc5200-gpt";
+                        reg = <0x600 0x10>;
+                        interrupts = <1 9 0>;
+                        fsl,has-wdt;
+                };
+
+                can@900 {
+                        compatible = "fsl,mpc5200-mscan";
+                        interrupts = <2 17 0>;
+                        reg = <0x900 0x80>;
+                };
+
+                can@980 {
+                        compatible = "fsl,mpc5200-mscan";
+                        interrupts = <2 18 0>;
+                        reg = <0x980 0x80>;
+                };
+
+                gpio_simple: gpio@b00 {
+                        compatible = "fsl,mpc5200-gpio";
+                        reg = <0xb00 0x40>;
+                        interrupts = <1 7 0>;
+                        gpio-controller;
+                        #gpio-cells = <2>;
+                };
+
+                usb@1000 {
+                        compatible = "fsl,mpc5200-ohci","ohci-be";
+                        reg = <0x1000 0xff>;
+                        interrupts = <2 6 0>;
+                };
+
+                dma-controller@1200 {
+                        device_type = "dma-controller";
+                        compatible = "fsl,mpc5200-bestcomm";
+                        reg = <0x1200 0x80>;
+                        interrupts = <3 0 0  3 1 0  3 2 0  3 3 0
+                                      3 4 0  3 5 0  3 6 0  3 7 0
+                                      3 8 0  3 9 0  3 10 0  3 11 0
+                                      3 12 0  3 13 0  3 14 0  3 15 0>;
+                };
+
+                xlb@1f00 {
+                        compatible = "fsl,mpc5200-xlb";
+                        reg = <0x1f00 0x100>;
+                };
+
+                serial@2000 {           // PSC1
+                        compatible = "fsl,mpc5200-psc-uart";
+                        reg = <0x2000 0x100>;
+                        interrupts = <2 1 0>;
+                };
+
+                serial@2400 {           // PSC3
+                        compatible = "fsl,mpc5200-psc-uart";
+                        reg = <0x2400 0x100>;
+                        interrupts = <2 3 0>;
+                };
+
+                ethernet@3000 {
+                        compatible = "fsl,mpc5200-fec";
+                        reg = <0x3000 0x400>;
+                        local-mac-address = [ 00 00 00 00 00 00 ];
+                        interrupts = <2 5 0>;
+                        fixed-link = <1 1 100 0 0>;
+                };
+
+                mdio@3000 {
+                        #address-cells = <1>;
+                        #size-cells = <0>;
+                        compatible = "fsl,mpc5200-mdio";
+                        reg = <0x3000 0x400>;       // fec range, since we need to setup fec interrupts
+                        interrupts = <2 5 0>;   // these are for "mii command finished", not link changes & co.
+                };
+
+                ata@3a00 {
+                        compatible = "fsl,mpc5200-ata";
+                        reg = <0x3a00 0x100>;
+                        interrupts = <2 7 0>;
+                };
+
+                i2c@3d00 {
+                        #address-cells = <1>;
+                        #size-cells = <0>;
+                        compatible = "fsl,mpc5200-i2c","fsl-i2c";
+                        reg = <0x3d00 0x40>;
+                        interrupts = <2 15 0>;
+                };
+
+
+                i2c@3d40 {
+                        #address-cells = <1>;
+                        #size-cells = <0>;
+                        compatible = "fsl,mpc5200-i2c","fsl-i2c";
+                        reg = <0x3d40 0x40>;
+                        interrupts = <2 16 0>;
+
+                        dtt@28 {
+                                compatible = "national,lm80";
+                                reg = <0x28>;
+                        };
+
+                        rtc@68 {
+                                compatible = "dallas,ds1374";
+                                reg = <0x68>;
+                        };
+                };
+
+                sram@8000 {
+                        compatible = "fsl,mpc5200-sram";
+                        reg = <0x8000 0x4000>;
+                };
+        };
+
+        localbus {
+                compatible = "fsl,mpc5200-lpb","simple-bus";
+                #address-cells = <2>;
+                #size-cells = <1>;
+                ranges = <      0 0 0xfc000000 0x02000000
+                                1 0 0xe0000000 0x04000000 // CS1 range, SM501
+                                3 0 0xe8000000 0x00080000>;
+
+                flash@0,0 {
+                        compatible = "cfi-flash";
+                        reg = <0 0 0x02000000>;
+                        bank-width = <4>;
+                        device-width = <2>;
+                        #size-cells = <1>;
+                        #address-cells = <1>;
+                };
+
+                display@1,0 {
+                        compatible = "smi,sm501";
+                        reg = <1 0x00000000 0x00800000
+                               1 0x03e00000 0x00200000>;
+                        mode = "640x480-32@60";
+                        interrupts = <1 1 3>;
+                        little-endian;
+                };
+
+                mram0@3,0 {
+                        compatible = "mtd-ram";
+                        reg = <3 0x00000 0x80000>;
+                        bank-width = <1>;
+                };
+        };
+
+        pci@f0000d00 {
+                #interrupt-cells = <1>;
+                #size-cells = <2>;
+                #address-cells = <3>;
+                device_type = "pci";
+                compatible = "fsl,mpc5200-pci";
+                reg = <0xf0000d00 0x100>;
+                interrupt-map-mask = <0xf800 0 0 7>;
+                interrupt-map = <0xc000 0 0 1 &mpc5200_pic 0 0 3
+                                 0xc000 0 0 2 &mpc5200_pic 0 0 3
+                                 0xc000 0 0 3 &mpc5200_pic 0 0 3
+                                 0xc000 0 0 4 &mpc5200_pic 0 0 3>;
+                clock-frequency = <0>; // From boot loader
+                interrupts = <2 8 0 2 9 0 2 10 0>;
+                bus-range = <0 0>;
+                ranges = <0x42000000 0 0x80000000 0x80000000 0 0x10000000
+                          0x02000000 0 0x90000000 0x90000000 0 0x10000000
+                          0x01000000 0 0x00000000 0xa0000000 0 0x01000000>;
+        };
+};
diff --git a/arch/powerpc/boot/dts/digsy_mtc.dts b/arch/powerpc/boot/dts/digsy_mtc.dts
index 27bd267d631c..a7511f2d844d 100644
--- a/arch/powerpc/boot/dts/digsy_mtc.dts
+++ b/arch/powerpc/boot/dts/digsy_mtc.dts
@@ -23,19 +23,26 @@
 
         soc5200@f0000000 {
                 timer@600 {     // General Purpose Timer
+                        #gpio-cells = <2>;
                         fsl,has-wdt;
+                        gpio-controller;
                 };
 
-                rtc@800 {
-                        status = "disabled";
+                timer@610 {
+                        #gpio-cells = <2>;
+                        gpio-controller;
                 };
 
-                can@900 {
+                rtc@800 {
                         status = "disabled";
                 };
 
-                can@980 {
-                        status = "disabled";
+                spi@f00 {
+                        msp430@0 {
+                                compatible = "spidev";
+                                spi-max-frequency = <32000>;
+                                reg = <0>;
+                        };
                 };
 
                 psc@2000 {              // PSC1
@@ -73,11 +80,16 @@
                 };
 
                 i2c@3d00 {
-                        rtc@50 {
+                        eeprom@50 {
                                 compatible = "at,24c08";
                                 reg = <0x50>;
                         };
 
+                        rtc@56 {
+                                compatible = "mc,rv3029c2";
+                                reg = <0x56>;
+                        };
+
                         rtc@68 {
                                 compatible = "dallas,ds1339";
                                 reg = <0x68>;
@@ -90,11 +102,22 @@
         };
 
         pci@f0000d00 {
-                status = "disabled";
+                interrupt-map-mask = <0xf800 0 0 7>;
+                interrupt-map = <0xc000 0 0 1 &mpc5200_pic 0 0 3
+                                 0xc000 0 0 2 &mpc5200_pic 0 0 3
+                                 0xc000 0 0 3 &mpc5200_pic 0 0 3
+                                 0xc000 0 0 4 &mpc5200_pic 0 0 3>;
+                clock-frequency = <0>; // From boot loader
+                interrupts = <2 8 0 2 9 0 2 10 0>;
+                bus-range = <0 0>;
+                ranges = <0x42000000 0 0x80000000 0x80000000 0 0x10000000
+                          0x02000000 0 0x90000000 0x90000000 0 0x10000000
+                          0x01000000 0 0x00000000 0xa0000000 0 0x01000000>;
         };
 
         localbus {
-                ranges = <0 0 0xff000000 0x1000000>;
+                ranges = <0 0 0xff000000 0x1000000
+                          4 0 0x60000000 0x0001000>;
 
                 // 16-bit flash device at LocalPlus Bus CS0
                 flash@0,0 {
@@ -122,5 +145,25 @@
                                 reg = <0x00f00000 0x100000>;
                         };
                 };
+
+                can@4,0 {
+                        compatible = "nxp,sja1000";
+                        reg = <4 0x000 0x80>;
+                        nxp,external-clock-frequency = <24000000>;
+                        interrupts = <1 2 3>; // Level-low
+                };
+
+                can@4,100 {
+                        compatible = "nxp,sja1000";
+                        reg = <4 0x100 0x80>;
+                        nxp,external-clock-frequency = <24000000>;
+                        interrupts = <1 2 3>;  // Level-low
+                };
+
+                serial@4,200 {
+                        compatible = "nxp,sc28l92";
+                        reg = <4 0x200 0x10>;
+                        interrupts = <1 3 3>;
+                };
         };
 };
diff --git a/arch/powerpc/boot/dts/gef_ppc9a.dts b/arch/powerpc/boot/dts/gef_ppc9a.dts
index 83f4b79dff85..2266bbb303d0 100644
--- a/arch/powerpc/boot/dts/gef_ppc9a.dts
+++ b/arch/powerpc/boot/dts/gef_ppc9a.dts
@@ -269,14 +269,16 @@
                 enet0: ethernet@24000 {
                         #address-cells = <1>;
                         #size-cells = <1>;
+                        cell-index = <0>;
                         device_type = "network";
-                        model = "eTSEC";
+                        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>;
+                        interrupts = <29 2 30  2 34 2>;
                         interrupt-parent = <&mpic>;
+                        tbi-handle = <&tbi0>;
                         phy-handle = <&phy0>;
                         phy-connection-type = "gmii";
 
@@ -290,25 +292,48 @@
                                         interrupt-parent = <&gef_pic>;
                                         interrupts = <0x9 0x4>;
                                         reg = <1>;
+                                        device_type = "ethernet-phy";
                                 };
                                 phy2: ethernet-phy@2 {
                                         interrupt-parent = <&gef_pic>;
                                         interrupts = <0x8 0x4>;
                                         reg = <3>;
+                                        device_type = "ethernet-phy";
+                                };
+                                tbi0: tbi-phy@11 {
+                                        reg = <0x11>;
+                                        device_type = "tbi-phy";
                                 };
                         };
                 };
 
                 enet1: ethernet@26000 {
+                        #address-cells = <1>;
+                        #size-cells = <1>;
+                        cell-index = <2>;
                         device_type = "network";
-                        model = "eTSEC";
+                        model = "TSEC";
                         compatible = "gianfar";
                         reg = <0x26000 0x1000>;
+                        ranges = <0x0 0x26000 0x1000>;
                         local-mac-address = [ 00 00 00 00 00 00 ];
-                        interrupts = <0x1f 0x2 0x20 0x2 0x21 0x2>;
+                        interrupts = <31 2 32 2 33 2>;
                         interrupt-parent = <&mpic>;
+                        tbi-handle = <&tbi2>;
                         phy-handle = <&phy2>;
                         phy-connection-type = "gmii";
+
+                        mdio@520 {
+                                #address-cells = <1>;
+                                #size-cells = <0>;
+                                compatible = "fsl,gianfar-tbi";
+                                reg = <0x520 0x20>;
+
+                                tbi2: tbi-phy@11 {
+                                        reg = <0x11>;
+                                        device_type = "tbi-phy";
+                                };
+                        };
                 };
 
                 serial0: serial@4500 {
diff --git a/arch/powerpc/boot/dts/gef_sbc310.dts b/arch/powerpc/boot/dts/gef_sbc310.dts
index fc3a331dd392..429e87d9acef 100644
--- a/arch/powerpc/boot/dts/gef_sbc310.dts
+++ b/arch/powerpc/boot/dts/gef_sbc310.dts
@@ -267,14 +267,16 @@
                 enet0: ethernet@24000 {
                         #address-cells = <1>;
                         #size-cells = <1>;
+                        cell-index = <0>;
                         device_type = "network";
-                        model = "eTSEC";
+                        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>;
+                        interrupts = <29 2 30  2 34 2>;
                         interrupt-parent = <&mpic>;
+                        tbi-handle = <&tbi0>;
                         phy-handle = <&phy0>;
                         phy-connection-type = "gmii";
 
@@ -288,25 +290,48 @@
                                         interrupt-parent = <&gef_pic>;
                                         interrupts = <0x9 0x4>;
                                         reg = <1>;
+                                        device_type = "ethernet-phy";
                                 };
                                 phy2: ethernet-phy@2 {
                                         interrupt-parent = <&gef_pic>;
                                         interrupts = <0x8 0x4>;
                                         reg = <3>;
+                                        device_type = "ethernet-phy";
+                                };
+                                tbi0: tbi-phy@11 {
+                                        reg = <0x11>;
+                                        device_type = "tbi-phy";
                                 };
                         };
                 };
 
                 enet1: ethernet@26000 {
+                        #address-cells = <1>;
+                        #size-cells = <1>;
+                        cell-index = <2>;
                         device_type = "network";
-                        model = "eTSEC";
+                        model = "TSEC";
                         compatible = "gianfar";
                         reg = <0x26000 0x1000>;
+                        ranges = <0x0 0x26000 0x1000>;
                         local-mac-address = [ 00 00 00 00 00 00 ];
-                        interrupts = <0x1f 0x2 0x20 0x2 0x21 0x2>;
+                        interrupts = <31 2 32 2 33 2>;
                         interrupt-parent = <&mpic>;
+                        tbi-handle = <&tbi2>;
                         phy-handle = <&phy2>;
                         phy-connection-type = "gmii";
+
+                        mdio@520 {
+                                #address-cells = <1>;
+                                #size-cells = <0>;
+                                compatible = "fsl,gianfar-tbi";
+                                reg = <0x520 0x20>;
+
+                                tbi2: tbi-phy@11 {
+                                        reg = <0x11>;
+                                        device_type = "tbi-phy";
+                                };
+                        };
                 };
 
                 serial0: serial@4500 {
diff --git a/arch/powerpc/boot/dts/gef_sbc610.dts b/arch/powerpc/boot/dts/gef_sbc610.dts
index c0671cc98125..d81201ac2cad 100644
--- a/arch/powerpc/boot/dts/gef_sbc610.dts
+++ b/arch/powerpc/boot/dts/gef_sbc610.dts
@@ -267,14 +267,16 @@
                 enet0: ethernet@24000 {
                         #address-cells = <1>;
                         #size-cells = <1>;
+                        cell-index = <0>;
                         device_type = "network";
-                        model = "eTSEC";
+                        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>;
+                        interrupts = <29 2 30  2 34 2>;
                         interrupt-parent = <&mpic>;
+                        tbi-handle = <&tbi0>;
                         phy-handle = <&phy0>;
                         phy-connection-type = "gmii";
 
@@ -288,25 +290,48 @@
                                         interrupt-parent = <&gef_pic>;
                                         interrupts = <0x9 0x4>;
                                         reg = <1>;
+                                        device_type = "ethernet-phy";
                                 };
                                 phy2: ethernet-phy@2 {
                                         interrupt-parent = <&gef_pic>;
                                         interrupts = <0x8 0x4>;
                                         reg = <3>;
+                                        device_type = "ethernet-phy";
+                                };
+                                tbi0: tbi-phy@11 {
+                                        reg = <0x11>;
+                                        device_type = "tbi-phy";
                                 };
                         };
                 };
 
                 enet1: ethernet@26000 {
+                        #address-cells = <1>;
+                        #size-cells = <1>;
+                        cell-index = <2>;
                         device_type = "network";
-                        model = "eTSEC";
+                        model = "TSEC";
                         compatible = "gianfar";
                         reg = <0x26000 0x1000>;
+                        ranges = <0x0 0x26000 0x1000>;
                         local-mac-address = [ 00 00 00 00 00 00 ];
-                        interrupts = <0x1f 0x2 0x20 0x2 0x21 0x2>;
+                        interrupts = <31 2 32 2 33 2>;
                         interrupt-parent = <&mpic>;
+                        tbi-handle = <&tbi2>;
                         phy-handle = <&phy2>;
                         phy-connection-type = "gmii";
+
+                        mdio@520 {
+                                #address-cells = <1>;
+                                #size-cells = <0>;
+                                compatible = "fsl,gianfar-tbi";
+                                reg = <0x520 0x20>;
+
+                                tbi2: tbi-phy@11 {
+                                        reg = <0x11>;
+                                        device_type = "tbi-phy";
+                                };
+                        };
                 };
 
                 serial0: serial@4500 {
diff --git a/arch/powerpc/boot/dts/hcu4.dts b/arch/powerpc/boot/dts/hcu4.dts
deleted file mode 100644
index 7988598da4c9..000000000000
--- a/arch/powerpc/boot/dts/hcu4.dts
+++ /dev/null
@@ -1,168 +0,0 @@
-/*
-* Device Tree Source for Netstal Maschinen HCU4
-* based on the IBM Walnut
-*
-* Copyright 2008
-* Niklaus Giger <niklaus.giger@member.fsf.org>
-*
-* Copyright 2007 IBM Corp.
-* Josh Boyer <jwboyer@linux.vnet.ibm.com>
-*
-* This file is licensed under the terms of the GNU General Public
-* License version 2.  This program is licensed "as is" without
-* any warranty of any kind, whether express or implied.
-*/
-
-/dts-v1/;
-
-/ {
-        #address-cells = <0x1>;
-        #size-cells = <0x1>;
-        model = "netstal,hcu4";
-        compatible = "netstal,hcu4";
-        dcr-parent = <0x1>;
-
-        aliases {
-                ethernet0 = "/plb/opb/ethernet@ef600800";
-                serial0 = "/plb/opb/serial@ef600300";
-        };
-
-        cpus {
-                #address-cells = <0x1>;
-                #size-cells = <0x0>;
-
-                cpu@0 {
-                        device_type = "cpu";
-                        model = "PowerPC,405GPr";
-                        reg = <0x0>;
-                        clock-frequency = <0>;          /* Filled in by U-Boot */
-                        timebase-frequency = <0x0>;     /* Filled in by U-Boot */
-                        i-cache-line-size = <0x20>;
-                        d-cache-line-size = <0x20>;
-                        i-cache-size = <0x4000>;
-                        d-cache-size = <0x4000>;
-                        dcr-controller;
-                        dcr-access-method = "native";
-                        linux,phandle = <0x1>;
-                };
-        };
-
-        memory {
-                device_type = "memory";
-                reg = <0x0 0x0>;        /* Filled in by U-Boot */
-        };
-
-        UIC0: interrupt-controller {
-                compatible = "ibm,uic";
-                interrupt-controller;
-                cell-index = <0x0>;
-                dcr-reg = <0xc0 0x9>;
-                #address-cells = <0x0>;
-                #size-cells = <0x0>;
-                #interrupt-cells = <0x2>;
-                linux,phandle = <0x2>;
-        };
-
-        plb {
-                compatible = "ibm,plb3";
-                #address-cells = <0x1>;
-                #size-cells = <0x1>;
-                ranges;
-                clock-frequency = <0x0>;        /* Filled in by U-Boot */
-
-                SDRAM0: memory-controller {
-                        compatible = "ibm,sdram-405gp";
-                        dcr-reg = <0x10 0x2>;
-                };
-
-                MAL: mcmal {
-                        compatible = "ibm,mcmal-405gp", "ibm,mcmal";
-                        dcr-reg = <0x180 0x62>;
-                        num-tx-chans = <0x1>;
-                        num-rx-chans = <0x1>;
-                        interrupt-parent = <0x2>;
-                        interrupts = <0xb 0x4 0xc 0x4 0xa 0x4 0xd 0x4 0xe 0x4>;
-                        linux,phandle = <0x3>;
-                };
-
-                POB0: opb {
-                        compatible = "ibm,opb-405gp", "ibm,opb";
-                        #address-cells = <0x1>;
-                        #size-cells = <0x1>;
-                        ranges = <0xef600000 0xef600000 0xa00000>;
-                        dcr-reg = <0xa0 0x5>;
-                        clock-frequency = <0x0>;        /* Filled in by U-Boot */
-
-                        UART0: serial@ef600300 {
-                                device_type = "serial";
-                                compatible = "ns16550";
-                                reg = <0xef600300 0x8>;
-                                virtual-reg = <0xef600300>;
-                                clock-frequency = <0x0>;/* Filled in by U-Boot */
-                                current-speed = <0>;    /* Filled in by U-Boot */
-                                interrupt-parent = <0x2>;
-                                interrupts = <0x0 0x4>;
-                        };
-
-                        IIC: i2c@ef600500 {
-                                compatible = "ibm,iic-405gp", "ibm,iic";
-                                reg = <0xef600500 0x11>;
-                                interrupt-parent = <0x2>;
-                                interrupts = <0x2 0x4>;
-                        };
-
-                        GPIO: gpio@ef600700 {
-                                compatible = "ibm,gpio-405gp";
-                                reg = <0xef600700 0x20>;
-                        };
-
-                        EMAC: ethernet@ef600800 {
-                                device_type = "network";
-                                compatible = "ibm,emac-405gp", "ibm,emac";
-                                interrupt-parent = <0x2>;
-                                interrupts = <0xf 0x4 0x9 0x4>;
-                                local-mac-address = [00 00 00 00 00 00];
-                                reg = <0xef600800 0x70>;
-                                mal-device = <0x3>;
-                                mal-tx-channel = <0x0>;
-                                mal-rx-channel = <0x0>;
-                                cell-index = <0x0>;
-                                max-frame-size = <0x5dc>;
-                                rx-fifo-size = <0x1000>;
-                                tx-fifo-size = <0x800>;
-                                phy-mode = "rmii";
-                                phy-map = <0x1>;
-                        };
-                };
-
-                EBC0: ebc {
-                        compatible = "ibm,ebc-405gp", "ibm,ebc";
-                        dcr-reg = <0x12 0x2>;
-                        #address-cells = <0x2>;
-                        #size-cells = <0x1>;
-                        clock-frequency = <0x0>;        /* Filled in by U-Boot */
-
-                        sram@0,0 {
-                                reg = <0x0 0x0 0x80000>;
-                        };
-
-                        flash@0,80000 {
-                                compatible = "jedec-flash";
-                                bank-width = <0x1>;
-                                reg = <0x0 0x80000 0x80000>;
-                                #address-cells = <0x1>;
-                                #size-cells = <0x1>;
-
-                                partition@0 {
-                                        label = "OpenBIOS";
-                                        reg = <0x0 0x80000>;
-                                        read-only;
-                                };
-                        };
-                };
-        };
-
-        chosen {
-                linux,stdout-path = "/plb/opb/serial@ef600300";
-        };
-};
diff --git a/arch/powerpc/boot/dts/ksi8560.dts b/arch/powerpc/boot/dts/ksi8560.dts
index bdb7fc0fa332..296c572ea605 100644
--- a/arch/powerpc/boot/dts/ksi8560.dts
+++ b/arch/powerpc/boot/dts/ksi8560.dts
@@ -306,7 +306,7 @@
         localbus@fdf05000 {
                 #address-cells = <2>;
                 #size-cells = <1>;
-                compatible = "fsl,mpc8560-localbus";
+                compatible = "fsl,mpc8560-localbus", "simple-bus";
                 reg = <0xfdf05000 0x68>;
 
                 ranges = <0x0 0x0 0xe0000000 0x00800000
diff --git a/arch/powerpc/boot/dts/mgcoge.dts b/arch/powerpc/boot/dts/mgcoge.dts
index 1360d2f69024..ededaf5ac015 100644
--- a/arch/powerpc/boot/dts/mgcoge.dts
+++ b/arch/powerpc/boot/dts/mgcoge.dts
@@ -213,6 +213,15 @@
                                 linux,network-index = <2>;
                                 fsl,cpm-command = <0x16200300>;
                         };
+
+                        usb@11b60 {
+                                compatible = "fsl,mpc8272-cpm-usb";
+                                mode = "peripheral";
+                                reg = <0x11b60 0x40 0x8b00 0x100>;
+                                interrupts = <11 8>;
+                                interrupt-parent = <&PIC>;
+                                usb-clock = <5>;
+                        };
                 };
 
                 cpm2_pio_c: gpio-controller@10d40 {
diff --git a/arch/powerpc/boot/dts/mpc5200b.dtsi b/arch/powerpc/boot/dts/mpc5200b.dtsi
index bc27548e895d..7ab286ab5300 100644
--- a/arch/powerpc/boot/dts/mpc5200b.dtsi
+++ b/arch/powerpc/boot/dts/mpc5200b.dtsi
@@ -147,6 +147,8 @@
                 };
 
                 spi@f00 {
+                        #address-cells = <1>;
+                        #size-cells = <0>;
                         compatible = "fsl,mpc5200b-spi","fsl,mpc5200-spi";
                         reg = <0xf00 0x20>;
                         interrupts = <2 13 0 2 14 0>;
diff --git a/arch/powerpc/boot/dts/mpc8349emitx.dts b/arch/powerpc/boot/dts/mpc8349emitx.dts
index b53d1df11e2d..505dc842d808 100644
--- a/arch/powerpc/boot/dts/mpc8349emitx.dts
+++ b/arch/powerpc/boot/dts/mpc8349emitx.dts
@@ -390,7 +390,8 @@
                 #address-cells = <2>;
                 #size-cells = <1>;
                 compatible = "fsl,mpc8349e-localbus",
-                             "fsl,pq2pro-localbus";
+                             "fsl,pq2pro-localbus",
+                             "simple-bus";
                 reg = <0xe0005000 0xd8>;
                 ranges = <0x0 0x0 0xfe000000 0x1000000  /* flash */
                           0x1 0x0 0xf8000000 0x20000    /* VSC 7385 */
diff --git a/arch/powerpc/boot/dts/p1010rdb.dts b/arch/powerpc/boot/dts/p1010rdb.dts
index 6b33b73a5ba0..d6c669c888e9 100644
--- a/arch/powerpc/boot/dts/p1010rdb.dts
+++ b/arch/powerpc/boot/dts/p1010rdb.dts
@@ -23,6 +23,8 @@
                 ethernet2 = &enet2;
                 pci0 = &pci0;
                 pci1 = &pci1;
+                can0 = &can0;
+                can1 = &can1;
         };
 
         memory {
@@ -169,14 +171,6 @@
                         };
                 };
 
-                can0@1c000 {
-                        fsl,flexcan-clock-source = "platform";
-                };
-
-                can1@1d000 {
-                        fsl,flexcan-clock-source = "platform";
-                };
-
                 usb@22000 {
                         phy_type = "utmi";
                 };
diff --git a/arch/powerpc/boot/dts/p1010si.dtsi b/arch/powerpc/boot/dts/p1010si.dtsi
index 7f51104f2e36..cabe0a453ae6 100644
--- a/arch/powerpc/boot/dts/p1010si.dtsi
+++ b/arch/powerpc/boot/dts/p1010si.dtsi
@@ -140,20 +140,18 @@
                         interrupt-parent = <&mpic>;
                 };
 
-                can0@1c000 {
-                        compatible = "fsl,flexcan-v1.0";
+                can0: can@1c000 {
+                        compatible = "fsl,p1010-flexcan";
                         reg = <0x1c000 0x1000>;
                         interrupts = <48 0x2>;
                         interrupt-parent = <&mpic>;
-                        fsl,flexcan-clock-divider = <2>;
                 };
 
-                can1@1d000 {
-                        compatible = "fsl,flexcan-v1.0";
+                can1: can@1d000 {
+                        compatible = "fsl,p1010-flexcan";
                         reg = <0x1d000 0x1000>;
                         interrupts = <61 0x2>;
                         interrupt-parent = <&mpic>;
-                        fsl,flexcan-clock-divider = <2>;
                 };
 
                 L2: l2-cache-controller@20000 {
diff --git a/arch/powerpc/boot/dts/p1022ds.dts b/arch/powerpc/boot/dts/p1022ds.dts
index 1be9743ab5e0..b9b8719a6204 100644
--- a/arch/powerpc/boot/dts/p1022ds.dts
+++ b/arch/powerpc/boot/dts/p1022ds.dts
@@ -150,7 +150,7 @@
                 };
 
                 board-control@3,0 {
-                        compatible = "fsl,p1022ds-pixis";
+                        compatible = "fsl,p1022ds-fpga", "fsl,fpga-ngpixis";
                         reg = <3 0 0x30>;
                         interrupt-parent = <&mpic>;
                         /*
diff --git a/arch/powerpc/boot/dts/p2020ds.dts b/arch/powerpc/boot/dts/p2020ds.dts
index dae403100f2f..66f03d6477b2 100644
--- a/arch/powerpc/boot/dts/p2020ds.dts
+++ b/arch/powerpc/boot/dts/p2020ds.dts
@@ -118,6 +118,11 @@
                         };
                 };
 
+                board-control@3,0 {
+                        compatible = "fsl,p2020ds-fpga", "fsl,fpga-ngpixis";
+                        reg = <0x3 0x0 0x30>;
+                };
+
                 nand@4,0 {
                         compatible = "fsl,elbc-fcm-nand";
                         reg = <0x4 0x0 0x40000>;
diff --git a/arch/powerpc/boot/dts/p2040rdb.dts b/arch/powerpc/boot/dts/p2041rdb.dts
index 7d84e391c632..79b6895027c0 100644
--- a/arch/powerpc/boot/dts/p2040rdb.dts
+++ b/arch/powerpc/boot/dts/p2041rdb.dts
@@ -1,5 +1,5 @@
 /*
- * P2040RDB Device Tree Source
+ * P2041RDB Device Tree Source
  *
  * Copyright 2011 Freescale Semiconductor Inc.
  *
@@ -32,11 +32,11 @@
  * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  */
 
-/include/ "p2040si.dtsi"
+/include/ "p2041si.dtsi"
 
 / {
-        model = "fsl,P2040RDB";
-        compatible = "fsl,P2040RDB";
+        model = "fsl,P2041RDB";
+        compatible = "fsl,P2041RDB";
         #address-cells = <2>;
         #size-cells = <2>;
         interrupt-parent = <&mpic>;
@@ -45,6 +45,10 @@
                 device_type = "memory";
         };
 
+        dcsr: dcsr@f00000000 {
+                ranges = <0x00000000 0xf 0x00000000 0x01008000>;
+        };
+
         soc: soc@ffe000000 {
                 spi@110000 {
                         flash@0 {
@@ -97,13 +101,8 @@
                         };
                 };
 
-                usb0: usb@210000 {
-                        phy_type = "utmi";
-                };
-
                 usb1: usb@211000 {
                         dr_mode = "host";
-                        phy_type = "utmi";
                 };
         };
 
diff --git a/arch/powerpc/boot/dts/p2040si.dtsi b/arch/powerpc/boot/dts/p2041si.dtsi
index 5fdbb24c0763..f7492edd0dfd 100644
--- a/arch/powerpc/boot/dts/p2040si.dtsi
+++ b/arch/powerpc/boot/dts/p2041si.dtsi
@@ -1,5 +1,5 @@
 /*
- * P2040 Silicon Device Tree Source
+ * P2041 Silicon Device Tree Source
  *
  * Copyright 2011 Freescale Semiconductor Inc.
  *
@@ -35,13 +35,14 @@
 /dts-v1/;
 
 / {
-        compatible = "fsl,P2040";
+        compatible = "fsl,P2041";
         #address-cells = <2>;
         #size-cells = <2>;
         interrupt-parent = <&mpic>;
 
         aliases {
                 ccsr = &soc;
+                dcsr = &dcsr;
 
                 serial0 = &serial0;
                 serial1 = &serial1;
@@ -109,6 +110,74 @@
                 };
         };
 
+        dcsr: dcsr@f00000000 {
+                #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>;
+                        interrupt-parent = <&mpic>;
+                        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,p2041-dcsr-dpaa", "fsl,dcsr-dpaa";
+                        reg = <0x9000 0x1000>;
+                };
+                dcsr-ocn@11000 {
+                        compatible = "fsl,p2041-dcsr-ocn", "fsl,dcsr-ocn";
+                        reg = <0x11000 0x1000>;
+                };
+                dcsr-ddr@12000 {
+                        compatible = "fsl,dcsr-ddr";
+                        dev-handle = <&ddr>;
+                        reg = <0x12000 0x1000>;
+                };
+                dcsr-nal@18000 {
+                        compatible = "fsl,p2041-dcsr-nal", "fsl,dcsr-nal";
+                        reg = <0x18000 0x1000>;
+                };
+                dcsr-rcpm@22000 {
+                        compatible = "fsl,p2041-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@42000 {
+                        compatible = "fsl,dcsr-e500mc-sb-proxy", "fsl,dcsr-cpu-sb-proxy";
+                        cpu-handle = <&cpu2>;
+                        reg = <0x42000 0x1000>;
+                };
+                dcsr-cpu-sb-proxy@43000 {
+                        compatible = "fsl,dcsr-e500mc-sb-proxy", "fsl,dcsr-cpu-sb-proxy";
+                        cpu-handle = <&cpu3>;
+                        reg = <0x43000 0x1000>;
+                };
+        };
+
         soc: soc@ffe000000 {
                 #address-cells = <1>;
                 #size-cells = <1>;
@@ -128,14 +197,14 @@
                         fsl,num-laws = <32>;
                 };
 
-                memory-controller@8000 {
+                ddr: memory-controller@8000 {
                         compatible = "fsl,qoriq-memory-controller-v4.5", "fsl,qoriq-memory-controller";
                         reg = <0x8000 0x1000>;
                         interrupts = <16 2 1 23>;
                 };
 
                 cpc: l3-cache-controller@10000 {
-                        compatible = "fsl,p2040-l3-cache-controller", "fsl,p4080-l3-cache-controller", "cache";
+                        compatible = "fsl,p2041-l3-cache-controller", "fsl,p4080-l3-cache-controller", "cache";
                         reg = <0x10000 0x1000>;
                         interrupts = <16 2 1 27>;
                 };
@@ -226,7 +295,7 @@
                 };
 
                 clockgen: global-utilities@e1000 {
-                        compatible = "fsl,p2040-clockgen", "fsl,qoriq-clockgen-1.0";
+                        compatible = "fsl,p2041-clockgen", "fsl,qoriq-clockgen-1.0";
                         reg = <0xe1000 0x1000>;
                         clock-frequency = <0>;
                 };
@@ -238,45 +307,45 @@
                 };
 
                 sfp: sfp@e8000 {
-                        compatible = "fsl,p2040-sfp", "fsl,qoriq-sfp-1.0";
+                        compatible = "fsl,p2041-sfp", "fsl,qoriq-sfp-1.0";
                         reg        = <0xe8000 0x1000>;
                 };
 
                 serdes: serdes@ea000 {
-                        compatible = "fsl,p2040-serdes";
+                        compatible = "fsl,p2041-serdes";
                         reg        = <0xea000 0x1000>;
                 };
 
                 dma0: dma@100300 {
                         #address-cells = <1>;
                         #size-cells = <1>;
-                        compatible = "fsl,p2040-dma", "fsl,eloplus-dma";
+                        compatible = "fsl,p2041-dma", "fsl,eloplus-dma";
                         reg = <0x100300 0x4>;
                         ranges = <0x0 0x100100 0x200>;
                         cell-index = <0>;
                         dma-channel@0 {
-                                compatible = "fsl,p2040-dma-channel",
+                                compatible = "fsl,p2041-dma-channel",
                                                 "fsl,eloplus-dma-channel";
                                 reg = <0x0 0x80>;
                                 cell-index = <0>;
                                 interrupts = <28 2 0 0>;
                         };
                         dma-channel@80 {
-                                compatible = "fsl,p2040-dma-channel",
+                                compatible = "fsl,p2041-dma-channel",
                                                 "fsl,eloplus-dma-channel";
                                 reg = <0x80 0x80>;
                                 cell-index = <1>;
                                 interrupts = <29 2 0 0>;
                         };
                         dma-channel@100 {
-                                compatible = "fsl,p2040-dma-channel",
+                                compatible = "fsl,p2041-dma-channel",
                                                 "fsl,eloplus-dma-channel";
                                 reg = <0x100 0x80>;
                                 cell-index = <2>;
                                 interrupts = <30 2 0 0>;
                         };
                         dma-channel@180 {
-                                compatible = "fsl,p2040-dma-channel",
+                                compatible = "fsl,p2041-dma-channel",
                                                 "fsl,eloplus-dma-channel";
                                 reg = <0x180 0x80>;
                                 cell-index = <3>;
@@ -287,33 +356,33 @@
                 dma1: dma@101300 {
                         #address-cells = <1>;
                         #size-cells = <1>;
-                        compatible = "fsl,p2040-dma", "fsl,eloplus-dma";
+                        compatible = "fsl,p2041-dma", "fsl,eloplus-dma";
                         reg = <0x101300 0x4>;
                         ranges = <0x0 0x101100 0x200>;
                         cell-index = <1>;
                         dma-channel@0 {
-                                compatible = "fsl,p2040-dma-channel",
+                                compatible = "fsl,p2041-dma-channel",
                                                 "fsl,eloplus-dma-channel";
                                 reg = <0x0 0x80>;
                                 cell-index = <0>;
                                 interrupts = <32 2 0 0>;
                         };
                         dma-channel@80 {
-                                compatible = "fsl,p2040-dma-channel",
+                                compatible = "fsl,p2041-dma-channel",
                                                 "fsl,eloplus-dma-channel";
                                 reg = <0x80 0x80>;
                                 cell-index = <1>;
                                 interrupts = <33 2 0 0>;
                         };
                         dma-channel@100 {
-                                compatible = "fsl,p2040-dma-channel",
+                                compatible = "fsl,p2041-dma-channel",
                                                 "fsl,eloplus-dma-channel";
                                 reg = <0x100 0x80>;
                                 cell-index = <2>;
                                 interrupts = <34 2 0 0>;
                         };
                         dma-channel@180 {
-                                compatible = "fsl,p2040-dma-channel",
+                                compatible = "fsl,p2041-dma-channel",
                                                 "fsl,eloplus-dma-channel";
                                 reg = <0x180 0x80>;
                                 cell-index = <3>;
@@ -324,22 +393,20 @@
                 spi@110000 {
                         #address-cells = <1>;
                         #size-cells = <0>;
-                        compatible = "fsl,p2040-espi", "fsl,mpc8536-espi";
+                        compatible = "fsl,p2041-espi", "fsl,mpc8536-espi";
                         reg = <0x110000 0x1000>;
                         interrupts = <53 0x2 0 0>;
                         fsl,espi-num-chipselects = <4>;
-
                 };
 
                 sdhc: sdhc@114000 {
-                        compatible = "fsl,p2040-esdhc", "fsl,esdhc";
+                        compatible = "fsl,p2041-esdhc", "fsl,esdhc";
                         reg = <0x114000 0x1000>;
                         interrupts = <48 2 0 0>;
                         sdhci,auto-cmd12;
                         clock-frequency = <0>;
                 };
 
-
                 i2c@118000 {
                         #address-cells = <1>;
                         #size-cells = <0>;
@@ -417,7 +484,7 @@
                 };
 
                 gpio0: gpio@130000 {
-                        compatible = "fsl,p2040-gpio", "fsl,qoriq-gpio";
+                        compatible = "fsl,p2041-gpio", "fsl,qoriq-gpio";
                         reg = <0x130000 0x1000>;
                         interrupts = <55 2 0 0>;
                         #gpio-cells = <2>;
@@ -425,32 +492,34 @@
                 };
 
                 usb0: usb@210000 {
-                        compatible = "fsl,p2040-usb2-mph",
+                        compatible = "fsl,p2041-usb2-mph",
                                         "fsl,mpc85xx-usb2-mph", "fsl-usb2-mph";
                         reg = <0x210000 0x1000>;
                         #address-cells = <1>;
                         #size-cells = <0>;
                         interrupts = <44 0x2 0 0>;
+                        phy_type = "utmi";
                         port0;
                 };
 
                 usb1: usb@211000 {
-                        compatible = "fsl,p2040-usb2-dr",
+                        compatible = "fsl,p2041-usb2-dr",
                                         "fsl,mpc85xx-usb2-dr", "fsl-usb2-dr";
                         reg = <0x211000 0x1000>;
                         #address-cells = <1>;
                         #size-cells = <0>;
                         interrupts = <45 0x2 0 0>;
+                        phy_type = "utmi";
                 };
 
                 sata@220000 {
-                        compatible = "fsl,p2040-sata", "fsl,pq-sata-v2";
+                        compatible = "fsl,p2041-sata", "fsl,pq-sata-v2";
                         reg = <0x220000 0x1000>;
                         interrupts = <68 0x2 0 0>;
                 };
 
                 sata@221000 {
-                        compatible = "fsl,p2040-sata", "fsl,pq-sata-v2";
+                        compatible = "fsl,p2041-sata", "fsl,pq-sata-v2";
                         reg = <0x221000 0x1000>;
                         interrupts = <69 0x2 0 0>;
                 };
@@ -534,19 +603,19 @@
         };
 
         localbus@ffe124000 {
-                compatible = "fsl,p2040-elbc", "fsl,elbc", "simple-bus";
+                compatible = "fsl,p2041-elbc", "fsl,elbc", "simple-bus";
                 interrupts = <25 2 0 0>;
                 #address-cells = <2>;
                 #size-cells = <1>;
         };
 
         pci0: pcie@ffe200000 {
-                compatible = "fsl,p2040-pcie", "fsl,qoriq-pcie-v2.2";
+                compatible = "fsl,p2041-pcie", "fsl,qoriq-pcie-v2.2";
                 device_type = "pci";
                 #size-cells = <2>;
                 #address-cells = <3>;
                 bus-range = <0x0 0xff>;
-                clock-frequency = <0x1fca055>;
+                clock-frequency = <33333333>;
                 fsl,msi = <&msi0>;
                 interrupts = <16 2 1 15>;
                 pcie@0 {
@@ -568,12 +637,12 @@
         };
 
         pci1: pcie@ffe201000 {
-                compatible = "fsl,p2040-pcie", "fsl,qoriq-pcie-v2.2";
+                compatible = "fsl,p2041-pcie", "fsl,qoriq-pcie-v2.2";
                 device_type = "pci";
                 #size-cells = <2>;
                 #address-cells = <3>;
                 bus-range = <0 0xff>;
-                clock-frequency = <0x1fca055>;
+                clock-frequency = <33333333>;
                 fsl,msi = <&msi1>;
                 interrupts = <16 2 1 14>;
                 pcie@0 {
@@ -595,12 +664,12 @@
         };
 
         pci2: pcie@ffe202000 {
-                compatible = "fsl,p2040-pcie", "fsl,qoriq-pcie-v2.2";
+                compatible = "fsl,p2041-pcie", "fsl,qoriq-pcie-v2.2";
                 device_type = "pci";
                 #size-cells = <2>;
                 #address-cells = <3>;
                 bus-range = <0x0 0xff>;
-                clock-frequency = <0x1fca055>;
+                clock-frequency = <33333333>;
                 fsl,msi = <&msi2>;
                 interrupts = <16 2 1 13>;
                 pcie@0 {
diff --git a/arch/powerpc/boot/dts/p3041ds.dts b/arch/powerpc/boot/dts/p3041ds.dts
index 69cae674f396..bbd113b49a8f 100644
--- a/arch/powerpc/boot/dts/p3041ds.dts
+++ b/arch/powerpc/boot/dts/p3041ds.dts
@@ -45,6 +45,10 @@
                 device_type = "memory";
         };
 
+        dcsr: dcsr@f00000000 {
+                ranges = <0x00000000 0xf 0x00000000 0x01008000>;
+        };
+
         soc: soc@ffe000000 {
                 spi@110000 {
                         flash@0 {
@@ -147,8 +151,8 @@
                 };
 
                 board-control@3,0 {
-                        compatible = "fsl,p3041ds-pixis";
-                        reg = <3 0 0x20>;
+                        compatible = "fsl,p3041ds-fpga", "fsl,fpga-ngpixis";
+                        reg = <3 0 0x30>;
                 };
         };
 
diff --git a/arch/powerpc/boot/dts/p3041si.dtsi b/arch/powerpc/boot/dts/p3041si.dtsi
index 8b695801f505..87130b732bc7 100644
--- a/arch/powerpc/boot/dts/p3041si.dtsi
+++ b/arch/powerpc/boot/dts/p3041si.dtsi
@@ -42,6 +42,7 @@
 
         aliases {
                 ccsr = &soc;
+                dcsr = &dcsr;
 
                 serial0 = &serial0;
                 serial1 = &serial1;
@@ -114,6 +115,74 @@
                 };
         };
 
+        dcsr: dcsr@f00000000 {
+                #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>;
+                        interrupt-parent = <&mpic>;
+                        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,p43041-dcsr-dpaa", "fsl,dcsr-dpaa";
+                        reg = <0x9000 0x1000>;
+                };
+                dcsr-ocn@11000 {
+                        compatible = "fsl,p43041-dcsr-ocn", "fsl,dcsr-ocn";
+                        reg = <0x11000 0x1000>;
+                };
+                dcsr-ddr@12000 {
+                        compatible = "fsl,dcsr-ddr";
+                        dev-handle = <&ddr>;
+                        reg = <0x12000 0x1000>;
+                };
+                dcsr-nal@18000 {
+                        compatible = "fsl,p43041-dcsr-nal", "fsl,dcsr-nal";
+                        reg = <0x18000 0x1000>;
+                };
+                dcsr-rcpm@22000 {
+                        compatible = "fsl,p43041-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@42000 {
+                        compatible = "fsl,dcsr-e500mc-sb-proxy", "fsl,dcsr-cpu-sb-proxy";
+                        cpu-handle = <&cpu2>;
+                        reg = <0x42000 0x1000>;
+                };
+                dcsr-cpu-sb-proxy@43000 {
+                        compatible = "fsl,dcsr-e500mc-sb-proxy", "fsl,dcsr-cpu-sb-proxy";
+                        cpu-handle = <&cpu3>;
+                        reg = <0x43000 0x1000>;
+                };
+        };
+
         soc: soc@ffe000000 {
                 #address-cells = <1>;
                 #size-cells = <1>;
@@ -133,7 +202,7 @@
                         fsl,num-laws = <32>;
                 };
 
-                memory-controller@8000 {
+                ddr: memory-controller@8000 {
                         compatible = "fsl,qoriq-memory-controller-v4.5", "fsl,qoriq-memory-controller";
                         reg = <0x8000 0x1000>;
                         interrupts = <16 2 1 23>;
diff --git a/arch/powerpc/boot/dts/p3060qds.dts b/arch/powerpc/boot/dts/p3060qds.dts
new file mode 100644
index 000000000000..08b9193213e7
--- /dev/null
+++ b/arch/powerpc/boot/dts/p3060qds.dts
@@ -0,0 +1,238 @@
+/*
+ * 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/ "p3060si.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 {
+                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";
+                };
+        };
+
+        rapidio@ffe0c0000 {
+                reg = <0xf 0xfe0c0000 0 0x11000>;
+
+                port1 {
+                        ranges = <0 0 0xc 0x20000000 0 0x10000000>;
+                };
+                port2 {
+                        ranges = <0 0 0xc 0x30000000 0 0x10000000>;
+                };
+        };
+
+        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>;
+                };
+        };
+};
diff --git a/arch/powerpc/boot/dts/p3060si.dtsi b/arch/powerpc/boot/dts/p3060si.dtsi
new file mode 100644
index 000000000000..68947e157bbc
--- /dev/null
+++ b/arch/powerpc/boot/dts/p3060si.dtsi
@@ -0,0 +1,719 @@
+/*
+ * P3060 Silicon 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.
+ */
+
+/dts-v1/;
+
+/ {
+        compatible = "fsl,P3060";
+        #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;
+        };
+
+        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 {
+                        device_type = "cpu";
+                        reg = <7>;
+                        next-level-cache = <&L2_7>;
+                        L2_7: l2-cache {
+                                next-level-cache = <&cpc>;
+                        };
+                };
+        };
+
+        dcsr: dcsr@f00000000 {
+                #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>;
+                        interrupt-parent = <&mpic>;
+                        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 = <&ddr>;
+                        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: soc@ffe000000 {
+                #address-cells = <1>;
+                #size-cells = <1>;
+                device_type = "soc";
+                compatible = "simple-bus";
+                ranges = <0x00000000 0xf 0xfe000000 0x1000000>;
+                reg = <0xf 0xfe000000 0 0x00001000>;
+
+                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>;
+                };
+
+                ddr: 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>;
+                };
+
+                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>;
+                };
+
+                mpic: pic@40000 {
+                        clock-frequency = <0>;
+                        interrupt-controller;
+                        #address-cells = <0>;
+                        #interrupt-cells = <4>;
+                        reg = <0x40000 0x40000>;
+                        compatible = "fsl,mpic", "chrp,open-pic";
+                        device_type = "open-pic";
+                };
+
+                msi0: msi@41600 {
+                        compatible = "fsl,mpic-msi";
+                        reg = <0x41600 0x200>;
+                        msi-available-ranges = <0 0x100>;
+                        interrupts = <
+                                0xe0 0 0 0
+                                0xe1 0 0 0
+                                0xe2 0 0 0
+                                0xe3 0 0 0
+                                0xe4 0 0 0
+                                0xe5 0 0 0
+                                0xe6 0 0 0
+                                0xe7 0 0 0>;
+                };
+
+                msi1: msi@41800 {
+                        compatible = "fsl,mpic-msi";
+                        reg = <0x41800 0x200>;
+                        msi-available-ranges = <0 0x100>;
+                        interrupts = <
+                                0xe8 0 0 0
+                                0xe9 0 0 0
+                                0xea 0 0 0
+                                0xeb 0 0 0
+                                0xec 0 0 0
+                                0xed 0 0 0
+                                0xee 0 0 0
+                                0xef 0 0 0>;
+                };
+
+                msi2: msi@41a00 {
+                        compatible = "fsl,mpic-msi";
+                        reg = <0x41a00 0x200>;
+                        msi-available-ranges = <0 0x100>;
+                        interrupts = <
+                                0xf0 0 0 0
+                                0xf1 0 0 0
+                                0xf2 0 0 0
+                                0xf3 0 0 0
+                                0xf4 0 0 0
+                                0xf5 0 0 0
+                                0xf6 0 0 0
+                                0xf7 0 0 0>;
+                };
+
+                rmu: rmu@d3000 {
+                        #address-cells = <1>;
+                        #size-cells = <1>;
+                        compatible = "fsl,srio-rmu";
+                        reg = <0xd3000 0x500>;
+                        ranges = <0x0 0xd3000 0x500>;
+
+                        message-unit@0 {
+                                compatible = "fsl,srio-msg-unit";
+                                reg = <0x0 0x100>;
+                                interrupts = <
+                                        60 2 0 0  /* msg1_tx_irq */
+                                        61 2 0 0>;/* msg1_rx_irq */
+                        };
+                        message-unit@100 {
+                                compatible = "fsl,srio-msg-unit";
+                                reg = <0x100 0x100>;
+                                interrupts = <
+                                        62 2 0 0  /* msg2_tx_irq */
+                                        63 2 0 0>;/* msg2_rx_irq */
+                        };
+                        doorbell-unit@400 {
+                                compatible = "fsl,srio-dbell-unit";
+                                reg = <0x400 0x80>;
+                                interrupts = <
+                                        56 2 0 0  /* bell_outb_irq */
+                                        57 2 0 0>;/* bell_inb_irq */
+                        };
+                        port-write-unit@4e0 {
+                                compatible = "fsl,srio-port-write-unit";
+                                reg = <0x4e0 0x20>;
+                                interrupts = <16 2 1 11>;
+                        };
+                };
+
+                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>;
+                };
+
+                dma0: dma@100300 {
+                        #address-cells = <1>;
+                        #size-cells = <1>;
+                        compatible = "fsl,p3060-dma", "fsl,eloplus-dma";
+                        reg = <0x100300 0x4>;
+                        ranges = <0x0 0x100100 0x200>;
+                        cell-index = <0>;
+                        dma-channel@0 {
+                                compatible = "fsl,p3060-dma-channel",
+                                                "fsl,eloplus-dma-channel";
+                                reg = <0x0 0x80>;
+                                cell-index = <0>;
+                                interrupts = <28 2 0 0>;
+                        };
+                        dma-channel@80 {
+                                compatible = "fsl,p3060-dma-channel",
+                                                "fsl,eloplus-dma-channel";
+                                reg = <0x80 0x80>;
+                                cell-index = <1>;
+                                interrupts = <29 2 0 0>;
+                        };
+                        dma-channel@100 {
+                                compatible = "fsl,p3060-dma-channel",
+                                                "fsl,eloplus-dma-channel";
+                                reg = <0x100 0x80>;
+                                cell-index = <2>;
+                                interrupts = <30 2 0 0>;
+                        };
+                        dma-channel@180 {
+                                compatible = "fsl,p3060-dma-channel",
+                                                "fsl,eloplus-dma-channel";
+                                reg = <0x180 0x80>;
+                                cell-index = <3>;
+                                interrupts = <31 2 0 0>;
+                        };
+                };
+
+                dma1: dma@101300 {
+                        #address-cells = <1>;
+                        #size-cells = <1>;
+                        compatible = "fsl,p3060-dma", "fsl,eloplus-dma";
+                        reg = <0x101300 0x4>;
+                        ranges = <0x0 0x101100 0x200>;
+                        cell-index = <1>;
+                        dma-channel@0 {
+                                compatible = "fsl,p3060-dma-channel",
+                                                "fsl,eloplus-dma-channel";
+                                reg = <0x0 0x80>;
+                                cell-index = <0>;
+                                interrupts = <32 2 0 0>;
+                        };
+                        dma-channel@80 {
+                                compatible = "fsl,p3060-dma-channel",
+                                                "fsl,eloplus-dma-channel";
+                                reg = <0x80 0x80>;
+                                cell-index = <1>;
+                                interrupts = <33 2 0 0>;
+                        };
+                        dma-channel@100 {
+                                compatible = "fsl,p3060-dma-channel",
+                                                "fsl,eloplus-dma-channel";
+                                reg = <0x100 0x80>;
+                                cell-index = <2>;
+                                interrupts = <34 2 0 0>;
+                        };
+                        dma-channel@180 {
+                                compatible = "fsl,p3060-dma-channel",
+                                                "fsl,eloplus-dma-channel";
+                                reg = <0x180 0x80>;
+                                cell-index = <3>;
+                                interrupts = <35 2 0 0>;
+                        };
+                };
+
+                spi@110000 {
+                        #address-cells = <1>;
+                        #size-cells = <0>;
+                        compatible = "fsl,p3060-espi", "fsl,mpc8536-espi";
+                        reg = <0x110000 0x1000>;
+                        interrupts = <53 0x2 0 0>;
+                        fsl,espi-num-chipselects = <4>;
+                };
+
+                i2c@118000 {
+                        #address-cells = <1>;
+                        #size-cells = <0>;
+                        cell-index = <0>;
+                        compatible = "fsl-i2c";
+                        reg = <0x118000 0x100>;
+                        interrupts = <38 2 0 0>;
+                        dfsrr;
+                };
+
+                i2c@118100 {
+                        #address-cells = <1>;
+                        #size-cells = <0>;
+                        cell-index = <1>;
+                        compatible = "fsl-i2c";
+                        reg = <0x118100 0x100>;
+                        interrupts = <38 2 0 0>;
+                        dfsrr;
+                };
+
+                i2c@119000 {
+                        #address-cells = <1>;
+                        #size-cells = <0>;
+                        cell-index = <2>;
+                        compatible = "fsl-i2c";
+                        reg = <0x119000 0x100>;
+                        interrupts = <39 2 0 0>;
+                        dfsrr;
+                };
+
+                i2c@119100 {
+                        #address-cells = <1>;
+                        #size-cells = <0>;
+                        cell-index = <3>;
+                        compatible = "fsl-i2c";
+                        reg = <0x119100 0x100>;
+                        interrupts = <39 2 0 0>;
+                        dfsrr;
+                };
+
+                serial0: serial@11c500 {
+                        cell-index = <0>;
+                        device_type = "serial";
+                        compatible = "ns16550";
+                        reg = <0x11c500 0x100>;
+                        clock-frequency = <0>;
+                        interrupts = <36 2 0 0>;
+                };
+
+                serial1: serial@11c600 {
+                        cell-index = <1>;
+                        device_type = "serial";
+                        compatible = "ns16550";
+                        reg = <0x11c600 0x100>;
+                        clock-frequency = <0>;
+                        interrupts = <36 2 0 0>;
+                };
+
+                serial2: serial@11d500 {
+                        cell-index = <2>;
+                        device_type = "serial";
+                        compatible = "ns16550";
+                        reg = <0x11d500 0x100>;
+                        clock-frequency = <0>;
+                        interrupts = <37 2 0 0>;
+                };
+
+                serial3: serial@11d600 {
+                        cell-index = <3>;
+                        device_type = "serial";
+                        compatible = "ns16550";
+                        reg = <0x11d600 0x100>;
+                        clock-frequency = <0>;
+                        interrupts = <37 2 0 0>;
+                };
+
+                gpio0: gpio@130000 {
+                        compatible = "fsl,p3060-gpio", "fsl,qoriq-gpio";
+                        reg = <0x130000 0x1000>;
+                        interrupts = <55 2 0 0>;
+                        #gpio-cells = <2>;
+                        gpio-controller;
+                };
+
+                usb0: usb@210000 {
+                        compatible = "fsl,p3060-usb2-mph",
+                                        "fsl,mpc85xx-usb2-mph", "fsl-usb2-mph";
+                        reg = <0x210000 0x1000>;
+                        #address-cells = <1>;
+                        #size-cells = <0>;
+                        interrupts = <44 0x2 0 0>;
+                };
+
+                usb1: usb@211000 {
+                        compatible = "fsl,p3060-usb2-dr",
+                                        "fsl,mpc85xx-usb2-dr", "fsl-usb2-dr";
+                        reg = <0x211000 0x1000>;
+                        #address-cells = <1>;
+                        #size-cells = <0>;
+                        interrupts = <45 0x2 0 0>;
+                };
+
+                crypto: crypto@300000 {
+                        compatible = "fsl,sec-v4.1", "fsl,sec-v4.0";
+                        #address-cells = <1>;
+                        #size-cells = <1>;
+                        reg = <0x300000 0x10000>;
+                        ranges = <0 0x300000 0x10000>;
+                        interrupt-parent = <&mpic>;
+                        interrupts = <92 2 0 0>;
+
+                        sec_jr0: jr@1000 {
+                                compatible = "fsl,sec-v4.1-job-ring", "fsl,sec-v4.0-job-ring";
+                                reg = <0x1000 0x1000>;
+                                interrupt-parent = <&mpic>;
+                                interrupts = <88 2 0 0>;
+                        };
+
+                        sec_jr1: jr@2000 {
+                                compatible = "fsl,sec-v4.1-job-ring", "fsl,sec-v4.0-job-ring";
+                                reg = <0x2000 0x1000>;
+                                interrupt-parent = <&mpic>;
+                                interrupts = <89 2 0 0>;
+                        };
+
+                        sec_jr2: jr@3000 {
+                                compatible = "fsl,sec-v4.1-job-ring", "fsl,sec-v4.0-job-ring";
+                                reg = <0x3000 0x1000>;
+                                interrupt-parent = <&mpic>;
+                                interrupts = <90 2 0 0>;
+                        };
+
+                        sec_jr3: jr@4000 {
+                                compatible = "fsl,sec-v4.1-job-ring", "fsl,sec-v4.0-job-ring";
+                                reg = <0x4000 0x1000>;
+                                interrupt-parent = <&mpic>;
+                                interrupts = <91 2 0 0>;
+                        };
+
+                        rtic@6000 {
+                                compatible = "fsl,sec-v4.1-rtic", "fsl,sec-v4.0-rtic";
+                                #address-cells = <1>;
+                                #size-cells = <1>;
+                                reg = <0x6000 0x100>;
+                                ranges = <0x0 0x6100 0xe00>;
+
+                                rtic_a: rtic-a@0 {
+                                        compatible = "fsl,sec-v4.1-rtic-memory", "fsl,sec-v4.0-rtic-memory";
+                                        reg = <0x00 0x20 0x100 0x80>;
+                                };
+
+                                rtic_b: rtic-b@20 {
+                                        compatible = "fsl,sec-v4.1-rtic-memory", "fsl,sec-v4.0-rtic-memory";
+                                        reg = <0x20 0x20 0x200 0x80>;
+                                };
+
+                                rtic_c: rtic-c@40 {
+                                        compatible = "fsl,sec-v4.1-rtic-memory", "fsl,sec-v4.0-rtic-memory";
+                                        reg = <0x40 0x20 0x300 0x80>;
+                                };
+
+                                rtic_d: rtic-d@60 {
+                                        compatible = "fsl,sec-v4.1-rtic-memory", "fsl,sec-v4.0-rtic-memory";
+                                        reg = <0x60 0x20 0x500 0x80>;
+                                };
+                        };
+                };
+
+                sec_mon: sec_mon@314000 {
+                        compatible = "fsl,sec-v4.1-mon", "fsl,sec-v4.0-mon";
+                        reg = <0x314000 0x1000>;
+                        interrupt-parent = <&mpic>;
+                        interrupts = <93 2 0 0>;
+                };
+        };
+
+        rapidio@ffe0c0000 {
+                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>;
+                };
+        };
+
+        localbus@ffe124000 {
+                compatible = "fsl,p3060-elbc", "fsl,elbc", "simple-bus";
+                interrupts = <25 2 0 0>;
+                #address-cells = <2>;
+                #size-cells = <1>;
+        };
+
+        pci0: pcie@ffe200000 {
+                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>;
+                fsl,msi = <&msi0>;
+                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
+                                >;
+                };
+        };
+
+        pci1: pcie@ffe201000 {
+                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>;
+                fsl,msi = <&msi1>;
+                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
+                                >;
+                };
+        };
+};
diff --git a/arch/powerpc/boot/dts/p4080ds.dts b/arch/powerpc/boot/dts/p4080ds.dts
index eb11098bb687..c7916dc28014 100644
--- a/arch/powerpc/boot/dts/p4080ds.dts
+++ b/arch/powerpc/boot/dts/p4080ds.dts
@@ -45,6 +45,10 @@
                 device_type = "memory";
         };
 
+        dcsr: dcsr@f00000000 {
+                ranges = <0x00000000 0xf 0x00000000 0x01008000>;
+        };
+
         soc: soc@ffe000000 {
                 spi@110000 {
                         flash@0 {
@@ -108,7 +112,8 @@
 
         localbus@ffe124000 {
                 reg = <0xf 0xfe124000 0 0x1000>;
-                ranges = <0 0 0xf 0xe8000000 0x08000000>;
+                ranges = <0 0 0xf 0xe8000000 0x08000000
+                          3 0 0xf 0xffdf0000 0x00008000>;
 
                 flash@0,0 {
                         compatible = "cfi-flash";
@@ -116,6 +121,11 @@
                         bank-width = <2>;
                         device-width = <2>;
                 };
+
+                board-control@3,0 {
+                        compatible = "fsl,p4080ds-fpga", "fsl,fpga-ngpixis";
+                        reg = <3 0 0x30>;
+                };
         };
 
         pci0: pcie@ffe200000 {
diff --git a/arch/powerpc/boot/dts/p4080si.dtsi b/arch/powerpc/boot/dts/p4080si.dtsi
index b71051f506c1..f20c01ab2473 100644
--- a/arch/powerpc/boot/dts/p4080si.dtsi
+++ b/arch/powerpc/boot/dts/p4080si.dtsi
@@ -42,6 +42,7 @@
 
         aliases {
                 ccsr = &soc;
+                dcsr = &dcsr;
 
                 serial0 = &serial0;
                 serial1 = &serial1;
@@ -77,7 +78,7 @@
                 #address-cells = <1>;
                 #size-cells = <0>;
 
-                cpu0: PowerPC,4080@0 {
+                cpu0: PowerPC,e500mc@0 {
                         device_type = "cpu";
                         reg = <0>;
                         next-level-cache = <&L2_0>;
@@ -85,7 +86,7 @@
                                 next-level-cache = <&cpc>;
                         };
                 };
-                cpu1: PowerPC,4080@1 {
+                cpu1: PowerPC,e500mc@1 {
                         device_type = "cpu";
                         reg = <1>;
                         next-level-cache = <&L2_1>;
@@ -93,7 +94,7 @@
                                 next-level-cache = <&cpc>;
                         };
                 };
-                cpu2: PowerPC,4080@2 {
+                cpu2: PowerPC,e500mc@2 {
                         device_type = "cpu";
                         reg = <2>;
                         next-level-cache = <&L2_2>;
@@ -101,7 +102,7 @@
                                 next-level-cache = <&cpc>;
                         };
                 };
-                cpu3: PowerPC,4080@3 {
+                cpu3: PowerPC,e500mc@3 {
                         device_type = "cpu";
                         reg = <3>;
                         next-level-cache = <&L2_3>;
@@ -109,7 +110,7 @@
                                 next-level-cache = <&cpc>;
                         };
                 };
-                cpu4: PowerPC,4080@4 {
+                cpu4: PowerPC,e500mc@4 {
                         device_type = "cpu";
                         reg = <4>;
                         next-level-cache = <&L2_4>;
@@ -117,7 +118,7 @@
                                 next-level-cache = <&cpc>;
                         };
                 };
-                cpu5: PowerPC,4080@5 {
+                cpu5: PowerPC,e500mc@5 {
                         device_type = "cpu";
                         reg = <5>;
                         next-level-cache = <&L2_5>;
@@ -125,7 +126,7 @@
                                 next-level-cache = <&cpc>;
                         };
                 };
-                cpu6: PowerPC,4080@6 {
+                cpu6: PowerPC,e500mc@6 {
                         device_type = "cpu";
                         reg = <6>;
                         next-level-cache = <&L2_6>;
@@ -133,7 +134,7 @@
                                 next-level-cache = <&cpc>;
                         };
                 };
-                cpu7: PowerPC,4080@7 {
+                cpu7: PowerPC,e500mc@7 {
                         device_type = "cpu";
                         reg = <7>;
                         next-level-cache = <&L2_7>;
@@ -143,6 +144,99 @@
                 };
         };
 
+        dcsr: dcsr@f00000000 {
+                #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>;
+                        interrupt-parent = <&mpic>;
+                        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,p4080-dcsr-dpaa", "fsl,dcsr-dpaa";
+                        reg = <0x9000 0x1000>;
+                };
+                dcsr-ocn@11000 {
+                        compatible = "fsl,p4080-dcsr-ocn", "fsl,dcsr-ocn";
+                        reg = <0x11000 0x1000>;
+                };
+                dcsr-ddr@12000 {
+                        compatible = "fsl,dcsr-ddr";
+                        dev-handle = <&ddr1>;
+                        reg = <0x12000 0x1000>;
+                };
+                dcsr-ddr@13000 {
+                        compatible = "fsl,dcsr-ddr";
+                        dev-handle = <&ddr2>;
+                        reg = <0x13000 0x1000>;
+                };
+                dcsr-nal@18000 {
+                        compatible = "fsl,p4080-dcsr-nal", "fsl,dcsr-nal";
+                        reg = <0x18000 0x1000>;
+                };
+                dcsr-rcpm@22000 {
+                        compatible = "fsl,p4080-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@42000 {
+                        compatible = "fsl,dcsr-e500mc-sb-proxy", "fsl,dcsr-cpu-sb-proxy";
+                        cpu-handle = <&cpu2>;
+                        reg = <0x42000 0x1000>;
+                };
+                dcsr-cpu-sb-proxy@43000 {
+                        compatible = "fsl,dcsr-e500mc-sb-proxy", "fsl,dcsr-cpu-sb-proxy";
+                        cpu-handle = <&cpu3>;
+                        reg = <0x43000 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: soc@ffe000000 {
                 #address-cells = <1>;
                 #size-cells = <1>;
@@ -162,13 +256,13 @@
                         fsl,num-laws = <32>;
                 };
 
-                memory-controller@8000 {
+                ddr1: memory-controller@8000 {
                         compatible = "fsl,qoriq-memory-controller-v4.4", "fsl,qoriq-memory-controller";
                         reg = <0x8000 0x1000>;
                         interrupts = <16 2 1 23>;
                 };
 
-                memory-controller@9000 {
+                ddr2: memory-controller@9000 {
                         compatible = "fsl,qoriq-memory-controller-v4.4","fsl,qoriq-memory-controller";
                         reg = <0x9000 0x1000>;
                         interrupts = <16 2 1 22>;
diff --git a/arch/powerpc/boot/dts/p5020ds.dts b/arch/powerpc/boot/dts/p5020ds.dts
index 8366e2fd2fba..e6d40999ccd7 100644
--- a/arch/powerpc/boot/dts/p5020ds.dts
+++ b/arch/powerpc/boot/dts/p5020ds.dts
@@ -45,6 +45,10 @@
                 device_type = "memory";
         };
 
+        dcsr: dcsr@f00000000 {
+                ranges = <0x00000000 0xf 0x00000000 0x01008000>;
+        };
+
         soc: soc@ffe000000 {
                 spi@110000 {
                         flash@0 {
@@ -147,8 +151,8 @@
                 };
 
                 board-control@3,0 {
-                        compatible = "fsl,p5020ds-pixis";
-                        reg = <3 0 0x20>;
+                        compatible = "fsl,p5020ds-fpga", "fsl,fpga-ngpixis";
+                        reg = <3 0 0x30>;
                 };
         };
 
diff --git a/arch/powerpc/boot/dts/p5020si.dtsi b/arch/powerpc/boot/dts/p5020si.dtsi
index 5e6048ec55bb..e7948ad71fa3 100644
--- a/arch/powerpc/boot/dts/p5020si.dtsi
+++ b/arch/powerpc/boot/dts/p5020si.dtsi
@@ -42,6 +42,7 @@
 
         aliases {
                 ccsr = &soc;
+                dcsr = &dcsr;
 
                 serial0 = &serial0;
                 serial1 = &serial1;
@@ -98,6 +99,69 @@
                 };
         };
 
+        dcsr: dcsr@f00000000 {
+                #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>;
+                        interrupt-parent = <&mpic>;
+                        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,p5020-dcsr-dpaa", "fsl,dcsr-dpaa";
+                        reg = <0x9000 0x1000>;
+                };
+                dcsr-ocn@11000 {
+                        compatible = "fsl,p5020-dcsr-ocn", "fsl,dcsr-ocn";
+                        reg = <0x11000 0x1000>;
+                };
+                dcsr-ddr@12000 {
+                        compatible = "fsl,dcsr-ddr";
+                        dev-handle = <&ddr1>;
+                        reg = <0x12000 0x1000>;
+                };
+                dcsr-ddr@13000 {
+                        compatible = "fsl,dcsr-ddr";
+                        dev-handle = <&ddr2>;
+                        reg = <0x13000 0x1000>;
+                };
+                dcsr-nal@18000 {
+                        compatible = "fsl,p5020-dcsr-nal", "fsl,dcsr-nal";
+                        reg = <0x18000 0x1000>;
+                };
+                dcsr-rcpm@22000 {
+                        compatible = "fsl,p5020-dcsr-rcpm", "fsl,dcsr-rcpm";
+                        reg = <0x22000 0x1000>;
+                };
+                dcsr-cpu-sb-proxy@40000 {
+                        compatible = "fsl,dcsr-e5500-sb-proxy", "fsl,dcsr-cpu-sb-proxy";
+                        cpu-handle = <&cpu0>;
+                        reg = <0x40000 0x1000>;
+                };
+                dcsr-cpu-sb-proxy@41000 {
+                        compatible = "fsl,dcsr-e5500-sb-proxy", "fsl,dcsr-cpu-sb-proxy";
+                        cpu-handle = <&cpu1>;
+                        reg = <0x41000 0x1000>;
+                };
+        };
+
         soc: soc@ffe000000 {
                 #address-cells = <1>;
                 #size-cells = <1>;
@@ -117,13 +181,13 @@
                         fsl,num-laws = <32>;
                 };
 
-                memory-controller@8000 {
+                ddr1: memory-controller@8000 {
                         compatible = "fsl,qoriq-memory-controller-v4.5", "fsl,qoriq-memory-controller";
                         reg = <0x8000 0x1000>;
                         interrupts = <16 2 1 23>;
                 };
 
-                memory-controller@9000 {
+                ddr2: memory-controller@9000 {
                         compatible = "fsl,qoriq-memory-controller-v4.5", "fsl,qoriq-memory-controller";
                         reg = <0x9000 0x1000>;
                         interrupts = <16 2 1 22>;
diff --git a/arch/powerpc/boot/dts/sbc8560.dts b/arch/powerpc/boot/dts/sbc8560.dts
index 9e13ed8a1193..72078eb15616 100644
--- a/arch/powerpc/boot/dts/sbc8560.dts
+++ b/arch/powerpc/boot/dts/sbc8560.dts
@@ -331,7 +331,7 @@
         };
 
         localbus@ff705000 {
-                compatible = "fsl,mpc8560-localbus";
+                compatible = "fsl,mpc8560-localbus", "simple-bus";
                 #address-cells = <2>;
                 #size-cells = <1>;
                 reg = <0xff705000 0x100>;       // BRx, ORx, etc.
diff --git a/arch/powerpc/boot/dts/yosemite.dts b/arch/powerpc/boot/dts/yosemite.dts
index 64923245f0e5..30bb4753577a 100644
--- a/arch/powerpc/boot/dts/yosemite.dts
+++ b/arch/powerpc/boot/dts/yosemite.dts
@@ -138,6 +138,42 @@
                                 clock-frequency = <0>; /* Filled in by zImage */
                                 interrupts = <0x5 0x1>;
                                 interrupt-parent = <&UIC1>;
+
+                                nor_flash@0,0 {
+                                        compatible = "amd,s29gl256n", "cfi-flash";
+                                        bank-width = <2>;
+                                        reg = <0x00000000 0x00000000 0x04000000>;
+                                        #address-cells = <1>;
+                                        #size-cells = <1>;
+                                        partition@0 {
+                                                label = "kernel";
+                                                reg = <0x00000000 0x001e0000>;
+                                        };
+                                        partition@1e0000 {
+                                                label = "dtb";
+                                                reg = <0x001e0000 0x00020000>;
+                                        };
+                                        partition@200000 {
+                                                label = "ramdisk";
+                                                reg = <0x00200000 0x01400000>;
+                                        };
+                                        partition@1600000 {
+                                                label = "jffs2";
+                                                reg = <0x01600000 0x00400000>;
+                                        };
+                                        partition@1a00000 {
+                                                label = "user";
+                                                reg = <0x01a00000 0x02540000>;
+                                        };
+                                        partition@3f40000 {
+                                                label = "env";
+                                                reg = <0x03f40000 0x00040000>;
+                                        };
+                                        partition@3f80000 {
+                                                label = "u-boot";
+                                                reg = <0x03f80000 0x00080000>;
+                                        };
+                                };
                         };
 
                         UART0: serial@ef600300 {
diff --git a/arch/powerpc/configs/40x/acadia_defconfig b/arch/powerpc/configs/40x/acadia_defconfig
index 4182c772340b..ed3bab72a834 100644
--- a/arch/powerpc/configs/40x/acadia_defconfig
+++ b/arch/powerpc/configs/40x/acadia_defconfig
@@ -44,12 +44,13 @@ CONFIG_BLK_DEV_RAM=y
 CONFIG_BLK_DEV_RAM_SIZE=35000
 # CONFIG_MISC_DEVICES is not set
 CONFIG_NETDEVICES=y
-CONFIG_NET_ETHERNET=y
+CONFIG_ETHERNET=y
+CONFIG_NET_VENDOR_IBM=y
 CONFIG_MII=y
-CONFIG_IBM_NEW_EMAC=y
-CONFIG_IBM_NEW_EMAC_RXB=256
-CONFIG_IBM_NEW_EMAC_TXB=256
-CONFIG_IBM_NEW_EMAC_DEBUG=y
+CONFIG_IBM_EMAC=y
+CONFIG_IBM_EMAC_RXB=256
+CONFIG_IBM_EMAC_TXB=256
+CONFIG_IBM_EMAC_DEBUG=y
 # CONFIG_NETDEV_1000 is not set
 # CONFIG_NETDEV_10000 is not set
 # CONFIG_INPUT is not set
diff --git a/arch/powerpc/configs/40x/ep405_defconfig b/arch/powerpc/configs/40x/ep405_defconfig
index 2dbb293163f5..17582a3420fb 100644
--- a/arch/powerpc/configs/40x/ep405_defconfig
+++ b/arch/powerpc/configs/40x/ep405_defconfig
@@ -42,8 +42,9 @@ CONFIG_PROC_DEVICETREE=y
 CONFIG_BLK_DEV_RAM=y
 CONFIG_BLK_DEV_RAM_SIZE=35000
 CONFIG_NETDEVICES=y
-CONFIG_NET_ETHERNET=y
-CONFIG_IBM_NEW_EMAC=y
+CONFIG_ETHERNET=y
+CONFIG_NET_VENDOR_IBM=y
+CONFIG_IBM_EMAC=y
 # CONFIG_INPUT is not set
 # CONFIG_SERIO is not set
 # CONFIG_VT is not set
diff --git a/arch/powerpc/configs/40x/hcu4_defconfig b/arch/powerpc/configs/40x/hcu4_defconfig
deleted file mode 100644
index ebeb4accad65..000000000000
--- a/arch/powerpc/configs/40x/hcu4_defconfig
+++ /dev/null
@@ -1,80 +0,0 @@
-CONFIG_40x=y
-CONFIG_EXPERIMENTAL=y
-CONFIG_SYSVIPC=y
-CONFIG_POSIX_MQUEUE=y
-CONFIG_LOG_BUF_SHIFT=14
-CONFIG_BLK_DEV_INITRD=y
-# CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
-CONFIG_EXPERT=y
-CONFIG_KALLSYMS_ALL=y
-CONFIG_KALLSYMS_EXTRA_PASS=y
-CONFIG_MODULES=y
-CONFIG_MODULE_UNLOAD=y
-# CONFIG_BLK_DEV_BSG is not set
-CONFIG_HCU4=y
-# CONFIG_WALNUT is not set
-CONFIG_SPARSE_IRQ=y
-CONFIG_PCI=y
-CONFIG_NET=y
-CONFIG_PACKET=y
-CONFIG_UNIX=y
-CONFIG_INET=y
-CONFIG_IP_PNP=y
-CONFIG_IP_PNP_DHCP=y
-CONFIG_IP_PNP_BOOTP=y
-# CONFIG_INET_XFRM_MODE_TRANSPORT is not set
-# CONFIG_INET_XFRM_MODE_TUNNEL is not set
-# CONFIG_INET_XFRM_MODE_BEET is not set
-# CONFIG_INET_LRO is not set
-# CONFIG_IPV6 is not set
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
-CONFIG_CONNECTOR=y
-CONFIG_MTD=y
-CONFIG_MTD_PARTITIONS=y
-CONFIG_MTD_CMDLINE_PARTS=y
-CONFIG_MTD_OF_PARTS=y
-CONFIG_MTD_CHAR=y
-CONFIG_MTD_BLOCK=m
-CONFIG_MTD_CFI=y
-CONFIG_MTD_JEDECPROBE=y
-CONFIG_MTD_CFI_AMDSTD=y
-CONFIG_MTD_PHYSMAP_OF=y
-CONFIG_PROC_DEVICETREE=y
-CONFIG_BLK_DEV_RAM=y
-CONFIG_BLK_DEV_RAM_SIZE=35000
-CONFIG_NETDEVICES=y
-CONFIG_NET_ETHERNET=y
-CONFIG_IBM_NEW_EMAC=y
-# CONFIG_INPUT 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_EXTENDED=y
-CONFIG_SERIAL_8250_SHARE_IRQ=y
-CONFIG_SERIAL_OF_PLATFORM=y
-# CONFIG_HW_RANDOM is not set
-# CONFIG_HWMON is not set
-CONFIG_VIDEO_OUTPUT_CONTROL=m
-# CONFIG_USB_SUPPORT is not set
-CONFIG_EXT2_FS=y
-CONFIG_INOTIFY=y
-CONFIG_PROC_KCORE=y
-CONFIG_TMPFS=y
-CONFIG_CRAMFS=y
-CONFIG_NFS_FS=y
-CONFIG_NFS_V3=y
-CONFIG_ROOT_NFS=y
-CONFIG_MAGIC_SYSRQ=y
-CONFIG_DEBUG_FS=y
-CONFIG_DEBUG_KERNEL=y
-CONFIG_DETECT_HUNG_TASK=y
-# CONFIG_RCU_CPU_STALL_DETECTOR is not set
-CONFIG_SYSCTL_SYSCALL_CHECK=y
-CONFIG_CRYPTO=y
-CONFIG_CRYPTO_CBC=y
-CONFIG_CRYPTO_ECB=y
-CONFIG_CRYPTO_PCBC=y
-CONFIG_CRYPTO_MD5=y
-CONFIG_CRYPTO_DES=y
-# CONFIG_CRYPTO_ANSI_CPRNG is not set
diff --git a/arch/powerpc/configs/40x/kilauea_defconfig b/arch/powerpc/configs/40x/kilauea_defconfig
index 532ea9d93a15..f2d4be936e08 100644
--- a/arch/powerpc/configs/40x/kilauea_defconfig
+++ b/arch/powerpc/configs/40x/kilauea_defconfig
@@ -51,10 +51,11 @@ CONFIG_BLK_DEV_RAM=y
 CONFIG_BLK_DEV_RAM_SIZE=35000
 # CONFIG_MISC_DEVICES is not set
 CONFIG_NETDEVICES=y
-CONFIG_NET_ETHERNET=y
-CONFIG_IBM_NEW_EMAC=y
-CONFIG_IBM_NEW_EMAC_RXB=256
-CONFIG_IBM_NEW_EMAC_TXB=256
+CONFIG_ETHERNET=y
+CONFIG_NET_VENDOR_IBM=y
+CONFIG_IBM_EMAC=y
+CONFIG_IBM_EMAC_RXB=256
+CONFIG_IBM_EMAC_TXB=256
 # CONFIG_NETDEV_1000 is not set
 # CONFIG_NETDEV_10000 is not set
 # CONFIG_INPUT is not set
diff --git a/arch/powerpc/configs/40x/makalu_defconfig b/arch/powerpc/configs/40x/makalu_defconfig
index 3c142ac1b344..42b979355f9b 100644
--- a/arch/powerpc/configs/40x/makalu_defconfig
+++ b/arch/powerpc/configs/40x/makalu_defconfig
@@ -43,10 +43,11 @@ CONFIG_BLK_DEV_RAM=y
 CONFIG_BLK_DEV_RAM_SIZE=35000
 # CONFIG_MISC_DEVICES is not set
 CONFIG_NETDEVICES=y
-CONFIG_NET_ETHERNET=y
-CONFIG_IBM_NEW_EMAC=y
-CONFIG_IBM_NEW_EMAC_RXB=256
-CONFIG_IBM_NEW_EMAC_TXB=256
+CONFIG_ETHERNET=y
+CONFIG_NET_VENDOR_IBM=y
+CONFIG_IBM_EMAC=y
+CONFIG_IBM_EMAC_RXB=256
+CONFIG_IBM_EMAC_TXB=256
 # CONFIG_NETDEV_1000 is not set
 # CONFIG_NETDEV_10000 is not set
 # CONFIG_INPUT is not set
diff --git a/arch/powerpc/configs/40x/walnut_defconfig b/arch/powerpc/configs/40x/walnut_defconfig
index ff57d4828ffc..aa1a4cac3708 100644
--- a/arch/powerpc/configs/40x/walnut_defconfig
+++ b/arch/powerpc/configs/40x/walnut_defconfig
@@ -40,8 +40,9 @@ CONFIG_PROC_DEVICETREE=y
 CONFIG_BLK_DEV_RAM=y
 CONFIG_BLK_DEV_RAM_SIZE=35000
 CONFIG_NETDEVICES=y
-CONFIG_NET_ETHERNET=y
-CONFIG_IBM_NEW_EMAC=y
+CONFIG_ETHERNET=y
+CONFIG_NET_VENDOR_IBM=y
+CONFIG_IBM_EMAC=y
 # CONFIG_INPUT is not set
 # CONFIG_SERIO is not set
 # CONFIG_VT is not set
diff --git a/arch/powerpc/configs/44x/arches_defconfig b/arch/powerpc/configs/44x/arches_defconfig
index 3ed16d5c909d..329f9a3b892e 100644
--- a/arch/powerpc/configs/44x/arches_defconfig
+++ b/arch/powerpc/configs/44x/arches_defconfig
@@ -44,10 +44,11 @@ CONFIG_BLK_DEV_RAM=y
 CONFIG_BLK_DEV_RAM_SIZE=35000
 # CONFIG_MISC_DEVICES is not set
 CONFIG_NETDEVICES=y
-CONFIG_NET_ETHERNET=y
-CONFIG_IBM_NEW_EMAC=y
-CONFIG_IBM_NEW_EMAC_RXB=256
-CONFIG_IBM_NEW_EMAC_TXB=256
+CONFIG_ETHERNET=y
+CONFIG_NET_VENDOR_IBM=y
+CONFIG_IBM_EMAC=y
+CONFIG_IBM_EMAC_RXB=256
+CONFIG_IBM_EMAC_TXB=256
 # CONFIG_NETDEV_1000 is not set
 # CONFIG_NETDEV_10000 is not set
 # CONFIG_INPUT is not set
diff --git a/arch/powerpc/configs/44x/bamboo_defconfig b/arch/powerpc/configs/44x/bamboo_defconfig
index b1b7d2c5c059..cef7d62560c4 100644
--- a/arch/powerpc/configs/44x/bamboo_defconfig
+++ b/arch/powerpc/configs/44x/bamboo_defconfig
@@ -32,8 +32,9 @@ CONFIG_PROC_DEVICETREE=y
 CONFIG_BLK_DEV_RAM=y
 CONFIG_BLK_DEV_RAM_SIZE=35000
 CONFIG_NETDEVICES=y
-CONFIG_NET_ETHERNET=y
-CONFIG_IBM_NEW_EMAC=y
+CONFIG_ETHERNET=y
+CONFIG_NET_VENDOR_IBM=y
+CONFIG_IBM_EMAC=y
 # CONFIG_INPUT is not set
 # CONFIG_SERIO is not set
 # CONFIG_VT is not set
diff --git a/arch/powerpc/configs/44x/bluestone_defconfig b/arch/powerpc/configs/44x/bluestone_defconfig
index 30a0a8e08fdd..20c8d26d7fc0 100644
--- a/arch/powerpc/configs/44x/bluestone_defconfig
+++ b/arch/powerpc/configs/44x/bluestone_defconfig
@@ -38,10 +38,11 @@ CONFIG_PROC_DEVICETREE=y
 CONFIG_BLK_DEV_RAM=y
 CONFIG_BLK_DEV_RAM_SIZE=35000
 CONFIG_NETDEVICES=y
-CONFIG_NET_ETHERNET=y
-CONFIG_IBM_NEW_EMAC=y
-CONFIG_IBM_NEW_EMAC_RXB=256
-CONFIG_IBM_NEW_EMAC_TXB=256
+CONFIG_ETHERNET=y
+CONFIG_NET_VENDOR_IBM=y
+CONFIG_IBM_EMAC=y
+CONFIG_IBM_EMAC_RXB=256
+CONFIG_IBM_EMAC_TXB=256
 CONFIG_SERIAL_8250=y
 CONFIG_SERIAL_8250_CONSOLE=y
 CONFIG_SERIAL_8250_NR_UARTS=2
diff --git a/arch/powerpc/configs/44x/canyonlands_defconfig b/arch/powerpc/configs/44x/canyonlands_defconfig
index a46942aac695..d5be93e6e92d 100644
--- a/arch/powerpc/configs/44x/canyonlands_defconfig
+++ b/arch/powerpc/configs/44x/canyonlands_defconfig
@@ -49,10 +49,11 @@ CONFIG_BLK_DEV_RAM=y
 CONFIG_BLK_DEV_RAM_SIZE=35000
 # CONFIG_MISC_DEVICES is not set
 CONFIG_NETDEVICES=y
-CONFIG_NET_ETHERNET=y
-CONFIG_IBM_NEW_EMAC=y
-CONFIG_IBM_NEW_EMAC_RXB=256
-CONFIG_IBM_NEW_EMAC_TXB=256
+CONFIG_ETHERNET=y
+CONFIG_NET_VENDOR_IBM=y
+CONFIG_IBM_EMAC=y
+CONFIG_IBM_EMAC_RXB=256
+CONFIG_IBM_EMAC_TXB=256
 # CONFIG_NETDEV_1000 is not set
 # CONFIG_NETDEV_10000 is not set
 # CONFIG_INPUT is not set
diff --git a/arch/powerpc/configs/44x/ebony_defconfig b/arch/powerpc/configs/44x/ebony_defconfig
index 07d77e51f1ba..f9269fc4ffcc 100644
--- a/arch/powerpc/configs/44x/ebony_defconfig
+++ b/arch/powerpc/configs/44x/ebony_defconfig
@@ -40,8 +40,9 @@ CONFIG_PROC_DEVICETREE=y
 CONFIG_BLK_DEV_RAM=y
 CONFIG_BLK_DEV_RAM_SIZE=35000
 CONFIG_NETDEVICES=y
-CONFIG_NET_ETHERNET=y
-CONFIG_IBM_NEW_EMAC=y
+CONFIG_ETHERNET=y
+CONFIG_NET_VENDOR_IBM=y
+CONFIG_IBM_EMAC=y
 # CONFIG_INPUT is not set
 # CONFIG_SERIO is not set
 # CONFIG_VT is not set
diff --git a/arch/powerpc/configs/44x/eiger_defconfig b/arch/powerpc/configs/44x/eiger_defconfig
index 2ce7e9aff09e..9be089038fd7 100644
--- a/arch/powerpc/configs/44x/eiger_defconfig
+++ b/arch/powerpc/configs/44x/eiger_defconfig
@@ -55,10 +55,11 @@ CONFIG_FUSION=y
 CONFIG_FUSION_SAS=y
 CONFIG_I2O=y
 CONFIG_NETDEVICES=y
-CONFIG_NET_ETHERNET=y
-CONFIG_IBM_NEW_EMAC=y
-CONFIG_IBM_NEW_EMAC_RXB=256
-CONFIG_IBM_NEW_EMAC_TXB=256
+CONFIG_ETHERNET=y
+CONFIG_NET_VENDOR_IBM=y
+CONFIG_IBM_EMAC=y
+CONFIG_IBM_EMAC_RXB=256
+CONFIG_IBM_EMAC_TXB=256
 CONFIG_E1000E=y
 # CONFIG_NETDEV_10000 is not set
 # CONFIG_INPUT is not set
diff --git a/arch/powerpc/configs/44x/icon_defconfig b/arch/powerpc/configs/44x/icon_defconfig
index 18730ff9de7c..82f73035a7ce 100644
--- a/arch/powerpc/configs/44x/icon_defconfig
+++ b/arch/powerpc/configs/44x/icon_defconfig
@@ -56,8 +56,9 @@ CONFIG_FUSION_SAS=y
 CONFIG_FUSION_CTL=y
 CONFIG_FUSION_LOGGING=y
 CONFIG_NETDEVICES=y
-CONFIG_NET_ETHERNET=y
-CONFIG_IBM_NEW_EMAC=y
+CONFIG_ETHERNET=y
+CONFIG_NET_VENDOR_IBM=y
+CONFIG_IBM_EMAC=y
 # CONFIG_NETDEV_1000 is not set
 # CONFIG_NETDEV_10000 is not set
 # CONFIG_WLAN is not set
diff --git a/arch/powerpc/configs/44x/katmai_defconfig b/arch/powerpc/configs/44x/katmai_defconfig
index 34c09144a699..109562c3c6be 100644
--- a/arch/powerpc/configs/44x/katmai_defconfig
+++ b/arch/powerpc/configs/44x/katmai_defconfig
@@ -42,8 +42,9 @@ CONFIG_BLK_DEV_RAM=y
 CONFIG_BLK_DEV_RAM_SIZE=35000
 CONFIG_MACINTOSH_DRIVERS=y
 CONFIG_NETDEVICES=y
-CONFIG_NET_ETHERNET=y
-CONFIG_IBM_NEW_EMAC=y
+CONFIG_ETHERNET=y
+CONFIG_NET_VENDOR_IBM=y
+CONFIG_IBM_EMAC=y
 # CONFIG_INPUT is not set
 # CONFIG_SERIO is not set
 # CONFIG_VT is not set
diff --git a/arch/powerpc/configs/44x/redwood_defconfig b/arch/powerpc/configs/44x/redwood_defconfig
index 01cc2b1a7f9a..48802811da76 100644
--- a/arch/powerpc/configs/44x/redwood_defconfig
+++ b/arch/powerpc/configs/44x/redwood_defconfig
@@ -53,11 +53,12 @@ CONFIG_FUSION=y
 CONFIG_FUSION_SAS=y
 CONFIG_I2O=y
 CONFIG_NETDEVICES=y
-CONFIG_NET_ETHERNET=y
-CONFIG_IBM_NEW_EMAC=y
-CONFIG_IBM_NEW_EMAC_RXB=256
-CONFIG_IBM_NEW_EMAC_TXB=256
-CONFIG_IBM_NEW_EMAC_DEBUG=y
+CONFIG_ETHERNET=y
+CONFIG_NET_VENDOR_IBM=y
+CONFIG_IBM_EMAC=y
+CONFIG_IBM_EMAC_RXB=256
+CONFIG_IBM_EMAC_TXB=256
+CONFIG_IBM_EMAC_DEBUG=y
 CONFIG_E1000E=y
 # CONFIG_NETDEV_10000 is not set
 # CONFIG_INPUT is not set
diff --git a/arch/powerpc/configs/44x/sam440ep_defconfig b/arch/powerpc/configs/44x/sam440ep_defconfig
index dfcffede16ad..ca088cd581af 100644
--- a/arch/powerpc/configs/44x/sam440ep_defconfig
+++ b/arch/powerpc/configs/44x/sam440ep_defconfig
@@ -44,8 +44,9 @@ CONFIG_ATA=y
 # CONFIG_SATA_PMP is not set
 CONFIG_SATA_SIL=y
 CONFIG_NETDEVICES=y
-CONFIG_NET_ETHERNET=y
-CONFIG_IBM_NEW_EMAC=y
+CONFIG_ETHERNET=y
+CONFIG_NET_VENDOR_IBM=y
+CONFIG_IBM_EMAC=y
 # CONFIG_NETDEV_1000 is not set
 # CONFIG_NETDEV_10000 is not set
 CONFIG_INPUT_FF_MEMLESS=m
diff --git a/arch/powerpc/configs/44x/sequoia_defconfig b/arch/powerpc/configs/44x/sequoia_defconfig
index 47e399f2892f..b7a653b626db 100644
--- a/arch/powerpc/configs/44x/sequoia_defconfig
+++ b/arch/powerpc/configs/44x/sequoia_defconfig
@@ -46,8 +46,9 @@ CONFIG_PROC_DEVICETREE=y
 CONFIG_BLK_DEV_RAM=y
 CONFIG_BLK_DEV_RAM_SIZE=35000
 CONFIG_NETDEVICES=y
-CONFIG_NET_ETHERNET=y
-CONFIG_IBM_NEW_EMAC=y
+CONFIG_ETHERNET=y
+CONFIG_NET_VENDOR_IBM=y
+CONFIG_IBM_EMAC=y
 # CONFIG_INPUT is not set
 # CONFIG_SERIO is not set
 # CONFIG_VT is not set
diff --git a/arch/powerpc/configs/44x/taishan_defconfig b/arch/powerpc/configs/44x/taishan_defconfig
index a6a002ed5681..30de97f158a4 100644
--- a/arch/powerpc/configs/44x/taishan_defconfig
+++ b/arch/powerpc/configs/44x/taishan_defconfig
@@ -40,8 +40,9 @@ CONFIG_BLK_DEV_RAM=y
 CONFIG_BLK_DEV_RAM_SIZE=35000
 CONFIG_MACINTOSH_DRIVERS=y
 CONFIG_NETDEVICES=y
-CONFIG_NET_ETHERNET=y
-CONFIG_IBM_NEW_EMAC=y
+CONFIG_ETHERNET=y
+CONFIG_NET_VENDOR_IBM=y
+CONFIG_IBM_EMAC=y
 # CONFIG_INPUT is not set
 # CONFIG_SERIO is not set
 # CONFIG_VT is not set
diff --git a/arch/powerpc/configs/44x/warp_defconfig b/arch/powerpc/configs/44x/warp_defconfig
index abf74dc1f79c..105bc56f4b2b 100644
--- a/arch/powerpc/configs/44x/warp_defconfig
+++ b/arch/powerpc/configs/44x/warp_defconfig
@@ -54,9 +54,10 @@ CONFIG_BLK_DEV_SD=y
 CONFIG_SCSI_SPI_ATTRS=y
 # CONFIG_SCSI_LOWLEVEL is not set
 CONFIG_NETDEVICES=y
-CONFIG_NET_ETHERNET=y
+CONFIG_ETHERNET=y
+CONFIG_NET_VENDOR_IBM=y
 CONFIG_MII=y
-CONFIG_IBM_NEW_EMAC=y
+CONFIG_IBM_EMAC=y
 # CONFIG_NETDEV_1000 is not set
 # CONFIG_NETDEV_10000 is not set
 # CONFIG_INPUT is not set
diff --git a/arch/powerpc/configs/52xx/tqm5200_defconfig b/arch/powerpc/configs/52xx/tqm5200_defconfig
index 959cd2cfc275..716a37be16e3 100644
--- a/arch/powerpc/configs/52xx/tqm5200_defconfig
+++ b/arch/powerpc/configs/52xx/tqm5200_defconfig
@@ -1,9 +1,10 @@
 CONFIG_EXPERIMENTAL=y
 CONFIG_SYSVIPC=y
+CONFIG_SPARSE_IRQ=y
 CONFIG_LOG_BUF_SHIFT=14
 CONFIG_BLK_DEV_INITRD=y
 # CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
-CONFIG_EXPERT=y
+CONFIG_EMBEDDED=y
 # CONFIG_SYSCTL_SYSCALL is not set
 # CONFIG_KALLSYMS is not set
 # CONFIG_EPOLL is not set
@@ -17,7 +18,6 @@ CONFIG_PPC_MPC5200_SIMPLE=y
 CONFIG_PPC_MPC5200_BUGFIX=y
 # CONFIG_PPC_PMAC is not set
 CONFIG_PPC_BESTCOMM=y
-CONFIG_SPARSE_IRQ=y
 CONFIG_PM=y
 # CONFIG_PCI is not set
 CONFIG_NET=y
@@ -38,17 +38,18 @@ CONFIG_MTD=y
 CONFIG_MTD_CONCAT=y
 CONFIG_MTD_PARTITIONS=y
 CONFIG_MTD_CMDLINE_PARTS=y
+CONFIG_MTD_OF_PARTS=y
 CONFIG_MTD_CHAR=y
 CONFIG_MTD_BLOCK=y
 CONFIG_MTD_CFI=y
 CONFIG_MTD_CFI_AMDSTD=y
 CONFIG_MTD_ROM=y
 CONFIG_MTD_PHYSMAP_OF=y
+CONFIG_MTD_PLATRAM=y
 CONFIG_PROC_DEVICETREE=y
 CONFIG_BLK_DEV_LOOP=y
 CONFIG_BLK_DEV_RAM=y
 CONFIG_BLK_DEV_RAM_SIZE=32768
-# CONFIG_MISC_DEVICES is not set
 CONFIG_BLK_DEV_SD=y
 CONFIG_CHR_DEV_SG=y
 CONFIG_ATA=y
@@ -56,13 +57,11 @@ CONFIG_PATA_MPC52xx=y
 CONFIG_PATA_PLATFORM=y
 CONFIG_NETDEVICES=y
 CONFIG_LXT_PHY=y
+CONFIG_FIXED_PHY=y
 CONFIG_NET_ETHERNET=y
 CONFIG_FEC_MPC52xx=y
 # CONFIG_NETDEV_1000 is not set
 # CONFIG_NETDEV_10000 is not set
-# CONFIG_INPUT is not set
-# CONFIG_SERIO is not set
-# CONFIG_VT is not set
 CONFIG_SERIAL_MPC52xx=y
 CONFIG_SERIAL_MPC52xx_CONSOLE=y
 CONFIG_SERIAL_MPC52xx_CONSOLE_BAUD=115200
@@ -70,7 +69,13 @@ CONFIG_SERIAL_MPC52xx_CONSOLE_BAUD=115200
 CONFIG_I2C=y
 CONFIG_I2C_CHARDEV=y
 CONFIG_I2C_MPC=y
+CONFIG_SENSORS_LM80=y
 CONFIG_WATCHDOG=y
+CONFIG_MFD_SM501=y
+CONFIG_FB=y
+CONFIG_FB_FOREIGN_ENDIAN=y
+CONFIG_FB_SM501=y
+CONFIG_FRAMEBUFFER_CONSOLE=y
 CONFIG_USB=y
 CONFIG_USB_DEVICEFS=y
 # CONFIG_USB_DEVICE_CLASS is not set
@@ -80,10 +85,10 @@ CONFIG_USB_OHCI_HCD_PPC_OF_BE=y
 CONFIG_USB_STORAGE=y
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_DS1307=y
+CONFIG_RTC_DRV_DS1374=y
 CONFIG_EXT2_FS=y
 CONFIG_EXT3_FS=y
 # CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
-CONFIG_INOTIFY=y
 CONFIG_MSDOS_FS=y
 CONFIG_VFAT_FS=y
 CONFIG_PROC_KCORE=y
@@ -102,7 +107,6 @@ CONFIG_DEBUG_KERNEL=y
 CONFIG_DETECT_HUNG_TASK=y
 # CONFIG_DEBUG_BUGVERBOSE is not set
 CONFIG_DEBUG_INFO=y
-# CONFIG_RCU_CPU_STALL_DETECTOR is not set
 CONFIG_CRYPTO_ECB=y
 CONFIG_CRYPTO_PCBC=y
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
diff --git a/arch/powerpc/configs/85xx/p1023rds_defconfig b/arch/powerpc/configs/85xx/p1023rds_defconfig
index 3ff5a81c709f..c091aaf7685f 100644
--- a/arch/powerpc/configs/85xx/p1023rds_defconfig
+++ b/arch/powerpc/configs/85xx/p1023rds_defconfig
@@ -24,7 +24,7 @@ CONFIG_P1023_RDS=y
 CONFIG_QUICC_ENGINE=y
 CONFIG_QE_GPIO=y
 CONFIG_CPM2=y
-CONFIG_MPC8xxx_GPIO=y
+CONFIG_GPIO_MPC8XXX=y
 CONFIG_HIGHMEM=y
 CONFIG_NO_HZ=y
 CONFIG_HIGH_RES_TIMERS=y
diff --git a/arch/powerpc/configs/85xx/xes_mpc85xx_defconfig b/arch/powerpc/configs/85xx/xes_mpc85xx_defconfig
index 5ea3124518fd..1cd6fcb368e9 100644
--- a/arch/powerpc/configs/85xx/xes_mpc85xx_defconfig
+++ b/arch/powerpc/configs/85xx/xes_mpc85xx_defconfig
@@ -20,7 +20,7 @@ CONFIG_MODULE_FORCE_UNLOAD=y
 CONFIG_MODVERSIONS=y
 # CONFIG_BLK_DEV_BSG is not set
 CONFIG_XES_MPC85xx=y
-CONFIG_MPC8xxx_GPIO=y
+CONFIG_GPIO_MPC8XXX=y
 CONFIG_HIGHMEM=y
 CONFIG_MATH_EMULATION=y
 CONFIG_SPARSE_IRQ=y
diff --git a/arch/powerpc/configs/corenet32_smp_defconfig b/arch/powerpc/configs/corenet32_smp_defconfig
index 4311d02a3bfd..f087de6ec03f 100644
--- a/arch/powerpc/configs/corenet32_smp_defconfig
+++ b/arch/powerpc/configs/corenet32_smp_defconfig
@@ -12,9 +12,7 @@ CONFIG_IKCONFIG=y
 CONFIG_IKCONFIG_PROC=y
 CONFIG_LOG_BUF_SHIFT=14
 CONFIG_BLK_DEV_INITRD=y
-# CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
 CONFIG_KALLSYMS_ALL=y
-CONFIG_KALLSYMS_EXTRA_PASS=y
 CONFIG_EMBEDDED=y
 CONFIG_PERF_EVENTS=y
 CONFIG_SLAB=y
@@ -23,8 +21,9 @@ CONFIG_MODULE_UNLOAD=y
 CONFIG_MODULE_FORCE_UNLOAD=y
 CONFIG_MODVERSIONS=y
 # CONFIG_BLK_DEV_BSG is not set
-CONFIG_P2040_RDB=y
+CONFIG_P2041_RDB=y
 CONFIG_P3041_DS=y
+CONFIG_P3060_QDS=y
 CONFIG_P4080_DS=y
 CONFIG_P5020_DS=y
 CONFIG_HIGHMEM=y
@@ -69,7 +68,6 @@ CONFIG_IPV6=y
 CONFIG_IP_SCTP=m
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_MTD=y
-CONFIG_MTD_PARTITIONS=y
 CONFIG_MTD_CMDLINE_PARTS=y
 CONFIG_MTD_CHAR=y
 CONFIG_MTD_BLOCK=y
@@ -107,7 +105,6 @@ CONFIG_FSL_PQ_MDIO=y
 # CONFIG_INPUT_MOUSE is not set
 CONFIG_SERIO_LIBPS2=y
 # CONFIG_LEGACY_PTYS is not set
-CONFIG_PPC_EPAPR_HV_BYTECHAN=y
 CONFIG_SERIAL_8250=y
 CONFIG_SERIAL_8250_CONSOLE=y
 CONFIG_SERIAL_8250_EXTENDED=y
@@ -136,8 +133,6 @@ 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
@@ -146,7 +141,6 @@ CONFIG_RTC_DRV_DS3232=y
 CONFIG_RTC_DRV_CMOS=y
 CONFIG_UIO=y
 CONFIG_STAGING=y
-# CONFIG_STAGING_EXCLUDE_BUILD is not set
 CONFIG_VIRT_DRIVERS=y
 CONFIG_FSL_HV_MANAGER=y
 CONFIG_EXT2_FS=y
@@ -173,7 +167,6 @@ CONFIG_MAC_PARTITION=y
 CONFIG_NLS_ISO8859_1=y
 CONFIG_NLS_UTF8=m
 CONFIG_MAGIC_SYSRQ=y
-CONFIG_DEBUG_KERNEL=y
 CONFIG_DEBUG_SHIRQ=y
 CONFIG_DETECT_HUNG_TASK=y
 CONFIG_DEBUG_INFO=y
diff --git a/arch/powerpc/configs/corenet64_smp_defconfig b/arch/powerpc/configs/corenet64_smp_defconfig
index c92c204a204b..782822c32d15 100644
--- a/arch/powerpc/configs/corenet64_smp_defconfig
+++ b/arch/powerpc/configs/corenet64_smp_defconfig
@@ -11,10 +11,8 @@ CONFIG_IKCONFIG=y
 CONFIG_IKCONFIG_PROC=y
 CONFIG_LOG_BUF_SHIFT=14
 CONFIG_BLK_DEV_INITRD=y
-# CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
 CONFIG_EXPERT=y
 CONFIG_KALLSYMS_ALL=y
-CONFIG_KALLSYMS_EXTRA_PASS=y
 CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
 CONFIG_MODULE_FORCE_UNLOAD=y
@@ -25,7 +23,6 @@ CONFIG_P5020_DS=y
 CONFIG_NO_HZ=y
 CONFIG_HIGH_RES_TIMERS=y
 CONFIG_BINFMT_MISC=m
-# CONFIG_PCI is not set
 CONFIG_NET=y
 CONFIG_PACKET=y
 CONFIG_UNIX=y
@@ -93,10 +90,8 @@ CONFIG_CRC_T10DIF=y
 CONFIG_CRC_ITU_T=m
 CONFIG_FRAME_WARN=1024
 CONFIG_DEBUG_FS=y
-CONFIG_DEBUG_KERNEL=y
 CONFIG_DETECT_HUNG_TASK=y
 CONFIG_DEBUG_INFO=y
-# CONFIG_RCU_CPU_STALL_DETECTOR is not set
 CONFIG_SYSCTL_SYSCALL_CHECK=y
 CONFIG_VIRQ_DEBUG=y
 CONFIG_CRYPTO_PCBC=m
diff --git a/arch/powerpc/configs/mgcoge_defconfig b/arch/powerpc/configs/mgcoge_defconfig
index 6cb588a7d425..0d36b0e1e268 100644
--- a/arch/powerpc/configs/mgcoge_defconfig
+++ b/arch/powerpc/configs/mgcoge_defconfig
@@ -1,15 +1,22 @@
+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
 CONFIG_BLK_DEV_INITRD=y
-CONFIG_EXPERT=y
+# CONFIG_RD_GZIP is not set
 CONFIG_KALLSYMS_ALL=y
+# CONFIG_PCSPKR_PLATFORM is not set
+CONFIG_EMBEDDED=y
 CONFIG_SLAB=y
 # CONFIG_IOSCHED_CFQ is not set
+# CONFIG_PPC_PMAC is not set
 CONFIG_PPC_82xx=y
 CONFIG_MGCOGE=y
+CONFIG_HIGH_RES_TIMERS=y
 CONFIG_BINFMT_MISC=y
 # CONFIG_SECCOMP is not set
 CONFIG_NET=y
@@ -24,11 +31,10 @@ CONFIG_SYN_COOKIES=y
 # CONFIG_INET_LRO is not set
 # CONFIG_IPV6 is not set
 CONFIG_NETFILTER=y
+CONFIG_TIPC=y
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 # CONFIG_FW_LOADER is not set
 CONFIG_MTD=y
-CONFIG_MTD_CONCAT=y
-CONFIG_MTD_PARTITIONS=y
 CONFIG_MTD_CMDLINE_PARTS=y
 CONFIG_MTD_CHAR=y
 CONFIG_MTD_BLKDEVS=y
@@ -42,7 +48,6 @@ CONFIG_MTD_PHYSMAP_OF=y
 CONFIG_PROC_DEVICETREE=y
 CONFIG_BLK_DEV_LOOP=y
 CONFIG_BLK_DEV_RAM=y
-# CONFIG_MACINTOSH_DRIVERS is not set
 CONFIG_NETDEVICES=y
 CONFIG_FIXED_PHY=y
 CONFIG_NET_ETHERNET=y
@@ -50,6 +55,7 @@ CONFIG_FS_ENET=y
 CONFIG_FS_ENET_MDIO_FCC=y
 # CONFIG_NETDEV_1000 is not set
 # CONFIG_NETDEV_10000 is not set
+# CONFIG_WLAN is not set
 # CONFIG_INPUT is not set
 # CONFIG_SERIO is not set
 # CONFIG_VT is not set
@@ -57,24 +63,24 @@ CONFIG_SERIAL_CPM=y
 CONFIG_SERIAL_CPM_CONSOLE=y
 CONFIG_I2C=y
 CONFIG_I2C_CHARDEV=y
-# CONFIG_I2C_POWERMAC is not set
 CONFIG_I2C_CPM=y
 # CONFIG_HWMON is not set
-# CONFIG_USB_SUPPORT is not set
+CONFIG_USB_GADGET=y
+CONFIG_USB_FSL_USB2=y
+CONFIG_USB_G_SERIAL=y
+CONFIG_UIO=y
+CONFIG_UIO_PDRV=y
 CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
-# CONFIG_EXT3_FS_XATTR is not set
 CONFIG_AUTOFS4_FS=y
 CONFIG_PROC_KCORE=y
 CONFIG_TMPFS=y
 CONFIG_JFFS2_FS=y
 CONFIG_CRAMFS=y
+CONFIG_SQUASHFS=y
 CONFIG_NFS_FS=y
 CONFIG_NFS_V3=y
 CONFIG_ROOT_NFS=y
 CONFIG_PARTITION_ADVANCED=y
-# CONFIG_MAC_PARTITION is not set
 CONFIG_NLS=y
 CONFIG_NLS_CODEPAGE_437=y
 CONFIG_NLS_ASCII=y
@@ -82,7 +88,6 @@ CONFIG_NLS_ISO8859_1=y
 CONFIG_NLS_UTF8=y
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_DEBUG_FS=y
-CONFIG_DEBUG_KERNEL=y
 # CONFIG_SCHED_DEBUG is not set
 CONFIG_DEBUG_INFO=y
 CONFIG_SYSCTL_SYSCALL_CHECK=y
diff --git a/arch/powerpc/configs/mpc512x_defconfig b/arch/powerpc/configs/mpc512x_defconfig
index c02bbb2fddf8..211fcc9ed700 100644
--- a/arch/powerpc/configs/mpc512x_defconfig
+++ b/arch/powerpc/configs/mpc512x_defconfig
@@ -1,9 +1,9 @@
 CONFIG_EXPERIMENTAL=y
 # CONFIG_SWAP is not set
 CONFIG_SYSVIPC=y
+CONFIG_SPARSE_IRQ=y
 CONFIG_LOG_BUF_SHIFT=16
 CONFIG_BLK_DEV_INITRD=y
-# CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
 # CONFIG_COMPAT_BRK is not set
 CONFIG_SLAB=y
 CONFIG_MODULES=y
@@ -13,10 +13,11 @@ CONFIG_MODULE_UNLOAD=y
 # CONFIG_PPC_CHRP is not set
 CONFIG_PPC_MPC512x=y
 CONFIG_MPC5121_ADS=y
+CONFIG_MPC5121_GENERIC=y
+CONFIG_PDM360NG=y
 # CONFIG_PPC_PMAC is not set
 CONFIG_NO_HZ=y
 CONFIG_HZ_1000=y
-CONFIG_SPARSE_IRQ=y
 # CONFIG_MIGRATION is not set
 # CONFIG_SECCOMP is not set
 # CONFIG_PCI is not set
@@ -35,18 +36,16 @@ CONFIG_CAN=y
 CONFIG_CAN_RAW=y
 CONFIG_CAN_BCM=y
 CONFIG_CAN_VCAN=y
-CONFIG_CAN_DEV=y
 CONFIG_CAN_MSCAN=y
 CONFIG_CAN_DEBUG_DEVICES=y
 # CONFIG_WIRELESS is not set
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
+CONFIG_DEVTMPFS=y
+CONFIG_DEVTMPFS_MOUNT=y
 # CONFIG_PREVENT_FIRMWARE_BUILD is not set
 # CONFIG_FIRMWARE_IN_KERNEL is not set
 CONFIG_MTD=y
-CONFIG_MTD_CONCAT=y
-CONFIG_MTD_PARTITIONS=y
 CONFIG_MTD_CMDLINE_PARTS=y
-CONFIG_MTD_OF_PARTS=y
 CONFIG_MTD_CHAR=y
 CONFIG_MTD_BLOCK=y
 CONFIG_MTD_CFI=y
@@ -63,6 +62,7 @@ CONFIG_BLK_DEV_RAM_SIZE=8192
 CONFIG_BLK_DEV_XIP=y
 CONFIG_MISC_DEVICES=y
 CONFIG_EEPROM_AT24=y
+CONFIG_EEPROM_AT25=y
 CONFIG_SCSI=y
 # CONFIG_SCSI_PROC_FS is not set
 CONFIG_BLK_DEV_SD=y
@@ -99,10 +99,14 @@ CONFIG_SERIAL_MPC52xx_CONSOLE_BAUD=115200
 CONFIG_I2C=y
 CONFIG_I2C_CHARDEV=y
 CONFIG_I2C_MPC=y
+CONFIG_SPI=y
+CONFIG_SPI_MPC512x_PSC=y
+CONFIG_GPIOLIB=y
+CONFIG_GPIO_SYSFS=y
+CONFIG_GPIO_MPC8XXX=y
 # CONFIG_HWMON is not set
 CONFIG_MEDIA_SUPPORT=y
 CONFIG_VIDEO_DEV=y
-# CONFIG_VIDEO_ALLOW_V4L1 is not set
 CONFIG_VIDEO_ADV_DEBUG=y
 # CONFIG_VIDEO_HELPER_CHIPS_AUTO is not set
 CONFIG_VIDEO_SAA711X=y
@@ -132,6 +136,5 @@ CONFIG_NLS_CODEPAGE_437=y
 CONFIG_NLS_ISO8859_1=y
 # CONFIG_ENABLE_WARN_DEPRECATED is not set
 # CONFIG_ENABLE_MUST_CHECK is not set
-# CONFIG_RCU_CPU_STALL_DETECTOR is not set
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
 # CONFIG_CRYPTO_HW is not set
diff --git a/arch/powerpc/configs/mpc5200_defconfig b/arch/powerpc/configs/mpc5200_defconfig
index e63f537b854a..2a1320fb2723 100644
--- a/arch/powerpc/configs/mpc5200_defconfig
+++ b/arch/powerpc/configs/mpc5200_defconfig
@@ -88,6 +88,18 @@ CONFIG_FB_RADEON=y
 # CONFIG_VGA_CONSOLE is not set
 CONFIG_FRAMEBUFFER_CONSOLE=y
 CONFIG_LOGO=y
+CONFIG_SOUND=y
+CONFIG_SND=y
+# CONFIG_SND_SUPPORT_OLD_API is not set
+# CONFIG_SND_DRIVERS is not set
+# CONFIG_SND_PCI is not set
+# CONFIG_SND_PPC is not set
+# CONFIG_SND_SPI is not set
+# CONFIG_SND_USB is not set
+CONFIG_SND_SOC=y
+CONFIG_SND_SOC_MPC5200_I2S=y
+CONFIG_SND_MPC52xx_SOC_PCM030=y
+CONFIG_SND_MPC52xx_SOC_EFIKA=y
 CONFIG_HID_DRAGONRISE=y
 CONFIG_HID_GYRATION=y
 CONFIG_HID_TWINHAN=y
diff --git a/arch/powerpc/configs/mpc85xx_defconfig b/arch/powerpc/configs/mpc85xx_defconfig
index a3467bfb7671..a1e5a178a4ac 100644
--- a/arch/powerpc/configs/mpc85xx_defconfig
+++ b/arch/powerpc/configs/mpc85xx_defconfig
@@ -10,10 +10,8 @@ CONFIG_IKCONFIG=y
 CONFIG_IKCONFIG_PROC=y
 CONFIG_LOG_BUF_SHIFT=14
 CONFIG_BLK_DEV_INITRD=y
-# CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
 CONFIG_EXPERT=y
 CONFIG_KALLSYMS_ALL=y
-CONFIG_KALLSYMS_EXTRA_PASS=y
 CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
 CONFIG_MODULE_FORCE_UNLOAD=y
@@ -41,7 +39,6 @@ CONFIG_TQM8560=y
 CONFIG_SBC8548=y
 CONFIG_QUICC_ENGINE=y
 CONFIG_QE_GPIO=y
-CONFIG_MPC8xxx_GPIO=y
 CONFIG_HIGHMEM=y
 CONFIG_NO_HZ=y
 CONFIG_HIGH_RES_TIMERS=y
@@ -123,6 +120,7 @@ CONFIG_NVRAM=y
 CONFIG_I2C=y
 CONFIG_I2C_CPM=m
 CONFIG_I2C_MPC=y
+CONFIG_GPIO_MPC8XXX=y
 # CONFIG_HWMON is not set
 CONFIG_VIDEO_OUTPUT_CONTROL=y
 CONFIG_FB=y
@@ -206,7 +204,6 @@ CONFIG_PARTITION_ADVANCED=y
 CONFIG_MAC_PARTITION=y
 CONFIG_CRC_T10DIF=y
 CONFIG_DEBUG_FS=y
-CONFIG_DEBUG_KERNEL=y
 CONFIG_DETECT_HUNG_TASK=y
 CONFIG_DEBUG_INFO=y
 CONFIG_SYSCTL_SYSCALL_CHECK=y
diff --git a/arch/powerpc/configs/mpc85xx_smp_defconfig b/arch/powerpc/configs/mpc85xx_smp_defconfig
index 9693f6ed3da0..dd1e41386c4c 100644
--- a/arch/powerpc/configs/mpc85xx_smp_defconfig
+++ b/arch/powerpc/configs/mpc85xx_smp_defconfig
@@ -12,10 +12,8 @@ CONFIG_IKCONFIG=y
 CONFIG_IKCONFIG_PROC=y
 CONFIG_LOG_BUF_SHIFT=14
 CONFIG_BLK_DEV_INITRD=y
-# CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
 CONFIG_EXPERT=y
 CONFIG_KALLSYMS_ALL=y
-CONFIG_KALLSYMS_EXTRA_PASS=y
 CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
 CONFIG_MODULE_FORCE_UNLOAD=y
@@ -42,7 +40,6 @@ CONFIG_TQM8560=y
 CONFIG_SBC8548=y
 CONFIG_QUICC_ENGINE=y
 CONFIG_QE_GPIO=y
-CONFIG_MPC8xxx_GPIO=y
 CONFIG_HIGHMEM=y
 CONFIG_NO_HZ=y
 CONFIG_HIGH_RES_TIMERS=y
@@ -124,6 +121,7 @@ CONFIG_NVRAM=y
 CONFIG_I2C=y
 CONFIG_I2C_CPM=m
 CONFIG_I2C_MPC=y
+CONFIG_GPIO_MPC8XXX=y
 # CONFIG_HWMON is not set
 CONFIG_VIDEO_OUTPUT_CONTROL=y
 CONFIG_FB=y
@@ -207,10 +205,8 @@ CONFIG_PARTITION_ADVANCED=y
 CONFIG_MAC_PARTITION=y
 CONFIG_CRC_T10DIF=y
 CONFIG_DEBUG_FS=y
-CONFIG_DEBUG_KERNEL=y
 CONFIG_DETECT_HUNG_TASK=y
 CONFIG_DEBUG_INFO=y
-# CONFIG_RCU_CPU_STALL_DETECTOR is not set
 CONFIG_SYSCTL_SYSCALL_CHECK=y
 CONFIG_VIRQ_DEBUG=y
 CONFIG_CRYPTO_PCBC=m
diff --git a/arch/powerpc/configs/ppc40x_defconfig b/arch/powerpc/configs/ppc40x_defconfig
index bfd634b5ada7..1eb19ac45d09 100644
--- a/arch/powerpc/configs/ppc40x_defconfig
+++ b/arch/powerpc/configs/ppc40x_defconfig
@@ -14,7 +14,6 @@ CONFIG_MODULE_UNLOAD=y
 CONFIG_PPC4xx_GPIO=y
 CONFIG_ACADIA=y
 CONFIG_EP405=y
-CONFIG_HCU4=y
 CONFIG_HOTFOOT=y
 CONFIG_KILAUEA=y
 CONFIG_MAKALU=y
@@ -50,8 +49,9 @@ CONFIG_BLK_DEV_RAM=y
 CONFIG_BLK_DEV_RAM_SIZE=35000
 CONFIG_XILINX_SYSACE=m
 CONFIG_NETDEVICES=y
-CONFIG_NET_ETHERNET=y
-CONFIG_IBM_NEW_EMAC=y
+CONFIG_ETHERNET=y
+CONFIG_NET_VENDOR_IBM=y
+CONFIG_IBM_EMAC=y
 # CONFIG_INPUT is not set
 CONFIG_SERIO=m
 # CONFIG_SERIO_I8042 is not set
diff --git a/arch/powerpc/configs/ppc44x_defconfig b/arch/powerpc/configs/ppc44x_defconfig
index 47133202a625..6cdf1c0d2c8a 100644
--- a/arch/powerpc/configs/ppc44x_defconfig
+++ b/arch/powerpc/configs/ppc44x_defconfig
@@ -63,8 +63,9 @@ CONFIG_BLK_DEV_SD=m
 # CONFIG_SCSI_LOWLEVEL is not set
 CONFIG_NETDEVICES=y
 CONFIG_TUN=m
-CONFIG_NET_ETHERNET=y
-CONFIG_IBM_NEW_EMAC=y
+CONFIG_ETHERNET=y
+CONFIG_NET_VENDOR_IBM=y
+CONFIG_IBM_EMAC=y
 # CONFIG_INPUT is not set
 CONFIG_SERIO=m
 # CONFIG_SERIO_I8042 is not set
diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig
index 84a685a505fe..535711fcb13c 100644
--- a/arch/powerpc/configs/ppc64_defconfig
+++ b/arch/powerpc/configs/ppc64_defconfig
@@ -485,3 +485,7 @@ CONFIG_CRYPTO_TWOFISH=m
 CONFIG_CRYPTO_LZO=m
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
 # CONFIG_CRYPTO_HW is not set
+CONFIG_VIRTUALIZATION=y
+CONFIG_KVM_BOOK3S_64=m
+CONFIG_KVM_BOOK3S_64_HV=y
+CONFIG_VHOST_NET=m
diff --git a/arch/powerpc/configs/ppc6xx_defconfig b/arch/powerpc/configs/ppc6xx_defconfig
index 04360f9b0109..c47f2becfbc3 100644
--- a/arch/powerpc/configs/ppc6xx_defconfig
+++ b/arch/powerpc/configs/ppc6xx_defconfig
@@ -70,7 +70,7 @@ CONFIG_TAU_AVERAGE=y
 CONFIG_QUICC_ENGINE=y
 CONFIG_QE_GPIO=y
 CONFIG_PPC_BESTCOMM=y
-CONFIG_MPC8xxx_GPIO=y
+CONFIG_GPIO_MPC8XXX=y
 CONFIG_MCU_MPC8349EMITX=m
 CONFIG_HIGHMEM=y
 CONFIG_NO_HZ=y
diff --git a/arch/powerpc/configs/pseries_defconfig b/arch/powerpc/configs/pseries_defconfig
index 96a58b709705..a72f2415a647 100644
--- a/arch/powerpc/configs/pseries_defconfig
+++ b/arch/powerpc/configs/pseries_defconfig
@@ -362,3 +362,7 @@ CONFIG_CRYPTO_TWOFISH=m
 CONFIG_CRYPTO_LZO=m
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
 # CONFIG_CRYPTO_HW is not set
+CONFIG_VIRTUALIZATION=y
+CONFIG_KVM_BOOK3S_64=m
+CONFIG_KVM_BOOK3S_64_HV=y
+CONFIG_VHOST_NET=m
diff --git a/arch/powerpc/include/asm/compat.h b/arch/powerpc/include/asm/compat.h
index 91010e8f8479..88e602f6430d 100644
--- a/arch/powerpc/include/asm/compat.h
+++ b/arch/powerpc/include/asm/compat.h
@@ -100,7 +100,8 @@ struct compat_statfs {
         compat_fsid_t   f_fsid;
         int             f_namelen;      /* SunOS ignores this field. */
         int             f_frsize;
-        int             f_spare[5];
+        int             f_flags;
+        int             f_spare[4];
 };
 
 #define COMPAT_RLIM_OLD_INFINITY        0x7fffffff
diff --git a/arch/powerpc/include/asm/device.h b/arch/powerpc/include/asm/device.h
index 16d25c0974be..d57c08acedfc 100644
--- a/arch/powerpc/include/asm/device.h
+++ b/arch/powerpc/include/asm/device.h
@@ -37,4 +37,6 @@ struct pdev_archdata {
         u64 dma_mask;
 };
 
+#define ARCH_HAS_DMA_GET_REQUIRED_MASK
+
 #endif /* _ASM_POWERPC_DEVICE_H */
diff --git a/arch/powerpc/include/asm/firmware.h b/arch/powerpc/include/asm/firmware.h
index 3a6c586c4e40..14db29b18d0e 100644
--- a/arch/powerpc/include/asm/firmware.h
+++ b/arch/powerpc/include/asm/firmware.h
@@ -48,6 +48,8 @@
 #define FW_FEATURE_CMO          ASM_CONST(0x0000000002000000)
 #define FW_FEATURE_VPHN         ASM_CONST(0x0000000004000000)
 #define FW_FEATURE_XCMO         ASM_CONST(0x0000000008000000)
+#define FW_FEATURE_OPAL         ASM_CONST(0x0000000010000000)
+#define FW_FEATURE_OPALv2       ASM_CONST(0x0000000020000000)
 
 #ifndef __ASSEMBLY__
 
@@ -65,6 +67,8 @@ enum {
         FW_FEATURE_PSERIES_ALWAYS = 0,
         FW_FEATURE_ISERIES_POSSIBLE = FW_FEATURE_ISERIES | FW_FEATURE_LPAR,
         FW_FEATURE_ISERIES_ALWAYS = FW_FEATURE_ISERIES | FW_FEATURE_LPAR,
+        FW_FEATURE_POWERNV_POSSIBLE = FW_FEATURE_OPAL | FW_FEATURE_OPALv2,
+        FW_FEATURE_POWERNV_ALWAYS = 0,
         FW_FEATURE_PS3_POSSIBLE = FW_FEATURE_LPAR | FW_FEATURE_PS3_LV1,
         FW_FEATURE_PS3_ALWAYS = FW_FEATURE_LPAR | FW_FEATURE_PS3_LV1,
         FW_FEATURE_CELLEB_POSSIBLE = FW_FEATURE_LPAR | FW_FEATURE_BEAT,
@@ -78,6 +82,9 @@ enum {
 #ifdef CONFIG_PPC_ISERIES
                 FW_FEATURE_ISERIES_POSSIBLE |
 #endif
+#ifdef CONFIG_PPC_POWERNV
+                FW_FEATURE_POWERNV_POSSIBLE |
+#endif
 #ifdef CONFIG_PPC_PS3
                 FW_FEATURE_PS3_POSSIBLE |
 #endif
@@ -95,6 +102,9 @@ enum {
 #ifdef CONFIG_PPC_ISERIES
                 FW_FEATURE_ISERIES_ALWAYS &
 #endif
+#ifdef CONFIG_PPC_POWERNV
+                FW_FEATURE_POWERNV_ALWAYS &
+#endif
 #ifdef CONFIG_PPC_PS3
                 FW_FEATURE_PS3_ALWAYS &
 #endif
diff --git a/arch/powerpc/include/asm/floppy.h b/arch/powerpc/include/asm/floppy.h
index 24bd34c57e9d..936a904ae78c 100644
--- a/arch/powerpc/include/asm/floppy.h
+++ b/arch/powerpc/include/asm/floppy.h
@@ -108,10 +108,10 @@ static int fd_request_irq(void)
 {
         if (can_use_virtual_dma)
                 return request_irq(FLOPPY_IRQ, floppy_hardint,
-                                   IRQF_DISABLED, "floppy", NULL);
+                                   0, "floppy", NULL);
         else
                 return request_irq(FLOPPY_IRQ, floppy_interrupt,
-                                   IRQF_DISABLED, "floppy", NULL);
+                                   0, "floppy", NULL);
 }
 
 static int vdma_dma_setup(char *addr, unsigned long size, int mode, int io)
diff --git a/arch/powerpc/include/asm/hugetlb.h b/arch/powerpc/include/asm/hugetlb.h
index 5856a66ab404..86004930a78e 100644
--- a/arch/powerpc/include/asm/hugetlb.h
+++ b/arch/powerpc/include/asm/hugetlb.h
@@ -1,15 +1,60 @@
 #ifndef _ASM_POWERPC_HUGETLB_H
 #define _ASM_POWERPC_HUGETLB_H
 
+#ifdef CONFIG_HUGETLB_PAGE
 #include <asm/page.h>
 
+extern struct kmem_cache *hugepte_cache;
+extern void __init reserve_hugetlb_gpages(void);
+
+static inline pte_t *hugepd_page(hugepd_t hpd)
+{
+        BUG_ON(!hugepd_ok(hpd));
+        return (pte_t *)((hpd.pd & ~HUGEPD_SHIFT_MASK) | PD_HUGE);
+}
+
+static inline unsigned int hugepd_shift(hugepd_t hpd)
+{
+        return hpd.pd & HUGEPD_SHIFT_MASK;
+}
+
+static inline pte_t *hugepte_offset(hugepd_t *hpdp, unsigned long addr,
+                                    unsigned pdshift)
+{
+        /*
+         * On 32-bit, we have multiple higher-level table entries that point to
+         * the same hugepte.  Just use the first one since they're all
+         * identical.  So for that case, idx=0.
+         */
+        unsigned long idx = 0;
+
+        pte_t *dir = hugepd_page(*hpdp);
+#ifdef CONFIG_PPC64
+        idx = (addr & ((1UL << pdshift) - 1)) >> hugepd_shift(*hpdp);
+#endif
+
+        return dir + idx;
+}
+
 pte_t *huge_pte_offset_and_shift(struct mm_struct *mm,
                                  unsigned long addr, unsigned *shift);
 
 void flush_dcache_icache_hugepage(struct page *page);
 
+#if defined(CONFIG_PPC_MM_SLICES) || defined(CONFIG_PPC_SUBPAGE_PROT)
 int is_hugepage_only_range(struct mm_struct *mm, unsigned long addr,
                            unsigned long len);
+#else
+static inline int is_hugepage_only_range(struct mm_struct *mm,
+                                         unsigned long addr,
+                                         unsigned long len)
+{
+        return 0;
+}
+#endif
+
+void book3e_hugetlb_preload(struct mm_struct *mm, unsigned long ea, pte_t pte);
+void flush_hugetlb_page(struct vm_area_struct *vma, unsigned long vmaddr);
 
 void hugetlb_free_pgd_range(struct mmu_gather *tlb, unsigned long addr,
                             unsigned long end, unsigned long floor,
@@ -50,8 +95,11 @@ static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
                                             unsigned long addr, pte_t *ptep)
 {
-        unsigned long old = pte_update(mm, addr, ptep, ~0UL, 1);
-        return __pte(old);
+#ifdef CONFIG_PPC64
+        return __pte(pte_update(mm, addr, ptep, ~0UL, 1));
+#else
+        return __pte(pte_update(ptep, ~0UL, 0));
+#endif
 }
 
 static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
@@ -93,4 +141,15 @@ static inline void arch_release_hugepage(struct page *page)
 {
 }
 
+#else /* ! CONFIG_HUGETLB_PAGE */
+static inline void reserve_hugetlb_gpages(void)
+{
+        pr_err("Cannot reserve gpages without hugetlb enabled\n");
+}
+static inline void flush_hugetlb_page(struct vm_area_struct *vma,
+                                      unsigned long vmaddr)
+{
+}
+#endif
+
 #endif /* _ASM_POWERPC_HUGETLB_H */
diff --git a/arch/powerpc/include/asm/kexec.h b/arch/powerpc/include/asm/kexec.h
index 8a33698c61bd..f921eb121d39 100644
--- a/arch/powerpc/include/asm/kexec.h
+++ b/arch/powerpc/include/asm/kexec.h
@@ -2,7 +2,7 @@
 #define _ASM_POWERPC_KEXEC_H
 #ifdef __KERNEL__
 
-#ifdef CONFIG_FSL_BOOKE
+#if defined(CONFIG_FSL_BOOKE) || defined(CONFIG_44x)
 
 /*
  * On FSL-BookE we setup a 1:1 mapping which covers the first 2GiB of memory
diff --git a/arch/powerpc/include/asm/kvm.h b/arch/powerpc/include/asm/kvm.h
index a4f6c85431f8..08fe69edcd10 100644
--- a/arch/powerpc/include/asm/kvm.h
+++ b/arch/powerpc/include/asm/kvm.h
@@ -149,6 +149,12 @@ struct kvm_regs {
 #define KVM_SREGS_E_UPDATE_DBSR         (1 << 3)
 
 /*
+ * Book3S special bits to indicate contents in the struct by maintaining
+ * backwards compatibility with older structs. If adding a new field,
+ * please make sure to add a flag for that new field */
+#define KVM_SREGS_S_HIOR                (1 << 0)
+
+/*
  * In KVM_SET_SREGS, reserved/pad fields must be left untouched from a
  * previous KVM_GET_REGS.
  *
@@ -173,6 +179,8 @@ struct kvm_sregs {
                                 __u64 ibat[8]; 
                                 __u64 dbat[8]; 
                         } ppc32;
+                        __u64 flags; /* KVM_SREGS_S_ */
+                        __u64 hior;
                 } s;
                 struct {
                         union {
@@ -276,6 +284,11 @@ struct kvm_guest_debug_arch {
 #define KVM_INTERRUPT_UNSET     -2U
 #define KVM_INTERRUPT_SET_LEVEL -3U
 
+#define KVM_CPU_440             1
+#define KVM_CPU_E500V2          2
+#define KVM_CPU_3S_32           3
+#define KVM_CPU_3S_64           4
+
 /* for KVM_CAP_SPAPR_TCE */
 struct kvm_create_spapr_tce {
         __u64 liobn;
diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h
index 98da010252a3..a384ffdf33de 100644
--- a/arch/powerpc/include/asm/kvm_book3s.h
+++ b/arch/powerpc/include/asm/kvm_book3s.h
@@ -90,6 +90,8 @@ struct kvmppc_vcpu_book3s {
 #endif
         int context_id[SID_CONTEXTS];
 
+        bool hior_sregs;                /* HIOR is set by SREGS, not PVR */
+
         struct hlist_head hpte_hash_pte[HPTEG_HASH_NUM_PTE];
         struct hlist_head hpte_hash_pte_long[HPTEG_HASH_NUM_PTE_LONG];
         struct hlist_head hpte_hash_vpte[HPTEG_HASH_NUM_VPTE];
@@ -139,15 +141,14 @@ extern void kvmppc_giveup_ext(struct kvm_vcpu *vcpu, ulong msr);
 extern int kvmppc_emulate_paired_single(struct kvm_run *run, struct kvm_vcpu *vcpu);
 extern pfn_t kvmppc_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn);
 
-extern void kvmppc_handler_lowmem_trampoline(void);
-extern void kvmppc_handler_trampoline_enter(void);
-extern void kvmppc_rmcall(ulong srr0, ulong srr1);
+extern void kvmppc_entry_trampoline(void);
 extern void kvmppc_hv_entry_trampoline(void);
 extern void kvmppc_load_up_fpu(void);
 extern void kvmppc_load_up_altivec(void);
 extern void kvmppc_load_up_vsx(void);
 extern u32 kvmppc_alignment_dsisr(struct kvm_vcpu *vcpu, unsigned int inst);
 extern ulong kvmppc_alignment_dar(struct kvm_vcpu *vcpu, unsigned int inst);
+extern int kvmppc_h_pr(struct kvm_vcpu *vcpu, unsigned long cmd);
 
 static inline struct kvmppc_vcpu_book3s *to_book3s(struct kvm_vcpu *vcpu)
 {
@@ -382,6 +383,39 @@ static inline bool kvmppc_critical_section(struct kvm_vcpu *vcpu)
 }
 #endif
 
+static inline unsigned long compute_tlbie_rb(unsigned long v, unsigned long r,
+                                             unsigned long pte_index)
+{
+        unsigned long rb, va_low;
+
+        rb = (v & ~0x7fUL) << 16;               /* AVA field */
+        va_low = pte_index >> 3;
+        if (v & HPTE_V_SECONDARY)
+                va_low = ~va_low;
+        /* xor vsid from AVA */
+        if (!(v & HPTE_V_1TB_SEG))
+                va_low ^= v >> 12;
+        else
+                va_low ^= v >> 24;
+        va_low &= 0x7ff;
+        if (v & HPTE_V_LARGE) {
+                rb |= 1;                        /* L field */
+                if (cpu_has_feature(CPU_FTR_ARCH_206) &&
+                    (r & 0xff000)) {
+                        /* non-16MB large page, must be 64k */
+                        /* (masks depend on page size) */
+                        rb |= 0x1000;           /* page encoding in LP field */
+                        rb |= (va_low & 0x7f) << 16; /* 7b of VA in AVA/LP field */
+                        rb |= (va_low & 0xfe);  /* AVAL field (P7 doesn't seem to care) */
+                }
+        } else {
+                /* 4kB page */
+                rb |= (va_low & 0x7ff) << 12;   /* remaining 11b of VA */
+        }
+        rb |= (v >> 54) & 0x300;                /* B field */
+        return rb;
+}
+
 /* Magic register values loaded into r3 and r4 before the 'sc' assembly
  * instruction for the OSI hypercalls */
 #define OSI_SC_MAGIC_R3                 0x113724FA
diff --git a/arch/powerpc/include/asm/kvm_book3s_asm.h b/arch/powerpc/include/asm/kvm_book3s_asm.h
index ef7b3688c3b6..1f2f5b6156bd 100644
--- a/arch/powerpc/include/asm/kvm_book3s_asm.h
+++ b/arch/powerpc/include/asm/kvm_book3s_asm.h
@@ -75,6 +75,8 @@ struct kvmppc_host_state {
         ulong scratch0;
         ulong scratch1;
         u8 in_guest;
+        u8 restore_hid5;
+        u8 napping;
 
 #ifdef CONFIG_KVM_BOOK3S_64_HV
         struct kvm_vcpu *kvm_vcpu;
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index cc22b282d755..bf8af5d5d5dc 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -198,21 +198,29 @@ struct kvm_arch {
  */
 struct kvmppc_vcore {
         int n_runnable;
-        int n_blocked;
+        int n_busy;
         int num_threads;
         int entry_exit_count;
         int n_woken;
         int nap_count;
+        int napping_threads;
         u16 pcpu;
-        u8 vcore_running;
+        u8 vcore_state;
         u8 in_guest;
         struct list_head runnable_threads;
         spinlock_t lock;
+        wait_queue_head_t wq;
 };
 
 #define VCORE_ENTRY_COUNT(vc)   ((vc)->entry_exit_count & 0xff)
 #define VCORE_EXIT_COUNT(vc)    ((vc)->entry_exit_count >> 8)
 
+/* Values for vcore_state */
+#define VCORE_INACTIVE  0
+#define VCORE_RUNNING   1
+#define VCORE_EXITING   2
+#define VCORE_SLEEPING  3
+
 struct kvmppc_pte {
         ulong eaddr;
         u64 vpage;
@@ -258,14 +266,6 @@ struct kvm_vcpu_arch {
         ulong host_stack;
         u32 host_pid;
 #ifdef CONFIG_PPC_BOOK3S
-        ulong host_msr;
-        ulong host_r2;
-        void *host_retip;
-        ulong trampoline_lowmem;
-        ulong trampoline_enter;
-        ulong highmem_handler;
-        ulong rmcall;
-        ulong host_paca_phys;
         struct kvmppc_slb slb[64];
         int slb_max;            /* 1 + index of last valid entry in slb[] */
         int slb_nr;             /* total number of entries in SLB */
@@ -389,6 +389,9 @@ struct kvm_vcpu_arch {
         u8 dcr_is_write;
         u8 osi_needed;
         u8 osi_enabled;
+        u8 papr_enabled;
+        u8 sane;
+        u8 cpu_type;
         u8 hcall_needed;
 
         u32 cpr0_cfgaddr; /* holds the last set cpr0_cfgaddr */
@@ -408,11 +411,13 @@ struct kvm_vcpu_arch {
         struct dtl *dtl;
         struct dtl *dtl_end;
 
+        wait_queue_head_t *wqp;
         struct kvmppc_vcore *vcore;
         int ret;
         int trap;
         int state;
         int ptid;
+        bool timer_running;
         wait_queue_head_t cpu_run;
 
         struct kvm_vcpu_arch_shared *shared;
@@ -428,8 +433,9 @@ struct kvm_vcpu_arch {
 #endif
 };
 
-#define KVMPPC_VCPU_BUSY_IN_HOST        0
-#define KVMPPC_VCPU_BLOCKED             1
+/* Values for vcpu->arch.state */
+#define KVMPPC_VCPU_STOPPED             0
+#define KVMPPC_VCPU_BUSY_IN_HOST        1
 #define KVMPPC_VCPU_RUNNABLE            2
 
 #endif /* __POWERPC_KVM_HOST_H__ */
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index d121f49d62b8..46efd1a265c9 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -66,6 +66,7 @@ extern int kvmppc_emulate_instruction(struct kvm_run *run,
 extern int kvmppc_emulate_mmio(struct kvm_run *run, struct kvm_vcpu *vcpu);
 extern void kvmppc_emulate_dec(struct kvm_vcpu *vcpu);
 extern u32 kvmppc_get_dec(struct kvm_vcpu *vcpu, u64 tb);
+extern int kvmppc_sanity_check(struct kvm_vcpu *vcpu);
 
 /* Core-specific hooks */
 
diff --git a/arch/powerpc/include/asm/lv1call.h b/arch/powerpc/include/asm/lv1call.h
index 81713acf7529..f77c708c67a0 100644
--- a/arch/powerpc/include/asm/lv1call.h
+++ b/arch/powerpc/include/asm/lv1call.h
@@ -25,6 +25,7 @@
 #if !defined(__ASSEMBLY__)
 
 #include <linux/types.h>
+#include <linux/export.h>
 
 /* lv1 call declaration macros */
 
@@ -315,7 +316,7 @@ LV1_CALL(gpu_context_free,                              1, 0, 218 )
 LV1_CALL(gpu_context_iomap,                             5, 0, 221 )
 LV1_CALL(gpu_context_attribute,                         6, 0, 225 )
 LV1_CALL(gpu_context_intr,                              1, 1, 227 )
-LV1_CALL(gpu_attribute,                                 5, 0, 228 )
+LV1_CALL(gpu_attribute,                                 3, 0, 228 )
 LV1_CALL(get_rtc,                                       0, 2, 232 )
 LV1_CALL(set_ppe_periodic_tracer_frequency,             1, 0, 240 )
 LV1_CALL(start_ppe_periodic_tracer,                     5, 0, 241 )
diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h
index 47cacddb14cf..b540d6fcedd6 100644
--- a/arch/powerpc/include/asm/machdep.h
+++ b/arch/powerpc/include/asm/machdep.h
@@ -12,6 +12,7 @@
 #include <linux/seq_file.h>
 #include <linux/init.h>
 #include <linux/dma-mapping.h>
+#include <linux/export.h>
 
 #include <asm/setup.h>
 
@@ -85,8 +86,9 @@ struct machdep_calls {
         void            (*pci_dma_dev_setup)(struct pci_dev *dev);
         void            (*pci_dma_bus_setup)(struct pci_bus *bus);
 
-        /* Platform set_dma_mask override */
+        /* Platform set_dma_mask and dma_get_required_mask overrides */
         int             (*dma_set_mask)(struct device *dev, u64 dma_mask);
+        u64             (*dma_get_required_mask)(struct device *dev);
 
         int             (*probe)(void);
         void            (*setup_arch)(void); /* Optional, may be NULL */
diff --git a/arch/powerpc/include/asm/mmu-book3e.h b/arch/powerpc/include/asm/mmu-book3e.h
index 3ea0f9a259d8..0260ea5ec3c2 100644
--- a/arch/powerpc/include/asm/mmu-book3e.h
+++ b/arch/powerpc/include/asm/mmu-book3e.h
@@ -66,6 +66,7 @@
 #define MAS2_M                  0x00000004
 #define MAS2_G                  0x00000002
 #define MAS2_E                  0x00000001
+#define MAS2_WIMGE_MASK         0x0000001f
 #define MAS2_EPN_MASK(size)             (~0 << (size + 10))
 #define MAS2_VAL(addr, size, flags)     ((addr) & MAS2_EPN_MASK(size) | (flags))
 
@@ -80,6 +81,7 @@
 #define MAS3_SW                 0x00000004
 #define MAS3_UR                 0x00000002
 #define MAS3_SR                 0x00000001
+#define MAS3_BAP_MASK           0x0000003f
 #define MAS3_SPSIZE             0x0000003e
 #define MAS3_SPSIZE_SHIFT       1
 
@@ -212,6 +214,11 @@ typedef struct {
         unsigned int    id;
         unsigned int    active;
         unsigned long   vdso_base;
+#ifdef CONFIG_PPC_MM_SLICES
+        u64 low_slices_psize;   /* SLB page size encodings */
+        u64 high_slices_psize;  /* 4 bits per slice for now */
+        u16 user_psize;         /* page size index */
+#endif
 } mm_context_t;
 
 /* Page size definitions, common between 32 and 64-bit
diff --git a/arch/powerpc/include/asm/mmu-hash64.h b/arch/powerpc/include/asm/mmu-hash64.h
index b445e0af4c2b..db645ec842bd 100644
--- a/arch/powerpc/include/asm/mmu-hash64.h
+++ b/arch/powerpc/include/asm/mmu-hash64.h
@@ -262,8 +262,7 @@ extern void hash_failure_debug(unsigned long ea, unsigned long access,
 extern int htab_bolt_mapping(unsigned long vstart, unsigned long vend,
                              unsigned long pstart, unsigned long prot,
                              int psize, int ssize);
-extern void add_gpage(unsigned long addr, unsigned long page_size,
-                          unsigned long number_of_pages);
+extern void add_gpage(u64 addr, u64 page_size, unsigned long number_of_pages);
 extern void demote_segment_4k(struct mm_struct *mm, unsigned long addr);
 
 extern void hpte_init_native(void);
diff --git a/arch/powerpc/include/asm/mmu.h b/arch/powerpc/include/asm/mmu.h
index 698b30638681..f0145522cfba 100644
--- a/arch/powerpc/include/asm/mmu.h
+++ b/arch/powerpc/include/asm/mmu.h
@@ -175,14 +175,16 @@ extern u64 ppc64_rma_size;
 #define MMU_PAGE_64K_AP 3       /* "Admixed pages" (hash64 only) */
 #define MMU_PAGE_256K   4
 #define MMU_PAGE_1M     5
-#define MMU_PAGE_8M     6
-#define MMU_PAGE_16M    7
-#define MMU_PAGE_256M   8
-#define MMU_PAGE_1G     9
-#define MMU_PAGE_16G    10
-#define MMU_PAGE_64G    11
-#define MMU_PAGE_COUNT  12
-
+#define MMU_PAGE_4M     6
+#define MMU_PAGE_8M     7
+#define MMU_PAGE_16M    8
+#define MMU_PAGE_64M    9
+#define MMU_PAGE_256M   10
+#define MMU_PAGE_1G     11
+#define MMU_PAGE_16G    12
+#define MMU_PAGE_64G    13
+
+#define MMU_PAGE_COUNT  14
 
 #if defined(CONFIG_PPC_STD_MMU_64)
 /* 64-bit classic hash table MMU */
diff --git a/arch/powerpc/include/asm/mpic.h b/arch/powerpc/include/asm/mpic.h
index df18989e78d4..e6fae49e0b74 100644
--- a/arch/powerpc/include/asm/mpic.h
+++ b/arch/powerpc/include/asm/mpic.h
@@ -273,8 +273,6 @@ struct mpic
         unsigned int            irq_count;
         /* Number of sources */
         unsigned int            num_sources;
-        /* Number of CPUs */
-        unsigned int            num_cpus;
         /* default senses array */
         unsigned char           *senses;
         unsigned int            senses_count;
diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h
new file mode 100644
index 000000000000..2893e8f5406d
--- /dev/null
+++ b/arch/powerpc/include/asm/opal.h
@@ -0,0 +1,443 @@
+/*
+ * PowerNV OPAL definitions.
+ *
+ * Copyright 2011 IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#ifndef __OPAL_H
+#define __OPAL_H
+
+/****** Takeover interface ********/
+
+/* PAPR H-Call used to querty the HAL existence and/or instanciate
+ * it from within pHyp (tech preview only).
+ *
+ * This is exclusively used in prom_init.c
+ */
+
+#ifndef __ASSEMBLY__
+
+struct opal_takeover_args {
+        u64     k_image;                /* r4 */
+        u64     k_size;                 /* r5 */
+        u64     k_entry;                /* r6 */
+        u64     k_entry2;               /* r7 */
+        u64     hal_addr;               /* r8 */
+        u64     rd_image;               /* r9 */
+        u64     rd_size;                /* r10 */
+        u64     rd_loc;                 /* r11 */
+};
+
+extern long opal_query_takeover(u64 *hal_size, u64 *hal_align);
+
+extern long opal_do_takeover(struct opal_takeover_args *args);
+
+struct rtas_args;
+extern int opal_enter_rtas(struct rtas_args *args,
+                           unsigned long data,
+                           unsigned long entry);
+
+#endif /* __ASSEMBLY__ */
+
+/****** OPAL APIs ******/
+
+/* Return codes */
+#define OPAL_SUCCESS            0
+#define OPAL_PARAMETER          -1
+#define OPAL_BUSY               -2
+#define OPAL_PARTIAL            -3
+#define OPAL_CONSTRAINED        -4
+#define OPAL_CLOSED             -5
+#define OPAL_HARDWARE           -6
+#define OPAL_UNSUPPORTED        -7
+#define OPAL_PERMISSION         -8
+#define OPAL_NO_MEM             -9
+#define OPAL_RESOURCE           -10
+#define OPAL_INTERNAL_ERROR     -11
+#define OPAL_BUSY_EVENT         -12
+#define OPAL_HARDWARE_FROZEN    -13
+
+/* API Tokens (in r0) */
+#define OPAL_CONSOLE_WRITE                      1
+#define OPAL_CONSOLE_READ                       2
+#define OPAL_RTC_READ                           3
+#define OPAL_RTC_WRITE                          4
+#define OPAL_CEC_POWER_DOWN                     5
+#define OPAL_CEC_REBOOT                         6
+#define OPAL_READ_NVRAM                         7
+#define OPAL_WRITE_NVRAM                        8
+#define OPAL_HANDLE_INTERRUPT                   9
+#define OPAL_POLL_EVENTS                        10
+#define OPAL_PCI_SET_HUB_TCE_MEMORY             11
+#define OPAL_PCI_SET_PHB_TCE_MEMORY             12
+#define OPAL_PCI_CONFIG_READ_BYTE               13
+#define OPAL_PCI_CONFIG_READ_HALF_WORD          14
+#define OPAL_PCI_CONFIG_READ_WORD               15
+#define OPAL_PCI_CONFIG_WRITE_BYTE              16
+#define OPAL_PCI_CONFIG_WRITE_HALF_WORD         17
+#define OPAL_PCI_CONFIG_WRITE_WORD              18
+#define OPAL_SET_XIVE                           19
+#define OPAL_GET_XIVE                           20
+#define OPAL_GET_COMPLETION_TOKEN_STATUS        21 /* obsolete */
+#define OPAL_REGISTER_OPAL_EXCEPTION_HANDLER    22
+#define OPAL_PCI_EEH_FREEZE_STATUS              23
+#define OPAL_PCI_SHPC                           24
+#define OPAL_CONSOLE_WRITE_BUFFER_SPACE         25
+#define OPAL_PCI_EEH_FREEZE_CLEAR               26
+#define OPAL_PCI_PHB_MMIO_ENABLE                27
+#define OPAL_PCI_SET_PHB_MEM_WINDOW             28
+#define OPAL_PCI_MAP_PE_MMIO_WINDOW             29
+#define OPAL_PCI_SET_PHB_TABLE_MEMORY           30
+#define OPAL_PCI_SET_PE                         31
+#define OPAL_PCI_SET_PELTV                      32
+#define OPAL_PCI_SET_MVE                        33
+#define OPAL_PCI_SET_MVE_ENABLE                 34
+#define OPAL_PCI_GET_XIVE_REISSUE               35
+#define OPAL_PCI_SET_XIVE_REISSUE               36
+#define OPAL_PCI_SET_XIVE_PE                    37
+#define OPAL_GET_XIVE_SOURCE                    38
+#define OPAL_GET_MSI_32                         39
+#define OPAL_GET_MSI_64                         40
+#define OPAL_START_CPU                          41
+#define OPAL_QUERY_CPU_STATUS                   42
+#define OPAL_WRITE_OPPANEL                      43
+#define OPAL_PCI_MAP_PE_DMA_WINDOW              44
+#define OPAL_PCI_MAP_PE_DMA_WINDOW_REAL         45
+#define OPAL_PCI_RESET                          49
+
+#ifndef __ASSEMBLY__
+
+/* Other enums */
+enum OpalVendorApiTokens {
+        OPAL_START_VENDOR_API_RANGE = 1000, OPAL_END_VENDOR_API_RANGE = 1999
+};
+enum OpalFreezeState {
+        OPAL_EEH_STOPPED_NOT_FROZEN = 0,
+        OPAL_EEH_STOPPED_MMIO_FREEZE = 1,
+        OPAL_EEH_STOPPED_DMA_FREEZE = 2,
+        OPAL_EEH_STOPPED_MMIO_DMA_FREEZE = 3,
+        OPAL_EEH_STOPPED_RESET = 4,
+        OPAL_EEH_STOPPED_TEMP_UNAVAIL = 5,
+        OPAL_EEH_STOPPED_PERM_UNAVAIL = 6
+};
+enum OpalEehFreezeActionToken {
+        OPAL_EEH_ACTION_CLEAR_FREEZE_MMIO = 1,
+        OPAL_EEH_ACTION_CLEAR_FREEZE_DMA = 2,
+        OPAL_EEH_ACTION_CLEAR_FREEZE_ALL = 3
+};
+enum OpalPciStatusToken {
+        OPAL_EEH_PHB_NO_ERROR = 0,
+        OPAL_EEH_PHB_FATAL = 1,
+        OPAL_EEH_PHB_RECOVERABLE = 2,
+        OPAL_EEH_PHB_BUS_ERROR = 3,
+        OPAL_EEH_PCI_NO_DEVSEL = 4,
+        OPAL_EEH_PCI_TA = 5,
+        OPAL_EEH_PCIEX_UR = 6,
+        OPAL_EEH_PCIEX_CA = 7,
+        OPAL_EEH_PCI_MMIO_ERROR = 8,
+        OPAL_EEH_PCI_DMA_ERROR = 9
+};
+enum OpalShpcAction {
+        OPAL_SHPC_GET_LINK_STATE = 0,
+        OPAL_SHPC_GET_SLOT_STATE = 1
+};
+enum OpalShpcLinkState {
+        OPAL_SHPC_LINK_DOWN = 0,
+        OPAL_SHPC_LINK_UP = 1
+};
+enum OpalMmioWindowType {
+        OPAL_M32_WINDOW_TYPE = 1,
+        OPAL_M64_WINDOW_TYPE = 2,
+        OPAL_IO_WINDOW_TYPE = 3
+};
+enum OpalShpcSlotState {
+        OPAL_SHPC_DEV_NOT_PRESENT = 0,
+        OPAL_SHPC_DEV_PRESENT = 1
+};
+enum OpalExceptionHandler {
+        OPAL_MACHINE_CHECK_HANDLER = 1,
+        OPAL_HYPERVISOR_MAINTENANCE_HANDLER = 2,
+        OPAL_SOFTPATCH_HANDLER = 3
+};
+enum OpalPendingState {
+        OPAL_EVENT_OPAL_INTERNAL = 0x1,
+        OPAL_EVENT_NVRAM = 0x2,
+        OPAL_EVENT_RTC = 0x4,
+        OPAL_EVENT_CONSOLE_OUTPUT = 0x8,
+        OPAL_EVENT_CONSOLE_INPUT = 0x10
+};
+
+/* Machine check related definitions */
+enum OpalMCE_Version {
+        OpalMCE_V1 = 1,
+};
+
+enum OpalMCE_Severity {
+        OpalMCE_SEV_NO_ERROR = 0,
+        OpalMCE_SEV_WARNING = 1,
+        OpalMCE_SEV_ERROR_SYNC = 2,
+        OpalMCE_SEV_FATAL = 3,
+};
+
+enum OpalMCE_Disposition {
+        OpalMCE_DISPOSITION_RECOVERED = 0,
+        OpalMCE_DISPOSITION_NOT_RECOVERED = 1,
+};
+
+enum OpalMCE_Initiator {
+        OpalMCE_INITIATOR_UNKNOWN = 0,
+        OpalMCE_INITIATOR_CPU = 1,
+};
+
+enum OpalMCE_ErrorType {
+        OpalMCE_ERROR_TYPE_UNKNOWN = 0,
+        OpalMCE_ERROR_TYPE_UE = 1,
+        OpalMCE_ERROR_TYPE_SLB = 2,
+        OpalMCE_ERROR_TYPE_ERAT = 3,
+        OpalMCE_ERROR_TYPE_TLB = 4,
+};
+
+enum OpalMCE_UeErrorType {
+        OpalMCE_UE_ERROR_INDETERMINATE = 0,
+        OpalMCE_UE_ERROR_IFETCH = 1,
+        OpalMCE_UE_ERROR_PAGE_TABLE_WALK_IFETCH = 2,
+        OpalMCE_UE_ERROR_LOAD_STORE = 3,
+        OpalMCE_UE_ERROR_PAGE_TABLE_WALK_LOAD_STORE = 4,
+};
+
+enum OpalMCE_SlbErrorType {
+        OpalMCE_SLB_ERROR_INDETERMINATE = 0,
+        OpalMCE_SLB_ERROR_PARITY = 1,
+        OpalMCE_SLB_ERROR_MULTIHIT = 2,
+};
+
+enum OpalMCE_EratErrorType {
+        OpalMCE_ERAT_ERROR_INDETERMINATE = 0,
+        OpalMCE_ERAT_ERROR_PARITY = 1,
+        OpalMCE_ERAT_ERROR_MULTIHIT = 2,
+};
+
+enum OpalMCE_TlbErrorType {
+        OpalMCE_TLB_ERROR_INDETERMINATE = 0,
+        OpalMCE_TLB_ERROR_PARITY = 1,
+        OpalMCE_TLB_ERROR_MULTIHIT = 2,
+};
+
+enum OpalThreadStatus {
+        OPAL_THREAD_INACTIVE = 0x0,
+        OPAL_THREAD_STARTED = 0x1
+};
+
+enum OpalPciBusCompare {
+        OpalPciBusAny   = 0,    /* Any bus number match */
+        OpalPciBus3Bits = 2,    /* Match top 3 bits of bus number */
+        OpalPciBus4Bits = 3,    /* Match top 4 bits of bus number */
+        OpalPciBus5Bits = 4,    /* Match top 5 bits of bus number */
+        OpalPciBus6Bits = 5,    /* Match top 6 bits of bus number */
+        OpalPciBus7Bits = 6,    /* Match top 7 bits of bus number */
+        OpalPciBusAll   = 7,    /* Match bus number exactly */
+};
+
+enum OpalDeviceCompare {
+        OPAL_IGNORE_RID_DEVICE_NUMBER = 0,
+        OPAL_COMPARE_RID_DEVICE_NUMBER = 1
+};
+
+enum OpalFuncCompare {
+        OPAL_IGNORE_RID_FUNCTION_NUMBER = 0,
+        OPAL_COMPARE_RID_FUNCTION_NUMBER = 1
+};
+
+enum OpalPeAction {
+        OPAL_UNMAP_PE = 0,
+        OPAL_MAP_PE = 1
+};
+
+enum OpalPciResetAndReinitScope {
+        OPAL_PHB_COMPLETE = 1, OPAL_PCI_LINK = 2, OPAL_PHB_ERROR = 3,
+        OPAL_PCI_HOT_RESET = 4, OPAL_PCI_FUNDAMENTAL_RESET = 5,
+        OPAL_PCI_IODA_RESET = 6,
+};
+
+enum OpalPciResetState { OPAL_DEASSERT_RESET = 0, OPAL_ASSERT_RESET = 1 };
+
+struct opal_machine_check_event {
+        enum OpalMCE_Version    version:8;      /* 0x00 */
+        uint8_t                 in_use;         /* 0x01 */
+        enum OpalMCE_Severity   severity:8;     /* 0x02 */
+        enum OpalMCE_Initiator  initiator:8;    /* 0x03 */
+        enum OpalMCE_ErrorType  error_type:8;   /* 0x04 */
+        enum OpalMCE_Disposition disposition:8; /* 0x05 */
+        uint8_t                 reserved_1[2];  /* 0x06 */
+        uint64_t                gpr3;           /* 0x08 */
+        uint64_t                srr0;           /* 0x10 */
+        uint64_t                srr1;           /* 0x18 */
+        union {                                 /* 0x20 */
+                struct {
+                        enum OpalMCE_UeErrorType ue_error_type:8;
+                        uint8_t         effective_address_provided;
+                        uint8_t         physical_address_provided;
+                        uint8_t         reserved_1[5];
+                        uint64_t        effective_address;
+                        uint64_t        physical_address;
+                        uint8_t         reserved_2[8];
+                } ue_error;
+
+                struct {
+                        enum OpalMCE_SlbErrorType slb_error_type:8;
+                        uint8_t         effective_address_provided;
+                        uint8_t         reserved_1[6];
+                        uint64_t        effective_address;
+                        uint8_t         reserved_2[16];
+                } slb_error;
+
+                struct {
+                        enum OpalMCE_EratErrorType erat_error_type:8;
+                        uint8_t         effective_address_provided;
+                        uint8_t         reserved_1[6];
+                        uint64_t        effective_address;
+                        uint8_t         reserved_2[16];
+                } erat_error;
+
+                struct {
+                        enum OpalMCE_TlbErrorType tlb_error_type:8;
+                        uint8_t         effective_address_provided;
+                        uint8_t         reserved_1[6];
+                        uint64_t        effective_address;
+                        uint8_t         reserved_2[16];
+                } tlb_error;
+        } u;
+};
+
+typedef struct oppanel_line {
+        /* XXX */
+} oppanel_line_t;
+
+/* API functions */
+int64_t opal_console_write(int64_t term_number, int64_t *length,
+                           const uint8_t *buffer);
+int64_t opal_console_read(int64_t term_number, int64_t *length,
+                          uint8_t *buffer);
+int64_t opal_console_write_buffer_space(int64_t term_number,
+                                        int64_t *length);
+int64_t opal_rtc_read(uint32_t *year_month_day,
+                      uint64_t *hour_minute_second_millisecond);
+int64_t opal_rtc_write(uint32_t year_month_day,
+                       uint64_t hour_minute_second_millisecond);
+int64_t opal_cec_power_down(uint64_t request);
+int64_t opal_cec_reboot(void);
+int64_t opal_read_nvram(uint64_t buffer, uint64_t size, uint64_t offset);
+int64_t opal_write_nvram(uint64_t buffer, uint64_t size, uint64_t offset);
+int64_t opal_handle_interrupt(uint64_t isn, uint64_t *outstanding_event_mask);
+int64_t opal_poll_events(uint64_t *outstanding_event_mask);
+int64_t opal_pci_set_hub_tce_memory(uint64_t hub_id, uint64_t tce_mem_addr,
+                                    uint64_t tce_mem_size);
+int64_t opal_pci_set_phb_tce_memory(uint64_t phb_id, uint64_t tce_mem_addr,
+                                    uint64_t tce_mem_size);
+int64_t opal_pci_config_read_byte(uint64_t phb_id, uint64_t bus_dev_func,
+                                  uint64_t offset, uint8_t *data);
+int64_t opal_pci_config_read_half_word(uint64_t phb_id, uint64_t bus_dev_func,
+                                       uint64_t offset, uint16_t *data);
+int64_t opal_pci_config_read_word(uint64_t phb_id, uint64_t bus_dev_func,
+                                  uint64_t offset, uint32_t *data);
+int64_t opal_pci_config_write_byte(uint64_t phb_id, uint64_t bus_dev_func,
+                                   uint64_t offset, uint8_t data);
+int64_t opal_pci_config_write_half_word(uint64_t phb_id, uint64_t bus_dev_func,
+                                        uint64_t offset, uint16_t data);
+int64_t opal_pci_config_write_word(uint64_t phb_id, uint64_t bus_dev_func,
+                                   uint64_t offset, uint32_t data);
+int64_t opal_set_xive(uint32_t isn, uint16_t server, uint8_t priority);
+int64_t opal_get_xive(uint32_t isn, uint16_t *server, uint8_t *priority);
+int64_t opal_register_exception_handler(uint64_t opal_exception,
+                                        uint64_t handler_address,
+                                        uint64_t glue_cache_line);
+int64_t opal_pci_eeh_freeze_status(uint64_t phb_id, uint64_t pe_number,
+                                   uint8_t *freeze_state,
+                                   uint16_t *pci_error_type,
+                                   uint64_t *phb_status);
+int64_t opal_pci_eeh_freeze_clear(uint64_t phb_id, uint64_t pe_number,
+                                  uint64_t eeh_action_token);
+int64_t opal_pci_shpc(uint64_t phb_id, uint64_t shpc_action, uint8_t *state);
+
+
+
+int64_t opal_pci_phb_mmio_enable(uint64_t phb_id, uint16_t window_type,
+                                 uint16_t window_num, uint16_t enable);
+int64_t opal_pci_set_phb_mem_window(uint64_t phb_id, uint16_t window_type,
+                                    uint16_t window_num,
+                                    uint64_t starting_real_address,
+                                    uint64_t starting_pci_address,
+                                    uint16_t segment_size);
+int64_t opal_pci_map_pe_mmio_window(uint64_t phb_id, uint16_t pe_number,
+                                    uint16_t window_type, uint16_t window_num,
+                                    uint16_t segment_num);
+int64_t opal_pci_set_phb_table_memory(uint64_t phb_id, uint64_t rtt_addr,
+                                      uint64_t ivt_addr, uint64_t ivt_len,
+                                      uint64_t reject_array_addr,
+                                      uint64_t peltv_addr);
+int64_t opal_pci_set_pe(uint64_t phb_id, uint64_t pe_number, uint64_t bus_dev_func,
+                        uint8_t bus_compare, uint8_t dev_compare, uint8_t func_compare,
+                        uint8_t pe_action);
+int64_t opal_pci_set_peltv(uint64_t phb_id, uint32_t parent_pe, uint32_t child_pe,
+                           uint8_t state);
+int64_t opal_pci_set_mve(uint64_t phb_id, uint32_t mve_number, uint32_t pe_number);
+int64_t opal_pci_set_mve_enable(uint64_t phb_id, uint32_t mve_number,
+                                uint32_t state);
+int64_t opal_pci_get_xive_reissue(uint64_t phb_id, uint32_t xive_number,
+                                  uint8_t *p_bit, uint8_t *q_bit);
+int64_t opal_pci_set_xive_reissue(uint64_t phb_id, uint32_t xive_number,
+                                  uint8_t p_bit, uint8_t q_bit);
+int64_t opal_pci_set_xive_pe(uint64_t phb_id, uint32_t pe_number,
+                             uint32_t xive_num);
+int64_t opal_get_xive_source(uint64_t phb_id, uint32_t xive_num,
+                             int32_t *interrupt_source_number);
+int64_t opal_get_msi_32(uint64_t phb_id, uint32_t mve_number, uint32_t xive_num,
+                        uint8_t msi_range, uint32_t *msi_address,
+                        uint32_t *message_data);
+int64_t opal_get_msi_64(uint64_t phb_id, uint32_t mve_number,
+                        uint32_t xive_num, uint8_t msi_range,
+                        uint64_t *msi_address, uint32_t *message_data);
+int64_t opal_start_cpu(uint64_t thread_number, uint64_t start_address);
+int64_t opal_query_cpu_status(uint64_t thread_number, uint8_t *thread_status);
+int64_t opal_write_oppanel(oppanel_line_t *lines, uint64_t num_lines);
+int64_t opal_pci_map_pe_dma_window(uint64_t phb_id, uint16_t pe_number, uint16_t window_id,
+                                   uint16_t tce_levels, uint64_t tce_table_addr,
+                                   uint64_t tce_table_size, uint64_t tce_page_size);
+int64_t opal_pci_map_pe_dma_window_real(uint64_t phb_id, uint16_t pe_number,
+                                        uint16_t dma_window_number, uint64_t pci_start_addr,
+                                        uint64_t pci_mem_size);
+int64_t opal_pci_reset(uint64_t phb_id, uint8_t reset_scope, uint8_t assert_state);
+
+/* Internal functions */
+extern int early_init_dt_scan_opal(unsigned long node, const char *uname, int depth, void *data);
+
+extern int opal_get_chars(uint32_t vtermno, char *buf, int count);
+extern int opal_put_chars(uint32_t vtermno, const char *buf, int total_len);
+
+extern void hvc_opal_init_early(void);
+
+/* Internal functions */
+extern int early_init_dt_scan_opal(unsigned long node, const char *uname,
+                                   int depth, void *data);
+
+extern int opal_get_chars(uint32_t vtermno, char *buf, int count);
+extern int opal_put_chars(uint32_t vtermno, const char *buf, int total_len);
+
+extern void hvc_opal_init_early(void);
+
+struct rtc_time;
+extern int opal_set_rtc_time(struct rtc_time *tm);
+extern void opal_get_rtc_time(struct rtc_time *tm);
+extern unsigned long opal_get_boot_time(void);
+extern void opal_nvram_init(void);
+
+extern int opal_machine_check(struct pt_regs *regs);
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* __OPAL_H */
diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h
index 516bfb3f47d9..17722c73ba2e 100644
--- a/arch/powerpc/include/asm/paca.h
+++ b/arch/powerpc/include/asm/paca.h
@@ -43,6 +43,7 @@ extern unsigned int debug_smp_processor_id(void); /* from linux/smp.h */
 #define get_slb_shadow()        (get_paca()->slb_shadow_ptr)
 
 struct task_struct;
+struct opal_machine_check_event;
 
 /*
  * Defines the layout of the paca.
@@ -135,6 +136,13 @@ struct paca_struct {
         u8 io_sync;                     /* writel() needs spin_unlock sync */
         u8 irq_work_pending;            /* IRQ_WORK interrupt while soft-disable */
 
+#ifdef CONFIG_PPC_POWERNV
+        /* Pointer to OPAL machine check event structure set by the
+         * early exception handler for use by high level C handler
+         */
+        struct opal_machine_check_event *opal_mc_evt;
+#endif
+
         /* Stuff for accurate time accounting */
         u64 user_time;                  /* accumulated usermode TB ticks */
         u64 system_time;                /* accumulated system TB ticks */
diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h
index 2cd664ef0a5e..dd9c4fd038e0 100644
--- a/arch/powerpc/include/asm/page.h
+++ b/arch/powerpc/include/asm/page.h
@@ -36,6 +36,18 @@
 
 #define PAGE_SIZE               (ASM_CONST(1) << PAGE_SHIFT)
 
+#ifndef __ASSEMBLY__
+#ifdef CONFIG_HUGETLB_PAGE
+extern unsigned int HPAGE_SHIFT;
+#else
+#define HPAGE_SHIFT PAGE_SHIFT
+#endif
+#define HPAGE_SIZE              ((1UL) << HPAGE_SHIFT)
+#define HPAGE_MASK              (~(HPAGE_SIZE - 1))
+#define HUGETLB_PAGE_ORDER      (HPAGE_SHIFT - PAGE_SHIFT)
+#define HUGE_MAX_HSTATE         (MMU_PAGE_COUNT-1)
+#endif
+
 /* We do define AT_SYSINFO_EHDR but don't use the gate mechanism */
 #define __HAVE_ARCH_GATE_AREA           1
 
@@ -158,6 +170,24 @@ extern phys_addr_t kernstart_addr;
 #define is_kernel_addr(x)       ((x) >= PAGE_OFFSET)
 #endif
 
+/*
+ * Use the top bit of the higher-level page table entries to indicate whether
+ * the entries we point to contain hugepages.  This works because we know that
+ * the page tables live in kernel space.  If we ever decide to support having
+ * page tables at arbitrary addresses, this breaks and will have to change.
+ */
+#ifdef CONFIG_PPC64
+#define PD_HUGE 0x8000000000000000
+#else
+#define PD_HUGE 0x80000000
+#endif
+
+/*
+ * Some number of bits at the level of the page table that points to
+ * a hugepte are used to encode the size.  This masks those bits.
+ */
+#define HUGEPD_SHIFT_MASK     0x3f
+
 #ifndef __ASSEMBLY__
 
 #undef STRICT_MM_TYPECHECKS
@@ -243,7 +273,6 @@ typedef unsigned long pgprot_t;
 #endif
 
 typedef struct { signed long pd; } hugepd_t;
-#define HUGEPD_SHIFT_MASK     0x3f
 
 #ifdef CONFIG_HUGETLB_PAGE
 static inline int hugepd_ok(hugepd_t hpd)
diff --git a/arch/powerpc/include/asm/page_64.h b/arch/powerpc/include/asm/page_64.h
index 9356262fd3cc..fb40ede6bc0d 100644
--- a/arch/powerpc/include/asm/page_64.h
+++ b/arch/powerpc/include/asm/page_64.h
@@ -64,17 +64,6 @@ extern void copy_page(void *to, void *from);
 /* Log 2 of page table size */
 extern u64 ppc64_pft_size;
 
-/* Large pages size */
-#ifdef CONFIG_HUGETLB_PAGE
-extern unsigned int HPAGE_SHIFT;
-#else
-#define HPAGE_SHIFT PAGE_SHIFT
-#endif
-#define HPAGE_SIZE              ((1UL) << HPAGE_SHIFT)
-#define HPAGE_MASK              (~(HPAGE_SIZE - 1))
-#define HUGETLB_PAGE_ORDER      (HPAGE_SHIFT - PAGE_SHIFT)
-#define HUGE_MAX_HSTATE         (MMU_PAGE_COUNT-1)
-
 #endif /* __ASSEMBLY__ */
 
 #ifdef CONFIG_PPC_MM_SLICES
diff --git a/arch/powerpc/include/asm/pte-book3e.h b/arch/powerpc/include/asm/pte-book3e.h
index 082d515930a2..0156702ba24e 100644
--- a/arch/powerpc/include/asm/pte-book3e.h
+++ b/arch/powerpc/include/asm/pte-book3e.h
@@ -72,6 +72,9 @@
 #define PTE_RPN_SHIFT   (24)
 #endif
 
+#define PTE_WIMGE_SHIFT (19)
+#define PTE_BAP_SHIFT   (2)
+
 /* On 32-bit, we never clear the top part of the PTE */
 #ifdef CONFIG_PPC32
 #define _PTE_NONE_MASK  0xffffffff00000000ULL
diff --git a/arch/powerpc/include/asm/reg_booke.h b/arch/powerpc/include/asm/reg_booke.h
index 9ec0b39f9ddc..28cdbd9f399c 100644
--- a/arch/powerpc/include/asm/reg_booke.h
+++ b/arch/powerpc/include/asm/reg_booke.h
@@ -548,6 +548,9 @@
 #define L1CSR1_ICFI     0x00000002      /* Instr Cache Flash Invalidate */
 #define L1CSR1_ICE      0x00000001      /* Instr Cache Enable */
 
+/* Bit definitions for L1CSR2. */
+#define L1CSR2_DCWS     0x40000000      /* Data Cache write shadow */
+
 /* Bit definitions for L2CSR0. */
 #define L2CSR0_L2E      0x80000000      /* L2 Cache Enable */
 #define L2CSR0_L2PE     0x40000000      /* L2 Cache Parity/ECC Enable */
diff --git a/arch/powerpc/include/asm/rtas.h b/arch/powerpc/include/asm/rtas.h
index 58625d1e7802..41f69ae79d4e 100644
--- a/arch/powerpc/include/asm/rtas.h
+++ b/arch/powerpc/include/asm/rtas.h
@@ -249,10 +249,12 @@ extern void pSeries_log_error(char *buf, unsigned int err_type, int fatal);
 #define ERR_FLAG_ALREADY_LOGGED 0x0
 #define ERR_FLAG_BOOT           0x1     /* log was pulled from NVRAM on boot */
 #define ERR_TYPE_RTAS_LOG       0x2     /* from rtas event-scan */
-#define ERR_TYPE_KERNEL_PANIC   0x4     /* from panic() */
+#define ERR_TYPE_KERNEL_PANIC   0x4     /* from die()/panic() */
+#define ERR_TYPE_KERNEL_PANIC_GZ 0x8    /* ditto, compressed */
 
 /* All the types and not flags */
-#define ERR_TYPE_MASK   (ERR_TYPE_RTAS_LOG | ERR_TYPE_KERNEL_PANIC)
+#define ERR_TYPE_MASK \
+        (ERR_TYPE_RTAS_LOG | ERR_TYPE_KERNEL_PANIC | ERR_TYPE_KERNEL_PANIC_GZ)
 
 #define RTAS_DEBUG KERN_DEBUG "RTAS: "
  
diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h
index 15a70b7f638b..adba970ce918 100644
--- a/arch/powerpc/include/asm/smp.h
+++ b/arch/powerpc/include/asm/smp.h
@@ -65,6 +65,7 @@ int generic_cpu_disable(void);
 void generic_cpu_die(unsigned int cpu);
 void generic_mach_cpu_die(void);
 void generic_set_cpu_dead(unsigned int cpu);
+int generic_check_cpu_restart(unsigned int cpu);
 #endif
 
 #ifdef CONFIG_PPC64
diff --git a/arch/powerpc/include/asm/sparsemem.h b/arch/powerpc/include/asm/sparsemem.h
index 54a47ea2c3aa..0c5fa3145615 100644
--- a/arch/powerpc/include/asm/sparsemem.h
+++ b/arch/powerpc/include/asm/sparsemem.h
@@ -16,7 +16,7 @@
 #endif /* CONFIG_SPARSEMEM */
 
 #ifdef CONFIG_MEMORY_HOTPLUG
-extern void create_section_mapping(unsigned long start, unsigned long end);
+extern int create_section_mapping(unsigned long start, unsigned long end);
 extern int remove_section_mapping(unsigned long start, unsigned long end);
 #ifdef CONFIG_NUMA
 extern int hot_add_scn_to_nid(unsigned long scn_addr);
diff --git a/arch/powerpc/include/asm/spu.h b/arch/powerpc/include/asm/spu.h
index 0c8b35d75232..4e360bd4a35a 100644
--- a/arch/powerpc/include/asm/spu.h
+++ b/arch/powerpc/include/asm/spu.h
@@ -26,6 +26,7 @@
 
 #include <linux/workqueue.h>
 #include <linux/sysdev.h>
+#include <linux/mutex.h>
 
 #define LS_SIZE (256 * 1024)
 #define LS_ADDR_MASK (LS_SIZE - 1)
diff --git a/arch/powerpc/include/asm/systbl.h b/arch/powerpc/include/asm/systbl.h
index fa0d27a400de..559ae1ee6706 100644
--- a/arch/powerpc/include/asm/systbl.h
+++ b/arch/powerpc/include/asm/systbl.h
@@ -354,3 +354,5 @@ COMPAT_SYS_SPU(clock_adjtime)
 SYSCALL_SPU(syncfs)
 COMPAT_SYS_SPU(sendmmsg)
 SYSCALL_SPU(setns)
+COMPAT_SYS(process_vm_readv)
+COMPAT_SYS(process_vm_writev)
diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h
index 7ef0d90defc8..1e104af08483 100644
--- a/arch/powerpc/include/asm/topology.h
+++ b/arch/powerpc/include/asm/topology.h
@@ -19,14 +19,10 @@ struct device_node;
 #define RECLAIM_DISTANCE 10
 
 /*
- * Before going off node we want the VM to try and reclaim from the local
- * node. It does this if the remote distance is larger than RECLAIM_DISTANCE.
- * With the default REMOTE_DISTANCE of 20 and the default RECLAIM_DISTANCE of
- * 20, we never reclaim and go off node straight away.
- *
- * To fix this we choose a smaller value of RECLAIM_DISTANCE.
+ * Avoid creating an extra level of balancing (SD_ALLNODES) on the largest
+ * POWER7 boxes which have a maximum of 32 nodes.
  */
-#define RECLAIM_DISTANCE 10
+#define SD_NODES_PER_DOMAIN 32
 
 #include <asm/mmzone.h>
 
@@ -69,11 +65,11 @@ static inline int pcibus_to_node(struct pci_bus *bus)
         .forkexec_idx           = 0,                                    \
                                                                         \
         .flags                  = 1*SD_LOAD_BALANCE                     \
-                                | 1*SD_BALANCE_NEWIDLE                  \
+                                | 0*SD_BALANCE_NEWIDLE                  \
                                 | 1*SD_BALANCE_EXEC                     \
                                 | 1*SD_BALANCE_FORK                     \
                                 | 0*SD_BALANCE_WAKE                     \
-                                | 0*SD_WAKE_AFFINE                      \
+                                | 1*SD_WAKE_AFFINE                      \
                                 | 0*SD_PREFER_LOCAL                     \
                                 | 0*SD_SHARE_CPUPOWER                   \
                                 | 0*SD_POWERSAVINGS_BALANCE             \
diff --git a/arch/powerpc/include/asm/udbg.h b/arch/powerpc/include/asm/udbg.h
index 93e05d1b34b2..8338aef5a4d3 100644
--- a/arch/powerpc/include/asm/udbg.h
+++ b/arch/powerpc/include/asm/udbg.h
@@ -54,6 +54,10 @@ extern void __init udbg_init_40x_realmode(void);
 extern void __init udbg_init_cpm(void);
 extern void __init udbg_init_usbgecko(void);
 extern void __init udbg_init_wsp(void);
+extern void __init udbg_init_ehv_bc(void);
+extern void __init udbg_init_ps3gelic(void);
+extern void __init udbg_init_debug_opal_raw(void);
+extern void __init udbg_init_debug_opal_hvsi(void);
 
 #endif /* __KERNEL__ */
 #endif /* _ASM_POWERPC_UDBG_H */
diff --git a/arch/powerpc/include/asm/unistd.h b/arch/powerpc/include/asm/unistd.h
index b8b3f599362b..d3d1b5efd7eb 100644
--- a/arch/powerpc/include/asm/unistd.h
+++ b/arch/powerpc/include/asm/unistd.h
@@ -373,10 +373,12 @@
 #define __NR_syncfs             348
 #define __NR_sendmmsg           349
 #define __NR_setns              350
+#define __NR_process_vm_readv   351
+#define __NR_process_vm_writev  352
 
 #ifdef __KERNEL__
 
-#define __NR_syscalls           351
+#define __NR_syscalls           353
 
 #define __NR__exit __NR_exit
 #define NR_syscalls     __NR_syscalls
diff --git a/arch/powerpc/include/asm/xics.h b/arch/powerpc/include/asm/xics.h
index b183a4062011..c48de98ba94e 100644
--- a/arch/powerpc/include/asm/xics.h
+++ b/arch/powerpc/include/asm/xics.h
@@ -15,8 +15,8 @@
 #define DEFAULT_PRIORITY        5
 
 /*
- * Mark IPIs as higher priority so we can take them inside interrupts that
- * arent marked IRQF_DISABLED
+ * Mark IPIs as higher priority so we can take them inside interrupts
+ * FIXME: still true now?
  */
 #define IPI_PRIORITY            4
 
@@ -27,10 +27,18 @@
 #define MAX_NUM_PRIORITIES      3
 
 /* Native ICP */
+#ifdef CONFIG_PPC_ICP_NATIVE
 extern int icp_native_init(void);
+#else
+static inline int icp_native_init(void) { return -ENODEV; }
+#endif
 
 /* PAPR ICP */
+#ifdef CONFIG_PPC_ICP_HV
 extern int icp_hv_init(void);
+#else
+static inline int icp_hv_init(void) { return -ENODEV; }
+#endif
 
 /* ICP ops */
 struct icp_ops {
@@ -51,7 +59,18 @@ extern const struct icp_ops *icp_ops;
 extern int ics_native_init(void);
 
 /* RTAS ICS */
+#ifdef CONFIG_PPC_ICS_RTAS
 extern int ics_rtas_init(void);
+#else
+static inline int ics_rtas_init(void) { return -ENODEV; }
+#endif
+
+/* HAL ICS */
+#ifdef CONFIG_PPC_POWERNV
+extern int ics_opal_init(void);
+#else
+static inline int ics_opal_init(void) { return -ENODEV; }
+#endif
 
 /* ICS instance, hooked up to chip_data of an irq */
 struct ics {
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 5f078bc2063e..7c5324f1ec9c 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -44,10 +44,14 @@
 #include <asm/compat.h>
 #include <asm/mmu.h>
 #include <asm/hvcall.h>
+#include <asm/xics.h>
 #endif
 #ifdef CONFIG_PPC_ISERIES
 #include <asm/iseries/alpaca.h>
 #endif
+#ifdef CONFIG_PPC_POWERNV
+#include <asm/opal.h>
+#endif
 #if defined(CONFIG_KVM) || defined(CONFIG_KVM_GUEST)
 #include <linux/kvm_host.h>
 #endif
@@ -449,8 +453,6 @@ int main(void)
 #ifdef CONFIG_PPC_BOOK3S
         DEFINE(VCPU_KVM, offsetof(struct kvm_vcpu, kvm));
         DEFINE(VCPU_VCPUID, offsetof(struct kvm_vcpu, vcpu_id));
-        DEFINE(VCPU_HOST_RETIP, offsetof(struct kvm_vcpu, arch.host_retip));
-        DEFINE(VCPU_HOST_MSR, offsetof(struct kvm_vcpu, arch.host_msr));
         DEFINE(VCPU_PURR, offsetof(struct kvm_vcpu, arch.purr));
         DEFINE(VCPU_SPURR, offsetof(struct kvm_vcpu, arch.spurr));
         DEFINE(VCPU_DSCR, offsetof(struct kvm_vcpu, arch.dscr));
@@ -458,14 +460,12 @@ int main(void)
         DEFINE(VCPU_UAMOR, offsetof(struct kvm_vcpu, arch.uamor));
         DEFINE(VCPU_CTRL, offsetof(struct kvm_vcpu, arch.ctrl));
         DEFINE(VCPU_DABR, offsetof(struct kvm_vcpu, arch.dabr));
-        DEFINE(VCPU_TRAMPOLINE_LOWMEM, offsetof(struct kvm_vcpu, arch.trampoline_lowmem));
-        DEFINE(VCPU_TRAMPOLINE_ENTER, offsetof(struct kvm_vcpu, arch.trampoline_enter));
-        DEFINE(VCPU_HIGHMEM_HANDLER, offsetof(struct kvm_vcpu, arch.highmem_handler));
-        DEFINE(VCPU_RMCALL, offsetof(struct kvm_vcpu, arch.rmcall));
         DEFINE(VCPU_HFLAGS, offsetof(struct kvm_vcpu, arch.hflags));
         DEFINE(VCPU_DEC, offsetof(struct kvm_vcpu, arch.dec));
         DEFINE(VCPU_DEC_EXPIRES, offsetof(struct kvm_vcpu, arch.dec_expires));
         DEFINE(VCPU_PENDING_EXC, offsetof(struct kvm_vcpu, arch.pending_exceptions));
+        DEFINE(VCPU_CEDED, offsetof(struct kvm_vcpu, arch.ceded));
+        DEFINE(VCPU_PRODDED, offsetof(struct kvm_vcpu, arch.prodded));
         DEFINE(VCPU_VPA, offsetof(struct kvm_vcpu, arch.vpa));
         DEFINE(VCPU_MMCR, offsetof(struct kvm_vcpu, arch.mmcr));
         DEFINE(VCPU_PMC, offsetof(struct kvm_vcpu, arch.pmc));
@@ -481,6 +481,7 @@ int main(void)
         DEFINE(VCORE_ENTRY_EXIT, offsetof(struct kvmppc_vcore, entry_exit_count));
         DEFINE(VCORE_NAP_COUNT, offsetof(struct kvmppc_vcore, nap_count));
         DEFINE(VCORE_IN_GUEST, offsetof(struct kvmppc_vcore, in_guest));
+        DEFINE(VCORE_NAPPING_THREADS, offsetof(struct kvmppc_vcore, napping_threads));
         DEFINE(VCPU_SVCPU, offsetof(struct kvmppc_vcpu_book3s, shadow_vcpu) -
                            offsetof(struct kvmppc_vcpu_book3s, vcpu));
         DEFINE(VCPU_SLB_E, offsetof(struct kvmppc_slb, orige));
@@ -537,6 +538,8 @@ int main(void)
         HSTATE_FIELD(HSTATE_SCRATCH0, scratch0);
         HSTATE_FIELD(HSTATE_SCRATCH1, scratch1);
         HSTATE_FIELD(HSTATE_IN_GUEST, in_guest);
+        HSTATE_FIELD(HSTATE_RESTORE_HID5, restore_hid5);
+        HSTATE_FIELD(HSTATE_NAPPING, napping);
 
 #ifdef CONFIG_KVM_BOOK3S_64_HV
         HSTATE_FIELD(HSTATE_KVM_VCPU, kvm_vcpu);
@@ -549,6 +552,7 @@ int main(void)
         HSTATE_FIELD(HSTATE_DSCR, host_dscr);
         HSTATE_FIELD(HSTATE_DABR, dabr);
         HSTATE_FIELD(HSTATE_DECEXP, dec_expires);
+        DEFINE(IPI_PRIORITY, IPI_PRIORITY);
 #endif /* CONFIG_KVM_BOOK3S_64_HV */
 
 #else /* CONFIG_PPC_BOOK3S */
@@ -609,5 +613,12 @@ int main(void)
                                         arch.timing_last_enter.tv32.tbl));
 #endif
 
+#ifdef CONFIG_PPC_POWERNV
+        DEFINE(OPAL_MC_GPR3, offsetof(struct opal_machine_check_event, gpr3));
+        DEFINE(OPAL_MC_SRR0, offsetof(struct opal_machine_check_event, srr0));
+        DEFINE(OPAL_MC_SRR1, offsetof(struct opal_machine_check_event, srr1));
+        DEFINE(PACA_OPAL_MC_EVT, offsetof(struct paca_struct, opal_mc_evt));
+#endif
+
         return 0;
 }
diff --git a/arch/powerpc/kernel/btext.c b/arch/powerpc/kernel/btext.c
index 60b3e377b1e4..ac8f52732fde 100644
--- a/arch/powerpc/kernel/btext.c
+++ b/arch/powerpc/kernel/btext.c
@@ -6,7 +6,7 @@
 #include <linux/kernel.h>
 #include <linux/string.h>
 #include <linux/init.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/memblock.h>
 
 #include <asm/sections.h>
diff --git a/arch/powerpc/kernel/clock.c b/arch/powerpc/kernel/clock.c
index ce668f545758..a764b47791e8 100644
--- a/arch/powerpc/kernel/clock.c
+++ b/arch/powerpc/kernel/clock.c
@@ -6,7 +6,7 @@
 #include <linux/clk.h>
 #include <linux/err.h>
 #include <linux/errno.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <asm/clk_interface.h>
 
 struct clk_interface clk_functions;
diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index fa44ff538861..edae5bb06f1f 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -14,7 +14,7 @@
 #include <linux/sched.h>
 #include <linux/threads.h>
 #include <linux/init.h>
-#include <linux/module.h>
+#include <linux/export.h>
 
 #include <asm/oprofile_impl.h>
 #include <asm/cputable.h>
diff --git a/arch/powerpc/kernel/crash.c b/arch/powerpc/kernel/crash.c
index cc6a9d5d69ab..d879809d5c45 100644
--- a/arch/powerpc/kernel/crash.c
+++ b/arch/powerpc/kernel/crash.c
@@ -17,6 +17,7 @@
 #include <linux/reboot.h>
 #include <linux/kexec.h>
 #include <linux/bootmem.h>
+#include <linux/export.h>
 #include <linux/crash_dump.h>
 #include <linux/delay.h>
 #include <linux/elf.h>
diff --git a/arch/powerpc/kernel/dma-iommu.c b/arch/powerpc/kernel/dma-iommu.c
index e7554154a6de..3f6464b4d970 100644
--- a/arch/powerpc/kernel/dma-iommu.c
+++ b/arch/powerpc/kernel/dma-iommu.c
@@ -5,6 +5,7 @@
  * busses using the iommu infrastructure
  */
 
+#include <linux/export.h>
 #include <asm/iommu.h>
 
 /*
@@ -90,13 +91,27 @@ static int dma_iommu_dma_supported(struct device *dev, u64 mask)
                 return 1;
 }
 
+static u64 dma_iommu_get_required_mask(struct device *dev)
+{
+        struct iommu_table *tbl = get_iommu_table_base(dev);
+        u64 mask;
+        if (!tbl)
+                return 0;
+
+        mask = 1ULL < (fls_long(tbl->it_offset + tbl->it_size) - 1);
+        mask += mask - 1;
+
+        return mask;
+}
+
 struct dma_map_ops dma_iommu_ops = {
-        .alloc_coherent = dma_iommu_alloc_coherent,
-        .free_coherent  = dma_iommu_free_coherent,
-        .map_sg         = dma_iommu_map_sg,
-        .unmap_sg       = dma_iommu_unmap_sg,
-        .dma_supported  = dma_iommu_dma_supported,
-        .map_page       = dma_iommu_map_page,
-        .unmap_page     = dma_iommu_unmap_page,
+        .alloc_coherent         = dma_iommu_alloc_coherent,
+        .free_coherent          = dma_iommu_free_coherent,
+        .map_sg                 = dma_iommu_map_sg,
+        .unmap_sg               = dma_iommu_unmap_sg,
+        .dma_supported          = dma_iommu_dma_supported,
+        .map_page               = dma_iommu_map_page,
+        .unmap_page             = dma_iommu_unmap_page,
+        .get_required_mask      = dma_iommu_get_required_mask,
 };
 EXPORT_SYMBOL(dma_iommu_ops);
diff --git a/arch/powerpc/kernel/dma-swiotlb.c b/arch/powerpc/kernel/dma-swiotlb.c
index 4295e0b94b2d..1ebc9189aada 100644
--- a/arch/powerpc/kernel/dma-swiotlb.c
+++ b/arch/powerpc/kernel/dma-swiotlb.c
@@ -24,6 +24,21 @@
 
 unsigned int ppc_swiotlb_enable;
 
+static u64 swiotlb_powerpc_get_required(struct device *dev)
+{
+        u64 end, mask, max_direct_dma_addr = dev->archdata.max_direct_dma_addr;
+
+        end = memblock_end_of_DRAM();
+        if (max_direct_dma_addr && end > max_direct_dma_addr)
+                end = max_direct_dma_addr;
+        end += get_dma_offset(dev);
+
+        mask = 1ULL << (fls64(end) - 1);
+        mask += mask - 1;
+
+        return mask;
+}
+
 /*
  * At the moment, all platforms that use this code only require
  * swiotlb to be used if we're operating on HIGHMEM.  Since
@@ -44,6 +59,7 @@ struct dma_map_ops swiotlb_dma_ops = {
         .sync_sg_for_cpu = swiotlb_sync_sg_for_cpu,
         .sync_sg_for_device = swiotlb_sync_sg_for_device,
         .mapping_error = swiotlb_dma_mapping_error,
+        .get_required_mask = swiotlb_powerpc_get_required,
 };
 
 void pci_dma_dev_setup_swiotlb(struct pci_dev *pdev)
diff --git a/arch/powerpc/kernel/dma.c b/arch/powerpc/kernel/dma.c
index 4f0959fbfbee..7d0233c12ee3 100644
--- a/arch/powerpc/kernel/dma.c
+++ b/arch/powerpc/kernel/dma.c
@@ -10,6 +10,7 @@
 #include <linux/dma-debug.h>
 #include <linux/gfp.h>
 #include <linux/memblock.h>
+#include <linux/export.h>
 #include <asm/bug.h>
 #include <asm/abs_addr.h>
 #include <asm/machdep.h>
@@ -96,6 +97,18 @@ static int dma_direct_dma_supported(struct device *dev, u64 mask)
 #endif
 }
 
+static u64 dma_direct_get_required_mask(struct device *dev)
+{
+        u64 end, mask;
+
+        end = memblock_end_of_DRAM() + get_dma_offset(dev);
+
+        mask = 1ULL << (fls64(end) - 1);
+        mask += mask - 1;
+
+        return mask;
+}
+
 static inline dma_addr_t dma_direct_map_page(struct device *dev,
                                              struct page *page,
                                              unsigned long offset,
@@ -137,13 +150,14 @@ static inline void dma_direct_sync_single(struct device *dev,
 #endif
 
 struct dma_map_ops dma_direct_ops = {
-        .alloc_coherent = dma_direct_alloc_coherent,
-        .free_coherent  = dma_direct_free_coherent,
-        .map_sg         = dma_direct_map_sg,
-        .unmap_sg       = dma_direct_unmap_sg,
-        .dma_supported  = dma_direct_dma_supported,
-        .map_page       = dma_direct_map_page,
-        .unmap_page     = dma_direct_unmap_page,
+        .alloc_coherent                 = dma_direct_alloc_coherent,
+        .free_coherent                  = dma_direct_free_coherent,
+        .map_sg                         = dma_direct_map_sg,
+        .unmap_sg                       = dma_direct_unmap_sg,
+        .dma_supported                  = dma_direct_dma_supported,
+        .map_page                       = dma_direct_map_page,
+        .unmap_page                     = dma_direct_unmap_page,
+        .get_required_mask              = dma_direct_get_required_mask,
 #ifdef CONFIG_NOT_COHERENT_CACHE
         .sync_single_for_cpu            = dma_direct_sync_single,
         .sync_single_for_device         = dma_direct_sync_single,
@@ -170,6 +184,23 @@ int dma_set_mask(struct device *dev, u64 dma_mask)
 }
 EXPORT_SYMBOL(dma_set_mask);
 
+u64 dma_get_required_mask(struct device *dev)
+{
+        struct dma_map_ops *dma_ops = get_dma_ops(dev);
+
+        if (ppc_md.dma_get_required_mask)
+                return ppc_md.dma_get_required_mask(dev);
+
+        if (unlikely(dma_ops == NULL))
+                return 0;
+
+        if (dma_ops->get_required_mask)
+                return dma_ops->get_required_mask(dev);
+
+        return DMA_BIT_MASK(8 * sizeof(dma_addr_t));
+}
+EXPORT_SYMBOL_GPL(dma_get_required_mask);
+
 static int __init dma_init(void)
 {
        dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES);
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 41b02c792aa3..cf9c69b9189c 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -267,7 +267,7 @@ vsx_unavailable_pSeries_1:
 
 #ifdef CONFIG_CBE_RAS
         STD_EXCEPTION_HV(0x1200, 0x1202, cbe_system_error)
-        KVM_HANDLER_PR_SKIP(PACA_EXGEN, EXC_HV, 0x1202)
+        KVM_HANDLER_SKIP(PACA_EXGEN, EXC_HV, 0x1202)
 #endif /* CONFIG_CBE_RAS */
 
         STD_EXCEPTION_PSERIES(0x1300, 0x1300, instruction_breakpoint)
@@ -275,7 +275,7 @@ vsx_unavailable_pSeries_1:
 
 #ifdef CONFIG_CBE_RAS
         STD_EXCEPTION_HV(0x1600, 0x1602, cbe_maintenance)
-        KVM_HANDLER_PR_SKIP(PACA_EXGEN, EXC_HV, 0x1602)
+        KVM_HANDLER_SKIP(PACA_EXGEN, EXC_HV, 0x1602)
 #endif /* CONFIG_CBE_RAS */
 
         STD_EXCEPTION_PSERIES(0x1700, 0x1700, altivec_assist)
@@ -283,7 +283,7 @@ vsx_unavailable_pSeries_1:
 
 #ifdef CONFIG_CBE_RAS
         STD_EXCEPTION_HV(0x1800, 0x1802, cbe_thermal)
-        KVM_HANDLER_PR_SKIP(PACA_EXGEN, EXC_HV, 0x1802)
+        KVM_HANDLER_SKIP(PACA_EXGEN, EXC_HV, 0x1802)
 #endif /* CONFIG_CBE_RAS */
 
         . = 0x3000
@@ -427,16 +427,6 @@ slb_miss_user_pseries:
         b       .                               /* prevent spec. execution */
 #endif /* __DISABLED__ */
 
-/* KVM's trampoline code needs to be close to the interrupt handlers */
-
-#ifdef CONFIG_KVM_BOOK3S_64_HANDLER
-#ifdef CONFIG_KVM_BOOK3S_PR
-#include "../kvm/book3s_rmhandlers.S"
-#else
-#include "../kvm/book3s_hv_rmhandlers.S"
-#endif
-#endif
-
         .align  7
         .globl  __end_interrupts
 __end_interrupts:
@@ -1143,7 +1133,7 @@ _GLOBAL(do_stab_bolted)
         rfid
         b       .       /* prevent speculative execution */
 
-#ifdef CONFIG_PPC_PSERIES
+#if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV)
 /*
  * Data area reserved for FWNMI option.
  * This address (0x7000) is fixed by the RPA.
@@ -1151,7 +1141,7 @@ _GLOBAL(do_stab_bolted)
         .= 0x7000
         .globl fwnmi_data_area
 fwnmi_data_area:
-#endif /* CONFIG_PPC_PSERIES */
+#endif /* defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV) */
 
         /* iSeries does not use the FWNMI stuff, so it is safe to put
          * this here, even if we later allow kernels that will boot on
@@ -1176,9 +1166,12 @@ xLparMap:
 
 #endif /* CONFIG_PPC_ISERIES */
 
-#ifdef CONFIG_PPC_PSERIES
+#if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV)
+        /* pseries and powernv need to keep the whole page from
+         * 0x7000 to 0x8000 free for use by the firmware
+         */
         . = 0x8000
-#endif /* CONFIG_PPC_PSERIES */
+#endif /* defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV) */
 
 /*
  * Space for CPU0's segment table.
@@ -1193,3 +1186,19 @@ xLparMap:
         .globl initial_stab
 initial_stab:
         .space  4096
+#ifdef CONFIG_PPC_POWERNV
+_GLOBAL(opal_mc_secondary_handler)
+        HMT_MEDIUM
+        SET_SCRATCH0(r13)
+        GET_PACA(r13)
+        clrldi  r3,r3,2
+        tovirt(r3,r3)
+        std     r3,PACA_OPAL_MC_EVT(r13)
+        ld      r13,OPAL_MC_SRR0(r3)
+        mtspr   SPRN_SRR0,r13
+        ld      r13,OPAL_MC_SRR1(r3)
+        mtspr   SPRN_SRR1,r13
+        ld      r3,OPAL_MC_GPR3(r3)
+        GET_SCRATCH0(r13)
+        b       machine_check_pSeries
+#endif /* CONFIG_PPC_POWERNV */
diff --git a/arch/powerpc/kernel/firmware.c b/arch/powerpc/kernel/firmware.c
index 6b1f4271eb53..2eae4478f7a1 100644
--- a/arch/powerpc/kernel/firmware.c
+++ b/arch/powerpc/kernel/firmware.c
@@ -13,7 +13,8 @@
  *  2 of the License, or (at your option) any later version.
  */
 
-#include <linux/module.h>
+#include <linux/export.h>
+#include <linux/cache.h>
 
 #include <asm/firmware.h>
 
diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_32.S
index ba250d505e07..0654dba2c1f1 100644
--- a/arch/powerpc/kernel/head_32.S
+++ b/arch/powerpc/kernel/head_32.S
@@ -139,8 +139,7 @@ __start:
         trap
 #endif /* CONFIG_PPC_PMAC */
 
-1:      mr      r31,r3                  /* save parameters */
-        mr      r30,r4
+1:      mr      r31,r3                  /* save device tree ptr */
         li      r24,0                   /* cpu # */
 
 /*
@@ -964,8 +963,8 @@ start_here:
  * Do early platform-specific initialization,
  * and set up the MMU.
  */
-        mr      r3,r31
-        mr      r4,r30
+        li      r3,0
+        mr      r4,r31
         bl      machine_init
         bl      __save_cpu_setup
         bl      MMU_init
diff --git a/arch/powerpc/kernel/head_40x.S b/arch/powerpc/kernel/head_40x.S
index a91626d87fc9..872a6af83bad 100644
--- a/arch/powerpc/kernel/head_40x.S
+++ b/arch/powerpc/kernel/head_40x.S
@@ -58,13 +58,7 @@
 _ENTRY(_stext);
 _ENTRY(_start);
 
-        /* Save parameters we are passed.
-        */
-        mr      r31,r3
-        mr      r30,r4
-        mr      r29,r5
-        mr      r28,r6
-        mr      r27,r7
+        mr      r31,r3                  /* save device tree ptr */
 
         /* We have to turn on the MMU right away so we get cache modes
          * set correctly.
@@ -849,11 +843,8 @@ start_here:
 /*
  * Decide what sort of machine this is and initialize the MMU.
  */
-        mr      r3,r31
-        mr      r4,r30
-        mr      r5,r29
-        mr      r6,r28
-        mr      r7,r27
+        li      r3,0
+        mr      r4,r31
         bl      machine_init
         bl      MMU_init
 
diff --git a/arch/powerpc/kernel/head_44x.S b/arch/powerpc/kernel/head_44x.S
index f8e971ba94f5..b725dab0f88a 100644
--- a/arch/powerpc/kernel/head_44x.S
+++ b/arch/powerpc/kernel/head_44x.S
@@ -61,14 +61,7 @@ _ENTRY(_start);
          * of abatron_pteptrs
          */
         nop
-/*
- * Save parameters we are passed
- */
-        mr      r31,r3
-        mr      r30,r4
-        mr      r29,r5
-        mr      r28,r6
-        mr      r27,r7
+        mr      r31,r3          /* save device tree ptr */
         li      r24,0           /* CPU number */
 
         bl      init_cpu_state
@@ -120,11 +113,8 @@ _ENTRY(_start);
 /*
  * Decide what sort of machine this is and initialize the MMU.
  */
-        mr      r3,r31
-        mr      r4,r30
-        mr      r5,r29
-        mr      r6,r28
-        mr      r7,r27
+        li      r3,0
+        mr      r4,r31
         bl      machine_init
         bl      MMU_init
 
diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S
index 3564c49c683e..06c7251c1bf7 100644
--- a/arch/powerpc/kernel/head_64.S
+++ b/arch/powerpc/kernel/head_64.S
@@ -51,6 +51,11 @@
  *  For pSeries or server processors:
  *   1. The MMU is off & open firmware is running in real mode.
  *   2. The kernel is entered at __start
+ * -or- For OPAL entry:
+ *   1. The MMU is off, processor in HV mode, primary CPU enters at 0
+ *      with device-tree in gpr3. We also get OPAL base in r8 and
+ *      entry in r9 for debugging purposes
+ *   2. Secondary processors enter at 0x60 with PIR in gpr3
  *
  *  For iSeries:
  *   1. The MMU is on (as it always is for iSeries)
@@ -331,6 +336,11 @@ _GLOBAL(__start_initialization_multiplatform)
         /* Save parameters */
         mr      r31,r3
         mr      r30,r4
+#ifdef CONFIG_PPC_EARLY_DEBUG_OPAL
+        /* Save OPAL entry */
+        mr      r28,r8
+        mr      r29,r9
+#endif
 
 #ifdef CONFIG_PPC_BOOK3E
         bl      .start_initialization_book3e
@@ -674,9 +684,9 @@ _GLOBAL(enable_64b_mode)
 _GLOBAL(relative_toc)
         mflr    r0
         bcl     20,31,$+4
-0:      mflr    r9
-        ld      r2,(p_toc - 0b)(r9)
-        add     r2,r2,r9
+0:      mflr    r11
+        ld      r2,(p_toc - 0b)(r11)
+        add     r2,r2,r11
         mtlr    r0
         blr
 
@@ -707,6 +717,12 @@ _INIT_STATIC(start_here_multiplatform)
         bdnz    3b
 4:
 
+#ifdef CONFIG_PPC_EARLY_DEBUG_OPAL
+        /* Setup OPAL entry */
+        std     r28,0(r11);
+        std     r29,8(r11);
+#endif
+
 #ifndef CONFIG_PPC_BOOK3E
         mfmsr   r6
         ori     r6,r6,MSR_RI
diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S
index 1cbf64e6b416..b68cb173ba2c 100644
--- a/arch/powerpc/kernel/head_8xx.S
+++ b/arch/powerpc/kernel/head_8xx.S
@@ -76,11 +76,7 @@ _ENTRY(_start);
  */
         .globl  __start
 __start:
-        mr      r31,r3                  /* save parameters */
-        mr      r30,r4
-        mr      r29,r5
-        mr      r28,r6
-        mr      r27,r7
+        mr      r31,r3                  /* save device tree ptr */
 
         /* We have to turn on the MMU right away so we get cache modes
          * set correctly.
@@ -723,11 +719,8 @@ start_here:
 /*
  * Decide what sort of machine this is and initialize the MMU.
  */
-        mr      r3,r31
-        mr      r4,r30
-        mr      r5,r29
-        mr      r6,r28
-        mr      r7,r27
+        li      r3,0
+        mr      r4,r31
         bl      machine_init
         bl      MMU_init
 
diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S
index 50845924b7d9..9f5d210ddf3f 100644
--- a/arch/powerpc/kernel/head_fsl_booke.S
+++ b/arch/powerpc/kernel/head_fsl_booke.S
@@ -63,17 +63,30 @@ _ENTRY(_start);
          * of abatron_pteptrs
          */
         nop
-/*
- * Save parameters we are passed
- */
-        mr      r31,r3
-        mr      r30,r4
-        mr      r29,r5
-        mr      r28,r6
-        mr      r27,r7
-        li      r25,0           /* phys kernel start (low) */
-        li      r24,0           /* CPU number */
-        li      r23,0           /* phys kernel start (high) */
+
+        /* Translate device tree address to physical, save in r30/r31 */
+        mfmsr   r16
+        mfspr   r17,SPRN_PID
+        rlwinm  r17,r17,16,0x3fff0000   /* turn PID into MAS6[SPID] */
+        rlwimi  r17,r16,28,0x00000001   /* turn MSR[DS] into MAS6[SAS] */
+        mtspr   SPRN_MAS6,r17
+
+        tlbsx   0,r3                    /* must succeed */
+
+        mfspr   r16,SPRN_MAS1
+        mfspr   r20,SPRN_MAS3
+        rlwinm  r17,r16,25,0x1f         /* r17 = log2(page size) */
+        li      r18,1024
+        slw     r18,r18,r17             /* r18 = page size */
+        addi    r18,r18,-1
+        and     r19,r3,r18              /* r19 = page offset */
+        andc    r31,r20,r18             /* r31 = page base */
+        or      r31,r31,r19             /* r31 = devtree phys addr */
+        mfspr   r30,SPRN_MAS7
+
+        li      r25,0                   /* phys kernel start (low) */
+        li      r24,0                   /* CPU number */
+        li      r23,0                   /* phys kernel start (high) */
 
 /* We try to not make any assumptions about how the boot loader
  * setup or used the TLBs.  We invalidate all mappings from the
@@ -198,11 +211,8 @@ _ENTRY(__early_start)
 /*
  * Decide what sort of machine this is and initialize the MMU.
  */
-        mr      r3,r31
-        mr      r4,r30
-        mr      r5,r29
-        mr      r6,r28
-        mr      r7,r27
+        mr      r3,r30
+        mr      r4,r31
         bl      machine_init
         bl      MMU_init
 
@@ -236,8 +246,24 @@ _ENTRY(__early_start)
  * if we find the pte (fall through):
  *   r11 is low pte word
  *   r12 is pointer to the pte
+ *   r10 is the pshift from the PGD, if we're a hugepage
  */
 #ifdef CONFIG_PTE_64BIT
+#ifdef CONFIG_HUGETLB_PAGE
+#define FIND_PTE        \
+        rlwinm  r12, r10, 13, 19, 29;   /* Compute pgdir/pmd offset */  \
+        lwzx    r11, r12, r11;          /* Get pgd/pmd entry */         \
+        rlwinm. r12, r11, 0, 0, 20;     /* Extract pt base address */   \
+        blt     1000f;                  /* Normal non-huge page */      \
+        beq     2f;                     /* Bail if no table */          \
+        oris    r11, r11, PD_HUGE@h;    /* Put back address bit */      \
+        andi.   r10, r11, HUGEPD_SHIFT_MASK@l; /* extract size field */ \
+        xor     r12, r10, r11;          /* drop size bits from pointer */ \
+        b       1001f;                                                  \
+1000:   rlwimi  r12, r10, 23, 20, 28;   /* Compute pte address */       \
+        li      r10, 0;                 /* clear r10 */                 \
+1001:   lwz     r11, 4(r12);            /* Get pte entry */
+#else
 #define FIND_PTE        \
         rlwinm  r12, r10, 13, 19, 29;   /* Compute pgdir/pmd offset */  \
         lwzx    r11, r12, r11;          /* Get pgd/pmd entry */         \
@@ -245,7 +271,8 @@ _ENTRY(__early_start)
         beq     2f;                     /* Bail if no table */          \
         rlwimi  r12, r10, 23, 20, 28;   /* Compute pte address */       \
         lwz     r11, 4(r12);            /* Get pte entry */
-#else
+#endif /* HUGEPAGE */
+#else /* !PTE_64BIT */
 #define FIND_PTE        \
         rlwimi  r11, r10, 12, 20, 29;   /* Create L1 (pgdir/pmd) address */     \
         lwz     r11, 0(r11);            /* Get L1 entry */                      \
@@ -402,8 +429,8 @@ interrupt_base:
 
 #ifdef CONFIG_PTE_64BIT
 #ifdef CONFIG_SMP
-        subf    r10,r11,r12             /* create false data dep */
-        lwzx    r13,r11,r10             /* Get upper pte bits */
+        subf    r13,r11,r12             /* create false data dep */
+        lwzx    r13,r11,r13             /* Get upper pte bits */
 #else
         lwz     r13,0(r12)              /* Get upper pte bits */
 #endif
@@ -483,8 +510,8 @@ interrupt_base:
 
 #ifdef CONFIG_PTE_64BIT
 #ifdef CONFIG_SMP
-        subf    r10,r11,r12             /* create false data dep */
-        lwzx    r13,r11,r10             /* Get upper pte bits */
+        subf    r13,r11,r12             /* create false data dep */
+        lwzx    r13,r11,r13             /* Get upper pte bits */
 #else
         lwz     r13,0(r12)              /* Get upper pte bits */
 #endif
@@ -548,7 +575,7 @@ interrupt_base:
 /*
  * Both the instruction and data TLB miss get to this
  * point to load the TLB.
- *      r10 - available to use
+ *      r10 - tsize encoding (if HUGETLB_PAGE) or available to use
  *      r11 - TLB (info from Linux PTE)
  *      r12 - available to use
  *      r13 - upper bits of PTE (if PTE_64BIT) or available to use
@@ -558,21 +585,73 @@ interrupt_base:
  *      Upon exit, we reload everything and RFI.
  */
 finish_tlb_load:
+#ifdef CONFIG_HUGETLB_PAGE
+        cmpwi   6, r10, 0                       /* check for huge page */
+        beq     6, finish_tlb_load_cont         /* !huge */
+
+        /* Alas, we need more scratch registers for hugepages */
+        mfspr   r12, SPRN_SPRG_THREAD
+        stw     r14, THREAD_NORMSAVE(4)(r12)
+        stw     r15, THREAD_NORMSAVE(5)(r12)
+        stw     r16, THREAD_NORMSAVE(6)(r12)
+        stw     r17, THREAD_NORMSAVE(7)(r12)
+
+        /* Get the next_tlbcam_idx percpu var */
+#ifdef CONFIG_SMP
+        lwz     r12, THREAD_INFO-THREAD(r12)
+        lwz     r15, TI_CPU(r12)
+        lis     r14, __per_cpu_offset@h
+        ori     r14, r14, __per_cpu_offset@l
+        rlwinm  r15, r15, 2, 0, 29
+        lwzx    r16, r14, r15
+#else
+        li      r16, 0
+#endif
+        lis     r17, next_tlbcam_idx@h
+        ori     r17, r17, next_tlbcam_idx@l
+        add     r17, r17, r16                   /* r17 = *next_tlbcam_idx */
+        lwz     r15, 0(r17)                     /* r15 = next_tlbcam_idx */
+
+        lis     r14, MAS0_TLBSEL(1)@h           /* select TLB1 (TLBCAM) */
+        rlwimi  r14, r15, 16, 4, 15             /* next_tlbcam_idx entry */
+        mtspr   SPRN_MAS0, r14
+
+        /* Extract TLB1CFG(NENTRY) */
+        mfspr   r16, SPRN_TLB1CFG
+        andi.   r16, r16, 0xfff
+
+        /* Update next_tlbcam_idx, wrapping when necessary */
+        addi    r15, r15, 1
+        cmpw    r15, r16
+        blt     100f
+        lis     r14, tlbcam_index@h
+        ori     r14, r14, tlbcam_index@l
+        lwz     r15, 0(r14)
+100:    stw     r15, 0(r17)
+
+        /*
+         * Calc MAS1_TSIZE from r10 (which has pshift encoded)
+         * tlb_enc = (pshift - 10).
+         */
+        subi    r15, r10, 10
+        mfspr   r16, SPRN_MAS1
+        rlwimi  r16, r15, 7, 20, 24
+        mtspr   SPRN_MAS1, r16
+
+        /* copy the pshift for use later */
+        mr      r14, r10
+
+        /* fall through */
+
+#endif /* CONFIG_HUGETLB_PAGE */
+
         /*
          * We set execute, because we don't have the granularity to
          * properly set this at the page level (Linux problem).
          * Many of these bits are software only.  Bits we don't set
          * here we (properly should) assume have the appropriate value.
          */
-
-        mfspr   r12, SPRN_MAS2
-#ifdef CONFIG_PTE_64BIT
-        rlwimi  r12, r11, 32-19, 27, 31 /* extract WIMGE from pte */
-#else
-        rlwimi  r12, r11, 26, 27, 31    /* extract WIMGE from pte */
-#endif
-        mtspr   SPRN_MAS2, r12
-
+finish_tlb_load_cont:
 #ifdef CONFIG_PTE_64BIT
         rlwinm  r12, r11, 32-2, 26, 31  /* Move in perm bits */
         andi.   r10, r11, _PAGE_DIRTY
@@ -581,22 +660,40 @@ finish_tlb_load:
         andc    r12, r12, r10
 1:      rlwimi  r12, r13, 20, 0, 11     /* grab RPN[32:43] */
         rlwimi  r12, r11, 20, 12, 19    /* grab RPN[44:51] */
-        mtspr   SPRN_MAS3, r12
+2:      mtspr   SPRN_MAS3, r12
 BEGIN_MMU_FTR_SECTION
         srwi    r10, r13, 12            /* grab RPN[12:31] */
         mtspr   SPRN_MAS7, r10
 END_MMU_FTR_SECTION_IFSET(MMU_FTR_BIG_PHYS)
 #else
         li      r10, (_PAGE_EXEC | _PAGE_PRESENT)
+        mr      r13, r11
         rlwimi  r10, r11, 31, 29, 29    /* extract _PAGE_DIRTY into SW */
         and     r12, r11, r10
         andi.   r10, r11, _PAGE_USER    /* Test for _PAGE_USER */
         slwi    r10, r12, 1
         or      r10, r10, r12
         iseleq  r12, r12, r10
-        rlwimi  r11, r12, 0, 20, 31     /* Extract RPN from PTE and merge with perms */
-        mtspr   SPRN_MAS3, r11
+        rlwimi  r13, r12, 0, 20, 31     /* Get RPN from PTE, merge w/ perms */
+        mtspr   SPRN_MAS3, r13
 #endif
+
+        mfspr   r12, SPRN_MAS2
+#ifdef CONFIG_PTE_64BIT
+        rlwimi  r12, r11, 32-19, 27, 31 /* extract WIMGE from pte */
+#else
+        rlwimi  r12, r11, 26, 27, 31    /* extract WIMGE from pte */
+#endif
+#ifdef CONFIG_HUGETLB_PAGE
+        beq     6, 3f                   /* don't mask if page isn't huge */
+        li      r13, 1
+        slw     r13, r13, r14
+        subi    r13, r13, 1
+        rlwinm  r13, r13, 0, 0, 19      /* bottom bits used for WIMGE/etc */
+        andc    r12, r12, r13           /* mask off ea bits within the page */
+#endif
+3:      mtspr   SPRN_MAS2, r12
+
 #ifdef CONFIG_E200
         /* Round robin TLB1 entries assignment */
         mfspr   r12, SPRN_MAS0
@@ -622,11 +719,19 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_BIG_PHYS)
         mtspr   SPRN_MAS0,r12
 #endif /* CONFIG_E200 */
 
+tlb_write_entry:
         tlbwe
 
         /* Done...restore registers and get out of here.  */
         mfspr   r10, SPRN_SPRG_THREAD
-        lwz     r11, THREAD_NORMSAVE(3)(r10)
+#ifdef CONFIG_HUGETLB_PAGE
+        beq     6, 8f /* skip restore for 4k page faults */
+        lwz     r14, THREAD_NORMSAVE(4)(r10)
+        lwz     r15, THREAD_NORMSAVE(5)(r10)
+        lwz     r16, THREAD_NORMSAVE(6)(r10)
+        lwz     r17, THREAD_NORMSAVE(7)(r10)
+#endif
+8:      lwz     r11, THREAD_NORMSAVE(3)(r10)
         mtcr    r11
         lwz     r13, THREAD_NORMSAVE(2)(r10)
         lwz     r12, THREAD_NORMSAVE(1)(r10)
diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c
index 5ecd0401cdb1..2bc0584be81c 100644
--- a/arch/powerpc/kernel/hw_breakpoint.c
+++ b/arch/powerpc/kernel/hw_breakpoint.c
@@ -27,7 +27,6 @@
 #include <linux/kprobes.h>
 #include <linux/percpu.h>
 #include <linux/kernel.h>
-#include <linux/module.h>
 #include <linux/sched.h>
 #include <linux/init.h>
 #include <linux/smp.h>
diff --git a/arch/powerpc/kernel/ibmebus.c b/arch/powerpc/kernel/ibmebus.c
index 28581f1ad2c0..d39ae606ff8d 100644
--- a/arch/powerpc/kernel/ibmebus.c
+++ b/arch/powerpc/kernel/ibmebus.c
@@ -37,12 +37,14 @@
  */
 
 #include <linux/init.h>
+#include <linux/export.h>
 #include <linux/console.h>
 #include <linux/kobject.h>
 #include <linux/dma-mapping.h>
 #include <linux/interrupt.h>
 #include <linux/of.h>
 #include <linux/slab.h>
+#include <linux/stat.h>
 #include <linux/of_platform.h>
 #include <asm/ibmebus.h>
 #include <asm/abs_addr.h>
@@ -125,17 +127,23 @@ static void ibmebus_unmap_sg(struct device *dev,
 
 static int ibmebus_dma_supported(struct device *dev, u64 mask)
 {
-        return 1;
+        return mask == DMA_BIT_MASK(64);
+}
+
+static u64 ibmebus_dma_get_required_mask(struct device *dev)
+{
+        return DMA_BIT_MASK(64);
 }
 
 static struct dma_map_ops ibmebus_dma_ops = {
-        .alloc_coherent = ibmebus_alloc_coherent,
-        .free_coherent  = ibmebus_free_coherent,
-        .map_sg         = ibmebus_map_sg,
-        .unmap_sg       = ibmebus_unmap_sg,
-        .dma_supported  = ibmebus_dma_supported,
-        .map_page       = ibmebus_map_page,
-        .unmap_page     = ibmebus_unmap_page,
+        .alloc_coherent     = ibmebus_alloc_coherent,
+        .free_coherent      = ibmebus_free_coherent,
+        .map_sg             = ibmebus_map_sg,
+        .unmap_sg           = ibmebus_unmap_sg,
+        .dma_supported      = ibmebus_dma_supported,
+        .get_required_mask  = ibmebus_dma_get_required_mask,
+        .map_page           = ibmebus_map_page,
+        .unmap_page         = ibmebus_unmap_page,
 };
 
 static int ibmebus_match_path(struct device *dev, void *data)
diff --git a/arch/powerpc/kernel/idle_e500.S b/arch/powerpc/kernel/idle_e500.S
index 3e2b95c6ae67..4f0ab85f3788 100644
--- a/arch/powerpc/kernel/idle_e500.S
+++ b/arch/powerpc/kernel/idle_e500.S
@@ -26,7 +26,7 @@ _GLOBAL(e500_idle)
         ori     r4,r4,_TLF_NAPPING      /* so when we take an exception */
         stw     r4,TI_LOCAL_FLAGS(r3)   /* it will return to our caller */
 
-#ifdef CONFIG_E500MC
+#ifdef CONFIG_PPC_E500MC
         wrteei  1
 1:      wait
 
diff --git a/arch/powerpc/kernel/init_task.c b/arch/powerpc/kernel/init_task.c
index 2375b7eb1c76..d076d465dbd1 100644
--- a/arch/powerpc/kernel/init_task.c
+++ b/arch/powerpc/kernel/init_task.c
@@ -1,5 +1,5 @@
 #include <linux/mm.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/sched.h>
 #include <linux/init.h>
 #include <linux/init_task.h>
diff --git a/arch/powerpc/kernel/io-workarounds.c b/arch/powerpc/kernel/io-workarounds.c
index ffafaea3d261..12d329bcbb98 100644
--- a/arch/powerpc/kernel/io-workarounds.c
+++ b/arch/powerpc/kernel/io-workarounds.c
@@ -12,6 +12,7 @@
 #undef DEBUG
 
 #include <linux/kernel.h>
+#include <linux/sched.h>        /* for init_mm */
 
 #include <asm/io.h>
 #include <asm/machdep.h>
diff --git a/arch/powerpc/kernel/io.c b/arch/powerpc/kernel/io.c
index 8dc7547c2377..886381f32c3d 100644
--- a/arch/powerpc/kernel/io.c
+++ b/arch/powerpc/kernel/io.c
@@ -19,7 +19,7 @@
 #include <linux/kernel.h>
 #include <linux/types.h>
 #include <linux/compiler.h>
-#include <linux/module.h>
+#include <linux/export.h>
 
 #include <asm/io.h>
 #include <asm/firmware.h>
diff --git a/arch/powerpc/kernel/iomap.c b/arch/powerpc/kernel/iomap.c
index b25f6325fc70..262791807397 100644
--- a/arch/powerpc/kernel/iomap.c
+++ b/arch/powerpc/kernel/iomap.c
@@ -6,6 +6,7 @@
 #include <linux/init.h>
 #include <linux/pci.h>
 #include <linux/mm.h>
+#include <linux/export.h>
 #include <asm/io.h>
 #include <asm/pci-bridge.h>
 
diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index 961bb03413f3..0cfcf98aafca 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -501,6 +501,14 @@ struct iommu_table *iommu_init_table(struct iommu_table *tbl, int nid)
         tbl->it_map = page_address(page);
         memset(tbl->it_map, 0, sz);
 
+        /*
+         * Reserve page 0 so it will not be used for any mappings.
+         * This avoids buggy drivers that consider page 0 to be invalid
+         * to crash the machine or even lose data.
+         */
+        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);
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index d281fb6f12f3..5c3c46948d94 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -30,7 +30,7 @@
 
 #undef DEBUG
 
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/threads.h>
 #include <linux/kernel_stat.h>
 #include <linux/signal.h>
diff --git a/arch/powerpc/kernel/isa-bridge.c b/arch/powerpc/kernel/isa-bridge.c
index 4d5731b2429a..479752901ec6 100644
--- a/arch/powerpc/kernel/isa-bridge.c
+++ b/arch/powerpc/kernel/isa-bridge.c
@@ -18,6 +18,7 @@
 #include <linux/kernel.h>
 #include <linux/pci.h>
 #include <linux/string.h>
+#include <linux/export.h>
 #include <linux/init.h>
 #include <linux/mm.h>
 #include <linux/notifier.h>
diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c
index b06bdae04064..35f27646c4ff 100644
--- a/arch/powerpc/kernel/kvm.c
+++ b/arch/powerpc/kernel/kvm.c
@@ -20,6 +20,7 @@
 
 #include <linux/kvm_host.h>
 #include <linux/init.h>
+#include <linux/export.h>
 #include <linux/kvm_para.h>
 #include <linux/slab.h>
 #include <linux/of.h>
diff --git a/arch/powerpc/kernel/legacy_serial.c b/arch/powerpc/kernel/legacy_serial.c
index 2b97b80d6d7d..c7b5afeecaf2 100644
--- a/arch/powerpc/kernel/legacy_serial.c
+++ b/arch/powerpc/kernel/legacy_serial.c
@@ -6,6 +6,7 @@
 #include <linux/pci.h>
 #include <linux/of_address.h>
 #include <linux/of_device.h>
+#include <linux/serial_reg.h>
 #include <asm/io.h>
 #include <asm/mmu.h>
 #include <asm/prom.h>
@@ -47,6 +48,24 @@ static struct __initdata of_device_id legacy_serial_parents[] = {
 static unsigned int legacy_serial_count;
 static int legacy_serial_console = -1;
 
+static unsigned int tsi_serial_in(struct uart_port *p, int offset)
+{
+        unsigned int tmp;
+        offset = offset << p->regshift;
+        if (offset == UART_IIR) {
+                tmp = readl(p->membase + (UART_IIR & ~3));
+                return (tmp >> 16) & 0xff; /* UART_IIR % 4 == 2 */
+        } else
+                return readb(p->membase + offset);
+}
+
+static void tsi_serial_out(struct uart_port *p, int offset, int value)
+{
+        offset = offset << p->regshift;
+        if (!((offset == UART_IER) && (value & UART_IER_UUE)))
+                writeb(value, p->membase + offset);
+}
+
 static int __init add_legacy_port(struct device_node *np, int want_index,
                                   int iotype, phys_addr_t base,
                                   phys_addr_t taddr, unsigned long irq,
@@ -102,6 +121,7 @@ static int __init add_legacy_port(struct device_node *np, int want_index,
                 legacy_serial_ports[index].iobase = base;
         else
                 legacy_serial_ports[index].mapbase = base;
+
         legacy_serial_ports[index].iotype = iotype;
         legacy_serial_ports[index].uartclk = clock;
         legacy_serial_ports[index].irq = irq;
@@ -112,6 +132,11 @@ static int __init add_legacy_port(struct device_node *np, int want_index,
         legacy_serial_infos[index].speed = spd ? be32_to_cpup(spd) : 0;
         legacy_serial_infos[index].irq_check_parent = irq_check_parent;
 
+        if (iotype == UPIO_TSI) {
+                legacy_serial_ports[index].serial_in = tsi_serial_in;
+                legacy_serial_ports[index].serial_out = tsi_serial_out;
+        }
+
         printk(KERN_DEBUG "Found legacy serial port %d for %s\n",
                index, np->full_name);
         printk(KERN_DEBUG "  %s=%llx, taddr=%llx, irq=%lx, clk=%d, speed=%d\n",
diff --git a/arch/powerpc/kernel/machine_kexec_64.c b/arch/powerpc/kernel/machine_kexec_64.c
index 583af70c4b14..26ccbf77dd41 100644
--- a/arch/powerpc/kernel/machine_kexec_64.c
+++ b/arch/powerpc/kernel/machine_kexec_64.c
@@ -74,8 +74,7 @@ int default_machine_kexec_prepare(struct kimage *image)
         }
 
         /* We also should not overwrite the tce tables */
-        for (node = of_find_node_by_type(NULL, "pci"); node != NULL;
-                        node = of_find_node_by_type(node, "pci")) {
+        for_each_node_by_type(node, "pci") {
                 basep = of_get_property(node, "linux,tce-base", NULL);
                 sizep = of_get_property(node, "linux,tce-size", NULL);
                 if (basep == NULL || sizep == NULL)
diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S
index 998a10028608..f7d760ab5ca1 100644
--- a/arch/powerpc/kernel/misc_32.S
+++ b/arch/powerpc/kernel/misc_32.S
@@ -8,6 +8,8 @@
  * kexec bits:
  * Copyright (C) 2002-2003 Eric Biederman  <ebiederm@xmission.com>
  * GameCube/ppc32 port Copyright (C) 2004 Albert Herranz
+ * PPC44x port. Copyright (C) 2011,  IBM Corporation
+ *              Author: Suzuki Poulose <suzuki@in.ibm.com>
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License
@@ -736,6 +738,175 @@ relocate_new_kernel:
         mr      r5, r31
 
         li      r0, 0
+#elif defined(CONFIG_44x)  && !defined(CONFIG_47x)
+
+/*
+ * Code for setting up 1:1 mapping for PPC440x for KEXEC
+ *
+ * We cannot switch off the MMU on PPC44x.
+ * So we:
+ * 1) Invalidate all the mappings except the one we are running from.
+ * 2) Create a tmp mapping for our code in the other address space(TS) and
+ *    jump to it. Invalidate the entry we started in.
+ * 3) Create a 1:1 mapping for 0-2GiB in chunks of 256M in original TS.
+ * 4) Jump to the 1:1 mapping in original TS.
+ * 5) Invalidate the tmp mapping.
+ *
+ * - Based on the kexec support code for FSL BookE
+ * - Doesn't support 47x yet.
+ *
+ */
+        /* Save our parameters */
+        mr      r29, r3
+        mr      r30, r4
+        mr      r31, r5
+
+        /* Load our MSR_IS and TID to MMUCR for TLB search */
+        mfspr   r3,SPRN_PID
+        mfmsr   r4
+        andi.   r4,r4,MSR_IS@l
+        beq     wmmucr
+        oris    r3,r3,PPC44x_MMUCR_STS@h
+wmmucr:
+        mtspr   SPRN_MMUCR,r3
+        sync
+
+        /*
+         * Invalidate all the TLB entries except the current entry
+         * where we are running from
+         */
+        bl      0f                              /* Find our address */
+0:      mflr    r5                              /* Make it accessible */
+        tlbsx   r23,0,r5                        /* Find entry we are in */
+        li      r4,0                            /* Start at TLB entry 0 */
+        li      r3,0                            /* Set PAGEID inval value */
+1:      cmpw    r23,r4                          /* Is this our entry? */
+        beq     skip                            /* If so, skip the inval */
+        tlbwe   r3,r4,PPC44x_TLB_PAGEID         /* If not, inval the entry */
+skip:
+        addi    r4,r4,1                         /* Increment */
+        cmpwi   r4,64                           /* Are we done? */
+        bne     1b                              /* If not, repeat */
+        isync
+
+        /* Create a temp mapping and jump to it */
+        andi.   r6, r23, 1              /* Find the index to use */
+        addi    r24, r6, 1              /* r24 will contain 1 or 2 */
+
+        mfmsr   r9                      /* get the MSR */
+        rlwinm  r5, r9, 27, 31, 31      /* Extract the MSR[IS] */
+        xori    r7, r5, 1               /* Use the other address space */
+
+        /* Read the current mapping entries */
+        tlbre   r3, r23, PPC44x_TLB_PAGEID
+        tlbre   r4, r23, PPC44x_TLB_XLAT
+        tlbre   r5, r23, PPC44x_TLB_ATTRIB
+
+        /* Save our current XLAT entry */
+        mr      r25, r4
+
+        /* Extract the TLB PageSize */
+        li      r10, 1                  /* r10 will hold PageSize */
+        rlwinm  r11, r3, 0, 24, 27      /* bits 24-27 */
+
+        /* XXX: As of now we use 256M, 4K pages */
+        cmpwi   r11, PPC44x_TLB_256M
+        bne     tlb_4k
+        rotlwi  r10, r10, 28            /* r10 = 256M */
+        b       write_out
+tlb_4k:
+        cmpwi   r11, PPC44x_TLB_4K
+        bne     default
+        rotlwi  r10, r10, 12            /* r10 = 4K */
+        b       write_out
+default:
+        rotlwi  r10, r10, 10            /* r10 = 1K */
+
+write_out:
+        /*
+         * Write out the tmp 1:1 mapping for this code in other address space
+         * Fixup  EPN = RPN , TS=other address space
+         */
+        insrwi  r3, r7, 1, 23           /* Bit 23 is TS for PAGEID field */
+
+        /* Write out the tmp mapping entries */
+        tlbwe   r3, r24, PPC44x_TLB_PAGEID
+        tlbwe   r4, r24, PPC44x_TLB_XLAT
+        tlbwe   r5, r24, PPC44x_TLB_ATTRIB
+
+        subi    r11, r10, 1             /* PageOffset Mask = PageSize - 1 */
+        not     r10, r11                /* Mask for PageNum */
+
+        /* Switch to other address space in MSR */
+        insrwi  r9, r7, 1, 26           /* Set MSR[IS] = r7 */
+
+        bl      1f
+1:      mflr    r8
+        addi    r8, r8, (2f-1b)         /* Find the target offset */
+
+        /* Jump to the tmp mapping */
+        mtspr   SPRN_SRR0, r8
+        mtspr   SPRN_SRR1, r9
+        rfi
+
+2:
+        /* Invalidate the entry we were executing from */
+        li      r3, 0
+        tlbwe   r3, r23, PPC44x_TLB_PAGEID
+
+        /* attribute fields. rwx for SUPERVISOR mode */
+        li      r5, 0
+        ori     r5, r5, (PPC44x_TLB_SW | PPC44x_TLB_SR | PPC44x_TLB_SX | PPC44x_TLB_G)
+
+        /* Create 1:1 mapping in 256M pages */
+        xori    r7, r7, 1                       /* Revert back to Original TS */
+
+        li      r8, 0                           /* PageNumber */
+        li      r6, 3                           /* TLB Index, start at 3  */
+
+next_tlb:
+        rotlwi  r3, r8, 28                      /* Create EPN (bits 0-3) */
+        mr      r4, r3                          /* RPN = EPN  */
+        ori     r3, r3, (PPC44x_TLB_VALID | PPC44x_TLB_256M) /* SIZE = 256M, Valid */
+        insrwi  r3, r7, 1, 23                   /* Set TS from r7 */
+
+        tlbwe   r3, r6, PPC44x_TLB_PAGEID       /* PageID field : EPN, V, SIZE */
+        tlbwe   r4, r6, PPC44x_TLB_XLAT         /* Address translation : RPN   */
+        tlbwe   r5, r6, PPC44x_TLB_ATTRIB       /* Attributes */
+
+        addi    r8, r8, 1                       /* Increment PN */
+        addi    r6, r6, 1                       /* Increment TLB Index */
+        cmpwi   r8, 8                           /* Are we done ? */
+        bne     next_tlb
+        isync
+
+        /* Jump to the new mapping 1:1 */
+        li      r9,0
+        insrwi  r9, r7, 1, 26                   /* Set MSR[IS] = r7 */
+
+        bl      1f
+1:      mflr    r8
+        and     r8, r8, r11                     /* Get our offset within page */
+        addi    r8, r8, (2f-1b)
+
+        and     r5, r25, r10                    /* Get our target PageNum */
+        or      r8, r8, r5                      /* Target jump address */
+
+        mtspr   SPRN_SRR0, r8
+        mtspr   SPRN_SRR1, r9
+        rfi
+2:
+        /* Invalidate the tmp entry we used */
+        li      r3, 0
+        tlbwe   r3, r24, PPC44x_TLB_PAGEID
+        sync
+
+        /* Restore the parameters */
+        mr      r3, r29
+        mr      r4, r30
+        mr      r5, r31
+
+        li      r0, 0
 #else
         li      r0, 0
 
diff --git a/arch/powerpc/kernel/module.c b/arch/powerpc/kernel/module.c
index a1cd701b5753..2d275707f419 100644
--- a/arch/powerpc/kernel/module.c
+++ b/arch/powerpc/kernel/module.c
@@ -16,7 +16,6 @@
     along with this program; if not, write to the Free Software
     Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
 */
-#include <linux/module.h>
 #include <linux/elf.h>
 #include <linux/moduleloader.h>
 #include <linux/err.h>
diff --git a/arch/powerpc/kernel/of_platform.c b/arch/powerpc/kernel/of_platform.c
index 59dbf6abaaf3..e1612dfb4a93 100644
--- a/arch/powerpc/kernel/of_platform.c
+++ b/arch/powerpc/kernel/of_platform.c
@@ -15,7 +15,7 @@
 #include <linux/string.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/mod_devicetable.h>
 #include <linux/pci.h>
 #include <linux/of.h>
diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c
index 0a5a899846bb..41456ff55e14 100644
--- a/arch/powerpc/kernel/paca.c
+++ b/arch/powerpc/kernel/paca.c
@@ -8,7 +8,7 @@
  */
 
 #include <linux/smp.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/memblock.h>
 
 #include <asm/firmware.h>
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index 32656f105250..458ed3bee663 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -21,6 +21,7 @@
 #include <linux/string.h>
 #include <linux/init.h>
 #include <linux/bootmem.h>
+#include <linux/export.h>
 #include <linux/of_address.h>
 #include <linux/of_pci.h>
 #include <linux/mm.h>
@@ -1730,6 +1731,17 @@ void __devinit pcibios_scan_phb(struct pci_controller *hose)
 
         if (mode == PCI_PROBE_NORMAL)
                 hose->last_busno = bus->subordinate = pci_scan_child_bus(bus);
+
+        /* Configure PCI Express settings */
+        if (bus && !pci_has_flag(PCI_PROBE_ONLY)) {
+                struct pci_bus *child;
+                list_for_each_entry(child, &bus->children, node) {
+                        struct pci_dev *self = child->self;
+                        if (!self)
+                                continue;
+                        pcie_bus_configure_settings(child, self->pcie_mpss);
+                }
+        }
 }
 
 static void fixup_hide_host_resource_fsl(struct pci_dev *dev)
diff --git a/arch/powerpc/kernel/pci_32.c b/arch/powerpc/kernel/pci_32.c
index bb154511db5e..fdd1a3d951dc 100644
--- a/arch/powerpc/kernel/pci_32.c
+++ b/arch/powerpc/kernel/pci_32.c
@@ -15,6 +15,7 @@
 #include <linux/list.h>
 #include <linux/of.h>
 #include <linux/slab.h>
+#include <linux/export.h>
 
 #include <asm/processor.h>
 #include <asm/io.h>
diff --git a/arch/powerpc/kernel/pci_64.c b/arch/powerpc/kernel/pci_64.c
index ab34046752bf..bcf4bf9e72d9 100644
--- a/arch/powerpc/kernel/pci_64.c
+++ b/arch/powerpc/kernel/pci_64.c
@@ -18,6 +18,7 @@
 #include <linux/string.h>
 #include <linux/init.h>
 #include <linux/bootmem.h>
+#include <linux/export.h>
 #include <linux/mm.h>
 #include <linux/list.h>
 #include <linux/syscalls.h>
diff --git a/arch/powerpc/kernel/pci_dn.c b/arch/powerpc/kernel/pci_dn.c
index 478f8d78716b..4e69deb89b37 100644
--- a/arch/powerpc/kernel/pci_dn.c
+++ b/arch/powerpc/kernel/pci_dn.c
@@ -22,6 +22,7 @@
 #include <linux/kernel.h>
 #include <linux/pci.h>
 #include <linux/string.h>
+#include <linux/export.h>
 #include <linux/init.h>
 #include <linux/gfp.h>
 
diff --git a/arch/powerpc/kernel/pci_of_scan.c b/arch/powerpc/kernel/pci_of_scan.c
index fe0a5ad6f73e..b37d0b5a796e 100644
--- a/arch/powerpc/kernel/pci_of_scan.c
+++ b/arch/powerpc/kernel/pci_of_scan.c
@@ -15,6 +15,7 @@
  */
 
 #include <linux/pci.h>
+#include <linux/export.h>
 #include <asm/pci-bridge.h>
 #include <asm/prom.h>
 
diff --git a/arch/powerpc/kernel/pmc.c b/arch/powerpc/kernel/pmc.c
index 461499b43cff..a841a9d136a2 100644
--- a/arch/powerpc/kernel/pmc.c
+++ b/arch/powerpc/kernel/pmc.c
@@ -14,7 +14,7 @@
 
 #include <linux/errno.h>
 #include <linux/spinlock.h>
-#include <linux/module.h>
+#include <linux/export.h>
 
 #include <asm/processor.h>
 #include <asm/cputable.h>
diff --git a/arch/powerpc/kernel/power6-pmu.c b/arch/powerpc/kernel/power6-pmu.c
index 03b95e2c6d65..0bbc901e7efc 100644
--- a/arch/powerpc/kernel/power6-pmu.c
+++ b/arch/powerpc/kernel/power6-pmu.c
@@ -487,8 +487,8 @@ static int power6_generic_events[] = {
  */
 static int power6_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
         [C(L1D)] = {            /*      RESULT_ACCESS   RESULT_MISS */
-                [C(OP_READ)] = {        0x80082,        0x80080         },
-                [C(OP_WRITE)] = {       0x80086,        0x80088         },
+                [C(OP_READ)] = {        0x280030,       0x80080         },
+                [C(OP_WRITE)] = {       0x180032,       0x80088         },
                 [C(OP_PREFETCH)] = {    0x810a4,        0               },
         },
         [C(L1I)] = {            /*      RESULT_ACCESS   RESULT_MISS */
diff --git a/arch/powerpc/kernel/power7-pmu.c b/arch/powerpc/kernel/power7-pmu.c
index de83d6060dda..1251e4d7e262 100644
--- a/arch/powerpc/kernel/power7-pmu.c
+++ b/arch/powerpc/kernel/power7-pmu.c
@@ -297,6 +297,8 @@ static void power7_disable_pmc(unsigned int pmc, unsigned long mmcr[])
 
 static int power7_generic_events[] = {
         [PERF_COUNT_HW_CPU_CYCLES] = 0x1e,
+        [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x100f8, /* GCT_NOSLOT_CYC */
+        [PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = 0x4000a,  /* CMPLU_STALL */
         [PERF_COUNT_HW_INSTRUCTIONS] = 2,
         [PERF_COUNT_HW_CACHE_REFERENCES] = 0xc880,      /* LD_REF_L1_LSU*/
         [PERF_COUNT_HW_CACHE_MISSES] = 0x400f0,         /* LD_MISS_L1   */
diff --git a/arch/powerpc/kernel/ppc_ksyms.c b/arch/powerpc/kernel/ppc_ksyms.c
index f5ae872a2ef0..d3114a71dd32 100644
--- a/arch/powerpc/kernel/ppc_ksyms.c
+++ b/arch/powerpc/kernel/ppc_ksyms.c
@@ -1,4 +1,4 @@
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/threads.h>
 #include <linux/smp.h>
 #include <linux/sched.h>
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 8f53954e75a3..9054ca9ab4f9 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -28,7 +28,7 @@
 #include <linux/init.h>
 #include <linux/prctl.h>
 #include <linux/init_task.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/kallsyms.h>
 #include <linux/mqueue.h>
 #include <linux/hardirq.h>
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index 174e1e96175e..fa1235b0503b 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -27,7 +27,7 @@
 #include <linux/delay.h>
 #include <linux/initrd.h>
 #include <linux/bitops.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/kexec.h>
 #include <linux/debugfs.h>
 #include <linux/irq.h>
@@ -54,6 +54,8 @@
 #include <asm/pci-bridge.h>
 #include <asm/phyp_dump.h>
 #include <asm/kexec.h>
+#include <asm/opal.h>
+
 #include <mm/mmu_decl.h>
 
 #ifdef DEBUG
@@ -707,11 +709,23 @@ void __init early_init_devtree(void *params)
         of_scan_flat_dt(early_init_dt_scan_rtas, NULL);
 #endif
 
+#ifdef CONFIG_PPC_POWERNV
+        /* Some machines might need OPAL info for debugging, grab it now. */
+        of_scan_flat_dt(early_init_dt_scan_opal, NULL);
+#endif
+
 #ifdef CONFIG_PHYP_DUMP
         /* scan tree to see if dump occurred during last boot */
         of_scan_flat_dt(early_init_dt_scan_phyp_dump, NULL);
 #endif
 
+        /* Pre-initialize the cmd_line with the content of boot_commmand_line,
+         * which will be empty except when the content of the variable has
+         * been overriden by a bootloading mechanism. This happens typically
+         * with HAL takeover
+         */
+        strlcpy(cmd_line, boot_command_line, COMMAND_LINE_SIZE);
+
         /* Retrieve various informations from the /chosen node of the
          * device-tree, including the platform type, initrd location and
          * size, TCE reserve, and more ...
@@ -723,12 +737,15 @@ void __init early_init_devtree(void *params)
 
         of_scan_flat_dt(early_init_dt_scan_root, NULL);
         of_scan_flat_dt(early_init_dt_scan_memory_ppc, NULL);
-        setup_initial_memory_limit(memstart_addr, first_memblock_size);
 
         /* Save command line for /proc/cmdline and then parse parameters */
         strlcpy(boot_command_line, cmd_line, COMMAND_LINE_SIZE);
         parse_early_param();
 
+        /* make sure we've parsed cmdline for mem= before this */
+        if (memory_limit)
+                first_memblock_size = min(first_memblock_size, memory_limit);
+        setup_initial_memory_limit(memstart_addr, first_memblock_size);
         /* Reserve MEMBLOCK regions used by kernel, initrd, dt, etc... */
         memblock_reserve(PHYSICAL_START, __pa(klimit) - PHYSICAL_START);
         /* If relocatable, reserve first 32k for interrupt vectors etc. */
diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index a909f4e9343b..b4fa66127495 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -43,6 +43,7 @@
 #include <asm/btext.h>
 #include <asm/sections.h>
 #include <asm/machdep.h>
+#include <asm/opal.h>
 
 #include <linux/linux_logo.h>
 
@@ -139,7 +140,9 @@ struct mem_map_entry {
 
 typedef u32 cell_t;
 
-extern void __start(unsigned long r3, unsigned long r4, unsigned long r5);
+extern void __start(unsigned long r3, unsigned long r4, unsigned long r5,
+                    unsigned long r6, unsigned long r7, unsigned long r8,
+                    unsigned long r9);
 
 #ifdef CONFIG_PPC64
 extern int enter_prom(struct prom_args *args, unsigned long entry);
@@ -185,6 +188,7 @@ static unsigned long __initdata prom_tce_alloc_end;
 #define PLATFORM_LPAR           0x0001
 #define PLATFORM_POWERMAC       0x0400
 #define PLATFORM_GENERIC        0x0500
+#define PLATFORM_OPAL           0x0600
 
 static int __initdata of_platform;
 
@@ -644,7 +648,7 @@ static void __init early_cmdline_parse(void)
         }
 }
 
-#ifdef CONFIG_PPC_PSERIES
+#if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV)
 /*
  * There are two methods for telling firmware what our capabilities are.
  * Newer machines have an "ibm,client-architecture-support" method on the
@@ -1274,6 +1278,284 @@ static void __init prom_init_mem(void)
         prom_printf("  ram_top      : %x\n", RELOC(ram_top));
 }
 
+static void __init prom_close_stdin(void)
+{
+        struct prom_t *_prom = &RELOC(prom);
+        ihandle val;
+
+        if (prom_getprop(_prom->chosen, "stdin", &val, sizeof(val)) > 0)
+                call_prom("close", 1, 0, val);
+}
+
+#ifdef CONFIG_PPC_POWERNV
+
+static u64 __initdata prom_opal_size;
+static u64 __initdata prom_opal_align;
+static int __initdata prom_rtas_start_cpu;
+static u64 __initdata prom_rtas_data;
+static u64 __initdata prom_rtas_entry;
+
+#ifdef CONFIG_PPC_EARLY_DEBUG_OPAL
+static u64 __initdata prom_opal_base;
+static u64 __initdata prom_opal_entry;
+#endif
+
+/* XXX Don't change this structure without updating opal-takeover.S */
+static struct opal_secondary_data {
+        s64                             ack;    /*  0 */
+        u64                             go;     /*  8 */
+        struct opal_takeover_args       args;   /* 16 */
+} opal_secondary_data;
+
+extern char opal_secondary_entry;
+
+static void prom_query_opal(void)
+{
+        long rc;
+
+        /* We must not query for OPAL presence on a machine that
+         * supports TNK takeover (970 blades), as this uses the same
+         * h-call with different arguments and will crash
+         */
+        if (PHANDLE_VALID(call_prom("finddevice", 1, 1,
+                                    ADDR("/tnk-memory-map")))) {
+                prom_printf("TNK takeover detected, skipping OPAL check\n");
+                return;
+        }
+
+        prom_printf("Querying for OPAL presence... ");
+        rc = opal_query_takeover(&RELOC(prom_opal_size),
+                                 &RELOC(prom_opal_align));
+        prom_debug("(rc = %ld) ", rc);
+        if (rc != 0) {
+                prom_printf("not there.\n");
+                return;
+        }
+        RELOC(of_platform) = PLATFORM_OPAL;
+        prom_printf(" there !\n");
+        prom_debug("  opal_size  = 0x%lx\n", RELOC(prom_opal_size));
+        prom_debug("  opal_align = 0x%lx\n", RELOC(prom_opal_align));
+        if (RELOC(prom_opal_align) < 0x10000)
+                RELOC(prom_opal_align) = 0x10000;
+}
+
+static int prom_rtas_call(int token, int nargs, int nret, int *outputs, ...)
+{
+        struct rtas_args rtas_args;
+        va_list list;
+        int i;
+
+        rtas_args.token = token;
+        rtas_args.nargs = nargs;
+        rtas_args.nret  = nret;
+        rtas_args.rets  = (rtas_arg_t *)&(rtas_args.args[nargs]);
+        va_start(list, outputs);
+        for (i = 0; i < nargs; ++i)
+                rtas_args.args[i] = va_arg(list, rtas_arg_t);
+        va_end(list);
+
+        for (i = 0; i < nret; ++i)
+                rtas_args.rets[i] = 0;
+
+        opal_enter_rtas(&rtas_args, RELOC(prom_rtas_data),
+                        RELOC(prom_rtas_entry));
+
+        if (nret > 1 && outputs != NULL)
+                for (i = 0; i < nret-1; ++i)
+                        outputs[i] = rtas_args.rets[i+1];
+        return (nret > 0)? rtas_args.rets[0]: 0;
+}
+
+static void __init prom_opal_hold_cpus(void)
+{
+        int i, cnt, cpu, rc;
+        long j;
+        phandle node;
+        char type[64];
+        u32 servers[8];
+        struct prom_t *_prom = &RELOC(prom);
+        void *entry = (unsigned long *)&RELOC(opal_secondary_entry);
+        struct opal_secondary_data *data = &RELOC(opal_secondary_data);
+
+        prom_debug("prom_opal_hold_cpus: start...\n");
+        prom_debug("    - entry       = 0x%x\n", entry);
+        prom_debug("    - data        = 0x%x\n", data);
+
+        data->ack = -1;
+        data->go = 0;
+
+        /* look for cpus */
+        for (node = 0; prom_next_node(&node); ) {
+                type[0] = 0;
+                prom_getprop(node, "device_type", type, sizeof(type));
+                if (strcmp(type, RELOC("cpu")) != 0)
+                        continue;
+
+                /* Skip non-configured cpus. */
+                if (prom_getprop(node, "status", type, sizeof(type)) > 0)
+                        if (strcmp(type, RELOC("okay")) != 0)
+                                continue;
+
+                cnt = prom_getprop(node, "ibm,ppc-interrupt-server#s", servers,
+                             sizeof(servers));
+                if (cnt == PROM_ERROR)
+                        break;
+                cnt >>= 2;
+                for (i = 0; i < cnt; i++) {
+                        cpu = servers[i];
+                        prom_debug("CPU %d ... ", cpu);
+                        if (cpu == _prom->cpu) {
+                                prom_debug("booted !\n");
+                                continue;
+                        }
+                        prom_debug("starting ... ");
+
+                        /* Init the acknowledge var which will be reset by
+                         * the secondary cpu when it awakens from its OF
+                         * spinloop.
+                         */
+                        data->ack = -1;
+                        rc = prom_rtas_call(RELOC(prom_rtas_start_cpu), 3, 1,
+                                            NULL, cpu, entry, data);
+                        prom_debug("rtas rc=%d ...", rc);
+
+                        for (j = 0; j < 100000000 && data->ack == -1; j++) {
+                                HMT_low();
+                                mb();
+                        }
+                        HMT_medium();
+                        if (data->ack != -1)
+                                prom_debug("done, PIR=0x%x\n", data->ack);
+                        else
+                                prom_debug("timeout !\n");
+                }
+        }
+        prom_debug("prom_opal_hold_cpus: end...\n");
+}
+
+static void prom_opal_takeover(void)
+{
+        struct opal_secondary_data *data = &RELOC(opal_secondary_data);
+        struct opal_takeover_args *args = &data->args;
+        u64 align = RELOC(prom_opal_align);
+        u64 top_addr, opal_addr;
+
+        args->k_image   = (u64)RELOC(_stext);
+        args->k_size    = _end - _stext;
+        args->k_entry   = 0;
+        args->k_entry2  = 0x60;
+
+        top_addr = _ALIGN_UP(args->k_size, align);
+
+        if (RELOC(prom_initrd_start) != 0) {
+                args->rd_image = RELOC(prom_initrd_start);
+                args->rd_size = RELOC(prom_initrd_end) - args->rd_image;
+                args->rd_loc = top_addr;
+                top_addr = _ALIGN_UP(args->rd_loc + args->rd_size, align);
+        }
+
+        /* Pickup an address for the HAL. We want to go really high
+         * up to avoid problem with future kexecs. On the other hand
+         * we don't want to be all over the TCEs on P5IOC2 machines
+         * which are going to be up there too. We assume the machine
+         * has plenty of memory, and we ask for the HAL for now to
+         * be just below the 1G point, or above the initrd
+         */
+        opal_addr = _ALIGN_DOWN(0x40000000 - RELOC(prom_opal_size), align);
+        if (opal_addr < top_addr)
+                opal_addr = top_addr;
+        args->hal_addr = opal_addr;
+
+        /* Copy the command line to the kernel image */
+        strlcpy(RELOC(boot_command_line), RELOC(prom_cmd_line),
+                COMMAND_LINE_SIZE);
+
+        prom_debug("  k_image    = 0x%lx\n", args->k_image);
+        prom_debug("  k_size     = 0x%lx\n", args->k_size);
+        prom_debug("  k_entry    = 0x%lx\n", args->k_entry);
+        prom_debug("  k_entry2   = 0x%lx\n", args->k_entry2);
+        prom_debug("  hal_addr   = 0x%lx\n", args->hal_addr);
+        prom_debug("  rd_image   = 0x%lx\n", args->rd_image);
+        prom_debug("  rd_size    = 0x%lx\n", args->rd_size);
+        prom_debug("  rd_loc     = 0x%lx\n", args->rd_loc);
+        prom_printf("Performing OPAL takeover,this can take a few minutes..\n");
+        prom_close_stdin();
+        mb();
+        data->go = 1;
+        for (;;)
+                opal_do_takeover(args);
+}
+
+/*
+ * Allocate room for and instantiate OPAL
+ */
+static void __init prom_instantiate_opal(void)
+{
+        phandle opal_node;
+        ihandle opal_inst;
+        u64 base, entry;
+        u64 size = 0, align = 0x10000;
+        u32 rets[2];
+
+        prom_debug("prom_instantiate_opal: start...\n");
+
+        opal_node = call_prom("finddevice", 1, 1, ADDR("/ibm,opal"));
+        prom_debug("opal_node: %x\n", opal_node);
+        if (!PHANDLE_VALID(opal_node))
+                return;
+
+        prom_getprop(opal_node, "opal-runtime-size", &size, sizeof(size));
+        if (size == 0)
+                return;
+        prom_getprop(opal_node, "opal-runtime-alignment", &align,
+                     sizeof(align));
+
+        base = alloc_down(size, align, 0);
+        if (base == 0) {
+                prom_printf("OPAL allocation failed !\n");
+                return;
+        }
+
+        opal_inst = call_prom("open", 1, 1, ADDR("/ibm,opal"));
+        if (!IHANDLE_VALID(opal_inst)) {
+                prom_printf("opening opal package failed (%x)\n", opal_inst);
+                return;
+        }
+
+        prom_printf("instantiating opal at 0x%x...", base);
+
+        if (call_prom_ret("call-method", 4, 3, rets,
+                          ADDR("load-opal-runtime"),
+                          opal_inst,
+                          base >> 32, base & 0xffffffff) != 0
+            || (rets[0] == 0 && rets[1] == 0)) {
+                prom_printf(" failed\n");
+                return;
+        }
+        entry = (((u64)rets[0]) << 32) | rets[1];
+
+        prom_printf(" done\n");
+
+        reserve_mem(base, size);
+
+        prom_debug("opal base     = 0x%x\n", base);
+        prom_debug("opal align    = 0x%x\n", align);
+        prom_debug("opal entry    = 0x%x\n", entry);
+        prom_debug("opal size     = 0x%x\n", (long)size);
+
+        prom_setprop(opal_node, "/ibm,opal", "opal-base-address",
+                     &base, sizeof(base));
+        prom_setprop(opal_node, "/ibm,opal", "opal-entry-address",
+                     &entry, sizeof(entry));
+
+#ifdef CONFIG_PPC_EARLY_DEBUG_OPAL
+        RELOC(prom_opal_base) = base;
+        RELOC(prom_opal_entry) = entry;
+#endif
+        prom_debug("prom_instantiate_opal: end...\n");
+}
+
+#endif /* CONFIG_PPC_POWERNV */
 
 /*
  * Allocate room for and instantiate RTAS
@@ -1326,6 +1608,12 @@ static void __init prom_instantiate_rtas(void)
         prom_setprop(rtas_node, "/rtas", "linux,rtas-entry",
                      &entry, sizeof(entry));
 
+#ifdef CONFIG_PPC_POWERNV
+        /* PowerVN takeover hack */
+        RELOC(prom_rtas_data) = base;
+        RELOC(prom_rtas_entry) = entry;
+        prom_getprop(rtas_node, "start-cpu", &RELOC(prom_rtas_start_cpu), 4);
+#endif
         prom_debug("rtas base     = 0x%x\n", base);
         prom_debug("rtas entry    = 0x%x\n", entry);
         prom_debug("rtas size     = 0x%x\n", (long)size);
@@ -1543,7 +1831,7 @@ static void __init prom_hold_cpus(void)
                 *acknowledge = (unsigned long)-1;
 
                 if (reg != _prom->cpu) {
-                        /* Primary Thread of non-boot cpu */
+                        /* Primary Thread of non-boot cpu or any thread */
                         prom_printf("starting cpu hw idx %lu... ", reg);
                         call_prom("start-cpu", 3, 0, node,
                                   secondary_hold, reg);
@@ -1652,15 +1940,6 @@ static void __init prom_init_stdout(void)
                 prom_setprop(val, path, "linux,boot-display", NULL, 0);
 }
 
-static void __init prom_close_stdin(void)
-{
-        struct prom_t *_prom = &RELOC(prom);
-        ihandle val;
-
-        if (prom_getprop(_prom->chosen, "stdin", &val, sizeof(val)) > 0)
-                call_prom("close", 1, 0, val);
-}
-
 static int __init prom_find_machine_type(void)
 {
         struct prom_t *_prom = &RELOC(prom);
@@ -1671,7 +1950,7 @@ static int __init prom_find_machine_type(void)
         int x;
 #endif
 
-        /* Look for a PowerMac */
+        /* Look for a PowerMac or a Cell */
         len = prom_getprop(_prom->root, "compatible",
                            compat, sizeof(compat)-1);
         if (len > 0) {
@@ -1697,7 +1976,11 @@ static int __init prom_find_machine_type(void)
                 }
         }
 #ifdef CONFIG_PPC64
-        /* If not a mac, try to figure out if it's an IBM pSeries or any other
+        /* Try to detect OPAL */
+        if (PHANDLE_VALID(call_prom("finddevice", 1, 1, ADDR("/ibm,opal"))))
+                return PLATFORM_OPAL;
+
+        /* Try to figure out if it's an IBM pSeries or any other
          * PAPR compliant platform. We assume it is if :
          *  - /device_type is "chrp" (please, do NOT use that for future
          *    non-IBM designs !
@@ -1924,7 +2207,7 @@ static void __init scan_dt_build_struct(phandle node, unsigned long *mem_start,
         unsigned long soff;
         unsigned char *valp;
         static char pname[MAX_PROPERTY_NAME];
-        int l, room;
+        int l, room, has_phandle = 0;
 
         dt_push_token(OF_DT_BEGIN_NODE, mem_start, mem_end);
 
@@ -2008,19 +2291,26 @@ static void __init scan_dt_build_struct(phandle node, unsigned long *mem_start,
                 valp = make_room(mem_start, mem_end, l, 4);
                 call_prom("getprop", 4, 1, node, RELOC(pname), valp, l);
                 *mem_start = _ALIGN(*mem_start, 4);
+
+                if (!strcmp(RELOC(pname), RELOC("phandle")))
+                        has_phandle = 1;
         }
 
-        /* Add a "linux,phandle" property. */
-        soff = dt_find_string(RELOC("linux,phandle"));
-        if (soff == 0)
-                prom_printf("WARNING: Can't find string index for"
-                            " <linux-phandle> node %s\n", path);
-        else {
-                dt_push_token(OF_DT_PROP, mem_start, mem_end);
-                dt_push_token(4, mem_start, mem_end);
-                dt_push_token(soff, mem_start, mem_end);
-                valp = make_room(mem_start, mem_end, 4, 4);
-                *(u32 *)valp = node;
+        /* Add a "linux,phandle" property if no "phandle" property already
+         * existed (can happen with OPAL)
+         */
+        if (!has_phandle) {
+                soff = dt_find_string(RELOC("linux,phandle"));
+                if (soff == 0)
+                        prom_printf("WARNING: Can't find string index for"
+                                    " <linux-phandle> node %s\n", path);
+                else {
+                        dt_push_token(OF_DT_PROP, mem_start, mem_end);
+                        dt_push_token(4, mem_start, mem_end);
+                        dt_push_token(soff, mem_start, mem_end);
+                        valp = make_room(mem_start, mem_end, 4, 4);
+                        *(u32 *)valp = node;
+                }
         }
 
         /* do all our children */
@@ -2504,6 +2794,7 @@ static void __init prom_check_initrd(unsigned long r3, unsigned long r4)
 #endif /* CONFIG_BLK_DEV_INITRD */
 }
 
+
 /*
  * We enter here early on, when the Open Firmware prom is still
  * handling exceptions and the MMU hash table for us.
@@ -2553,6 +2844,7 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4,
          * between pSeries SMP and pSeries LPAR
          */
         RELOC(of_platform) = prom_find_machine_type();
+        prom_printf("Detected machine type: %x\n", RELOC(of_platform));
 
 #ifndef CONFIG_RELOCATABLE
         /* Bail if this is a kdump kernel. */
@@ -2565,7 +2857,7 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4,
          */
         prom_check_initrd(r3, r4);
 
-#ifdef CONFIG_PPC_PSERIES
+#if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV)
         /*
          * On pSeries, inform the firmware about our capabilities
          */
@@ -2611,14 +2903,33 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4,
 #endif
 
         /*
-         * On non-powermacs, try to instantiate RTAS and puts all CPUs
-         * in spin-loops. PowerMacs don't have a working RTAS and use
-         * a different way to spin CPUs
+         * On non-powermacs, try to instantiate RTAS. PowerMacs don't
+         * have a usable RTAS implementation.
          */
-        if (RELOC(of_platform) != PLATFORM_POWERMAC) {
+        if (RELOC(of_platform) != PLATFORM_POWERMAC &&
+            RELOC(of_platform) != PLATFORM_OPAL)
                 prom_instantiate_rtas();
+
+#ifdef CONFIG_PPC_POWERNV
+        /* Detect HAL and try instanciating it & doing takeover */
+        if (RELOC(of_platform) == PLATFORM_PSERIES_LPAR) {
+                prom_query_opal();
+                if (RELOC(of_platform) == PLATFORM_OPAL) {
+                        prom_opal_hold_cpus();
+                        prom_opal_takeover();
+                }
+        } else if (RELOC(of_platform) == PLATFORM_OPAL)
+                prom_instantiate_opal();
+#endif
+
+        /*
+         * On non-powermacs, put all CPUs in spin-loops.
+         *
+         * PowerMacs use a different mechanism to spin CPUs
+         */
+        if (RELOC(of_platform) != PLATFORM_POWERMAC &&
+            RELOC(of_platform) != PLATFORM_OPAL)
                 prom_hold_cpus();
-        }
 
         /*
          * Fill in some infos for use by the kernel later on
@@ -2685,7 +2996,13 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4,
         reloc_got2(-offset);
 #endif
 
-        __start(hdr, kbase, 0);
+#ifdef CONFIG_PPC_EARLY_DEBUG_OPAL
+        /* OPAL early debug gets the OPAL base & entry in r8 and r9 */
+        __start(hdr, kbase, 0, 0, 0,
+                RELOC(prom_opal_base), RELOC(prom_opal_entry));
+#else
+        __start(hdr, kbase, 0, 0, 0, 0, 0);
+#endif
 
         return 0;
 }
diff --git a/arch/powerpc/kernel/prom_init_check.sh b/arch/powerpc/kernel/prom_init_check.sh
index 9f82f4937892..70f4286eaa7a 100644
--- a/arch/powerpc/kernel/prom_init_check.sh
+++ b/arch/powerpc/kernel/prom_init_check.sh
@@ -20,7 +20,9 @@ WHITELIST="add_reloc_offset __bss_start __bss_stop copy_and_flush
 _end enter_prom memcpy memset reloc_offset __secondary_hold
 __secondary_hold_acknowledge __secondary_hold_spinloop __start
 strcmp strcpy strlcpy strlen strncmp strstr logo_linux_clut224
-reloc_got2 kernstart_addr memstart_addr linux_banner"
+reloc_got2 kernstart_addr memstart_addr linux_banner _stext
+opal_query_takeover opal_do_takeover opal_enter_rtas opal_secondary_entry
+boot_command_line"
 
 NM="$1"
 OBJ="$2"
diff --git a/arch/powerpc/kernel/prom_parse.c b/arch/powerpc/kernel/prom_parse.c
index 47187cc2cf00..4e1331b8eb33 100644
--- a/arch/powerpc/kernel/prom_parse.c
+++ b/arch/powerpc/kernel/prom_parse.c
@@ -2,7 +2,6 @@
 
 #include <linux/kernel.h>
 #include <linux/string.h>
-#include <linux/module.h>
 #include <linux/ioport.h>
 #include <linux/etherdevice.h>
 #include <linux/of_address.h>
diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c
index 05b7dd217f60..5de73dbd15c7 100644
--- a/arch/powerpc/kernel/ptrace.c
+++ b/arch/powerpc/kernel/ptrace.c
@@ -30,9 +30,6 @@
 #include <linux/seccomp.h>
 #include <linux/audit.h>
 #include <trace/syscall.h>
-#ifdef CONFIG_PPC32
-#include <linux/module.h>
-#endif
 #include <linux/hw_breakpoint.h>
 #include <linux/perf_event.h>
 
@@ -1497,9 +1494,14 @@ long arch_ptrace(struct task_struct *child, long request,
                 if (index < PT_FPR0) {
                         tmp = ptrace_get_reg(child, (int) index);
                 } else {
+                        unsigned int fpidx = index - PT_FPR0;
+
                         flush_fp_to_thread(child);
-                        tmp = ((unsigned long *)child->thread.fpr)
-                                [TS_FPRWIDTH * (index - PT_FPR0)];
+                        if (fpidx < (PT_FPSCR - PT_FPR0))
+                                tmp = ((unsigned long *)child->thread.fpr)
+                                        [fpidx * TS_FPRWIDTH];
+                        else
+                                tmp = child->thread.fpscr.val;
                 }
                 ret = put_user(tmp, datalp);
                 break;
@@ -1525,9 +1527,14 @@ long arch_ptrace(struct task_struct *child, long request,
                 if (index < PT_FPR0) {
                         ret = ptrace_put_reg(child, index, data);
                 } else {
+                        unsigned int fpidx = index - PT_FPR0;
+
                         flush_fp_to_thread(child);
-                        ((unsigned long *)child->thread.fpr)
-                                [TS_FPRWIDTH * (index - PT_FPR0)] = data;
+                        if (fpidx < (PT_FPSCR - PT_FPR0))
+                                ((unsigned long *)child->thread.fpr)
+                                        [fpidx * TS_FPRWIDTH] = data;
+                        else
+                                child->thread.fpscr.val = data;
                         ret = 0;
                 }
                 break;
diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c
index d5ca8236315c..517b1d8f455b 100644
--- a/arch/powerpc/kernel/rtas.c
+++ b/arch/powerpc/kernel/rtas.c
@@ -15,7 +15,7 @@
 #include <linux/kernel.h>
 #include <linux/types.h>
 #include <linux/spinlock.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/init.h>
 #include <linux/capability.h>
 #include <linux/delay.h>
diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index b1d738d12890..77bb77da05c1 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -12,7 +12,7 @@
 
 #undef DEBUG
 
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/string.h>
 #include <linux/sched.h>
 #include <linux/init.h>
diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c
index 209135af0a40..c1ce86357ecb 100644
--- a/arch/powerpc/kernel/setup_32.c
+++ b/arch/powerpc/kernel/setup_32.c
@@ -117,7 +117,7 @@ notrace unsigned long __init early_init(unsigned long dt_ptr)
  * This is called very early on the boot process, after a minimal
  * MMU environment has been set up but before MMU_init is called.
  */
-notrace void __init machine_init(unsigned long dt_ptr)
+notrace void __init machine_init(u64 dt_ptr)
 {
         lockdep_init();
 
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index aebef1320ed7..1a9dea80a69b 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -12,7 +12,7 @@
 
 #undef DEBUG
 
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/string.h>
 #include <linux/sched.h>
 #include <linux/init.h>
@@ -278,14 +278,14 @@ static void __init initialize_cache_info(void)
 
         DBG(" -> initialize_cache_info()\n");
 
-        for (np = NULL; (np = of_find_node_by_type(np, "cpu"));) {
+        for_each_node_by_type(np, "cpu") {
                 num_cpus += 1;
 
-                /* We're assuming *all* of the CPUs have the same
+                /*
+                 * We're assuming *all* of the CPUs have the same
                  * d-cache and i-cache sizes... -Peter
                  */
-
-                if ( num_cpus == 1 ) {
+                if (num_cpus == 1) {
                         const u32 *sizep, *lsizep;
                         u32 size, lsize;
 
@@ -294,10 +294,13 @@ static void __init initialize_cache_info(void)
                         sizep = of_get_property(np, "d-cache-size", NULL);
                         if (sizep != NULL)
                                 size = *sizep;
-                        lsizep = of_get_property(np, "d-cache-block-size", NULL);
+                        lsizep = of_get_property(np, "d-cache-block-size",
+                                                 NULL);
                         /* fallback if block size missing */
                         if (lsizep == NULL)
-                                lsizep = of_get_property(np, "d-cache-line-size", NULL);
+                                lsizep = of_get_property(np,
+                                                         "d-cache-line-size",
+                                                         NULL);
                         if (lsizep != NULL)
                                 lsize = *lsizep;
                         if (sizep == 0 || lsizep == 0)
@@ -314,9 +317,12 @@ static void __init initialize_cache_info(void)
                         sizep = of_get_property(np, "i-cache-size", NULL);
                         if (sizep != NULL)
                                 size = *sizep;
-                        lsizep = of_get_property(np, "i-cache-block-size", NULL);
+                        lsizep = of_get_property(np, "i-cache-block-size",
+                                                 NULL);
                         if (lsizep == NULL)
-                                lsizep = of_get_property(np, "i-cache-line-size", NULL);
+                                lsizep = of_get_property(np,
+                                                         "i-cache-line-size",
+                                                         NULL);
                         if (lsizep != NULL)
                                 lsize = *lsizep;
                         if (sizep == 0 || lsizep == 0)
diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c
index e91c736cc842..a50b5ec281dc 100644
--- a/arch/powerpc/kernel/signal_64.c
+++ b/arch/powerpc/kernel/signal_64.c
@@ -23,7 +23,6 @@
 #include <linux/stddef.h>
 #include <linux/elf.h>
 #include <linux/ptrace.h>
-#include <linux/module.h>
 #include <linux/ratelimit.h>
 
 #include <asm/sigcontext.h>
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 7bf2187dfd99..6df70907d60a 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -18,7 +18,7 @@
 #undef DEBUG
 
 #include <linux/kernel.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/sched.h>
 #include <linux/smp.h>
 #include <linux/interrupt.h>
@@ -70,6 +70,10 @@
 static DEFINE_PER_CPU(struct task_struct *, idle_thread_array);
 #define get_idle_for_cpu(x)      (per_cpu(idle_thread_array, x))
 #define set_idle_for_cpu(x, p)   (per_cpu(idle_thread_array, x) = (p))
+
+/* State of each CPU during hotplug phases */
+static DEFINE_PER_CPU(int, cpu_state) = { 0 };
+
 #else
 static struct task_struct *idle_thread_array[NR_CPUS] __cpuinitdata ;
 #define get_idle_for_cpu(x)      (idle_thread_array[(x)])
@@ -104,12 +108,25 @@ int __devinit smp_generic_kick_cpu(int nr)
          * cpu_start field to become non-zero After we set cpu_start,
          * the processor will continue on to secondary_start
          */
-        paca[nr].cpu_start = 1;
-        smp_mb();
+        if (!paca[nr].cpu_start) {
+                paca[nr].cpu_start = 1;
+                smp_mb();
+                return 0;
+        }
+
+#ifdef CONFIG_HOTPLUG_CPU
+        /*
+         * Ok it's not there, so it might be soft-unplugged, let's
+         * try to bring it back
+         */
+        per_cpu(cpu_state, nr) = CPU_UP_PREPARE;
+        smp_wmb();
+        smp_send_reschedule(nr);
+#endif /* CONFIG_HOTPLUG_CPU */
 
         return 0;
 }
-#endif
+#endif /* CONFIG_PPC64 */
 
 static irqreturn_t call_function_action(int irq, void *data)
 {
@@ -170,7 +187,7 @@ int smp_request_message_ipi(int virq, int msg)
                 return 1;
         }
 #endif
-        err = request_irq(virq, smp_ipi_action[msg], IRQF_DISABLED|IRQF_PERCPU,
+        err = request_irq(virq, smp_ipi_action[msg], IRQF_PERCPU,
                           smp_ipi_name[msg], 0);
         WARN(err < 0, "unable to request_irq %d for %s (rc %d)\n",
                 virq, smp_ipi_name[msg], err);
@@ -357,8 +374,6 @@ void __devinit smp_prepare_boot_cpu(void)
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
-/* State of each CPU during hotplug phases */
-static DEFINE_PER_CPU(int, cpu_state) = { 0 };
 
 int generic_cpu_disable(void)
 {
@@ -406,6 +421,11 @@ void generic_set_cpu_dead(unsigned int cpu)
 {
         per_cpu(cpu_state, cpu) = CPU_DEAD;
 }
+
+int generic_check_cpu_restart(unsigned int cpu)
+{
+        return per_cpu(cpu_state, cpu) == CPU_UP_PREPARE;
+}
 #endif
 
 struct create_idle {
diff --git a/arch/powerpc/kernel/stacktrace.c b/arch/powerpc/kernel/stacktrace.c
index b0dbb1daa4df..3d30ef1038e5 100644
--- a/arch/powerpc/kernel/stacktrace.c
+++ b/arch/powerpc/kernel/stacktrace.c
@@ -10,7 +10,7 @@
  *      2 of the License, or (at your option) any later version.
  */
 
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/sched.h>
 #include <linux/stacktrace.h>
 #include <asm/ptrace.h>
diff --git a/arch/powerpc/kernel/swsusp.c b/arch/powerpc/kernel/swsusp.c
index aa17b76dd427..641f9adc6205 100644
--- a/arch/powerpc/kernel/swsusp.c
+++ b/arch/powerpc/kernel/swsusp.c
@@ -33,6 +33,6 @@ void save_processor_state(void)
 void restore_processor_state(void)
 {
 #ifdef CONFIG_PPC32
-        switch_mmu_context(NULL, current->active_mm);
+        switch_mmu_context(current->active_mm, current->active_mm);
 #endif
 }
diff --git a/arch/powerpc/kernel/swsusp_64.c b/arch/powerpc/kernel/swsusp_64.c
index 6f3f0697274e..168e88480223 100644
--- a/arch/powerpc/kernel/swsusp_64.c
+++ b/arch/powerpc/kernel/swsusp_64.c
@@ -9,6 +9,7 @@
 #include <asm/system.h>
 #include <asm/iommu.h>
 #include <linux/irq.h>
+#include <linux/sched.h>
 #include <linux/interrupt.h>
 
 void do_after_copyback(void)
diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c
index f0f2199e64e1..ce035c1905f0 100644
--- a/arch/powerpc/kernel/sysfs.c
+++ b/arch/powerpc/kernel/sysfs.c
@@ -4,7 +4,7 @@
 #include <linux/percpu.h>
 #include <linux/init.h>
 #include <linux/sched.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/nodemask.h>
 #include <linux/cpumask.h>
 #include <linux/notifier.h>
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 03b29a6759ab..522bb1dfc353 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -33,7 +33,7 @@
  */
 
 #include <linux/errno.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/sched.h>
 #include <linux/kernel.h>
 #include <linux/param.h>
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index f19d9777d3c1..4e5908264d1a 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -457,7 +457,14 @@ int machine_check_e500mc(struct pt_regs *regs)
 
         if (reason & MCSR_DCPERR_MC) {
                 printk("Data Cache Parity Error\n");
-                recoverable = 0;
+
+                /*
+                 * In write shadow mode we auto-recover from the error, but it
+                 * may still get logged and cause a machine check.  We should
+                 * only treat the non-write shadow case as non-recoverable.
+                 */
+                if (!(mfspr(SPRN_L1CSR2) & L1CSR2_DCWS))
+                        recoverable = 0;
         }
 
         if (reason & MCSR_L2MMU_MHIT) {
diff --git a/arch/powerpc/kernel/udbg.c b/arch/powerpc/kernel/udbg.c
index faa82c1f3f68..57fa2c0a531c 100644
--- a/arch/powerpc/kernel/udbg.c
+++ b/arch/powerpc/kernel/udbg.c
@@ -67,6 +67,14 @@ void __init udbg_early_init(void)
         udbg_init_usbgecko();
 #elif defined(CONFIG_PPC_EARLY_DEBUG_WSP)
         udbg_init_wsp();
+#elif defined(CONFIG_PPC_EARLY_DEBUG_EHV_BC)
+        udbg_init_ehv_bc();
+#elif defined(CONFIG_PPC_EARLY_DEBUG_PS3GELIC)
+        udbg_init_ps3gelic();
+#elif defined(CONFIG_PPC_EARLY_DEBUG_OPAL_RAW)
+        udbg_init_debug_opal_raw();
+#elif defined(CONFIG_PPC_EARLY_DEBUG_OPAL_HVSI)
+        udbg_init_debug_opal_hvsi();
 #endif
 
 #ifdef CONFIG_PPC_EARLY_DEBUG
diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c
index 142ab1008c3b..7d14bb697d40 100644
--- a/arch/powerpc/kernel/vdso.c
+++ b/arch/powerpc/kernel/vdso.c
@@ -9,7 +9,6 @@
  *  2 of the License, or (at your option) any later version.
  */
 
-#include <linux/module.h>
 #include <linux/errno.h>
 #include <linux/sched.h>
 #include <linux/kernel.h>
diff --git a/arch/powerpc/kernel/vio.c b/arch/powerpc/kernel/vio.c
index 1b695fdc362b..f65af61996bd 100644
--- a/arch/powerpc/kernel/vio.c
+++ b/arch/powerpc/kernel/vio.c
@@ -15,11 +15,12 @@
  */
 
 #include <linux/types.h>
+#include <linux/stat.h>
 #include <linux/device.h>
 #include <linux/init.h>
 #include <linux/slab.h>
 #include <linux/console.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/mm.h>
 #include <linux/dma-mapping.h>
 #include <linux/kobject.h>
@@ -605,15 +606,20 @@ static int vio_dma_iommu_dma_supported(struct device *dev, u64 mask)
         return dma_iommu_ops.dma_supported(dev, mask);
 }
 
-struct dma_map_ops vio_dma_mapping_ops = {
-        .alloc_coherent = vio_dma_iommu_alloc_coherent,
-        .free_coherent  = vio_dma_iommu_free_coherent,
-        .map_sg         = vio_dma_iommu_map_sg,
-        .unmap_sg       = vio_dma_iommu_unmap_sg,
-        .map_page       = vio_dma_iommu_map_page,
-        .unmap_page     = vio_dma_iommu_unmap_page,
-        .dma_supported  = vio_dma_iommu_dma_supported,
+static u64 vio_dma_get_required_mask(struct device *dev)
+{
+        return dma_iommu_ops.get_required_mask(dev);
+}
 
+struct dma_map_ops vio_dma_mapping_ops = {
+        .alloc_coherent    = vio_dma_iommu_alloc_coherent,
+        .free_coherent     = vio_dma_iommu_free_coherent,
+        .map_sg            = vio_dma_iommu_map_sg,
+        .unmap_sg          = vio_dma_iommu_unmap_sg,
+        .map_page          = vio_dma_iommu_map_page,
+        .unmap_page        = vio_dma_iommu_unmap_page,
+        .dma_supported     = vio_dma_iommu_dma_supported,
+        .get_required_mask = vio_dma_get_required_mask,
 };
 
 /**
diff --git a/arch/powerpc/kvm/44x.c b/arch/powerpc/kvm/44x.c
index da3a1225c0ac..7b612a76c701 100644
--- a/arch/powerpc/kvm/44x.c
+++ b/arch/powerpc/kvm/44x.c
@@ -20,6 +20,7 @@
 #include <linux/kvm_host.h>
 #include <linux/slab.h>
 #include <linux/err.h>
+#include <linux/export.h>
 
 #include <asm/reg.h>
 #include <asm/cputable.h>
@@ -78,6 +79,8 @@ int kvmppc_core_vcpu_setup(struct kvm_vcpu *vcpu)
         for (i = 0; i < ARRAY_SIZE(vcpu_44x->shadow_refs); i++)
                 vcpu_44x->shadow_refs[i].gtlb_index = -1;
 
+        vcpu->arch.cpu_type = KVM_CPU_440;
+
         return 0;
 }
 
diff --git a/arch/powerpc/kvm/Makefile b/arch/powerpc/kvm/Makefile
index 08428e2c188d..3688aeecc4b2 100644
--- a/arch/powerpc/kvm/Makefile
+++ b/arch/powerpc/kvm/Makefile
@@ -43,18 +43,22 @@ kvm-book3s_64-objs-$(CONFIG_KVM_BOOK3S_64_PR) := \
         fpu.o \
         book3s_paired_singles.o \
         book3s_pr.o \
+        book3s_pr_papr.o \
         book3s_emulate.o \
         book3s_interrupts.o \
         book3s_mmu_hpte.o \
         book3s_64_mmu_host.o \
         book3s_64_mmu.o \
         book3s_32_mmu.o
+kvm-book3s_64-builtin-objs-$(CONFIG_KVM_BOOK3S_64_PR) := \
+        book3s_rmhandlers.o
 
 kvm-book3s_64-objs-$(CONFIG_KVM_BOOK3S_64_HV) := \
         book3s_hv.o \
         book3s_hv_interrupts.o \
         book3s_64_mmu_hv.o
 kvm-book3s_64-builtin-objs-$(CONFIG_KVM_BOOK3S_64_HV) := \
+        book3s_hv_rmhandlers.o \
         book3s_hv_rm_mmu.o \
         book3s_64_vio_hv.o \
         book3s_hv_builtin.o
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index f68a34d16035..a459479995c6 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -16,6 +16,7 @@
 
 #include <linux/kvm_host.h>
 #include <linux/err.h>
+#include <linux/export.h>
 #include <linux/slab.h>
 
 #include <asm/reg.h>
diff --git a/arch/powerpc/kvm/book3s_32_sr.S b/arch/powerpc/kvm/book3s_32_sr.S
index 3608471ad2d8..7e06a6fc8d07 100644
--- a/arch/powerpc/kvm/book3s_32_sr.S
+++ b/arch/powerpc/kvm/book3s_32_sr.S
@@ -31,7 +31,7 @@
          * R1 = host R1
          * R2 = host R2
          * R3 = shadow vcpu
-         * all other volatile GPRS = free
+         * all other volatile GPRS = free except R4, R6
          * SVCPU[CR]  = guest CR
          * SVCPU[XER] = guest XER
          * SVCPU[CTR] = guest CTR
diff --git a/arch/powerpc/kvm/book3s_64_mmu.c b/arch/powerpc/kvm/book3s_64_mmu.c
index c6d3e194b6b4..b871721c0050 100644
--- a/arch/powerpc/kvm/book3s_64_mmu.c
+++ b/arch/powerpc/kvm/book3s_64_mmu.c
@@ -128,7 +128,13 @@ static hva_t kvmppc_mmu_book3s_64_get_pteg(
         dprintk("MMU: page=0x%x sdr1=0x%llx pteg=0x%llx vsid=0x%llx\n",
                 page, vcpu_book3s->sdr1, pteg, slbe->vsid);
 
-        r = gfn_to_hva(vcpu_book3s->vcpu.kvm, pteg >> PAGE_SHIFT);
+        /* When running a PAPR guest, SDR1 contains a HVA address instead
+           of a GPA */
+        if (vcpu_book3s->vcpu.arch.papr_enabled)
+                r = pteg;
+        else
+                r = gfn_to_hva(vcpu_book3s->vcpu.kvm, pteg >> PAGE_SHIFT);
+
         if (kvm_is_error_hva(r))
                 return r;
         return r | (pteg & ~PAGE_MASK);
diff --git a/arch/powerpc/kvm/book3s_64_slb.S b/arch/powerpc/kvm/book3s_64_slb.S
index 04e7d3bbfe8b..f2e6e48ea463 100644
--- a/arch/powerpc/kvm/book3s_64_slb.S
+++ b/arch/powerpc/kvm/book3s_64_slb.S
@@ -53,7 +53,7 @@ slb_exit_skip_ ## num:
          * R1 = host R1
          * R2 = host R2
          * R3 = shadow vcpu
-         * all other volatile GPRS = free
+         * all other volatile GPRS = free except R4, R6
          * SVCPU[CR]  = guest CR
          * SVCPU[XER] = guest XER
          * SVCPU[CTR] = guest CTR
diff --git a/arch/powerpc/kvm/book3s_emulate.c b/arch/powerpc/kvm/book3s_emulate.c
index 466846557089..0c9dc62532d0 100644
--- a/arch/powerpc/kvm/book3s_emulate.c
+++ b/arch/powerpc/kvm/book3s_emulate.c
@@ -63,6 +63,25 @@
  * function pointers, so let's just disable the define. */
 #undef mfsrin
 
+enum priv_level {
+        PRIV_PROBLEM = 0,
+        PRIV_SUPER = 1,
+        PRIV_HYPER = 2,
+};
+
+static bool spr_allowed(struct kvm_vcpu *vcpu, enum priv_level level)
+{
+        /* PAPR VMs only access supervisor SPRs */
+        if (vcpu->arch.papr_enabled && (level > PRIV_SUPER))
+                return false;
+
+        /* Limit user space to its own small SPR set */
+        if ((vcpu->arch.shared->msr & MSR_PR) && level > PRIV_PROBLEM)
+                return false;
+
+        return true;
+}
+
 int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
                            unsigned int inst, int *advance)
 {
@@ -296,6 +315,8 @@ int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs)
 
         switch (sprn) {
         case SPRN_SDR1:
+                if (!spr_allowed(vcpu, PRIV_HYPER))
+                        goto unprivileged;
                 to_book3s(vcpu)->sdr1 = spr_val;
                 break;
         case SPRN_DSISR:
@@ -390,6 +411,7 @@ int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs)
         case SPRN_PMC4_GEKKO:
         case SPRN_WPAR_GEKKO:
                 break;
+unprivileged:
         default:
                 printk(KERN_INFO "KVM: invalid SPR write: %d\n", sprn);
 #ifndef DEBUG_SPR
@@ -421,6 +443,8 @@ int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt)
                 break;
         }
         case SPRN_SDR1:
+                if (!spr_allowed(vcpu, PRIV_HYPER))
+                        goto unprivileged;
                 kvmppc_set_gpr(vcpu, rt, to_book3s(vcpu)->sdr1);
                 break;
         case SPRN_DSISR:
@@ -449,6 +473,10 @@ int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt)
         case SPRN_HID5:
                 kvmppc_set_gpr(vcpu, rt, to_book3s(vcpu)->hid[5]);
                 break;
+        case SPRN_CFAR:
+        case SPRN_PURR:
+                kvmppc_set_gpr(vcpu, rt, 0);
+                break;
         case SPRN_GQR0:
         case SPRN_GQR1:
         case SPRN_GQR2:
@@ -476,6 +504,7 @@ int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt)
                 kvmppc_set_gpr(vcpu, rt, 0);
                 break;
         default:
+unprivileged:
                 printk(KERN_INFO "KVM: invalid SPR read: %d\n", sprn);
 #ifndef DEBUG_SPR
                 emulated = EMULATE_FAIL;
diff --git a/arch/powerpc/kvm/book3s_exports.c b/arch/powerpc/kvm/book3s_exports.c
index 88c8f26add02..a150817d6d4c 100644
--- a/arch/powerpc/kvm/book3s_exports.c
+++ b/arch/powerpc/kvm/book3s_exports.c
@@ -17,15 +17,13 @@
  * Authors: Alexander Graf <agraf@suse.de>
  */
 
-#include <linux/module.h>
+#include <linux/export.h>
 #include <asm/kvm_book3s.h>
 
 #ifdef CONFIG_KVM_BOOK3S_64_HV
 EXPORT_SYMBOL_GPL(kvmppc_hv_entry_trampoline);
 #else
-EXPORT_SYMBOL_GPL(kvmppc_handler_trampoline_enter);
-EXPORT_SYMBOL_GPL(kvmppc_handler_lowmem_trampoline);
-EXPORT_SYMBOL_GPL(kvmppc_rmcall);
+EXPORT_SYMBOL_GPL(kvmppc_entry_trampoline);
 EXPORT_SYMBOL_GPL(kvmppc_load_up_fpu);
 #ifdef CONFIG_ALTIVEC
 EXPORT_SYMBOL_GPL(kvmppc_load_up_altivec);
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index cc0d7f1b19ab..0cdbc07cec14 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -24,6 +24,7 @@
 #include <linux/preempt.h>
 #include <linux/sched.h>
 #include <linux/delay.h>
+#include <linux/export.h>
 #include <linux/fs.h>
 #include <linux/anon_inodes.h>
 #include <linux/cpumask.h>
@@ -62,6 +63,8 @@
 /* #define EXIT_DEBUG_SIMPLE */
 /* #define EXIT_DEBUG_INT */
 
+static void kvmppc_end_cede(struct kvm_vcpu *vcpu);
+
 void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
         local_paca->kvm_hstate.kvm_vcpu = vcpu;
@@ -72,40 +75,10 @@ void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu)
 {
 }
 
-static void kvmppc_vcpu_blocked(struct kvm_vcpu *vcpu);
-static void kvmppc_vcpu_unblocked(struct kvm_vcpu *vcpu);
-
-void kvmppc_vcpu_block(struct kvm_vcpu *vcpu)
-{
-        u64 now;
-        unsigned long dec_nsec;
-
-        now = get_tb();
-        if (now >= vcpu->arch.dec_expires && !kvmppc_core_pending_dec(vcpu))
-                kvmppc_core_queue_dec(vcpu);
-        if (vcpu->arch.pending_exceptions)
-                return;
-        if (vcpu->arch.dec_expires != ~(u64)0) {
-                dec_nsec = (vcpu->arch.dec_expires - now) * NSEC_PER_SEC /
-                        tb_ticks_per_sec;
-                hrtimer_start(&vcpu->arch.dec_timer, ktime_set(0, dec_nsec),
-                              HRTIMER_MODE_REL);
-        }
-
-        kvmppc_vcpu_blocked(vcpu);
-
-        kvm_vcpu_block(vcpu);
-        vcpu->stat.halt_wakeup++;
-
-        if (vcpu->arch.dec_expires != ~(u64)0)
-                hrtimer_try_to_cancel(&vcpu->arch.dec_timer);
-
-        kvmppc_vcpu_unblocked(vcpu);
-}
-
 void kvmppc_set_msr(struct kvm_vcpu *vcpu, u64 msr)
 {
         vcpu->arch.shregs.msr = msr;
+        kvmppc_end_cede(vcpu);
 }
 
 void kvmppc_set_pvr(struct kvm_vcpu *vcpu, u32 pvr)
@@ -257,15 +230,6 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
 
         switch (req) {
         case H_CEDE:
-                vcpu->arch.shregs.msr |= MSR_EE;
-                vcpu->arch.ceded = 1;
-                smp_mb();
-                if (!vcpu->arch.prodded)
-                        kvmppc_vcpu_block(vcpu);
-                else
-                        vcpu->arch.prodded = 0;
-                smp_mb();
-                vcpu->arch.ceded = 0;
                 break;
         case H_PROD:
                 target = kvmppc_get_gpr(vcpu, 4);
@@ -388,20 +352,6 @@ static int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
                 break;
         }
 
-
-        if (!(r & RESUME_HOST)) {
-                /* To avoid clobbering exit_reason, only check for signals if
-                 * we aren't already exiting to userspace for some other
-                 * reason. */
-                if (signal_pending(tsk)) {
-                        vcpu->stat.signal_exits++;
-                        run->exit_reason = KVM_EXIT_INTR;
-                        r = -EINTR;
-                } else {
-                        kvmppc_core_deliver_interrupts(vcpu);
-                }
-        }
-
         return r;
 }
 
@@ -479,13 +429,9 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
         kvmppc_mmu_book3s_hv_init(vcpu);
 
         /*
-         * Some vcpus may start out in stopped state.  If we initialize
-         * them to busy-in-host state they will stop other vcpus in the
-         * vcore from running.  Instead we initialize them to blocked
-         * state, effectively considering them to be stopped until we
-         * see the first run ioctl for them.
+         * We consider the vcpu stopped until we see the first run ioctl for it.
          */
-        vcpu->arch.state = KVMPPC_VCPU_BLOCKED;
+        vcpu->arch.state = KVMPPC_VCPU_STOPPED;
 
         init_waitqueue_head(&vcpu->arch.cpu_run);
 
@@ -496,6 +442,7 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
                 if (vcore) {
                         INIT_LIST_HEAD(&vcore->runnable_threads);
                         spin_lock_init(&vcore->lock);
+                        init_waitqueue_head(&vcore->wq);
                 }
                 kvm->arch.vcores[core] = vcore;
         }
@@ -506,10 +453,12 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
 
         spin_lock(&vcore->lock);
         ++vcore->num_threads;
-        ++vcore->n_blocked;
         spin_unlock(&vcore->lock);
         vcpu->arch.vcore = vcore;
 
+        vcpu->arch.cpu_type = KVM_CPU_3S_64;
+        kvmppc_sanity_check(vcpu);
+
         return vcpu;
 
 free_vcpu:
@@ -524,30 +473,31 @@ void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu)
         kfree(vcpu);
 }
 
-static void kvmppc_vcpu_blocked(struct kvm_vcpu *vcpu)
+static void kvmppc_set_timer(struct kvm_vcpu *vcpu)
 {
-        struct kvmppc_vcore *vc = vcpu->arch.vcore;
+        unsigned long dec_nsec, now;
 
-        spin_lock(&vc->lock);
-        vcpu->arch.state = KVMPPC_VCPU_BLOCKED;
-        ++vc->n_blocked;
-        if (vc->n_runnable > 0 &&
-            vc->n_runnable + vc->n_blocked == vc->num_threads) {
-                vcpu = list_first_entry(&vc->runnable_threads, struct kvm_vcpu,
-                                        arch.run_list);
-                wake_up(&vcpu->arch.cpu_run);
+        now = get_tb();
+        if (now > vcpu->arch.dec_expires) {
+                /* decrementer has already gone negative */
+                kvmppc_core_queue_dec(vcpu);
+                kvmppc_core_deliver_interrupts(vcpu);
+                return;
         }
-        spin_unlock(&vc->lock);
+        dec_nsec = (vcpu->arch.dec_expires - now) * NSEC_PER_SEC
+                   / tb_ticks_per_sec;
+        hrtimer_start(&vcpu->arch.dec_timer, ktime_set(0, dec_nsec),
+                      HRTIMER_MODE_REL);
+        vcpu->arch.timer_running = 1;
 }
 
-static void kvmppc_vcpu_unblocked(struct kvm_vcpu *vcpu)
+static void kvmppc_end_cede(struct kvm_vcpu *vcpu)
 {
-        struct kvmppc_vcore *vc = vcpu->arch.vcore;
-
-        spin_lock(&vc->lock);
-        vcpu->arch.state = KVMPPC_VCPU_BUSY_IN_HOST;
-        --vc->n_blocked;
-        spin_unlock(&vc->lock);
+        vcpu->arch.ceded = 0;
+        if (vcpu->arch.timer_running) {
+                hrtimer_try_to_cancel(&vcpu->arch.dec_timer);
+                vcpu->arch.timer_running = 0;
+        }
 }
 
 extern int __kvmppc_vcore_entry(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu);
@@ -562,6 +512,7 @@ static void kvmppc_remove_runnable(struct kvmppc_vcore *vc,
                 return;
         vcpu->arch.state = KVMPPC_VCPU_BUSY_IN_HOST;
         --vc->n_runnable;
+        ++vc->n_busy;
         /* decrement the physical thread id of each following vcpu */
         v = vcpu;
         list_for_each_entry_continue(v, &vc->runnable_threads, arch.run_list)
@@ -575,15 +526,20 @@ static void kvmppc_start_thread(struct kvm_vcpu *vcpu)
         struct paca_struct *tpaca;
         struct kvmppc_vcore *vc = vcpu->arch.vcore;
 
+        if (vcpu->arch.timer_running) {
+                hrtimer_try_to_cancel(&vcpu->arch.dec_timer);
+                vcpu->arch.timer_running = 0;
+        }
         cpu = vc->pcpu + vcpu->arch.ptid;
         tpaca = &paca[cpu];
         tpaca->kvm_hstate.kvm_vcpu = vcpu;
         tpaca->kvm_hstate.kvm_vcore = vc;
+        tpaca->kvm_hstate.napping = 0;
+        vcpu->cpu = vc->pcpu;
         smp_wmb();
 #ifdef CONFIG_PPC_ICP_NATIVE
         if (vcpu->arch.ptid) {
                 tpaca->cpu_start = 0x80;
-                tpaca->kvm_hstate.in_guest = KVM_GUEST_MODE_GUEST;
                 wmb();
                 xics_wake_cpu(cpu);
                 ++vc->n_woken;
@@ -631,9 +587,10 @@ static int on_primary_thread(void)
  */
 static int kvmppc_run_core(struct kvmppc_vcore *vc)
 {
-        struct kvm_vcpu *vcpu, *vnext;
+        struct kvm_vcpu *vcpu, *vcpu0, *vnext;
         long ret;
         u64 now;
+        int ptid;
 
         /* don't start if any threads have a signal pending */
         list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list)
@@ -652,29 +609,50 @@ static int kvmppc_run_core(struct kvmppc_vcore *vc)
                 goto out;
         }
 
+        /*
+         * Assign physical thread IDs, first to non-ceded vcpus
+         * and then to ceded ones.
+         */
+        ptid = 0;
+        vcpu0 = NULL;
+        list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list) {
+                if (!vcpu->arch.ceded) {
+                        if (!ptid)
+                                vcpu0 = vcpu;
+                        vcpu->arch.ptid = ptid++;
+                }
+        }
+        if (!vcpu0)
+                return 0;               /* nothing to run */
+        list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list)
+                if (vcpu->arch.ceded)
+                        vcpu->arch.ptid = ptid++;
+
         vc->n_woken = 0;
         vc->nap_count = 0;
         vc->entry_exit_count = 0;
-        vc->vcore_running = 1;
+        vc->vcore_state = VCORE_RUNNING;
         vc->in_guest = 0;
         vc->pcpu = smp_processor_id();
+        vc->napping_threads = 0;
         list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list)
                 kvmppc_start_thread(vcpu);
-        vcpu = list_first_entry(&vc->runnable_threads, struct kvm_vcpu,
-                                arch.run_list);
 
+        preempt_disable();
         spin_unlock(&vc->lock);
 
-        preempt_disable();
         kvm_guest_enter();
-        __kvmppc_vcore_entry(NULL, vcpu);
+        __kvmppc_vcore_entry(NULL, vcpu0);
 
-        /* wait for secondary threads to finish writing their state to memory */
         spin_lock(&vc->lock);
+        /* disable sending of IPIs on virtual external irqs */
+        list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list)
+                vcpu->cpu = -1;
+        /* wait for secondary threads to finish writing their state to memory */
         if (vc->nap_count < vc->n_woken)
                 kvmppc_wait_for_nap(vc);
         /* prevent other vcpu threads from doing kvmppc_start_thread() now */
-        vc->vcore_running = 2;
+        vc->vcore_state = VCORE_EXITING;
         spin_unlock(&vc->lock);
 
         /* make sure updates to secondary vcpu structs are visible now */
@@ -690,22 +668,26 @@ static int kvmppc_run_core(struct kvmppc_vcore *vc)
                 if (now < vcpu->arch.dec_expires &&
                     kvmppc_core_pending_dec(vcpu))
                         kvmppc_core_dequeue_dec(vcpu);
-                if (!vcpu->arch.trap) {
-                        if (signal_pending(vcpu->arch.run_task)) {
-                                vcpu->arch.kvm_run->exit_reason = KVM_EXIT_INTR;
-                                vcpu->arch.ret = -EINTR;
-                        }
-                        continue;               /* didn't get to run */
-                }
-                ret = kvmppc_handle_exit(vcpu->arch.kvm_run, vcpu,
-                                         vcpu->arch.run_task);
+
+                ret = RESUME_GUEST;
+                if (vcpu->arch.trap)
+                        ret = kvmppc_handle_exit(vcpu->arch.kvm_run, vcpu,
+                                                 vcpu->arch.run_task);
+
                 vcpu->arch.ret = ret;
                 vcpu->arch.trap = 0;
+
+                if (vcpu->arch.ceded) {
+                        if (ret != RESUME_GUEST)
+                                kvmppc_end_cede(vcpu);
+                        else
+                                kvmppc_set_timer(vcpu);
+                }
         }
 
         spin_lock(&vc->lock);
  out:
-        vc->vcore_running = 0;
+        vc->vcore_state = VCORE_INACTIVE;
         list_for_each_entry_safe(vcpu, vnext, &vc->runnable_threads,
                                  arch.run_list) {
                 if (vcpu->arch.ret != RESUME_GUEST) {
@@ -717,82 +699,130 @@ static int kvmppc_run_core(struct kvmppc_vcore *vc)
         return 1;
 }
 
-static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
+/*
+ * Wait for some other vcpu thread to execute us, and
+ * wake us up when we need to handle something in the host.
+ */
+static void kvmppc_wait_for_exec(struct kvm_vcpu *vcpu, int wait_state)
 {
-        int ptid;
-        int wait_state;
-        struct kvmppc_vcore *vc;
         DEFINE_WAIT(wait);
 
-        /* No need to go into the guest when all we do is going out */
-        if (signal_pending(current)) {
-                kvm_run->exit_reason = KVM_EXIT_INTR;
-                return -EINTR;
+        prepare_to_wait(&vcpu->arch.cpu_run, &wait, wait_state);
+        if (vcpu->arch.state == KVMPPC_VCPU_RUNNABLE)
+                schedule();
+        finish_wait(&vcpu->arch.cpu_run, &wait);
+}
+
+/*
+ * All the vcpus in this vcore are idle, so wait for a decrementer
+ * or external interrupt to one of the vcpus.  vc->lock is held.
+ */
+static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc)
+{
+        DEFINE_WAIT(wait);
+        struct kvm_vcpu *v;
+        int all_idle = 1;
+
+        prepare_to_wait(&vc->wq, &wait, TASK_INTERRUPTIBLE);
+        vc->vcore_state = VCORE_SLEEPING;
+        spin_unlock(&vc->lock);
+        list_for_each_entry(v, &vc->runnable_threads, arch.run_list) {
+                if (!v->arch.ceded || v->arch.pending_exceptions) {
+                        all_idle = 0;
+                        break;
+                }
         }
+        if (all_idle)
+                schedule();
+        finish_wait(&vc->wq, &wait);
+        spin_lock(&vc->lock);
+        vc->vcore_state = VCORE_INACTIVE;
+}
 
-        /* On PPC970, check that we have an RMA region */
-        if (!vcpu->kvm->arch.rma && cpu_has_feature(CPU_FTR_ARCH_201))
-                return -EPERM;
+static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
+{
+        int n_ceded;
+        int prev_state;
+        struct kvmppc_vcore *vc;
+        struct kvm_vcpu *v, *vn;
 
         kvm_run->exit_reason = 0;
         vcpu->arch.ret = RESUME_GUEST;
         vcpu->arch.trap = 0;
 
-        flush_fp_to_thread(current);
-        flush_altivec_to_thread(current);
-        flush_vsx_to_thread(current);
-
         /*
          * Synchronize with other threads in this virtual core
          */
         vc = vcpu->arch.vcore;
         spin_lock(&vc->lock);
-        /* This happens the first time this is called for a vcpu */
-        if (vcpu->arch.state == KVMPPC_VCPU_BLOCKED)
-                --vc->n_blocked;
-        vcpu->arch.state = KVMPPC_VCPU_RUNNABLE;
-        ptid = vc->n_runnable;
+        vcpu->arch.ceded = 0;
         vcpu->arch.run_task = current;
         vcpu->arch.kvm_run = kvm_run;
-        vcpu->arch.ptid = ptid;
+        prev_state = vcpu->arch.state;
+        vcpu->arch.state = KVMPPC_VCPU_RUNNABLE;
         list_add_tail(&vcpu->arch.run_list, &vc->runnable_threads);
         ++vc->n_runnable;
 
-        wait_state = TASK_INTERRUPTIBLE;
-        while (vcpu->arch.state == KVMPPC_VCPU_RUNNABLE) {
-                if (signal_pending(current)) {
-                        if (!vc->vcore_running) {
-                                kvm_run->exit_reason = KVM_EXIT_INTR;
-                                vcpu->arch.ret = -EINTR;
-                                break;
-                        }
-                        /* have to wait for vcore to stop executing guest */
-                        wait_state = TASK_UNINTERRUPTIBLE;
-                        smp_send_reschedule(vc->pcpu);
+        /*
+         * This happens the first time this is called for a vcpu.
+         * If the vcore is already running, we may be able to start
+         * this thread straight away and have it join in.
+         */
+        if (prev_state == KVMPPC_VCPU_STOPPED) {
+                if (vc->vcore_state == VCORE_RUNNING &&
+                    VCORE_EXIT_COUNT(vc) == 0) {
+                        vcpu->arch.ptid = vc->n_runnable - 1;
+                        kvmppc_start_thread(vcpu);
                 }
 
-                if (!vc->vcore_running &&
-                    vc->n_runnable + vc->n_blocked == vc->num_threads) {
-                        /* we can run now */
-                        if (kvmppc_run_core(vc))
-                                continue;
-                }
+        } else if (prev_state == KVMPPC_VCPU_BUSY_IN_HOST)
+                --vc->n_busy;
 
-                if (vc->vcore_running == 1 && VCORE_EXIT_COUNT(vc) == 0)
-                        kvmppc_start_thread(vcpu);
+        while (vcpu->arch.state == KVMPPC_VCPU_RUNNABLE &&
+               !signal_pending(current)) {
+                if (vc->n_busy || vc->vcore_state != VCORE_INACTIVE) {
+                        spin_unlock(&vc->lock);
+                        kvmppc_wait_for_exec(vcpu, TASK_INTERRUPTIBLE);
+                        spin_lock(&vc->lock);
+                        continue;
+                }
+                n_ceded = 0;
+                list_for_each_entry(v, &vc->runnable_threads, arch.run_list)
+                        n_ceded += v->arch.ceded;
+                if (n_ceded == vc->n_runnable)
+                        kvmppc_vcore_blocked(vc);
+                else
+                        kvmppc_run_core(vc);
+
+                list_for_each_entry_safe(v, vn, &vc->runnable_threads,
+                                         arch.run_list) {
+                        kvmppc_core_deliver_interrupts(v);
+                        if (signal_pending(v->arch.run_task)) {
+                                kvmppc_remove_runnable(vc, v);
+                                v->stat.signal_exits++;
+                                v->arch.kvm_run->exit_reason = KVM_EXIT_INTR;
+                                v->arch.ret = -EINTR;
+                                wake_up(&v->arch.cpu_run);
+                        }
+                }
+        }
 
-                /* wait for other threads to come in, or wait for vcore */
-                prepare_to_wait(&vcpu->arch.cpu_run, &wait, wait_state);
-                spin_unlock(&vc->lock);
-                schedule();
-                finish_wait(&vcpu->arch.cpu_run, &wait);
-                spin_lock(&vc->lock);
+        if (signal_pending(current)) {
+                if (vc->vcore_state == VCORE_RUNNING ||
+                    vc->vcore_state == VCORE_EXITING) {
+                        spin_unlock(&vc->lock);
+                        kvmppc_wait_for_exec(vcpu, TASK_UNINTERRUPTIBLE);
+                        spin_lock(&vc->lock);
+                }
+                if (vcpu->arch.state == KVMPPC_VCPU_RUNNABLE) {
+                        kvmppc_remove_runnable(vc, vcpu);
+                        vcpu->stat.signal_exits++;
+                        kvm_run->exit_reason = KVM_EXIT_INTR;
+                        vcpu->arch.ret = -EINTR;
+                }
         }
 
-        if (vcpu->arch.state == KVMPPC_VCPU_RUNNABLE)
-                kvmppc_remove_runnable(vc, vcpu);
         spin_unlock(&vc->lock);
-
         return vcpu->arch.ret;
 }
 
@@ -800,6 +830,26 @@ int kvmppc_vcpu_run(struct kvm_run *run, struct kvm_vcpu *vcpu)
 {
         int r;
 
+        if (!vcpu->arch.sane) {
+                run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
+                return -EINVAL;
+        }
+
+        /* No need to go into the guest when all we'll do is come back out */
+        if (signal_pending(current)) {
+                run->exit_reason = KVM_EXIT_INTR;
+                return -EINTR;
+        }
+
+        /* On PPC970, check that we have an RMA region */
+        if (!vcpu->kvm->arch.rma && cpu_has_feature(CPU_FTR_ARCH_201))
+                return -EPERM;
+
+        flush_fp_to_thread(current);
+        flush_altivec_to_thread(current);
+        flush_vsx_to_thread(current);
+        vcpu->arch.wqp = &vcpu->arch.vcore->wq;
+
         do {
                 r = kvmppc_run_vcpu(run, vcpu);
 
diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c
index d43120355eec..286f13d601cf 100644
--- a/arch/powerpc/kvm/book3s_hv_builtin.c
+++ b/arch/powerpc/kvm/book3s_hv_builtin.c
@@ -8,6 +8,7 @@
 
 #include <linux/kvm_host.h>
 #include <linux/preempt.h>
+#include <linux/export.h>
 #include <linux/sched.h>
 #include <linux/spinlock.h>
 #include <linux/bootmem.h>
diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
index fcfe6b055558..bacb0cfa3602 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
@@ -110,39 +110,6 @@ long kvmppc_h_enter(struct kvm_vcpu *vcpu, unsigned long flags,
         return H_SUCCESS;
 }
 
-static unsigned long compute_tlbie_rb(unsigned long v, unsigned long r,
-                                      unsigned long pte_index)
-{
-        unsigned long rb, va_low;
-
-        rb = (v & ~0x7fUL) << 16;               /* AVA field */
-        va_low = pte_index >> 3;
-        if (v & HPTE_V_SECONDARY)
-                va_low = ~va_low;
-        /* xor vsid from AVA */
-        if (!(v & HPTE_V_1TB_SEG))
-                va_low ^= v >> 12;
-        else
-                va_low ^= v >> 24;
-        va_low &= 0x7ff;
-        if (v & HPTE_V_LARGE) {
-                rb |= 1;                        /* L field */
-                if (cpu_has_feature(CPU_FTR_ARCH_206) &&
-                    (r & 0xff000)) {
-                        /* non-16MB large page, must be 64k */
-                        /* (masks depend on page size) */
-                        rb |= 0x1000;           /* page encoding in LP field */
-                        rb |= (va_low & 0x7f) << 16; /* 7b of VA in AVA/LP field */
-                        rb |= (va_low & 0xfe);  /* AVAL field (P7 doesn't seem to care) */
-                }
-        } else {
-                /* 4kB page */
-                rb |= (va_low & 0x7ff) << 12;   /* remaining 11b of VA */
-        }
-        rb |= (v >> 54) & 0x300;                /* B field */
-        return rb;
-}
-
 #define LOCK_TOKEN      (*(u32 *)(&get_paca()->lock_token))
 
 static inline int try_lock_tlbie(unsigned int *lock)
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index de2950135e6e..44d8829334ab 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -20,7 +20,10 @@
 #include <asm/ppc_asm.h>
 #include <asm/kvm_asm.h>
 #include <asm/reg.h>
+#include <asm/mmu.h>
 #include <asm/page.h>
+#include <asm/ptrace.h>
+#include <asm/hvcall.h>
 #include <asm/asm-offsets.h>
 #include <asm/exception-64s.h>
 
@@ -49,7 +52,7 @@ kvmppc_skip_Hinterrupt:
         b       .
 
 /*
- * Call kvmppc_handler_trampoline_enter in real mode.
+ * Call kvmppc_hv_entry in real mode.
  * Must be called with interrupts hard-disabled.
  *
  * Input Registers:
@@ -89,6 +92,12 @@ _GLOBAL(kvmppc_hv_entry_trampoline)
 kvm_start_guest:
         ld      r1,PACAEMERGSP(r13)
         subi    r1,r1,STACK_FRAME_OVERHEAD
+        ld      r2,PACATOC(r13)
+
+        /* were we napping due to cede? */
+        lbz     r0,HSTATE_NAPPING(r13)
+        cmpwi   r0,0
+        bne     kvm_end_cede
 
         /* get vcpu pointer */
         ld      r4, HSTATE_KVM_VCPU(r13)
@@ -276,15 +285,9 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
         cmpwi   r0,0
         beq     20b
 
-        /* Set LPCR.  Set the MER bit if there is a pending external irq. */
+        /* Set LPCR and RMOR. */
 10:     ld      r8,KVM_LPCR(r9)
-        ld      r0,VCPU_PENDING_EXC(r4)
-        li      r7,(1 << BOOK3S_IRQPRIO_EXTERNAL)
-        oris    r7,r7,(1 << BOOK3S_IRQPRIO_EXTERNAL_LEVEL)@h
-        and.    r0,r0,r7
-        beq     11f
-        ori     r8,r8,LPCR_MER
-11:     mtspr   SPRN_LPCR,r8
+        mtspr   SPRN_LPCR,r8
         ld      r8,KVM_RMOR(r9)
         mtspr   SPRN_RMOR,r8
         isync
@@ -448,19 +451,50 @@ toc_tlbie_lock:
         mtctr   r6
         mtxer   r7
 
-        /* Move SRR0 and SRR1 into the respective regs */
+kvmppc_cede_reentry:            /* r4 = vcpu, r13 = paca */
         ld      r6, VCPU_SRR0(r4)
         ld      r7, VCPU_SRR1(r4)
-        mtspr   SPRN_SRR0, r6
-        mtspr   SPRN_SRR1, r7
-
         ld      r10, VCPU_PC(r4)
+        ld      r11, VCPU_MSR(r4)       /* r11 = vcpu->arch.msr & ~MSR_HV */
 
-        ld      r11, VCPU_MSR(r4)       /* r10 = vcpu->arch.msr & ~MSR_HV */
         rldicl  r11, r11, 63 - MSR_HV_LG, 1
         rotldi  r11, r11, 1 + MSR_HV_LG
         ori     r11, r11, MSR_ME
 
+        /* Check if we can deliver an external or decrementer interrupt now */
+        ld      r0,VCPU_PENDING_EXC(r4)
+        li      r8,(1 << BOOK3S_IRQPRIO_EXTERNAL)
+        oris    r8,r8,(1 << BOOK3S_IRQPRIO_EXTERNAL_LEVEL)@h
+        and     r0,r0,r8
+        cmpdi   cr1,r0,0
+        andi.   r0,r11,MSR_EE
+        beq     cr1,11f
+BEGIN_FTR_SECTION
+        mfspr   r8,SPRN_LPCR
+        ori     r8,r8,LPCR_MER
+        mtspr   SPRN_LPCR,r8
+        isync
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
+        beq     5f
+        li      r0,BOOK3S_INTERRUPT_EXTERNAL
+12:     mr      r6,r10
+        mr      r10,r0
+        mr      r7,r11
+        li      r11,(MSR_ME << 1) | 1   /* synthesize MSR_SF | MSR_ME */
+        rotldi  r11,r11,63
+        b       5f
+11:     beq     5f
+        mfspr   r0,SPRN_DEC
+        cmpwi   r0,0
+        li      r0,BOOK3S_INTERRUPT_DECREMENTER
+        blt     12b
+
+        /* Move SRR0 and SRR1 into the respective regs */
+5:      mtspr   SPRN_SRR0, r6
+        mtspr   SPRN_SRR1, r7
+        li      r0,0
+        stb     r0,VCPU_CEDED(r4)       /* cancel cede */
+
 fast_guest_return:
         mtspr   SPRN_HSRR0,r10
         mtspr   SPRN_HSRR1,r11
@@ -574,21 +608,20 @@ kvmppc_interrupt:
         /* See if this is something we can handle in real mode */
         cmpwi   r12,BOOK3S_INTERRUPT_SYSCALL
         beq     hcall_try_real_mode
-hcall_real_cont:
 
         /* Check for mediated interrupts (could be done earlier really ...) */
 BEGIN_FTR_SECTION
         cmpwi   r12,BOOK3S_INTERRUPT_EXTERNAL
         bne+    1f
-        ld      r5,VCPU_KVM(r9)
-        ld      r5,KVM_LPCR(r5)
         andi.   r0,r11,MSR_EE
         beq     1f
+        mfspr   r5,SPRN_LPCR
         andi.   r0,r5,LPCR_MER
         bne     bounce_ext_interrupt
 1:
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
 
+hcall_real_cont:                /* r9 = vcpu, r12 = trap, r13 = paca */
         /* Save DEC */
         mfspr   r5,SPRN_DEC
         mftb    r6
@@ -682,7 +715,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_201)
         slbia
         ptesync
 
-hdec_soon:
+hdec_soon:                      /* r9 = vcpu, r12 = trap, r13 = paca */
 BEGIN_FTR_SECTION
         b       32f
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
@@ -700,6 +733,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
         addi    r0,r3,0x100
         stwcx.  r0,0,r6
         bne     41b
+        lwsync
 
         /*
          * At this point we have an interrupt that we have to pass
@@ -713,18 +747,39 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
          * interrupt, since the other threads will already be on their
          * way here in that case.
          */
+        cmpwi   r3,0x100        /* Are we the first here? */
+        bge     43f
+        cmpwi   r3,1            /* Are any other threads in the guest? */
+        ble     43f
         cmpwi   r12,BOOK3S_INTERRUPT_HV_DECREMENTER
         beq     40f
-        cmpwi   r3,0x100        /* Are we the first here? */
-        bge     40f
-        cmpwi   r3,1
-        ble     40f
         li      r0,0
         mtspr   SPRN_HDEC,r0
 40:
+        /*
+         * Send an IPI to any napping threads, since an HDEC interrupt
+         * doesn't wake CPUs up from nap.
+         */
+        lwz     r3,VCORE_NAPPING_THREADS(r5)
+        lwz     r4,VCPU_PTID(r9)
+        li      r0,1
+        sldi    r0,r0,r4
+        andc.   r3,r3,r0                /* no sense IPI'ing ourselves */
+        beq     43f
+        mulli   r4,r4,PACA_SIZE         /* get paca for thread 0 */
+        subf    r6,r4,r13
+42:     andi.   r0,r3,1
+        beq     44f
+        ld      r8,HSTATE_XICS_PHYS(r6) /* get thread's XICS reg addr */
+        li      r0,IPI_PRIORITY
+        li      r7,XICS_QIRR
+        stbcix  r0,r7,r8                /* trigger the IPI */
+44:     srdi.   r3,r3,1
+        addi    r6,r6,PACA_SIZE
+        bne     42b
 
         /* Secondary threads wait for primary to do partition switch */
-        ld      r4,VCPU_KVM(r9)         /* pointer to struct kvm */
+43:     ld      r4,VCPU_KVM(r9)         /* pointer to struct kvm */
         ld      r5,HSTATE_KVM_VCORE(r13)
         lwz     r3,VCPU_PTID(r9)
         cmpwi   r3,0
@@ -1077,7 +1132,6 @@ hcall_try_real_mode:
 hcall_real_fallback:
         li      r12,BOOK3S_INTERRUPT_SYSCALL
         ld      r9, HSTATE_KVM_VCPU(r13)
-        ld      r11, VCPU_MSR(r9)
 
         b       hcall_real_cont
 
@@ -1139,7 +1193,7 @@ hcall_real_table:
         .long   0               /* 0xd4 */
         .long   0               /* 0xd8 */
         .long   0               /* 0xdc */
-        .long   0               /* 0xe0 */
+        .long   .kvmppc_h_cede - hcall_real_table
         .long   0               /* 0xe4 */
         .long   0               /* 0xe8 */
         .long   0               /* 0xec */
@@ -1168,7 +1222,8 @@ bounce_ext_interrupt:
         mtspr   SPRN_SRR0,r10
         mtspr   SPRN_SRR1,r11
         li      r10,BOOK3S_INTERRUPT_EXTERNAL
-        LOAD_REG_IMMEDIATE(r11,MSR_SF | MSR_ME);
+        li      r11,(MSR_ME << 1) | 1   /* synthesize MSR_SF | MSR_ME */
+        rotldi  r11,r11,63
         b       fast_guest_return
 
 _GLOBAL(kvmppc_h_set_dabr)
@@ -1177,6 +1232,178 @@ _GLOBAL(kvmppc_h_set_dabr)
         li      r3,0
         blr
 
+_GLOBAL(kvmppc_h_cede)
+        ori     r11,r11,MSR_EE
+        std     r11,VCPU_MSR(r3)
+        li      r0,1
+        stb     r0,VCPU_CEDED(r3)
+        sync                    /* order setting ceded vs. testing prodded */
+        lbz     r5,VCPU_PRODDED(r3)
+        cmpwi   r5,0
+        bne     1f
+        li      r0,0            /* set trap to 0 to say hcall is handled */
+        stw     r0,VCPU_TRAP(r3)
+        li      r0,H_SUCCESS
+        std     r0,VCPU_GPR(r3)(r3)
+BEGIN_FTR_SECTION
+        b       2f              /* just send it up to host on 970 */
+END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_206)
+
+        /*
+         * Set our bit in the bitmask of napping threads unless all the
+         * other threads are already napping, in which case we send this
+         * up to the host.
+         */
+        ld      r5,HSTATE_KVM_VCORE(r13)
+        lwz     r6,VCPU_PTID(r3)
+        lwz     r8,VCORE_ENTRY_EXIT(r5)
+        clrldi  r8,r8,56
+        li      r0,1
+        sld     r0,r0,r6
+        addi    r6,r5,VCORE_NAPPING_THREADS
+31:     lwarx   r4,0,r6
+        or      r4,r4,r0
+        PPC_POPCNTW(r7,r4)
+        cmpw    r7,r8
+        bge     2f
+        stwcx.  r4,0,r6
+        bne     31b
+        li      r0,1
+        stb     r0,HSTATE_NAPPING(r13)
+        /* order napping_threads update vs testing entry_exit_count */
+        lwsync
+        mr      r4,r3
+        lwz     r7,VCORE_ENTRY_EXIT(r5)
+        cmpwi   r7,0x100
+        bge     33f             /* another thread already exiting */
+
+/*
+ * Although not specifically required by the architecture, POWER7
+ * preserves the following registers in nap mode, even if an SMT mode
+ * switch occurs: SLB entries, PURR, SPURR, AMOR, UAMOR, AMR, SPRG0-3,
+ * 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)
+
+        /* save FP state */
+        bl      .kvmppc_save_fp
+
+        /*
+         * Take a nap until a decrementer or external interrupt occurs,
+         * with PECE1 (wake on decr) and PECE0 (wake on external) set in LPCR
+         */
+        li      r0,0x80
+        stb     r0,PACAPROCSTART(r13)
+        mfspr   r5,SPRN_LPCR
+        ori     r5,r5,LPCR_PECE0 | LPCR_PECE1
+        mtspr   SPRN_LPCR,r5
+        isync
+        li      r0, 0
+        std     r0, HSTATE_SCRATCH0(r13)
+        ptesync
+        ld      r0, HSTATE_SCRATCH0(r13)
+1:      cmpd    r0, r0
+        bne     1b
+        nap
+        b       .
+
+kvm_end_cede:
+        /* Woken by external or decrementer interrupt */
+        ld      r1, HSTATE_HOST_R1(r13)
+        ld      r2, PACATOC(r13)
+
+        /* If we're a secondary thread and we got here by an IPI, ack it */
+        ld      r4,HSTATE_KVM_VCPU(r13)
+        lwz     r3,VCPU_PTID(r4)
+        cmpwi   r3,0
+        beq     27f
+        mfspr   r3,SPRN_SRR1
+        rlwinm  r3,r3,44-31,0x7         /* extract wake reason field */
+        cmpwi   r3,4                    /* was it an external interrupt? */
+        bne     27f
+        ld      r5, HSTATE_XICS_PHYS(r13)
+        li      r0,0xff
+        li      r6,XICS_QIRR
+        li      r7,XICS_XIRR
+        lwzcix  r8,r5,r7                /* ack the interrupt */
+        sync
+        stbcix  r0,r5,r6                /* clear it */
+        stwcix  r8,r5,r7                /* EOI it */
+27:
+        /* load up FP state */
+        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)
+
+        /* clear our bit in vcore->napping_threads */
+33:     ld      r5,HSTATE_KVM_VCORE(r13)
+        lwz     r3,VCPU_PTID(r4)
+        li      r0,1
+        sld     r0,r0,r3
+        addi    r6,r5,VCORE_NAPPING_THREADS
+32:     lwarx   r7,0,r6
+        andc    r7,r7,r0
+        stwcx.  r7,0,r6
+        bne     32b
+        li      r0,0
+        stb     r0,HSTATE_NAPPING(r13)
+
+        /* see if any other thread is already exiting */
+        lwz     r0,VCORE_ENTRY_EXIT(r5)
+        cmpwi   r0,0x100
+        blt     kvmppc_cede_reentry     /* if not go back to guest */
+
+        /* some threads are exiting, so go to the guest exit path */
+        b       hcall_real_fallback
+
+        /* cede when already previously prodded case */
+1:      li      r0,0
+        stb     r0,VCPU_PRODDED(r3)
+        sync                    /* order testing prodded vs. clearing ceded */
+        stb     r0,VCPU_CEDED(r3)
+        li      r3,H_SUCCESS
+        blr
+
+        /* we've ceded but we want to give control to the host */
+2:      li      r3,H_TOO_HARD
+        blr
+
 secondary_too_late:
         ld      r5,HSTATE_KVM_VCORE(r13)
         HMT_LOW
@@ -1194,14 +1421,20 @@ secondary_too_late:
         slbmte  r6,r5
 1:      addi    r11,r11,16
         .endr
-        b       50f
 
 secondary_nap:
-        /* Clear any pending IPI */
-50:     ld      r5, HSTATE_XICS_PHYS(r13)
+        /* Clear any pending IPI - assume we're a secondary thread */
+        ld      r5, HSTATE_XICS_PHYS(r13)
+        li      r7, XICS_XIRR
+        lwzcix  r3, r5, r7              /* ack any pending interrupt */
+        rlwinm. r0, r3, 0, 0xffffff     /* any pending? */
+        beq     37f
+        sync
         li      r0, 0xff
         li      r6, XICS_QIRR
-        stbcix  r0, r5, r6
+        stbcix  r0, r5, r6              /* clear the IPI */
+        stwcix  r3, r5, r7              /* EOI it */
+37:     sync
 
         /* increment the nap count and then go to nap mode */
         ld      r4, HSTATE_KVM_VCORE(r13)
@@ -1211,13 +1444,12 @@ secondary_nap:
         addi    r3, r3, 1
         stwcx.  r3, 0, r4
         bne     51b
-        isync
 
+        li      r3, LPCR_PECE0
         mfspr   r4, SPRN_LPCR
-        li      r0, LPCR_PECE
-        andc    r4, r4, r0
-        ori     r4, r4, LPCR_PECE0      /* exit nap on interrupt */
+        rlwimi  r4, r3, 0, LPCR_PECE0 | LPCR_PECE1
         mtspr   SPRN_LPCR, r4
+        isync
         li      r0, 0
         std     r0, HSTATE_SCRATCH0(r13)
         ptesync
diff --git a/arch/powerpc/kvm/book3s_interrupts.S b/arch/powerpc/kvm/book3s_interrupts.S
index c54b0e30cf3f..0a8515a5c042 100644
--- a/arch/powerpc/kvm/book3s_interrupts.S
+++ b/arch/powerpc/kvm/book3s_interrupts.S
@@ -29,27 +29,11 @@
 #define ULONG_SIZE              8
 #define FUNC(name)              GLUE(.,name)
 
-#define GET_SHADOW_VCPU_R13
-
-#define DISABLE_INTERRUPTS      \
-        mfmsr   r0;             \
-        rldicl  r0,r0,48,1;     \
-        rotldi  r0,r0,16;       \
-        mtmsrd  r0,1;           \
-
 #elif defined(CONFIG_PPC_BOOK3S_32)
 
 #define ULONG_SIZE              4
 #define FUNC(name)              name
 
-#define GET_SHADOW_VCPU_R13     \
-        lwz     r13, (THREAD + THREAD_KVM_SVCPU)(r2)
-
-#define DISABLE_INTERRUPTS      \
-        mfmsr   r0;             \
-        rlwinm  r0,r0,0,17,15;  \
-        mtmsr   r0;             \
-
 #endif /* CONFIG_PPC_BOOK3S_XX */
 
 
@@ -108,44 +92,17 @@ kvm_start_entry:
 
 kvm_start_lightweight:
 
-        GET_SHADOW_VCPU_R13
-        PPC_LL  r3, VCPU_HIGHMEM_HANDLER(r4)
-        PPC_STL r3, HSTATE_VMHANDLER(r13)
-
-        PPC_LL  r10, VCPU_SHADOW_MSR(r4)        /* r10 = vcpu->arch.shadow_msr */
-
-        DISABLE_INTERRUPTS
-
 #ifdef CONFIG_PPC_BOOK3S_64
-        /* Some guests may need to have dcbz set to 32 byte length.
-         *
-         * Usually we ensure that by patching the guest's instructions
-         * to trap on dcbz and emulate it in the hypervisor.
-         *
-         * If we can, we should tell the CPU to use 32 byte dcbz though,
-         * because that's a lot faster.
-         */
-
         PPC_LL  r3, VCPU_HFLAGS(r4)
-        rldicl. r3, r3, 0, 63           /* CR = ((r3 & 1) == 0) */
-        beq     no_dcbz32_on
-
-        mfspr   r3,SPRN_HID5
-        ori     r3, r3, 0x80            /* XXX HID5_dcbz32 = 0x80 */
-        mtspr   SPRN_HID5,r3
-
-no_dcbz32_on:
-
+        rldicl  r3, r3, 0, 63           /* r3 &= 1 */
+        stb     r3, HSTATE_RESTORE_HID5(r13)
 #endif /* CONFIG_PPC_BOOK3S_64 */
 
-        PPC_LL  r6, VCPU_RMCALL(r4)
-        mtctr   r6
-
-        PPC_LL  r3, VCPU_TRAMPOLINE_ENTER(r4)
-        LOAD_REG_IMMEDIATE(r4, MSR_KERNEL & ~(MSR_IR | MSR_DR))
+        PPC_LL  r4, VCPU_SHADOW_MSR(r4) /* get shadow_msr */
 
         /* Jump to segment patching handler and into our guest */
-        bctr
+        bl      FUNC(kvmppc_entry_trampoline)
+        nop
 
 /*
  * This is the handler in module memory. It gets jumped at from the
@@ -170,21 +127,6 @@ kvmppc_handler_highmem:
         /* R7 = vcpu */
         PPC_LL  r7, GPR4(r1)
 
-#ifdef CONFIG_PPC_BOOK3S_64
-
-        PPC_LL  r5, VCPU_HFLAGS(r7)
-        rldicl. r5, r5, 0, 63           /* CR = ((r5 & 1) == 0) */
-        beq     no_dcbz32_off
-
-        li      r4, 0
-        mfspr   r5,SPRN_HID5
-        rldimi  r5,r4,6,56
-        mtspr   SPRN_HID5,r5
-
-no_dcbz32_off:
-
-#endif /* CONFIG_PPC_BOOK3S_64 */
-
         PPC_STL r14, VCPU_GPR(r14)(r7)
         PPC_STL r15, VCPU_GPR(r15)(r7)
         PPC_STL r16, VCPU_GPR(r16)(r7)
@@ -204,67 +146,6 @@ no_dcbz32_off:
         PPC_STL r30, VCPU_GPR(r30)(r7)
         PPC_STL r31, VCPU_GPR(r31)(r7)
 
-        /* Restore host msr -> SRR1 */
-        PPC_LL  r6, VCPU_HOST_MSR(r7)
-
-        /*
-         * For some interrupts, we need to call the real Linux
-         * handler, so it can do work for us. This has to happen
-         * as if the interrupt arrived from the kernel though,
-         * so let's fake it here where most state is restored.
-         *
-         * Call Linux for hardware interrupts/decrementer
-         * r3 = address of interrupt handler (exit reason)
-         */
-
-        cmpwi   r12, BOOK3S_INTERRUPT_EXTERNAL
-        beq     call_linux_handler
-        cmpwi   r12, BOOK3S_INTERRUPT_DECREMENTER
-        beq     call_linux_handler
-        cmpwi   r12, BOOK3S_INTERRUPT_PERFMON
-        beq     call_linux_handler
-
-        /* Back to EE=1 */
-        mtmsr   r6
-        sync
-        b       kvm_return_point
-
-call_linux_handler:
-
-        /*
-         * If we land here we need to jump back to the handler we
-         * came from.
-         *
-         * We have a page that we can access from real mode, so let's
-         * jump back to that and use it as a trampoline to get back into the
-         * interrupt handler!
-         *
-         * R3 still contains the exit code,
-         * R5 VCPU_HOST_RETIP and
-         * R6 VCPU_HOST_MSR
-         */
-
-        /* Restore host IP -> SRR0 */
-        PPC_LL  r5, VCPU_HOST_RETIP(r7)
-
-        /* XXX Better move to a safe function?
-         *     What if we get an HTAB flush in between mtsrr0 and mtsrr1? */
-
-        mtlr    r12
-
-        PPC_LL  r4, VCPU_TRAMPOLINE_LOWMEM(r7)
-        mtsrr0  r4
-        LOAD_REG_IMMEDIATE(r3, MSR_KERNEL & ~(MSR_IR | MSR_DR))
-        mtsrr1  r3
-
-        RFI
-
-.global kvm_return_point
-kvm_return_point:
-
-        /* Jump back to lightweight entry if we're supposed to */
-        /* go back into the guest */
-
         /* Pass the exit number as 3rd argument to kvmppc_handle_exit */
         mr      r5, r12
 
diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c
index 0c0d3f274437..bc4d50dec78b 100644
--- a/arch/powerpc/kvm/book3s_pr.c
+++ b/arch/powerpc/kvm/book3s_pr.c
@@ -20,6 +20,7 @@
  */
 
 #include <linux/kvm_host.h>
+#include <linux/export.h>
 #include <linux/err.h>
 #include <linux/slab.h>
 
@@ -150,16 +151,22 @@ void kvmppc_set_pvr(struct kvm_vcpu *vcpu, u32 pvr)
 #ifdef CONFIG_PPC_BOOK3S_64
         if ((pvr >= 0x330000) && (pvr < 0x70330000)) {
                 kvmppc_mmu_book3s_64_init(vcpu);
-                to_book3s(vcpu)->hior = 0xfff00000;
+                if (!to_book3s(vcpu)->hior_sregs)
+                        to_book3s(vcpu)->hior = 0xfff00000;
                 to_book3s(vcpu)->msr_mask = 0xffffffffffffffffULL;
+                vcpu->arch.cpu_type = KVM_CPU_3S_64;
         } else
 #endif
         {
                 kvmppc_mmu_book3s_32_init(vcpu);
-                to_book3s(vcpu)->hior = 0;
+                if (!to_book3s(vcpu)->hior_sregs)
+                        to_book3s(vcpu)->hior = 0;
                 to_book3s(vcpu)->msr_mask = 0xffffffffULL;
+                vcpu->arch.cpu_type = KVM_CPU_3S_32;
         }
 
+        kvmppc_sanity_check(vcpu);
+
         /* If we are in hypervisor level on 970, we can tell the CPU to
          * treat DCBZ as 32 bytes store */
         vcpu->arch.hflags &= ~BOOK3S_HFLAG_DCBZ32;
@@ -646,7 +653,27 @@ program_interrupt:
                 break;
         }
         case BOOK3S_INTERRUPT_SYSCALL:
-                if (vcpu->arch.osi_enabled &&
+                if (vcpu->arch.papr_enabled &&
+                    (kvmppc_get_last_inst(vcpu) == 0x44000022) &&
+                    !(vcpu->arch.shared->msr & MSR_PR)) {
+                        /* SC 1 papr hypercalls */
+                        ulong cmd = kvmppc_get_gpr(vcpu, 3);
+                        int i;
+
+                        if (kvmppc_h_pr(vcpu, cmd) == EMULATE_DONE) {
+                                r = RESUME_GUEST;
+                                break;
+                        }
+
+                        run->papr_hcall.nr = cmd;
+                        for (i = 0; i < 9; ++i) {
+                                ulong gpr = kvmppc_get_gpr(vcpu, 4 + i);
+                                run->papr_hcall.args[i] = gpr;
+                        }
+                        run->exit_reason = KVM_EXIT_PAPR_HCALL;
+                        vcpu->arch.hcall_needed = 1;
+                        r = RESUME_HOST;
+                } else if (vcpu->arch.osi_enabled &&
                     (((u32)kvmppc_get_gpr(vcpu, 3)) == OSI_SC_MAGIC_R3) &&
                     (((u32)kvmppc_get_gpr(vcpu, 4)) == OSI_SC_MAGIC_R4)) {
                         /* MOL hypercalls */
@@ -770,6 +797,9 @@ int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
                 }
         }
 
+        if (sregs->u.s.flags & KVM_SREGS_S_HIOR)
+                sregs->u.s.hior = to_book3s(vcpu)->hior;
+
         return 0;
 }
 
@@ -806,6 +836,11 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
         /* Flush the MMU after messing with the segments */
         kvmppc_mmu_pte_flush(vcpu, 0, 0);
 
+        if (sregs->u.s.flags & KVM_SREGS_S_HIOR) {
+                to_book3s(vcpu)->hior_sregs = true;
+                to_book3s(vcpu)->hior = sregs->u.s.hior;
+        }
+
         return 0;
 }
 
@@ -841,8 +876,6 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
         if (!p)
                 goto uninit_vcpu;
 
-        vcpu->arch.host_retip = kvm_return_point;
-        vcpu->arch.host_msr = mfmsr();
 #ifdef CONFIG_PPC_BOOK3S_64
         /* default to book3s_64 (970fx) */
         vcpu->arch.pvr = 0x3C0301;
@@ -853,16 +886,6 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
         kvmppc_set_pvr(vcpu, vcpu->arch.pvr);
         vcpu->arch.slb_nr = 64;
 
-        /* remember where some real-mode handlers are */
-        vcpu->arch.trampoline_lowmem = __pa(kvmppc_handler_lowmem_trampoline);
-        vcpu->arch.trampoline_enter = __pa(kvmppc_handler_trampoline_enter);
-        vcpu->arch.highmem_handler = (ulong)kvmppc_handler_highmem;
-#ifdef CONFIG_PPC_BOOK3S_64
-        vcpu->arch.rmcall = *(ulong*)kvmppc_rmcall;
-#else
-        vcpu->arch.rmcall = (ulong)kvmppc_rmcall;
-#endif
-
         vcpu->arch.shadow_msr = MSR_USER64;
 
         err = kvmppc_mmu_init(vcpu);
@@ -908,6 +931,12 @@ int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 #endif
         ulong ext_msr;
 
+        /* Check if we can run the vcpu at all */
+        if (!vcpu->arch.sane) {
+                kvm_run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
+                return -EINVAL;
+        }
+
         /* No need to go into the guest when all we do is going out */
         if (signal_pending(current)) {
                 kvm_run->exit_reason = KVM_EXIT_INTR;
diff --git a/arch/powerpc/kvm/book3s_pr_papr.c b/arch/powerpc/kvm/book3s_pr_papr.c
new file mode 100644
index 000000000000..b9589324797b
--- /dev/null
+++ b/arch/powerpc/kvm/book3s_pr_papr.c
@@ -0,0 +1,158 @@
+/*
+ * Copyright (C) 2011. Freescale Inc. All rights reserved.
+ *
+ * Authors:
+ *    Alexander Graf <agraf@suse.de>
+ *    Paul Mackerras <paulus@samba.org>
+ *
+ * Description:
+ *
+ * Hypercall handling for running PAPR guests in PR KVM on Book 3S
+ * processors.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ */
+
+#include <asm/uaccess.h>
+#include <asm/kvm_ppc.h>
+#include <asm/kvm_book3s.h>
+
+static unsigned long get_pteg_addr(struct kvm_vcpu *vcpu, long pte_index)
+{
+        struct kvmppc_vcpu_book3s *vcpu_book3s = to_book3s(vcpu);
+        unsigned long pteg_addr;
+
+        pte_index <<= 4;
+        pte_index &= ((1 << ((vcpu_book3s->sdr1 & 0x1f) + 11)) - 1) << 7 | 0x70;
+        pteg_addr = vcpu_book3s->sdr1 & 0xfffffffffffc0000ULL;
+        pteg_addr |= pte_index;
+
+        return pteg_addr;
+}
+
+static int kvmppc_h_pr_enter(struct kvm_vcpu *vcpu)
+{
+        long flags = kvmppc_get_gpr(vcpu, 4);
+        long pte_index = kvmppc_get_gpr(vcpu, 5);
+        unsigned long pteg[2 * 8];
+        unsigned long pteg_addr, i, *hpte;
+
+        pte_index &= ~7UL;
+        pteg_addr = get_pteg_addr(vcpu, pte_index);
+
+        copy_from_user(pteg, (void __user *)pteg_addr, sizeof(pteg));
+        hpte = pteg;
+
+        if (likely((flags & H_EXACT) == 0)) {
+                pte_index &= ~7UL;
+                for (i = 0; ; ++i) {
+                        if (i == 8)
+                                return H_PTEG_FULL;
+                        if ((*hpte & HPTE_V_VALID) == 0)
+                                break;
+                        hpte += 2;
+                }
+        } else {
+                i = kvmppc_get_gpr(vcpu, 5) & 7UL;
+                hpte += i * 2;
+        }
+
+        hpte[0] = kvmppc_get_gpr(vcpu, 6);
+        hpte[1] = kvmppc_get_gpr(vcpu, 7);
+        copy_to_user((void __user *)pteg_addr, pteg, sizeof(pteg));
+        kvmppc_set_gpr(vcpu, 3, H_SUCCESS);
+        kvmppc_set_gpr(vcpu, 4, pte_index | i);
+
+        return EMULATE_DONE;
+}
+
+static int kvmppc_h_pr_remove(struct kvm_vcpu *vcpu)
+{
+        unsigned long flags= kvmppc_get_gpr(vcpu, 4);
+        unsigned long pte_index = kvmppc_get_gpr(vcpu, 5);
+        unsigned long avpn = kvmppc_get_gpr(vcpu, 6);
+        unsigned long v = 0, pteg, rb;
+        unsigned long pte[2];
+
+        pteg = get_pteg_addr(vcpu, pte_index);
+        copy_from_user(pte, (void __user *)pteg, sizeof(pte));
+
+        if ((pte[0] & HPTE_V_VALID) == 0 ||
+            ((flags & H_AVPN) && (pte[0] & ~0x7fUL) != avpn) ||
+            ((flags & H_ANDCOND) && (pte[0] & avpn) != 0)) {
+                kvmppc_set_gpr(vcpu, 3, H_NOT_FOUND);
+                return EMULATE_DONE;
+        }
+
+        copy_to_user((void __user *)pteg, &v, sizeof(v));
+
+        rb = compute_tlbie_rb(pte[0], pte[1], pte_index);
+        vcpu->arch.mmu.tlbie(vcpu, rb, rb & 1 ? true : false);
+
+        kvmppc_set_gpr(vcpu, 3, H_SUCCESS);
+        kvmppc_set_gpr(vcpu, 4, pte[0]);
+        kvmppc_set_gpr(vcpu, 5, pte[1]);
+
+        return EMULATE_DONE;
+}
+
+static int kvmppc_h_pr_protect(struct kvm_vcpu *vcpu)
+{
+        unsigned long flags = kvmppc_get_gpr(vcpu, 4);
+        unsigned long pte_index = kvmppc_get_gpr(vcpu, 5);
+        unsigned long avpn = kvmppc_get_gpr(vcpu, 6);
+        unsigned long rb, pteg, r, v;
+        unsigned long pte[2];
+
+        pteg = get_pteg_addr(vcpu, pte_index);
+        copy_from_user(pte, (void __user *)pteg, sizeof(pte));
+
+        if ((pte[0] & HPTE_V_VALID) == 0 ||
+            ((flags & H_AVPN) && (pte[0] & ~0x7fUL) != avpn)) {
+                kvmppc_set_gpr(vcpu, 3, H_NOT_FOUND);
+                return EMULATE_DONE;
+        }
+
+        v = pte[0];
+        r = pte[1];
+        r &= ~(HPTE_R_PP0 | HPTE_R_PP | HPTE_R_N | HPTE_R_KEY_HI |
+               HPTE_R_KEY_LO);
+        r |= (flags << 55) & HPTE_R_PP0;
+        r |= (flags << 48) & HPTE_R_KEY_HI;
+        r |= flags & (HPTE_R_PP | HPTE_R_N | HPTE_R_KEY_LO);
+
+        pte[1] = r;
+
+        rb = compute_tlbie_rb(v, r, pte_index);
+        vcpu->arch.mmu.tlbie(vcpu, rb, rb & 1 ? true : false);
+        copy_to_user((void __user *)pteg, pte, sizeof(pte));
+
+        kvmppc_set_gpr(vcpu, 3, H_SUCCESS);
+
+        return EMULATE_DONE;
+}
+
+int kvmppc_h_pr(struct kvm_vcpu *vcpu, unsigned long cmd)
+{
+        switch (cmd) {
+        case H_ENTER:
+                return kvmppc_h_pr_enter(vcpu);
+        case H_REMOVE:
+                return kvmppc_h_pr_remove(vcpu);
+        case H_PROTECT:
+                return kvmppc_h_pr_protect(vcpu);
+        case H_BULK_REMOVE:
+                /* We just flush all PTEs, so user space can
+                   handle the HPT modifications */
+                kvmppc_mmu_pte_flush(vcpu, 0, 0);
+                break;
+        case H_CEDE:
+                kvm_vcpu_block(vcpu);
+                vcpu->stat.halt_wakeup++;
+                return EMULATE_DONE;
+        }
+
+        return EMULATE_FAIL;
+}
diff --git a/arch/powerpc/kvm/book3s_rmhandlers.S b/arch/powerpc/kvm/book3s_rmhandlers.S
index c1f877c4a884..34187585c507 100644
--- a/arch/powerpc/kvm/book3s_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_rmhandlers.S
@@ -20,6 +20,7 @@
 #include <asm/ppc_asm.h>
 #include <asm/kvm_asm.h>
 #include <asm/reg.h>
+#include <asm/mmu.h>
 #include <asm/page.h>
 #include <asm/asm-offsets.h>
 
@@ -35,10 +36,10 @@
 
 #if defined(CONFIG_PPC_BOOK3S_64)
 
-#define LOAD_SHADOW_VCPU(reg)   GET_PACA(reg)                                   
-#define MSR_NOIRQ               MSR_KERNEL & ~(MSR_IR | MSR_DR)
 #define FUNC(name)              GLUE(.,name)
+#define MTMSR_EERI(reg)         mtmsrd  (reg),1
 
+        .globl  kvmppc_skip_interrupt
 kvmppc_skip_interrupt:
         /*
          * Here all GPRs are unchanged from when the interrupt happened
@@ -51,6 +52,7 @@ kvmppc_skip_interrupt:
         rfid
         b       .
 
+        .globl  kvmppc_skip_Hinterrupt
 kvmppc_skip_Hinterrupt:
         /*
          * Here all GPRs are unchanged from when the interrupt happened
@@ -65,8 +67,8 @@ kvmppc_skip_Hinterrupt:
 
 #elif defined(CONFIG_PPC_BOOK3S_32)
 
-#define MSR_NOIRQ               MSR_KERNEL
 #define FUNC(name)              name
+#define MTMSR_EERI(reg)         mtmsr   (reg)
 
 .macro INTERRUPT_TRAMPOLINE intno
 
@@ -167,40 +169,24 @@ kvmppc_handler_skip_ins:
 #endif
 
 /*
- * This trampoline brings us back to a real mode handler
- *
- * Input Registers:
- *
- * R5 = SRR0
- * R6 = SRR1
- * LR = real-mode IP
+ * Call kvmppc_handler_trampoline_enter in real mode
  *
+ * On entry, r4 contains the guest shadow MSR
  */
-.global kvmppc_handler_lowmem_trampoline
-kvmppc_handler_lowmem_trampoline:
-
-        mtsrr0  r5
+_GLOBAL(kvmppc_entry_trampoline)
+        mfmsr   r5
+        LOAD_REG_ADDR(r7, kvmppc_handler_trampoline_enter)
+        toreal(r7)
+
+        li      r9, MSR_RI
+        ori     r9, r9, MSR_EE
+        andc    r9, r5, r9      /* Clear EE and RI in MSR value */
+        li      r6, MSR_IR | MSR_DR
+        ori     r6, r6, MSR_EE
+        andc    r6, r5, r6      /* Clear EE, DR and IR in MSR value */
+        MTMSR_EERI(r9)          /* Clear EE and RI in MSR */
+        mtsrr0  r7              /* before we set srr0/1 */
         mtsrr1  r6
-        blr
-kvmppc_handler_lowmem_trampoline_end:
-
-/*
- * Call a function in real mode
- *
- * Input Registers:
- *
- * R3 = function
- * R4 = MSR
- * R5 = scratch register
- *
- */
-_GLOBAL(kvmppc_rmcall)
-        LOAD_REG_IMMEDIATE(r5, MSR_NOIRQ)
-        mtmsr   r5              /* Disable relocation and interrupts, so mtsrr
-                                   doesn't get interrupted */
-        sync
-        mtsrr0  r3
-        mtsrr1  r4
         RFI
 
 #if defined(CONFIG_PPC_BOOK3S_32)
diff --git a/arch/powerpc/kvm/book3s_segment.S b/arch/powerpc/kvm/book3s_segment.S
index aed32e517212..0676ae249b9f 100644
--- a/arch/powerpc/kvm/book3s_segment.S
+++ b/arch/powerpc/kvm/book3s_segment.S
@@ -23,6 +23,7 @@
 
 #define GET_SHADOW_VCPU(reg)    \
         mr      reg, r13
+#define MTMSR_EERI(reg)         mtmsrd  (reg),1
 
 #elif defined(CONFIG_PPC_BOOK3S_32)
 
@@ -30,6 +31,7 @@
         tophys(reg, r2);                        \
         lwz     reg, (THREAD + THREAD_KVM_SVCPU)(reg);  \
         tophys(reg, reg)
+#define MTMSR_EERI(reg)         mtmsr   (reg)
 
 #endif
 
@@ -57,10 +59,12 @@ kvmppc_handler_trampoline_enter:
         /* Required state:
          *
          * MSR = ~IR|DR
-         * R13 = PACA
          * R1 = host R1
          * R2 = host R2
-         * R10 = guest MSR
+         * R4 = guest shadow MSR
+         * R5 = normal host MSR
+         * R6 = current host MSR (EE, IR, DR off)
+         * LR = highmem guest exit code
          * all other volatile GPRS = free
          * SVCPU[CR] = guest CR
          * SVCPU[XER] = guest XER
@@ -71,15 +75,15 @@ kvmppc_handler_trampoline_enter:
         /* r3 = shadow vcpu */
         GET_SHADOW_VCPU(r3)
 
+        /* Save guest exit handler address and MSR */
+        mflr    r0
+        PPC_STL r0, HSTATE_VMHANDLER(r3)
+        PPC_STL r5, HSTATE_HOST_MSR(r3)
+
         /* Save R1/R2 in the PACA (64-bit) or shadow_vcpu (32-bit) */
         PPC_STL r1, HSTATE_HOST_R1(r3)
         PPC_STL r2, HSTATE_HOST_R2(r3)
 
-        /* Move SRR0 and SRR1 into the respective regs */
-        PPC_LL  r9, SVCPU_PC(r3)
-        mtsrr0  r9
-        mtsrr1  r10
-
         /* Activate guest mode, so faults get handled by KVM */
         li      r11, KVM_GUEST_MODE_GUEST
         stb     r11, HSTATE_IN_GUEST(r3)
@@ -87,17 +91,46 @@ kvmppc_handler_trampoline_enter:
         /* Switch to guest segment. This is subarch specific. */
         LOAD_GUEST_SEGMENTS
 
+#ifdef CONFIG_PPC_BOOK3S_64
+        /* Some guests may need to have dcbz set to 32 byte length.
+         *
+         * Usually we ensure that by patching the guest's instructions
+         * to trap on dcbz and emulate it in the hypervisor.
+         *
+         * If we can, we should tell the CPU to use 32 byte dcbz though,
+         * because that's a lot faster.
+         */
+        lbz     r0, HSTATE_RESTORE_HID5(r3)
+        cmpwi   r0, 0
+        beq     no_dcbz32_on
+
+        mfspr   r0,SPRN_HID5
+        ori     r0, r0, 0x80            /* XXX HID5_dcbz32 = 0x80 */
+        mtspr   SPRN_HID5,r0
+no_dcbz32_on:
+
+#endif /* CONFIG_PPC_BOOK3S_64 */
+
         /* Enter guest */
 
-        PPC_LL  r4, SVCPU_CTR(r3)
-        PPC_LL  r5, SVCPU_LR(r3)
-        lwz     r6, SVCPU_CR(r3)
-        lwz     r7, SVCPU_XER(r3)
+        PPC_LL  r8, SVCPU_CTR(r3)
+        PPC_LL  r9, SVCPU_LR(r3)
+        lwz     r10, SVCPU_CR(r3)
+        lwz     r11, SVCPU_XER(r3)
+
+        mtctr   r8
+        mtlr    r9
+        mtcr    r10
+        mtxer   r11
 
-        mtctr   r4
-        mtlr    r5
-        mtcr    r6
-        mtxer   r7
+        /* Move SRR0 and SRR1 into the respective regs */
+        PPC_LL  r9, SVCPU_PC(r3)
+        /* First clear RI in our current MSR value */
+        li      r0, MSR_RI
+        andc    r6, r6, r0
+        MTMSR_EERI(r6)
+        mtsrr0  r9
+        mtsrr1  r4
 
         PPC_LL  r0, SVCPU_R0(r3)
         PPC_LL  r1, SVCPU_R1(r3)
@@ -213,11 +246,16 @@ END_FTR_SECTION_IFSET(CPU_FTR_HVMODE)
         beq     ld_last_inst
         cmpwi   r12, BOOK3S_INTERRUPT_PROGRAM
         beq     ld_last_inst
+        cmpwi   r12, BOOK3S_INTERRUPT_SYSCALL
+        beq     ld_last_prev_inst
         cmpwi   r12, BOOK3S_INTERRUPT_ALIGNMENT
         beq-    ld_last_inst
 
         b       no_ld_last_inst
 
+ld_last_prev_inst:
+        addi    r3, r3, -4
+
 ld_last_inst:
         /* Save off the guest instruction we're at */
 
@@ -254,6 +292,43 @@ no_ld_last_inst:
         /* Switch back to host MMU */
         LOAD_HOST_SEGMENTS
 
+#ifdef CONFIG_PPC_BOOK3S_64
+
+        lbz     r5, HSTATE_RESTORE_HID5(r13)
+        cmpwi   r5, 0
+        beq     no_dcbz32_off
+
+        li      r4, 0
+        mfspr   r5,SPRN_HID5
+        rldimi  r5,r4,6,56
+        mtspr   SPRN_HID5,r5
+
+no_dcbz32_off:
+
+#endif /* CONFIG_PPC_BOOK3S_64 */
+
+        /*
+         * For some interrupts, we need to call the real Linux
+         * handler, so it can do work for us. This has to happen
+         * as if the interrupt arrived from the kernel though,
+         * so let's fake it here where most state is restored.
+         *
+         * Having set up SRR0/1 with the address where we want
+         * to continue with relocation on (potentially in module
+         * space), we either just go straight there with rfi[d],
+         * or we jump to an interrupt handler with bctr if there
+         * is an interrupt to be handled first.  In the latter
+         * case, the rfi[d] at the end of the interrupt handler
+         * will get us back to where we want to continue.
+         */
+
+        cmpwi   r12, BOOK3S_INTERRUPT_EXTERNAL
+        beq     1f
+        cmpwi   r12, BOOK3S_INTERRUPT_DECREMENTER
+        beq     1f
+        cmpwi   r12, BOOK3S_INTERRUPT_PERFMON
+1:      mtctr   r12
+
         /* Register usage at this point:
          *
          * R1       = host R1
@@ -264,13 +339,15 @@ no_ld_last_inst:
          *
          */
 
-        /* RFI into the highmem handler */
-        mfmsr   r7
-        ori     r7, r7, MSR_IR|MSR_DR|MSR_RI|MSR_ME     /* Enable paging */
-        mtsrr1  r7
-        /* Load highmem handler address */
+        PPC_LL  r6, HSTATE_HOST_MSR(r13)
         PPC_LL  r8, HSTATE_VMHANDLER(r13)
+
+        /* Restore host msr -> SRR1 */
+        mtsrr1  r6
+        /* Load highmem handler address */
         mtsrr0  r8
 
+        /* RFI into the highmem handler, or jump to interrupt handler */
+        beqctr
         RFI
 kvmppc_handler_trampoline_exit_end:
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index ee45fa01220e..bb6c988f010a 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -316,6 +316,11 @@ int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 {
         int ret;
 
+        if (!vcpu->arch.sane) {
+                kvm_run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
+                return -EINVAL;
+        }
+
         local_irq_disable();
         kvm_guest_enter();
         ret = __kvmppc_vcpu_run(kvm_run, vcpu);
@@ -618,6 +623,7 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 {
         int i;
+        int r;
 
         vcpu->arch.pc = 0;
         vcpu->arch.shared->msr = 0;
@@ -634,7 +640,9 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 
         kvmppc_init_timing_stats(vcpu);
 
-        return kvmppc_core_vcpu_setup(vcpu);
+        r = kvmppc_core_vcpu_setup(vcpu);
+        kvmppc_sanity_check(vcpu);
+        return r;
 }
 
 int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
diff --git a/arch/powerpc/kvm/e500.c b/arch/powerpc/kvm/e500.c
index 797a7447c268..26d20903f2bc 100644
--- a/arch/powerpc/kvm/e500.c
+++ b/arch/powerpc/kvm/e500.c
@@ -73,6 +73,8 @@ int kvmppc_core_vcpu_setup(struct kvm_vcpu *vcpu)
         /* Since booke kvm only support one core, update all vcpus' PIR to 0 */
         vcpu->vcpu_id = 0;
 
+        vcpu->arch.cpu_type = KVM_CPU_E500V2;
+
         return 0;
 }
 
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index a107c9be0fb1..efbf9ad87203 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -21,7 +21,6 @@
 #include <linux/errno.h>
 #include <linux/err.h>
 #include <linux/kvm_host.h>
-#include <linux/module.h>
 #include <linux/vmalloc.h>
 #include <linux/hrtimer.h>
 #include <linux/fs.h>
@@ -39,12 +38,8 @@
 
 int kvm_arch_vcpu_runnable(struct kvm_vcpu *v)
 {
-#ifndef CONFIG_KVM_BOOK3S_64_HV
         return !(v->arch.shared->msr & MSR_WE) ||
                !!(v->arch.pending_exceptions);
-#else
-        return !(v->arch.ceded) || !!(v->arch.pending_exceptions);
-#endif
 }
 
 int kvmppc_kvm_pv(struct kvm_vcpu *vcpu)
@@ -95,6 +90,31 @@ int kvmppc_kvm_pv(struct kvm_vcpu *vcpu)
         return r;
 }
 
+int kvmppc_sanity_check(struct kvm_vcpu *vcpu)
+{
+        int r = false;
+
+        /* We have to know what CPU to virtualize */
+        if (!vcpu->arch.pvr)
+                goto out;
+
+        /* PAPR only works with book3s_64 */
+        if ((vcpu->arch.cpu_type != KVM_CPU_3S_64) && vcpu->arch.papr_enabled)
+                goto out;
+
+#ifdef CONFIG_KVM_BOOK3S_64_HV
+        /* HV KVM can only do PAPR mode for now */
+        if (!vcpu->arch.papr_enabled)
+                goto out;
+#endif
+
+        r = true;
+
+out:
+        vcpu->arch.sane = r;
+        return r ? 0 : -EINVAL;
+}
+
 int kvmppc_emulate_mmio(struct kvm_run *run, struct kvm_vcpu *vcpu)
 {
         enum emulation_result er;
@@ -188,6 +208,8 @@ int kvm_dev_ioctl_check_extension(long ext)
         case KVM_CAP_PPC_BOOKE_SREGS:
 #else
         case KVM_CAP_PPC_SEGSTATE:
+        case KVM_CAP_PPC_HIOR:
+        case KVM_CAP_PPC_PAPR:
 #endif
         case KVM_CAP_PPC_UNSET_IRQ:
         case KVM_CAP_PPC_IRQ_LEVEL:
@@ -258,6 +280,7 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id)
 {
         struct kvm_vcpu *vcpu;
         vcpu = kvmppc_core_vcpu_create(kvm, id);
+        vcpu->arch.wqp = &vcpu->wq;
         if (!IS_ERR(vcpu))
                 kvmppc_create_vcpu_debugfs(vcpu, id);
         return vcpu;
@@ -289,8 +312,8 @@ static void kvmppc_decrementer_func(unsigned long data)
 
         kvmppc_core_queue_dec(vcpu);
 
-        if (waitqueue_active(&vcpu->wq)) {
-                wake_up_interruptible(&vcpu->wq);
+        if (waitqueue_active(vcpu->arch.wqp)) {
+                wake_up_interruptible(vcpu->arch.wqp);
                 vcpu->stat.halt_wakeup++;
         }
 }
@@ -543,13 +566,15 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 
 int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu, struct kvm_interrupt *irq)
 {
-        if (irq->irq == KVM_INTERRUPT_UNSET)
+        if (irq->irq == KVM_INTERRUPT_UNSET) {
                 kvmppc_core_dequeue_external(vcpu, irq);
-        else
-                kvmppc_core_queue_external(vcpu, irq);
+                return 0;
+        }
+
+        kvmppc_core_queue_external(vcpu, irq);
 
-        if (waitqueue_active(&vcpu->wq)) {
-                wake_up_interruptible(&vcpu->wq);
+        if (waitqueue_active(vcpu->arch.wqp)) {
+                wake_up_interruptible(vcpu->arch.wqp);
                 vcpu->stat.halt_wakeup++;
         } else if (vcpu->cpu != -1) {
                 smp_send_reschedule(vcpu->cpu);
@@ -571,11 +596,18 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
                 r = 0;
                 vcpu->arch.osi_enabled = true;
                 break;
+        case KVM_CAP_PPC_PAPR:
+                r = 0;
+                vcpu->arch.papr_enabled = true;
+                break;
         default:
                 r = -EINVAL;
                 break;
         }
 
+        if (!r)
+                r = kvmppc_sanity_check(vcpu);
+
         return r;
 }
 
diff --git a/arch/powerpc/lib/checksum_wrappers_64.c b/arch/powerpc/lib/checksum_wrappers_64.c
index 769b817fbb32..08e3a3356c40 100644
--- a/arch/powerpc/lib/checksum_wrappers_64.c
+++ b/arch/powerpc/lib/checksum_wrappers_64.c
@@ -17,7 +17,7 @@
  *
  * Author: Anton Blanchard <anton@au.ibm.com>
  */
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/compiler.h>
 #include <linux/types.h>
 #include <asm/checksum.h>
diff --git a/arch/powerpc/lib/devres.c b/arch/powerpc/lib/devres.c
index e91615abae66..8df55fc3aad6 100644
--- a/arch/powerpc/lib/devres.c
+++ b/arch/powerpc/lib/devres.c
@@ -10,7 +10,7 @@
 #include <linux/device.h>       /* devres_*(), devm_ioremap_release() */
 #include <linux/gfp.h>
 #include <linux/io.h>           /* ioremap_prot() */
-#include <linux/module.h>       /* EXPORT_SYMBOL() */
+#include <linux/export.h>       /* EXPORT_SYMBOL() */
 
 /**
  * devm_ioremap_prot - Managed ioremap_prot()
diff --git a/arch/powerpc/lib/locks.c b/arch/powerpc/lib/locks.c
index 9b8182e82166..a6ebba56fdd4 100644
--- a/arch/powerpc/lib/locks.c
+++ b/arch/powerpc/lib/locks.c
@@ -14,7 +14,7 @@
 
 #include <linux/kernel.h>
 #include <linux/spinlock.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/stringify.h>
 #include <linux/smp.h>
 
diff --git a/arch/powerpc/lib/rheap.c b/arch/powerpc/lib/rheap.c
index 45907c1dae66..a1060a868e69 100644
--- a/arch/powerpc/lib/rheap.c
+++ b/arch/powerpc/lib/rheap.c
@@ -15,7 +15,7 @@
 #include <linux/types.h>
 #include <linux/errno.h>
 #include <linux/kernel.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/mm.h>
 #include <linux/err.h>
 #include <linux/slab.h>
diff --git a/arch/powerpc/math-emu/math_efp.c b/arch/powerpc/math-emu/math_efp.c
index 62279200d965..a73f0884d358 100644
--- a/arch/powerpc/math-emu/math_efp.c
+++ b/arch/powerpc/math-emu/math_efp.c
@@ -171,10 +171,6 @@ static unsigned long insn_type(unsigned long speinsn)
         case EFDNABS:   ret = XA;       break;
         case EFDNEG:    ret = XA;       break;
         case EFDSUB:    ret = AB;       break;
-
-        default:
-                printk(KERN_ERR "\nOoops! SPE instruction no type found.");
-                printk(KERN_ERR "\ninst code: %08lx\n", speinsn);
         }
 
         return ret;
@@ -195,7 +191,7 @@ int do_spe_mathemu(struct pt_regs *regs)
 
         type = insn_type(speinsn);
         if (type == NOTYPE)
-                return -ENOSYS;
+                goto illegal;
 
         func = speinsn & 0x7ff;
         fc = (speinsn >> 21) & 0x1f;
@@ -212,12 +208,10 @@ int do_spe_mathemu(struct pt_regs *regs)
 
         __FPU_FPSCR = mfspr(SPRN_SPEFSCR);
 
-#ifdef DEBUG
-        printk("speinsn:%08lx spefscr:%08lx\n", speinsn, __FPU_FPSCR);
-        printk("vc: %08x  %08x\n", vc.wp[0], vc.wp[1]);
-        printk("va: %08x  %08x\n", va.wp[0], va.wp[1]);
-        printk("vb: %08x  %08x\n", vb.wp[0], vb.wp[1]);
-#endif
+        pr_debug("speinsn:%08lx spefscr:%08lx\n", speinsn, __FPU_FPSCR);
+        pr_debug("vc: %08x  %08x\n", vc.wp[0], vc.wp[1]);
+        pr_debug("va: %08x  %08x\n", va.wp[0], va.wp[1]);
+        pr_debug("vb: %08x  %08x\n", vb.wp[0], vb.wp[1]);
 
         switch (src) {
         case SPFP: {
@@ -235,10 +229,8 @@ int do_spe_mathemu(struct pt_regs *regs)
                         break;
                 }
 
-#ifdef DEBUG
-                printk("SA: %ld %08lx %ld (%ld)\n", SA_s, SA_f, SA_e, SA_c);
-                printk("SB: %ld %08lx %ld (%ld)\n", SB_s, SB_f, SB_e, SB_c);
-#endif
+                pr_debug("SA: %ld %08lx %ld (%ld)\n", SA_s, SA_f, SA_e, SA_c);
+                pr_debug("SB: %ld %08lx %ld (%ld)\n", SB_s, SB_f, SB_e, SB_c);
 
                 switch (func) {
                 case EFSABS:
@@ -305,10 +297,10 @@ int do_spe_mathemu(struct pt_regs *regs)
                         FP_DECL_D(DB);
                         FP_CLEAR_EXCEPTIONS;
                         FP_UNPACK_DP(DB, vb.dp);
-#ifdef DEBUG
-                        printk("DB: %ld %08lx %08lx %ld (%ld)\n",
+
+                        pr_debug("DB: %ld %08lx %08lx %ld (%ld)\n",
                                         DB_s, DB_f1, DB_f0, DB_e, DB_c);
-#endif
+
                         FP_CONV(S, D, 1, 2, SR, DB);
                         goto pack_s;
                 }
@@ -332,9 +324,8 @@ int do_spe_mathemu(struct pt_regs *regs)
                 break;
 
 pack_s:
-#ifdef DEBUG
-                printk("SR: %ld %08lx %ld (%ld)\n", SR_s, SR_f, SR_e, SR_c);
-#endif
+                pr_debug("SR: %ld %08lx %ld (%ld)\n", SR_s, SR_f, SR_e, SR_c);
+
                 FP_PACK_SP(vc.wp + 1, SR);
                 goto update_regs;
 
@@ -365,12 +356,10 @@ cmp_s:
                         break;
                 }
 
-#ifdef DEBUG
-                printk("DA: %ld %08lx %08lx %ld (%ld)\n",
+                pr_debug("DA: %ld %08lx %08lx %ld (%ld)\n",
                                 DA_s, DA_f1, DA_f0, DA_e, DA_c);
-                printk("DB: %ld %08lx %08lx %ld (%ld)\n",
+                pr_debug("DB: %ld %08lx %08lx %ld (%ld)\n",
                                 DB_s, DB_f1, DB_f0, DB_e, DB_c);
-#endif
 
                 switch (func) {
                 case EFDABS:
@@ -438,10 +427,10 @@ cmp_s:
                         FP_DECL_S(SB);
                         FP_CLEAR_EXCEPTIONS;
                         FP_UNPACK_SP(SB, vb.wp + 1);
-#ifdef DEBUG
-                        printk("SB: %ld %08lx %ld (%ld)\n",
+
+                        pr_debug("SB: %ld %08lx %ld (%ld)\n",
                                         SB_s, SB_f, SB_e, SB_c);
-#endif
+
                         FP_CONV(D, S, 2, 1, DR, SB);
                         goto pack_d;
                 }
@@ -471,10 +460,9 @@ cmp_s:
                 break;
 
 pack_d:
-#ifdef DEBUG
-                printk("DR: %ld %08lx %08lx %ld (%ld)\n",
+                pr_debug("DR: %ld %08lx %08lx %ld (%ld)\n",
                                 DR_s, DR_f1, DR_f0, DR_e, DR_c);
-#endif
+
                 FP_PACK_DP(vc.dp, DR);
                 goto update_regs;
 
@@ -511,12 +499,14 @@ cmp_d:
                         break;
                 }
 
-#ifdef DEBUG
-                printk("SA0: %ld %08lx %ld (%ld)\n", SA0_s, SA0_f, SA0_e, SA0_c);
-                printk("SA1: %ld %08lx %ld (%ld)\n", SA1_s, SA1_f, SA1_e, SA1_c);
-                printk("SB0: %ld %08lx %ld (%ld)\n", SB0_s, SB0_f, SB0_e, SB0_c);
-                printk("SB1: %ld %08lx %ld (%ld)\n", SB1_s, SB1_f, SB1_e, SB1_c);
-#endif
+                pr_debug("SA0: %ld %08lx %ld (%ld)\n",
+                                SA0_s, SA0_f, SA0_e, SA0_c);
+                pr_debug("SA1: %ld %08lx %ld (%ld)\n",
+                                SA1_s, SA1_f, SA1_e, SA1_c);
+                pr_debug("SB0: %ld %08lx %ld (%ld)\n",
+                                SB0_s, SB0_f, SB0_e, SB0_c);
+                pr_debug("SB1: %ld %08lx %ld (%ld)\n",
+                                SB1_s, SB1_f, SB1_e, SB1_c);
 
                 switch (func) {
                 case EVFSABS:
@@ -605,10 +595,11 @@ cmp_d:
                 break;
 
 pack_vs:
-#ifdef DEBUG
-                printk("SR0: %ld %08lx %ld (%ld)\n", SR0_s, SR0_f, SR0_e, SR0_c);
-                printk("SR1: %ld %08lx %ld (%ld)\n", SR1_s, SR1_f, SR1_e, SR1_c);
-#endif
+                pr_debug("SR0: %ld %08lx %ld (%ld)\n",
+                                SR0_s, SR0_f, SR0_e, SR0_c);
+                pr_debug("SR1: %ld %08lx %ld (%ld)\n",
+                                SR1_s, SR1_f, SR1_e, SR1_c);
+
                 FP_PACK_SP(vc.wp, SR0);
                 FP_PACK_SP(vc.wp + 1, SR1);
                 goto update_regs;
@@ -646,14 +637,12 @@ update_regs:
         current->thread.evr[fc] = vc.wp[0];
         regs->gpr[fc] = vc.wp[1];
 
-#ifdef DEBUG
-        printk("ccr = %08lx\n", regs->ccr);
-        printk("cur exceptions = %08x spefscr = %08lx\n",
+        pr_debug("ccr = %08lx\n", regs->ccr);
+        pr_debug("cur exceptions = %08x spefscr = %08lx\n",
                         FP_CUR_EXCEPTIONS, __FPU_FPSCR);
-        printk("vc: %08x  %08x\n", vc.wp[0], vc.wp[1]);
-        printk("va: %08x  %08x\n", va.wp[0], va.wp[1]);
-        printk("vb: %08x  %08x\n", vb.wp[0], vb.wp[1]);
-#endif
+        pr_debug("vc: %08x  %08x\n", vc.wp[0], vc.wp[1]);
+        pr_debug("va: %08x  %08x\n", va.wp[0], va.wp[1]);
+        pr_debug("vb: %08x  %08x\n", vb.wp[0], vb.wp[1]);
 
         return 0;
 
@@ -661,9 +650,7 @@ illegal:
         if (have_e500_cpu_a005_erratum) {
                 /* according to e500 cpu a005 erratum, reissue efp inst */
                 regs->nip -= 4;
-#ifdef DEBUG
-                printk(KERN_DEBUG "re-issue efp inst: %08lx\n", speinsn);
-#endif
+                pr_debug("re-issue efp inst: %08lx\n", speinsn);
                 return 0;
         }
 
@@ -685,13 +672,20 @@ int speround_handler(struct pt_regs *regs)
         type = insn_type(speinsn & 0x7ff);
         if (type == XCR) return -ENOSYS;
 
+        __FPU_FPSCR = mfspr(SPRN_SPEFSCR);
+        pr_debug("speinsn:%08lx spefscr:%08lx\n", speinsn, __FPU_FPSCR);
+
+        /* No need to round if the result is exact */
+        if (!(__FPU_FPSCR & FP_EX_INEXACT))
+                return 0;
+
         fc = (speinsn >> 21) & 0x1f;
         s_lo = regs->gpr[fc] & SIGN_BIT_S;
         s_hi = current->thread.evr[fc] & SIGN_BIT_S;
         fgpr.wp[0] = current->thread.evr[fc];
         fgpr.wp[1] = regs->gpr[fc];
 
-        __FPU_FPSCR = mfspr(SPRN_SPEFSCR);
+        pr_debug("round fgpr: %08x  %08x\n", fgpr.wp[0], fgpr.wp[1]);
 
         switch ((speinsn >> 5) & 0x7) {
         /* Since SPE instructions on E500 core can handle round to nearest
@@ -731,6 +725,8 @@ int speround_handler(struct pt_regs *regs)
         current->thread.evr[fc] = fgpr.wp[0];
         regs->gpr[fc] = fgpr.wp[1];
 
+        pr_debug("  to fgpr: %08x  %08x\n", fgpr.wp[0], fgpr.wp[1]);
+
         return 0;
 }
 
diff --git a/arch/powerpc/mm/Makefile b/arch/powerpc/mm/Makefile
index bdca46e08382..991ee813d2a8 100644
--- a/arch/powerpc/mm/Makefile
+++ b/arch/powerpc/mm/Makefile
@@ -29,6 +29,7 @@ obj-$(CONFIG_PPC_MM_SLICES)	+= slice.o
 ifeq ($(CONFIG_HUGETLB_PAGE),y)
 obj-y                           += hugetlbpage.o
 obj-$(CONFIG_PPC_STD_MMU_64)    += hugetlbpage-hash64.o
+obj-$(CONFIG_PPC_BOOK3E_MMU)    += hugetlbpage-book3e.o
 endif
 obj-$(CONFIG_PPC_SUBPAGE_PROT)  += subpage-prot.o
 obj-$(CONFIG_NOT_COHERENT_CACHE) += dma-noncoherent.o
diff --git a/arch/powerpc/mm/dma-noncoherent.c b/arch/powerpc/mm/dma-noncoherent.c
index b42f76c4948d..329be36c0a8d 100644
--- a/arch/powerpc/mm/dma-noncoherent.c
+++ b/arch/powerpc/mm/dma-noncoherent.c
@@ -30,6 +30,7 @@
 #include <linux/types.h>
 #include <linux/highmem.h>
 #include <linux/dma-mapping.h>
+#include <linux/export.h>
 
 #include <asm/tlbflush.h>
 
diff --git a/arch/powerpc/mm/fsl_booke_mmu.c b/arch/powerpc/mm/fsl_booke_mmu.c
index f7802c8bba0a..66a6fd38e9cd 100644
--- a/arch/powerpc/mm/fsl_booke_mmu.c
+++ b/arch/powerpc/mm/fsl_booke_mmu.c
@@ -101,17 +101,17 @@ unsigned long p_mapped_by_tlbcam(phys_addr_t pa)
 
 /*
  * Set up a variable-size TLB entry (tlbcam). The parameters are not checked;
- * in particular size must be a power of 4 between 4k and 256M (or 1G, for cpus
- * that support extended page sizes).  Note that while some cpus support a
- * page size of 4G, we don't allow its use here.
+ * in particular size must be a power of 4 between 4k and the max supported by
+ * an implementation; max may further be limited by what can be represented in
+ * an unsigned long (for example, 32-bit implementations cannot support a 4GB
+ * size).
  */
 static void settlbcam(int index, unsigned long virt, phys_addr_t phys,
                 unsigned long size, unsigned long flags, unsigned int pid)
 {
-        unsigned int tsize, lz;
+        unsigned int tsize;
 
-        asm (PPC_CNTLZL "%0,%1" : "=r" (lz) : "r" (size));
-        tsize = 21 - lz;
+        tsize = __ilog2(size) - 10;
 
 #ifdef CONFIG_SMP
         if ((flags & _PAGE_NO_CACHE) == 0)
@@ -146,29 +146,36 @@ static void settlbcam(int index, unsigned long virt, phys_addr_t phys,
         loadcam_entry(index);
 }
 
+unsigned long calc_cam_sz(unsigned long ram, unsigned long virt,
+                          phys_addr_t phys)
+{
+        unsigned int camsize = __ilog2(ram) & ~1U;
+        unsigned int align = __ffs(virt | phys) & ~1U;
+        unsigned long max_cam = (mfspr(SPRN_TLB1CFG) >> 16) & 0xf;
+
+        /* Convert (4^max) kB to (2^max) bytes */
+        max_cam = max_cam * 2 + 10;
+
+        if (camsize > align)
+                camsize = align;
+        if (camsize > max_cam)
+                camsize = max_cam;
+
+        return 1UL << camsize;
+}
+
 unsigned long map_mem_in_cams(unsigned long ram, int max_cam_idx)
 {
         int i;
         unsigned long virt = PAGE_OFFSET;
         phys_addr_t phys = memstart_addr;
         unsigned long amount_mapped = 0;
-        unsigned long max_cam = (mfspr(SPRN_TLB1CFG) >> 16) & 0xf;
-
-        /* Convert (4^max) kB to (2^max) bytes */
-        max_cam = max_cam * 2 + 10;
 
         /* Calculate CAM values */
         for (i = 0; ram && i < max_cam_idx; i++) {
-                unsigned int camsize = __ilog2(ram) & ~1U;
-                unsigned int align = __ffs(virt | phys) & ~1U;
                 unsigned long cam_sz;
 
-                if (camsize > align)
-                        camsize = align;
-                if (camsize > max_cam)
-                        camsize = max_cam;
-
-                cam_sz = 1UL << camsize;
+                cam_sz = calc_cam_sz(ram, virt, phys);
                 settlbcam(i, virt, phys, cam_sz, PAGE_KERNEL_X, 0);
 
                 ram -= cam_sz;
diff --git a/arch/powerpc/mm/gup.c b/arch/powerpc/mm/gup.c
index fec13200868f..d7efdbf640c7 100644
--- a/arch/powerpc/mm/gup.c
+++ b/arch/powerpc/mm/gup.c
@@ -16,16 +16,6 @@
 
 #ifdef __HAVE_ARCH_PTE_SPECIAL
 
-static inline void get_huge_page_tail(struct page *page)
-{
-        /*
-         * __split_huge_page_refcount() cannot run
-         * from under us.
-         */
-        VM_BUG_ON(atomic_read(&page->_count) < 0);
-        atomic_inc(&page->_count);
-}
-
 /*
  * The performance critical leaf functions are made noinline otherwise gcc
  * inlines everything into a single function which results in too much
@@ -57,8 +47,6 @@ static noinline int gup_pte_range(pmd_t pmd, unsigned long addr,
                         put_page(page);
                         return 0;
                 }
-                if (PageTail(page))
-                        get_huge_page_tail(page);
                 pages[*nr] = page;
                 (*nr)++;
 
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index 26b2872b3d00..2d282186cb45 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -27,6 +27,7 @@
 #include <linux/proc_fs.h>
 #include <linux/stat.h>
 #include <linux/sysctl.h>
+#include <linux/export.h>
 #include <linux/ctype.h>
 #include <linux/cache.h>
 #include <linux/init.h>
@@ -105,9 +106,6 @@ int mmu_kernel_ssize = MMU_SEGSIZE_256M;
 int mmu_highuser_ssize = MMU_SEGSIZE_256M;
 u16 mmu_slb_size = 64;
 EXPORT_SYMBOL_GPL(mmu_slb_size);
-#ifdef CONFIG_HUGETLB_PAGE
-unsigned int HPAGE_SHIFT;
-#endif
 #ifdef CONFIG_PPC_64K_PAGES
 int mmu_ci_restrictions;
 #endif
@@ -534,11 +532,11 @@ static unsigned long __init htab_get_table_size(void)
 }
 
 #ifdef CONFIG_MEMORY_HOTPLUG
-void create_section_mapping(unsigned long start, unsigned long end)
+int create_section_mapping(unsigned long start, unsigned long end)
 {
-        BUG_ON(htab_bolt_mapping(start, end, __pa(start),
+        return htab_bolt_mapping(start, end, __pa(start),
                                  pgprot_val(PAGE_KERNEL), mmu_linear_psize,
-                                 mmu_kernel_ssize));
+                                 mmu_kernel_ssize);
 }
 
 int remove_section_mapping(unsigned long start, unsigned long end)
diff --git a/arch/powerpc/mm/hugetlbpage-book3e.c b/arch/powerpc/mm/hugetlbpage-book3e.c
new file mode 100644
index 000000000000..343ad0b87261
--- /dev/null
+++ b/arch/powerpc/mm/hugetlbpage-book3e.c
@@ -0,0 +1,121 @@
+/*
+ * PPC Huge TLB Page Support for Book3E MMU
+ *
+ * Copyright (C) 2009 David Gibson, IBM Corporation.
+ * Copyright (C) 2011 Becky Bruce, Freescale Semiconductor
+ *
+ */
+#include <linux/mm.h>
+#include <linux/hugetlb.h>
+
+static inline int mmu_get_tsize(int psize)
+{
+        return mmu_psize_defs[psize].enc;
+}
+
+static inline int book3e_tlb_exists(unsigned long ea, unsigned long pid)
+{
+        int found = 0;
+
+        mtspr(SPRN_MAS6, pid << 16);
+        if (mmu_has_feature(MMU_FTR_USE_TLBRSRV)) {
+                asm volatile(
+                        "li     %0,0\n"
+                        "tlbsx. 0,%1\n"
+                        "bne    1f\n"
+                        "li     %0,1\n"
+                        "1:\n"
+                        : "=&r"(found) : "r"(ea));
+        } else {
+                asm volatile(
+                        "tlbsx  0,%1\n"
+                        "mfspr  %0,0x271\n"
+                        "srwi   %0,%0,31\n"
+                        : "=&r"(found) : "r"(ea));
+        }
+
+        return found;
+}
+
+void book3e_hugetlb_preload(struct mm_struct *mm, unsigned long ea, pte_t pte)
+{
+        unsigned long mas1, mas2;
+        u64 mas7_3;
+        unsigned long psize, tsize, shift;
+        unsigned long flags;
+
+#ifdef CONFIG_PPC_FSL_BOOK3E
+        int index, lz, ncams;
+        struct vm_area_struct *vma;
+#endif
+
+        if (unlikely(is_kernel_addr(ea)))
+                return;
+
+#ifdef CONFIG_PPC_MM_SLICES
+        psize = mmu_get_tsize(get_slice_psize(mm, ea));
+        tsize = mmu_get_psize(psize);
+        shift = mmu_psize_defs[psize].shift;
+#else
+        vma = find_vma(mm, ea);
+        psize = vma_mmu_pagesize(vma);  /* returns actual size in bytes */
+        asm (PPC_CNTLZL "%0,%1" : "=r" (lz) : "r" (psize));
+        shift = 31 - lz;
+        tsize = 21 - lz;
+#endif
+
+        /*
+         * We can't be interrupted while we're setting up the MAS
+         * regusters or after we've confirmed that no tlb exists.
+         */
+        local_irq_save(flags);
+
+        if (unlikely(book3e_tlb_exists(ea, mm->context.id))) {
+                local_irq_restore(flags);
+                return;
+        }
+
+#ifdef CONFIG_PPC_FSL_BOOK3E
+        ncams = mfspr(SPRN_TLB1CFG) & TLBnCFG_N_ENTRY;
+
+        /* We have to use the CAM(TLB1) on FSL parts for hugepages */
+        index = __get_cpu_var(next_tlbcam_idx);
+        mtspr(SPRN_MAS0, MAS0_ESEL(index) | MAS0_TLBSEL(1));
+
+        /* Just round-robin the entries and wrap when we hit the end */
+        if (unlikely(index == ncams - 1))
+                __get_cpu_var(next_tlbcam_idx) = tlbcam_index;
+        else
+                __get_cpu_var(next_tlbcam_idx)++;
+#endif
+        mas1 = MAS1_VALID | MAS1_TID(mm->context.id) | MAS1_TSIZE(tsize);
+        mas2 = ea & ~((1UL << shift) - 1);
+        mas2 |= (pte_val(pte) >> PTE_WIMGE_SHIFT) & MAS2_WIMGE_MASK;
+        mas7_3 = (u64)pte_pfn(pte) << PAGE_SHIFT;
+        mas7_3 |= (pte_val(pte) >> PTE_BAP_SHIFT) & MAS3_BAP_MASK;
+        if (!pte_dirty(pte))
+                mas7_3 &= ~(MAS3_SW|MAS3_UW);
+
+        mtspr(SPRN_MAS1, mas1);
+        mtspr(SPRN_MAS2, mas2);
+
+        if (mmu_has_feature(MMU_FTR_USE_PAIRED_MAS)) {
+                mtspr(SPRN_MAS7_MAS3, mas7_3);
+        } else {
+                mtspr(SPRN_MAS7, upper_32_bits(mas7_3));
+                mtspr(SPRN_MAS3, lower_32_bits(mas7_3));
+        }
+
+        asm volatile ("tlbwe");
+
+        local_irq_restore(flags);
+}
+
+void flush_hugetlb_page(struct vm_area_struct *vma, unsigned long vmaddr)
+{
+        struct hstate *hstate = hstate_file(vma->vm_file);
+        unsigned long tsize = huge_page_shift(hstate) - 10;
+
+        __flush_tlb_page(vma ? vma->vm_mm : NULL, vmaddr, tsize, 0);
+
+}
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index 0b9a5c1901b9..5964371303ac 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -1,7 +1,8 @@
 /*
- * PPC64 (POWER4) Huge TLB Page Support for Kernel.
+ * PPC Huge TLB Page Support for Kernel.
  *
  * Copyright (C) 2003 David Gibson, IBM Corporation.
+ * Copyright (C) 2011 Becky Bruce, Freescale Semiconductor
  *
  * Based on the IA-32 version:
  * Copyright (C) 2002, Rohit Seth <rohit.seth@intel.com>
@@ -11,24 +12,39 @@
 #include <linux/io.h>
 #include <linux/slab.h>
 #include <linux/hugetlb.h>
+#include <linux/of_fdt.h>
+#include <linux/memblock.h>
+#include <linux/bootmem.h>
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
 #include <asm/tlb.h>
+#include <asm/setup.h>
 
 #define PAGE_SHIFT_64K  16
 #define PAGE_SHIFT_16M  24
 #define PAGE_SHIFT_16G  34
 
-#define MAX_NUMBER_GPAGES       1024
+unsigned int HPAGE_SHIFT;
 
-/* Tracks the 16G pages after the device tree is scanned and before the
- * huge_boot_pages list is ready.  */
-static unsigned long gpage_freearray[MAX_NUMBER_GPAGES];
+/*
+ * Tracks gpages after the device tree is scanned and before the
+ * huge_boot_pages list is ready.  On 64-bit implementations, this is
+ * just used to track 16G pages and so is a single array.  32-bit
+ * implementations may have more than one gpage size due to limitations
+ * of the memory allocators, so we need multiple arrays
+ */
+#ifdef CONFIG_PPC64
+#define MAX_NUMBER_GPAGES       1024
+static u64 gpage_freearray[MAX_NUMBER_GPAGES];
 static unsigned nr_gpages;
-
-/* Flag to mark huge PD pointers.  This means pmd_bad() and pud_bad()
- * will choke on pointers to hugepte tables, which is handy for
- * catching screwups early. */
+#else
+#define MAX_NUMBER_GPAGES       128
+struct psize_gpages {
+        u64 gpage_list[MAX_NUMBER_GPAGES];
+        unsigned int nr_gpages;
+};
+static struct psize_gpages gpage_freearray[MMU_PAGE_COUNT];
+#endif
 
 static inline int shift_to_mmu_psize(unsigned int shift)
 {
@@ -49,25 +65,6 @@ static inline unsigned int mmu_psize_to_shift(unsigned int mmu_psize)
 
 #define hugepd_none(hpd)        ((hpd).pd == 0)
 
-static inline pte_t *hugepd_page(hugepd_t hpd)
-{
-        BUG_ON(!hugepd_ok(hpd));
-        return (pte_t *)((hpd.pd & ~HUGEPD_SHIFT_MASK) | 0xc000000000000000);
-}
-
-static inline unsigned int hugepd_shift(hugepd_t hpd)
-{
-        return hpd.pd & HUGEPD_SHIFT_MASK;
-}
-
-static inline pte_t *hugepte_offset(hugepd_t *hpdp, unsigned long addr, unsigned pdshift)
-{
-        unsigned long idx = (addr & ((1UL << pdshift) - 1)) >> hugepd_shift(*hpdp);
-        pte_t *dir = hugepd_page(*hpdp);
-
-        return dir + idx;
-}
-
 pte_t *find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea, unsigned *shift)
 {
         pgd_t *pg;
@@ -93,7 +90,7 @@ pte_t *find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea, unsigned *shift
                         if (is_hugepd(pm))
                                 hpdp = (hugepd_t *)pm;
                         else if (!pmd_none(*pm)) {
-                                return pte_offset_map(pm, ea);
+                                return pte_offset_kernel(pm, ea);
                         }
                 }
         }
@@ -114,8 +111,18 @@ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
 static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp,
                            unsigned long address, unsigned pdshift, unsigned pshift)
 {
-        pte_t *new = kmem_cache_zalloc(PGT_CACHE(pdshift - pshift),
-                                       GFP_KERNEL|__GFP_REPEAT);
+        struct kmem_cache *cachep;
+        pte_t *new;
+
+#ifdef CONFIG_PPC64
+        cachep = PGT_CACHE(pdshift - pshift);
+#else
+        int i;
+        int num_hugepd = 1 << (pshift - pdshift);
+        cachep = hugepte_cache;
+#endif
+
+        new = kmem_cache_zalloc(cachep, GFP_KERNEL|__GFP_REPEAT);
 
         BUG_ON(pshift > HUGEPD_SHIFT_MASK);
         BUG_ON((unsigned long)new & HUGEPD_SHIFT_MASK);
@@ -124,10 +131,31 @@ static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp,
                 return -ENOMEM;
 
         spin_lock(&mm->page_table_lock);
+#ifdef CONFIG_PPC64
         if (!hugepd_none(*hpdp))
-                kmem_cache_free(PGT_CACHE(pdshift - pshift), new);
+                kmem_cache_free(cachep, new);
         else
-                hpdp->pd = ((unsigned long)new & ~0x8000000000000000) | pshift;
+                hpdp->pd = ((unsigned long)new & ~PD_HUGE) | pshift;
+#else
+        /*
+         * We have multiple higher-level entries that point to the same
+         * actual pte location.  Fill in each as we go and backtrack on error.
+         * We need all of these so the DTLB pgtable walk code can find the
+         * right higher-level entry without knowing if it's a hugepage or not.
+         */
+        for (i = 0; i < num_hugepd; i++, hpdp++) {
+                if (unlikely(!hugepd_none(*hpdp)))
+                        break;
+                else
+                        hpdp->pd = ((unsigned long)new & ~PD_HUGE) | pshift;
+        }
+        /* If we bailed from the for loop early, an error occurred, clean up */
+        if (i < num_hugepd) {
+                for (i = i - 1 ; i >= 0; i--, hpdp--)
+                        hpdp->pd = 0;
+                kmem_cache_free(cachep, new);
+        }
+#endif
         spin_unlock(&mm->page_table_lock);
         return 0;
 }
@@ -169,11 +197,132 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr, unsigned long sz
         return hugepte_offset(hpdp, addr, pdshift);
 }
 
+#ifdef CONFIG_PPC32
+/* Build list of addresses of gigantic pages.  This function is used in early
+ * boot before the buddy or bootmem allocator is setup.
+ */
+void add_gpage(u64 addr, u64 page_size, unsigned long number_of_pages)
+{
+        unsigned int idx = shift_to_mmu_psize(__ffs(page_size));
+        int i;
+
+        if (addr == 0)
+                return;
+
+        gpage_freearray[idx].nr_gpages = number_of_pages;
+
+        for (i = 0; i < number_of_pages; i++) {
+                gpage_freearray[idx].gpage_list[i] = addr;
+                addr += page_size;
+        }
+}
+
+/*
+ * Moves the gigantic page addresses from the temporary list to the
+ * huge_boot_pages list.
+ */
+int alloc_bootmem_huge_page(struct hstate *hstate)
+{
+        struct huge_bootmem_page *m;
+        int idx = shift_to_mmu_psize(hstate->order + PAGE_SHIFT);
+        int nr_gpages = gpage_freearray[idx].nr_gpages;
+
+        if (nr_gpages == 0)
+                return 0;
+
+#ifdef CONFIG_HIGHMEM
+        /*
+         * If gpages can be in highmem we can't use the trick of storing the
+         * data structure in the page; allocate space for this
+         */
+        m = alloc_bootmem(sizeof(struct huge_bootmem_page));
+        m->phys = gpage_freearray[idx].gpage_list[--nr_gpages];
+#else
+        m = phys_to_virt(gpage_freearray[idx].gpage_list[--nr_gpages]);
+#endif
+
+        list_add(&m->list, &huge_boot_pages);
+        gpage_freearray[idx].nr_gpages = nr_gpages;
+        gpage_freearray[idx].gpage_list[nr_gpages] = 0;
+        m->hstate = hstate;
+
+        return 1;
+}
+/*
+ * Scan the command line hugepagesz= options for gigantic pages; store those in
+ * a list that we use to allocate the memory once all options are parsed.
+ */
+
+unsigned long gpage_npages[MMU_PAGE_COUNT];
+
+static int __init do_gpage_early_setup(char *param, char *val)
+{
+        static phys_addr_t size;
+        unsigned long npages;
+
+        /*
+         * The hugepagesz and hugepages cmdline options are interleaved.  We
+         * use the size variable to keep track of whether or not this was done
+         * properly and skip over instances where it is incorrect.  Other
+         * command-line parsing code will issue warnings, so we don't need to.
+         *
+         */
+        if ((strcmp(param, "default_hugepagesz") == 0) ||
+            (strcmp(param, "hugepagesz") == 0)) {
+                size = memparse(val, NULL);
+        } else if (strcmp(param, "hugepages") == 0) {
+                if (size != 0) {
+                        if (sscanf(val, "%lu", &npages) <= 0)
+                                npages = 0;
+                        gpage_npages[shift_to_mmu_psize(__ffs(size))] = npages;
+                        size = 0;
+                }
+        }
+        return 0;
+}
+
+
+/*
+ * This function allocates physical space for pages that are larger than the
+ * buddy allocator can handle.  We want to allocate these in highmem because
+ * the amount of lowmem is limited.  This means that this function MUST be
+ * called before lowmem_end_addr is set up in MMU_init() in order for the lmb
+ * allocate to grab highmem.
+ */
+void __init reserve_hugetlb_gpages(void)
+{
+        static __initdata char cmdline[COMMAND_LINE_SIZE];
+        phys_addr_t size, base;
+        int i;
+
+        strlcpy(cmdline, boot_command_line, COMMAND_LINE_SIZE);
+        parse_args("hugetlb gpages", cmdline, NULL, 0, &do_gpage_early_setup);
+
+        /*
+         * Walk gpage list in reverse, allocating larger page sizes first.
+         * Skip over unsupported sizes, or sizes that have 0 gpages allocated.
+         * When we reach the point in the list where pages are no longer
+         * considered gpages, we're done.
+         */
+        for (i = MMU_PAGE_COUNT-1; i >= 0; i--) {
+                if (mmu_psize_defs[i].shift == 0 || gpage_npages[i] == 0)
+                        continue;
+                else if (mmu_psize_to_shift(i) < (MAX_ORDER + PAGE_SHIFT))
+                        break;
+
+                size = (phys_addr_t)(1ULL << mmu_psize_to_shift(i));
+                base = memblock_alloc_base(size * gpage_npages[i], size,
+                                           MEMBLOCK_ALLOC_ANYWHERE);
+                add_gpage(base, size, gpage_npages[i]);
+        }
+}
+
+#else /* PPC64 */
+
 /* Build list of addresses of gigantic pages.  This function is used in early
  * boot before the buddy or bootmem allocator is setup.
  */
-void add_gpage(unsigned long addr, unsigned long page_size,
-        unsigned long number_of_pages)
+void add_gpage(u64 addr, u64 page_size, unsigned long number_of_pages)
 {
         if (!addr)
                 return;
@@ -199,19 +348,79 @@ int alloc_bootmem_huge_page(struct hstate *hstate)
         m->hstate = hstate;
         return 1;
 }
+#endif
 
 int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep)
 {
         return 0;
 }
 
+#ifdef CONFIG_PPC32
+#define HUGEPD_FREELIST_SIZE \
+        ((PAGE_SIZE - sizeof(struct hugepd_freelist)) / sizeof(pte_t))
+
+struct hugepd_freelist {
+        struct rcu_head rcu;
+        unsigned int index;
+        void *ptes[0];
+};
+
+static DEFINE_PER_CPU(struct hugepd_freelist *, hugepd_freelist_cur);
+
+static void hugepd_free_rcu_callback(struct rcu_head *head)
+{
+        struct hugepd_freelist *batch =
+                container_of(head, struct hugepd_freelist, rcu);
+        unsigned int i;
+
+        for (i = 0; i < batch->index; i++)
+                kmem_cache_free(hugepte_cache, batch->ptes[i]);
+
+        free_page((unsigned long)batch);
+}
+
+static void hugepd_free(struct mmu_gather *tlb, void *hugepte)
+{
+        struct hugepd_freelist **batchp;
+
+        batchp = &__get_cpu_var(hugepd_freelist_cur);
+
+        if (atomic_read(&tlb->mm->mm_users) < 2 ||
+            cpumask_equal(mm_cpumask(tlb->mm),
+                          cpumask_of(smp_processor_id()))) {
+                kmem_cache_free(hugepte_cache, hugepte);
+                return;
+        }
+
+        if (*batchp == NULL) {
+                *batchp = (struct hugepd_freelist *)__get_free_page(GFP_ATOMIC);
+                (*batchp)->index = 0;
+        }
+
+        (*batchp)->ptes[(*batchp)->index++] = hugepte;
+        if ((*batchp)->index == HUGEPD_FREELIST_SIZE) {
+                call_rcu_sched(&(*batchp)->rcu, hugepd_free_rcu_callback);
+                *batchp = NULL;
+        }
+}
+#endif
+
 static void free_hugepd_range(struct mmu_gather *tlb, hugepd_t *hpdp, int pdshift,
                               unsigned long start, unsigned long end,
                               unsigned long floor, unsigned long ceiling)
 {
         pte_t *hugepte = hugepd_page(*hpdp);
-        unsigned shift = hugepd_shift(*hpdp);
+        int i;
+
         unsigned long pdmask = ~((1UL << pdshift) - 1);
+        unsigned int num_hugepd = 1;
+
+#ifdef CONFIG_PPC64
+        unsigned int shift = hugepd_shift(*hpdp);
+#else
+        /* Note: On 32-bit the hpdp may be the first of several */
+        num_hugepd = (1 << (hugepd_shift(*hpdp) - pdshift));
+#endif
 
         start &= pdmask;
         if (start < floor)
@@ -224,9 +433,15 @@ static void free_hugepd_range(struct mmu_gather *tlb, hugepd_t *hpdp, int pdshif
         if (end - 1 > ceiling - 1)
                 return;
 
-        hpdp->pd = 0;
+        for (i = 0; i < num_hugepd; i++, hpdp++)
+                hpdp->pd = 0;
+
         tlb->need_flush = 1;
+#ifdef CONFIG_PPC64
         pgtable_free_tlb(tlb, hugepte, pdshift - shift);
+#else
+        hugepd_free(tlb, hugepte);
+#endif
 }
 
 static void hugetlb_free_pmd_range(struct mmu_gather *tlb, pud_t *pud,
@@ -331,18 +546,27 @@ void hugetlb_free_pgd_range(struct mmu_gather *tlb,
          * too.
          */
 
-        pgd = pgd_offset(tlb->mm, addr);
         do {
                 next = pgd_addr_end(addr, end);
+                pgd = pgd_offset(tlb->mm, addr);
                 if (!is_hugepd(pgd)) {
                         if (pgd_none_or_clear_bad(pgd))
                                 continue;
                         hugetlb_free_pud_range(tlb, pgd, addr, next, floor, ceiling);
                 } else {
+#ifdef CONFIG_PPC32
+                        /*
+                         * Increment next by the size of the huge mapping since
+                         * on 32-bit there may be more than one entry at the pgd
+                         * level for a single hugepage, but all of them point to
+                         * the same kmem cache that holds the hugepte.
+                         */
+                        next = addr + (1 << hugepd_shift(*(hugepd_t *)pgd));
+#endif
                         free_hugepd_range(tlb, (hugepd_t *)pgd, PGDIR_SHIFT,
                                           addr, next, floor, ceiling);
                 }
-        } while (pgd++, addr = next, addr != end);
+        } while (addr = next, addr != end);
 }
 
 struct page *
@@ -390,7 +614,7 @@ static noinline int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long add
 {
         unsigned long mask;
         unsigned long pte_end;
-        struct page *head, *page;
+        struct page *head, *page, *tail;
         pte_t pte;
         int refs;
 
@@ -413,6 +637,7 @@ static noinline int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long add
         head = pte_page(pte);
 
         page = head + ((addr & (sz-1)) >> PAGE_SHIFT);
+        tail = page;
         do {
                 VM_BUG_ON(compound_head(page) != head);
                 pages[*nr] = page;
@@ -428,10 +653,20 @@ static noinline int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long add
 
         if (unlikely(pte_val(pte) != pte_val(*ptep))) {
                 /* Could be optimized better */
-                while (*nr) {
-                        put_page(page);
-                        (*nr)--;
-                }
+                *nr -= refs;
+                while (refs--)
+                        put_page(head);
+                return 0;
+        }
+
+        /*
+         * Any tail page need their mapcount reference taken before we
+         * return.
+         */
+        while (refs--) {
+                if (PageTail(tail))
+                        get_huge_page_tail(tail);
+                tail++;
         }
 
         return 1;
@@ -466,17 +701,35 @@ unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
                                         unsigned long len, unsigned long pgoff,
                                         unsigned long flags)
 {
+#ifdef CONFIG_PPC_MM_SLICES
         struct hstate *hstate = hstate_file(file);
         int mmu_psize = shift_to_mmu_psize(huge_page_shift(hstate));
 
         return slice_get_unmapped_area(addr, len, flags, mmu_psize, 1, 0);
+#else
+        return get_unmapped_area(file, addr, len, pgoff, flags);
+#endif
 }
 
 unsigned long vma_mmu_pagesize(struct vm_area_struct *vma)
 {
+#ifdef CONFIG_PPC_MM_SLICES
         unsigned int psize = get_slice_psize(vma->vm_mm, vma->vm_start);
 
         return 1UL << mmu_psize_to_shift(psize);
+#else
+        if (!is_vm_hugetlb_page(vma))
+                return PAGE_SIZE;
+
+        return huge_page_size(hstate_vma(vma));
+#endif
+}
+
+static inline bool is_power_of_4(unsigned long x)
+{
+        if (is_power_of_2(x))
+                return (__ilog2(x) % 2) ? false : true;
+        return false;
 }
 
 static int __init add_huge_page_size(unsigned long long size)
@@ -486,9 +739,14 @@ static int __init add_huge_page_size(unsigned long long size)
 
         /* Check that it is a page size supported by the hardware and
          * that it fits within pagetable and slice limits. */
+#ifdef CONFIG_PPC_FSL_BOOK3E
+        if ((size < PAGE_SIZE) || !is_power_of_4(size))
+                return -EINVAL;
+#else
         if (!is_power_of_2(size)
             || (shift > SLICE_HIGH_SHIFT) || (shift <= PAGE_SHIFT))
                 return -EINVAL;
+#endif
 
         if ((mmu_psize = shift_to_mmu_psize(shift)) < 0)
                 return -EINVAL;
@@ -525,6 +783,46 @@ static int __init hugepage_setup_sz(char *str)
 }
 __setup("hugepagesz=", hugepage_setup_sz);
 
+#ifdef CONFIG_FSL_BOOKE
+struct kmem_cache *hugepte_cache;
+static int __init hugetlbpage_init(void)
+{
+        int psize;
+
+        for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) {
+                unsigned shift;
+
+                if (!mmu_psize_defs[psize].shift)
+                        continue;
+
+                shift = mmu_psize_to_shift(psize);
+
+                /* Don't treat normal page sizes as huge... */
+                if (shift != PAGE_SHIFT)
+                        if (add_huge_page_size(1ULL << shift) < 0)
+                                continue;
+        }
+
+        /*
+         * Create a kmem cache for hugeptes.  The bottom bits in the pte have
+         * size information encoded in them, so align them to allow this
+         */
+        hugepte_cache =  kmem_cache_create("hugepte-cache", sizeof(pte_t),
+                                           HUGEPD_SHIFT_MASK + 1, 0, NULL);
+        if (hugepte_cache == NULL)
+                panic("%s: Unable to create kmem cache for hugeptes\n",
+                      __func__);
+
+        /* Default hpage size = 4M */
+        if (mmu_psize_defs[MMU_PAGE_4M].shift)
+                HPAGE_SHIFT = mmu_psize_defs[MMU_PAGE_4M].shift;
+        else
+                panic("%s: Unable to set default huge page size\n", __func__);
+
+
+        return 0;
+}
+#else
 static int __init hugetlbpage_init(void)
 {
         int psize;
@@ -567,15 +865,23 @@ static int __init hugetlbpage_init(void)
 
         return 0;
 }
-
+#endif
 module_init(hugetlbpage_init);
 
 void flush_dcache_icache_hugepage(struct page *page)
 {
         int i;
+        void *start;
 
         BUG_ON(!PageCompound(page));
 
-        for (i = 0; i < (1UL << compound_order(page)); i++)
-                __flush_dcache_icache(page_address(page+i));
+        for (i = 0; i < (1UL << compound_order(page)); i++) {
+                if (!PageHighMem(page)) {
+                        __flush_dcache_icache(page_address(page+i));
+                } else {
+                        start = kmap_atomic(page+i, KM_PPC_SYNC_ICACHE);
+                        __flush_dcache_icache(start);
+                        kunmap_atomic(start, KM_PPC_SYNC_ICACHE);
+                }
+        }
 }
diff --git a/arch/powerpc/mm/init_32.c b/arch/powerpc/mm/init_32.c
index c77fef56dad6..161cefde5c15 100644
--- a/arch/powerpc/mm/init_32.c
+++ b/arch/powerpc/mm/init_32.c
@@ -32,6 +32,8 @@
 #include <linux/pagemap.h>
 #include <linux/memblock.h>
 #include <linux/gfp.h>
+#include <linux/slab.h>
+#include <linux/hugetlb.h>
 
 #include <asm/pgalloc.h>
 #include <asm/prom.h>
@@ -44,6 +46,7 @@
 #include <asm/tlb.h>
 #include <asm/sections.h>
 #include <asm/system.h>
+#include <asm/hugetlb.h>
 
 #include "mmu_decl.h"
 
@@ -123,6 +126,12 @@ void __init MMU_init(void)
         /* parse args from command line */
         MMU_setup();
 
+        /*
+         * Reserve gigantic pages for hugetlb.  This MUST occur before
+         * lowmem_end_addr is initialized below.
+         */
+        reserve_hugetlb_gpages();
+
         if (memblock.memory.cnt > 1) {
 #ifndef CONFIG_WII
                 memblock.memory.cnt = 1;
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index c781bbcf7338..2dd6bdd31fe1 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -17,7 +17,7 @@
  *
  */
 
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/sched.h>
 #include <linux/kernel.h>
 #include <linux/errno.h>
@@ -34,6 +34,7 @@
 #include <linux/suspend.h>
 #include <linux/memblock.h>
 #include <linux/hugetlb.h>
+#include <linux/slab.h>
 
 #include <asm/pgalloc.h>
 #include <asm/prom.h>
@@ -123,7 +124,8 @@ int arch_add_memory(int nid, u64 start, u64 size)
         pgdata = NODE_DATA(nid);
 
         start = (unsigned long)__va(start);
-        create_section_mapping(start, start + size);
+        if (create_section_mapping(start, start + size))
+                return -EINVAL;
 
         /* this should work for most non-highmem platforms */
         zone = pgdata->node_zones;
@@ -548,4 +550,38 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long address,
                 return;
         hash_preload(vma->vm_mm, address, access, trap);
 #endif /* CONFIG_PPC_STD_MMU */
+#if (defined(CONFIG_PPC_BOOK3E_64) || defined(CONFIG_PPC_FSL_BOOK3E)) \
+        && defined(CONFIG_HUGETLB_PAGE)
+        if (is_vm_hugetlb_page(vma))
+                book3e_hugetlb_preload(vma->vm_mm, address, *ptep);
+#endif
+}
+
+/*
+ * System memory should not be in /proc/iomem but various tools expect it
+ * (eg kdump).
+ */
+static int add_system_ram_resources(void)
+{
+        struct memblock_region *reg;
+
+        for_each_memblock(memory, reg) {
+                struct resource *res;
+                unsigned long base = reg->base;
+                unsigned long size = reg->size;
+
+                res = kzalloc(sizeof(struct resource), GFP_KERNEL);
+                WARN_ON(!res);
+
+                if (res) {
+                        res->name = "System RAM";
+                        res->start = base;
+                        res->end = base + size - 1;
+                        res->flags = IORESOURCE_MEM;
+                        WARN_ON(request_resource(&iomem_resource, res) < 0);
+                }
+        }
+
+        return 0;
 }
+subsys_initcall(add_system_ram_resources);
diff --git a/arch/powerpc/mm/mmu_context_hash32.c b/arch/powerpc/mm/mmu_context_hash32.c
index d0ee554e86e4..78fef6726e10 100644
--- a/arch/powerpc/mm/mmu_context_hash32.c
+++ b/arch/powerpc/mm/mmu_context_hash32.c
@@ -24,6 +24,7 @@
 
 #include <linux/mm.h>
 #include <linux/init.h>
+#include <linux/export.h>
 
 #include <asm/mmu_context.h>
 #include <asm/tlbflush.h>
diff --git a/arch/powerpc/mm/mmu_context_hash64.c b/arch/powerpc/mm/mmu_context_hash64.c
index 3bafc3deca6d..ca988a3d5fb2 100644
--- a/arch/powerpc/mm/mmu_context_hash64.c
+++ b/arch/powerpc/mm/mmu_context_hash64.c
@@ -18,7 +18,7 @@
 #include <linux/mm.h>
 #include <linux/spinlock.h>
 #include <linux/idr.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/gfp.h>
 #include <linux/slab.h>
 
@@ -136,8 +136,8 @@ int use_cop(unsigned long acop, struct mm_struct *mm)
         if (!mm || !acop)
                 return -EINVAL;
 
-        /* We need to make sure mm_users doesn't change */
-        down_read(&mm->mmap_sem);
+        /* The page_table_lock ensures mm_users won't change under us */
+        spin_lock(&mm->page_table_lock);
         spin_lock(mm->context.cop_lockp);
 
         if (mm->context.cop_pid == COP_PID_NONE) {
@@ -164,7 +164,7 @@ int use_cop(unsigned long acop, struct mm_struct *mm)
 
 out:
         spin_unlock(mm->context.cop_lockp);
-        up_read(&mm->mmap_sem);
+        spin_unlock(&mm->page_table_lock);
 
         return ret;
 }
@@ -185,8 +185,8 @@ void drop_cop(unsigned long acop, struct mm_struct *mm)
         if (WARN_ON_ONCE(!mm))
                 return;
 
-        /* We need to make sure mm_users doesn't change */
-        down_read(&mm->mmap_sem);
+        /* The page_table_lock ensures mm_users won't change under us */
+        spin_lock(&mm->page_table_lock);
         spin_lock(mm->context.cop_lockp);
 
         mm->context.acop &= ~acop;
@@ -213,7 +213,7 @@ void drop_cop(unsigned long acop, struct mm_struct *mm)
         }
 
         spin_unlock(mm->context.cop_lockp);
-        up_read(&mm->mmap_sem);
+        spin_unlock(&mm->page_table_lock);
 }
 EXPORT_SYMBOL_GPL(drop_cop);
 
diff --git a/arch/powerpc/mm/mmu_context_nohash.c b/arch/powerpc/mm/mmu_context_nohash.c
index 336807de550e..5b63bd3da4a9 100644
--- a/arch/powerpc/mm/mmu_context_nohash.c
+++ b/arch/powerpc/mm/mmu_context_nohash.c
@@ -292,6 +292,11 @@ int init_new_context(struct task_struct *t, struct mm_struct *mm)
         mm->context.id = MMU_NO_CONTEXT;
         mm->context.active = 0;
 
+#ifdef CONFIG_PPC_MM_SLICES
+        if (slice_mm_new_context(mm))
+                slice_set_user_psize(mm, mmu_virtual_psize);
+#endif
+
         return 0;
 }
 
diff --git a/arch/powerpc/mm/mmu_decl.h b/arch/powerpc/mm/mmu_decl.h
index dd0a2589591d..83eb5d5f53d5 100644
--- a/arch/powerpc/mm/mmu_decl.h
+++ b/arch/powerpc/mm/mmu_decl.h
@@ -142,6 +142,8 @@ extern unsigned long mmu_mapin_ram(unsigned long top);
 
 #elif defined(CONFIG_PPC_FSL_BOOK3E)
 extern unsigned long map_mem_in_cams(unsigned long ram, int max_cam_idx);
+extern unsigned long calc_cam_sz(unsigned long ram, unsigned long virt,
+                                 phys_addr_t phys);
 #ifdef CONFIG_PPC32
 extern void MMU_init_hw(void);
 extern unsigned long mmu_mapin_ram(unsigned long top);
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 2164006fe170..b22a83a91cb8 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -13,7 +13,7 @@
 #include <linux/init.h>
 #include <linux/mm.h>
 #include <linux/mmzone.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/nodemask.h>
 #include <linux/cpu.h>
 #include <linux/notifier.h>
@@ -315,7 +315,10 @@ static int __init find_min_common_depth(void)
         struct device_node *root;
         const char *vec5;
 
-        root = of_find_node_by_path("/rtas");
+        if (firmware_has_feature(FW_FEATURE_OPAL))
+                root = of_find_node_by_path("/ibm,opal");
+        else
+                root = of_find_node_by_path("/rtas");
         if (!root)
                 root = of_find_node_by_path("/");
 
@@ -344,12 +347,19 @@ static int __init find_min_common_depth(void)
 
 #define VEC5_AFFINITY_BYTE      5
 #define VEC5_AFFINITY           0x80
-        chosen = of_find_node_by_path("/chosen");
-        if (chosen) {
-                vec5 = of_get_property(chosen, "ibm,architecture-vec-5", NULL);
-                if (vec5 && (vec5[VEC5_AFFINITY_BYTE] & VEC5_AFFINITY)) {
-                        dbg("Using form 1 affinity\n");
-                        form1_affinity = 1;
+
+        if (firmware_has_feature(FW_FEATURE_OPAL))
+                form1_affinity = 1;
+        else {
+                chosen = of_find_node_by_path("/chosen");
+                if (chosen) {
+                        vec5 = of_get_property(chosen,
+                                               "ibm,architecture-vec-5", NULL);
+                        if (vec5 && (vec5[VEC5_AFFINITY_BYTE] &
+                                                        VEC5_AFFINITY)) {
+                                dbg("Using form 1 affinity\n");
+                                form1_affinity = 1;
+                        }
                 }
         }
 
@@ -709,8 +719,7 @@ static void __init parse_drconf_memory(struct device_node *memory)
 
 static int __init parse_numa_properties(void)
 {
-        struct device_node *cpu = NULL;
-        struct device_node *memory = NULL;
+        struct device_node *memory;
         int default_nid = 0;
         unsigned long i;
 
@@ -732,6 +741,7 @@ static int __init parse_numa_properties(void)
          * each node to be onlined must have NODE_DATA etc backing it.
          */
         for_each_present_cpu(i) {
+                struct device_node *cpu;
                 int nid;
 
                 cpu = of_get_cpu_node(i, NULL);
@@ -750,8 +760,8 @@ static int __init parse_numa_properties(void)
         }
 
         get_n_mem_cells(&n_mem_addr_cells, &n_mem_size_cells);
-        memory = NULL;
-        while ((memory = of_find_node_by_type(memory, "memory")) != NULL) {
+
+        for_each_node_by_type(memory, "memory") {
                 unsigned long start;
                 unsigned long size;
                 int nid;
@@ -800,8 +810,9 @@ new_range:
         }
 
         /*
-         * Now do the same thing for each MEMBLOCK listed in the ibm,dynamic-memory
-         * property in the ibm,dynamic-reconfiguration-memory node.
+         * Now do the same thing for each MEMBLOCK listed in the
+         * ibm,dynamic-memory property in the
+         * ibm,dynamic-reconfiguration-memory node.
          */
         memory = of_find_node_by_path("/ibm,dynamic-reconfiguration-memory");
         if (memory)
@@ -1187,10 +1198,10 @@ static int hot_add_drconf_scn_to_nid(struct device_node *memory,
  */
 int hot_add_node_scn_to_nid(unsigned long scn_addr)
 {
-        struct device_node *memory = NULL;
+        struct device_node *memory;
         int nid = -1;
 
-        while ((memory = of_find_node_by_type(memory, "memory")) != NULL) {
+        for_each_node_by_type(memory, "memory") {
                 unsigned long start, size;
                 int ranges;
                 const unsigned int *memcell_buf;
@@ -1214,11 +1225,12 @@ int hot_add_node_scn_to_nid(unsigned long scn_addr)
                         break;
                 }
 
-                of_node_put(memory);
                 if (nid >= 0)
                         break;
         }
 
+        of_node_put(memory);
+
         return nid;
 }
 
diff --git a/arch/powerpc/mm/pgtable.c b/arch/powerpc/mm/pgtable.c
index af40c8768a78..214130a4edc6 100644
--- a/arch/powerpc/mm/pgtable.c
+++ b/arch/powerpc/mm/pgtable.c
@@ -27,6 +27,7 @@
 #include <linux/init.h>
 #include <linux/percpu.h>
 #include <linux/hardirq.h>
+#include <linux/hugetlb.h>
 #include <asm/pgalloc.h>
 #include <asm/tlbflush.h>
 #include <asm/tlb.h>
@@ -212,7 +213,7 @@ int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address,
         entry = set_access_flags_filter(entry, vma, dirty);
         changed = !pte_same(*(ptep), entry);
         if (changed) {
-                if (!(vma->vm_flags & VM_HUGETLB))
+                if (!is_vm_hugetlb_page(vma))
                         assert_pte_locked(vma->vm_mm, address);
                 __ptep_set_access_flags(ptep, entry);
                 flush_tlb_page_nohash(vma, address);
diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c
index 6e595f6496d4..ad36ede469cc 100644
--- a/arch/powerpc/mm/pgtable_64.c
+++ b/arch/powerpc/mm/pgtable_64.c
@@ -26,6 +26,7 @@
 #include <linux/kernel.h>
 #include <linux/errno.h>
 #include <linux/string.h>
+#include <linux/export.h>
 #include <linux/types.h>
 #include <linux/mman.h>
 #include <linux/mm.h>
diff --git a/arch/powerpc/mm/slice.c b/arch/powerpc/mm/slice.c
index ba5194817f8a..73709f7ce92c 100644
--- a/arch/powerpc/mm/slice.c
+++ b/arch/powerpc/mm/slice.c
@@ -29,7 +29,7 @@
 #include <linux/pagemap.h>
 #include <linux/err.h>
 #include <linux/spinlock.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <asm/mman.h>
 #include <asm/mmu.h>
 #include <asm/spu.h>
diff --git a/arch/powerpc/mm/tlb_hash32.c b/arch/powerpc/mm/tlb_hash32.c
index 9a445f64accd..558e30cce33e 100644
--- a/arch/powerpc/mm/tlb_hash32.c
+++ b/arch/powerpc/mm/tlb_hash32.c
@@ -27,6 +27,7 @@
 #include <linux/init.h>
 #include <linux/highmem.h>
 #include <linux/pagemap.h>
+#include <linux/export.h>
 
 #include <asm/tlbflush.h>
 #include <asm/tlb.h>
diff --git a/arch/powerpc/mm/tlb_low_64e.S b/arch/powerpc/mm/tlb_low_64e.S
index 4ebb34bc01d6..dc4a5f385e41 100644
--- a/arch/powerpc/mm/tlb_low_64e.S
+++ b/arch/powerpc/mm/tlb_low_64e.S
@@ -553,24 +553,24 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_TLBRSRV)
         rldicl  r11,r16,64-VPTE_PGD_SHIFT,64-PGD_INDEX_SIZE-3
         clrrdi  r10,r11,3
         ldx     r15,r10,r15
-        cmpldi  cr0,r15,0
-        beq     virt_page_table_tlb_miss_fault
+        cmpdi   cr0,r15,0
+        bge     virt_page_table_tlb_miss_fault
 
 #ifndef CONFIG_PPC_64K_PAGES
         /* Get to PUD entry */
         rldicl  r11,r16,64-VPTE_PUD_SHIFT,64-PUD_INDEX_SIZE-3
         clrrdi  r10,r11,3
         ldx     r15,r10,r15
-        cmpldi  cr0,r15,0
-        beq     virt_page_table_tlb_miss_fault
+        cmpdi   cr0,r15,0
+        bge     virt_page_table_tlb_miss_fault
 #endif /* CONFIG_PPC_64K_PAGES */
 
         /* Get to PMD entry */
         rldicl  r11,r16,64-VPTE_PMD_SHIFT,64-PMD_INDEX_SIZE-3
         clrrdi  r10,r11,3
         ldx     r15,r10,r15
-        cmpldi  cr0,r15,0
-        beq     virt_page_table_tlb_miss_fault
+        cmpdi   cr0,r15,0
+        bge     virt_page_table_tlb_miss_fault
 
         /* Ok, we're all right, we can now create a kernel translation for
          * a 4K or 64K page from r16 -> r15.
@@ -802,24 +802,24 @@ htw_tlb_miss:
         rldicl  r11,r16,64-(PGDIR_SHIFT-3),64-PGD_INDEX_SIZE-3
         clrrdi  r10,r11,3
         ldx     r15,r10,r15
-        cmpldi  cr0,r15,0
-        beq     htw_tlb_miss_fault
+        cmpdi   cr0,r15,0
+        bge     htw_tlb_miss_fault
 
 #ifndef CONFIG_PPC_64K_PAGES
         /* Get to PUD entry */
         rldicl  r11,r16,64-(PUD_SHIFT-3),64-PUD_INDEX_SIZE-3
         clrrdi  r10,r11,3
         ldx     r15,r10,r15
-        cmpldi  cr0,r15,0
-        beq     htw_tlb_miss_fault
+        cmpdi   cr0,r15,0
+        bge     htw_tlb_miss_fault
 #endif /* CONFIG_PPC_64K_PAGES */
 
         /* Get to PMD entry */
         rldicl  r11,r16,64-(PMD_SHIFT-3),64-PMD_INDEX_SIZE-3
         clrrdi  r10,r11,3
         ldx     r15,r10,r15
-        cmpldi  cr0,r15,0
-        beq     htw_tlb_miss_fault
+        cmpdi   cr0,r15,0
+        bge     htw_tlb_miss_fault
 
         /* Ok, we're all right, we can now create an indirect entry for
          * a 1M or 256M page.
diff --git a/arch/powerpc/mm/tlb_nohash.c b/arch/powerpc/mm/tlb_nohash.c
index d32ec643c231..4e13d6f9023e 100644
--- a/arch/powerpc/mm/tlb_nohash.c
+++ b/arch/powerpc/mm/tlb_nohash.c
@@ -28,6 +28,7 @@
  */
 
 #include <linux/kernel.h>
+#include <linux/export.h>
 #include <linux/mm.h>
 #include <linux/init.h>
 #include <linux/highmem.h>
@@ -36,14 +37,49 @@
 #include <linux/spinlock.h>
 #include <linux/memblock.h>
 #include <linux/of_fdt.h>
+#include <linux/hugetlb.h>
 
 #include <asm/tlbflush.h>
 #include <asm/tlb.h>
 #include <asm/code-patching.h>
+#include <asm/hugetlb.h>
 
 #include "mmu_decl.h"
 
-#ifdef CONFIG_PPC_BOOK3E
+/*
+ * This struct lists the sw-supported page sizes.  The hardawre MMU may support
+ * other sizes not listed here.   The .ind field is only used on MMUs that have
+ * indirect page table entries.
+ */
+#ifdef CONFIG_PPC_BOOK3E_MMU
+#ifdef CONFIG_FSL_BOOKE
+struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT] = {
+        [MMU_PAGE_4K] = {
+                .shift  = 12,
+                .enc    = BOOK3E_PAGESZ_4K,
+        },
+        [MMU_PAGE_4M] = {
+                .shift  = 22,
+                .enc    = BOOK3E_PAGESZ_4M,
+        },
+        [MMU_PAGE_16M] = {
+                .shift  = 24,
+                .enc    = BOOK3E_PAGESZ_16M,
+        },
+        [MMU_PAGE_64M] = {
+                .shift  = 26,
+                .enc    = BOOK3E_PAGESZ_64M,
+        },
+        [MMU_PAGE_256M] = {
+                .shift  = 28,
+                .enc    = BOOK3E_PAGESZ_256M,
+        },
+        [MMU_PAGE_1G] = {
+                .shift  = 30,
+                .enc    = BOOK3E_PAGESZ_1GB,
+        },
+};
+#else
 struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT] = {
         [MMU_PAGE_4K] = {
                 .shift  = 12,
@@ -77,6 +113,8 @@ struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT] = {
                 .enc    = BOOK3E_PAGESZ_1GB,
         },
 };
+#endif /* CONFIG_FSL_BOOKE */
+
 static inline int mmu_get_tsize(int psize)
 {
         return mmu_psize_defs[psize].enc;
@@ -87,7 +125,7 @@ static inline int mmu_get_tsize(int psize)
         /* This isn't used on !Book3E for now */
         return 0;
 }
-#endif
+#endif /* CONFIG_PPC_BOOK3E_MMU */
 
 /* The variables below are currently only used on 64-bit Book3E
  * though this will probably be made common with other nohash
@@ -266,6 +304,11 @@ void __flush_tlb_page(struct mm_struct *mm, unsigned long vmaddr,
 
 void flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr)
 {
+#ifdef CONFIG_HUGETLB_PAGE
+        if (is_vm_hugetlb_page(vma))
+                flush_hugetlb_page(vma, vmaddr);
+#endif
+
         __flush_tlb_page(vma ? vma->vm_mm : NULL, vmaddr,
                          mmu_get_tsize(mmu_virtual_psize), 0);
 }
@@ -600,13 +643,28 @@ void __cpuinit early_init_mmu_secondary(void)
 void setup_initial_memory_limit(phys_addr_t first_memblock_base,
                                 phys_addr_t first_memblock_size)
 {
-        /* On Embedded 64-bit, we adjust the RMA size to match
+        /* On non-FSL Embedded 64-bit, we adjust the RMA size to match
          * the bolted TLB entry. We know for now that only 1G
          * entries are supported though that may eventually
-         * change. We crop it to the size of the first MEMBLOCK to
+         * change.
+         *
+         * on FSL Embedded 64-bit, we adjust the RMA size to match the
+         * first bolted TLB entry size.  We still limit max to 1G even if
+         * the TLB could cover more.  This is due to what the early init
+         * code is setup to do.
+         *
+         * We crop it to the size of the first MEMBLOCK to
          * avoid going over total available memory just in case...
          */
-        ppc64_rma_size = min_t(u64, first_memblock_size, 0x40000000);
+#ifdef CONFIG_PPC_FSL_BOOK3E
+        if (mmu_has_feature(MMU_FTR_TYPE_FSL_E)) {
+                unsigned long linear_sz;
+                linear_sz = calc_cam_sz(first_memblock_size, PAGE_OFFSET,
+                                        first_memblock_base);
+                ppc64_rma_size = min_t(u64, linear_sz, 0x40000000);
+        } else
+#endif
+                ppc64_rma_size = min_t(u64, first_memblock_size, 0x40000000);
 
         /* Finally limit subsequent allocations */
         memblock_set_current_limit(first_memblock_base + ppc64_rma_size);
diff --git a/arch/powerpc/platforms/40x/Kconfig b/arch/powerpc/platforms/40x/Kconfig
index e568e85813ae..bd69cf8d8222 100644
--- a/arch/powerpc/platforms/40x/Kconfig
+++ b/arch/powerpc/platforms/40x/Kconfig
@@ -16,14 +16,6 @@ config EP405
         help
           This option enables support for the EP405/EP405PC boards.
 
-config HCU4
-        bool "Hcu4"
-        depends on 40x
-        default n
-        select 405GPR
-        help
-          This option enables support for the Nestal Maschinen HCU4 board.
-
 config HOTFOOT
         bool "Hotfoot"
         depends on 40x
@@ -91,11 +83,6 @@ config PPC40x_SIMPLE
         help
           This option enables the simple PowerPC 40x platform support.
 
-# 40x specific CPU modules, selected based on the board above.
-config NP405H
-        bool
-        #depends on ASH
-
 # OAK doesn't exist but wanted to keep this around for any future 403GCX boards
 config 403GCX
         bool
@@ -106,21 +93,21 @@ config 405GP
         bool
         select IBM405_ERR77
         select IBM405_ERR51
-        select IBM_NEW_EMAC_ZMII
+        select IBM_EMAC_ZMII
 
 config 405EP
         bool
 
 config 405EX
         bool
-        select IBM_NEW_EMAC_EMAC4
-        select IBM_NEW_EMAC_RGMII
+        select IBM_EMAC_EMAC4
+        select IBM_EMAC_RGMII
 
 config 405EZ
         bool
-        select IBM_NEW_EMAC_NO_FLOW_CTRL
-        select IBM_NEW_EMAC_MAL_CLR_ICINTSTAT
-        select IBM_NEW_EMAC_MAL_COMMON_ERR
+        select IBM_EMAC_NO_FLOW_CTRL
+        select IBM_EMAC_MAL_CLR_ICINTSTAT
+        select IBM_EMAC_MAL_COMMON_ERR
 
 config 405GPR
         bool
diff --git a/arch/powerpc/platforms/40x/Makefile b/arch/powerpc/platforms/40x/Makefile
index 56e89004c468..88c22de0c850 100644
--- a/arch/powerpc/platforms/40x/Makefile
+++ b/arch/powerpc/platforms/40x/Makefile
@@ -1,4 +1,3 @@
-obj-$(CONFIG_HCU4)                              += hcu4.o
 obj-$(CONFIG_WALNUT)                            += walnut.o
 obj-$(CONFIG_XILINX_VIRTEX_GENERIC_BOARD)       += virtex.o
 obj-$(CONFIG_EP405)                             += ep405.o
diff --git a/arch/powerpc/platforms/40x/hcu4.c b/arch/powerpc/platforms/40x/hcu4.c
deleted file mode 100644
index 60b2afecab75..000000000000
--- a/arch/powerpc/platforms/40x/hcu4.c
+++ /dev/null
@@ -1,61 +0,0 @@
-/*
- * Architecture- / platform-specific boot-time initialization code for
- * IBM PowerPC 4xx based boards. Adapted from original
- * code by Gary Thomas, Cort Dougan <cort@fsmlabs.com>, and Dan Malek
- * <dan@net4x.com>.
- *
- * Copyright(c) 1999-2000 Grant Erickson <grant@lcse.umn.edu>
- *
- * Rewritten and ported to the merged powerpc tree:
- * Copyright 2007 IBM Corporation
- * Josh Boyer <jwboyer@linux.vnet.ibm.com>
- *
- * 2002 (c) MontaVista, Software, Inc.  This file is licensed under
- * the terms of the GNU General Public License version 2.  This program
- * is licensed "as is" without any warranty of any kind, whether express
- * or implied.
- */
-
-#include <linux/init.h>
-#include <linux/of_platform.h>
-
-#include <asm/machdep.h>
-#include <asm/prom.h>
-#include <asm/udbg.h>
-#include <asm/time.h>
-#include <asm/uic.h>
-#include <asm/ppc4xx.h>
-
-static __initdata struct of_device_id hcu4_of_bus[] = {
-        { .compatible = "ibm,plb3", },
-        { .compatible = "ibm,opb", },
-        { .compatible = "ibm,ebc", },
-        {},
-};
-
-static int __init hcu4_device_probe(void)
-{
-        of_platform_bus_probe(NULL, hcu4_of_bus, NULL);
-        return 0;
-}
-machine_device_initcall(hcu4, hcu4_device_probe);
-
-static int __init hcu4_probe(void)
-{
-        unsigned long root = of_get_flat_dt_root();
-
-        if (!of_flat_dt_is_compatible(root, "netstal,hcu4"))
-                return 0;
-
-        return 1;
-}
-
-define_machine(hcu4) {
-        .name                   = "HCU4",
-        .probe                  = hcu4_probe,
-        .progress               = udbg_progress,
-        .init_IRQ               = uic_init_tree,
-        .get_irq                = uic_get_irq,
-        .restart                = ppc4xx_reset_system,
-        .calibrate_decr         = generic_calibrate_decr,
-};
diff --git a/arch/powerpc/platforms/44x/Kconfig b/arch/powerpc/platforms/44x/Kconfig
index 2c1a3e694114..0cb8899a5cc1 100644
--- a/arch/powerpc/platforms/44x/Kconfig
+++ b/arch/powerpc/platforms/44x/Kconfig
@@ -23,7 +23,7 @@ config BLUESTONE
         default n
         select PPC44x_SIMPLE
         select APM821xx
-        select IBM_NEW_EMAC_RGMII
+        select IBM_EMAC_RGMII
         help
           This option enables support for the APM APM821xx Evaluation board.
 
@@ -122,8 +122,8 @@ config CANYONLANDS
         select PPC4xx_PCI_EXPRESS
         select PCI_MSI
         select PPC4xx_MSI
-        select IBM_NEW_EMAC_RGMII
-        select IBM_NEW_EMAC_ZMII
+        select IBM_EMAC_RGMII
+        select IBM_EMAC_ZMII
         help
           This option enables support for the AMCC PPC460EX evaluation board.
 
@@ -135,8 +135,8 @@ config GLACIER
         select 460EX # Odd since it uses 460GT but the effects are the same
         select PCI
         select PPC4xx_PCI_EXPRESS
-        select IBM_NEW_EMAC_RGMII
-        select IBM_NEW_EMAC_ZMII
+        select IBM_EMAC_RGMII
+        select IBM_EMAC_ZMII
         help
           This option enables support for the AMCC PPC460GT evaluation board.
 
@@ -161,7 +161,7 @@ config EIGER
         select 460SX
         select PCI
         select PPC4xx_PCI_EXPRESS
-        select IBM_NEW_EMAC_RGMII
+        select IBM_EMAC_RGMII
         help
           This option enables support for the AMCC PPC460SX evaluation board.
 
@@ -244,59 +244,59 @@ config 440EP
         bool
         select PPC_FPU
         select IBM440EP_ERR42
-        select IBM_NEW_EMAC_ZMII
+        select IBM_EMAC_ZMII
         select USB_ARCH_HAS_OHCI
 
 config 440EPX
         bool
         select PPC_FPU
-        select IBM_NEW_EMAC_EMAC4
-        select IBM_NEW_EMAC_RGMII
-        select IBM_NEW_EMAC_ZMII
+        select IBM_EMAC_EMAC4
+        select IBM_EMAC_RGMII
+        select IBM_EMAC_ZMII
 
 config 440GRX
         bool
-        select IBM_NEW_EMAC_EMAC4
-        select IBM_NEW_EMAC_RGMII
-        select IBM_NEW_EMAC_ZMII
+        select IBM_EMAC_EMAC4
+        select IBM_EMAC_RGMII
+        select IBM_EMAC_ZMII
 
 config 440GP
         bool
-        select IBM_NEW_EMAC_ZMII
+        select IBM_EMAC_ZMII
 
 config 440GX
         bool
-        select IBM_NEW_EMAC_EMAC4
-        select IBM_NEW_EMAC_RGMII
-        select IBM_NEW_EMAC_ZMII #test only
-        select IBM_NEW_EMAC_TAH  #test only
+        select IBM_EMAC_EMAC4
+        select IBM_EMAC_RGMII
+        select IBM_EMAC_ZMII #test only
+        select IBM_EMAC_TAH  #test only
 
 config 440SP
         bool
 
 config 440SPe
         bool
-        select IBM_NEW_EMAC_EMAC4
+        select IBM_EMAC_EMAC4
 
 config 460EX
         bool
         select PPC_FPU
-        select IBM_NEW_EMAC_EMAC4
-        select IBM_NEW_EMAC_TAH
+        select IBM_EMAC_EMAC4
+        select IBM_EMAC_TAH
 
 config 460SX
         bool
         select PPC_FPU
-        select IBM_NEW_EMAC_EMAC4
-        select IBM_NEW_EMAC_RGMII
-        select IBM_NEW_EMAC_ZMII
-        select IBM_NEW_EMAC_TAH
+        select IBM_EMAC_EMAC4
+        select IBM_EMAC_RGMII
+        select IBM_EMAC_ZMII
+        select IBM_EMAC_TAH
 
 config APM821xx
         bool
         select PPC_FPU
-        select IBM_NEW_EMAC_EMAC4
-        select IBM_NEW_EMAC_TAH
+        select IBM_EMAC_EMAC4
+        select IBM_EMAC_TAH
 
 # 44x errata/workaround config symbols, selected by the CPU models above
 config IBM440EP_ERR42
diff --git a/arch/powerpc/platforms/44x/warp.c b/arch/powerpc/platforms/44x/warp.c
index 8f771395f424..4cfa49901c02 100644
--- a/arch/powerpc/platforms/44x/warp.c
+++ b/arch/powerpc/platforms/44x/warp.c
@@ -18,6 +18,7 @@
 #include <linux/of_gpio.h>
 #include <linux/of_i2c.h>
 #include <linux/slab.h>
+#include <linux/export.h>
 
 #include <asm/machdep.h>
 #include <asm/prom.h>
diff --git a/arch/powerpc/platforms/512x/Kconfig b/arch/powerpc/platforms/512x/Kconfig
index 27b0651221d1..b3ebce1aec07 100644
--- a/arch/powerpc/platforms/512x/Kconfig
+++ b/arch/powerpc/platforms/512x/Kconfig
@@ -6,6 +6,7 @@ config PPC_MPC512x
         select PPC_CLOCK
         select PPC_PCI_CHOICE
         select FSL_PCI if PCI
+        select ARCH_WANT_OPTIONAL_GPIOLIB
 
 config MPC5121_ADS
         bool "Freescale MPC5121E ADS"
diff --git a/arch/powerpc/platforms/512x/clock.c b/arch/powerpc/platforms/512x/clock.c
index 3dc2a8d262b8..1d8700ff60b0 100644
--- a/arch/powerpc/platforms/512x/clock.c
+++ b/arch/powerpc/platforms/512x/clock.c
@@ -18,6 +18,7 @@
 #include <linux/list.h>
 #include <linux/errno.h>
 #include <linux/err.h>
+#include <linux/module.h>
 #include <linux/string.h>
 #include <linux/clk.h>
 #include <linux/mutex.h>
diff --git a/arch/powerpc/platforms/512x/mpc512x_shared.c b/arch/powerpc/platforms/512x/mpc512x_shared.c
index e41ebbdb3e12..cfe958e94e1e 100644
--- a/arch/powerpc/platforms/512x/mpc512x_shared.c
+++ b/arch/powerpc/platforms/512x/mpc512x_shared.c
@@ -66,8 +66,8 @@ struct fsl_diu_shared_fb {
         bool            in_use;
 };
 
-unsigned int mpc512x_get_pixel_format(unsigned int bits_per_pixel,
-                                      int monitor_port)
+u32 mpc512x_get_pixel_format(enum fsl_diu_monitor_port port,
+                             unsigned int bits_per_pixel)
 {
         switch (bits_per_pixel) {
         case 32:
@@ -80,11 +80,12 @@ unsigned int mpc512x_get_pixel_format(unsigned int bits_per_pixel,
         return 0x00000400;
 }
 
-void mpc512x_set_gamma_table(int monitor_port, char *gamma_table_base)
+void mpc512x_set_gamma_table(enum fsl_diu_monitor_port port,
+                             char *gamma_table_base)
 {
 }
 
-void mpc512x_set_monitor_port(int monitor_port)
+void mpc512x_set_monitor_port(enum fsl_diu_monitor_port port)
 {
 }
 
@@ -182,14 +183,10 @@ void mpc512x_set_pixel_clock(unsigned int pixclock)
         iounmap(ccm);
 }
 
-ssize_t mpc512x_show_monitor_port(int monitor_port, char *buf)
+enum fsl_diu_monitor_port
+mpc512x_valid_monitor_port(enum fsl_diu_monitor_port port)
 {
-        return sprintf(buf, "0 - 5121 LCD\n");
-}
-
-int mpc512x_set_sysfs_monitor_port(int val)
-{
-        return 0;
+        return FSL_DIU_PORT_DVI;
 }
 
 static struct fsl_diu_shared_fb __attribute__ ((__aligned__(8))) diu_shared_fb;
@@ -256,7 +253,7 @@ void __init mpc512x_init_diu(void)
         }
 
         mode = in_be32(&diu_reg->diu_mode);
-        if (mode != MFB_MODE1) {
+        if (mode == MFB_MODE0) {
                 pr_info("%s: DIU OFF\n", __func__);
                 goto out;
         }
@@ -332,8 +329,7 @@ void __init mpc512x_setup_diu(void)
         diu_ops.set_gamma_table         = mpc512x_set_gamma_table;
         diu_ops.set_monitor_port        = mpc512x_set_monitor_port;
         diu_ops.set_pixel_clock         = mpc512x_set_pixel_clock;
-        diu_ops.show_monitor_port       = mpc512x_show_monitor_port;
-        diu_ops.set_sysfs_monitor_port  = mpc512x_set_sysfs_monitor_port;
+        diu_ops.valid_monitor_port      = mpc512x_valid_monitor_port;
         diu_ops.release_bootmem         = mpc512x_release_bootmem;
 #endif
 }
diff --git a/arch/powerpc/platforms/52xx/mpc5200_simple.c b/arch/powerpc/platforms/52xx/mpc5200_simple.c
index e36d6e232ae6..846b789fb195 100644
--- a/arch/powerpc/platforms/52xx/mpc5200_simple.c
+++ b/arch/powerpc/platforms/52xx/mpc5200_simple.c
@@ -50,6 +50,7 @@ static void __init mpc5200_simple_setup_arch(void)
 
 /* list of the supported boards */
 static const char *board[] __initdata = {
+        "anon,charon",
         "intercontrol,digsy-mtc",
         "manroland,mucmc52",
         "manroland,uc101",
diff --git a/arch/powerpc/platforms/52xx/mpc52xx_common.c b/arch/powerpc/platforms/52xx/mpc52xx_common.c
index 41f3a7eda1de..369fd5457a3f 100644
--- a/arch/powerpc/platforms/52xx/mpc52xx_common.c
+++ b/arch/powerpc/platforms/52xx/mpc52xx_common.c
@@ -17,6 +17,7 @@
 #include <linux/spinlock.h>
 #include <linux/of_platform.h>
 #include <linux/of_gpio.h>
+#include <linux/export.h>
 #include <asm/io.h>
 #include <asm/prom.h>
 #include <asm/mpc52xx.h>
diff --git a/arch/powerpc/platforms/52xx/mpc52xx_gpt.c b/arch/powerpc/platforms/52xx/mpc52xx_gpt.c
index 6c39b9cc2fa3..f94f06e52762 100644
--- a/arch/powerpc/platforms/52xx/mpc52xx_gpt.c
+++ b/arch/powerpc/platforms/52xx/mpc52xx_gpt.c
@@ -67,6 +67,7 @@
 #include <linux/watchdog.h>
 #include <linux/miscdevice.h>
 #include <linux/uaccess.h>
+#include <linux/module.h>
 #include <asm/div64.h>
 #include <asm/mpc52xx.h>
 
diff --git a/arch/powerpc/platforms/52xx/mpc52xx_lpbfifo.c b/arch/powerpc/platforms/52xx/mpc52xx_lpbfifo.c
index 9940ce8a2d4e..d61fb1c0c1a0 100644
--- a/arch/powerpc/platforms/52xx/mpc52xx_lpbfifo.c
+++ b/arch/powerpc/platforms/52xx/mpc52xx_lpbfifo.c
@@ -14,6 +14,7 @@
 #include <linux/of.h>
 #include <linux/of_platform.h>
 #include <linux/spinlock.h>
+#include <linux/module.h>
 #include <asm/io.h>
 #include <asm/prom.h>
 #include <asm/mpc52xx.h>
diff --git a/arch/powerpc/platforms/82xx/km82xx.c b/arch/powerpc/platforms/82xx/km82xx.c
index 428c5e0a0e75..3661bcdc326a 100644
--- a/arch/powerpc/platforms/82xx/km82xx.c
+++ b/arch/powerpc/platforms/82xx/km82xx.c
@@ -49,6 +49,9 @@ struct cpm_pin {
 };
 
 static __initdata struct cpm_pin km82xx_pins[] = {
+        /* SMC1 */
+        {2, 4, CPM_PIN_INPUT | CPM_PIN_PRIMARY},
+        {2, 5, CPM_PIN_OUTPUT | CPM_PIN_PRIMARY},
 
         /* SMC2 */
         {0, 8, CPM_PIN_INPUT | CPM_PIN_PRIMARY},
@@ -137,6 +140,7 @@ static void __init init_ioports(void)
         }
 
         cpm2_smc_clk_setup(CPM_CLK_SMC2, CPM_BRG8);
+        cpm2_smc_clk_setup(CPM_CLK_SMC1, CPM_BRG7);
         cpm2_clk_setup(CPM_CLK_SCC1, CPM_CLK11, CPM_CLK_RX);
         cpm2_clk_setup(CPM_CLK_SCC1, CPM_CLK11, CPM_CLK_TX);
         cpm2_clk_setup(CPM_CLK_SCC3, CPM_CLK5, CPM_CLK_RTX);
diff --git a/arch/powerpc/platforms/83xx/Kconfig b/arch/powerpc/platforms/83xx/Kconfig
index 73f4135f3a1a..670a033264c0 100644
--- a/arch/powerpc/platforms/83xx/Kconfig
+++ b/arch/powerpc/platforms/83xx/Kconfig
@@ -114,18 +114,21 @@ config KMETER1
 
 endif
 
-# used for usb
+# used for usb & gpio
 config PPC_MPC831x
         bool
+        select ARCH_WANT_OPTIONAL_GPIOLIB
 
 # used for math-emu
 config PPC_MPC832x
         bool
 
-# used for usb
+# used for usb & gpio
 config PPC_MPC834x
         bool
+        select ARCH_WANT_OPTIONAL_GPIOLIB
 
-# used for usb
+# used for usb & gpio
 config PPC_MPC837x
         bool
+        select ARCH_WANT_OPTIONAL_GPIOLIB
diff --git a/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c b/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c
index 70798ac911ef..ef6537b8ed33 100644
--- a/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c
+++ b/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c
@@ -21,6 +21,8 @@
 #include <linux/of.h>
 #include <linux/of_gpio.h>
 #include <linux/slab.h>
+#include <linux/kthread.h>
+#include <linux/reboot.h>
 #include <asm/prom.h>
 #include <asm/machdep.h>
 
@@ -30,6 +32,7 @@
  */
 #define MCU_REG_CTRL    0x20
 #define MCU_CTRL_POFF   0x40
+#define MCU_CTRL_BTN    0x80
 
 #define MCU_NUM_GPIO    2
 
@@ -42,13 +45,55 @@ struct mcu {
 
 static struct mcu *glob_mcu;
 
+struct task_struct *shutdown_thread;
+static int shutdown_thread_fn(void *data)
+{
+        int ret;
+        struct mcu *mcu = glob_mcu;
+
+        while (!kthread_should_stop()) {
+                ret = i2c_smbus_read_byte_data(mcu->client, MCU_REG_CTRL);
+                if (ret < 0)
+                        pr_err("MCU status reg read failed.\n");
+                mcu->reg_ctrl = ret;
+
+
+                if (mcu->reg_ctrl & MCU_CTRL_BTN) {
+                        i2c_smbus_write_byte_data(mcu->client, MCU_REG_CTRL,
+                                                  mcu->reg_ctrl & ~MCU_CTRL_BTN);
+
+                        ctrl_alt_del();
+                }
+
+                set_current_state(TASK_INTERRUPTIBLE);
+                schedule_timeout(HZ);
+        }
+
+        return 0;
+}
+
+static ssize_t show_status(struct device *d,
+                           struct device_attribute *attr, char *buf)
+{
+        int ret;
+        struct mcu *mcu = glob_mcu;
+
+        ret = i2c_smbus_read_byte_data(mcu->client, MCU_REG_CTRL);
+        if (ret < 0)
+                return -ENODEV;
+        mcu->reg_ctrl = ret;
+
+        return sprintf(buf, "%02x\n", ret);
+}
+static DEVICE_ATTR(status, S_IRUGO, show_status, NULL);
+
 static void mcu_power_off(void)
 {
         struct mcu *mcu = glob_mcu;
 
         pr_info("Sending power-off request to the MCU...\n");
         mutex_lock(&mcu->lock);
-        i2c_smbus_write_byte_data(glob_mcu->client, MCU_REG_CTRL,
+        i2c_smbus_write_byte_data(mcu->client, MCU_REG_CTRL,
                                   mcu->reg_ctrl | MCU_CTRL_POFF);
         mutex_unlock(&mcu->lock);
 }
@@ -130,6 +175,13 @@ static int __devinit mcu_probe(struct i2c_client *client,
                 dev_info(&client->dev, "will provide power-off service\n");
         }
 
+        if (device_create_file(&client->dev, &dev_attr_status))
+                dev_err(&client->dev,
+                        "couldn't create device file for status\n");
+
+        shutdown_thread = kthread_run(shutdown_thread_fn, NULL,
+                                      "mcu-i2c-shdn");
+
         return 0;
 err:
         kfree(mcu);
@@ -141,6 +193,10 @@ static int __devexit mcu_remove(struct i2c_client *client)
         struct mcu *mcu = i2c_get_clientdata(client);
         int ret;
 
+        kthread_stop(shutdown_thread);
+
+        device_remove_file(&client->dev, &dev_attr_status);
+
         if (glob_mcu == mcu) {
                 ppc_md.power_off = NULL;
                 glob_mcu = NULL;
diff --git a/arch/powerpc/platforms/83xx/suspend.c b/arch/powerpc/platforms/83xx/suspend.c
index 104faa8aa23c..edf66870d978 100644
--- a/arch/powerpc/platforms/83xx/suspend.c
+++ b/arch/powerpc/platforms/83xx/suspend.c
@@ -21,6 +21,7 @@
 #include <linux/suspend.h>
 #include <linux/fsl_devices.h>
 #include <linux/of_platform.h>
+#include <linux/export.h>
 
 #include <asm/reg.h>
 #include <asm/io.h>
diff --git a/arch/powerpc/platforms/85xx/Kconfig b/arch/powerpc/platforms/85xx/Kconfig
index 12f5932dadc9..45023e26aea3 100644
--- a/arch/powerpc/platforms/85xx/Kconfig
+++ b/arch/powerpc/platforms/85xx/Kconfig
@@ -171,17 +171,18 @@ config SBC8560
         help
           This option enables support for the Wind River SBC8560 board
 
-config P2040_RDB
-        bool "Freescale P2040 RDB"
+config P2041_RDB
+        bool "Freescale P2041 RDB"
         select DEFAULT_UIMAGE
         select PPC_E500MC
         select PHYS_64BIT
         select SWIOTLB
-        select MPC8xxx_GPIO
+        select ARCH_REQUIRE_GPIOLIB
+        select GPIO_MPC8XXX
         select HAS_RAPIDIO
         select PPC_EPAPR_HV_PIC
         help
-          This option enables support for the P2040 RDB board
+          This option enables support for the P2041 RDB board
 
 config P3041_DS
         bool "Freescale P3041 DS"
@@ -189,19 +190,33 @@ config P3041_DS
         select PPC_E500MC
         select PHYS_64BIT
         select SWIOTLB
-        select MPC8xxx_GPIO
+        select ARCH_REQUIRE_GPIOLIB
+        select GPIO_MPC8XXX
         select HAS_RAPIDIO
         select PPC_EPAPR_HV_PIC
         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 MPC8xxx_GPIO
+        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
         select PPC_E500MC
         select PHYS_64BIT
         select SWIOTLB
-        select MPC8xxx_GPIO
+        select ARCH_REQUIRE_GPIOLIB
+        select GPIO_MPC8XXX
         select HAS_RAPIDIO
         select PPC_EPAPR_HV_PIC
         help
@@ -216,7 +231,8 @@ config P5020_DS
         select PPC_E500MC
         select PHYS_64BIT
         select SWIOTLB
-        select MPC8xxx_GPIO
+        select ARCH_REQUIRE_GPIOLIB
+        select GPIO_MPC8XXX
         select HAS_RAPIDIO
         select PPC_EPAPR_HV_PIC
         help
diff --git a/arch/powerpc/platforms/85xx/Makefile b/arch/powerpc/platforms/85xx/Makefile
index a971b32c5c0a..bc5acb95917a 100644
--- a/arch/powerpc/platforms/85xx/Makefile
+++ b/arch/powerpc/platforms/85xx/Makefile
@@ -13,8 +13,9 @@ obj-$(CONFIG_MPC85xx_RDB) += mpc85xx_rdb.o
 obj-$(CONFIG_P1010_RDB)   += p1010rdb.o
 obj-$(CONFIG_P1022_DS)    += p1022_ds.o
 obj-$(CONFIG_P1023_RDS)   += p1023_rds.o
-obj-$(CONFIG_P2040_RDB)   += p2040_rdb.o corenet_ds.o
+obj-$(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
diff --git a/arch/powerpc/platforms/85xx/mpc85xx_cds.c b/arch/powerpc/platforms/85xx/mpc85xx_cds.c
index 2bf99786d249..66cb8d64079f 100644
--- a/arch/powerpc/platforms/85xx/mpc85xx_cds.c
+++ b/arch/powerpc/platforms/85xx/mpc85xx_cds.c
@@ -23,7 +23,6 @@
 #include <linux/delay.h>
 #include <linux/seq_file.h>
 #include <linux/initrd.h>
-#include <linux/module.h>
 #include <linux/interrupt.h>
 #include <linux/fsl_devices.h>
 #include <linux/of_platform.h>
diff --git a/arch/powerpc/platforms/85xx/mpc85xx_mds.c b/arch/powerpc/platforms/85xx/mpc85xx_mds.c
index 973b3f4a4b49..a23a3ff634c5 100644
--- a/arch/powerpc/platforms/85xx/mpc85xx_mds.c
+++ b/arch/powerpc/platforms/85xx/mpc85xx_mds.c
@@ -28,7 +28,6 @@
 #include <linux/delay.h>
 #include <linux/seq_file.h>
 #include <linux/initrd.h>
-#include <linux/module.h>
 #include <linux/fsl_devices.h>
 #include <linux/of_platform.h>
 #include <linux/of_device.h>
diff --git a/arch/powerpc/platforms/85xx/p1022_ds.c b/arch/powerpc/platforms/85xx/p1022_ds.c
index 266b3aadfe5e..fda15716fada 100644
--- a/arch/powerpc/platforms/85xx/p1022_ds.c
+++ b/arch/powerpc/platforms/85xx/p1022_ds.c
@@ -93,8 +93,8 @@
  * The Area Descriptor is a 32-bit value that determine which bits in each
  * pixel are to be used for each color.
  */
-static unsigned int p1022ds_get_pixel_format(unsigned int bits_per_pixel,
-        int monitor_port)
+static u32 p1022ds_get_pixel_format(enum fsl_diu_monitor_port port,
+                                    unsigned int bits_per_pixel)
 {
         switch (bits_per_pixel) {
         case 32:
@@ -118,7 +118,8 @@ static unsigned int p1022ds_get_pixel_format(unsigned int bits_per_pixel,
  * On some boards, the gamma table for some ports may need to be modified.
  * This is not the case on the P1022DS, so we do nothing.
 */
-static void p1022ds_set_gamma_table(int monitor_port, char *gamma_table_base)
+static void p1022ds_set_gamma_table(enum fsl_diu_monitor_port port,
+                                    char *gamma_table_base)
 {
 }
 
@@ -126,38 +127,43 @@ static void p1022ds_set_gamma_table(int monitor_port, char *gamma_table_base)
  * p1022ds_set_monitor_port: switch the output to a different monitor port
  *
  */
-static void p1022ds_set_monitor_port(int monitor_port)
+static void p1022ds_set_monitor_port(enum fsl_diu_monitor_port port)
 {
-        struct device_node *pixis_node;
+        struct device_node *np;
         void __iomem *pixis;
         u8 __iomem *brdcfg1;
 
-        pixis_node = of_find_compatible_node(NULL, NULL, "fsl,p1022ds-pixis");
-        if (!pixis_node) {
+        np = of_find_compatible_node(NULL, NULL, "fsl,p1022ds-fpga");
+        if (!np)
+                /* older device trees used "fsl,p1022ds-pixis" */
+                np = of_find_compatible_node(NULL, NULL, "fsl,p1022ds-pixis");
+        if (!np) {
                 pr_err("p1022ds: missing ngPIXIS node\n");
                 return;
         }
 
-        pixis = of_iomap(pixis_node, 0);
+        pixis = of_iomap(np, 0);
         if (!pixis) {
                 pr_err("p1022ds: could not map ngPIXIS registers\n");
                 return;
         }
         brdcfg1 = pixis + 9;    /* BRDCFG1 is at offset 9 in the ngPIXIS */
 
-        switch (monitor_port) {
-        case 0: /* DVI */
+        switch (port) {
+        case FSL_DIU_PORT_DVI:
+                printk(KERN_INFO "%s:%u\n", __func__, __LINE__);
                 /* Enable the DVI port, disable the DFP and the backlight */
                 clrsetbits_8(brdcfg1, PX_BRDCFG1_DFPEN | PX_BRDCFG1_BACKLIGHT,
                              PX_BRDCFG1_DVIEN);
                 break;
-        case 1: /* Single link LVDS */
+        case FSL_DIU_PORT_LVDS:
+                printk(KERN_INFO "%s:%u\n", __func__, __LINE__);
                 /* Enable the DFP port, disable the DVI and the backlight */
                 clrsetbits_8(brdcfg1, PX_BRDCFG1_DVIEN | PX_BRDCFG1_BACKLIGHT,
                              PX_BRDCFG1_DFPEN);
                 break;
         default:
-                pr_err("p1022ds: unsupported monitor port %i\n", monitor_port);
+                pr_err("p1022ds: unsupported monitor port %i\n", port);
         }
 
         iounmap(pixis);
@@ -214,23 +220,18 @@ void p1022ds_set_pixel_clock(unsigned int pixclock)
 }
 
 /**
- * p1022ds_show_monitor_port: show the current monitor
- *
- * This function returns a string indicating whether the current monitor is
- * set to DVI or LVDS.
- */
-ssize_t p1022ds_show_monitor_port(int monitor_port, char *buf)
-{
-        return sprintf(buf, "%c0 - DVI\n%c1 - Single link LVDS\n",
-                monitor_port == 0 ? '*' : ' ', monitor_port == 1 ? '*' : ' ');
-}
-
-/**
- * p1022ds_set_sysfs_monitor_port: set the monitor port for sysfs
+ * p1022ds_valid_monitor_port: set the monitor port for sysfs
  */
-int p1022ds_set_sysfs_monitor_port(int val)
+enum fsl_diu_monitor_port
+p1022ds_valid_monitor_port(enum fsl_diu_monitor_port port)
 {
-        return val < 2 ? val : 0;
+        switch (port) {
+        case FSL_DIU_PORT_DVI:
+        case FSL_DIU_PORT_LVDS:
+                return port;
+        default:
+                return FSL_DIU_PORT_DVI; /* Dual-link LVDS is not supported */
+        }
 }
 
 #endif
@@ -305,8 +306,7 @@ static void __init p1022_ds_setup_arch(void)
         diu_ops.set_gamma_table         = p1022ds_set_gamma_table;
         diu_ops.set_monitor_port        = p1022ds_set_monitor_port;
         diu_ops.set_pixel_clock         = p1022ds_set_pixel_clock;
-        diu_ops.show_monitor_port       = p1022ds_show_monitor_port;
-        diu_ops.set_sysfs_monitor_port  = p1022ds_set_sysfs_monitor_port;
+        diu_ops.valid_monitor_port      = p1022ds_valid_monitor_port;
 #endif
 
 #ifdef CONFIG_SMP
diff --git a/arch/powerpc/platforms/85xx/p2040_rdb.c b/arch/powerpc/platforms/85xx/p2041_rdb.c
index 32b56ac73dfb..eda6ed5683e1 100644
--- a/arch/powerpc/platforms/85xx/p2040_rdb.c
+++ b/arch/powerpc/platforms/85xx/p2041_rdb.c
@@ -1,5 +1,5 @@
 /*
- * P2040 RDB Setup
+ * P2041 RDB Setup
  *
  * Copyright 2011 Freescale Semiconductor Inc.
  *
@@ -35,18 +35,18 @@
 /*
  * Called very early, device-tree isn't unflattened
  */
-static int __init p2040_rdb_probe(void)
+static int __init p2041_rdb_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,P2040RDB"))
+        if (of_flat_dt_is_compatible(root, "fsl,P2041RDB"))
                 return 1;
 
         /* Check if we're running under the Freescale hypervisor */
-        if (of_flat_dt_is_compatible(root, "fsl,P2040RDB-hv")) {
+        if (of_flat_dt_is_compatible(root, "fsl,P2041RDB-hv")) {
                 ppc_md.init_IRQ = ehv_pic_init;
                 ppc_md.get_irq = ehv_pic_get_irq;
                 ppc_md.restart = fsl_hv_restart;
@@ -66,9 +66,9 @@ static int __init p2040_rdb_probe(void)
         return 0;
 }
 
-define_machine(p2040_rdb) {
-        .name                   = "P2040 RDB",
-        .probe                  = p2040_rdb_probe,
+define_machine(p2041_rdb) {
+        .name                   = "P2041 RDB",
+        .probe                  = p2041_rdb_probe,
         .setup_arch             = corenet_ds_setup_arch,
         .init_IRQ               = corenet_ds_pic_init,
 #ifdef CONFIG_PCI
@@ -81,8 +81,8 @@ define_machine(p2040_rdb) {
         .power_save             = e500_idle,
 };
 
-machine_device_initcall(p2040_rdb, corenet_ds_publish_devices);
+machine_device_initcall(p2041_rdb, corenet_ds_publish_devices);
 
 #ifdef CONFIG_SWIOTLB
-machine_arch_initcall(p2040_rdb, swiotlb_setup_bus_notifier);
+machine_arch_initcall(p2041_rdb, swiotlb_setup_bus_notifier);
 #endif
diff --git a/arch/powerpc/platforms/85xx/p3060_qds.c b/arch/powerpc/platforms/85xx/p3060_qds.c
new file mode 100644
index 000000000000..01dcf44871e9
--- /dev/null
+++ b/arch/powerpc/platforms/85xx/p3060_qds.c
@@ -0,0 +1,77 @@
+/*
+ * 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, declare_of_platform_devices);
+
+#ifdef CONFIG_SWIOTLB
+machine_arch_initcall(p3060_qds, swiotlb_setup_bus_notifier);
+#endif
diff --git a/arch/powerpc/platforms/85xx/sbc8548.c b/arch/powerpc/platforms/85xx/sbc8548.c
index d07dcb7f4ee9..14632a971225 100644
--- a/arch/powerpc/platforms/85xx/sbc8548.c
+++ b/arch/powerpc/platforms/85xx/sbc8548.c
@@ -26,7 +26,6 @@
 #include <linux/delay.h>
 #include <linux/seq_file.h>
 #include <linux/initrd.h>
-#include <linux/module.h>
 #include <linux/interrupt.h>
 #include <linux/fsl_devices.h>
 #include <linux/of_platform.h>
diff --git a/arch/powerpc/platforms/85xx/sbc8560.c b/arch/powerpc/platforms/85xx/sbc8560.c
index 09ced7221750..cebd786dc334 100644
--- a/arch/powerpc/platforms/85xx/sbc8560.c
+++ b/arch/powerpc/platforms/85xx/sbc8560.c
@@ -283,7 +283,7 @@ static int __init sbc8560_bdrstcr_init(void)
 
         of_address_to_resource(np, 0, &res);
 
-        printk(KERN_INFO "sbc8560: Found BRSTCR at i/o 0x%x\n", res.start);
+        printk(KERN_INFO "sbc8560: Found BRSTCR at %pR\n", &res);
 
         brstcr = ioremap(res.start, resource_size(&res));
         if(!brstcr)
diff --git a/arch/powerpc/platforms/85xx/smp.c b/arch/powerpc/platforms/85xx/smp.c
index 5b9b901f6443..2df4785ffd4e 100644
--- a/arch/powerpc/platforms/85xx/smp.c
+++ b/arch/powerpc/platforms/85xx/smp.c
@@ -48,10 +48,11 @@ smp_85xx_kick_cpu(int nr)
         const u64 *cpu_rel_addr;
         __iomem u32 *bptr_vaddr;
         struct device_node *np;
-        int n = 0;
+        int n = 0, hw_cpu = get_hard_smp_processor_id(nr);
         int ioremappable;
 
-        WARN_ON (nr < 0 || nr >= NR_CPUS);
+        WARN_ON(nr < 0 || nr >= NR_CPUS);
+        WARN_ON(hw_cpu < 0 || hw_cpu >= NR_CPUS);
 
         pr_debug("smp_85xx_kick_cpu: kick CPU #%d\n", nr);
 
@@ -79,7 +80,7 @@ smp_85xx_kick_cpu(int nr)
 
         local_irq_save(flags);
 
-        out_be32(bptr_vaddr + BOOT_ENTRY_PIR, nr);
+        out_be32(bptr_vaddr + BOOT_ENTRY_PIR, hw_cpu);
 #ifdef CONFIG_PPC32
         out_be32(bptr_vaddr + BOOT_ENTRY_ADDR_LOWER, __pa(__early_start));
 
@@ -88,7 +89,7 @@ smp_85xx_kick_cpu(int nr)
                                 (ulong)(bptr_vaddr + SIZE_BOOT_ENTRY));
 
         /* Wait a bit for the CPU to ack. */
-        while ((__secondary_hold_acknowledge != nr) && (++n < 1000))
+        while ((__secondary_hold_acknowledge != hw_cpu) && (++n < 1000))
                 mdelay(1);
 #else
         smp_generic_kick_cpu(nr);
@@ -206,7 +207,7 @@ static void mpc85xx_smp_machine_kexec(struct kimage *image)
         if ( !timeout )
                 printk(KERN_ERR "Unable to bring down secondary cpu(s)");
 
-        for (i = 0; i < num_cpus; i++)
+        for_each_online_cpu(i)
         {
                 if ( i == smp_processor_id() ) continue;
                 mpic_reset_core(i);
@@ -243,6 +244,7 @@ void __init mpc85xx_smp_init(void)
                  * If left NULL, .message_pass defaults to
                  * smp_muxed_ipi_message_pass
                  */
+                smp_85xx_ops.message_pass = NULL;
                 smp_85xx_ops.cause_ipi = doorbell_cause_ipi;
         }
 
diff --git a/arch/powerpc/platforms/86xx/Kconfig b/arch/powerpc/platforms/86xx/Kconfig
index a0b5638c5dc8..8d6599d54ea6 100644
--- a/arch/powerpc/platforms/86xx/Kconfig
+++ b/arch/powerpc/platforms/86xx/Kconfig
@@ -4,6 +4,7 @@ menuconfig PPC_86xx
         depends on 6xx
         select FSL_SOC
         select ALTIVEC
+        select ARCH_WANT_OPTIONAL_GPIOLIB
         help
           The Freescale E600 SoCs have 74xx cores.
 
diff --git a/arch/powerpc/platforms/86xx/gef_gpio.c b/arch/powerpc/platforms/86xx/gef_gpio.c
index 4ff7b1e7bbad..2a703365e664 100644
--- a/arch/powerpc/platforms/86xx/gef_gpio.c
+++ b/arch/powerpc/platforms/86xx/gef_gpio.c
@@ -27,6 +27,7 @@
 #include <linux/of_gpio.h>
 #include <linux/gpio.h>
 #include <linux/slab.h>
+#include <linux/module.h>
 
 #define GEF_GPIO_DIRECT         0x00
 #define GEF_GPIO_IN             0x04
diff --git a/arch/powerpc/platforms/86xx/mpc8610_hpcd.c b/arch/powerpc/platforms/86xx/mpc8610_hpcd.c
index 74e018ef724b..13fa9a6403e6 100644
--- a/arch/powerpc/platforms/86xx/mpc8610_hpcd.c
+++ b/arch/powerpc/platforms/86xx/mpc8610_hpcd.c
@@ -152,10 +152,10 @@ machine_device_initcall(mpc86xx_hpcd, mpc8610_declare_of_platform_devices);
         (c2 << AD_COMP_2_SHIFT) | (c1 << AD_COMP_1_SHIFT) | \
         (c0 << AD_COMP_0_SHIFT) | (size << AD_PIXEL_S_SHIFT))
 
-unsigned int mpc8610hpcd_get_pixel_format(unsigned int bits_per_pixel,
-                                                int monitor_port)
+u32 mpc8610hpcd_get_pixel_format(enum fsl_diu_monitor_port port,
+                                 unsigned int bits_per_pixel)
 {
-        static const unsigned long pixelformat[][3] = {
+        static const u32 pixelformat[][3] = {
                 {
                         MAKE_AD(3, 0, 2, 1, 3, 8, 8, 8, 8),
                         MAKE_AD(4, 2, 0, 1, 2, 8, 8, 8, 0),
@@ -170,7 +170,8 @@ unsigned int mpc8610hpcd_get_pixel_format(unsigned int bits_per_pixel,
         unsigned int arch_monitor;
 
         /* The DVI port is mis-wired on revision 1 of this board. */
-        arch_monitor = ((*pixis_arch == 0x01) && (monitor_port == 0))? 0 : 1;
+        arch_monitor =
+                ((*pixis_arch == 0x01) && (port == FSL_DIU_PORT_DVI)) ? 0 : 1;
 
         switch (bits_per_pixel) {
         case 32:
@@ -185,10 +186,11 @@ unsigned int mpc8610hpcd_get_pixel_format(unsigned int bits_per_pixel,
         }
 }
 
-void mpc8610hpcd_set_gamma_table(int monitor_port, char *gamma_table_base)
+void mpc8610hpcd_set_gamma_table(enum fsl_diu_monitor_port port,
+                                 char *gamma_table_base)
 {
         int i;
-        if (monitor_port == 2) {                /* dual link LVDS */
+        if (port == FSL_DIU_PORT_DLVDS) {
                 for (i = 0; i < 256*3; i++)
                         gamma_table_base[i] = (gamma_table_base[i] << 2) |
                                          ((gamma_table_base[i] >> 6) & 0x03);
@@ -199,17 +201,21 @@ void mpc8610hpcd_set_gamma_table(int monitor_port, char *gamma_table_base)
 #define PX_BRDCFG0_DLINK        (1 << 4)
 #define PX_BRDCFG0_DIU_MASK     (PX_BRDCFG0_DVISEL | PX_BRDCFG0_DLINK)
 
-void mpc8610hpcd_set_monitor_port(int monitor_port)
+void mpc8610hpcd_set_monitor_port(enum fsl_diu_monitor_port port)
 {
-        static const u8 bdcfg[] = {
-                PX_BRDCFG0_DVISEL | PX_BRDCFG0_DLINK,
-                PX_BRDCFG0_DLINK,
-                0,
-        };
-
-        if (monitor_port < 3)
+        switch (port) {
+        case FSL_DIU_PORT_DVI:
                 clrsetbits_8(pixis_bdcfg0, PX_BRDCFG0_DIU_MASK,
-                             bdcfg[monitor_port]);
+                             PX_BRDCFG0_DVISEL | PX_BRDCFG0_DLINK);
+                break;
+        case FSL_DIU_PORT_LVDS:
+                clrsetbits_8(pixis_bdcfg0, PX_BRDCFG0_DIU_MASK,
+                             PX_BRDCFG0_DLINK);
+                break;
+        case FSL_DIU_PORT_DLVDS:
+                clrbits8(pixis_bdcfg0, PX_BRDCFG0_DIU_MASK);
+                break;
+        }
 }
 
 /**
@@ -262,20 +268,10 @@ void mpc8610hpcd_set_pixel_clock(unsigned int pixclock)
         iounmap(guts);
 }
 
-ssize_t mpc8610hpcd_show_monitor_port(int monitor_port, char *buf)
-{
-        return snprintf(buf, PAGE_SIZE,
-                        "%c0 - DVI\n"
-                        "%c1 - Single link LVDS\n"
-                        "%c2 - Dual link LVDS\n",
-                        monitor_port == 0 ? '*' : ' ',
-                        monitor_port == 1 ? '*' : ' ',
-                        monitor_port == 2 ? '*' : ' ');
-}
-
-int mpc8610hpcd_set_sysfs_monitor_port(int val)
+enum fsl_diu_monitor_port
+mpc8610hpcd_valid_monitor_port(enum fsl_diu_monitor_port port)
 {
-        return val < 3 ? val : 0;
+        return port;
 }
 
 #endif
@@ -307,8 +303,7 @@ static void __init mpc86xx_hpcd_setup_arch(void)
         diu_ops.set_gamma_table         = mpc8610hpcd_set_gamma_table;
         diu_ops.set_monitor_port        = mpc8610hpcd_set_monitor_port;
         diu_ops.set_pixel_clock         = mpc8610hpcd_set_pixel_clock;
-        diu_ops.show_monitor_port       = mpc8610hpcd_show_monitor_port;
-        diu_ops.set_sysfs_monitor_port  = mpc8610hpcd_set_sysfs_monitor_port;
+        diu_ops.valid_monitor_port      = mpc8610hpcd_valid_monitor_port;
 #endif
 
         pixis_node = of_find_compatible_node(NULL, NULL, "fsl,fpga-pixis");
diff --git a/arch/powerpc/platforms/8xx/tqm8xx_setup.c b/arch/powerpc/platforms/8xx/tqm8xx_setup.c
index b71c650fbb11..528e00ddef31 100644
--- a/arch/powerpc/platforms/8xx/tqm8xx_setup.c
+++ b/arch/powerpc/platforms/8xx/tqm8xx_setup.c
@@ -18,7 +18,6 @@
  */
 
 #include <linux/init.h>
-#include <linux/module.h>
 #include <linux/param.h>
 #include <linux/string.h>
 #include <linux/ioport.h>
diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig
index b9ba86191aed..e4588721ef34 100644
--- a/arch/powerpc/platforms/Kconfig
+++ b/arch/powerpc/platforms/Kconfig
@@ -1,5 +1,6 @@
 menu "Platform support"
 
+source "arch/powerpc/platforms/powernv/Kconfig"
 source "arch/powerpc/platforms/pseries/Kconfig"
 source "arch/powerpc/platforms/iseries/Kconfig"
 source "arch/powerpc/platforms/chrp/Kconfig"
@@ -333,16 +334,6 @@ config OF_RTC
 
 source "arch/powerpc/sysdev/bestcomm/Kconfig"
 
-config MPC8xxx_GPIO
-        bool "MPC512x/MPC8xxx GPIO support"
-        depends on PPC_MPC512x || PPC_MPC831x || PPC_MPC834x || PPC_MPC837x || \
-                   FSL_SOC_BOOKE || PPC_86xx
-        select GENERIC_GPIO
-        select ARCH_REQUIRE_GPIOLIB
-        help
-          Say Y here if you're going to use hardware that connects to the
-          MPC512x/831x/834x/837x/8572/8610 GPIOs.
-
 config SIMPLE_GPIO
         bool "Support for simple, memory-mapped GPIO controllers"
         depends on PPC
@@ -355,7 +346,7 @@ config SIMPLE_GPIO
           on-board peripherals.
 
 config MCU_MPC8349EMITX
-        tristate "MPC8349E-mITX MCU driver"
+        bool "MPC8349E-mITX MCU driver"
         depends on I2C && PPC_83xx
         select GENERIC_GPIO
         select ARCH_REQUIRE_GPIOLIB
diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype
index e06e39589a09..fbecae0fbb49 100644
--- a/arch/powerpc/platforms/Kconfig.cputype
+++ b/arch/powerpc/platforms/Kconfig.cputype
@@ -69,6 +69,7 @@ config PPC_BOOK3S_64
         bool "Server processors"
         select PPC_FPU
         select PPC_HAVE_PMU_SUPPORT
+        select SYS_SUPPORTS_HUGETLBFS
 
 config PPC_BOOK3E_64
         bool "Embedded processors"
@@ -173,6 +174,7 @@ config BOOKE
 config FSL_BOOKE
         bool
         depends on (E200 || E500) && PPC32
+        select SYS_SUPPORTS_HUGETLBFS if PHYS_64BIT
         default y
 
 # this is for common code between PPC32 & PPC64 FSL BOOKE
@@ -282,21 +284,13 @@ config PPC_MMU_NOHASH
         def_bool y
         depends on !PPC_STD_MMU
 
-config PPC_MMU_NOHASH_32
-        def_bool y
-        depends on PPC_MMU_NOHASH && PPC32
-
-config PPC_MMU_NOHASH_64
-        def_bool y
-        depends on PPC_MMU_NOHASH && PPC64
-
 config PPC_BOOK3E_MMU
         def_bool y
         depends on FSL_BOOKE || PPC_BOOK3E
 
 config PPC_MM_SLICES
         bool
-        default y if HUGETLB_PAGE || (PPC_STD_MMU_64 && PPC_64K_PAGES)
+        default y if (PPC64 && HUGETLB_PAGE) || (PPC_STD_MMU_64 && PPC_64K_PAGES)
         default n
 
 config VIRT_CPU_ACCOUNTING
diff --git a/arch/powerpc/platforms/Makefile b/arch/powerpc/platforms/Makefile
index 73e2116cfeed..2635a22bade2 100644
--- a/arch/powerpc/platforms/Makefile
+++ b/arch/powerpc/platforms/Makefile
@@ -14,6 +14,7 @@ obj-$(CONFIG_PPC_82xx)		+= 82xx/
 obj-$(CONFIG_PPC_83xx)          += 83xx/
 obj-$(CONFIG_FSL_SOC_BOOKE)     += 85xx/
 obj-$(CONFIG_PPC_86xx)          += 86xx/
+obj-$(CONFIG_PPC_POWERNV)       += powernv/
 obj-$(CONFIG_PPC_PSERIES)       += pseries/
 obj-$(CONFIG_PPC_ISERIES)       += iseries/
 obj-$(CONFIG_PPC_MAPLE)         += maple/
diff --git a/arch/powerpc/platforms/cell/Kconfig b/arch/powerpc/platforms/cell/Kconfig
index 67d5009b4e86..2e7ff0c5cf42 100644
--- a/arch/powerpc/platforms/cell/Kconfig
+++ b/arch/powerpc/platforms/cell/Kconfig
@@ -17,10 +17,10 @@ config PPC_CELL_NATIVE
         select PPC_CELL_COMMON
         select MPIC
         select PPC_IO_WORKAROUNDS
-        select IBM_NEW_EMAC_EMAC4
-        select IBM_NEW_EMAC_RGMII
-        select IBM_NEW_EMAC_ZMII #test only
-        select IBM_NEW_EMAC_TAH  #test only
+        select IBM_EMAC_EMAC4
+        select IBM_EMAC_RGMII
+        select IBM_EMAC_ZMII #test only
+        select IBM_EMAC_TAH  #test only
         default n
 
 config PPC_IBM_CELL_BLADE
diff --git a/arch/powerpc/platforms/cell/axon_msi.c b/arch/powerpc/platforms/cell/axon_msi.c
index ac06903e136a..40a6e34793b4 100644
--- a/arch/powerpc/platforms/cell/axon_msi.c
+++ b/arch/powerpc/platforms/cell/axon_msi.c
@@ -13,6 +13,7 @@
 #include <linux/kernel.h>
 #include <linux/pci.h>
 #include <linux/msi.h>
+#include <linux/export.h>
 #include <linux/of_platform.h>
 #include <linux/debugfs.h>
 #include <linux/slab.h>
diff --git a/arch/powerpc/platforms/cell/beat.c b/arch/powerpc/platforms/cell/beat.c
index 48c690ea65da..852592b2b712 100644
--- a/arch/powerpc/platforms/cell/beat.c
+++ b/arch/powerpc/platforms/cell/beat.c
@@ -18,7 +18,7 @@
  * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
  */
 
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/init.h>
 #include <linux/err.h>
 #include <linux/rtc.h>
@@ -230,7 +230,7 @@ static int __init beat_register_event(void)
                 }
                 ev->virq = virq;
 
-                rc = request_irq(virq, ev->handler, IRQF_DISABLED,
+                rc = request_irq(virq, ev->handler, 0,
                                       ev->typecode, NULL);
                 if (rc != 0) {
                         printk(KERN_ERR "Beat: failed to request virtual IRQ"
diff --git a/arch/powerpc/platforms/cell/beat_spu_priv1.c b/arch/powerpc/platforms/cell/beat_spu_priv1.c
index bcc17f7fe8ad..13f52589d3a9 100644
--- a/arch/powerpc/platforms/cell/beat_spu_priv1.c
+++ b/arch/powerpc/platforms/cell/beat_spu_priv1.c
@@ -18,8 +18,6 @@
  * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
  */
 
-#include <linux/module.h>
-
 #include <asm/types.h>
 #include <asm/spu.h>
 #include <asm/spu_priv1.h>
diff --git a/arch/powerpc/platforms/cell/beat_wrapper.h b/arch/powerpc/platforms/cell/beat_wrapper.h
index b47dfda48d06..c1109969f242 100644
--- a/arch/powerpc/platforms/cell/beat_wrapper.h
+++ b/arch/powerpc/platforms/cell/beat_wrapper.h
@@ -20,6 +20,7 @@
  * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
  */
 #ifndef BEAT_HCALL
+#include <linux/string.h>
 #include "beat_syscall.h"
 
 /* defined in hvCall.S */
diff --git a/arch/powerpc/platforms/cell/cbe_cpufreq.c b/arch/powerpc/platforms/cell/cbe_cpufreq.c
index bfa2c0cb3d1e..d4c39e32f147 100644
--- a/arch/powerpc/platforms/cell/cbe_cpufreq.c
+++ b/arch/powerpc/platforms/cell/cbe_cpufreq.c
@@ -21,6 +21,7 @@
  */
 
 #include <linux/cpufreq.h>
+#include <linux/module.h>
 #include <linux/of_platform.h>
 
 #include <asm/machdep.h>
diff --git a/arch/powerpc/platforms/cell/cbe_cpufreq_pmi.c b/arch/powerpc/platforms/cell/cbe_cpufreq_pmi.c
index 3233fe84d158..60a07a4f9326 100644
--- a/arch/powerpc/platforms/cell/cbe_cpufreq_pmi.c
+++ b/arch/powerpc/platforms/cell/cbe_cpufreq_pmi.c
@@ -23,6 +23,7 @@
 #include <linux/kernel.h>
 #include <linux/types.h>
 #include <linux/timer.h>
+#include <linux/module.h>
 #include <linux/of_platform.h>
 
 #include <asm/processor.h>
diff --git a/arch/powerpc/platforms/cell/cbe_powerbutton.c b/arch/powerpc/platforms/cell/cbe_powerbutton.c
index f75a4daa4ca2..2bb8031303f0 100644
--- a/arch/powerpc/platforms/cell/cbe_powerbutton.c
+++ b/arch/powerpc/platforms/cell/cbe_powerbutton.c
@@ -21,6 +21,7 @@
  */
 
 #include <linux/input.h>
+#include <linux/module.h>
 #include <linux/platform_device.h>
 #include <asm/pmi.h>
 #include <asm/prom.h>
diff --git a/arch/powerpc/platforms/cell/cbe_regs.c b/arch/powerpc/platforms/cell/cbe_regs.c
index f3917e7a5b44..1428d583c238 100644
--- a/arch/powerpc/platforms/cell/cbe_regs.c
+++ b/arch/powerpc/platforms/cell/cbe_regs.c
@@ -8,7 +8,7 @@
 
 #include <linux/percpu.h>
 #include <linux/types.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/of_device.h>
 #include <linux/of_platform.h>
 
diff --git a/arch/powerpc/platforms/cell/celleb_scc_pciex.c b/arch/powerpc/platforms/cell/celleb_scc_pciex.c
index ae790ac4a589..14be2bd358b8 100644
--- a/arch/powerpc/platforms/cell/celleb_scc_pciex.c
+++ b/arch/powerpc/platforms/cell/celleb_scc_pciex.c
@@ -514,7 +514,7 @@ static __init int celleb_setup_pciex(struct device_node *node,
         virq = irq_create_of_mapping(oirq.controller, oirq.specifier,
                                      oirq.size);
         if (request_irq(virq, pciex_handle_internal_irq,
-                        IRQF_DISABLED, "pciex", (void *)phb)) {
+                        0, "pciex", (void *)phb)) {
                 pr_err("PCIEXC:Failed to request irq\n");
                 goto error;
         }
diff --git a/arch/powerpc/platforms/cell/celleb_setup.c b/arch/powerpc/platforms/cell/celleb_setup.c
index d58d9bae4b9b..1d5a4d8ddad9 100644
--- a/arch/powerpc/platforms/cell/celleb_setup.c
+++ b/arch/powerpc/platforms/cell/celleb_setup.c
@@ -30,6 +30,7 @@
 #include <linux/cpu.h>
 #include <linux/sched.h>
 #include <linux/kernel.h>
+#include <linux/export.h>
 #include <linux/mm.h>
 #include <linux/stddef.h>
 #include <linux/unistd.h>
diff --git a/arch/powerpc/platforms/cell/cpufreq_spudemand.c b/arch/powerpc/platforms/cell/cpufreq_spudemand.c
index 7f92096fe968..23bc9db4317e 100644
--- a/arch/powerpc/platforms/cell/cpufreq_spudemand.c
+++ b/arch/powerpc/platforms/cell/cpufreq_spudemand.c
@@ -22,6 +22,7 @@
 
 #include <linux/cpufreq.h>
 #include <linux/sched.h>
+#include <linux/module.h>
 #include <linux/timer.h>
 #include <linux/workqueue.h>
 #include <linux/atomic.h>
diff --git a/arch/powerpc/platforms/cell/interrupt.c b/arch/powerpc/platforms/cell/interrupt.c
index 3e4eba603e6b..96a433dd2d64 100644
--- a/arch/powerpc/platforms/cell/interrupt.c
+++ b/arch/powerpc/platforms/cell/interrupt.c
@@ -31,7 +31,7 @@
 
 #include <linux/interrupt.h>
 #include <linux/irq.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/percpu.h>
 #include <linux/types.h>
 #include <linux/ioport.h>
diff --git a/arch/powerpc/platforms/cell/iommu.c b/arch/powerpc/platforms/cell/iommu.c
index 26a067122a54..592c3d51b817 100644
--- a/arch/powerpc/platforms/cell/iommu.c
+++ b/arch/powerpc/platforms/cell/iommu.c
@@ -412,8 +412,7 @@ static void cell_iommu_enable_hardware(struct cbe_iommu *iommu)
                         IIC_IRQ_IOEX_ATI | (iommu->nid << IIC_IRQ_NODE_SHIFT));
         BUG_ON(virq == NO_IRQ);
 
-        ret = request_irq(virq, ioc_interrupt, IRQF_DISABLED,
-                        iommu->name, iommu);
+        ret = request_irq(virq, ioc_interrupt, 0, iommu->name, iommu);
         BUG_ON(ret);
 
         /* set the IOC segment table origin register (and turn on the iommu) */
@@ -1159,6 +1158,26 @@ static int __init setup_iommu_fixed(char *str)
 }
 __setup("iommu_fixed=", setup_iommu_fixed);
 
+static u64 cell_dma_get_required_mask(struct device *dev)
+{
+        struct dma_map_ops *dma_ops;
+
+        if (!dev->dma_mask)
+                return 0;
+
+        if (!iommu_fixed_disabled &&
+                        cell_iommu_get_fixed_address(dev) != OF_BAD_ADDR)
+                return DMA_BIT_MASK(64);
+
+        dma_ops = get_dma_ops(dev);
+        if (dma_ops->get_required_mask)
+                return dma_ops->get_required_mask(dev);
+
+        WARN_ONCE(1, "no get_required_mask in %p ops", dma_ops);
+
+        return DMA_BIT_MASK(64);
+}
+
 static int __init cell_iommu_init(void)
 {
         struct device_node *np;
@@ -1175,6 +1194,7 @@ static int __init cell_iommu_init(void)
 
         /* Setup various ppc_md. callbacks */
         ppc_md.pci_dma_dev_setup = cell_pci_dma_dev_setup;
+        ppc_md.dma_get_required_mask = cell_dma_get_required_mask;
         ppc_md.tce_build = tce_build_cell;
         ppc_md.tce_free = tce_free_cell;
 
diff --git a/arch/powerpc/platforms/cell/pmu.c b/arch/powerpc/platforms/cell/pmu.c
index 69ed0d7f1646..59c1a1694104 100644
--- a/arch/powerpc/platforms/cell/pmu.c
+++ b/arch/powerpc/platforms/cell/pmu.c
@@ -24,6 +24,7 @@
 
 #include <linux/interrupt.h>
 #include <linux/types.h>
+#include <linux/export.h>
 #include <asm/io.h>
 #include <asm/irq_regs.h>
 #include <asm/machdep.h>
@@ -391,7 +392,7 @@ static int __init cbe_init_pm_irq(void)
                 }
 
                 rc = request_irq(irq, cbe_pm_irq,
-                                 IRQF_DISABLED, "cbe-pmu-0", NULL);
+                                 0, "cbe-pmu-0", NULL);
                 if (rc) {
                         printk("ERROR: Request for irq on node %d failed\n",
                                node);
diff --git a/arch/powerpc/platforms/cell/qpace_setup.c b/arch/powerpc/platforms/cell/qpace_setup.c
index 51e290126bc1..7f9b6742f8b6 100644
--- a/arch/powerpc/platforms/cell/qpace_setup.c
+++ b/arch/powerpc/platforms/cell/qpace_setup.c
@@ -17,6 +17,7 @@
 #include <linux/sched.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
+#include <linux/export.h>
 #include <linux/delay.h>
 #include <linux/irq.h>
 #include <linux/console.h>
diff --git a/arch/powerpc/platforms/cell/setup.c b/arch/powerpc/platforms/cell/setup.c
index c73cf4c43fc2..0fc9b7256126 100644
--- a/arch/powerpc/platforms/cell/setup.c
+++ b/arch/powerpc/platforms/cell/setup.c
@@ -18,6 +18,7 @@
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/stddef.h>
+#include <linux/export.h>
 #include <linux/unistd.h>
 #include <linux/user.h>
 #include <linux/reboot.h>
diff --git a/arch/powerpc/platforms/cell/smp.c b/arch/powerpc/platforms/cell/smp.c
index f2e1dfe4bf31..f5c5c762d5a3 100644
--- a/arch/powerpc/platforms/cell/smp.c
+++ b/arch/powerpc/platforms/cell/smp.c
@@ -15,7 +15,6 @@
 #undef DEBUG
 
 #include <linux/kernel.h>
-#include <linux/module.h>
 #include <linux/sched.h>
 #include <linux/smp.h>
 #include <linux/interrupt.h>
diff --git a/arch/powerpc/platforms/cell/spu_base.c b/arch/powerpc/platforms/cell/spu_base.c
index 3675da73623f..e94d3ecdd8bb 100644
--- a/arch/powerpc/platforms/cell/spu_base.c
+++ b/arch/powerpc/platforms/cell/spu_base.c
@@ -442,8 +442,7 @@ static int spu_request_irqs(struct spu *spu)
                 snprintf(spu->irq_c0, sizeof (spu->irq_c0), "spe%02d.0",
                          spu->number);
                 ret = request_irq(spu->irqs[0], spu_irq_class_0,
-                                  IRQF_DISABLED,
-                                  spu->irq_c0, spu);
+                                  0, spu->irq_c0, spu);
                 if (ret)
                         goto bail0;
         }
@@ -451,8 +450,7 @@ static int spu_request_irqs(struct spu *spu)
                 snprintf(spu->irq_c1, sizeof (spu->irq_c1), "spe%02d.1",
                          spu->number);
                 ret = request_irq(spu->irqs[1], spu_irq_class_1,
-                                  IRQF_DISABLED,
-                                  spu->irq_c1, spu);
+                                  0, spu->irq_c1, spu);
                 if (ret)
                         goto bail1;
         }
@@ -460,8 +458,7 @@ static int spu_request_irqs(struct spu *spu)
                 snprintf(spu->irq_c2, sizeof (spu->irq_c2), "spe%02d.2",
                          spu->number);
                 ret = request_irq(spu->irqs[2], spu_irq_class_2,
-                                  IRQF_DISABLED,
-                                  spu->irq_c2, spu);
+                                  0, spu->irq_c2, spu);
                 if (ret)
                         goto bail2;
         }
diff --git a/arch/powerpc/platforms/cell/spu_callbacks.c b/arch/powerpc/platforms/cell/spu_callbacks.c
index fec1495e6b12..75d613313f10 100644
--- a/arch/powerpc/platforms/cell/spu_callbacks.c
+++ b/arch/powerpc/platforms/cell/spu_callbacks.c
@@ -5,7 +5,7 @@
 #undef DEBUG
 
 #include <linux/kallsyms.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/syscalls.h>
 
 #include <asm/spu.h>
diff --git a/arch/powerpc/platforms/cell/spu_fault.c b/arch/powerpc/platforms/cell/spu_fault.c
index d06ba87f1a19..641e7273d75a 100644
--- a/arch/powerpc/platforms/cell/spu_fault.c
+++ b/arch/powerpc/platforms/cell/spu_fault.c
@@ -22,7 +22,7 @@
  */
 #include <linux/sched.h>
 #include <linux/mm.h>
-#include <linux/module.h>
+#include <linux/export.h>
 
 #include <asm/spu.h>
 #include <asm/spu_csa.h>
diff --git a/arch/powerpc/platforms/cell/spu_manage.c b/arch/powerpc/platforms/cell/spu_manage.c
index 4e5c91489c02..2bb6977c0a5a 100644
--- a/arch/powerpc/platforms/cell/spu_manage.c
+++ b/arch/powerpc/platforms/cell/spu_manage.c
@@ -21,7 +21,7 @@
 
 #include <linux/interrupt.h>
 #include <linux/list.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/ptrace.h>
 #include <linux/wait.h>
 #include <linux/mm.h>
diff --git a/arch/powerpc/platforms/cell/spu_notify.c b/arch/powerpc/platforms/cell/spu_notify.c
index 34d156959f39..afdf857c318f 100644
--- a/arch/powerpc/platforms/cell/spu_notify.c
+++ b/arch/powerpc/platforms/cell/spu_notify.c
@@ -21,7 +21,8 @@
 
 #undef DEBUG
 
-#include <linux/module.h>
+#include <linux/export.h>
+#include <linux/notifier.h>
 #include <asm/spu.h>
 #include "spufs/spufs.h"
 
diff --git a/arch/powerpc/platforms/cell/spu_priv1_mmio.c b/arch/powerpc/platforms/cell/spu_priv1_mmio.c
index 121aec353f26..66d33724f16e 100644
--- a/arch/powerpc/platforms/cell/spu_priv1_mmio.c
+++ b/arch/powerpc/platforms/cell/spu_priv1_mmio.c
@@ -20,7 +20,6 @@
 
 #include <linux/interrupt.h>
 #include <linux/list.h>
-#include <linux/module.h>
 #include <linux/ptrace.h>
 #include <linux/wait.h>
 #include <linux/mm.h>
diff --git a/arch/powerpc/platforms/cell/spufs/backing_ops.c b/arch/powerpc/platforms/cell/spufs/backing_ops.c
index 64eb15b22040..6e8a9ef8590e 100644
--- a/arch/powerpc/platforms/cell/spufs/backing_ops.c
+++ b/arch/powerpc/platforms/cell/spufs/backing_ops.c
@@ -21,7 +21,6 @@
  * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
-#include <linux/module.h>
 #include <linux/errno.h>
 #include <linux/sched.h>
 #include <linux/kernel.h>
diff --git a/arch/powerpc/platforms/cell/spufs/context.c b/arch/powerpc/platforms/cell/spufs/context.c
index bf4d41d8fa14..9c6790d17eda 100644
--- a/arch/powerpc/platforms/cell/spufs/context.c
+++ b/arch/powerpc/platforms/cell/spufs/context.c
@@ -22,9 +22,9 @@
 
 #include <linux/fs.h>
 #include <linux/mm.h>
-#include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/atomic.h>
+#include <linux/sched.h>
 #include <asm/spu.h>
 #include <asm/spu_csa.h>
 #include "spufs.h"
diff --git a/arch/powerpc/platforms/cell/spufs/coredump.c b/arch/powerpc/platforms/cell/spufs/coredump.c
index 6cf3ec628527..03c5fce2a5b3 100644
--- a/arch/powerpc/platforms/cell/spufs/coredump.c
+++ b/arch/powerpc/platforms/cell/spufs/coredump.c
@@ -26,7 +26,6 @@
 #include <linux/fs.h>
 #include <linux/gfp.h>
 #include <linux/list.h>
-#include <linux/module.h>
 #include <linux/syscalls.h>
 
 #include <asm/uaccess.h>
diff --git a/arch/powerpc/platforms/cell/spufs/fault.c b/arch/powerpc/platforms/cell/spufs/fault.c
index a4dd3ae7223a..8cb6260cc80f 100644
--- a/arch/powerpc/platforms/cell/spufs/fault.c
+++ b/arch/powerpc/platforms/cell/spufs/fault.c
@@ -21,7 +21,6 @@
  */
 #include <linux/sched.h>
 #include <linux/mm.h>
-#include <linux/module.h>
 
 #include <asm/spu.h>
 #include <asm/spu_csa.h>
diff --git a/arch/powerpc/platforms/cell/spufs/file.c b/arch/powerpc/platforms/cell/spufs/file.c
index fb59c46e9e9e..0cfece4cf6ef 100644
--- a/arch/powerpc/platforms/cell/spufs/file.c
+++ b/arch/powerpc/platforms/cell/spufs/file.c
@@ -24,7 +24,7 @@
 
 #include <linux/fs.h>
 #include <linux/ioctl.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/pagemap.h>
 #include <linux/poll.h>
 #include <linux/ptrace.h>
diff --git a/arch/powerpc/platforms/cell/spufs/hw_ops.c b/arch/powerpc/platforms/cell/spufs/hw_ops.c
index 64f8540b832c..8655c4cbefc2 100644
--- a/arch/powerpc/platforms/cell/spufs/hw_ops.c
+++ b/arch/powerpc/platforms/cell/spufs/hw_ops.c
@@ -18,7 +18,6 @@
  * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
-#include <linux/module.h>
 #include <linux/errno.h>
 #include <linux/sched.h>
 #include <linux/kernel.h>
diff --git a/arch/powerpc/platforms/cell/spufs/sched.c b/arch/powerpc/platforms/cell/spufs/sched.c
index 32cb4e66d2cd..965d381abd75 100644
--- a/arch/powerpc/platforms/cell/spufs/sched.c
+++ b/arch/powerpc/platforms/cell/spufs/sched.c
@@ -22,7 +22,6 @@
 
 #undef DEBUG
 
-#include <linux/module.h>
 #include <linux/errno.h>
 #include <linux/sched.h>
 #include <linux/kernel.h>
diff --git a/arch/powerpc/platforms/cell/spufs/switch.c b/arch/powerpc/platforms/cell/spufs/switch.c
index 3df9a36eb2f5..dde35551e744 100644
--- a/arch/powerpc/platforms/cell/spufs/switch.c
+++ b/arch/powerpc/platforms/cell/spufs/switch.c
@@ -32,7 +32,7 @@
  * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/errno.h>
 #include <linux/hardirq.h>
 #include <linux/sched.h>
diff --git a/arch/powerpc/platforms/cell/spufs/syscalls.c b/arch/powerpc/platforms/cell/spufs/syscalls.c
index 609e016e92d0..71a5b5207266 100644
--- a/arch/powerpc/platforms/cell/spufs/syscalls.c
+++ b/arch/powerpc/platforms/cell/spufs/syscalls.c
@@ -1,6 +1,6 @@
 #include <linux/file.h>
 #include <linux/fs.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/mount.h>
 #include <linux/namei.h>
 #include <linux/slab.h>
diff --git a/arch/powerpc/platforms/embedded6xx/Kconfig b/arch/powerpc/platforms/embedded6xx/Kconfig
index 524d971a1478..5a8f50a9afa7 100644
--- a/arch/powerpc/platforms/embedded6xx/Kconfig
+++ b/arch/powerpc/platforms/embedded6xx/Kconfig
@@ -87,10 +87,6 @@ config MV64X60
 config MPC10X_OPENPIC
         bool
 
-config MPC10X_STORE_GATHERING
-        bool "Enable MPC10x store gathering"
-        depends on MPC10X_BRIDGE
-
 config GAMECUBE_COMMON
         bool
 
diff --git a/arch/powerpc/platforms/embedded6xx/holly.c b/arch/powerpc/platforms/embedded6xx/holly.c
index 487bda0d18d8..2e9bcf6444c8 100644
--- a/arch/powerpc/platforms/embedded6xx/holly.c
+++ b/arch/powerpc/platforms/embedded6xx/holly.c
@@ -26,6 +26,7 @@
 #include <linux/tty.h>
 #include <linux/serial_core.h>
 #include <linux/of_platform.h>
+#include <linux/module.h>
 
 #include <asm/system.h>
 #include <asm/time.h>
diff --git a/arch/powerpc/platforms/embedded6xx/mpc7448_hpc2.c b/arch/powerpc/platforms/embedded6xx/mpc7448_hpc2.c
index 1cb907c94359..f8f33e16c6b6 100644
--- a/arch/powerpc/platforms/embedded6xx/mpc7448_hpc2.c
+++ b/arch/powerpc/platforms/embedded6xx/mpc7448_hpc2.c
@@ -23,6 +23,7 @@
 #include <linux/pci.h>
 #include <linux/kdev_t.h>
 #include <linux/console.h>
+#include <linux/module.h>
 #include <linux/delay.h>
 #include <linux/irq.h>
 #include <linux/seq_file.h>
diff --git a/arch/powerpc/platforms/iseries/hvlpconfig.c b/arch/powerpc/platforms/iseries/hvlpconfig.c
index f0475f0b1853..f62a0c5fa670 100644
--- a/arch/powerpc/platforms/iseries/hvlpconfig.c
+++ b/arch/powerpc/platforms/iseries/hvlpconfig.c
@@ -16,7 +16,7 @@
  * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
  */
 
-#include <linux/module.h>
+#include <linux/export.h>
 #include <asm/iseries/hv_lp_config.h>
 #include "it_lp_naca.h"
 
diff --git a/arch/powerpc/platforms/iseries/iommu.c b/arch/powerpc/platforms/iseries/iommu.c
index d8b76335bd13..2f3d9110248c 100644
--- a/arch/powerpc/platforms/iseries/iommu.c
+++ b/arch/powerpc/platforms/iseries/iommu.c
@@ -28,7 +28,7 @@
 #include <linux/dma-mapping.h>
 #include <linux/list.h>
 #include <linux/pci.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/slab.h>
 
 #include <asm/iommu.h>
diff --git a/arch/powerpc/platforms/iseries/ksyms.c b/arch/powerpc/platforms/iseries/ksyms.c
index 2430848b98e7..997e234fb8b7 100644
--- a/arch/powerpc/platforms/iseries/ksyms.c
+++ b/arch/powerpc/platforms/iseries/ksyms.c
@@ -6,7 +6,7 @@
  *      as published by the Free Software Foundation; either version
  *      2 of the License, or (at your option) any later version.
  */
-#include <linux/module.h>
+#include <linux/export.h>
 
 #include <asm/hw_irq.h>
 #include <asm/iseries/hv_call_sc.h>
diff --git a/arch/powerpc/platforms/iseries/lpardata.c b/arch/powerpc/platforms/iseries/lpardata.c
index 98bd2d37038a..00e0ec813a1c 100644
--- a/arch/powerpc/platforms/iseries/lpardata.c
+++ b/arch/powerpc/platforms/iseries/lpardata.c
@@ -8,7 +8,6 @@
  */
 #include <linux/types.h>
 #include <linux/threads.h>
-#include <linux/module.h>
 #include <linux/bitops.h>
 #include <asm/processor.h>
 #include <asm/ptrace.h>
diff --git a/arch/powerpc/platforms/iseries/lpevents.c b/arch/powerpc/platforms/iseries/lpevents.c
index b0f8a857ec02..202e22798d30 100644
--- a/arch/powerpc/platforms/iseries/lpevents.c
+++ b/arch/powerpc/platforms/iseries/lpevents.c
@@ -13,7 +13,7 @@
 #include <linux/bootmem.h>
 #include <linux/seq_file.h>
 #include <linux/proc_fs.h>
-#include <linux/module.h>
+#include <linux/export.h>
 
 #include <asm/system.h>
 #include <asm/paca.h>
diff --git a/arch/powerpc/platforms/iseries/mf.c b/arch/powerpc/platforms/iseries/mf.c
index 62dabe3c2bfa..254c1fc3d8dd 100644
--- a/arch/powerpc/platforms/iseries/mf.c
+++ b/arch/powerpc/platforms/iseries/mf.c
@@ -30,6 +30,7 @@
 #include <linux/init.h>
 #include <linux/completion.h>
 #include <linux/delay.h>
+#include <linux/export.h>
 #include <linux/proc_fs.h>
 #include <linux/dma-mapping.h>
 #include <linux/bcd.h>
diff --git a/arch/powerpc/platforms/iseries/pci.c b/arch/powerpc/platforms/iseries/pci.c
index ab3962b0d246..c75412884625 100644
--- a/arch/powerpc/platforms/iseries/pci.c
+++ b/arch/powerpc/platforms/iseries/pci.c
@@ -29,7 +29,6 @@
 #include <linux/string.h>
 #include <linux/slab.h>
 #include <linux/init.h>
-#include <linux/module.h>
 #include <linux/pci.h>
 #include <linux/of.h>
 #include <linux/ratelimit.h>
diff --git a/arch/powerpc/platforms/iseries/setup.c b/arch/powerpc/platforms/iseries/setup.c
index c25a0815c26b..ea0acbd8966d 100644
--- a/arch/powerpc/platforms/iseries/setup.c
+++ b/arch/powerpc/platforms/iseries/setup.c
@@ -21,6 +21,7 @@
 #include <linux/smp.h>
 #include <linux/param.h>
 #include <linux/string.h>
+#include <linux/export.h>
 #include <linux/seq_file.h>
 #include <linux/kdev_t.h>
 #include <linux/kexec.h>
diff --git a/arch/powerpc/platforms/iseries/smp.c b/arch/powerpc/platforms/iseries/smp.c
index 8bda9be06fa0..7e2a5515ed76 100644
--- a/arch/powerpc/platforms/iseries/smp.c
+++ b/arch/powerpc/platforms/iseries/smp.c
@@ -15,7 +15,6 @@
 #undef DEBUG
 
 #include <linux/kernel.h>
-#include <linux/module.h>
 #include <linux/sched.h>
 #include <linux/smp.h>
 #include <linux/interrupt.h>
diff --git a/arch/powerpc/platforms/iseries/vio.c b/arch/powerpc/platforms/iseries/vio.c
index b6db7cef83b4..04be62d368a6 100644
--- a/arch/powerpc/platforms/iseries/vio.c
+++ b/arch/powerpc/platforms/iseries/vio.c
@@ -25,7 +25,7 @@
 #include <linux/slab.h>
 #include <linux/completion.h>
 #include <linux/proc_fs.h>
-#include <linux/module.h>
+#include <linux/export.h>
 
 #include <asm/firmware.h>
 #include <asm/vio.h>
diff --git a/arch/powerpc/platforms/iseries/viopath.c b/arch/powerpc/platforms/iseries/viopath.c
index 2376069cdc14..40dad0840eb3 100644
--- a/arch/powerpc/platforms/iseries/viopath.c
+++ b/arch/powerpc/platforms/iseries/viopath.c
@@ -27,7 +27,7 @@
  * Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
  *
  */
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/kernel.h>
 #include <linux/slab.h>
 #include <linux/errno.h>
diff --git a/arch/powerpc/platforms/maple/setup.c b/arch/powerpc/platforms/maple/setup.c
index 5b3388b9f911..4c372047c94e 100644
--- a/arch/powerpc/platforms/maple/setup.c
+++ b/arch/powerpc/platforms/maple/setup.c
@@ -17,6 +17,7 @@
 #include <linux/errno.h>
 #include <linux/sched.h>
 #include <linux/kernel.h>
+#include <linux/export.h>
 #include <linux/mm.h>
 #include <linux/stddef.h>
 #include <linux/unistd.h>
diff --git a/arch/powerpc/platforms/pasemi/cpufreq.c b/arch/powerpc/platforms/pasemi/cpufreq.c
index c16537bc0c6e..95d00173029f 100644
--- a/arch/powerpc/platforms/pasemi/cpufreq.c
+++ b/arch/powerpc/platforms/pasemi/cpufreq.c
@@ -27,6 +27,7 @@
 
 #include <linux/cpufreq.h>
 #include <linux/timer.h>
+#include <linux/module.h>
 
 #include <asm/hw_irq.h>
 #include <asm/io.h>
diff --git a/arch/powerpc/platforms/pasemi/dma_lib.c b/arch/powerpc/platforms/pasemi/dma_lib.c
index 756123bf06ac..f3defd8a2806 100644
--- a/arch/powerpc/platforms/pasemi/dma_lib.c
+++ b/arch/powerpc/platforms/pasemi/dma_lib.c
@@ -19,10 +19,11 @@
 
 #include <linux/kernel.h>
 #include <linux/init.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/pci.h>
 #include <linux/slab.h>
 #include <linux/of.h>
+#include <linux/sched.h>
 
 #include <asm/pasemi_dma.h>
 
diff --git a/arch/powerpc/platforms/pasemi/setup.c b/arch/powerpc/platforms/pasemi/setup.c
index 7c858e6f843c..6f3558210554 100644
--- a/arch/powerpc/platforms/pasemi/setup.c
+++ b/arch/powerpc/platforms/pasemi/setup.c
@@ -26,6 +26,7 @@
 #include <linux/kernel.h>
 #include <linux/delay.h>
 #include <linux/console.h>
+#include <linux/export.h>
 #include <linux/pci.h>
 #include <linux/of_platform.h>
 #include <linux/gfp.h>
diff --git a/arch/powerpc/platforms/powermac/backlight.c b/arch/powerpc/platforms/powermac/backlight.c
index c2f3e861f5ea..a00096b1c713 100644
--- a/arch/powerpc/platforms/powermac/backlight.c
+++ b/arch/powerpc/platforms/powermac/backlight.c
@@ -13,6 +13,7 @@
 #include <linux/adb.h>
 #include <linux/pmu.h>
 #include <linux/atomic.h>
+#include <linux/export.h>
 #include <asm/prom.h>
 #include <asm/backlight.h>
 
diff --git a/arch/powerpc/platforms/powermac/feature.c b/arch/powerpc/platforms/powermac/feature.c
index df423993f175..63d82bbc05e9 100644
--- a/arch/powerpc/platforms/powermac/feature.c
+++ b/arch/powerpc/platforms/powermac/feature.c
@@ -27,6 +27,7 @@
 #include <linux/adb.h>
 #include <linux/pmu.h>
 #include <linux/ioport.h>
+#include <linux/export.h>
 #include <linux/pci.h>
 #include <asm/sections.h>
 #include <asm/errno.h>
diff --git a/arch/powerpc/platforms/powermac/low_i2c.c b/arch/powerpc/platforms/powermac/low_i2c.c
index e9c8a607268e..996c5ff7824b 100644
--- a/arch/powerpc/platforms/powermac/low_i2c.c
+++ b/arch/powerpc/platforms/powermac/low_i2c.c
@@ -33,7 +33,7 @@
 #include <linux/types.h>
 #include <linux/sched.h>
 #include <linux/init.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/adb.h>
 #include <linux/pmu.h>
 #include <linux/delay.h>
diff --git a/arch/powerpc/platforms/powermac/nvram.c b/arch/powerpc/platforms/powermac/nvram.c
index 695443bfdb08..54d227127c9f 100644
--- a/arch/powerpc/platforms/powermac/nvram.c
+++ b/arch/powerpc/platforms/powermac/nvram.c
@@ -8,7 +8,7 @@
  *
  *  Todo: - add support for the OF persistent properties
  */
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/kernel.h>
 #include <linux/stddef.h>
 #include <linux/string.h>
diff --git a/arch/powerpc/platforms/powermac/pic.c b/arch/powerpc/platforms/powermac/pic.c
index 7667db448aa7..901bfbddc3dd 100644
--- a/arch/powerpc/platforms/powermac/pic.c
+++ b/arch/powerpc/platforms/powermac/pic.c
@@ -24,7 +24,6 @@
 #include <linux/syscore_ops.h>
 #include <linux/adb.h>
 #include <linux/pmu.h>
-#include <linux/module.h>
 
 #include <asm/sections.h>
 #include <asm/io.h>
@@ -273,7 +272,6 @@ static struct irqaction xmon_action = {
 
 static struct irqaction gatwick_cascade_action = {
         .handler        = gatwick_action,
-        .flags          = IRQF_DISABLED,
         .name           = "cascade",
 };
 
diff --git a/arch/powerpc/platforms/powermac/setup.c b/arch/powerpc/platforms/powermac/setup.c
index a028f08309d6..96580b189ec2 100644
--- a/arch/powerpc/platforms/powermac/setup.c
+++ b/arch/powerpc/platforms/powermac/setup.c
@@ -31,6 +31,7 @@
 #include <linux/stddef.h>
 #include <linux/unistd.h>
 #include <linux/ptrace.h>
+#include <linux/export.h>
 #include <linux/user.h>
 #include <linux/tty.h>
 #include <linux/string.h>
diff --git a/arch/powerpc/platforms/powermac/smp.c b/arch/powerpc/platforms/powermac/smp.c
index 9a521dc8e485..9b6a820bdd7d 100644
--- a/arch/powerpc/platforms/powermac/smp.c
+++ b/arch/powerpc/platforms/powermac/smp.c
@@ -200,7 +200,7 @@ static int psurge_secondary_ipi_init(void)
 
         if (psurge_secondary_virq)
                 rc = request_irq(psurge_secondary_virq, psurge_ipi_intr,
-                        IRQF_DISABLED|IRQF_PERCPU, "IPI", NULL);
+                        IRQF_PERCPU, "IPI", NULL);
 
         if (rc)
                 pr_err("Failed to setup secondary cpu IPI\n");
@@ -408,7 +408,7 @@ static int __init smp_psurge_kick_cpu(int nr)
 
 static struct irqaction psurge_irqaction = {
         .handler = psurge_ipi_intr,
-        .flags = IRQF_DISABLED|IRQF_PERCPU,
+        .flags = IRQF_PERCPU,
         .name = "primary IPI",
 };
 
diff --git a/arch/powerpc/platforms/powernv/Kconfig b/arch/powerpc/platforms/powernv/Kconfig
new file mode 100644
index 000000000000..74fea5c21839
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/Kconfig
@@ -0,0 +1,16 @@
+config PPC_POWERNV
+        depends on PPC64 && PPC_BOOK3S
+        bool "IBM PowerNV (Non-Virtualized) platform support"
+        select PPC_NATIVE
+        select PPC_XICS
+        select PPC_ICP_NATIVE
+        select PPC_P7_NAP
+        select PPC_PCI_CHOICE if EMBEDDED
+        default y
+
+config PPC_POWERNV_RTAS
+        depends on PPC_POWERNV
+        bool "Support for RTAS based PowerNV platforms such as BML"
+        default y
+        select PPC_ICS_RTAS
+        select PPC_RTAS
diff --git a/arch/powerpc/platforms/powernv/Makefile b/arch/powerpc/platforms/powernv/Makefile
new file mode 100644
index 000000000000..31853008b418
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/Makefile
@@ -0,0 +1,5 @@
+obj-y                   += setup.o opal-takeover.o opal-wrappers.o opal.o
+obj-y                   += opal-rtc.o opal-nvram.o
+
+obj-$(CONFIG_SMP)       += smp.o
+obj-$(CONFIG_PCI)       += pci.o pci-p5ioc2.o
diff --git a/arch/powerpc/platforms/powernv/opal-nvram.c b/arch/powerpc/platforms/powernv/opal-nvram.c
new file mode 100644
index 000000000000..3f83e1ae26ac
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/opal-nvram.c
@@ -0,0 +1,88 @@
+/*
+ * PowerNV nvram code.
+ *
+ * Copyright 2011 IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#define DEBUG
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/of.h>
+
+#include <asm/opal.h>
+#include <asm/machdep.h>
+
+static unsigned int nvram_size;
+
+static ssize_t opal_nvram_size(void)
+{
+        return nvram_size;
+}
+
+static ssize_t opal_nvram_read(char *buf, size_t count, loff_t *index)
+{
+        s64 rc;
+        int off;
+
+        if (*index >= nvram_size)
+                return 0;
+        off = *index;
+        if ((off + count) > nvram_size)
+                count = nvram_size - off;
+        rc = opal_read_nvram(__pa(buf), count, off);
+        if (rc != OPAL_SUCCESS)
+                return -EIO;
+        *index += count;
+        return count;
+}
+
+static ssize_t opal_nvram_write(char *buf, size_t count, loff_t *index)
+{
+        s64 rc = OPAL_BUSY;
+        int off;
+
+        if (*index >= nvram_size)
+                return 0;
+        off = *index;
+        if ((off + count) > nvram_size)
+                count = nvram_size - off;
+
+        while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) {
+                rc = opal_write_nvram(__pa(buf), count, off);
+                if (rc == OPAL_BUSY_EVENT)
+                        opal_poll_events(NULL);
+        }
+        *index += count;
+        return count;
+}
+
+void __init opal_nvram_init(void)
+{
+        struct device_node *np;
+        const u32 *nbytes_p;
+
+        np = of_find_compatible_node(NULL, NULL, "ibm,opal-nvram");
+        if (np == NULL)
+                return;
+
+        nbytes_p = of_get_property(np, "#bytes", NULL);
+        if (!nbytes_p) {
+                of_node_put(np);
+                return;
+        }
+        nvram_size = *nbytes_p;
+
+        printk(KERN_INFO "OPAL nvram setup, %u bytes\n", nvram_size);
+        of_node_put(np);
+
+        ppc_md.nvram_read = opal_nvram_read;
+        ppc_md.nvram_write = opal_nvram_write;
+        ppc_md.nvram_size = opal_nvram_size;
+}
+
diff --git a/arch/powerpc/platforms/powernv/opal-rtc.c b/arch/powerpc/platforms/powernv/opal-rtc.c
new file mode 100644
index 000000000000..2aa7641aac9b
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/opal-rtc.c
@@ -0,0 +1,97 @@
+/*
+ * PowerNV Real Time Clock.
+ *
+ * Copyright 2011 IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+
+#include <linux/kernel.h>
+#include <linux/time.h>
+#include <linux/bcd.h>
+#include <linux/rtc.h>
+#include <linux/delay.h>
+
+#include <asm/opal.h>
+#include <asm/firmware.h>
+
+static void opal_to_tm(u32 y_m_d, u64 h_m_s_ms, struct rtc_time *tm)
+{
+        tm->tm_year     = ((bcd2bin(y_m_d >> 24) * 100) +
+                           bcd2bin((y_m_d >> 16) & 0xff)) - 1900;
+        tm->tm_mon      = bcd2bin((y_m_d >> 8) & 0xff) - 1;
+        tm->tm_mday     = bcd2bin(y_m_d & 0xff);
+        tm->tm_hour     = bcd2bin((h_m_s_ms >> 56) & 0xff);
+        tm->tm_min      = bcd2bin((h_m_s_ms >> 48) & 0xff);
+        tm->tm_sec      = bcd2bin((h_m_s_ms >> 40) & 0xff);
+
+        GregorianDay(tm);
+}
+
+unsigned long __init opal_get_boot_time(void)
+{
+        struct rtc_time tm;
+        u32 y_m_d;
+        u64 h_m_s_ms;
+        long rc = OPAL_BUSY;
+
+        while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) {
+                rc = opal_rtc_read(&y_m_d, &h_m_s_ms);
+                if (rc == OPAL_BUSY_EVENT)
+                        opal_poll_events(NULL);
+                else
+                        mdelay(10);
+        }
+        if (rc != OPAL_SUCCESS)
+                return 0;
+        opal_to_tm(y_m_d, h_m_s_ms, &tm);
+        return mktime(tm.tm_year + 1900, tm.tm_mon + 1, tm.tm_mday,
+                      tm.tm_hour, tm.tm_min, tm.tm_sec);
+}
+
+void opal_get_rtc_time(struct rtc_time *tm)
+{
+        long rc = OPAL_BUSY;
+        u32 y_m_d;
+        u64 h_m_s_ms;
+
+        while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) {
+                rc = opal_rtc_read(&y_m_d, &h_m_s_ms);
+                if (rc == OPAL_BUSY_EVENT)
+                        opal_poll_events(NULL);
+                else
+                        mdelay(10);
+        }
+        if (rc != OPAL_SUCCESS)
+                return;
+        opal_to_tm(y_m_d, h_m_s_ms, tm);
+}
+
+int opal_set_rtc_time(struct rtc_time *tm)
+{
+        long rc = OPAL_BUSY;
+        u32 y_m_d = 0;
+        u64 h_m_s_ms = 0;
+
+        y_m_d |= ((u32)bin2bcd((tm->tm_year + 1900) / 100)) << 24;
+        y_m_d |= ((u32)bin2bcd((tm->tm_year + 1900) % 100)) << 16;
+        y_m_d |= ((u32)bin2bcd((tm->tm_mon + 1))) << 8;
+        y_m_d |= ((u32)bin2bcd(tm->tm_mday));
+
+        h_m_s_ms |= ((u64)bin2bcd(tm->tm_hour)) << 56;
+        h_m_s_ms |= ((u64)bin2bcd(tm->tm_min)) << 48;
+        h_m_s_ms |= ((u64)bin2bcd(tm->tm_sec)) << 40;
+
+        while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) {
+                rc = opal_rtc_write(y_m_d, h_m_s_ms);
+                if (rc == OPAL_BUSY_EVENT)
+                        opal_poll_events(NULL);
+                else
+                        mdelay(10);
+        }
+        return rc == OPAL_SUCCESS ? 0 : -EIO;
+}
diff --git a/arch/powerpc/platforms/powernv/opal-takeover.S b/arch/powerpc/platforms/powernv/opal-takeover.S
new file mode 100644
index 000000000000..77b48b2b9309
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/opal-takeover.S
@@ -0,0 +1,140 @@
+/*
+ * PowerNV OPAL takeover assembly code, for use by prom_init.c
+ *
+ * Copyright 2011 IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <asm/ppc_asm.h>
+#include <asm/hvcall.h>
+#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
+
+        .text
+_GLOBAL(opal_query_takeover)
+        mfcr    r0
+        stw     r0,8(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)
+        std     r4,0(r10)
+        ld      r10,STK_PARAM(r4)(r1)
+        std     r5,0(r10)
+        lwz     r0,8(r1)
+        mtcrf   0xff,r0
+        blr
+
+_GLOBAL(opal_do_takeover)
+        mfcr    r0
+        stw     r0,8(r1)
+        mflr    r0
+        std     r0,16(r1)
+        bl      __opal_do_takeover
+        ld      r0,16(r1)
+        mtlr    r0
+        lwz     r0,8(r1)
+        mtcrf   0xff,r0
+        blr
+
+__opal_do_takeover:
+        ld      r4,0(r3)
+        ld      r5,0x8(r3)
+        ld      r6,0x10(r3)
+        ld      r7,0x18(r3)
+        ld      r8,0x20(r3)
+        ld      r9,0x28(r3)
+        ld      r10,0x30(r3)
+        ld      r11,0x38(r3)
+        li      r3,H_HAL_TAKEOVER
+        HVSC
+        blr
+
+        .globl opal_secondary_entry
+opal_secondary_entry:
+        mr      r31,r3
+        mfmsr   r11
+        li      r12,(MSR_SF | MSR_ISF)@highest
+        sldi    r12,r12,48
+        or      r11,r11,r12
+        mtmsrd  r11
+        isync
+        mfspr   r4,SPRN_PIR
+        std     r4,0(r3)
+1:      HMT_LOW
+        ld      r4,8(r3)
+        cmpli   cr0,r4,0
+        beq     1b
+        HMT_MEDIUM
+1:      addi    r3,r31,16
+        bl      __opal_do_takeover
+        b       1b
+
+_GLOBAL(opal_enter_rtas)
+        mflr    r0
+        std     r0,16(r1)
+        stdu    r1,-PROM_FRAME_SIZE(r1) /* Save SP and create stack space */
+
+        /* Because PROM is running in 32b mode, it clobbers the high order half
+         * of all registers that it saves.  We therefore save those registers
+         * PROM might touch to the stack.  (r0, r3-r13 are caller saved)
+        */
+        SAVE_GPR(2, r1)
+        SAVE_GPR(13, r1)
+        SAVE_8GPRS(14, r1)
+        SAVE_10GPRS(22, r1)
+        mfcr    r10
+        mfmsr   r11
+        std     r10,_CCR(r1)
+        std     r11,_MSR(r1)
+
+        /* Get the PROM entrypoint */
+        mtlr    r5
+
+        /* Switch MSR to 32 bits mode
+         */
+        li      r12,1
+        rldicr  r12,r12,MSR_SF_LG,(63-MSR_SF_LG)
+        andc    r11,r11,r12
+        li      r12,1
+        rldicr  r12,r12,MSR_ISF_LG,(63-MSR_ISF_LG)
+        andc    r11,r11,r12
+        mtmsrd  r11
+        isync
+
+        /* Enter RTAS here... */
+        blrl
+
+        /* Just make sure that r1 top 32 bits didn't get
+         * corrupt by OF
+         */
+        rldicl  r1,r1,0,32
+
+        /* Restore the MSR (back to 64 bits) */
+        ld      r0,_MSR(r1)
+        MTMSRD(r0)
+        isync
+
+        /* Restore other registers */
+        REST_GPR(2, r1)
+        REST_GPR(13, r1)
+        REST_8GPRS(14, r1)
+        REST_10GPRS(22, r1)
+        ld      r4,_CCR(r1)
+        mtcr    r4
+
+        addi    r1,r1,PROM_FRAME_SIZE
+        ld      r0,16(r1)
+        mtlr    r0
+        blr
diff --git a/arch/powerpc/platforms/powernv/opal-wrappers.S b/arch/powerpc/platforms/powernv/opal-wrappers.S
new file mode 100644
index 000000000000..4a3f46d8533e
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/opal-wrappers.S
@@ -0,0 +1,101 @@
+/*
+ * PowerNV OPAL API wrappers
+ *
+ * Copyright 2011 IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <asm/ppc_asm.h>
+#include <asm/hvcall.h>
+#include <asm/asm-offsets.h>
+#include <asm/opal.h>
+
+/* TODO:
+ *
+ * - Trace irqs in/off (needs saving/restoring all args, argh...)
+ * - Get r11 feed up by Dave so I can have better register usage
+ */
+#define OPAL_CALL(name, token)          \
+ _GLOBAL(name);                         \
+        mflr    r0;                     \
+        mfcr    r12;                    \
+        std     r0,16(r1);              \
+        std     r12,8(r1);              \
+        std     r1,PACAR1(r13);         \
+        li      r0,0;                   \
+        mfmsr   r12;                    \
+        ori     r0,r0,MSR_EE;           \
+        std     r12,PACASAVEDMSR(r13);  \
+        andc    r12,r12,r0;             \
+        mtmsrd  r12,1;                  \
+        LOAD_REG_ADDR(r0,.opal_return); \
+        mtlr    r0;                     \
+        li      r0,MSR_DR|MSR_IR;       \
+        andc    r12,r12,r0;             \
+        li      r0,token;               \
+        mtspr   SPRN_HSRR1,r12;         \
+        LOAD_REG_ADDR(r11,opal);        \
+        ld      r12,8(r11);             \
+        ld      r2,0(r11);              \
+        mtspr   SPRN_HSRR0,r12;         \
+        hrfid
+
+_STATIC(opal_return)
+        ld      r2,PACATOC(r13);
+        ld      r4,8(r1);
+        ld      r5,16(r1);
+        ld      r6,PACASAVEDMSR(r13);
+        mtspr   SPRN_SRR0,r5;
+        mtspr   SPRN_SRR1,r6;
+        mtcr    r4;
+        rfid
+
+OPAL_CALL(opal_console_write,                   OPAL_CONSOLE_WRITE);
+OPAL_CALL(opal_console_read,                    OPAL_CONSOLE_READ);
+OPAL_CALL(opal_console_write_buffer_space,      OPAL_CONSOLE_WRITE_BUFFER_SPACE);
+OPAL_CALL(opal_rtc_read,                        OPAL_RTC_READ);
+OPAL_CALL(opal_rtc_write,                       OPAL_RTC_WRITE);
+OPAL_CALL(opal_cec_power_down,                  OPAL_CEC_POWER_DOWN);
+OPAL_CALL(opal_cec_reboot,                      OPAL_CEC_REBOOT);
+OPAL_CALL(opal_read_nvram,                      OPAL_READ_NVRAM);
+OPAL_CALL(opal_write_nvram,                     OPAL_WRITE_NVRAM);
+OPAL_CALL(opal_handle_interrupt,                OPAL_HANDLE_INTERRUPT);
+OPAL_CALL(opal_poll_events,                     OPAL_POLL_EVENTS);
+OPAL_CALL(opal_pci_set_hub_tce_memory,          OPAL_PCI_SET_HUB_TCE_MEMORY);
+OPAL_CALL(opal_pci_set_phb_tce_memory,          OPAL_PCI_SET_PHB_TCE_MEMORY);
+OPAL_CALL(opal_pci_config_read_byte,            OPAL_PCI_CONFIG_READ_BYTE);
+OPAL_CALL(opal_pci_config_read_half_word,       OPAL_PCI_CONFIG_READ_HALF_WORD);
+OPAL_CALL(opal_pci_config_read_word,            OPAL_PCI_CONFIG_READ_WORD);
+OPAL_CALL(opal_pci_config_write_byte,           OPAL_PCI_CONFIG_WRITE_BYTE);
+OPAL_CALL(opal_pci_config_write_half_word,      OPAL_PCI_CONFIG_WRITE_HALF_WORD);
+OPAL_CALL(opal_pci_config_write_word,           OPAL_PCI_CONFIG_WRITE_WORD);
+OPAL_CALL(opal_set_xive,                        OPAL_SET_XIVE);
+OPAL_CALL(opal_get_xive,                        OPAL_GET_XIVE);
+OPAL_CALL(opal_register_exception_handler,      OPAL_REGISTER_OPAL_EXCEPTION_HANDLER);
+OPAL_CALL(opal_pci_eeh_freeze_status,           OPAL_PCI_EEH_FREEZE_STATUS);
+OPAL_CALL(opal_pci_eeh_freeze_clear,            OPAL_PCI_EEH_FREEZE_CLEAR);
+OPAL_CALL(opal_pci_shpc,                        OPAL_PCI_SHPC);
+OPAL_CALL(opal_pci_phb_mmio_enable,             OPAL_PCI_PHB_MMIO_ENABLE);
+OPAL_CALL(opal_pci_set_phb_mem_window,          OPAL_PCI_SET_PHB_MEM_WINDOW);
+OPAL_CALL(opal_pci_map_pe_mmio_window,          OPAL_PCI_MAP_PE_MMIO_WINDOW);
+OPAL_CALL(opal_pci_set_phb_table_memory,        OPAL_PCI_SET_PHB_TABLE_MEMORY);
+OPAL_CALL(opal_pci_set_pe,                      OPAL_PCI_SET_PE);
+OPAL_CALL(opal_pci_set_peltv,                   OPAL_PCI_SET_PELTV);
+OPAL_CALL(opal_pci_set_mve,                     OPAL_PCI_SET_MVE);
+OPAL_CALL(opal_pci_set_mve_enable,              OPAL_PCI_SET_MVE_ENABLE);
+OPAL_CALL(opal_pci_get_xive_reissue,            OPAL_PCI_GET_XIVE_REISSUE);
+OPAL_CALL(opal_pci_set_xive_reissue,            OPAL_PCI_SET_XIVE_REISSUE);
+OPAL_CALL(opal_pci_set_xive_pe,                 OPAL_PCI_SET_XIVE_PE);
+OPAL_CALL(opal_get_xive_source,                 OPAL_GET_XIVE_SOURCE);
+OPAL_CALL(opal_get_msi_32,                      OPAL_GET_MSI_32);
+OPAL_CALL(opal_get_msi_64,                      OPAL_GET_MSI_64);
+OPAL_CALL(opal_start_cpu,                       OPAL_START_CPU);
+OPAL_CALL(opal_query_cpu_status,                OPAL_QUERY_CPU_STATUS);
+OPAL_CALL(opal_write_oppanel,                   OPAL_WRITE_OPPANEL);
+OPAL_CALL(opal_pci_map_pe_dma_window,           OPAL_PCI_MAP_PE_DMA_WINDOW);
+OPAL_CALL(opal_pci_map_pe_dma_window_real,      OPAL_PCI_MAP_PE_DMA_WINDOW_REAL);
+OPAL_CALL(opal_pci_reset,                       OPAL_PCI_RESET);
diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c
new file mode 100644
index 000000000000..aaa0dba49471
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/opal.c
@@ -0,0 +1,322 @@
+/*
+ * PowerNV OPAL high level interfaces
+ *
+ * Copyright 2011 IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#undef DEBUG
+
+#include <linux/types.h>
+#include <linux/of.h>
+#include <linux/of_platform.h>
+#include <linux/interrupt.h>
+#include <asm/opal.h>
+#include <asm/firmware.h>
+
+#include "powernv.h"
+
+struct opal {
+        u64 base;
+        u64 entry;
+} opal;
+
+static struct device_node *opal_node;
+static DEFINE_SPINLOCK(opal_write_lock);
+extern u64 opal_mc_secondary_handler[];
+
+int __init early_init_dt_scan_opal(unsigned long node,
+                                   const char *uname, int depth, void *data)
+{
+        const void *basep, *entryp;
+        unsigned long basesz, entrysz;
+        u64 glue;
+
+        if (depth != 1 || strcmp(uname, "ibm,opal") != 0)
+                return 0;
+
+        basep  = of_get_flat_dt_prop(node, "opal-base-address", &basesz);
+        entryp = of_get_flat_dt_prop(node, "opal-entry-address", &entrysz);
+
+        if (!basep || !entryp)
+                return 1;
+
+        opal.base = of_read_number(basep, basesz/4);
+        opal.entry = of_read_number(entryp, entrysz/4);
+
+        pr_debug("OPAL Base  = 0x%llx (basep=%p basesz=%ld)\n",
+                 opal.base, basep, basesz);
+        pr_debug("OPAL Entry = 0x%llx (entryp=%p basesz=%ld)\n",
+                 opal.entry, entryp, entrysz);
+
+        powerpc_firmware_features |= FW_FEATURE_OPAL;
+        if (of_flat_dt_is_compatible(node, "ibm,opal-v2")) {
+                powerpc_firmware_features |= FW_FEATURE_OPALv2;
+                printk("OPAL V2 detected !\n");
+        } else {
+                printk("OPAL V1 detected !\n");
+        }
+
+        /* Hookup some exception handlers. We use the fwnmi area at 0x7000
+         * to provide the glue space to OPAL
+         */
+        glue = 0x7000;
+        opal_register_exception_handler(OPAL_MACHINE_CHECK_HANDLER,
+                                        __pa(opal_mc_secondary_handler[0]),
+                                        glue);
+        glue += 128;
+        opal_register_exception_handler(OPAL_HYPERVISOR_MAINTENANCE_HANDLER,
+                                        0, glue);
+        glue += 128;
+        opal_register_exception_handler(OPAL_SOFTPATCH_HANDLER, 0, glue);
+
+        return 1;
+}
+
+int opal_get_chars(uint32_t vtermno, char *buf, int count)
+{
+        s64 len, rc;
+        u64 evt;
+
+        if (!opal.entry)
+                return -ENODEV;
+        opal_poll_events(&evt);
+        if ((evt & OPAL_EVENT_CONSOLE_INPUT) == 0)
+                return 0;
+        len = count;
+        rc = opal_console_read(vtermno, &len, buf);
+        if (rc == OPAL_SUCCESS)
+                return len;
+        return 0;
+}
+
+int opal_put_chars(uint32_t vtermno, const char *data, int total_len)
+{
+        int written = 0;
+        s64 len, rc;
+        unsigned long flags;
+        u64 evt;
+
+        if (!opal.entry)
+                return -ENODEV;
+
+        /* We want put_chars to be atomic to avoid mangling of hvsi
+         * packets. To do that, we first test for room and return
+         * -EAGAIN if there isn't enough.
+         *
+         * Unfortunately, opal_console_write_buffer_space() doesn't
+         * appear to work on opal v1, so we just assume there is
+         * enough room and be done with it
+         */
+        spin_lock_irqsave(&opal_write_lock, flags);
+        if (firmware_has_feature(FW_FEATURE_OPALv2)) {
+                rc = opal_console_write_buffer_space(vtermno, &len);
+                if (rc || len < total_len) {
+                        spin_unlock_irqrestore(&opal_write_lock, flags);
+                        /* Closed -> drop characters */
+                        if (rc)
+                                return total_len;
+                        opal_poll_events(&evt);
+                        return -EAGAIN;
+                }
+        }
+
+        /* We still try to handle partial completions, though they
+         * should no longer happen.
+         */
+        rc = OPAL_BUSY;
+        while(total_len > 0 && (rc == OPAL_BUSY ||
+                                rc == OPAL_BUSY_EVENT || rc == OPAL_SUCCESS)) {
+                len = total_len;
+                rc = opal_console_write(vtermno, &len, data);
+                if (rc == OPAL_SUCCESS) {
+                        total_len -= len;
+                        data += len;
+                        written += len;
+                }
+                /* This is a bit nasty but we need that for the console to
+                 * flush when there aren't any interrupts. We will clean
+                 * things a bit later to limit that to synchronous path
+                 * such as the kernel console and xmon/udbg
+                 */
+                do
+                        opal_poll_events(&evt);
+                while(rc == OPAL_SUCCESS && (evt & OPAL_EVENT_CONSOLE_OUTPUT));
+        }
+        spin_unlock_irqrestore(&opal_write_lock, flags);
+        return written;
+}
+
+int opal_machine_check(struct pt_regs *regs)
+{
+        struct opal_machine_check_event *opal_evt = get_paca()->opal_mc_evt;
+        struct opal_machine_check_event evt;
+        const char *level, *sevstr, *subtype;
+        static const char *opal_mc_ue_types[] = {
+                "Indeterminate",
+                "Instruction fetch",
+                "Page table walk ifetch",
+                "Load/Store",
+                "Page table walk Load/Store",
+        };
+        static const char *opal_mc_slb_types[] = {
+                "Indeterminate",
+                "Parity",
+                "Multihit",
+        };
+        static const char *opal_mc_erat_types[] = {
+                "Indeterminate",
+                "Parity",
+                "Multihit",
+        };
+        static const char *opal_mc_tlb_types[] = {
+                "Indeterminate",
+                "Parity",
+                "Multihit",
+        };
+
+        /* Copy the event structure and release the original */
+        evt = *opal_evt;
+        opal_evt->in_use = 0;
+
+        /* Print things out */
+        if (evt.version != OpalMCE_V1) {
+                pr_err("Machine Check Exception, Unknown event version %d !\n",
+                       evt.version);
+                return 0;
+        }
+        switch(evt.severity) {
+        case OpalMCE_SEV_NO_ERROR:
+                level = KERN_INFO;
+                sevstr = "Harmless";
+                break;
+        case OpalMCE_SEV_WARNING:
+                level = KERN_WARNING;
+                sevstr = "";
+                break;
+        case OpalMCE_SEV_ERROR_SYNC:
+                level = KERN_ERR;
+                sevstr = "Severe";
+                break;
+        case OpalMCE_SEV_FATAL:
+        default:
+                level = KERN_ERR;
+                sevstr = "Fatal";
+                break;
+        }
+
+        printk("%s%s Machine check interrupt [%s]\n", level, sevstr,
+               evt.disposition == OpalMCE_DISPOSITION_RECOVERED ?
+               "Recovered" : "[Not recovered");
+        printk("%s  Initiator: %s\n", level,
+               evt.initiator == OpalMCE_INITIATOR_CPU ? "CPU" : "Unknown");
+        switch(evt.error_type) {
+        case OpalMCE_ERROR_TYPE_UE:
+                subtype = evt.u.ue_error.ue_error_type <
+                        ARRAY_SIZE(opal_mc_ue_types) ?
+                        opal_mc_ue_types[evt.u.ue_error.ue_error_type]
+                        : "Unknown";
+                printk("%s  Error type: UE [%s]\n", level, subtype);
+                if (evt.u.ue_error.effective_address_provided)
+                        printk("%s    Effective address: %016llx\n",
+                               level, evt.u.ue_error.effective_address);
+                if (evt.u.ue_error.physical_address_provided)
+                        printk("%s      Physial address: %016llx\n",
+                               level, evt.u.ue_error.physical_address);
+                break;
+        case OpalMCE_ERROR_TYPE_SLB:
+                subtype = evt.u.slb_error.slb_error_type <
+                        ARRAY_SIZE(opal_mc_slb_types) ?
+                        opal_mc_slb_types[evt.u.slb_error.slb_error_type]
+                        : "Unknown";
+                printk("%s  Error type: SLB [%s]\n", level, subtype);
+                if (evt.u.slb_error.effective_address_provided)
+                        printk("%s    Effective address: %016llx\n",
+                               level, evt.u.slb_error.effective_address);
+                break;
+        case OpalMCE_ERROR_TYPE_ERAT:
+                subtype = evt.u.erat_error.erat_error_type <
+                        ARRAY_SIZE(opal_mc_erat_types) ?
+                        opal_mc_erat_types[evt.u.erat_error.erat_error_type]
+                        : "Unknown";
+                printk("%s  Error type: ERAT [%s]\n", level, subtype);
+                if (evt.u.erat_error.effective_address_provided)
+                        printk("%s    Effective address: %016llx\n",
+                               level, evt.u.erat_error.effective_address);
+                break;
+        case OpalMCE_ERROR_TYPE_TLB:
+                subtype = evt.u.tlb_error.tlb_error_type <
+                        ARRAY_SIZE(opal_mc_tlb_types) ?
+                        opal_mc_tlb_types[evt.u.tlb_error.tlb_error_type]
+                        : "Unknown";
+                printk("%s  Error type: TLB [%s]\n", level, subtype);
+                if (evt.u.tlb_error.effective_address_provided)
+                        printk("%s    Effective address: %016llx\n",
+                               level, evt.u.tlb_error.effective_address);
+                break;
+        default:
+        case OpalMCE_ERROR_TYPE_UNKNOWN:
+                printk("%s  Error type: Unknown\n", level);
+                break;
+        }
+        return evt.severity == OpalMCE_SEV_FATAL ? 0 : 1;
+}
+
+static irqreturn_t opal_interrupt(int irq, void *data)
+{
+        uint64_t events;
+
+        opal_handle_interrupt(virq_to_hw(irq), &events);
+
+        /* XXX TODO: Do something with the events */
+
+        return IRQ_HANDLED;
+}
+
+static int __init opal_init(void)
+{
+        struct device_node *np, *consoles;
+        const u32 *irqs;
+        int rc, i, irqlen;
+
+        opal_node = of_find_node_by_path("/ibm,opal");
+        if (!opal_node) {
+                pr_warn("opal: Node not found\n");
+                return -ENODEV;
+        }
+        if (firmware_has_feature(FW_FEATURE_OPALv2))
+                consoles = of_find_node_by_path("/ibm,opal/consoles");
+        else
+                consoles = of_node_get(opal_node);
+
+        /* Register serial ports */
+        for_each_child_of_node(consoles, np) {
+                if (strcmp(np->name, "serial"))
+                        continue;
+                of_platform_device_create(np, NULL, NULL);
+        }
+        of_node_put(consoles);
+
+        /* Find all OPAL interrupts and request them */
+        irqs = of_get_property(opal_node, "opal-interrupts", &irqlen);
+        pr_debug("opal: Found %d interrupts reserved for OPAL\n",
+                 irqs ? (irqlen / 4) : 0);
+        for (i = 0; irqs && i < (irqlen / 4); i++, irqs++) {
+                unsigned int hwirq = be32_to_cpup(irqs);
+                unsigned int irq = irq_create_mapping(NULL, hwirq);
+                if (irq == NO_IRQ) {
+                        pr_warning("opal: Failed to map irq 0x%x\n", hwirq);
+                        continue;
+                }
+                rc = request_irq(irq, opal_interrupt, 0, "opal", NULL);
+                if (rc)
+                        pr_warning("opal: Error %d requesting irq %d"
+                                   " (0x%x)\n", rc, irq, hwirq);
+        }
+        return 0;
+}
+subsys_initcall(opal_init);
diff --git a/arch/powerpc/platforms/powernv/pci-p5ioc2.c b/arch/powerpc/platforms/powernv/pci-p5ioc2.c
new file mode 100644
index 000000000000..4c80f7c77d56
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/pci-p5ioc2.c
@@ -0,0 +1,234 @@
+/*
+ * Support PCI/PCIe on PowerNV platforms
+ *
+ * Currently supports only P5IOC2
+ *
+ * Copyright 2011 Benjamin Herrenschmidt, IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/pci.h>
+#include <linux/delay.h>
+#include <linux/string.h>
+#include <linux/init.h>
+#include <linux/bootmem.h>
+#include <linux/irq.h>
+#include <linux/io.h>
+#include <linux/msi.h>
+
+#include <asm/sections.h>
+#include <asm/io.h>
+#include <asm/prom.h>
+#include <asm/pci-bridge.h>
+#include <asm/machdep.h>
+#include <asm/ppc-pci.h>
+#include <asm/opal.h>
+#include <asm/iommu.h>
+#include <asm/tce.h>
+#include <asm/abs_addr.h>
+
+#include "powernv.h"
+#include "pci.h"
+
+/* For now, use a fixed amount of TCE memory for each p5ioc2
+ * hub, 16M will do
+ */
+#define P5IOC2_TCE_MEMORY       0x01000000
+
+#ifdef CONFIG_PCI_MSI
+static int pnv_pci_p5ioc2_msi_setup(struct pnv_phb *phb, struct pci_dev *dev,
+                                    unsigned int hwirq, unsigned int is_64,
+                                    struct msi_msg *msg)
+{
+        if (WARN_ON(!is_64))
+                return -ENXIO;
+        msg->data = hwirq - phb->msi_base;
+        msg->address_hi = 0x10000000;
+        msg->address_lo = 0;
+
+        return 0;
+}
+
+static void pnv_pci_init_p5ioc2_msis(struct pnv_phb *phb)
+{
+        unsigned int bmap_size;
+        const __be32 *prop = of_get_property(phb->hose->dn,
+                                             "ibm,opal-msi-ranges", NULL);
+        if (!prop)
+                return;
+
+        /* Don't do MSI's on p5ioc2 PCI-X are they are not properly
+         * verified in HW
+         */
+        if (of_device_is_compatible(phb->hose->dn, "ibm,p5ioc2-pcix"))
+                return;
+        phb->msi_base = be32_to_cpup(prop);
+        phb->msi_count = be32_to_cpup(prop + 1);
+        bmap_size = BITS_TO_LONGS(phb->msi_count) * sizeof(unsigned long);
+        phb->msi_map = zalloc_maybe_bootmem(bmap_size, GFP_KERNEL);
+        if (!phb->msi_map) {
+                pr_err("PCI %d: Failed to allocate MSI bitmap !\n",
+                       phb->hose->global_number);
+                return;
+        }
+        phb->msi_setup = pnv_pci_p5ioc2_msi_setup;
+        phb->msi32_support = 0;
+        pr_info(" Allocated bitmap for %d MSIs (base IRQ 0x%x)\n",
+                phb->msi_count, phb->msi_base);
+}
+#else
+static void pnv_pci_init_p5ioc2_msis(struct pnv_phb *phb) { }
+#endif /* CONFIG_PCI_MSI */
+
+static void __devinit pnv_pci_p5ioc2_dma_dev_setup(struct pnv_phb *phb,
+                                                   struct pci_dev *pdev)
+{
+        if (phb->p5ioc2.iommu_table.it_map == NULL)
+                iommu_init_table(&phb->p5ioc2.iommu_table, phb->hose->node);
+
+        set_iommu_table_base(&pdev->dev, &phb->p5ioc2.iommu_table);
+}
+
+static void __init pnv_pci_init_p5ioc2_phb(struct device_node *np,
+                                           void *tce_mem, u64 tce_size)
+{
+        struct pnv_phb *phb;
+        const u64 *prop64;
+        u64 phb_id;
+        int64_t rc;
+        static int primary = 1;
+
+        pr_info(" Initializing p5ioc2 PHB %s\n", np->full_name);
+
+        prop64 = of_get_property(np, "ibm,opal-phbid", NULL);
+        if (!prop64) {
+                pr_err("  Missing \"ibm,opal-phbid\" property !\n");
+                return;
+        }
+        phb_id = be64_to_cpup(prop64);
+        pr_devel("  PHB-ID  : 0x%016llx\n", phb_id);
+        pr_devel("  TCE AT  : 0x%016lx\n", __pa(tce_mem));
+        pr_devel("  TCE SZ  : 0x%016llx\n", tce_size);
+
+        rc = opal_pci_set_phb_tce_memory(phb_id, __pa(tce_mem), tce_size);
+        if (rc != OPAL_SUCCESS) {
+                pr_err("  Failed to set TCE memory, OPAL error %lld\n", rc);
+                return;
+        }
+
+        phb = alloc_bootmem(sizeof(struct pnv_phb));
+        if (phb) {
+                memset(phb, 0, sizeof(struct pnv_phb));
+                phb->hose = pcibios_alloc_controller(np);
+        }
+        if (!phb || !phb->hose) {
+                pr_err("  Failed to allocate PCI controller\n");
+                return;
+        }
+
+        spin_lock_init(&phb->lock);
+        phb->hose->first_busno = 0;
+        phb->hose->last_busno = 0xff;
+        phb->hose->private_data = phb;
+        phb->opal_id = phb_id;
+        phb->type = PNV_PHB_P5IOC2;
+
+        phb->regs = of_iomap(np, 0);
+
+        if (phb->regs == NULL)
+                pr_err("  Failed to map registers !\n");
+        else {
+                pr_devel("  P_BUID     = 0x%08x\n", in_be32(phb->regs + 0x100));
+                pr_devel("  P_IOSZ     = 0x%08x\n", in_be32(phb->regs + 0x1b0));
+                pr_devel("  P_IO_ST    = 0x%08x\n", in_be32(phb->regs + 0x1e0));
+                pr_devel("  P_MEM1_H   = 0x%08x\n", in_be32(phb->regs + 0x1a0));
+                pr_devel("  P_MEM1_L   = 0x%08x\n", in_be32(phb->regs + 0x190));
+                pr_devel("  P_MSZ1_L   = 0x%08x\n", in_be32(phb->regs + 0x1c0));
+                pr_devel("  P_MEM_ST   = 0x%08x\n", in_be32(phb->regs + 0x1d0));
+                pr_devel("  P_MEM2_H   = 0x%08x\n", in_be32(phb->regs + 0x2c0));
+                pr_devel("  P_MEM2_L   = 0x%08x\n", in_be32(phb->regs + 0x2b0));
+                pr_devel("  P_MSZ2_H   = 0x%08x\n", in_be32(phb->regs + 0x2d0));
+                pr_devel("  P_MSZ2_L   = 0x%08x\n", in_be32(phb->regs + 0x2e0));
+        }
+
+        /* Interpret the "ranges" property */
+        /* This also maps the I/O region and sets isa_io/mem_base */
+        pci_process_bridge_OF_ranges(phb->hose, np, primary);
+        primary = 0;
+
+        phb->hose->ops = &pnv_pci_ops;
+
+        /* Setup MSI support */
+        pnv_pci_init_p5ioc2_msis(phb);
+
+        /* Setup TCEs */
+        phb->dma_dev_setup = pnv_pci_p5ioc2_dma_dev_setup;
+        pnv_pci_setup_iommu_table(&phb->p5ioc2.iommu_table,
+                                  tce_mem, tce_size, 0);
+}
+
+void __init pnv_pci_init_p5ioc2_hub(struct device_node *np)
+{
+        struct device_node *phbn;
+        const u64 *prop64;
+        u64 hub_id;
+        void *tce_mem;
+        uint64_t tce_per_phb;
+        int64_t rc;
+        int phb_count = 0;
+
+        pr_info("Probing p5ioc2 IO-Hub %s\n", np->full_name);
+
+        prop64 = of_get_property(np, "ibm,opal-hubid", NULL);
+        if (!prop64) {
+                pr_err(" Missing \"ibm,opal-hubid\" property !\n");
+                return;
+        }
+        hub_id = be64_to_cpup(prop64);
+        pr_info(" HUB-ID : 0x%016llx\n", hub_id);
+
+        /* Currently allocate 16M of TCE memory for every Hub
+         *
+         * XXX TODO: Make it chip local if possible
+         */
+        tce_mem = __alloc_bootmem(P5IOC2_TCE_MEMORY, P5IOC2_TCE_MEMORY,
+                                  __pa(MAX_DMA_ADDRESS));
+        if (!tce_mem) {
+                pr_err(" Failed to allocate TCE Memory !\n");
+                return;
+        }
+        pr_debug(" TCE    : 0x%016lx..0x%016lx\n",
+                __pa(tce_mem), __pa(tce_mem) + P5IOC2_TCE_MEMORY - 1);
+        rc = opal_pci_set_hub_tce_memory(hub_id, __pa(tce_mem),
+                                        P5IOC2_TCE_MEMORY);
+        if (rc != OPAL_SUCCESS) {
+                pr_err(" Failed to allocate TCE memory, OPAL error %lld\n", rc);
+                return;
+        }
+
+        /* Count child PHBs */
+        for_each_child_of_node(np, phbn) {
+                if (of_device_is_compatible(phbn, "ibm,p5ioc2-pcix") ||
+                    of_device_is_compatible(phbn, "ibm,p5ioc2-pciex"))
+                        phb_count++;
+        }
+
+        /* Calculate how much TCE space we can give per PHB */
+        tce_per_phb = __rounddown_pow_of_two(P5IOC2_TCE_MEMORY / phb_count);
+        pr_info(" Allocating %lld MB of TCE memory per PHB\n",
+                tce_per_phb >> 20);
+
+        /* Initialize PHBs */
+        for_each_child_of_node(np, phbn) {
+                if (of_device_is_compatible(phbn, "ibm,p5ioc2-pcix") ||
+                    of_device_is_compatible(phbn, "ibm,p5ioc2-pciex")) {
+                        pnv_pci_init_p5ioc2_phb(phbn, tce_mem, tce_per_phb);
+                        tce_mem += tce_per_phb;
+                }
+        }
+}
diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c
new file mode 100644
index 000000000000..85bb66d7f933
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/pci.c
@@ -0,0 +1,427 @@
+/*
+ * Support PCI/PCIe on PowerNV platforms
+ *
+ * Currently supports only P5IOC2
+ *
+ * Copyright 2011 Benjamin Herrenschmidt, IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/pci.h>
+#include <linux/delay.h>
+#include <linux/string.h>
+#include <linux/init.h>
+#include <linux/bootmem.h>
+#include <linux/irq.h>
+#include <linux/io.h>
+#include <linux/msi.h>
+
+#include <asm/sections.h>
+#include <asm/io.h>
+#include <asm/prom.h>
+#include <asm/pci-bridge.h>
+#include <asm/machdep.h>
+#include <asm/ppc-pci.h>
+#include <asm/opal.h>
+#include <asm/iommu.h>
+#include <asm/tce.h>
+#include <asm/abs_addr.h>
+
+#include "powernv.h"
+#include "pci.h"
+
+/* Delay in usec */
+#define PCI_RESET_DELAY_US      3000000
+
+#define cfg_dbg(fmt...) do { } while(0)
+//#define cfg_dbg(fmt...)       printk(fmt)
+
+#ifdef CONFIG_PCI_MSI
+static int pnv_msi_check_device(struct pci_dev* pdev, int nvec, int type)
+{
+        struct pci_controller *hose = pci_bus_to_host(pdev->bus);
+        struct pnv_phb *phb = hose->private_data;
+
+        return (phb && phb->msi_map) ? 0 : -ENODEV;
+}
+
+static unsigned int pnv_get_one_msi(struct pnv_phb *phb)
+{
+        unsigned int id;
+
+        spin_lock(&phb->lock);
+        id = find_next_zero_bit(phb->msi_map, phb->msi_count, phb->msi_next);
+        if (id >= phb->msi_count && phb->msi_next)
+                id = find_next_zero_bit(phb->msi_map, phb->msi_count, 0);
+        if (id >= phb->msi_count) {
+                spin_unlock(&phb->lock);
+                return 0;
+        }
+        __set_bit(id, phb->msi_map);
+        spin_unlock(&phb->lock);
+        return id + phb->msi_base;
+}
+
+static void pnv_put_msi(struct pnv_phb *phb, unsigned int hwirq)
+{
+        unsigned int id;
+
+        if (WARN_ON(hwirq < phb->msi_base ||
+                    hwirq >= (phb->msi_base + phb->msi_count)))
+                return;
+        id = hwirq - phb->msi_base;
+        spin_lock(&phb->lock);
+        __clear_bit(id, phb->msi_map);
+        spin_unlock(&phb->lock);
+}
+
+static int pnv_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
+{
+        struct pci_controller *hose = pci_bus_to_host(pdev->bus);
+        struct pnv_phb *phb = hose->private_data;
+        struct msi_desc *entry;
+        struct msi_msg msg;
+        unsigned int hwirq, virq;
+        int rc;
+
+        if (WARN_ON(!phb))
+                return -ENODEV;
+
+        list_for_each_entry(entry, &pdev->msi_list, list) {
+                if (!entry->msi_attrib.is_64 && !phb->msi32_support) {
+                        pr_warn("%s: Supports only 64-bit MSIs\n",
+                                pci_name(pdev));
+                        return -ENXIO;
+                }
+                hwirq = pnv_get_one_msi(phb);
+                if (!hwirq) {
+                        pr_warn("%s: Failed to find a free MSI\n",
+                                pci_name(pdev));
+                        return -ENOSPC;
+                }
+                virq = irq_create_mapping(NULL, hwirq);
+                if (virq == NO_IRQ) {
+                        pr_warn("%s: Failed to map MSI to linux irq\n",
+                                pci_name(pdev));
+                        pnv_put_msi(phb, hwirq);
+                        return -ENOMEM;
+                }
+                rc = phb->msi_setup(phb, pdev, hwirq, entry->msi_attrib.is_64,
+                                    &msg);
+                if (rc) {
+                        pr_warn("%s: Failed to setup MSI\n", pci_name(pdev));
+                        irq_dispose_mapping(virq);
+                        pnv_put_msi(phb, hwirq);
+                        return rc;
+                }
+                irq_set_msi_desc(virq, entry);
+                write_msi_msg(virq, &msg);
+        }
+        return 0;
+}
+
+static void pnv_teardown_msi_irqs(struct pci_dev *pdev)
+{
+        struct pci_controller *hose = pci_bus_to_host(pdev->bus);
+        struct pnv_phb *phb = hose->private_data;
+        struct msi_desc *entry;
+
+        if (WARN_ON(!phb))
+                return;
+
+        list_for_each_entry(entry, &pdev->msi_list, list) {
+                if (entry->irq == NO_IRQ)
+                        continue;
+                irq_set_msi_desc(entry->irq, NULL);
+                pnv_put_msi(phb, virq_to_hw(entry->irq));
+                irq_dispose_mapping(entry->irq);
+        }
+}
+#endif /* CONFIG_PCI_MSI */
+
+static void pnv_pci_config_check_eeh(struct pnv_phb *phb, struct pci_bus *bus,
+                                     u32 bdfn)
+{
+        s64     rc;
+        u8      fstate;
+        u16     pcierr;
+        u32     pe_no;
+
+        /* Get PE# if we support IODA */
+        pe_no = phb->bdfn_to_pe ? phb->bdfn_to_pe(phb, bus, bdfn & 0xff) : 0;
+
+        /* Read freeze status */
+        rc = opal_pci_eeh_freeze_status(phb->opal_id, pe_no, &fstate, &pcierr,
+                                        NULL);
+        if (rc) {
+                pr_warning("PCI %d: Failed to read EEH status for PE#%d,"
+                           " err %lld\n", phb->hose->global_number, pe_no, rc);
+                return;
+        }
+        cfg_dbg(" -> EEH check, bdfn=%04x PE%d fstate=%x\n",
+                bdfn, pe_no, fstate);
+        if (fstate != 0) {
+                rc = opal_pci_eeh_freeze_clear(phb->opal_id, pe_no,
+                                              OPAL_EEH_ACTION_CLEAR_FREEZE_ALL);
+                if (rc) {
+                        pr_warning("PCI %d: Failed to clear EEH freeze state"
+                                   " for PE#%d, err %lld\n",
+                                   phb->hose->global_number, pe_no, rc);
+                }
+        }
+}
+
+static int pnv_pci_read_config(struct pci_bus *bus,
+                               unsigned int devfn,
+                               int where, int size, u32 *val)
+{
+        struct pci_controller *hose = pci_bus_to_host(bus);
+        struct pnv_phb *phb = hose->private_data;
+        u32 bdfn = (((uint64_t)bus->number) << 8) | devfn;
+        s64 rc;
+
+        if (hose == NULL)
+                return PCIBIOS_DEVICE_NOT_FOUND;
+
+        switch (size) {
+        case 1: {
+                u8 v8;
+                rc = opal_pci_config_read_byte(phb->opal_id, bdfn, where, &v8);
+                *val = (rc == OPAL_SUCCESS) ? v8 : 0xff;
+                break;
+        }
+        case 2: {
+                u16 v16;
+                rc = opal_pci_config_read_half_word(phb->opal_id, bdfn, where,
+                                                   &v16);
+                *val = (rc == OPAL_SUCCESS) ? v16 : 0xffff;
+                break;
+        }
+        case 4: {
+                u32 v32;
+                rc = opal_pci_config_read_word(phb->opal_id, bdfn, where, &v32);
+                *val = (rc == OPAL_SUCCESS) ? v32 : 0xffffffff;
+                break;
+        }
+        default:
+                return PCIBIOS_FUNC_NOT_SUPPORTED;
+        }
+        cfg_dbg("pnv_pci_read_config bus: %x devfn: %x +%x/%x -> %08x\n",
+                bus->number, devfn, where, size, *val);
+
+        /* Check if the PHB got frozen due to an error (no response) */
+        pnv_pci_config_check_eeh(phb, bus, bdfn);
+
+        return PCIBIOS_SUCCESSFUL;
+}
+
+static int pnv_pci_write_config(struct pci_bus *bus,
+                                unsigned int devfn,
+                                int where, int size, u32 val)
+{
+        struct pci_controller *hose = pci_bus_to_host(bus);
+        struct pnv_phb *phb = hose->private_data;
+        u32 bdfn = (((uint64_t)bus->number) << 8) | devfn;
+
+        if (hose == NULL)
+                return PCIBIOS_DEVICE_NOT_FOUND;
+
+        cfg_dbg("pnv_pci_write_config bus: %x devfn: %x +%x/%x -> %08x\n",
+                bus->number, devfn, where, size, val);
+        switch (size) {
+        case 1:
+                opal_pci_config_write_byte(phb->opal_id, bdfn, where, val);
+                break;
+        case 2:
+                opal_pci_config_write_half_word(phb->opal_id, bdfn, where, val);
+                break;
+        case 4:
+                opal_pci_config_write_word(phb->opal_id, bdfn, where, val);
+                break;
+        default:
+                return PCIBIOS_FUNC_NOT_SUPPORTED;
+        }
+        /* Check if the PHB got frozen due to an error (no response) */
+        pnv_pci_config_check_eeh(phb, bus, bdfn);
+
+        return PCIBIOS_SUCCESSFUL;
+}
+
+struct pci_ops pnv_pci_ops = {
+        .read = pnv_pci_read_config,
+        .write = pnv_pci_write_config,
+};
+
+static int pnv_tce_build(struct iommu_table *tbl, long index, long npages,
+                         unsigned long uaddr, enum dma_data_direction direction,
+                         struct dma_attrs *attrs)
+{
+        u64 proto_tce;
+        u64 *tcep;
+        u64 rpn;
+
+        proto_tce = TCE_PCI_READ; // Read allowed
+
+        if (direction != DMA_TO_DEVICE)
+                proto_tce |= TCE_PCI_WRITE;
+
+        tcep = ((u64 *)tbl->it_base) + index;
+
+        while (npages--) {
+                /* can't move this out since we might cross LMB boundary */
+                rpn = (virt_to_abs(uaddr)) >> TCE_SHIFT;
+                *tcep = proto_tce | (rpn & TCE_RPN_MASK) << TCE_RPN_SHIFT;
+
+                uaddr += TCE_PAGE_SIZE;
+                tcep++;
+        }
+        return 0;
+}
+
+static void pnv_tce_free(struct iommu_table *tbl, long index, long npages)
+{
+        u64 *tcep = ((u64 *)tbl->it_base) + index;
+
+        while (npages--)
+                *(tcep++) = 0;
+}
+
+void pnv_pci_setup_iommu_table(struct iommu_table *tbl,
+                               void *tce_mem, u64 tce_size,
+                               u64 dma_offset)
+{
+        tbl->it_blocksize = 16;
+        tbl->it_base = (unsigned long)tce_mem;
+        tbl->it_offset = dma_offset >> IOMMU_PAGE_SHIFT;
+        tbl->it_index = 0;
+        tbl->it_size = tce_size >> 3;
+        tbl->it_busno = 0;
+        tbl->it_type = TCE_PCI;
+}
+
+static struct iommu_table * __devinit
+pnv_pci_setup_bml_iommu(struct pci_controller *hose)
+{
+        struct iommu_table *tbl;
+        const __be64 *basep;
+        const __be32 *sizep;
+
+        basep = of_get_property(hose->dn, "linux,tce-base", NULL);
+        sizep = of_get_property(hose->dn, "linux,tce-size", NULL);
+        if (basep == NULL || sizep == NULL) {
+                pr_err("PCI: %s has missing tce entries !\n", hose->dn->full_name);
+                return NULL;
+        }
+        tbl = kzalloc_node(sizeof(struct iommu_table), GFP_KERNEL, hose->node);
+        if (WARN_ON(!tbl))
+                return NULL;
+        pnv_pci_setup_iommu_table(tbl, __va(be64_to_cpup(basep)),
+                                  be32_to_cpup(sizep), 0);
+        iommu_init_table(tbl, hose->node);
+        return tbl;
+}
+
+static void __devinit pnv_pci_dma_fallback_setup(struct pci_controller *hose,
+                                                 struct pci_dev *pdev)
+{
+        struct device_node *np = pci_bus_to_OF_node(hose->bus);
+        struct pci_dn *pdn;
+
+        if (np == NULL)
+                return;
+        pdn = PCI_DN(np);
+        if (!pdn->iommu_table)
+                pdn->iommu_table = pnv_pci_setup_bml_iommu(hose);
+        if (!pdn->iommu_table)
+                return;
+        set_iommu_table_base(&pdev->dev, pdn->iommu_table);
+}
+
+static void __devinit pnv_pci_dma_dev_setup(struct pci_dev *pdev)
+{
+        struct pci_controller *hose = pci_bus_to_host(pdev->bus);
+        struct pnv_phb *phb = hose->private_data;
+
+        /* If we have no phb structure, try to setup a fallback based on
+         * the device-tree (RTAS PCI for example)
+         */
+        if (phb && phb->dma_dev_setup)
+                phb->dma_dev_setup(phb, pdev);
+        else
+                pnv_pci_dma_fallback_setup(hose, pdev);
+}
+
+static int pnv_pci_probe_mode(struct pci_bus *bus)
+{
+        struct pci_controller *hose = pci_bus_to_host(bus);
+        const __be64 *tstamp;
+        u64 now, target;
+
+
+        /* We hijack this as a way to ensure we have waited long
+         * enough since the reset was lifted on the PCI bus
+         */
+        if (bus != hose->bus)
+                return PCI_PROBE_NORMAL;
+        tstamp = of_get_property(hose->dn, "reset-clear-timestamp", NULL);
+        if (!tstamp || !*tstamp)
+                return PCI_PROBE_NORMAL;
+
+        now = mftb() / tb_ticks_per_usec;
+        target = (be64_to_cpup(tstamp) / tb_ticks_per_usec)
+                + PCI_RESET_DELAY_US;
+
+        pr_devel("pci %04d: Reset target: 0x%llx now: 0x%llx\n",
+                 hose->global_number, target, now);
+
+        if (now < target)
+                msleep((target - now + 999) / 1000);
+
+        return PCI_PROBE_NORMAL;
+}
+
+void __init pnv_pci_init(void)
+{
+        struct device_node *np;
+
+        pci_set_flags(PCI_CAN_SKIP_ISA_ALIGN);
+
+        /* We do not want to just probe */
+        pci_probe_only = 0;
+
+        /* OPAL absent, try POPAL first then RTAS detection of PHBs */
+        if (!firmware_has_feature(FW_FEATURE_OPAL)) {
+#ifdef CONFIG_PPC_POWERNV_RTAS
+                init_pci_config_tokens();
+                find_and_init_phbs();
+#endif /* CONFIG_PPC_POWERNV_RTAS */
+        } else {
+                /* OPAL is here, do our normal stuff */
+
+                /* Look for p5ioc2 IO-Hubs */
+                for_each_compatible_node(np, NULL, "ibm,p5ioc2")
+                        pnv_pci_init_p5ioc2_hub(np);
+        }
+
+        /* Setup the linkage between OF nodes and PHBs */
+        pci_devs_phb_init();
+
+        /* Configure IOMMU DMA hooks */
+        ppc_md.pci_dma_dev_setup = pnv_pci_dma_dev_setup;
+        ppc_md.tce_build = pnv_tce_build;
+        ppc_md.tce_free = pnv_tce_free;
+        ppc_md.pci_probe_mode = pnv_pci_probe_mode;
+        set_pci_dma_ops(&dma_iommu_ops);
+
+        /* Configure MSIs */
+#ifdef CONFIG_PCI_MSI
+        ppc_md.msi_check_device = pnv_msi_check_device;
+        ppc_md.setup_msi_irqs = pnv_setup_msi_irqs;
+        ppc_md.teardown_msi_irqs = pnv_teardown_msi_irqs;
+#endif
+}
diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h
new file mode 100644
index 000000000000..d4dbc4950936
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/pci.h
@@ -0,0 +1,48 @@
+#ifndef __POWERNV_PCI_H
+#define __POWERNV_PCI_H
+
+struct pci_dn;
+
+enum pnv_phb_type {
+        PNV_PHB_P5IOC2,
+        PNV_PHB_IODA1,
+        PNV_PHB_IODA2,
+};
+
+struct pnv_phb {
+        struct pci_controller   *hose;
+        enum pnv_phb_type       type;
+        u64                     opal_id;
+        void __iomem            *regs;
+        spinlock_t              lock;
+
+#ifdef CONFIG_PCI_MSI
+        unsigned long           *msi_map;
+        unsigned int            msi_base;
+        unsigned int            msi_count;
+        unsigned int            msi_next;
+        unsigned int            msi32_support;
+#endif
+        int (*msi_setup)(struct pnv_phb *phb, struct pci_dev *dev,
+                         unsigned int hwirq, unsigned int is_64,
+                         struct msi_msg *msg);
+        void (*dma_dev_setup)(struct pnv_phb *phb, struct pci_dev *pdev);
+        void (*fixup_phb)(struct pci_controller *hose);
+        u32 (*bdfn_to_pe)(struct pnv_phb *phb, struct pci_bus *bus, u32 devfn);
+
+        union {
+                struct {
+                        struct iommu_table iommu_table;
+                } p5ioc2;
+        };
+};
+
+extern struct pci_ops pnv_pci_ops;
+
+extern void pnv_pci_setup_iommu_table(struct iommu_table *tbl,
+                                      void *tce_mem, u64 tce_size,
+                                      u64 dma_offset);
+extern void pnv_pci_init_p5ioc2_hub(struct device_node *np);
+
+
+#endif /* __POWERNV_PCI_H */
diff --git a/arch/powerpc/platforms/powernv/powernv.h b/arch/powerpc/platforms/powernv/powernv.h
new file mode 100644
index 000000000000..8a9df7f9667e
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/powernv.h
@@ -0,0 +1,16 @@
+#ifndef _POWERNV_H
+#define _POWERNV_H
+
+#ifdef CONFIG_SMP
+extern void pnv_smp_init(void);
+#else
+static inline void pnv_smp_init(void) { }
+#endif
+
+#ifdef CONFIG_PCI
+extern void pnv_pci_init(void);
+#else
+static inline void pnv_pci_init(void) { }
+#endif
+
+#endif /* _POWERNV_H */
diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c
new file mode 100644
index 000000000000..467bd4ac6824
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/setup.c
@@ -0,0 +1,196 @@
+/*
+ * PowerNV setup code.
+ *
+ * Copyright 2011 IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#undef DEBUG
+
+#include <linux/cpu.h>
+#include <linux/errno.h>
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/tty.h>
+#include <linux/reboot.h>
+#include <linux/init.h>
+#include <linux/console.h>
+#include <linux/delay.h>
+#include <linux/irq.h>
+#include <linux/seq_file.h>
+#include <linux/of.h>
+#include <linux/interrupt.h>
+#include <linux/bug.h>
+
+#include <asm/machdep.h>
+#include <asm/firmware.h>
+#include <asm/xics.h>
+#include <asm/rtas.h>
+#include <asm/opal.h>
+#include <asm/xics.h>
+
+#include "powernv.h"
+
+static void __init pnv_setup_arch(void)
+{
+        /* Initialize SMP */
+        pnv_smp_init();
+
+        /* Setup PCI */
+        pnv_pci_init();
+
+        /* Setup RTC and NVRAM callbacks */
+        if (firmware_has_feature(FW_FEATURE_OPAL))
+                opal_nvram_init();
+
+        /* Enable NAP mode */
+        powersave_nap = 1;
+
+        /* XXX PMCS */
+}
+
+static void __init pnv_init_early(void)
+{
+#ifdef CONFIG_HVC_OPAL
+        if (firmware_has_feature(FW_FEATURE_OPAL))
+                hvc_opal_init_early();
+        else
+#endif
+                add_preferred_console("hvc", 0, NULL);
+}
+
+static void __init pnv_init_IRQ(void)
+{
+        xics_init();
+
+        WARN_ON(!ppc_md.get_irq);
+}
+
+static void pnv_show_cpuinfo(struct seq_file *m)
+{
+        struct device_node *root;
+        const char *model = "";
+
+        root = of_find_node_by_path("/");
+        if (root)
+                model = of_get_property(root, "model", NULL);
+        seq_printf(m, "machine\t\t: PowerNV %s\n", model);
+        if (firmware_has_feature(FW_FEATURE_OPALv2))
+                seq_printf(m, "firmware\t: OPAL v2\n");
+        else if (firmware_has_feature(FW_FEATURE_OPAL))
+                seq_printf(m, "firmware\t: OPAL v1\n");
+        else
+                seq_printf(m, "firmware\t: BML\n");
+        of_node_put(root);
+}
+
+static void  __noreturn pnv_restart(char *cmd)
+{
+        long rc = OPAL_BUSY;
+
+        while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) {
+                rc = opal_cec_reboot();
+                if (rc == OPAL_BUSY_EVENT)
+                        opal_poll_events(NULL);
+                else
+                        mdelay(10);
+        }
+        for (;;)
+                opal_poll_events(NULL);
+}
+
+static void __noreturn pnv_power_off(void)
+{
+        long rc = OPAL_BUSY;
+
+        while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) {
+                rc = opal_cec_power_down(0);
+                if (rc == OPAL_BUSY_EVENT)
+                        opal_poll_events(NULL);
+                else
+                        mdelay(10);
+        }
+        for (;;)
+                opal_poll_events(NULL);
+}
+
+static void __noreturn pnv_halt(void)
+{
+        pnv_power_off();
+}
+
+static void pnv_progress(char *s, unsigned short hex)
+{
+}
+
+#ifdef CONFIG_KEXEC
+static void pnv_kexec_cpu_down(int crash_shutdown, int secondary)
+{
+        xics_kexec_teardown_cpu(secondary);
+}
+#endif /* CONFIG_KEXEC */
+
+static void __init pnv_setup_machdep_opal(void)
+{
+        ppc_md.get_boot_time = opal_get_boot_time;
+        ppc_md.get_rtc_time = opal_get_rtc_time;
+        ppc_md.set_rtc_time = opal_set_rtc_time;
+        ppc_md.restart = pnv_restart;
+        ppc_md.power_off = pnv_power_off;
+        ppc_md.halt = pnv_halt;
+        ppc_md.machine_check_exception = opal_machine_check;
+}
+
+#ifdef CONFIG_PPC_POWERNV_RTAS
+static void __init pnv_setup_machdep_rtas(void)
+{
+        if (rtas_token("get-time-of-day") != RTAS_UNKNOWN_SERVICE) {
+                ppc_md.get_boot_time = rtas_get_boot_time;
+                ppc_md.get_rtc_time = rtas_get_rtc_time;
+                ppc_md.set_rtc_time = rtas_set_rtc_time;
+        }
+        ppc_md.restart = rtas_restart;
+        ppc_md.power_off = rtas_power_off;
+        ppc_md.halt = rtas_halt;
+}
+#endif /* CONFIG_PPC_POWERNV_RTAS */
+
+static int __init pnv_probe(void)
+{
+        unsigned long root = of_get_flat_dt_root();
+
+        if (!of_flat_dt_is_compatible(root, "ibm,powernv"))
+                return 0;
+
+        hpte_init_native();
+
+        if (firmware_has_feature(FW_FEATURE_OPAL))
+                pnv_setup_machdep_opal();
+#ifdef CONFIG_PPC_POWERNV_RTAS
+        else if (rtas.base)
+                pnv_setup_machdep_rtas();
+#endif /* CONFIG_PPC_POWERNV_RTAS */
+
+        pr_debug("PowerNV detected !\n");
+
+        return 1;
+}
+
+define_machine(powernv) {
+        .name                   = "PowerNV",
+        .probe                  = pnv_probe,
+        .init_early             = pnv_init_early,
+        .setup_arch             = pnv_setup_arch,
+        .init_IRQ               = pnv_init_IRQ,
+        .show_cpuinfo           = pnv_show_cpuinfo,
+        .progress               = pnv_progress,
+        .power_save             = power7_idle,
+        .calibrate_decr         = generic_calibrate_decr,
+#ifdef CONFIG_KEXEC
+        .kexec_cpu_down         = pnv_kexec_cpu_down,
+#endif
+};
diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c
new file mode 100644
index 000000000000..e87736685243
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/smp.c
@@ -0,0 +1,182 @@
+/*
+ * SMP support for PowerNV machines.
+ *
+ * Copyright 2011 IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/sched.h>
+#include <linux/smp.h>
+#include <linux/interrupt.h>
+#include <linux/delay.h>
+#include <linux/init.h>
+#include <linux/spinlock.h>
+#include <linux/cpu.h>
+
+#include <asm/irq.h>
+#include <asm/smp.h>
+#include <asm/paca.h>
+#include <asm/machdep.h>
+#include <asm/cputable.h>
+#include <asm/firmware.h>
+#include <asm/system.h>
+#include <asm/rtas.h>
+#include <asm/vdso_datapage.h>
+#include <asm/cputhreads.h>
+#include <asm/xics.h>
+#include <asm/opal.h>
+
+#include "powernv.h"
+
+#ifdef DEBUG
+#include <asm/udbg.h>
+#define DBG(fmt...) udbg_printf(fmt)
+#else
+#define DBG(fmt...)
+#endif
+
+static void __cpuinit pnv_smp_setup_cpu(int cpu)
+{
+        if (cpu != boot_cpuid)
+                xics_setup_cpu();
+}
+
+static int pnv_smp_cpu_bootable(unsigned int nr)
+{
+        /* Special case - we inhibit secondary thread startup
+         * during boot if the user requests it.
+         */
+        if (system_state < SYSTEM_RUNNING && cpu_has_feature(CPU_FTR_SMT)) {
+                if (!smt_enabled_at_boot && cpu_thread_in_core(nr) != 0)
+                        return 0;
+                if (smt_enabled_at_boot
+                    && cpu_thread_in_core(nr) >= smt_enabled_at_boot)
+                        return 0;
+        }
+
+        return 1;
+}
+
+int __devinit pnv_smp_kick_cpu(int nr)
+{
+        unsigned int pcpu = get_hard_smp_processor_id(nr);
+        unsigned long start_here = __pa(*((unsigned long *)
+                                          generic_secondary_smp_init));
+        long rc;
+
+        BUG_ON(nr < 0 || nr >= NR_CPUS);
+
+        /* On OPAL v2 the CPU are still spinning inside OPAL itself,
+         * get them back now
+         */
+        if (firmware_has_feature(FW_FEATURE_OPALv2)) {
+                pr_devel("OPAL: Starting CPU %d (HW 0x%x)...\n", nr, pcpu);
+                rc = opal_start_cpu(pcpu, start_here);
+                if (rc != OPAL_SUCCESS)
+                        pr_warn("OPAL Error %ld starting CPU %d\n",
+                                rc, nr);
+        }
+        return smp_generic_kick_cpu(nr);
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+
+static int pnv_smp_cpu_disable(void)
+{
+        int cpu = smp_processor_id();
+
+        /* This is identical to pSeries... might consolidate by
+         * moving migrate_irqs_away to a ppc_md with default to
+         * the generic fixup_irqs. --BenH.
+         */
+        set_cpu_online(cpu, false);
+        vdso_data->processorCount--;
+        if (cpu == boot_cpuid)
+                boot_cpuid = cpumask_any(cpu_online_mask);
+        xics_migrate_irqs_away();
+        return 0;
+}
+
+static void pnv_smp_cpu_kill_self(void)
+{
+        unsigned int cpu;
+
+        /* If powersave_nap is enabled, use NAP mode, else just
+         * spin aimlessly
+         */
+        if (!powersave_nap) {
+                generic_mach_cpu_die();
+                return;
+        }
+
+        /* Standard hot unplug procedure */
+        local_irq_disable();
+        idle_task_exit();
+        current->active_mm = NULL; /* for sanity */
+        cpu = smp_processor_id();
+        DBG("CPU%d offline\n", cpu);
+        generic_set_cpu_dead(cpu);
+        smp_wmb();
+
+        /* We don't want to take decrementer interrupts while we are offline,
+         * so clear LPCR:PECE1. We keep PECE2 enabled.
+         */
+        mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) & ~(u64)LPCR_PECE1);
+        while (!generic_check_cpu_restart(cpu)) {
+                power7_idle();
+                if (!generic_check_cpu_restart(cpu)) {
+                        DBG("CPU%d Unexpected exit while offline !\n", cpu);
+                        /* We may be getting an IPI, so we re-enable
+                         * interrupts to process it, it will be ignored
+                         * since we aren't online (hopefully)
+                         */
+                        local_irq_enable();
+                        local_irq_disable();
+                }
+        }
+        mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) | LPCR_PECE1);
+        DBG("CPU%d coming online...\n", cpu);
+}
+
+#endif /* CONFIG_HOTPLUG_CPU */
+
+static struct smp_ops_t pnv_smp_ops = {
+        .message_pass   = smp_muxed_ipi_message_pass,
+        .cause_ipi      = NULL, /* Filled at runtime by xics_smp_probe() */
+        .probe          = xics_smp_probe,
+        .kick_cpu       = pnv_smp_kick_cpu,
+        .setup_cpu      = pnv_smp_setup_cpu,
+        .cpu_bootable   = pnv_smp_cpu_bootable,
+#ifdef CONFIG_HOTPLUG_CPU
+        .cpu_disable    = pnv_smp_cpu_disable,
+        .cpu_die        = generic_cpu_die,
+#endif /* CONFIG_HOTPLUG_CPU */
+};
+
+/* This is called very early during platform setup_arch */
+void __init pnv_smp_init(void)
+{
+        smp_ops = &pnv_smp_ops;
+
+        /* XXX We don't yet have a proper entry point from HAL, for
+         * now we rely on kexec-style entry from BML
+         */
+
+#ifdef CONFIG_PPC_RTAS
+        /* Non-lpar has additional take/give timebase */
+        if (rtas_token("freeze-time-base") != RTAS_UNKNOWN_SERVICE) {
+                smp_ops->give_timebase = rtas_give_timebase;
+                smp_ops->take_timebase = rtas_take_timebase;
+        }
+#endif /* CONFIG_PPC_RTAS */
+
+#ifdef CONFIG_HOTPLUG_CPU
+        ppc_md.cpu_die  = pnv_smp_cpu_kill_self;
+#endif
+}
diff --git a/arch/powerpc/platforms/prep/Kconfig b/arch/powerpc/platforms/prep/Kconfig
index f0536c7cda9f..1547f66235d9 100644
--- a/arch/powerpc/platforms/prep/Kconfig
+++ b/arch/powerpc/platforms/prep/Kconfig
@@ -21,12 +21,3 @@ config PREP_RESIDUAL
           or pass the 'noresidual' option to the kernel.
 
           If you are running a PReP system, say Y here, otherwise say N.
-
-config PROC_PREPRESIDUAL
-        bool "Support for reading of PReP Residual Data in /proc"
-        depends on PREP_RESIDUAL && PROC_FS
-        help
-          Enabling this option will create a /proc/residual file which allows
-          you to get at the residual data on PReP systems.  You will need a tool
-          (lsresidual) to parse it.  If you aren't on a PReP system, you don't
-          want this.
diff --git a/arch/powerpc/platforms/ps3/Kconfig b/arch/powerpc/platforms/ps3/Kconfig
index dfe316b161a9..476d9d9b2405 100644
--- a/arch/powerpc/platforms/ps3/Kconfig
+++ b/arch/powerpc/platforms/ps3/Kconfig
@@ -148,4 +148,16 @@ config PS3_LPM
           profiling support of the Cell processor with programs like
           oprofile and perfmon2, then say Y or M, otherwise say N.
 
+config PS3GELIC_UDBG
+        bool "PS3 udbg output via UDP broadcasts on Ethernet"
+        depends on PPC_PS3
+        help
+          Enables udbg early debugging output by sending broadcast UDP
+          via the Ethernet port (UDP port number 18194).
+
+          This driver uses a trivial implementation and is independent
+          from the main network driver.
+
+          If in doubt, say N here.
+
 endmenu
diff --git a/arch/powerpc/platforms/ps3/Makefile b/arch/powerpc/platforms/ps3/Makefile
index ac1bdf844eca..02b9e636dab7 100644
--- a/arch/powerpc/platforms/ps3/Makefile
+++ b/arch/powerpc/platforms/ps3/Makefile
@@ -2,6 +2,7 @@ obj-y += setup.o mm.o time.o hvcall.o htab.o repository.o
 obj-y += interrupt.o exports.o os-area.o
 obj-y += system-bus.o
 
+obj-$(CONFIG_PS3GELIC_UDBG) += gelic_udbg.o
 obj-$(CONFIG_SMP) += smp.o
 obj-$(CONFIG_SPU_BASE) += spu.o
 obj-y += device-init.o
diff --git a/arch/powerpc/platforms/ps3/device-init.c b/arch/powerpc/platforms/ps3/device-init.c
index 6c4b5837fc8a..3f175e8aedb4 100644
--- a/arch/powerpc/platforms/ps3/device-init.c
+++ b/arch/powerpc/platforms/ps3/device-init.c
@@ -825,7 +825,7 @@ static int ps3_probe_thread(void *data)
 
         spin_lock_init(&dev.lock);
 
-        res = request_irq(irq, ps3_notification_interrupt, IRQF_DISABLED,
+        res = request_irq(irq, ps3_notification_interrupt, 0,
                           "ps3_notification", &dev);
         if (res) {
                 pr_err("%s:%u: request_irq failed %d\n", __func__, __LINE__,
diff --git a/arch/powerpc/platforms/ps3/exports.c b/arch/powerpc/platforms/ps3/exports.c
index a7e8ffd24a65..7df5b7d8fc66 100644
--- a/arch/powerpc/platforms/ps3/exports.c
+++ b/arch/powerpc/platforms/ps3/exports.c
@@ -18,8 +18,6 @@
  *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
 
-#include <linux/module.h>
-
 #define LV1_CALL(name, in, out, num)                          \
   extern s64 _lv1_##name(LV1_##in##_IN_##out##_OUT_ARG_DECL); \
   EXPORT_SYMBOL(_lv1_##name);
diff --git a/arch/powerpc/platforms/ps3/gelic_udbg.c b/arch/powerpc/platforms/ps3/gelic_udbg.c
new file mode 100644
index 000000000000..20b46a19a48f
--- /dev/null
+++ b/arch/powerpc/platforms/ps3/gelic_udbg.c
@@ -0,0 +1,273 @@
+/*
+ * udbg debug output routine via GELIC UDP broadcasts
+ *
+ * Copyright (C) 2007 Sony Computer Entertainment Inc.
+ * Copyright 2006, 2007 Sony Corporation
+ * Copyright (C) 2010 Hector Martin <hector@marcansoft.com>
+ * Copyright (C) 2011 Andre Heider <a.heider@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version 2
+ * of the License, or (at your option) any later version.
+ *
+ */
+
+#include <asm/io.h>
+#include <asm/udbg.h>
+#include <asm/lv1call.h>
+
+#define GELIC_BUS_ID 1
+#define GELIC_DEVICE_ID 0
+#define GELIC_DEBUG_PORT 18194
+#define GELIC_MAX_MESSAGE_SIZE 1000
+
+#define GELIC_LV1_GET_MAC_ADDRESS 1
+#define GELIC_LV1_GET_VLAN_ID 4
+#define GELIC_LV1_VLAN_TX_ETHERNET_0 2
+
+#define GELIC_DESCR_DMA_STAT_MASK 0xf0000000
+#define GELIC_DESCR_DMA_CARDOWNED 0xa0000000
+
+#define GELIC_DESCR_TX_DMA_IKE 0x00080000
+#define GELIC_DESCR_TX_DMA_NO_CHKSUM 0x00000000
+#define GELIC_DESCR_TX_DMA_FRAME_TAIL 0x00040000
+
+#define GELIC_DESCR_DMA_CMD_NO_CHKSUM (GELIC_DESCR_DMA_CARDOWNED | \
+                                       GELIC_DESCR_TX_DMA_IKE | \
+                                       GELIC_DESCR_TX_DMA_NO_CHKSUM)
+
+static u64 bus_addr;
+
+struct gelic_descr {
+        /* as defined by the hardware */
+        __be32 buf_addr;
+        __be32 buf_size;
+        __be32 next_descr_addr;
+        __be32 dmac_cmd_status;
+        __be32 result_size;
+        __be32 valid_size;      /* all zeroes for tx */
+        __be32 data_status;
+        __be32 data_error;      /* all zeroes for tx */
+} __attribute__((aligned(32)));
+
+struct debug_block {
+        struct gelic_descr descr;
+        u8 pkt[1520];
+} __packed;
+
+struct ethhdr {
+        u8 dest[6];
+        u8 src[6];
+        u16 type;
+} __packed;
+
+struct vlantag {
+        u16 vlan;
+        u16 subtype;
+} __packed;
+
+struct iphdr {
+        u8 ver_len;
+        u8 dscp_ecn;
+        u16 total_length;
+        u16 ident;
+        u16 frag_off_flags;
+        u8 ttl;
+        u8 proto;
+        u16 checksum;
+        u32 src;
+        u32 dest;
+} __packed;
+
+struct udphdr {
+        u16 src;
+        u16 dest;
+        u16 len;
+        u16 checksum;
+} __packed;
+
+static __iomem struct ethhdr *h_eth;
+static __iomem struct vlantag *h_vlan;
+static __iomem struct iphdr *h_ip;
+static __iomem struct udphdr *h_udp;
+
+static __iomem char *pmsg;
+static __iomem char *pmsgc;
+
+static __iomem struct debug_block dbg __attribute__((aligned(32)));
+
+static int header_size;
+
+static void map_dma_mem(int bus_id, int dev_id, void *start, size_t len,
+                        u64 *real_bus_addr)
+{
+        s64 result;
+        u64 real_addr = ((u64)start) & 0x0fffffffffffffffUL;
+        u64 real_end = real_addr + len;
+        u64 map_start = real_addr & ~0xfff;
+        u64 map_end = (real_end + 0xfff) & ~0xfff;
+        u64 bus_addr = 0;
+
+        u64 flags = 0xf800000000000000UL;
+
+        result = lv1_allocate_device_dma_region(bus_id, dev_id,
+                                                map_end - map_start, 12, 0,
+                                                &bus_addr);
+        if (result)
+                lv1_panic(0);
+
+        result = lv1_map_device_dma_region(bus_id, dev_id, map_start,
+                                           bus_addr, map_end - map_start,
+                                           flags);
+        if (result)
+                lv1_panic(0);
+
+        *real_bus_addr = bus_addr + real_addr - map_start;
+}
+
+static int unmap_dma_mem(int bus_id, int dev_id, u64 bus_addr, size_t len)
+{
+        s64 result;
+        u64 real_bus_addr;
+
+        real_bus_addr = bus_addr & ~0xfff;
+        len += bus_addr - real_bus_addr;
+        len = (len + 0xfff) & ~0xfff;
+
+        result = lv1_unmap_device_dma_region(bus_id, dev_id, real_bus_addr,
+                                             len);
+        if (result)
+                return result;
+
+        return lv1_free_device_dma_region(bus_id, dev_id, real_bus_addr);
+}
+
+static void gelic_debug_init(void)
+{
+        s64 result;
+        u64 v2;
+        u64 mac;
+        u64 vlan_id;
+
+        result = lv1_open_device(GELIC_BUS_ID, GELIC_DEVICE_ID, 0);
+        if (result)
+                lv1_panic(0);
+
+        map_dma_mem(GELIC_BUS_ID, GELIC_DEVICE_ID, &dbg, sizeof(dbg),
+                    &bus_addr);
+
+        memset(&dbg, 0, sizeof(dbg));
+
+        dbg.descr.buf_addr = bus_addr + offsetof(struct debug_block, pkt);
+
+        wmb();
+
+        result = lv1_net_control(GELIC_BUS_ID, GELIC_DEVICE_ID,
+                                 GELIC_LV1_GET_MAC_ADDRESS, 0, 0, 0,
+                                 &mac, &v2);
+        if (result)
+                lv1_panic(0);
+
+        mac <<= 16;
+
+        h_eth = (struct ethhdr *)dbg.pkt;
+
+        memset(&h_eth->dest, 0xff, 6);
+        memcpy(&h_eth->src, &mac, 6);
+
+        header_size = sizeof(struct ethhdr);
+
+        result = lv1_net_control(GELIC_BUS_ID, GELIC_DEVICE_ID,
+                                 GELIC_LV1_GET_VLAN_ID,
+                                 GELIC_LV1_VLAN_TX_ETHERNET_0, 0, 0,
+                                 &vlan_id, &v2);
+        if (!result) {
+                h_eth->type = 0x8100;
+
+                header_size += sizeof(struct vlantag);
+                h_vlan = (struct vlantag *)(h_eth + 1);
+                h_vlan->vlan = vlan_id;
+                h_vlan->subtype = 0x0800;
+                h_ip = (struct iphdr *)(h_vlan + 1);
+        } else {
+                h_eth->type = 0x0800;
+                h_ip = (struct iphdr *)(h_eth + 1);
+        }
+
+        header_size += sizeof(struct iphdr);
+        h_ip->ver_len = 0x45;
+        h_ip->ttl = 10;
+        h_ip->proto = 0x11;
+        h_ip->src = 0x00000000;
+        h_ip->dest = 0xffffffff;
+
+        header_size += sizeof(struct udphdr);
+        h_udp = (struct udphdr *)(h_ip + 1);
+        h_udp->src = GELIC_DEBUG_PORT;
+        h_udp->dest = GELIC_DEBUG_PORT;
+
+        pmsgc = pmsg = (char *)(h_udp + 1);
+}
+
+static void gelic_debug_shutdown(void)
+{
+        if (bus_addr)
+                unmap_dma_mem(GELIC_BUS_ID, GELIC_DEVICE_ID,
+                              bus_addr, sizeof(dbg));
+        lv1_close_device(GELIC_BUS_ID, GELIC_DEVICE_ID);
+}
+
+static void gelic_sendbuf(int msgsize)
+{
+        u16 *p;
+        u32 sum;
+        int i;
+
+        dbg.descr.buf_size = header_size + msgsize;
+        h_ip->total_length = msgsize + sizeof(struct udphdr) +
+                             sizeof(struct iphdr);
+        h_udp->len = msgsize + sizeof(struct udphdr);
+
+        h_ip->checksum = 0;
+        sum = 0;
+        p = (u16 *)h_ip;
+        for (i = 0; i < 5; i++)
+                sum += *p++;
+        h_ip->checksum = ~(sum + (sum >> 16));
+
+        dbg.descr.dmac_cmd_status = GELIC_DESCR_DMA_CMD_NO_CHKSUM |
+                                    GELIC_DESCR_TX_DMA_FRAME_TAIL;
+        dbg.descr.result_size = 0;
+        dbg.descr.data_status = 0;
+
+        wmb();
+
+        lv1_net_start_tx_dma(GELIC_BUS_ID, GELIC_DEVICE_ID, bus_addr, 0);
+
+        while ((dbg.descr.dmac_cmd_status & GELIC_DESCR_DMA_STAT_MASK) ==
+               GELIC_DESCR_DMA_CARDOWNED)
+                cpu_relax();
+}
+
+static void ps3gelic_udbg_putc(char ch)
+{
+        *pmsgc++ = ch;
+        if (ch == '\n' || (pmsgc-pmsg) >= GELIC_MAX_MESSAGE_SIZE) {
+                gelic_sendbuf(pmsgc-pmsg);
+                pmsgc = pmsg;
+        }
+}
+
+void __init udbg_init_ps3gelic(void)
+{
+        gelic_debug_init();
+        udbg_putc = ps3gelic_udbg_putc;
+}
+
+void udbg_shutdown_ps3gelic(void)
+{
+        udbg_putc = NULL;
+        gelic_debug_shutdown();
+}
+EXPORT_SYMBOL(udbg_shutdown_ps3gelic);
diff --git a/arch/powerpc/platforms/ps3/interrupt.c b/arch/powerpc/platforms/ps3/interrupt.c
index 600ed2c0ed59..404bc52b7806 100644
--- a/arch/powerpc/platforms/ps3/interrupt.c
+++ b/arch/powerpc/platforms/ps3/interrupt.c
@@ -19,7 +19,7 @@
  */
 
 #include <linux/kernel.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/irq.h>
 
 #include <asm/machdep.h>
diff --git a/arch/powerpc/platforms/ps3/mm.c b/arch/powerpc/platforms/ps3/mm.c
index c2045880e674..72714ad27842 100644
--- a/arch/powerpc/platforms/ps3/mm.c
+++ b/arch/powerpc/platforms/ps3/mm.c
@@ -19,7 +19,7 @@
  */
 
 #include <linux/kernel.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/memory_hotplug.h>
 #include <linux/memblock.h>
 #include <linux/slab.h>
diff --git a/arch/powerpc/platforms/ps3/os-area.c b/arch/powerpc/platforms/ps3/os-area.c
index 5b759b669598..56d26bc4fd41 100644
--- a/arch/powerpc/platforms/ps3/os-area.c
+++ b/arch/powerpc/platforms/ps3/os-area.c
@@ -23,6 +23,7 @@
 #include <linux/workqueue.h>
 #include <linux/fs.h>
 #include <linux/syscalls.h>
+#include <linux/export.h>
 #include <linux/ctype.h>
 #include <linux/memblock.h>
 #include <linux/of.h>
diff --git a/arch/powerpc/platforms/ps3/repository.c b/arch/powerpc/platforms/ps3/repository.c
index 5e304c292f68..ca40f6afd35d 100644
--- a/arch/powerpc/platforms/ps3/repository.c
+++ b/arch/powerpc/platforms/ps3/repository.c
@@ -184,7 +184,7 @@ int ps3_repository_read_bus_type(unsigned int bus_index,
         enum ps3_bus_type *bus_type)
 {
         int result;
-        u64 v1;
+        u64 v1 = 0;
 
         result = read_node(PS3_LPAR_ID_PME,
                 make_first_field("bus", bus_index),
@@ -199,7 +199,7 @@ int ps3_repository_read_bus_num_dev(unsigned int bus_index,
         unsigned int *num_dev)
 {
         int result;
-        u64 v1;
+        u64 v1 = 0;
 
         result = read_node(PS3_LPAR_ID_PME,
                 make_first_field("bus", bus_index),
@@ -239,7 +239,7 @@ int ps3_repository_read_dev_type(unsigned int bus_index,
         unsigned int dev_index, enum ps3_dev_type *dev_type)
 {
         int result;
-        u64 v1;
+        u64 v1 = 0;
 
         result = read_node(PS3_LPAR_ID_PME,
                 make_first_field("bus", bus_index),
@@ -256,8 +256,8 @@ int ps3_repository_read_dev_intr(unsigned int bus_index,
         enum ps3_interrupt_type *intr_type, unsigned int *interrupt_id)
 {
         int result;
-        u64 v1;
-        u64 v2;
+        u64 v1 = 0;
+        u64 v2 = 0;
 
         result = read_node(PS3_LPAR_ID_PME,
                 make_first_field("bus", bus_index),
@@ -275,7 +275,7 @@ int ps3_repository_read_dev_reg_type(unsigned int bus_index,
         enum ps3_reg_type *reg_type)
 {
         int result;
-        u64 v1;
+        u64 v1 = 0;
 
         result = read_node(PS3_LPAR_ID_PME,
                 make_first_field("bus", bus_index),
@@ -615,7 +615,7 @@ int ps3_repository_read_stor_dev_num_regions(unsigned int bus_index,
         unsigned int dev_index, unsigned int *num_regions)
 {
         int result;
-        u64 v1;
+        u64 v1 = 0;
 
         result = read_node(PS3_LPAR_ID_PME,
                 make_first_field("bus", bus_index),
@@ -631,7 +631,7 @@ int ps3_repository_read_stor_dev_region_id(unsigned int bus_index,
         unsigned int *region_id)
 {
         int result;
-        u64 v1;
+        u64 v1 = 0;
 
         result = read_node(PS3_LPAR_ID_PME,
             make_first_field("bus", bus_index),
@@ -786,7 +786,7 @@ int ps3_repository_read_mm_info(u64 *rm_base, u64 *rm_size, u64 *region_total)
 int ps3_repository_read_num_spu_reserved(unsigned int *num_spu_reserved)
 {
         int result;
-        u64 v1;
+        u64 v1 = 0;
 
         result = read_node(PS3_LPAR_ID_CURRENT,
                 make_first_field("bi", 0),
@@ -805,7 +805,7 @@ int ps3_repository_read_num_spu_reserved(unsigned int *num_spu_reserved)
 int ps3_repository_read_num_spu_resource_id(unsigned int *num_resource_id)
 {
         int result;
-        u64 v1;
+        u64 v1 = 0;
 
         result = read_node(PS3_LPAR_ID_CURRENT,
                 make_first_field("bi", 0),
@@ -827,8 +827,8 @@ int ps3_repository_read_spu_resource_id(unsigned int res_index,
         enum ps3_spu_resource_type *resource_type, unsigned int *resource_id)
 {
         int result;
-        u64 v1;
-        u64 v2;
+        u64 v1 = 0;
+        u64 v2 = 0;
 
         result = read_node(PS3_LPAR_ID_CURRENT,
                 make_first_field("bi", 0),
@@ -854,7 +854,7 @@ static int ps3_repository_read_boot_dat_address(u64 *address)
 int ps3_repository_read_boot_dat_size(unsigned int *size)
 {
         int result;
-        u64 v1;
+        u64 v1 = 0;
 
         result = read_node(PS3_LPAR_ID_CURRENT,
                 make_first_field("bi", 0),
@@ -869,7 +869,7 @@ int ps3_repository_read_boot_dat_size(unsigned int *size)
 int ps3_repository_read_vuart_av_port(unsigned int *port)
 {
         int result;
-        u64 v1;
+        u64 v1 = 0;
 
         result = read_node(PS3_LPAR_ID_CURRENT,
                 make_first_field("bi", 0),
@@ -884,7 +884,7 @@ int ps3_repository_read_vuart_av_port(unsigned int *port)
 int ps3_repository_read_vuart_sysmgr_port(unsigned int *port)
 {
         int result;
-        u64 v1;
+        u64 v1 = 0;
 
         result = read_node(PS3_LPAR_ID_CURRENT,
                 make_first_field("bi", 0),
@@ -919,7 +919,7 @@ int ps3_repository_read_boot_dat_info(u64 *lpar_addr, unsigned int *size)
 int ps3_repository_read_num_be(unsigned int *num_be)
 {
         int result;
-        u64 v1;
+        u64 v1 = 0;
 
         result = read_node(PS3_LPAR_ID_PME,
                 make_first_field("ben", 0),
diff --git a/arch/powerpc/platforms/ps3/setup.c b/arch/powerpc/platforms/ps3/setup.c
index 149bea2ce583..e8ec1b2bfffd 100644
--- a/arch/powerpc/platforms/ps3/setup.c
+++ b/arch/powerpc/platforms/ps3/setup.c
@@ -23,6 +23,7 @@
 #include <linux/fs.h>
 #include <linux/root_dev.h>
 #include <linux/console.h>
+#include <linux/export.h>
 #include <linux/bootmem.h>
 
 #include <asm/machdep.h>
diff --git a/arch/powerpc/platforms/ps3/spu.c b/arch/powerpc/platforms/ps3/spu.c
index 375a9f92158d..451fad1c92a8 100644
--- a/arch/powerpc/platforms/ps3/spu.c
+++ b/arch/powerpc/platforms/ps3/spu.c
@@ -22,6 +22,7 @@
 #include <linux/init.h>
 #include <linux/slab.h>
 #include <linux/mmzone.h>
+#include <linux/export.h>
 #include <linux/io.h>
 #include <linux/mm.h>
 
diff --git a/arch/powerpc/platforms/ps3/system-bus.c b/arch/powerpc/platforms/ps3/system-bus.c
index 23083c397528..880eb9ce22c5 100644
--- a/arch/powerpc/platforms/ps3/system-bus.c
+++ b/arch/powerpc/platforms/ps3/system-bus.c
@@ -20,7 +20,7 @@
 
 #include <linux/kernel.h>
 #include <linux/init.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/dma-mapping.h>
 #include <linux/err.h>
 #include <linux/slab.h>
@@ -695,12 +695,18 @@ static int ps3_dma_supported(struct device *_dev, u64 mask)
         return mask >= DMA_BIT_MASK(32);
 }
 
+static u64 ps3_dma_get_required_mask(struct device *_dev)
+{
+        return DMA_BIT_MASK(32);
+}
+
 static struct dma_map_ops ps3_sb_dma_ops = {
         .alloc_coherent = ps3_alloc_coherent,
         .free_coherent = ps3_free_coherent,
         .map_sg = ps3_sb_map_sg,
         .unmap_sg = ps3_sb_unmap_sg,
         .dma_supported = ps3_dma_supported,
+        .get_required_mask = ps3_dma_get_required_mask,
         .map_page = ps3_sb_map_page,
         .unmap_page = ps3_unmap_page,
 };
@@ -711,6 +717,7 @@ static struct dma_map_ops ps3_ioc0_dma_ops = {
         .map_sg = ps3_ioc0_map_sg,
         .unmap_sg = ps3_ioc0_unmap_sg,
         .dma_supported = ps3_dma_supported,
+        .get_required_mask = ps3_dma_get_required_mask,
         .map_page = ps3_ioc0_map_page,
         .unmap_page = ps3_unmap_page,
 };
diff --git a/arch/powerpc/platforms/pseries/Kconfig b/arch/powerpc/platforms/pseries/Kconfig
index 05cf4769b88c..c81f6bb9c10f 100644
--- a/arch/powerpc/platforms/pseries/Kconfig
+++ b/arch/powerpc/platforms/pseries/Kconfig
@@ -15,6 +15,7 @@ config PPC_PSERIES
         select PPC_UDBG_16550
         select PPC_NATIVE
         select PPC_PCI_CHOICE if EXPERT
+        select ZLIB_DEFLATE
         default y
 
 config PPC_SPLPAR
diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c
index e9be25bc571b..0f1b706506ed 100644
--- a/arch/powerpc/platforms/pseries/dlpar.c
+++ b/arch/powerpc/platforms/pseries/dlpar.c
@@ -112,6 +112,7 @@ void dlpar_free_cc_nodes(struct device_node *dn)
         dlpar_free_one_cc_node(dn);
 }
 
+#define COMPLETE        0
 #define NEXT_SIBLING    1
 #define NEXT_CHILD      2
 #define NEXT_PROPERTY   3
@@ -158,6 +159,9 @@ struct device_node *dlpar_configure_connector(u32 drc_index)
                 spin_unlock(&rtas_data_buf_lock);
 
                 switch (rc) {
+                case COMPLETE:
+                        break;
+
                 case NEXT_SIBLING:
                         dn = dlpar_parse_cc_node(ccwa);
                         if (!dn)
diff --git a/arch/powerpc/platforms/pseries/eeh.c b/arch/powerpc/platforms/pseries/eeh.c
index ada6e07532ec..565869022e3d 100644
--- a/arch/powerpc/platforms/pseries/eeh.c
+++ b/arch/powerpc/platforms/pseries/eeh.c
@@ -22,6 +22,7 @@
  */
 
 #include <linux/delay.h>
+#include <linux/sched.h>        /* for init_mm */
 #include <linux/init.h>
 #include <linux/list.h>
 #include <linux/pci.h>
@@ -29,6 +30,7 @@
 #include <linux/rbtree.h>
 #include <linux/seq_file.h>
 #include <linux/spinlock.h>
+#include <linux/export.h>
 #include <linux/of.h>
 
 #include <linux/atomic.h>
@@ -1338,7 +1340,7 @@ static const struct file_operations proc_eeh_operations = {
 static int __init eeh_init_proc(void)
 {
         if (machine_is(pseries))
-                proc_create("ppc64/eeh", 0, NULL, &proc_eeh_operations);
+                proc_create("powerpc/eeh", 0, NULL, &proc_eeh_operations);
         return 0;
 }
 __initcall(eeh_init_proc);
diff --git a/arch/powerpc/platforms/pseries/eeh_event.c b/arch/powerpc/platforms/pseries/eeh_event.c
index 2ec500c130b5..d2383cfb6dfd 100644
--- a/arch/powerpc/platforms/pseries/eeh_event.c
+++ b/arch/powerpc/platforms/pseries/eeh_event.c
@@ -21,6 +21,7 @@
 #include <linux/delay.h>
 #include <linux/list.h>
 #include <linux/mutex.h>
+#include <linux/sched.h>
 #include <linux/pci.h>
 #include <linux/slab.h>
 #include <linux/workqueue.h>
diff --git a/arch/powerpc/platforms/pseries/eeh_sysfs.c b/arch/powerpc/platforms/pseries/eeh_sysfs.c
index 23982c7892d2..eb744ee234da 100644
--- a/arch/powerpc/platforms/pseries/eeh_sysfs.c
+++ b/arch/powerpc/platforms/pseries/eeh_sysfs.c
@@ -23,6 +23,7 @@
  * Send comments and feedback to Linas Vepstas <linas@austin.ibm.com>
  */
 #include <linux/pci.h>
+#include <linux/stat.h>
 #include <asm/ppc-pci.h>
 #include <asm/pci-bridge.h>
 
diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c
index 83a3ca2fd282..c986d08d0807 100644
--- a/arch/powerpc/platforms/pseries/hotplug-cpu.c
+++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c
@@ -21,6 +21,7 @@
 #include <linux/kernel.h>
 #include <linux/interrupt.h>
 #include <linux/delay.h>
+#include <linux/sched.h>        /* for idle_task_exit */
 #include <linux/cpu.h>
 #include <asm/system.h>
 #include <asm/prom.h>
diff --git a/arch/powerpc/platforms/pseries/hvconsole.c b/arch/powerpc/platforms/pseries/hvconsole.c
index 041e87ca1893..b344f94b0400 100644
--- a/arch/powerpc/platforms/pseries/hvconsole.c
+++ b/arch/powerpc/platforms/pseries/hvconsole.c
@@ -24,7 +24,8 @@
  */
 
 #include <linux/kernel.h>
-#include <linux/module.h>
+#include <linux/export.h>
+#include <linux/errno.h>
 #include <asm/hvcall.h>
 #include <asm/hvconsole.h>
 #include "plpar_wrappers.h"
diff --git a/arch/powerpc/platforms/pseries/io_event_irq.c b/arch/powerpc/platforms/pseries/io_event_irq.c
index 2c4dd1fb8333..1a709bc48ce1 100644
--- a/arch/powerpc/platforms/pseries/io_event_irq.c
+++ b/arch/powerpc/platforms/pseries/io_event_irq.c
@@ -9,7 +9,7 @@
 
 #include <linux/errno.h>
 #include <linux/slab.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/irq.h>
 #include <linux/interrupt.h>
 #include <linux/of.h>
diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index 01faab9456ca..b719d9709730 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -29,6 +29,7 @@
 #include <linux/slab.h>
 #include <linux/mm.h>
 #include <linux/spinlock.h>
+#include <linux/sched.h>        /* for show_stack */
 #include <linux/string.h>
 #include <linux/pci.h>
 #include <linux/dma-mapping.h>
@@ -939,14 +940,14 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn)
         if (ret) {
                 dev_info(&dev->dev, "failed to map direct window for %s: %d\n",
                          dn->full_name, ret);
-                goto out_clear_window;
+                goto out_free_window;
         }
 
         ret = prom_add_property(pdn, win64);
         if (ret) {
                 dev_err(&dev->dev, "unable to add dma window property for %s: %d",
                          pdn->full_name, ret);
-                goto out_clear_window;
+                goto out_free_window;
         }
 
         window->device = pdn;
@@ -958,6 +959,9 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn)
         dma_addr = of_read_number(&create.addr_hi, 2);
         goto out_unlock;
 
+out_free_window:
+        kfree(window);
+
 out_clear_window:
         remove_ddw(pdn);
 
@@ -1077,12 +1081,38 @@ check_mask:
         return 0;
 }
 
+static u64 dma_get_required_mask_pSeriesLP(struct device *dev)
+{
+        if (!dev->dma_mask)
+                return 0;
+
+        if (!disable_ddw && dev_is_pci(dev)) {
+                struct pci_dev *pdev = to_pci_dev(dev);
+                struct device_node *dn;
+
+                dn = pci_device_to_OF_node(pdev);
+
+                /* search upwards for ibm,dma-window */
+                for (; dn && PCI_DN(dn) && !PCI_DN(dn)->iommu_table;
+                                dn = dn->parent)
+                        if (of_get_property(dn, "ibm,dma-window", NULL))
+                                break;
+                /* if there is a ibm,ddw-applicable property require 64 bits */
+                if (dn && PCI_DN(dn) &&
+                                of_get_property(dn, "ibm,ddw-applicable", NULL))
+                        return DMA_BIT_MASK(64);
+        }
+
+        return dma_iommu_ops.get_required_mask(dev);
+}
+
 #else  /* CONFIG_PCI */
 #define pci_dma_bus_setup_pSeries       NULL
 #define pci_dma_dev_setup_pSeries       NULL
 #define pci_dma_bus_setup_pSeriesLP     NULL
 #define pci_dma_dev_setup_pSeriesLP     NULL
 #define dma_set_mask_pSeriesLP          NULL
+#define dma_get_required_mask_pSeriesLP NULL
 #endif /* !CONFIG_PCI */
 
 static int iommu_mem_notifier(struct notifier_block *nb, unsigned long action,
@@ -1186,6 +1216,7 @@ void iommu_init_early_pSeries(void)
                 ppc_md.pci_dma_bus_setup = pci_dma_bus_setup_pSeriesLP;
                 ppc_md.pci_dma_dev_setup = pci_dma_dev_setup_pSeriesLP;
                 ppc_md.dma_set_mask = dma_set_mask_pSeriesLP;
+                ppc_md.dma_get_required_mask = dma_get_required_mask_pSeriesLP;
         } else {
                 ppc_md.tce_build = tce_build_pSeries;
                 ppc_md.tce_free  = tce_free_pSeries;
diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c
index c9a29dae8c05..27a49508b410 100644
--- a/arch/powerpc/platforms/pseries/lpar.c
+++ b/arch/powerpc/platforms/pseries/lpar.c
@@ -25,6 +25,7 @@
 #include <linux/kernel.h>
 #include <linux/dma-mapping.h>
 #include <linux/console.h>
+#include <linux/export.h>
 #include <asm/processor.h>
 #include <asm/mmu.h>
 #include <asm/page.h>
diff --git a/arch/powerpc/platforms/pseries/mobility.c b/arch/powerpc/platforms/pseries/mobility.c
index 3e7f651e50ac..029a562af373 100644
--- a/arch/powerpc/platforms/pseries/mobility.c
+++ b/arch/powerpc/platforms/pseries/mobility.c
@@ -12,6 +12,7 @@
 #include <linux/kernel.h>
 #include <linux/kobject.h>
 #include <linux/smp.h>
+#include <linux/stat.h>
 #include <linux/completion.h>
 #include <linux/device.h>
 #include <linux/delay.h>
diff --git a/arch/powerpc/platforms/pseries/nvram.c b/arch/powerpc/platforms/pseries/nvram.c
index 00cc3a094885..a76b22844d18 100644
--- a/arch/powerpc/platforms/pseries/nvram.c
+++ b/arch/powerpc/platforms/pseries/nvram.c
@@ -18,6 +18,8 @@
 #include <linux/spinlock.h>
 #include <linux/slab.h>
 #include <linux/kmsg_dump.h>
+#include <linux/ctype.h>
+#include <linux/zlib.h>
 #include <asm/uaccess.h>
 #include <asm/nvram.h>
 #include <asm/rtas.h>
@@ -78,8 +80,41 @@ static struct kmsg_dumper nvram_kmsg_dumper = {
 #define NVRAM_RTAS_READ_TIMEOUT 5               /* seconds */
 static unsigned long last_unread_rtas_event;    /* timestamp */
 
-/* We preallocate oops_buf during init to avoid kmalloc during oops/panic. */
-static char *oops_buf;
+/*
+ * For capturing and compressing an oops or panic report...
+
+ * big_oops_buf[] holds the uncompressed text we're capturing.
+ *
+ * oops_buf[] holds the compressed text, preceded by a prefix.
+ * The prefix is just a u16 holding the length of the compressed* text.
+ * (*Or uncompressed, if compression fails.)  oops_buf[] gets written
+ * to NVRAM.
+ *
+ * oops_len points to the prefix.  oops_data points to the compressed text.
+ *
+ * +- oops_buf
+ * |            +- oops_data
+ * v            v
+ * +------------+-----------------------------------------------+
+ * | length     | text                                          |
+ * | (2 bytes)  | (oops_data_sz bytes)                          |
+ * +------------+-----------------------------------------------+
+ * ^
+ * +- oops_len
+ *
+ * We preallocate these buffers during init to avoid kmalloc during oops/panic.
+ */
+static size_t big_oops_buf_sz;
+static char *big_oops_buf, *oops_buf;
+static u16 *oops_len;
+static char *oops_data;
+static size_t oops_data_sz;
+
+/* Compression parameters */
+#define COMPR_LEVEL 6
+#define WINDOW_BITS 12
+#define MEM_LEVEL 4
+static struct z_stream_s stream;
 
 static ssize_t pSeries_nvram_read(char *buf, size_t count, loff_t *index)
 {
@@ -387,11 +422,44 @@ static void __init nvram_init_oops_partition(int rtas_partition_exists)
                                                 sizeof(rtas_log_partition));
         }
         oops_buf = kmalloc(oops_log_partition.size, GFP_KERNEL);
+        if (!oops_buf) {
+                pr_err("nvram: No memory for %s partition\n",
+                                                oops_log_partition.name);
+                return;
+        }
+        oops_len = (u16*) oops_buf;
+        oops_data = oops_buf + sizeof(u16);
+        oops_data_sz = oops_log_partition.size - sizeof(u16);
+
+        /*
+         * Figure compression (preceded by elimination of each line's <n>
+         * severity prefix) will reduce the oops/panic report to at most
+         * 45% of its original size.
+         */
+        big_oops_buf_sz = (oops_data_sz * 100) / 45;
+        big_oops_buf = kmalloc(big_oops_buf_sz, GFP_KERNEL);
+        if (big_oops_buf) {
+                stream.workspace = kmalloc(zlib_deflate_workspacesize(
+                                WINDOW_BITS, MEM_LEVEL), GFP_KERNEL);
+                if (!stream.workspace) {
+                        pr_err("nvram: No memory for compression workspace; "
+                                "skipping compression of %s partition data\n",
+                                oops_log_partition.name);
+                        kfree(big_oops_buf);
+                        big_oops_buf = NULL;
+                }
+        } else {
+                pr_err("No memory for uncompressed %s data; "
+                        "skipping compression\n", oops_log_partition.name);
+                stream.workspace = NULL;
+        }
+
         rc = kmsg_dump_register(&nvram_kmsg_dumper);
         if (rc != 0) {
                 pr_err("nvram: kmsg_dump_register() failed; returned %d\n", rc);
                 kfree(oops_buf);
-                return;
+                kfree(big_oops_buf);
+                kfree(stream.workspace);
         }
 }
 
@@ -473,7 +541,83 @@ static int clobbering_unread_rtas_event(void)
                                                 NVRAM_RTAS_READ_TIMEOUT);
 }
 
-/* our kmsg_dump callback */
+/* Squeeze out each line's <n> severity prefix. */
+static size_t elide_severities(char *buf, size_t len)
+{
+        char *in, *out, *buf_end = buf + len;
+        /* Assume a <n> at the very beginning marks the start of a line. */
+        int newline = 1;
+
+        in = out = buf;
+        while (in < buf_end) {
+                if (newline && in+3 <= buf_end &&
+                                *in == '<' && isdigit(in[1]) && in[2] == '>') {
+                        in += 3;
+                        newline = 0;
+                } else {
+                        newline = (*in == '\n');
+                        *out++ = *in++;
+                }
+        }
+        return out - buf;
+}
+
+/* Derived from logfs_compress() */
+static int nvram_compress(const void *in, void *out, size_t inlen,
+                                                        size_t outlen)
+{
+        int err, ret;
+
+        ret = -EIO;
+        err = zlib_deflateInit2(&stream, COMPR_LEVEL, Z_DEFLATED, WINDOW_BITS,
+                                                MEM_LEVEL, Z_DEFAULT_STRATEGY);
+        if (err != Z_OK)
+                goto error;
+
+        stream.next_in = in;
+        stream.avail_in = inlen;
+        stream.total_in = 0;
+        stream.next_out = out;
+        stream.avail_out = outlen;
+        stream.total_out = 0;
+
+        err = zlib_deflate(&stream, Z_FINISH);
+        if (err != Z_STREAM_END)
+                goto error;
+
+        err = zlib_deflateEnd(&stream);
+        if (err != Z_OK)
+                goto error;
+
+        if (stream.total_out >= stream.total_in)
+                goto error;
+
+        ret = stream.total_out;
+error:
+        return ret;
+}
+
+/* Compress the text from big_oops_buf into oops_buf. */
+static int zip_oops(size_t text_len)
+{
+        int zipped_len = nvram_compress(big_oops_buf, oops_data, text_len,
+                                                                oops_data_sz);
+        if (zipped_len < 0) {
+                pr_err("nvram: compression failed; returned %d\n", zipped_len);
+                pr_err("nvram: logging uncompressed oops/panic report\n");
+                return -1;
+        }
+        *oops_len = (u16) zipped_len;
+        return 0;
+}
+
+/*
+ * This is our kmsg_dump callback, called after an oops or panic report
+ * has been written to the printk buffer.  We want to capture as much
+ * of the printk buffer as possible.  First, capture as much as we can
+ * that we think will compress sufficiently to fit in the lnx,oops-log
+ * partition.  If that's too much, go back and capture uncompressed text.
+ */
 static void oops_to_nvram(struct kmsg_dumper *dumper,
                 enum kmsg_dump_reason reason,
                 const char *old_msgs, unsigned long old_len,
@@ -482,6 +626,8 @@ static void oops_to_nvram(struct kmsg_dumper *dumper,
         static unsigned int oops_count = 0;
         static bool panicking = false;
         size_t text_len;
+        unsigned int err_type = ERR_TYPE_KERNEL_PANIC_GZ;
+        int rc = -1;
 
         switch (reason) {
         case KMSG_DUMP_RESTART:
@@ -509,8 +655,19 @@ static void oops_to_nvram(struct kmsg_dumper *dumper,
         if (clobbering_unread_rtas_event())
                 return;
 
-        text_len = capture_last_msgs(old_msgs, old_len, new_msgs, new_len,
-                                        oops_buf, oops_log_partition.size);
+        if (big_oops_buf) {
+                text_len = capture_last_msgs(old_msgs, old_len,
+                        new_msgs, new_len, big_oops_buf, big_oops_buf_sz);
+                text_len = elide_severities(big_oops_buf, text_len);
+                rc = zip_oops(text_len);
+        }
+        if (rc != 0) {
+                text_len = capture_last_msgs(old_msgs, old_len,
+                                new_msgs, new_len, oops_data, oops_data_sz);
+                err_type = ERR_TYPE_KERNEL_PANIC;
+                *oops_len = (u16) text_len;
+        }
+
         (void) nvram_write_os_partition(&oops_log_partition, oops_buf,
-                (int) text_len, ERR_TYPE_KERNEL_PANIC, ++oops_count);
+                (int) (sizeof(*oops_len) + *oops_len), err_type, ++oops_count);
 }
diff --git a/arch/powerpc/platforms/pseries/pci_dlpar.c b/arch/powerpc/platforms/pseries/pci_dlpar.c
index 3bf4488aaec6..55d4ec1bd1ac 100644
--- a/arch/powerpc/platforms/pseries/pci_dlpar.c
+++ b/arch/powerpc/platforms/pseries/pci_dlpar.c
@@ -26,6 +26,7 @@
  */
 
 #include <linux/pci.h>
+#include <linux/export.h>
 #include <asm/pci-bridge.h>
 #include <asm/ppc-pci.h>
 #include <asm/firmware.h>
diff --git a/arch/powerpc/platforms/pseries/plpar_wrappers.h b/arch/powerpc/platforms/pseries/plpar_wrappers.h
index 41c24c146d6a..342797fc0f9c 100644
--- a/arch/powerpc/platforms/pseries/plpar_wrappers.h
+++ b/arch/powerpc/platforms/pseries/plpar_wrappers.h
@@ -1,7 +1,10 @@
 #ifndef _PSERIES_PLPAR_WRAPPERS_H
 #define _PSERIES_PLPAR_WRAPPERS_H
 
+#include <linux/string.h>
+
 #include <asm/hvcall.h>
+#include <asm/paca.h>
 #include <asm/page.h>
 
 /* Get state of physical CPU from query_cpu_stopped */
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index 0969fd98c4fa..c3408ca8855e 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -34,7 +34,7 @@
 #include <linux/pci.h>
 #include <linux/utsname.h>
 #include <linux/adb.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/delay.h>
 #include <linux/irq.h>
 #include <linux/seq_file.h>
diff --git a/arch/powerpc/platforms/pseries/smp.c b/arch/powerpc/platforms/pseries/smp.c
index 4e44c4dcd11c..26e93fd4c62b 100644
--- a/arch/powerpc/platforms/pseries/smp.c
+++ b/arch/powerpc/platforms/pseries/smp.c
@@ -14,7 +14,6 @@
 
 
 #include <linux/kernel.h>
-#include <linux/module.h>
 #include <linux/sched.h>
 #include <linux/smp.h>
 #include <linux/interrupt.h>
diff --git a/arch/powerpc/platforms/pseries/suspend.c b/arch/powerpc/platforms/pseries/suspend.c
index a8ca289ff267..d3de0849f296 100644
--- a/arch/powerpc/platforms/pseries/suspend.c
+++ b/arch/powerpc/platforms/pseries/suspend.c
@@ -18,6 +18,7 @@
 
 #include <linux/delay.h>
 #include <linux/suspend.h>
+#include <linux/stat.h>
 #include <asm/firmware.h>
 #include <asm/hvcall.h>
 #include <asm/machdep.h>
diff --git a/arch/powerpc/platforms/wsp/Kconfig b/arch/powerpc/platforms/wsp/Kconfig
index c3c48eb62cc1..bd560c786ed6 100644
--- a/arch/powerpc/platforms/wsp/Kconfig
+++ b/arch/powerpc/platforms/wsp/Kconfig
@@ -1,5 +1,12 @@
 config PPC_WSP
         bool
+        select PPC_A2
+        select PPC_SCOM
+        select PPC_XICS
+        select PPC_ICP_NATIVE
+        select PCI
+        select PPC_IO_WORKAROUNDS if PCI
+        select PPC_INDIRECT_PIO if PCI
         default n
 
 menu "WSP platform selection"
@@ -7,13 +14,9 @@ menu "WSP platform selection"
 
 config PPC_PSR2
         bool "PSR-2 platform"
-        select PPC_A2
         select GENERIC_TBSYNC
-        select PPC_SCOM
         select EPAPR_BOOT
         select PPC_WSP
-        select PPC_XICS
-        select PPC_ICP_NATIVE
         default y
 
 endmenu
@@ -21,8 +24,3 @@ endmenu
 config PPC_A2_DD2
         bool "Support for DD2 based A2/WSP systems"
         depends on PPC_A2
-
-config WORKAROUND_ERRATUM_463
-        depends on PPC_A2_DD2
-        bool "Workaround erratum 463"
-        default y
diff --git a/arch/powerpc/platforms/wsp/Makefile b/arch/powerpc/platforms/wsp/Makefile
index 095be73d6cd4..a1486b436f02 100644
--- a/arch/powerpc/platforms/wsp/Makefile
+++ b/arch/powerpc/platforms/wsp/Makefile
@@ -4,3 +4,5 @@ obj-y				+= setup.o ics.o
 obj-$(CONFIG_PPC_PSR2)          += psr2.o opb_pic.o
 obj-$(CONFIG_PPC_WSP)           += scom_wsp.o
 obj-$(CONFIG_SMP)               += smp.o scom_smp.o
+obj-$(CONFIG_PCI)               += wsp_pci.o
+obj-$(CONFIG_PCI_MSI)           += msi.o
\ No newline at end of file
diff --git a/arch/powerpc/platforms/wsp/ics.c b/arch/powerpc/platforms/wsp/ics.c
index e53bd9e7b125..576874392543 100644
--- a/arch/powerpc/platforms/wsp/ics.c
+++ b/arch/powerpc/platforms/wsp/ics.c
@@ -710,3 +710,51 @@ void __init wsp_init_irq(void)
         /* We need to patch our irq chip's EOI to point to the right ICP */
         wsp_irq_chip.irq_eoi = icp_ops->eoi;
 }
+
+#ifdef CONFIG_PCI_MSI
+static void wsp_ics_msi_unmask_irq(struct irq_data *d)
+{
+        wsp_chip_unmask_irq(d);
+        unmask_msi_irq(d);
+}
+
+static unsigned int wsp_ics_msi_startup(struct irq_data *d)
+{
+        wsp_ics_msi_unmask_irq(d);
+        return 0;
+}
+
+static void wsp_ics_msi_mask_irq(struct irq_data *d)
+{
+        mask_msi_irq(d);
+        wsp_chip_mask_irq(d);
+}
+
+/*
+ * we do it this way because we reassinge default EOI handling in
+ * irq_init() above
+ */
+static void wsp_ics_eoi(struct irq_data *data)
+{
+        wsp_irq_chip.irq_eoi(data);
+}
+
+static struct irq_chip wsp_ics_msi = {
+        .name = "WSP ICS MSI",
+        .irq_startup = wsp_ics_msi_startup,
+        .irq_mask = wsp_ics_msi_mask_irq,
+        .irq_unmask = wsp_ics_msi_unmask_irq,
+        .irq_eoi = wsp_ics_eoi,
+        .irq_set_affinity = wsp_chip_set_affinity
+};
+
+void wsp_ics_set_msi_chip(unsigned int irq)
+{
+        irq_set_chip(irq, &wsp_ics_msi);
+}
+
+void wsp_ics_set_std_chip(unsigned int irq)
+{
+        irq_set_chip(irq, &wsp_irq_chip);
+}
+#endif /* CONFIG_PCI_MSI */
diff --git a/arch/powerpc/platforms/wsp/ics.h b/arch/powerpc/platforms/wsp/ics.h
index e34d53102640..07b644e0cf97 100644
--- a/arch/powerpc/platforms/wsp/ics.h
+++ b/arch/powerpc/platforms/wsp/ics.h
@@ -17,4 +17,9 @@ extern void wsp_init_irq(void);
 extern int wsp_ics_alloc_irq(struct device_node *dn, int num);
 extern void wsp_ics_free_irq(struct device_node *dn, unsigned int irq);
 
+#ifdef CONFIG_PCI_MSI
+extern void wsp_ics_set_msi_chip(unsigned int irq);
+extern void wsp_ics_set_std_chip(unsigned int irq);
+#endif /* CONFIG_PCI_MSI */
+
 #endif /* __ICS_H */
diff --git a/arch/powerpc/platforms/wsp/msi.c b/arch/powerpc/platforms/wsp/msi.c
new file mode 100644
index 000000000000..380882f27add
--- /dev/null
+++ b/arch/powerpc/platforms/wsp/msi.c
@@ -0,0 +1,102 @@
+/*
+ * Copyright 2011 Michael Ellerman, IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/pci.h>
+#include <linux/msi.h>
+#include <linux/irq.h>
+#include <linux/interrupt.h>
+
+#include "msi.h"
+#include "ics.h"
+#include "wsp_pci.h"
+
+/* Magic addresses for 32 & 64-bit MSIs with hardcoded MVE 0 */
+#define MSI_ADDR_32             0xFFFF0000ul
+#define MSI_ADDR_64             0x1000000000000000ul
+
+int wsp_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
+{
+        struct pci_controller *phb;
+        struct msi_desc *entry;
+        struct msi_msg msg;
+        unsigned int virq;
+        int hwirq;
+
+        phb = pci_bus_to_host(dev->bus);
+        if (!phb)
+                return -ENOENT;
+
+        entry = list_first_entry(&dev->msi_list, struct msi_desc, list);
+        if (entry->msi_attrib.is_64) {
+                msg.address_lo = 0;
+                msg.address_hi = MSI_ADDR_64 >> 32;
+        } else {
+                msg.address_lo = MSI_ADDR_32;
+                msg.address_hi = 0;
+        }
+
+        list_for_each_entry(entry, &dev->msi_list, list) {
+                hwirq = wsp_ics_alloc_irq(phb->dn, 1);
+                if (hwirq < 0) {
+                        dev_warn(&dev->dev, "wsp_msi: hwirq alloc failed!\n");
+                        return hwirq;
+                }
+
+                virq = irq_create_mapping(NULL, hwirq);
+                if (virq == NO_IRQ) {
+                        dev_warn(&dev->dev, "wsp_msi: virq alloc failed!\n");
+                        return -1;
+                }
+
+                dev_dbg(&dev->dev, "wsp_msi: allocated irq %#x/%#x\n",
+                        hwirq, virq);
+
+                wsp_ics_set_msi_chip(virq);
+                irq_set_msi_desc(virq, entry);
+                msg.data = hwirq & XIVE_ADDR_MASK;
+                write_msi_msg(virq, &msg);
+        }
+
+        return 0;
+}
+
+void wsp_teardown_msi_irqs(struct pci_dev *dev)
+{
+        struct pci_controller *phb;
+        struct msi_desc *entry;
+        int hwirq;
+
+        phb = pci_bus_to_host(dev->bus);
+
+        dev_dbg(&dev->dev, "wsp_msi: tearing down msi irqs\n");
+
+        list_for_each_entry(entry, &dev->msi_list, list) {
+                if (entry->irq == NO_IRQ)
+                        continue;
+
+                irq_set_msi_desc(entry->irq, NULL);
+                wsp_ics_set_std_chip(entry->irq);
+
+                hwirq = virq_to_hw(entry->irq);
+                /* In this order to avoid racing with irq_create_mapping() */
+                irq_dispose_mapping(entry->irq);
+                wsp_ics_free_irq(phb->dn, hwirq);
+        }
+}
+
+void wsp_setup_phb_msi(struct pci_controller *phb)
+{
+        /* Create a single MVE at offset 0 that matches everything */
+        out_be64(phb->cfg_data + PCIE_REG_IODA_ADDR, PCIE_REG_IODA_AD_TBL_MVT);
+        out_be64(phb->cfg_data + PCIE_REG_IODA_DATA0, 1ull << 63);
+
+        ppc_md.setup_msi_irqs = wsp_setup_msi_irqs;
+        ppc_md.teardown_msi_irqs = wsp_teardown_msi_irqs;
+}
diff --git a/arch/powerpc/platforms/wsp/msi.h b/arch/powerpc/platforms/wsp/msi.h
new file mode 100644
index 000000000000..0ab27b71b24d
--- /dev/null
+++ b/arch/powerpc/platforms/wsp/msi.h
@@ -0,0 +1,19 @@
+/*
+ * Copyright 2011 Michael Ellerman, IBM Corp.
+ *
+ *  This program is free software; you can redistribute it and/or
+ *  modify it under the terms of the GNU General Public License
+ *  as published by the Free Software Foundation; either version
+ *  2 of the License, or (at your option) any later version.
+ */
+
+#ifndef __WSP_MSI_H
+#define __WSP_MSI_H
+
+#ifdef CONFIG_PCI_MSI
+extern void wsp_setup_phb_msi(struct pci_controller *phb);
+#else
+static inline void wsp_setup_phb_msi(struct pci_controller *phb) { }
+#endif
+
+#endif /* __WSP_MSI_H */
diff --git a/arch/powerpc/platforms/wsp/psr2.c b/arch/powerpc/platforms/wsp/psr2.c
index 40f28916ff6c..166f2e4b4bee 100644
--- a/arch/powerpc/platforms/wsp/psr2.c
+++ b/arch/powerpc/platforms/wsp/psr2.c
@@ -63,6 +63,10 @@ static void __init psr2_setup_arch(void)
 #ifdef CONFIG_SMP
         a2_setup_smp();
 #endif
+#ifdef CONFIG_PCI
+        wsp_setup_pci();
+#endif
+
 }
 
 static int __init psr2_probe(void)
diff --git a/arch/powerpc/platforms/wsp/wsp.h b/arch/powerpc/platforms/wsp/wsp.h
index 7c3e087fd2f2..33479818f62a 100644
--- a/arch/powerpc/platforms/wsp/wsp.h
+++ b/arch/powerpc/platforms/wsp/wsp.h
@@ -3,6 +3,9 @@
 
 #include <asm/wsp.h>
 
+/* Devtree compatible strings for major devices */
+#define PCIE_COMPATIBLE     "ibm,wsp-pciex"
+
 extern void wsp_setup_pci(void);
 extern void scom_init_wsp(void);
 
diff --git a/arch/powerpc/platforms/wsp/wsp_pci.c b/arch/powerpc/platforms/wsp/wsp_pci.c
new file mode 100644
index 000000000000..e0262cd0e2d3
--- /dev/null
+++ b/arch/powerpc/platforms/wsp/wsp_pci.c
@@ -0,0 +1,1133 @@
+/*
+ * Copyright 2010 Ben Herrenschmidt, IBM Corporation
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#define DEBUG
+
+#include <linux/kernel.h>
+#include <linux/pci.h>
+#include <linux/delay.h>
+#include <linux/string.h>
+#include <linux/init.h>
+#include <linux/bootmem.h>
+#include <linux/irq.h>
+#include <linux/interrupt.h>
+#include <linux/debugfs.h>
+
+#include <asm/sections.h>
+#include <asm/io.h>
+#include <asm/prom.h>
+#include <asm/pci-bridge.h>
+#include <asm/machdep.h>
+#include <asm/ppc-pci.h>
+#include <asm/iommu.h>
+#include <asm/io-workarounds.h>
+
+#include "wsp.h"
+#include "wsp_pci.h"
+#include "msi.h"
+
+
+/* Max number of TVTs for one table. Only 32-bit tables can use
+ * multiple TVTs and so the max currently supported is thus 8
+ * since only 2G of DMA space is supported
+ */
+#define MAX_TABLE_TVT_COUNT             8
+
+struct wsp_dma_table {
+        struct list_head        link;
+        struct iommu_table      table;
+        struct wsp_phb  *phb;
+        struct page             *tces[MAX_TABLE_TVT_COUNT];
+};
+
+/* We support DMA regions from 0...2G in 32bit space (no support for
+ * 64-bit DMA just yet). Each device gets a separate TCE table (TVT
+ * entry) with validation enabled (though not supported by SimiCS
+ * just yet).
+ *
+ * To simplify things, we divide this 2G space into N regions based
+ * on the constant below which could be turned into a tunable eventually
+ *
+ * We then assign dynamically those regions to devices as they show up.
+ *
+ * We use a bitmap as an allocator for these.
+ *
+ * Tables are allocated/created dynamically as devices are discovered,
+ * multiple TVT entries are used if needed
+ *
+ * When 64-bit DMA support is added we should simply use a separate set
+ * of larger regions (the HW supports 64 TVT entries). We can
+ * additionally create a bypass region in 64-bit space for performances
+ * though that would have a cost in term of security.
+ *
+ * If you set NUM_DMA32_REGIONS to 1, then a single table is shared
+ * for all devices and bus/dev/fn validation is disabled
+ *
+ * Note that a DMA32 region cannot be smaller than 256M so the max
+ * supported here for now is 8. We don't yet support sharing regions
+ * between multiple devices so the max number of devices supported
+ * is MAX_TABLE_TVT_COUNT.
+ */
+#define NUM_DMA32_REGIONS       1
+
+struct wsp_phb {
+        struct pci_controller   *hose;
+
+        /* Lock controlling access to the list of dma tables.
+         * It does -not- protect against dma_* operations on
+         * those tables, those should be stopped before an entry
+         * is removed from the list.
+         *
+         * The lock is also used for error handling operations
+         */
+        spinlock_t              lock;
+        struct list_head        dma_tables;
+        unsigned long           dma32_map;
+        unsigned long           dma32_base;
+        unsigned int            dma32_num_regions;
+        unsigned long           dma32_region_size;
+
+        /* Debugfs stuff */
+        struct dentry           *ddir;
+
+        struct list_head        all;
+};
+static LIST_HEAD(wsp_phbs);
+
+//#define cfg_debug(fmt...)     pr_debug(fmt)
+#define cfg_debug(fmt...)
+
+
+static int wsp_pcie_read_config(struct pci_bus *bus, unsigned int devfn,
+                                  int offset, int len, u32 *val)
+{
+        struct pci_controller *hose;
+        int suboff;
+        u64 addr;
+
+        hose = pci_bus_to_host(bus);
+        if (hose == NULL)
+                return PCIBIOS_DEVICE_NOT_FOUND;
+        if (offset >= 0x1000)
+                return  PCIBIOS_BAD_REGISTER_NUMBER;
+        addr = PCIE_REG_CA_ENABLE |
+                ((u64)bus->number) << PCIE_REG_CA_BUS_SHIFT |
+                ((u64)devfn) << PCIE_REG_CA_FUNC_SHIFT |
+                ((u64)offset & ~3) << PCIE_REG_CA_REG_SHIFT;
+        suboff = offset & 3;
+
+        /*
+         * Note: the caller has already checked that offset is
+         * suitably aligned and that len is 1, 2 or 4.
+         */
+
+        switch (len) {
+        case 1:
+                addr |= (0x8ul >> suboff) << PCIE_REG_CA_BE_SHIFT;
+                out_be64(hose->cfg_data + PCIE_REG_CONFIG_ADDRESS, addr);
+                *val = (in_le32(hose->cfg_data + PCIE_REG_CONFIG_DATA)
+                        >> (suboff << 3)) & 0xff;
+                cfg_debug("read 1 %02x:%02x:%02x + %02x/%x addr=0x%llx val=%02x\n",
+                          bus->number, devfn >> 3, devfn & 7,
+                          offset, suboff, addr, *val);
+                break;
+        case 2:
+                addr |= (0xcul >> suboff) << PCIE_REG_CA_BE_SHIFT;
+                out_be64(hose->cfg_data + PCIE_REG_CONFIG_ADDRESS, addr);
+                *val = (in_le32(hose->cfg_data + PCIE_REG_CONFIG_DATA)
+                        >> (suboff << 3)) & 0xffff;
+                cfg_debug("read 2 %02x:%02x:%02x + %02x/%x addr=0x%llx val=%04x\n",
+                          bus->number, devfn >> 3, devfn & 7,
+                          offset, suboff, addr, *val);
+                break;
+        default:
+                addr |= 0xful << PCIE_REG_CA_BE_SHIFT;
+                out_be64(hose->cfg_data + PCIE_REG_CONFIG_ADDRESS, addr);
+                *val = in_le32(hose->cfg_data + PCIE_REG_CONFIG_DATA);
+                cfg_debug("read 4 %02x:%02x:%02x + %02x/%x addr=0x%llx val=%08x\n",
+                          bus->number, devfn >> 3, devfn & 7,
+                          offset, suboff, addr, *val);
+                break;
+        }
+        return PCIBIOS_SUCCESSFUL;
+}
+
+static int wsp_pcie_write_config(struct pci_bus *bus, unsigned int devfn,
+                                   int offset, int len, u32 val)
+{
+        struct pci_controller *hose;
+        int suboff;
+        u64 addr;
+
+        hose = pci_bus_to_host(bus);
+        if (hose == NULL)
+                return PCIBIOS_DEVICE_NOT_FOUND;
+        if (offset >= 0x1000)
+                return  PCIBIOS_BAD_REGISTER_NUMBER;
+        addr = PCIE_REG_CA_ENABLE |
+                ((u64)bus->number) << PCIE_REG_CA_BUS_SHIFT |
+                ((u64)devfn) << PCIE_REG_CA_FUNC_SHIFT |
+                ((u64)offset & ~3) << PCIE_REG_CA_REG_SHIFT;
+        suboff = offset & 3;
+
+        /*
+         * Note: the caller has already checked that offset is
+         * suitably aligned and that len is 1, 2 or 4.
+         */
+        switch (len) {
+        case 1:
+                addr |= (0x8ul >> suboff) << PCIE_REG_CA_BE_SHIFT;
+                val <<= suboff << 3;
+                out_be64(hose->cfg_data + PCIE_REG_CONFIG_ADDRESS, addr);
+                out_le32(hose->cfg_data + PCIE_REG_CONFIG_DATA, val);
+                cfg_debug("write 1 %02x:%02x:%02x + %02x/%x addr=0x%llx val=%02x\n",
+                          bus->number, devfn >> 3, devfn & 7,
+                          offset, suboff, addr, val);
+                break;
+        case 2:
+                addr |= (0xcul >> suboff) << PCIE_REG_CA_BE_SHIFT;
+                val <<= suboff << 3;
+                out_be64(hose->cfg_data + PCIE_REG_CONFIG_ADDRESS, addr);
+                out_le32(hose->cfg_data + PCIE_REG_CONFIG_DATA, val);
+                cfg_debug("write 2 %02x:%02x:%02x + %02x/%x addr=0x%llx val=%04x\n",
+                          bus->number, devfn >> 3, devfn & 7,
+                          offset, suboff, addr, val);
+                break;
+        default:
+                addr |= 0xful << PCIE_REG_CA_BE_SHIFT;
+                out_be64(hose->cfg_data + PCIE_REG_CONFIG_ADDRESS, addr);
+                out_le32(hose->cfg_data + PCIE_REG_CONFIG_DATA, val);
+                cfg_debug("write 4 %02x:%02x:%02x + %02x/%x addr=0x%llx val=%08x\n",
+                          bus->number, devfn >> 3, devfn & 7,
+                          offset, suboff, addr, val);
+                break;
+        }
+        return PCIBIOS_SUCCESSFUL;
+}
+
+static struct pci_ops wsp_pcie_pci_ops =
+{
+        .read = wsp_pcie_read_config,
+        .write = wsp_pcie_write_config,
+};
+
+#define TCE_SHIFT               12
+#define TCE_PAGE_SIZE           (1 << TCE_SHIFT)
+#define TCE_PCI_WRITE           0x2              /* write from PCI allowed */
+#define TCE_PCI_READ            0x1              /* read from PCI allowed */
+#define TCE_RPN_MASK            0x3fffffffffful  /* 42-bit RPN (4K pages) */
+#define TCE_RPN_SHIFT           12
+
+//#define dma_debug(fmt...)     pr_debug(fmt)
+#define dma_debug(fmt...)
+
+static int tce_build_wsp(struct iommu_table *tbl, long index, long npages,
+                           unsigned long uaddr, enum dma_data_direction direction,
+                           struct dma_attrs *attrs)
+{
+        struct wsp_dma_table *ptbl = container_of(tbl,
+                                                    struct wsp_dma_table,
+                                                    table);
+        u64 proto_tce;
+        u64 *tcep;
+        u64 rpn;
+
+        proto_tce = TCE_PCI_READ;
+#ifdef CONFIG_WSP_DD1_WORKAROUND_DD1_TCE_BUGS
+        proto_tce |= TCE_PCI_WRITE;
+#else
+        if (direction != DMA_TO_DEVICE)
+                proto_tce |= TCE_PCI_WRITE;
+#endif
+
+        /* XXX Make this faster by factoring out the page address for
+         * within a TCE table
+         */
+        while (npages--) {
+                /* We don't use it->base as the table can be scattered */
+                tcep = (u64 *)page_address(ptbl->tces[index >> 16]);
+                tcep += (index & 0xffff);
+
+                /* can't move this out since we might cross LMB boundary */
+                rpn = __pa(uaddr) >> TCE_SHIFT;
+                *tcep = proto_tce | (rpn & TCE_RPN_MASK) << TCE_RPN_SHIFT;
+
+                dma_debug("[DMA] TCE %p set to 0x%016llx (dma addr: 0x%lx)\n",
+                          tcep, *tcep, (tbl->it_offset + index) << IOMMU_PAGE_SHIFT);
+
+                uaddr += TCE_PAGE_SIZE;
+                index++;
+        }
+        return 0;
+}
+
+static void tce_free_wsp(struct iommu_table *tbl, long index, long npages)
+{
+        struct wsp_dma_table *ptbl = container_of(tbl,
+                                                    struct wsp_dma_table,
+                                                    table);
+#ifndef CONFIG_WSP_DD1_WORKAROUND_DD1_TCE_BUGS
+        struct pci_controller *hose = ptbl->phb->hose;
+#endif
+        u64 *tcep;
+
+        /* XXX Make this faster by factoring out the page address for
+         * within a TCE table. Also use line-kill option to kill multiple
+         * TCEs at once
+         */
+        while (npages--) {
+                /* We don't use it->base as the table can be scattered */
+                tcep = (u64 *)page_address(ptbl->tces[index >> 16]);
+                tcep += (index & 0xffff);
+                dma_debug("[DMA] TCE %p cleared\n", tcep);
+                *tcep = 0;
+#ifndef CONFIG_WSP_DD1_WORKAROUND_DD1_TCE_BUGS
+                /* Don't write there since it would pollute other MMIO accesses */
+                out_be64(hose->cfg_data + PCIE_REG_TCE_KILL,
+                         PCIE_REG_TCEKILL_SINGLE | PCIE_REG_TCEKILL_PS_4K |
+                         (__pa(tcep) & PCIE_REG_TCEKILL_ADDR_MASK));
+#endif
+                index++;
+        }
+}
+
+static struct wsp_dma_table *wsp_pci_create_dma32_table(struct wsp_phb *phb,
+                                                            unsigned int region,
+                                                            struct pci_dev *validate)
+{
+        struct pci_controller *hose = phb->hose;
+        unsigned long size = phb->dma32_region_size;
+        unsigned long addr = phb->dma32_region_size * region + phb->dma32_base;
+        struct wsp_dma_table *tbl;
+        int tvts_per_table, i, tvt, nid;
+        unsigned long flags;
+
+        nid = of_node_to_nid(phb->hose->dn);
+
+        /* Calculate how many TVTs are needed */
+        tvts_per_table = size / 0x10000000;
+        if (tvts_per_table == 0)
+                tvts_per_table = 1;
+
+        /* Calculate the base TVT index. We know all tables have the same
+         * size so we just do a simple multiply here
+         */
+        tvt = region * tvts_per_table;
+
+        pr_debug("         Region : %d\n", region);
+        pr_debug("      DMA range : 0x%08lx..0x%08lx\n", addr, addr + size - 1);
+        pr_debug(" Number of TVTs : %d\n", tvts_per_table);
+        pr_debug("       Base TVT : %d\n", tvt);
+        pr_debug("         Node   : %d\n", nid);
+
+        tbl = kzalloc_node(sizeof(struct wsp_dma_table), GFP_KERNEL, nid);
+        if (!tbl)
+                return ERR_PTR(-ENOMEM);
+        tbl->phb = phb;
+
+        /* Create as many TVTs as needed, each represents 256M at most */
+        for (i = 0; i < tvts_per_table; i++) {
+                u64 tvt_data1, tvt_data0;
+
+                /* Allocate table. We use a 4K TCE size for now always so
+                 * one table is always 8 * (258M / 4K) == 512K
+                 */
+                tbl->tces[i] = alloc_pages_node(nid, GFP_KERNEL, get_order(0x80000));
+                if (tbl->tces[i] == NULL)
+                        goto fail;
+                memset(page_address(tbl->tces[i]), 0, 0x80000);
+
+                pr_debug(" TCE table %d at : %p\n", i, page_address(tbl->tces[i]));
+
+                /* Table size. We currently set it to be the whole 256M region */
+                tvt_data0 = 2ull << IODA_TVT0_TCE_TABLE_SIZE_SHIFT;
+                /* IO page size set to 4K */
+                tvt_data1 = 1ull << IODA_TVT1_IO_PAGE_SIZE_SHIFT;
+                /* Shift in the address */
+                tvt_data0 |= __pa(page_address(tbl->tces[i])) << IODA_TVT0_TTA_SHIFT;
+
+                /* Validation stuff. We only validate fully bus/dev/fn for now
+                 * one day maybe we can group devices but that isn't the case
+                 * at the moment
+                 */
+                if (validate) {
+                        tvt_data0 |= IODA_TVT0_BUSNUM_VALID_MASK;
+                        tvt_data0 |= validate->bus->number;
+                        tvt_data1 |= IODA_TVT1_DEVNUM_VALID;
+                        tvt_data1 |= ((u64)PCI_SLOT(validate->devfn))
+                                << IODA_TVT1_DEVNUM_VALUE_SHIFT;
+                        tvt_data1 |= IODA_TVT1_FUNCNUM_VALID;
+                        tvt_data1 |= ((u64)PCI_FUNC(validate->devfn))
+                                << IODA_TVT1_FUNCNUM_VALUE_SHIFT;
+                }
+
+                /* XX PE number is always 0 for now */
+
+                /* Program the values using the PHB lock */
+                spin_lock_irqsave(&phb->lock, flags);
+                out_be64(hose->cfg_data + PCIE_REG_IODA_ADDR,
+                         (tvt + i) | PCIE_REG_IODA_AD_TBL_TVT);
+                out_be64(hose->cfg_data + PCIE_REG_IODA_DATA1, tvt_data1);
+                out_be64(hose->cfg_data + PCIE_REG_IODA_DATA0, tvt_data0);
+                spin_unlock_irqrestore(&phb->lock, flags);
+        }
+
+        /* Init bits and pieces */
+        tbl->table.it_blocksize = 16;
+        tbl->table.it_offset = addr >> IOMMU_PAGE_SHIFT;
+        tbl->table.it_size = size >> IOMMU_PAGE_SHIFT;
+
+        /*
+         * It's already blank but we clear it anyway.
+         * Consider an aditiona interface that makes cleaing optional
+         */
+        iommu_init_table(&tbl->table, nid);
+
+        list_add(&tbl->link, &phb->dma_tables);
+        return tbl;
+
+ fail:
+        pr_debug("  Failed to allocate a 256M TCE table !\n");
+        for (i = 0; i < tvts_per_table; i++)
+                if (tbl->tces[i])
+                        __free_pages(tbl->tces[i], get_order(0x80000));
+        kfree(tbl);
+        return ERR_PTR(-ENOMEM);
+}
+
+static void __devinit wsp_pci_dma_dev_setup(struct pci_dev *pdev)
+{
+        struct dev_archdata *archdata = &pdev->dev.archdata;
+        struct pci_controller *hose = pci_bus_to_host(pdev->bus);
+        struct wsp_phb *phb = hose->private_data;
+        struct wsp_dma_table *table = NULL;
+        unsigned long flags;
+        int i;
+
+        /* Don't assign an iommu table to a bridge */
+        if (pdev->hdr_type == PCI_HEADER_TYPE_BRIDGE)
+                return;
+
+        pr_debug("%s: Setting up DMA...\n", pci_name(pdev));
+
+        spin_lock_irqsave(&phb->lock, flags);
+
+        /* If only one region, check if it already exist */
+        if (phb->dma32_num_regions == 1) {
+                spin_unlock_irqrestore(&phb->lock, flags);
+                if (list_empty(&phb->dma_tables))
+                        table = wsp_pci_create_dma32_table(phb, 0, NULL);
+                else
+                        table = list_first_entry(&phb->dma_tables,
+                                                 struct wsp_dma_table,
+                                                 link);
+        } else {
+                /* else find a free region */
+                for (i = 0; i < phb->dma32_num_regions && !table; i++) {
+                        if (__test_and_set_bit(i, &phb->dma32_map))
+                                continue;
+                        spin_unlock_irqrestore(&phb->lock, flags);
+                        table = wsp_pci_create_dma32_table(phb, i, pdev);
+                }
+        }
+
+        /* Check if we got an error */
+        if (IS_ERR(table)) {
+                pr_err("%s: Failed to create DMA table, err %ld !\n",
+                       pci_name(pdev), PTR_ERR(table));
+                return;
+        }
+
+        /* Or a valid table */
+        if (table) {
+                pr_info("%s: Setup iommu: 32-bit DMA region 0x%08lx..0x%08lx\n",
+                        pci_name(pdev),
+                        table->table.it_offset << IOMMU_PAGE_SHIFT,
+                        (table->table.it_offset << IOMMU_PAGE_SHIFT)
+                        + phb->dma32_region_size - 1);
+                archdata->dma_data.iommu_table_base = &table->table;
+                return;
+        }
+
+        /* Or no room */
+        spin_unlock_irqrestore(&phb->lock, flags);
+        pr_err("%s: Out of DMA space !\n", pci_name(pdev));
+}
+
+static void __init wsp_pcie_configure_hw(struct pci_controller *hose)
+{
+        u64 val;
+        int i;
+
+#define DUMP_REG(x) \
+        pr_debug("%-30s : 0x%016llx\n", #x, in_be64(hose->cfg_data + x))
+
+#ifdef CONFIG_WSP_DD1_WORKAROUND_BAD_PCIE_CLASS
+        /* WSP DD1 has a bogus class code by default in the PCI-E
+         * root complex's built-in P2P bridge */
+        val = in_be64(hose->cfg_data + PCIE_REG_SYS_CFG1);
+        pr_debug("PCI-E SYS_CFG1 : 0x%llx\n", val);
+        out_be64(hose->cfg_data + PCIE_REG_SYS_CFG1,
+                 (val & ~PCIE_REG_SYS_CFG1_CLASS_CODE) | (PCI_CLASS_BRIDGE_PCI << 8));
+        pr_debug("PCI-E SYS_CFG1 : 0x%llx\n", in_be64(hose->cfg_data + PCIE_REG_SYS_CFG1));
+#endif /* CONFIG_WSP_DD1_WORKAROUND_BAD_PCIE_CLASS */
+
+#ifdef CONFIG_WSP_DD1_WORKAROUND_DD1_TCE_BUGS
+        /* XXX Disable TCE caching, it doesn't work on DD1 */
+        out_be64(hose->cfg_data + 0xe50,
+                 in_be64(hose->cfg_data + 0xe50) | (3ull << 62));
+        printk("PCI-E DEBUG CONTROL 5 = 0x%llx\n", in_be64(hose->cfg_data + 0xe50));
+#endif
+
+        /* Configure M32A and IO. IO is hard wired to be 1M for now */
+        out_be64(hose->cfg_data + PCIE_REG_IO_BASE_ADDR, hose->io_base_phys);
+        out_be64(hose->cfg_data + PCIE_REG_IO_BASE_MASK,
+                 (~(hose->io_resource.end - hose->io_resource.start)) &
+                 0x3fffffff000ul);
+        out_be64(hose->cfg_data + PCIE_REG_IO_START_ADDR, 0 | 1);
+
+        out_be64(hose->cfg_data + PCIE_REG_M32A_BASE_ADDR,
+                 hose->mem_resources[0].start);
+        printk("Want to write to M32A_BASE_MASK : 0x%llx\n",
+                 (~(hose->mem_resources[0].end -
+                    hose->mem_resources[0].start)) & 0x3ffffff0000ul);
+        out_be64(hose->cfg_data + PCIE_REG_M32A_BASE_MASK,
+                 (~(hose->mem_resources[0].end -
+                    hose->mem_resources[0].start)) & 0x3ffffff0000ul);
+        out_be64(hose->cfg_data + PCIE_REG_M32A_START_ADDR,
+                 (hose->mem_resources[0].start - hose->pci_mem_offset) | 1);
+
+        /* Clear all TVT entries
+         *
+         * XX Might get TVT count from device-tree
+         */
+        for (i = 0; i < IODA_TVT_COUNT; i++) {
+                out_be64(hose->cfg_data + PCIE_REG_IODA_ADDR,
+                         PCIE_REG_IODA_AD_TBL_TVT | i);
+                out_be64(hose->cfg_data + PCIE_REG_IODA_DATA1, 0);
+                out_be64(hose->cfg_data + PCIE_REG_IODA_DATA0, 0);
+        }
+
+        /* Kill the TCE cache */
+        out_be64(hose->cfg_data + PCIE_REG_PHB_CONFIG,
+                 in_be64(hose->cfg_data + PCIE_REG_PHB_CONFIG) |
+                 PCIE_REG_PHBC_64B_TCE_EN);
+
+        /* Enable 32 & 64-bit MSIs, IO space and M32A */
+        val = PCIE_REG_PHBC_32BIT_MSI_EN |
+              PCIE_REG_PHBC_IO_EN |
+              PCIE_REG_PHBC_64BIT_MSI_EN |
+              PCIE_REG_PHBC_M32A_EN;
+        if (iommu_is_off)
+                val |= PCIE_REG_PHBC_DMA_XLATE_BYPASS;
+        pr_debug("Will write config: 0x%llx\n", val);
+        out_be64(hose->cfg_data + PCIE_REG_PHB_CONFIG, val);
+
+        /* Enable error reporting */
+        out_be64(hose->cfg_data + 0xe00,
+                 in_be64(hose->cfg_data + 0xe00) | 0x0008000000000000ull);
+
+        /* Mask an error that's generated when doing config space probe
+         *
+         * XXX Maybe we should only mask it around config space cycles... that or
+         * ignore it when we know we had a config space cycle recently ?
+         */
+        out_be64(hose->cfg_data + PCIE_REG_DMA_ERR_STATUS_MASK, 0x8000000000000000ull);
+        out_be64(hose->cfg_data + PCIE_REG_DMA_ERR1_STATUS_MASK, 0x8000000000000000ull);
+
+        /* Enable UTL errors, for now, all of them got to UTL irq 1
+         *
+         * We similarily mask one UTL error caused apparently during normal
+         * probing. We also mask the link up error
+         */
+        out_be64(hose->cfg_data + PCIE_UTL_SYS_BUS_AGENT_ERR_SEV, 0);
+        out_be64(hose->cfg_data + PCIE_UTL_RC_ERR_SEVERITY, 0);
+        out_be64(hose->cfg_data + PCIE_UTL_PCIE_PORT_ERROR_SEV, 0);
+        out_be64(hose->cfg_data + PCIE_UTL_SYS_BUS_AGENT_IRQ_EN, 0xffffffff00000000ull);
+        out_be64(hose->cfg_data + PCIE_UTL_PCIE_PORT_IRQ_EN, 0xff5fffff00000000ull);
+        out_be64(hose->cfg_data + PCIE_UTL_EP_ERR_IRQ_EN, 0xffffffff00000000ull);
+
+        DUMP_REG(PCIE_REG_IO_BASE_ADDR);
+        DUMP_REG(PCIE_REG_IO_BASE_MASK);
+        DUMP_REG(PCIE_REG_IO_START_ADDR);
+        DUMP_REG(PCIE_REG_M32A_BASE_ADDR);
+        DUMP_REG(PCIE_REG_M32A_BASE_MASK);
+        DUMP_REG(PCIE_REG_M32A_START_ADDR);
+        DUMP_REG(PCIE_REG_M32B_BASE_ADDR);
+        DUMP_REG(PCIE_REG_M32B_BASE_MASK);
+        DUMP_REG(PCIE_REG_M32B_START_ADDR);
+        DUMP_REG(PCIE_REG_M64_BASE_ADDR);
+        DUMP_REG(PCIE_REG_M64_BASE_MASK);
+        DUMP_REG(PCIE_REG_M64_START_ADDR);
+        DUMP_REG(PCIE_REG_PHB_CONFIG);
+}
+
+static void wsp_pci_wait_io_idle(struct wsp_phb *phb, unsigned long port)
+{
+        u64 val;
+        int i;
+
+        for (i = 0; i < 10000; i++) {
+                val = in_be64(phb->hose->cfg_data + 0xe08);
+                if ((val & 0x1900000000000000ull) == 0x0100000000000000ull)
+                        return;
+                udelay(1);
+        }
+        pr_warning("PCI IO timeout on domain %d port 0x%lx\n",
+                   phb->hose->global_number, port);
+}
+
+#define DEF_PCI_AC_RET_pio(name, ret, at, al, aa)               \
+static ret wsp_pci_##name at                                    \
+{                                                               \
+        struct iowa_bus *bus;                                   \
+        struct wsp_phb *phb;                                    \
+        unsigned long flags;                                    \
+        ret rval;                                               \
+        bus = iowa_pio_find_bus(aa);                            \
+        WARN_ON(!bus);                                          \
+        phb = bus->private;                                     \
+        spin_lock_irqsave(&phb->lock, flags);                   \
+        wsp_pci_wait_io_idle(phb, aa);                          \
+        rval = __do_##name al;                                  \
+        spin_unlock_irqrestore(&phb->lock, flags);              \
+        return rval;                                            \
+}
+
+#define DEF_PCI_AC_NORET_pio(name, at, al, aa)                  \
+static void wsp_pci_##name at                                   \
+{                                                               \
+        struct iowa_bus *bus;                                   \
+        struct wsp_phb *phb;                                    \
+        unsigned long flags;                                    \
+        bus = iowa_pio_find_bus(aa);                            \
+        WARN_ON(!bus);                                          \
+        phb = bus->private;                                     \
+        spin_lock_irqsave(&phb->lock, flags);                   \
+        wsp_pci_wait_io_idle(phb, aa);                          \
+        __do_##name al;                                         \
+        spin_unlock_irqrestore(&phb->lock, flags);              \
+}
+
+#define DEF_PCI_AC_RET_mem(name, ret, at, al, aa)
+#define DEF_PCI_AC_NORET_mem(name, at, al, aa)
+
+#define DEF_PCI_AC_RET(name, ret, at, al, space, aa)            \
+        DEF_PCI_AC_RET_##space(name, ret, at, al, aa)
+
+#define DEF_PCI_AC_NORET(name, at, al, space, aa)               \
+        DEF_PCI_AC_NORET_##space(name, at, al, aa)              \
+
+
+#include <asm/io-defs.h>
+
+#undef DEF_PCI_AC_RET
+#undef DEF_PCI_AC_NORET
+
+static struct ppc_pci_io wsp_pci_iops = {
+        .inb = wsp_pci_inb,
+        .inw = wsp_pci_inw,
+        .inl = wsp_pci_inl,
+        .outb = wsp_pci_outb,
+        .outw = wsp_pci_outw,
+        .outl = wsp_pci_outl,
+        .insb = wsp_pci_insb,
+        .insw = wsp_pci_insw,
+        .insl = wsp_pci_insl,
+        .outsb = wsp_pci_outsb,
+        .outsw = wsp_pci_outsw,
+        .outsl = wsp_pci_outsl,
+};
+
+static int __init wsp_setup_one_phb(struct device_node *np)
+{
+        struct pci_controller *hose;
+        struct wsp_phb *phb;
+
+        pr_info("PCI: Setting up PCIe host bridge 0x%s\n", np->full_name);
+
+        phb = zalloc_maybe_bootmem(sizeof(struct wsp_phb), GFP_KERNEL);
+        if (!phb)
+                return -ENOMEM;
+        hose = pcibios_alloc_controller(np);
+        if (!hose) {
+                /* Can't really free the phb */
+                return -ENOMEM;
+        }
+        hose->private_data = phb;
+        phb->hose = hose;
+
+        INIT_LIST_HEAD(&phb->dma_tables);
+        spin_lock_init(&phb->lock);
+
+        /* XXX Use bus-range property ? */
+        hose->first_busno = 0;
+        hose->last_busno = 0xff;
+
+        /* We use cfg_data as the address for the whole bridge MMIO space
+         */
+        hose->cfg_data = of_iomap(hose->dn, 0);
+
+        pr_debug("PCIe registers mapped at 0x%p\n", hose->cfg_data);
+
+        /* Get the ranges of the device-tree */
+        pci_process_bridge_OF_ranges(hose, np, 0);
+
+        /* XXX Force re-assigning of everything for now */
+        pci_add_flags(PCI_REASSIGN_ALL_BUS | PCI_REASSIGN_ALL_RSRC |
+                      PCI_ENABLE_PROC_DOMAINS);
+        pci_probe_only = 0;
+
+        /* Calculate how the TCE space is divided */
+        phb->dma32_base         = 0;
+        phb->dma32_num_regions  = NUM_DMA32_REGIONS;
+        if (phb->dma32_num_regions > MAX_TABLE_TVT_COUNT) {
+                pr_warning("IOMMU: Clamped to %d DMA32 regions\n",
+                           MAX_TABLE_TVT_COUNT);
+                phb->dma32_num_regions = MAX_TABLE_TVT_COUNT;
+        }
+        phb->dma32_region_size  = 0x80000000 / phb->dma32_num_regions;
+
+        BUG_ON(!is_power_of_2(phb->dma32_region_size));
+
+        /* Setup config ops */
+        hose->ops = &wsp_pcie_pci_ops;
+
+        /* Configure the HW */
+        wsp_pcie_configure_hw(hose);
+
+        /* Instanciate IO workarounds */
+        iowa_register_bus(hose, &wsp_pci_iops, NULL, phb);
+#ifdef CONFIG_PCI_MSI
+        wsp_setup_phb_msi(hose);
+#endif
+
+        /* Add to global list */
+        list_add(&phb->all, &wsp_phbs);
+
+        return 0;
+}
+
+void __init wsp_setup_pci(void)
+{
+        struct device_node *np;
+        int rc;
+
+        /* Find host bridges */
+        for_each_compatible_node(np, "pciex", PCIE_COMPATIBLE) {
+                rc = wsp_setup_one_phb(np);
+                if (rc)
+                        pr_err("Failed to setup PCIe bridge %s, rc=%d\n",
+                               np->full_name, rc);
+        }
+
+        /* Establish device-tree linkage */
+        pci_devs_phb_init();
+
+        /* Set DMA ops to use TCEs */
+        if (iommu_is_off) {
+                pr_info("PCI-E: Disabled TCEs, using direct DMA\n");
+                set_pci_dma_ops(&dma_direct_ops);
+        } else {
+                ppc_md.pci_dma_dev_setup = wsp_pci_dma_dev_setup;
+                ppc_md.tce_build = tce_build_wsp;
+                ppc_md.tce_free = tce_free_wsp;
+                set_pci_dma_ops(&dma_iommu_ops);
+        }
+}
+
+#define err_debug(fmt...)       pr_debug(fmt)
+//#define err_debug(fmt...)
+
+static int __init wsp_pci_get_err_irq_no_dt(struct device_node *np)
+{
+        const u32 *prop;
+        int hw_irq;
+
+        /* Ok, no interrupts property, let's try to find our child P2P */
+        np = of_get_next_child(np, NULL);
+        if (np == NULL)
+                return 0;
+
+        /* Grab it's interrupt map */
+        prop = of_get_property(np, "interrupt-map", NULL);
+        if (prop == NULL)
+                return 0;
+
+        /* Grab one of the interrupts in there, keep the low 4 bits */
+        hw_irq = prop[5] & 0xf;
+
+        /* 0..4 for PHB 0 and 5..9 for PHB 1 */
+        if (hw_irq < 5)
+                hw_irq = 4;
+        else
+                hw_irq = 9;
+        hw_irq |= prop[5] & ~0xf;
+
+        err_debug("PCI: Using 0x%x as error IRQ for %s\n",
+                  hw_irq, np->parent->full_name);
+        return irq_create_mapping(NULL, hw_irq);
+}
+
+static const struct {
+        u32 offset;
+        const char *name;
+} wsp_pci_regs[] = {
+#define DREG(x) { PCIE_REG_##x, #x }
+#define DUTL(x) { PCIE_UTL_##x, "UTL_" #x }
+        /* Architected registers except CONFIG_ and IODA
+         * to avoid side effects
+         */
+        DREG(DMA_CHAN_STATUS),
+        DREG(CPU_LOADSTORE_STATUS),
+        DREG(LOCK0),
+        DREG(LOCK1),
+        DREG(PHB_CONFIG),
+        DREG(IO_BASE_ADDR),
+        DREG(IO_BASE_MASK),
+        DREG(IO_START_ADDR),
+        DREG(M32A_BASE_ADDR),
+        DREG(M32A_BASE_MASK),
+        DREG(M32A_START_ADDR),
+        DREG(M32B_BASE_ADDR),
+        DREG(M32B_BASE_MASK),
+        DREG(M32B_START_ADDR),
+        DREG(M64_BASE_ADDR),
+        DREG(M64_BASE_MASK),
+        DREG(M64_START_ADDR),
+        DREG(TCE_KILL),
+        DREG(LOCK2),
+        DREG(PHB_GEN_CAP),
+        DREG(PHB_TCE_CAP),
+        DREG(PHB_IRQ_CAP),
+        DREG(PHB_EEH_CAP),
+        DREG(PAPR_ERR_INJ_CONTROL),
+        DREG(PAPR_ERR_INJ_ADDR),
+        DREG(PAPR_ERR_INJ_MASK),
+
+        /* UTL core regs */
+        DUTL(SYS_BUS_CONTROL),
+        DUTL(STATUS),
+        DUTL(SYS_BUS_AGENT_STATUS),
+        DUTL(SYS_BUS_AGENT_ERR_SEV),
+        DUTL(SYS_BUS_AGENT_IRQ_EN),
+        DUTL(SYS_BUS_BURST_SZ_CONF),
+        DUTL(REVISION_ID),
+        DUTL(OUT_POST_HDR_BUF_ALLOC),
+        DUTL(OUT_POST_DAT_BUF_ALLOC),
+        DUTL(IN_POST_HDR_BUF_ALLOC),
+        DUTL(IN_POST_DAT_BUF_ALLOC),
+        DUTL(OUT_NP_BUF_ALLOC),
+        DUTL(IN_NP_BUF_ALLOC),
+        DUTL(PCIE_TAGS_ALLOC),
+        DUTL(GBIF_READ_TAGS_ALLOC),
+
+        DUTL(PCIE_PORT_CONTROL),
+        DUTL(PCIE_PORT_STATUS),
+        DUTL(PCIE_PORT_ERROR_SEV),
+        DUTL(PCIE_PORT_IRQ_EN),
+        DUTL(RC_STATUS),
+        DUTL(RC_ERR_SEVERITY),
+        DUTL(RC_IRQ_EN),
+        DUTL(EP_STATUS),
+        DUTL(EP_ERR_SEVERITY),
+        DUTL(EP_ERR_IRQ_EN),
+        DUTL(PCI_PM_CTRL1),
+        DUTL(PCI_PM_CTRL2),
+
+        /* PCIe stack regs */
+        DREG(SYSTEM_CONFIG1),
+        DREG(SYSTEM_CONFIG2),
+        DREG(EP_SYSTEM_CONFIG),
+        DREG(EP_FLR),
+        DREG(EP_BAR_CONFIG),
+        DREG(LINK_CONFIG),
+        DREG(PM_CONFIG),
+        DREG(DLP_CONTROL),
+        DREG(DLP_STATUS),
+        DREG(ERR_REPORT_CONTROL),
+        DREG(SLOT_CONTROL1),
+        DREG(SLOT_CONTROL2),
+        DREG(UTL_CONFIG),
+        DREG(BUFFERS_CONFIG),
+        DREG(ERROR_INJECT),
+        DREG(SRIOV_CONFIG),
+        DREG(PF0_SRIOV_STATUS),
+        DREG(PF1_SRIOV_STATUS),
+        DREG(PORT_NUMBER),
+        DREG(POR_SYSTEM_CONFIG),
+
+        /* Internal logic regs */
+        DREG(PHB_VERSION),
+        DREG(RESET),
+        DREG(PHB_CONTROL),
+        DREG(PHB_TIMEOUT_CONTROL1),
+        DREG(PHB_QUIESCE_DMA),
+        DREG(PHB_DMA_READ_TAG_ACTV),
+        DREG(PHB_TCE_READ_TAG_ACTV),
+
+        /* FIR registers */
+        DREG(LEM_FIR_ACCUM),
+        DREG(LEM_FIR_AND_MASK),
+        DREG(LEM_FIR_OR_MASK),
+        DREG(LEM_ACTION0),
+        DREG(LEM_ACTION1),
+        DREG(LEM_ERROR_MASK),
+        DREG(LEM_ERROR_AND_MASK),
+        DREG(LEM_ERROR_OR_MASK),
+
+        /* Error traps registers */
+        DREG(PHB_ERR_STATUS),
+        DREG(PHB_ERR_STATUS),
+        DREG(PHB_ERR1_STATUS),
+        DREG(PHB_ERR_INJECT),
+        DREG(PHB_ERR_LEM_ENABLE),
+        DREG(PHB_ERR_IRQ_ENABLE),
+        DREG(PHB_ERR_FREEZE_ENABLE),
+        DREG(PHB_ERR_SIDE_ENABLE),
+        DREG(PHB_ERR_LOG_0),
+        DREG(PHB_ERR_LOG_1),
+        DREG(PHB_ERR_STATUS_MASK),
+        DREG(PHB_ERR1_STATUS_MASK),
+        DREG(MMIO_ERR_STATUS),
+        DREG(MMIO_ERR1_STATUS),
+        DREG(MMIO_ERR_INJECT),
+        DREG(MMIO_ERR_LEM_ENABLE),
+        DREG(MMIO_ERR_IRQ_ENABLE),
+        DREG(MMIO_ERR_FREEZE_ENABLE),
+        DREG(MMIO_ERR_SIDE_ENABLE),
+        DREG(MMIO_ERR_LOG_0),
+        DREG(MMIO_ERR_LOG_1),
+        DREG(MMIO_ERR_STATUS_MASK),
+        DREG(MMIO_ERR1_STATUS_MASK),
+        DREG(DMA_ERR_STATUS),
+        DREG(DMA_ERR1_STATUS),
+        DREG(DMA_ERR_INJECT),
+        DREG(DMA_ERR_LEM_ENABLE),
+        DREG(DMA_ERR_IRQ_ENABLE),
+        DREG(DMA_ERR_FREEZE_ENABLE),
+        DREG(DMA_ERR_SIDE_ENABLE),
+        DREG(DMA_ERR_LOG_0),
+        DREG(DMA_ERR_LOG_1),
+        DREG(DMA_ERR_STATUS_MASK),
+        DREG(DMA_ERR1_STATUS_MASK),
+
+        /* Debug and Trace registers */
+        DREG(PHB_DEBUG_CONTROL0),
+        DREG(PHB_DEBUG_STATUS0),
+        DREG(PHB_DEBUG_CONTROL1),
+        DREG(PHB_DEBUG_STATUS1),
+        DREG(PHB_DEBUG_CONTROL2),
+        DREG(PHB_DEBUG_STATUS2),
+        DREG(PHB_DEBUG_CONTROL3),
+        DREG(PHB_DEBUG_STATUS3),
+        DREG(PHB_DEBUG_CONTROL4),
+        DREG(PHB_DEBUG_STATUS4),
+        DREG(PHB_DEBUG_CONTROL5),
+        DREG(PHB_DEBUG_STATUS5),
+
+        /* Don't seem to exist ...
+        DREG(PHB_DEBUG_CONTROL6),
+        DREG(PHB_DEBUG_STATUS6),
+        */
+};
+
+static int wsp_pci_regs_show(struct seq_file *m, void *private)
+{
+        struct wsp_phb *phb = m->private;
+        struct pci_controller *hose = phb->hose;
+        int i;
+
+        for (i = 0; i < ARRAY_SIZE(wsp_pci_regs); i++) {
+                /* Skip write-only regs */
+                if (wsp_pci_regs[i].offset == 0xc08 ||
+                    wsp_pci_regs[i].offset == 0xc10 ||
+                    wsp_pci_regs[i].offset == 0xc38 ||
+                    wsp_pci_regs[i].offset == 0xc40)
+                        continue;
+                seq_printf(m, "0x%03x: 0x%016llx %s\n",
+                           wsp_pci_regs[i].offset,
+                           in_be64(hose->cfg_data + wsp_pci_regs[i].offset),
+                           wsp_pci_regs[i].name);
+        }
+        return 0;
+}
+
+static int wsp_pci_regs_open(struct inode *inode, struct file *file)
+{
+        return single_open(file, wsp_pci_regs_show, inode->i_private);
+}
+
+static const struct file_operations wsp_pci_regs_fops = {
+        .open = wsp_pci_regs_open,
+        .read = seq_read,
+        .llseek = seq_lseek,
+        .release = single_release,
+};
+
+static int wsp_pci_reg_set(void *data, u64 val)
+{
+        out_be64((void __iomem *)data, val);
+        return 0;
+}
+
+static int wsp_pci_reg_get(void *data, u64 *val)
+{
+        *val = in_be64((void __iomem *)data);
+        return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(wsp_pci_reg_fops, wsp_pci_reg_get, wsp_pci_reg_set, "0x%llx\n");
+
+static irqreturn_t wsp_pci_err_irq(int irq, void *dev_id)
+{
+        struct wsp_phb *phb = dev_id;
+        struct pci_controller *hose = phb->hose;
+        irqreturn_t handled = IRQ_NONE;
+        struct wsp_pcie_err_log_data ed;
+
+        pr_err("PCI: Error interrupt on %s (PHB %d)\n",
+               hose->dn->full_name, hose->global_number);
+ again:
+        memset(&ed, 0, sizeof(ed));
+
+        /* Read and clear UTL errors */
+        ed.utl_sys_err = in_be64(hose->cfg_data + PCIE_UTL_SYS_BUS_AGENT_STATUS);
+        if (ed.utl_sys_err)
+                out_be64(hose->cfg_data + PCIE_UTL_SYS_BUS_AGENT_STATUS, ed.utl_sys_err);
+        ed.utl_port_err = in_be64(hose->cfg_data + PCIE_UTL_PCIE_PORT_STATUS);
+        if (ed.utl_port_err)
+                out_be64(hose->cfg_data + PCIE_UTL_PCIE_PORT_STATUS, ed.utl_port_err);
+        ed.utl_rc_err = in_be64(hose->cfg_data + PCIE_UTL_RC_STATUS);
+        if (ed.utl_rc_err)
+                out_be64(hose->cfg_data + PCIE_UTL_RC_STATUS, ed.utl_rc_err);
+
+        /* Read and clear main trap errors */
+        ed.phb_err = in_be64(hose->cfg_data + PCIE_REG_PHB_ERR_STATUS);
+        if (ed.phb_err) {
+                ed.phb_err1 = in_be64(hose->cfg_data + PCIE_REG_PHB_ERR1_STATUS);
+                ed.phb_log0 = in_be64(hose->cfg_data + PCIE_REG_PHB_ERR_LOG_0);
+                ed.phb_log1 = in_be64(hose->cfg_data + PCIE_REG_PHB_ERR_LOG_1);
+                out_be64(hose->cfg_data + PCIE_REG_PHB_ERR1_STATUS, 0);
+                out_be64(hose->cfg_data + PCIE_REG_PHB_ERR_STATUS, 0);
+        }
+        ed.mmio_err = in_be64(hose->cfg_data + PCIE_REG_MMIO_ERR_STATUS);
+        if (ed.mmio_err) {
+                ed.mmio_err1 = in_be64(hose->cfg_data + PCIE_REG_MMIO_ERR1_STATUS);
+                ed.mmio_log0 = in_be64(hose->cfg_data + PCIE_REG_MMIO_ERR_LOG_0);
+                ed.mmio_log1 = in_be64(hose->cfg_data + PCIE_REG_MMIO_ERR_LOG_1);
+                out_be64(hose->cfg_data + PCIE_REG_MMIO_ERR1_STATUS, 0);
+                out_be64(hose->cfg_data + PCIE_REG_MMIO_ERR_STATUS, 0);
+        }
+        ed.dma_err = in_be64(hose->cfg_data + PCIE_REG_DMA_ERR_STATUS);
+        if (ed.dma_err) {
+                ed.dma_err1 = in_be64(hose->cfg_data + PCIE_REG_DMA_ERR1_STATUS);
+                ed.dma_log0 = in_be64(hose->cfg_data + PCIE_REG_DMA_ERR_LOG_0);
+                ed.dma_log1 = in_be64(hose->cfg_data + PCIE_REG_DMA_ERR_LOG_1);
+                out_be64(hose->cfg_data + PCIE_REG_DMA_ERR1_STATUS, 0);
+                out_be64(hose->cfg_data + PCIE_REG_DMA_ERR_STATUS, 0);
+        }
+
+        /* Now print things out */
+        if (ed.phb_err) {
+                pr_err("   PHB Error Status      : 0x%016llx\n", ed.phb_err);
+                pr_err("   PHB First Error Status: 0x%016llx\n", ed.phb_err1);
+                pr_err("   PHB Error Log 0       : 0x%016llx\n", ed.phb_log0);
+                pr_err("   PHB Error Log 1       : 0x%016llx\n", ed.phb_log1);
+        }
+        if (ed.mmio_err) {
+                pr_err("  MMIO Error Status      : 0x%016llx\n", ed.mmio_err);
+                pr_err("  MMIO First Error Status: 0x%016llx\n", ed.mmio_err1);
+                pr_err("  MMIO Error Log 0       : 0x%016llx\n", ed.mmio_log0);
+                pr_err("  MMIO Error Log 1       : 0x%016llx\n", ed.mmio_log1);
+        }
+        if (ed.dma_err) {
+                pr_err("   DMA Error Status      : 0x%016llx\n", ed.dma_err);
+                pr_err("   DMA First Error Status: 0x%016llx\n", ed.dma_err1);
+                pr_err("   DMA Error Log 0       : 0x%016llx\n", ed.dma_log0);
+                pr_err("   DMA Error Log 1       : 0x%016llx\n", ed.dma_log1);
+        }
+        if (ed.utl_sys_err)
+                pr_err("   UTL Sys Error Status  : 0x%016llx\n", ed.utl_sys_err);
+        if (ed.utl_port_err)
+                pr_err("   UTL Port Error Status : 0x%016llx\n", ed.utl_port_err);
+        if (ed.utl_rc_err)
+                pr_err("   UTL RC Error Status   : 0x%016llx\n", ed.utl_rc_err);
+
+        /* Interrupts are caused by the error traps. If we had any error there
+         * we loop again in case the UTL buffered some new stuff between
+         * going there and going to the traps
+         */
+        if (ed.dma_err || ed.mmio_err || ed.phb_err) {
+                handled = IRQ_HANDLED;
+                goto again;
+        }
+        return handled;
+}
+
+static void __init wsp_setup_pci_err_reporting(struct wsp_phb *phb)
+{
+        struct pci_controller *hose = phb->hose;
+        int err_irq, i, rc;
+        char fname[16];
+
+        /* Create a debugfs file for that PHB */
+        sprintf(fname, "phb%d", phb->hose->global_number);
+        phb->ddir = debugfs_create_dir(fname, powerpc_debugfs_root);
+
+        /* Some useful debug output */
+        if (phb->ddir) {
+                struct dentry *d = debugfs_create_dir("regs", phb->ddir);
+                char tmp[64];
+
+                for (i = 0; i < ARRAY_SIZE(wsp_pci_regs); i++) {
+                        sprintf(tmp, "%03x_%s", wsp_pci_regs[i].offset,
+                                wsp_pci_regs[i].name);
+                        debugfs_create_file(tmp, 0600, d,
+                                            hose->cfg_data + wsp_pci_regs[i].offset,
+                                            &wsp_pci_reg_fops);
+                }
+                debugfs_create_file("all_regs", 0600, phb->ddir, phb, &wsp_pci_regs_fops);
+        }
+
+        /* Find the IRQ number for that PHB */
+        err_irq = irq_of_parse_and_map(hose->dn, 0);
+        if (err_irq == 0)
+                /* XXX Error IRQ lacking from device-tree */
+                err_irq = wsp_pci_get_err_irq_no_dt(hose->dn);
+        if (err_irq == 0) {
+                pr_err("PCI: Failed to fetch error interrupt for %s\n",
+                       hose->dn->full_name);
+                return;
+        }
+        /* Request it */
+        rc = request_irq(err_irq, wsp_pci_err_irq, 0, "wsp_pci error", phb);
+        if (rc) {
+                pr_err("PCI: Failed to request interrupt for %s\n",
+                       hose->dn->full_name);
+        }
+        /* Enable interrupts for all errors for now */
+        out_be64(hose->cfg_data + PCIE_REG_PHB_ERR_IRQ_ENABLE, 0xffffffffffffffffull);
+        out_be64(hose->cfg_data + PCIE_REG_MMIO_ERR_IRQ_ENABLE, 0xffffffffffffffffull);
+        out_be64(hose->cfg_data + PCIE_REG_DMA_ERR_IRQ_ENABLE, 0xffffffffffffffffull);
+}
+
+/*
+ * This is called later to hookup with the error interrupt
+ */
+static int __init wsp_setup_pci_late(void)
+{
+        struct wsp_phb *phb;
+
+        list_for_each_entry(phb, &wsp_phbs, all)
+                wsp_setup_pci_err_reporting(phb);
+
+        return 0;
+}
+arch_initcall(wsp_setup_pci_late);
diff --git a/arch/powerpc/platforms/wsp/wsp_pci.h b/arch/powerpc/platforms/wsp/wsp_pci.h
new file mode 100644
index 000000000000..52e9bd95250d
--- /dev/null
+++ b/arch/powerpc/platforms/wsp/wsp_pci.h
@@ -0,0 +1,268 @@
+/*
+ * Copyright 2010 Ben Herrenschmidt, IBM Corporation
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#ifndef __WSP_PCI_H
+#define __WSP_PCI_H
+
+/* Architected registers */
+#define PCIE_REG_DMA_CHAN_STATUS        0x110
+#define PCIE_REG_CPU_LOADSTORE_STATUS   0x120
+
+#define PCIE_REG_CONFIG_DATA            0x130
+#define PCIE_REG_LOCK0                  0x138
+#define PCIE_REG_CONFIG_ADDRESS         0x140
+#define   PCIE_REG_CA_ENABLE                    0x8000000000000000ull
+#define   PCIE_REG_CA_BUS_MASK                  0x0ff0000000000000ull
+#define   PCIE_REG_CA_BUS_SHIFT                 (20+32)
+#define   PCIE_REG_CA_DEV_MASK                  0x000f800000000000ull
+#define   PCIE_REG_CA_DEV_SHIFT                 (15+32)
+#define   PCIE_REG_CA_FUNC_MASK                 0x0000700000000000ull
+#define   PCIE_REG_CA_FUNC_SHIFT                (12+32)
+#define   PCIE_REG_CA_REG_MASK                  0x00000fff00000000ull
+#define   PCIE_REG_CA_REG_SHIFT                 ( 0+32)
+#define   PCIE_REG_CA_BE_MASK                   0x00000000f0000000ull
+#define   PCIE_REG_CA_BE_SHIFT                  (   28)
+#define PCIE_REG_LOCK1                  0x148
+
+#define PCIE_REG_PHB_CONFIG             0x160
+#define   PCIE_REG_PHBC_64B_TCE_EN              0x2000000000000000ull
+#define   PCIE_REG_PHBC_MMIO_DMA_FREEZE_EN      0x1000000000000000ull
+#define   PCIE_REG_PHBC_32BIT_MSI_EN            0x0080000000000000ull
+#define   PCIE_REG_PHBC_M64_EN                  0x0040000000000000ull
+#define   PCIE_REG_PHBC_IO_EN                   0x0008000000000000ull
+#define   PCIE_REG_PHBC_64BIT_MSI_EN            0x0002000000000000ull
+#define   PCIE_REG_PHBC_M32A_EN                 0x0000800000000000ull
+#define   PCIE_REG_PHBC_M32B_EN                 0x0000400000000000ull
+#define   PCIE_REG_PHBC_MSI_PE_VALIDATE         0x0000200000000000ull
+#define   PCIE_REG_PHBC_DMA_XLATE_BYPASS        0x0000100000000000ull
+
+#define PCIE_REG_IO_BASE_ADDR           0x170
+#define PCIE_REG_IO_BASE_MASK           0x178
+#define PCIE_REG_IO_START_ADDR          0x180
+
+#define PCIE_REG_M32A_BASE_ADDR         0x190
+#define PCIE_REG_M32A_BASE_MASK         0x198
+#define PCIE_REG_M32A_START_ADDR        0x1a0
+
+#define PCIE_REG_M32B_BASE_ADDR         0x1b0
+#define PCIE_REG_M32B_BASE_MASK         0x1b8
+#define PCIE_REG_M32B_START_ADDR        0x1c0
+
+#define PCIE_REG_M64_BASE_ADDR          0x1e0
+#define PCIE_REG_M64_BASE_MASK          0x1e8
+#define PCIE_REG_M64_START_ADDR         0x1f0
+
+#define PCIE_REG_TCE_KILL               0x210
+#define   PCIE_REG_TCEKILL_SINGLE       0x8000000000000000ull
+#define   PCIE_REG_TCEKILL_ADDR_MASK    0x000003fffffffff8ull
+#define   PCIE_REG_TCEKILL_PS_4K        0
+#define   PCIE_REG_TCEKILL_PS_64K       1
+#define   PCIE_REG_TCEKILL_PS_16M       2
+#define   PCIE_REG_TCEKILL_PS_16G       3
+
+#define PCIE_REG_IODA_ADDR              0x220
+#define   PCIE_REG_IODA_AD_AUTOINC      0x8000000000000000ull
+#define   PCIE_REG_IODA_AD_TBL_MVT      0x0005000000000000ull
+#define   PCIE_REG_IODA_AD_TBL_PELT     0x0006000000000000ull
+#define   PCIE_REG_IODA_AD_TBL_PESTA    0x0007000000000000ull
+#define   PCIE_REG_IODA_AD_TBL_PESTB    0x0008000000000000ull
+#define   PCIE_REG_IODA_AD_TBL_TVT      0x0009000000000000ull
+#define   PCIE_REG_IODA_AD_TBL_TCE      0x000a000000000000ull
+#define PCIE_REG_IODA_DATA0             0x228
+#define PCIE_REG_IODA_DATA1             0x230
+
+#define PCIE_REG_LOCK2                  0x240
+
+#define PCIE_REG_PHB_GEN_CAP            0x250
+#define PCIE_REG_PHB_TCE_CAP            0x258
+#define PCIE_REG_PHB_IRQ_CAP            0x260
+#define PCIE_REG_PHB_EEH_CAP            0x268
+
+#define PCIE_REG_PAPR_ERR_INJ_CONTROL   0x2b0
+#define PCIE_REG_PAPR_ERR_INJ_ADDR      0x2b8
+#define PCIE_REG_PAPR_ERR_INJ_MASK      0x2c0
+
+
+#define PCIE_REG_SYS_CFG1               0x600
+#define   PCIE_REG_SYS_CFG1_CLASS_CODE  0x0000000000ffffffull
+
+#define IODA_TVT0_TTA_MASK              0x000fffffffff0000ull
+#define IODA_TVT0_TTA_SHIFT             4
+#define IODA_TVT0_BUSNUM_VALID_MASK     0x000000000000e000ull
+#define IODA_TVT0_TCE_TABLE_SIZE_MASK   0x0000000000001f00ull
+#define IODA_TVT0_TCE_TABLE_SIZE_SHIFT  8
+#define IODA_TVT0_BUSNUM_VALUE_MASK     0x00000000000000ffull
+#define IODA_TVT0_BUSNUM_VALID_SHIFT    0
+#define IODA_TVT1_DEVNUM_VALID          0x2000000000000000ull
+#define IODA_TVT1_DEVNUM_VALUE_MASK     0x1f00000000000000ull
+#define IODA_TVT1_DEVNUM_VALUE_SHIFT    56
+#define IODA_TVT1_FUNCNUM_VALID         0x0008000000000000ull
+#define IODA_TVT1_FUNCNUM_VALUE_MASK    0x0007000000000000ull
+#define IODA_TVT1_FUNCNUM_VALUE_SHIFT   48
+#define IODA_TVT1_IO_PAGE_SIZE_MASK     0x00001f0000000000ull
+#define IODA_TVT1_IO_PAGE_SIZE_SHIFT    40
+#define IODA_TVT1_PE_NUMBER_MASK        0x000000000000003full
+#define IODA_TVT1_PE_NUMBER_SHIFT       0
+
+#define IODA_TVT_COUNT                  64
+
+/* UTL Core registers */
+#define PCIE_UTL_SYS_BUS_CONTROL        0x400
+#define PCIE_UTL_STATUS                 0x408
+#define PCIE_UTL_SYS_BUS_AGENT_STATUS   0x410
+#define PCIE_UTL_SYS_BUS_AGENT_ERR_SEV  0x418
+#define PCIE_UTL_SYS_BUS_AGENT_IRQ_EN   0x420
+#define PCIE_UTL_SYS_BUS_BURST_SZ_CONF  0x440
+#define PCIE_UTL_REVISION_ID            0x448
+
+#define PCIE_UTL_OUT_POST_HDR_BUF_ALLOC 0x4c0
+#define PCIE_UTL_OUT_POST_DAT_BUF_ALLOC 0x4d0
+#define PCIE_UTL_IN_POST_HDR_BUF_ALLOC  0x4e0
+#define PCIE_UTL_IN_POST_DAT_BUF_ALLOC  0x4f0
+#define PCIE_UTL_OUT_NP_BUF_ALLOC       0x500
+#define PCIE_UTL_IN_NP_BUF_ALLOC        0x510
+#define PCIE_UTL_PCIE_TAGS_ALLOC        0x520
+#define PCIE_UTL_GBIF_READ_TAGS_ALLOC   0x530
+
+#define PCIE_UTL_PCIE_PORT_CONTROL      0x540
+#define PCIE_UTL_PCIE_PORT_STATUS       0x548
+#define PCIE_UTL_PCIE_PORT_ERROR_SEV    0x550
+#define PCIE_UTL_PCIE_PORT_IRQ_EN       0x558
+#define PCIE_UTL_RC_STATUS              0x560
+#define PCIE_UTL_RC_ERR_SEVERITY        0x568
+#define PCIE_UTL_RC_IRQ_EN              0x570
+#define PCIE_UTL_EP_STATUS              0x578
+#define PCIE_UTL_EP_ERR_SEVERITY        0x580
+#define PCIE_UTL_EP_ERR_IRQ_EN          0x588
+
+#define PCIE_UTL_PCI_PM_CTRL1           0x590
+#define PCIE_UTL_PCI_PM_CTRL2           0x598
+
+/* PCIe stack registers */
+#define PCIE_REG_SYSTEM_CONFIG1         0x600
+#define PCIE_REG_SYSTEM_CONFIG2         0x608
+#define PCIE_REG_EP_SYSTEM_CONFIG       0x618
+#define PCIE_REG_EP_FLR                 0x620
+#define PCIE_REG_EP_BAR_CONFIG          0x628
+#define PCIE_REG_LINK_CONFIG            0x630
+#define PCIE_REG_PM_CONFIG              0x640
+#define PCIE_REG_DLP_CONTROL            0x650
+#define PCIE_REG_DLP_STATUS             0x658
+#define PCIE_REG_ERR_REPORT_CONTROL     0x660
+#define PCIE_REG_SLOT_CONTROL1          0x670
+#define PCIE_REG_SLOT_CONTROL2          0x678
+#define PCIE_REG_UTL_CONFIG             0x680
+#define PCIE_REG_BUFFERS_CONFIG         0x690
+#define PCIE_REG_ERROR_INJECT           0x698
+#define PCIE_REG_SRIOV_CONFIG           0x6a0
+#define PCIE_REG_PF0_SRIOV_STATUS       0x6a8
+#define PCIE_REG_PF1_SRIOV_STATUS       0x6b0
+#define PCIE_REG_PORT_NUMBER            0x700
+#define PCIE_REG_POR_SYSTEM_CONFIG      0x708
+
+/* PHB internal logic registers */
+#define PCIE_REG_PHB_VERSION            0x800
+#define PCIE_REG_RESET                  0x808
+#define PCIE_REG_PHB_CONTROL            0x810
+#define PCIE_REG_PHB_TIMEOUT_CONTROL1   0x878
+#define PCIE_REG_PHB_QUIESCE_DMA        0x888
+#define PCIE_REG_PHB_DMA_READ_TAG_ACTV  0x900
+#define PCIE_REG_PHB_TCE_READ_TAG_ACTV  0x908
+
+/* FIR registers */
+#define PCIE_REG_LEM_FIR_ACCUM          0xc00
+#define PCIE_REG_LEM_FIR_AND_MASK       0xc08
+#define PCIE_REG_LEM_FIR_OR_MASK        0xc10
+#define PCIE_REG_LEM_ACTION0            0xc18
+#define PCIE_REG_LEM_ACTION1            0xc20
+#define PCIE_REG_LEM_ERROR_MASK         0xc30
+#define PCIE_REG_LEM_ERROR_AND_MASK     0xc38
+#define PCIE_REG_LEM_ERROR_OR_MASK      0xc40
+
+/* PHB Error registers */
+#define PCIE_REG_PHB_ERR_STATUS         0xc80
+#define PCIE_REG_PHB_ERR1_STATUS        0xc88
+#define PCIE_REG_PHB_ERR_INJECT         0xc90
+#define PCIE_REG_PHB_ERR_LEM_ENABLE     0xc98
+#define PCIE_REG_PHB_ERR_IRQ_ENABLE     0xca0
+#define PCIE_REG_PHB_ERR_FREEZE_ENABLE  0xca8
+#define PCIE_REG_PHB_ERR_SIDE_ENABLE    0xcb8
+#define PCIE_REG_PHB_ERR_LOG_0          0xcc0
+#define PCIE_REG_PHB_ERR_LOG_1          0xcc8
+#define PCIE_REG_PHB_ERR_STATUS_MASK    0xcd0
+#define PCIE_REG_PHB_ERR1_STATUS_MASK   0xcd8
+
+#define PCIE_REG_MMIO_ERR_STATUS        0xd00
+#define PCIE_REG_MMIO_ERR1_STATUS       0xd08
+#define PCIE_REG_MMIO_ERR_INJECT        0xd10
+#define PCIE_REG_MMIO_ERR_LEM_ENABLE    0xd18
+#define PCIE_REG_MMIO_ERR_IRQ_ENABLE    0xd20
+#define PCIE_REG_MMIO_ERR_FREEZE_ENABLE 0xd28
+#define PCIE_REG_MMIO_ERR_SIDE_ENABLE   0xd38
+#define PCIE_REG_MMIO_ERR_LOG_0         0xd40
+#define PCIE_REG_MMIO_ERR_LOG_1         0xd48
+#define PCIE_REG_MMIO_ERR_STATUS_MASK   0xd50
+#define PCIE_REG_MMIO_ERR1_STATUS_MASK  0xd58
+
+#define PCIE_REG_DMA_ERR_STATUS         0xd80
+#define PCIE_REG_DMA_ERR1_STATUS        0xd88
+#define PCIE_REG_DMA_ERR_INJECT         0xd90
+#define PCIE_REG_DMA_ERR_LEM_ENABLE     0xd98
+#define PCIE_REG_DMA_ERR_IRQ_ENABLE     0xda0
+#define PCIE_REG_DMA_ERR_FREEZE_ENABLE  0xda8
+#define PCIE_REG_DMA_ERR_SIDE_ENABLE    0xdb8
+#define PCIE_REG_DMA_ERR_LOG_0          0xdc0
+#define PCIE_REG_DMA_ERR_LOG_1          0xdc8
+#define PCIE_REG_DMA_ERR_STATUS_MASK    0xdd0
+#define PCIE_REG_DMA_ERR1_STATUS_MASK   0xdd8
+
+/* Shortcuts for access to the above using the PHB definitions
+ * with an offset
+ */
+#define PCIE_REG_ERR_PHB_OFFSET         0x0
+#define PCIE_REG_ERR_MMIO_OFFSET        0x80
+#define PCIE_REG_ERR_DMA_OFFSET         0x100
+
+/* Debug and Trace registers */
+#define PCIE_REG_PHB_DEBUG_CONTROL0     0xe00
+#define PCIE_REG_PHB_DEBUG_STATUS0      0xe08
+#define PCIE_REG_PHB_DEBUG_CONTROL1     0xe10
+#define PCIE_REG_PHB_DEBUG_STATUS1      0xe18
+#define PCIE_REG_PHB_DEBUG_CONTROL2     0xe20
+#define PCIE_REG_PHB_DEBUG_STATUS2      0xe28
+#define PCIE_REG_PHB_DEBUG_CONTROL3     0xe30
+#define PCIE_REG_PHB_DEBUG_STATUS3      0xe38
+#define PCIE_REG_PHB_DEBUG_CONTROL4     0xe40
+#define PCIE_REG_PHB_DEBUG_STATUS4      0xe48
+#define PCIE_REG_PHB_DEBUG_CONTROL5     0xe50
+#define PCIE_REG_PHB_DEBUG_STATUS5      0xe58
+#define PCIE_REG_PHB_DEBUG_CONTROL6     0xe60
+#define PCIE_REG_PHB_DEBUG_STATUS6      0xe68
+
+/* Definition for PCIe errors */
+struct wsp_pcie_err_log_data {
+        __u64   phb_err;
+        __u64   phb_err1;
+        __u64   phb_log0;
+        __u64   phb_log1;
+        __u64   mmio_err;
+        __u64   mmio_err1;
+        __u64   mmio_log0;
+        __u64   mmio_log1;
+        __u64   dma_err;
+        __u64   dma_err1;
+        __u64   dma_log0;
+        __u64   dma_log1;
+        __u64   utl_sys_err;
+        __u64   utl_port_err;
+        __u64   utl_rc_err;
+        __u64   unused;
+};
+
+#endif /* __WSP_PCI_H */
diff --git a/arch/powerpc/sysdev/Makefile b/arch/powerpc/sysdev/Makefile
index cf736ca0cf05..84e13253aec5 100644
--- a/arch/powerpc/sysdev/Makefile
+++ b/arch/powerpc/sysdev/Makefile
@@ -18,7 +18,6 @@ obj-$(CONFIG_FSL_PCI)		+= fsl_pci.o $(fsl-msi-obj-y)
 obj-$(CONFIG_FSL_PMC)           += fsl_pmc.o
 obj-$(CONFIG_FSL_LBC)           += fsl_lbc.o
 obj-$(CONFIG_FSL_GTM)           += fsl_gtm.o
-obj-$(CONFIG_MPC8xxx_GPIO)      += mpc8xxx_gpio.o
 obj-$(CONFIG_FSL_85XX_CACHE_SRAM)       += fsl_85xx_l2ctlr.o fsl_85xx_cache_sram.o
 obj-$(CONFIG_SIMPLE_GPIO)       += simple_gpio.o
 obj-$(CONFIG_FSL_RIO)           += fsl_rio.o
diff --git a/arch/powerpc/sysdev/axonram.c b/arch/powerpc/sysdev/axonram.c
index 265f0f09395a..ba4271919062 100644
--- a/arch/powerpc/sysdev/axonram.c
+++ b/arch/powerpc/sysdev/axonram.c
@@ -104,7 +104,7 @@ axon_ram_irq_handler(int irq, void *dev)
  * axon_ram_make_request - make_request() method for block device
  * @queue, @bio: see blk_queue_make_request()
  */
-static int
+static void
 axon_ram_make_request(struct request_queue *queue, struct bio *bio)
 {
         struct axon_ram_bank *bank = bio->bi_bdev->bd_disk->private_data;
@@ -113,7 +113,6 @@ axon_ram_make_request(struct request_queue *queue, struct bio *bio)
         struct bio_vec *vec;
         unsigned int transfered;
         unsigned short idx;
-        int rc = 0;
 
         phys_mem = bank->io_addr + (bio->bi_sector << AXON_RAM_SECTOR_SHIFT);
         phys_end = bank->io_addr + bank->size;
@@ -121,8 +120,7 @@ axon_ram_make_request(struct request_queue *queue, struct bio *bio)
         bio_for_each_segment(vec, bio, idx) {
                 if (unlikely(phys_mem + vec->bv_len > phys_end)) {
                         bio_io_error(bio);
-                        rc = -ERANGE;
-                        break;
+                        return;
                 }
 
                 user_mem = page_address(vec->bv_page) + vec->bv_offset;
@@ -135,8 +133,6 @@ axon_ram_make_request(struct request_queue *queue, struct bio *bio)
                 transfered += vec->bv_len;
         }
         bio_endio(bio, 0);
-
-        return rc;
 }
 
 /**
diff --git a/arch/powerpc/sysdev/bestcomm/sram.c b/arch/powerpc/sysdev/bestcomm/sram.c
index 1225012a681a..b6db23e085fb 100644
--- a/arch/powerpc/sysdev/bestcomm/sram.c
+++ b/arch/powerpc/sysdev/bestcomm/sram.c
@@ -13,7 +13,7 @@
 
 #include <linux/err.h>
 #include <linux/kernel.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/string.h>
diff --git a/arch/powerpc/sysdev/cpm_common.c b/arch/powerpc/sysdev/cpm_common.c
index d55d0ad0deab..bf6c7cc0a6af 100644
--- a/arch/powerpc/sysdev/cpm_common.c
+++ b/arch/powerpc/sysdev/cpm_common.c
@@ -3,7 +3,7 @@
  *
  * Author: Scott Wood <scottwood@freescale.com>
  *
- * Copyright 2007 Freescale Semiconductor, Inc.
+ * Copyright 2007-2008,2010 Freescale Semiconductor, Inc.
  *
  * Some parts derived from commproc.c/cpm2_common.c, which is:
  * Copyright (c) 1997 Dan error_act (dmalek@jlc.net)
@@ -20,6 +20,7 @@
 #include <linux/init.h>
 #include <linux/of_device.h>
 #include <linux/spinlock.h>
+#include <linux/export.h>
 #include <linux/of.h>
 #include <linux/slab.h>
 
@@ -146,6 +147,7 @@ unsigned long cpm_muram_alloc(unsigned long size, unsigned long align)
         spin_lock_irqsave(&cpm_muram_lock, flags);
         cpm_muram_info.alignment = align;
         start = rh_alloc(&cpm_muram_info, size, "commproc");
+        memset(cpm_muram_addr(start), 0, size);
         spin_unlock_irqrestore(&cpm_muram_lock, flags);
 
         return start;
diff --git a/arch/powerpc/sysdev/dcr.c b/arch/powerpc/sysdev/dcr.c
index bb44aa9fd470..1bd0eba4d355 100644
--- a/arch/powerpc/sysdev/dcr.c
+++ b/arch/powerpc/sysdev/dcr.c
@@ -20,6 +20,7 @@
 #undef DEBUG
 
 #include <linux/kernel.h>
+#include <linux/export.h>
 #include <asm/prom.h>
 #include <asm/dcr.h>
 
diff --git a/arch/powerpc/sysdev/fsl_gtm.c b/arch/powerpc/sysdev/fsl_gtm.c
index 7dd2885321ad..02cf1e7e77fc 100644
--- a/arch/powerpc/sysdev/fsl_gtm.c
+++ b/arch/powerpc/sysdev/fsl_gtm.c
@@ -22,6 +22,7 @@
 #include <linux/spinlock.h>
 #include <linux/bitops.h>
 #include <linux/slab.h>
+#include <linux/export.h>
 #include <asm/fsl_gtm.h>
 
 #define GTCFR_STP(x)            ((x) & 1 ? 1 << 5 : 1 << 1)
diff --git a/arch/powerpc/sysdev/fsl_lbc.c b/arch/powerpc/sysdev/fsl_lbc.c
index d917573cf1a8..c4d96fa32ba5 100644
--- a/arch/powerpc/sysdev/fsl_lbc.c
+++ b/arch/powerpc/sysdev/fsl_lbc.c
@@ -15,7 +15,7 @@
  */
 
 #include <linux/init.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/kernel.h>
 #include <linux/compiler.h>
 #include <linux/spinlock.h>
@@ -23,6 +23,7 @@
 #include <linux/io.h>
 #include <linux/of.h>
 #include <linux/slab.h>
+#include <linux/sched.h>
 #include <linux/platform_device.h>
 #include <linux/interrupt.h>
 #include <linux/mod_devicetable.h>
diff --git a/arch/powerpc/sysdev/fsl_msi.c b/arch/powerpc/sysdev/fsl_msi.c
index 419a77239bd7..e5c344d336ea 100644
--- a/arch/powerpc/sysdev/fsl_msi.c
+++ b/arch/powerpc/sysdev/fsl_msi.c
@@ -30,7 +30,7 @@ LIST_HEAD(msi_head);
 
 struct fsl_msi_feature {
         u32 fsl_pic_ip;
-        u32 msiir_offset;
+        u32 msiir_offset; /* Offset of MSIIR, relative to start of MSIR bank */
 };
 
 struct fsl_msi_cascade_data {
@@ -126,10 +126,19 @@ static void fsl_compose_msi_msg(struct pci_dev *pdev, int hwirq,
 {
         struct fsl_msi *msi_data = fsl_msi_data;
         struct pci_controller *hose = pci_bus_to_host(pdev->bus);
-        u64 base = fsl_pci_immrbar_base(hose);
+        u64 address; /* Physical address of the MSIIR */
+        int len;
+        const u64 *reg;
+
+        /* If the msi-address-64 property exists, then use it */
+        reg = of_get_property(hose->dn, "msi-address-64", &len);
+        if (reg && (len == sizeof(u64)))
+                address = be64_to_cpup(reg);
+        else
+                address = fsl_pci_immrbar_base(hose) + msi_data->msiir_offset;
 
-        msg->address_lo = msi_data->msi_addr_lo + lower_32_bits(base);
-        msg->address_hi = msi_data->msi_addr_hi + upper_32_bits(base);
+        msg->address_lo = lower_32_bits(address);
+        msg->address_hi = upper_32_bits(address);
 
         msg->data = hwirq;
 
@@ -296,7 +305,7 @@ static int __devinit fsl_msi_setup_hwirq(struct fsl_msi *msi,
         }
 
         msi->msi_virqs[irq_index] = virt_msir;
-        cascade_data->index = offset + irq_index;
+        cascade_data->index = offset;
         cascade_data->msi_data = msi;
         irq_set_handler_data(virt_msir, cascade_data);
         irq_set_chained_handler(virt_msir, fsl_msi_cascade);
@@ -359,8 +368,7 @@ static int __devinit fsl_of_msi_probe(struct platform_device *dev)
 
         msi->irqhost->host_data = msi;
 
-        msi->msi_addr_hi = 0x0;
-        msi->msi_addr_lo = features->msiir_offset + (res.start & 0xfffff);
+        msi->msiir_offset = features->msiir_offset + (res.start & 0xfffff);
 
         rc = fsl_msi_init_allocator(msi);
         if (rc) {
@@ -376,8 +384,10 @@ static int __devinit fsl_of_msi_probe(struct platform_device *dev)
                 goto error_out;
         }
 
-        if (!p)
+        if (!p) {
                 p = all_avail;
+                len = sizeof(all_avail);
+        }
 
         for (irq_index = 0, i = 0; i < len / (2 * sizeof(u32)); i++) {
                 if (p[i * 2] % IRQS_PER_MSI_REG ||
@@ -393,7 +403,7 @@ static int __devinit fsl_of_msi_probe(struct platform_device *dev)
                 count = p[i * 2 + 1] / IRQS_PER_MSI_REG;
 
                 for (j = 0; j < count; j++, irq_index++) {
-                        err = fsl_msi_setup_hwirq(msi, dev, offset, irq_index);
+                        err = fsl_msi_setup_hwirq(msi, dev, offset + j, irq_index);
                         if (err)
                                 goto error_out;
                 }
diff --git a/arch/powerpc/sysdev/fsl_msi.h b/arch/powerpc/sysdev/fsl_msi.h
index 624580c252d7..1313abbc5200 100644
--- a/arch/powerpc/sysdev/fsl_msi.h
+++ b/arch/powerpc/sysdev/fsl_msi.h
@@ -28,8 +28,7 @@ struct fsl_msi {
 
         unsigned long cascade_irq;
 
-        u32 msi_addr_lo;
-        u32 msi_addr_hi;
+        u32 msiir_offset; /* Offset of MSIIR, relative to start of CCSR */
         void __iomem *msi_regs;
         u32 feature;
         int msi_virqs[NR_MSI_REG];
diff --git a/arch/powerpc/sysdev/fsl_pmc.c b/arch/powerpc/sysdev/fsl_pmc.c
index f122e8961d32..592a0f8d527a 100644
--- a/arch/powerpc/sysdev/fsl_pmc.c
+++ b/arch/powerpc/sysdev/fsl_pmc.c
@@ -14,6 +14,7 @@
 #include <linux/init.h>
 #include <linux/types.h>
 #include <linux/errno.h>
+#include <linux/export.h>
 #include <linux/suspend.h>
 #include <linux/delay.h>
 #include <linux/device.h>
diff --git a/arch/powerpc/sysdev/fsl_rio.c b/arch/powerpc/sysdev/fsl_rio.c
index c65f75aa7ff7..de170fd5ba4e 100644
--- a/arch/powerpc/sysdev/fsl_rio.c
+++ b/arch/powerpc/sysdev/fsl_rio.c
@@ -23,7 +23,7 @@
  */
 
 #include <linux/init.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/types.h>
 #include <linux/dma-mapping.h>
 #include <linux/interrupt.h>
@@ -1608,6 +1608,7 @@ int fsl_rio_setup(struct platform_device *dev)
         return 0;
 err:
         iounmap(priv->regs_win);
+        release_resource(&port->iores);
 err_res:
         kfree(priv);
 err_priv:
diff --git a/arch/powerpc/sysdev/fsl_soc.c b/arch/powerpc/sysdev/fsl_soc.c
index 2d66275e489f..e8f385fbf549 100644
--- a/arch/powerpc/sysdev/fsl_soc.c
+++ b/arch/powerpc/sysdev/fsl_soc.c
@@ -19,7 +19,7 @@
 #include <linux/major.h>
 #include <linux/delay.h>
 #include <linux/irq.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/device.h>
 #include <linux/platform_device.h>
 #include <linux/of.h>
diff --git a/arch/powerpc/sysdev/fsl_soc.h b/arch/powerpc/sysdev/fsl_soc.h
index 2ece02beb8ff..c6d00736f07f 100644
--- a/arch/powerpc/sysdev/fsl_soc.h
+++ b/arch/powerpc/sysdev/fsl_soc.h
@@ -22,15 +22,24 @@ struct device_node;
 extern void fsl_rstcr_restart(char *cmd);
 
 #if defined(CONFIG_FB_FSL_DIU) || defined(CONFIG_FB_FSL_DIU_MODULE)
+
+/* The different ports that the DIU can be connected to */
+enum fsl_diu_monitor_port {
+        FSL_DIU_PORT_DVI,       /* DVI */
+        FSL_DIU_PORT_LVDS,      /* Single-link LVDS */
+        FSL_DIU_PORT_DLVDS      /* Dual-link LVDS */
+};
+
 struct platform_diu_data_ops {
-        unsigned int (*get_pixel_format) (unsigned int bits_per_pixel,
-                int monitor_port);
-        void (*set_gamma_table) (int monitor_port, char *gamma_table_base);
-        void (*set_monitor_port) (int monitor_port);
-        void (*set_pixel_clock) (unsigned int pixclock);
-        ssize_t (*show_monitor_port) (int monitor_port, char *buf);
-        int (*set_sysfs_monitor_port) (int val);
-        void (*release_bootmem) (void);
+        u32 (*get_pixel_format)(enum fsl_diu_monitor_port port,
+                unsigned int bpp);
+        void (*set_gamma_table)(enum fsl_diu_monitor_port port,
+                char *gamma_table_base);
+        void (*set_monitor_port)(enum fsl_diu_monitor_port port);
+        void (*set_pixel_clock)(unsigned int pixclock);
+        enum fsl_diu_monitor_port (*valid_monitor_port)
+                (enum fsl_diu_monitor_port port);
+        void (*release_bootmem)(void);
 };
 
 extern struct platform_diu_data_ops diu_ops;
diff --git a/arch/powerpc/sysdev/mpc5xxx_clocks.c b/arch/powerpc/sysdev/mpc5xxx_clocks.c
index 34e12f9995fe..96f815a55dfd 100644
--- a/arch/powerpc/sysdev/mpc5xxx_clocks.c
+++ b/arch/powerpc/sysdev/mpc5xxx_clocks.c
@@ -8,6 +8,7 @@
 
 #include <linux/kernel.h>
 #include <linux/of_platform.h>
+#include <linux/export.h>
 
 unsigned int
 mpc5xxx_get_bus_frequency(struct device_node *node)
diff --git a/arch/powerpc/sysdev/mpc8xx_pic.c b/arch/powerpc/sysdev/mpc8xx_pic.c
index 22e48e2d71f1..2ca0a85fcce9 100644
--- a/arch/powerpc/sysdev/mpc8xx_pic.c
+++ b/arch/powerpc/sysdev/mpc8xx_pic.c
@@ -1,5 +1,4 @@
 #include <linux/kernel.h>
-#include <linux/module.h>
 #include <linux/stddef.h>
 #include <linux/init.h>
 #include <linux/sched.h>
diff --git a/arch/powerpc/sysdev/mpc8xxx_gpio.c b/arch/powerpc/sysdev/mpc8xxx_gpio.c
deleted file mode 100644
index fb4963abdf55..000000000000
--- a/arch/powerpc/sysdev/mpc8xxx_gpio.c
+++ /dev/null
@@ -1,395 +0,0 @@
-/*
- * GPIOs on MPC512x/8349/8572/8610 and compatible
- *
- * Copyright (C) 2008 Peter Korsgaard <jacmet@sunsite.dk>
- *
- * This file is licensed under the terms of the GNU General Public License
- * version 2.  This program is licensed "as is" without any warranty of any
- * kind, whether express or implied.
- */
-
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/spinlock.h>
-#include <linux/io.h>
-#include <linux/of.h>
-#include <linux/of_gpio.h>
-#include <linux/gpio.h>
-#include <linux/slab.h>
-#include <linux/irq.h>
-
-#define MPC8XXX_GPIO_PINS       32
-
-#define GPIO_DIR                0x00
-#define GPIO_ODR                0x04
-#define GPIO_DAT                0x08
-#define GPIO_IER                0x0c
-#define GPIO_IMR                0x10
-#define GPIO_ICR                0x14
-#define GPIO_ICR2               0x18
-
-struct mpc8xxx_gpio_chip {
-        struct of_mm_gpio_chip mm_gc;
-        spinlock_t lock;
-
-        /*
-         * shadowed data register to be able to clear/set output pins in
-         * open drain mode safely
-         */
-        u32 data;
-        struct irq_host *irq;
-        void *of_dev_id_data;
-};
-
-static inline u32 mpc8xxx_gpio2mask(unsigned int gpio)
-{
-        return 1u << (MPC8XXX_GPIO_PINS - 1 - gpio);
-}
-
-static inline struct mpc8xxx_gpio_chip *
-to_mpc8xxx_gpio_chip(struct of_mm_gpio_chip *mm)
-{
-        return container_of(mm, struct mpc8xxx_gpio_chip, mm_gc);
-}
-
-static void mpc8xxx_gpio_save_regs(struct of_mm_gpio_chip *mm)
-{
-        struct mpc8xxx_gpio_chip *mpc8xxx_gc = to_mpc8xxx_gpio_chip(mm);
-
-        mpc8xxx_gc->data = in_be32(mm->regs + GPIO_DAT);
-}
-
-/* Workaround GPIO 1 errata on MPC8572/MPC8536. The status of GPIOs
- * defined as output cannot be determined by reading GPDAT register,
- * so we use shadow data register instead. The status of input pins
- * is determined by reading GPDAT register.
- */
-static int mpc8572_gpio_get(struct gpio_chip *gc, unsigned int gpio)
-{
-        u32 val;
-        struct of_mm_gpio_chip *mm = to_of_mm_gpio_chip(gc);
-        struct mpc8xxx_gpio_chip *mpc8xxx_gc = to_mpc8xxx_gpio_chip(mm);
-
-        val = in_be32(mm->regs + GPIO_DAT) & ~in_be32(mm->regs + GPIO_DIR);
-
-        return (val | mpc8xxx_gc->data) & mpc8xxx_gpio2mask(gpio);
-}
-
-static int mpc8xxx_gpio_get(struct gpio_chip *gc, unsigned int gpio)
-{
-        struct of_mm_gpio_chip *mm = to_of_mm_gpio_chip(gc);
-
-        return in_be32(mm->regs + GPIO_DAT) & mpc8xxx_gpio2mask(gpio);
-}
-
-static void mpc8xxx_gpio_set(struct gpio_chip *gc, unsigned int gpio, int val)
-{
-        struct of_mm_gpio_chip *mm = to_of_mm_gpio_chip(gc);
-        struct mpc8xxx_gpio_chip *mpc8xxx_gc = to_mpc8xxx_gpio_chip(mm);
-        unsigned long flags;
-
-        spin_lock_irqsave(&mpc8xxx_gc->lock, flags);
-
-        if (val)
-                mpc8xxx_gc->data |= mpc8xxx_gpio2mask(gpio);
-        else
-                mpc8xxx_gc->data &= ~mpc8xxx_gpio2mask(gpio);
-
-        out_be32(mm->regs + GPIO_DAT, mpc8xxx_gc->data);
-
-        spin_unlock_irqrestore(&mpc8xxx_gc->lock, flags);
-}
-
-static int mpc8xxx_gpio_dir_in(struct gpio_chip *gc, unsigned int gpio)
-{
-        struct of_mm_gpio_chip *mm = to_of_mm_gpio_chip(gc);
-        struct mpc8xxx_gpio_chip *mpc8xxx_gc = to_mpc8xxx_gpio_chip(mm);
-        unsigned long flags;
-
-        spin_lock_irqsave(&mpc8xxx_gc->lock, flags);
-
-        clrbits32(mm->regs + GPIO_DIR, mpc8xxx_gpio2mask(gpio));
-
-        spin_unlock_irqrestore(&mpc8xxx_gc->lock, flags);
-
-        return 0;
-}
-
-static int mpc8xxx_gpio_dir_out(struct gpio_chip *gc, unsigned int gpio, int val)
-{
-        struct of_mm_gpio_chip *mm = to_of_mm_gpio_chip(gc);
-        struct mpc8xxx_gpio_chip *mpc8xxx_gc = to_mpc8xxx_gpio_chip(mm);
-        unsigned long flags;
-
-        mpc8xxx_gpio_set(gc, gpio, val);
-
-        spin_lock_irqsave(&mpc8xxx_gc->lock, flags);
-
-        setbits32(mm->regs + GPIO_DIR, mpc8xxx_gpio2mask(gpio));
-
-        spin_unlock_irqrestore(&mpc8xxx_gc->lock, flags);
-
-        return 0;
-}
-
-static int mpc8xxx_gpio_to_irq(struct gpio_chip *gc, unsigned offset)
-{
-        struct of_mm_gpio_chip *mm = to_of_mm_gpio_chip(gc);
-        struct mpc8xxx_gpio_chip *mpc8xxx_gc = to_mpc8xxx_gpio_chip(mm);
-
-        if (mpc8xxx_gc->irq && offset < MPC8XXX_GPIO_PINS)
-                return irq_create_mapping(mpc8xxx_gc->irq, offset);
-        else
-                return -ENXIO;
-}
-
-static void mpc8xxx_gpio_irq_cascade(unsigned int irq, struct irq_desc *desc)
-{
-        struct mpc8xxx_gpio_chip *mpc8xxx_gc = irq_desc_get_handler_data(desc);
-        struct of_mm_gpio_chip *mm = &mpc8xxx_gc->mm_gc;
-        unsigned int mask;
-
-        mask = in_be32(mm->regs + GPIO_IER) & in_be32(mm->regs + GPIO_IMR);
-        if (mask)
-                generic_handle_irq(irq_linear_revmap(mpc8xxx_gc->irq,
-                                                     32 - ffs(mask)));
-}
-
-static void mpc8xxx_irq_unmask(struct irq_data *d)
-{
-        struct mpc8xxx_gpio_chip *mpc8xxx_gc = irq_data_get_irq_chip_data(d);
-        struct of_mm_gpio_chip *mm = &mpc8xxx_gc->mm_gc;
-        unsigned long flags;
-
-        spin_lock_irqsave(&mpc8xxx_gc->lock, flags);
-
-        setbits32(mm->regs + GPIO_IMR, mpc8xxx_gpio2mask(irqd_to_hwirq(d)));
-
-        spin_unlock_irqrestore(&mpc8xxx_gc->lock, flags);
-}
-
-static void mpc8xxx_irq_mask(struct irq_data *d)
-{
-        struct mpc8xxx_gpio_chip *mpc8xxx_gc = irq_data_get_irq_chip_data(d);
-        struct of_mm_gpio_chip *mm = &mpc8xxx_gc->mm_gc;
-        unsigned long flags;
-
-        spin_lock_irqsave(&mpc8xxx_gc->lock, flags);
-
-        clrbits32(mm->regs + GPIO_IMR, mpc8xxx_gpio2mask(irqd_to_hwirq(d)));
-
-        spin_unlock_irqrestore(&mpc8xxx_gc->lock, flags);
-}
-
-static void mpc8xxx_irq_ack(struct irq_data *d)
-{
-        struct mpc8xxx_gpio_chip *mpc8xxx_gc = irq_data_get_irq_chip_data(d);
-        struct of_mm_gpio_chip *mm = &mpc8xxx_gc->mm_gc;
-
-        out_be32(mm->regs + GPIO_IER, mpc8xxx_gpio2mask(irqd_to_hwirq(d)));
-}
-
-static int mpc8xxx_irq_set_type(struct irq_data *d, unsigned int flow_type)
-{
-        struct mpc8xxx_gpio_chip *mpc8xxx_gc = irq_data_get_irq_chip_data(d);
-        struct of_mm_gpio_chip *mm = &mpc8xxx_gc->mm_gc;
-        unsigned long flags;
-
-        switch (flow_type) {
-        case IRQ_TYPE_EDGE_FALLING:
-                spin_lock_irqsave(&mpc8xxx_gc->lock, flags);
-                setbits32(mm->regs + GPIO_ICR,
-                          mpc8xxx_gpio2mask(irqd_to_hwirq(d)));
-                spin_unlock_irqrestore(&mpc8xxx_gc->lock, flags);
-                break;
-
-        case IRQ_TYPE_EDGE_BOTH:
-                spin_lock_irqsave(&mpc8xxx_gc->lock, flags);
-                clrbits32(mm->regs + GPIO_ICR,
-                          mpc8xxx_gpio2mask(irqd_to_hwirq(d)));
-                spin_unlock_irqrestore(&mpc8xxx_gc->lock, flags);
-                break;
-
-        default:
-                return -EINVAL;
-        }
-
-        return 0;
-}
-
-static int mpc512x_irq_set_type(struct irq_data *d, unsigned int flow_type)
-{
-        struct mpc8xxx_gpio_chip *mpc8xxx_gc = irq_data_get_irq_chip_data(d);
-        struct of_mm_gpio_chip *mm = &mpc8xxx_gc->mm_gc;
-        unsigned long gpio = irqd_to_hwirq(d);
-        void __iomem *reg;
-        unsigned int shift;
-        unsigned long flags;
-
-        if (gpio < 16) {
-                reg = mm->regs + GPIO_ICR;
-                shift = (15 - gpio) * 2;
-        } else {
-                reg = mm->regs + GPIO_ICR2;
-                shift = (15 - (gpio % 16)) * 2;
-        }
-
-        switch (flow_type) {
-        case IRQ_TYPE_EDGE_FALLING:
-        case IRQ_TYPE_LEVEL_LOW:
-                spin_lock_irqsave(&mpc8xxx_gc->lock, flags);
-                clrsetbits_be32(reg, 3 << shift, 2 << shift);
-                spin_unlock_irqrestore(&mpc8xxx_gc->lock, flags);
-                break;
-
-        case IRQ_TYPE_EDGE_RISING:
-        case IRQ_TYPE_LEVEL_HIGH:
-                spin_lock_irqsave(&mpc8xxx_gc->lock, flags);
-                clrsetbits_be32(reg, 3 << shift, 1 << shift);
-                spin_unlock_irqrestore(&mpc8xxx_gc->lock, flags);
-                break;
-
-        case IRQ_TYPE_EDGE_BOTH:
-                spin_lock_irqsave(&mpc8xxx_gc->lock, flags);
-                clrbits32(reg, 3 << shift);
-                spin_unlock_irqrestore(&mpc8xxx_gc->lock, flags);
-                break;
-
-        default:
-                return -EINVAL;
-        }
-
-        return 0;
-}
-
-static struct irq_chip mpc8xxx_irq_chip = {
-        .name           = "mpc8xxx-gpio",
-        .irq_unmask     = mpc8xxx_irq_unmask,
-        .irq_mask       = mpc8xxx_irq_mask,
-        .irq_ack        = mpc8xxx_irq_ack,
-        .irq_set_type   = mpc8xxx_irq_set_type,
-};
-
-static int mpc8xxx_gpio_irq_map(struct irq_host *h, unsigned int virq,
-                                irq_hw_number_t hw)
-{
-        struct mpc8xxx_gpio_chip *mpc8xxx_gc = h->host_data;
-
-        if (mpc8xxx_gc->of_dev_id_data)
-                mpc8xxx_irq_chip.irq_set_type = mpc8xxx_gc->of_dev_id_data;
-
-        irq_set_chip_data(virq, h->host_data);
-        irq_set_chip_and_handler(virq, &mpc8xxx_irq_chip, handle_level_irq);
-        irq_set_irq_type(virq, IRQ_TYPE_NONE);
-
-        return 0;
-}
-
-static int mpc8xxx_gpio_irq_xlate(struct irq_host *h, struct device_node *ct,
-                                  const u32 *intspec, unsigned int intsize,
-                                  irq_hw_number_t *out_hwirq,
-                                  unsigned int *out_flags)
-
-{
-        /* interrupt sense values coming from the device tree equal either
-         * EDGE_FALLING or EDGE_BOTH
-         */
-        *out_hwirq = intspec[0];
-        *out_flags = intspec[1];
-
-        return 0;
-}
-
-static struct irq_host_ops mpc8xxx_gpio_irq_ops = {
-        .map    = mpc8xxx_gpio_irq_map,
-        .xlate  = mpc8xxx_gpio_irq_xlate,
-};
-
-static struct of_device_id mpc8xxx_gpio_ids[] __initdata = {
-        { .compatible = "fsl,mpc8349-gpio", },
-        { .compatible = "fsl,mpc8572-gpio", },
-        { .compatible = "fsl,mpc8610-gpio", },
-        { .compatible = "fsl,mpc5121-gpio", .data = mpc512x_irq_set_type, },
-        { .compatible = "fsl,qoriq-gpio",   },
-        {}
-};
-
-static void __init mpc8xxx_add_controller(struct device_node *np)
-{
-        struct mpc8xxx_gpio_chip *mpc8xxx_gc;
-        struct of_mm_gpio_chip *mm_gc;
-        struct gpio_chip *gc;
-        const struct of_device_id *id;
-        unsigned hwirq;
-        int ret;
-
-        mpc8xxx_gc = kzalloc(sizeof(*mpc8xxx_gc), GFP_KERNEL);
-        if (!mpc8xxx_gc) {
-                ret = -ENOMEM;
-                goto err;
-        }
-
-        spin_lock_init(&mpc8xxx_gc->lock);
-
-        mm_gc = &mpc8xxx_gc->mm_gc;
-        gc = &mm_gc->gc;
-
-        mm_gc->save_regs = mpc8xxx_gpio_save_regs;
-        gc->ngpio = MPC8XXX_GPIO_PINS;
-        gc->direction_input = mpc8xxx_gpio_dir_in;
-        gc->direction_output = mpc8xxx_gpio_dir_out;
-        if (of_device_is_compatible(np, "fsl,mpc8572-gpio"))
-                gc->get = mpc8572_gpio_get;
-        else
-                gc->get = mpc8xxx_gpio_get;
-        gc->set = mpc8xxx_gpio_set;
-        gc->to_irq = mpc8xxx_gpio_to_irq;
-
-        ret = of_mm_gpiochip_add(np, mm_gc);
-        if (ret)
-                goto err;
-
-        hwirq = irq_of_parse_and_map(np, 0);
-        if (hwirq == NO_IRQ)
-                goto skip_irq;
-
-        mpc8xxx_gc->irq =
-                irq_alloc_host(np, IRQ_HOST_MAP_LINEAR, MPC8XXX_GPIO_PINS,
-                               &mpc8xxx_gpio_irq_ops, MPC8XXX_GPIO_PINS);
-        if (!mpc8xxx_gc->irq)
-                goto skip_irq;
-
-        id = of_match_node(mpc8xxx_gpio_ids, np);
-        if (id)
-                mpc8xxx_gc->of_dev_id_data = id->data;
-
-        mpc8xxx_gc->irq->host_data = mpc8xxx_gc;
-
-        /* ack and mask all irqs */
-        out_be32(mm_gc->regs + GPIO_IER, 0xffffffff);
-        out_be32(mm_gc->regs + GPIO_IMR, 0);
-
-        irq_set_handler_data(hwirq, mpc8xxx_gc);
-        irq_set_chained_handler(hwirq, mpc8xxx_gpio_irq_cascade);
-
-skip_irq:
-        return;
-
-err:
-        pr_err("%s: registration failed with status %d\n",
-               np->full_name, ret);
-        kfree(mpc8xxx_gc);
-
-        return;
-}
-
-static int __init mpc8xxx_add_gpiochips(void)
-{
-        struct device_node *np;
-
-        for_each_matching_node(np, mpc8xxx_gpio_ids)
-                mpc8xxx_add_controller(np);
-
-        return 0;
-}
-arch_initcall(mpc8xxx_add_gpiochips);
diff --git a/arch/powerpc/sysdev/mpic.c b/arch/powerpc/sysdev/mpic.c
index d5d3ff3d757e..8c7e8528e7c4 100644
--- a/arch/powerpc/sysdev/mpic.c
+++ b/arch/powerpc/sysdev/mpic.c
@@ -800,8 +800,6 @@ static void mpic_end_ipi(struct irq_data *d)
          * IPIs are marked IRQ_PER_CPU. This has the side effect of
          * preventing the IRQ_PENDING/IRQ_INPROGRESS logic from
          * applying to them. We EOI them late to avoid re-entering.
-         * We mark IPI's with IRQF_DISABLED as they must run with
-         * irqs disabled.
          */
         mpic_eoi(mpic);
 }
@@ -1285,13 +1283,11 @@ struct mpic * __init mpic_alloc(struct device_node *node,
                            mpic_read(mpic->gregs, MPIC_INFO(GREG_GLOBAL_CONF_0))
                            | MPIC_GREG_GCONF_MCK);
 
-        /* Read feature register, calculate num CPUs and, for non-ISU
-         * MPICs, num sources as well. On ISU MPICs, sources are counted
-         * as ISUs are added
+        /*
+         * Read feature register.  For non-ISU MPICs, num sources as well. On
+         * ISU MPICs, sources are counted as ISUs are added
          */
         greg_feature = mpic_read(mpic->gregs, MPIC_INFO(GREG_FEATURE_0));
-        mpic->num_cpus = ((greg_feature & MPIC_GREG_FEATURE_LAST_CPU_MASK)
-                          >> MPIC_GREG_FEATURE_LAST_CPU_SHIFT) + 1;
         if (isu_size == 0) {
                 if (flags & MPIC_BROKEN_FRR_NIRQS)
                         mpic->num_sources = mpic->irq_count;
@@ -1301,10 +1297,18 @@ struct mpic * __init mpic_alloc(struct device_node *node,
                                  >> MPIC_GREG_FEATURE_LAST_SRC_SHIFT) + 1;
         }
 
+        /*
+         * The MPIC driver will crash if there are more cores than we
+         * can initialize, so we may as well catch that problem here.
+         */
+        BUG_ON(num_possible_cpus() > MPIC_MAX_CPUS);
+
         /* Map the per-CPU registers */
-        for (i = 0; i < mpic->num_cpus; i++) {
-                mpic_map(mpic, node, paddr, &mpic->cpuregs[i],
-                         MPIC_INFO(CPU_BASE) + i * MPIC_INFO(CPU_STRIDE),
+        for_each_possible_cpu(i) {
+                unsigned int cpu = get_hard_smp_processor_id(i);
+
+                mpic_map(mpic, node, paddr, &mpic->cpuregs[cpu],
+                         MPIC_INFO(CPU_BASE) + cpu * MPIC_INFO(CPU_STRIDE),
                          0x1000);
         }
 
@@ -1343,7 +1347,7 @@ struct mpic * __init mpic_alloc(struct device_node *node,
         }
         printk(KERN_INFO "mpic: Setting up MPIC \"%s\" version %s at %llx,"
                " max %d CPUs\n",
-               name, vers, (unsigned long long)paddr, mpic->num_cpus);
+               name, vers, (unsigned long long)paddr, num_possible_cpus());
         printk(KERN_INFO "mpic: ISU size: %d, shift: %d, mask: %x\n",
                mpic->isu_size, mpic->isu_shift, mpic->isu_mask);
 
@@ -1742,6 +1746,7 @@ void mpic_reset_core(int cpu)
         struct mpic *mpic = mpic_primary;
         u32 pir;
         int cpuid = get_hard_smp_processor_id(cpu);
+        int i;
 
         /* Set target bit for core reset */
         pir = mpic_read(mpic->gregs, MPIC_INFO(GREG_PROCESSOR_INIT));
@@ -1753,6 +1758,15 @@ void mpic_reset_core(int cpu)
         pir &= ~(1 << cpuid);
         mpic_write(mpic->gregs, MPIC_INFO(GREG_PROCESSOR_INIT), pir);
         mpic_read(mpic->gregs, MPIC_INFO(GREG_PROCESSOR_INIT));
+
+        /* Perform 15 EOI on each reset core to clear pending interrupts.
+         * This is required for FSL CoreNet based devices */
+        if (mpic->flags & MPIC_FSL) {
+                for (i = 0; i < 15; i++) {
+                        _mpic_write(mpic->reg_type, &mpic->cpuregs[cpuid],
+                                      MPIC_CPU_EOI, 0);
+                }
+        }
 }
 #endif /* CONFIG_SMP */
 
diff --git a/arch/powerpc/sysdev/mv64x60_pci.c b/arch/powerpc/sysdev/mv64x60_pci.c
index 77bb3f4d530a..b0037cefaada 100644
--- a/arch/powerpc/sysdev/mv64x60_pci.c
+++ b/arch/powerpc/sysdev/mv64x60_pci.c
@@ -12,6 +12,7 @@
 #include <linux/stddef.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
+#include <linux/stat.h>
 #include <linux/pci.h>
 
 #include <asm/prom.h>
diff --git a/arch/powerpc/sysdev/pmi.c b/arch/powerpc/sysdev/pmi.c
index 8ce4fc3d9828..8f0465422b1e 100644
--- a/arch/powerpc/sysdev/pmi.c
+++ b/arch/powerpc/sysdev/pmi.c
@@ -28,6 +28,7 @@
 #include <linux/slab.h>
 #include <linux/completion.h>
 #include <linux/spinlock.h>
+#include <linux/module.h>
 #include <linux/workqueue.h>
 #include <linux/of_device.h>
 #include <linux/of_platform.h>
diff --git a/arch/powerpc/sysdev/ppc4xx_msi.c b/arch/powerpc/sysdev/ppc4xx_msi.c
index 367af0241851..1c2d7af17bbe 100644
--- a/arch/powerpc/sysdev/ppc4xx_msi.c
+++ b/arch/powerpc/sysdev/ppc4xx_msi.c
@@ -27,6 +27,7 @@
 #include <linux/msi.h>
 #include <linux/of_platform.h>
 #include <linux/interrupt.h>
+#include <linux/export.h>
 #include <asm/prom.h>
 #include <asm/hw_irq.h>
 #include <asm/ppc-pci.h>
diff --git a/arch/powerpc/sysdev/ppc4xx_pci.c b/arch/powerpc/sysdev/ppc4xx_pci.c
index dbfe96bc878a..862f11b3821e 100644
--- a/arch/powerpc/sysdev/ppc4xx_pci.c
+++ b/arch/powerpc/sysdev/ppc4xx_pci.c
@@ -834,7 +834,7 @@ static int __init ppc440spe_pciex_core_init(struct device_node *np)
         return 3;
 }
 
-static int ppc440spe_pciex_init_port_hw(struct ppc4xx_pciex_port *port)
+static int __init ppc440spe_pciex_init_port_hw(struct ppc4xx_pciex_port *port)
 {
         u32 val = 1 << 24;
 
@@ -872,12 +872,12 @@ static int ppc440spe_pciex_init_port_hw(struct ppc4xx_pciex_port *port)
         return ppc4xx_pciex_port_reset_sdr(port);
 }
 
-static int ppc440speA_pciex_init_port_hw(struct ppc4xx_pciex_port *port)
+static int __init ppc440speA_pciex_init_port_hw(struct ppc4xx_pciex_port *port)
 {
         return ppc440spe_pciex_init_port_hw(port);
 }
 
-static int ppc440speB_pciex_init_port_hw(struct ppc4xx_pciex_port *port)
+static int __init ppc440speB_pciex_init_port_hw(struct ppc4xx_pciex_port *port)
 {
         int rc = ppc440spe_pciex_init_port_hw(port);
 
@@ -936,7 +936,7 @@ static int __init ppc460ex_pciex_core_init(struct device_node *np)
         return 2;
 }
 
-static int ppc460ex_pciex_init_port_hw(struct ppc4xx_pciex_port *port)
+static int __init ppc460ex_pciex_init_port_hw(struct ppc4xx_pciex_port *port)
 {
         u32 val;
         u32 utlset1;
@@ -1092,6 +1092,10 @@ static int __init ppc460sx_pciex_core_init(struct device_node *np)
         mtdcri(SDR0, PESDR1_460SX_HSSSLEW, 0xFFFF0000);
         mtdcri(SDR0, PESDR2_460SX_HSSSLEW, 0xFFFF0000);
 
+        /* Set HSS PRBS enabled */
+        mtdcri(SDR0, PESDR0_460SX_HSSCTLSET, 0x00001130);
+        mtdcri(SDR0, PESDR2_460SX_HSSCTLSET, 0x00001130);
+
         udelay(100);
 
         /* De-assert PLLRESET */
@@ -1122,7 +1126,7 @@ static int __init ppc460sx_pciex_core_init(struct device_node *np)
         return 2;
 }
 
-static int ppc460sx_pciex_init_port_hw(struct ppc4xx_pciex_port *port)
+static int __init ppc460sx_pciex_init_port_hw(struct ppc4xx_pciex_port *port)
 {
 
         if (port->endpoint)
@@ -1132,9 +1136,6 @@ static int ppc460sx_pciex_init_port_hw(struct ppc4xx_pciex_port *port)
                 dcri_clrset(SDR0, port->sdr_base + PESDRn_UTLSET2,
                                 0, 0x01000000);
 
-        /*Gen-1*/
-        mtdcri(SDR0, port->sdr_base + PESDRn_460SX_RCEI, 0x08000000);
-
         dcri_clrset(SDR0, port->sdr_base + PESDRn_RCSSET,
                         (PESDRx_RCSSET_RSTGU | PESDRx_RCSSET_RSTDL),
                         PESDRx_RCSSET_RSTPYN);
@@ -1148,14 +1149,42 @@ static int ppc460sx_pciex_init_utl(struct ppc4xx_pciex_port *port)
 {
         /* Max 128 Bytes */
         out_be32 (port->utl_base + PEUTL_PBBSZ,   0x00000000);
+        /* Assert VRB and TXE - per datasheet turn off addr validation */
+        out_be32(port->utl_base + PEUTL_PCTL,  0x80800000);
         return 0;
 }
 
+static void __init ppc460sx_pciex_check_link(struct ppc4xx_pciex_port *port)
+{
+        void __iomem *mbase;
+        int attempt = 50;
+
+        port->link = 0;
+
+        mbase = ioremap(port->cfg_space.start + 0x10000000, 0x1000);
+        if (mbase == NULL) {
+                printk(KERN_ERR "%s: Can't map internal config space !",
+                        port->node->full_name);
+                goto done;
+        }
+
+        while (attempt && (0 == (in_le32(mbase + PECFG_460SX_DLLSTA)
+                        & PECFG_460SX_DLLSTA_LINKUP))) {
+                attempt--;
+                mdelay(10);
+        }
+        if (attempt)
+                port->link = 1;
+done:
+        iounmap(mbase);
+
+}
+
 static struct ppc4xx_pciex_hwops ppc460sx_pcie_hwops __initdata = {
         .core_init      = ppc460sx_pciex_core_init,
         .port_init_hw   = ppc460sx_pciex_init_port_hw,
         .setup_utl      = ppc460sx_pciex_init_utl,
-        .check_link     = ppc4xx_pciex_check_link_sdr,
+        .check_link     = ppc460sx_pciex_check_link,
 };
 
 #endif /* CONFIG_44x */
@@ -1189,7 +1218,7 @@ static void ppc405ex_pcie_phy_reset(struct ppc4xx_pciex_port *port)
         mtdcri(SDR0, port->sdr_base + PESDRn_RCSSET, 0x00101000);
 }
 
-static int ppc405ex_pciex_init_port_hw(struct ppc4xx_pciex_port *port)
+static int __init ppc405ex_pciex_init_port_hw(struct ppc4xx_pciex_port *port)
 {
         u32 val;
 
@@ -1338,15 +1367,15 @@ static int __init ppc4xx_pciex_port_init(struct ppc4xx_pciex_port *port)
         if (rc != 0)
                 return rc;
 
-        if (ppc4xx_pciex_hwops->check_link)
-                ppc4xx_pciex_hwops->check_link(port);
-
         /*
          * Initialize mapping: disable all regions and configure
          * CFG and REG regions based on resources in the device tree
          */
         ppc4xx_pciex_port_init_mapping(port);
 
+        if (ppc4xx_pciex_hwops->check_link)
+                ppc4xx_pciex_hwops->check_link(port);
+
         /*
          * Map UTL
          */
@@ -1360,13 +1389,23 @@ static int __init ppc4xx_pciex_port_init(struct ppc4xx_pciex_port *port)
                 ppc4xx_pciex_hwops->setup_utl(port);
 
         /*
-         * Check for VC0 active and assert RDY.
+         * Check for VC0 active or PLL Locked and assert RDY.
          */
         if (port->sdr_base) {
-                if (port->link &&
-                    ppc4xx_pciex_wait_on_sdr(port, PESDRn_RCSSTS,
-                                             1 << 16, 1 << 16, 5000)) {
-                        printk(KERN_INFO "PCIE%d: VC0 not active\n", port->index);
+                if (of_device_is_compatible(port->node,
+                                "ibm,plb-pciex-460sx")){
+                        if (port->link && ppc4xx_pciex_wait_on_sdr(port,
+                                        PESDRn_RCSSTS,
+                                        1 << 12, 1 << 12, 5000)) {
+                                printk(KERN_INFO "PCIE%d: PLL not locked\n",
+                                                port->index);
+                                port->link = 0;
+                        }
+                } else if (port->link &&
+                        ppc4xx_pciex_wait_on_sdr(port, PESDRn_RCSSTS,
+                                1 << 16, 1 << 16, 5000)) {
+                        printk(KERN_INFO "PCIE%d: VC0 not active\n",
+                                        port->index);
                         port->link = 0;
                 }
 
@@ -1573,8 +1612,15 @@ static int __init ppc4xx_setup_one_pciex_POM(struct ppc4xx_pciex_port	*port,
                 dcr_write(port->dcrs, DCRO_PEGPL_OMR1BAH, lah);
                 dcr_write(port->dcrs, DCRO_PEGPL_OMR1BAL, lal);
                 dcr_write(port->dcrs, DCRO_PEGPL_OMR1MSKH, 0x7fffffff);
-                /* Note that 3 here means enabled | single region */
-                dcr_write(port->dcrs, DCRO_PEGPL_OMR1MSKL, sa | 3);
+                /*Enabled and single region */
+                if (of_device_is_compatible(port->node, "ibm,plb-pciex-460sx"))
+                        dcr_write(port->dcrs, DCRO_PEGPL_OMR1MSKL,
+                                sa | DCRO_PEGPL_460SX_OMR1MSKL_UOT
+                                        | DCRO_PEGPL_OMRxMSKL_VAL);
+                else
+                        dcr_write(port->dcrs, DCRO_PEGPL_OMR1MSKL,
+                                sa | DCRO_PEGPL_OMR1MSKL_UOT
+                                        | DCRO_PEGPL_OMRxMSKL_VAL);
                 break;
         case 1:
                 out_le32(mbase + PECFG_POM1LAH, pciah);
@@ -1582,8 +1628,8 @@ static int __init ppc4xx_setup_one_pciex_POM(struct ppc4xx_pciex_port	*port,
                 dcr_write(port->dcrs, DCRO_PEGPL_OMR2BAH, lah);
                 dcr_write(port->dcrs, DCRO_PEGPL_OMR2BAL, lal);
                 dcr_write(port->dcrs, DCRO_PEGPL_OMR2MSKH, 0x7fffffff);
-                /* Note that 3 here means enabled | single region */
-                dcr_write(port->dcrs, DCRO_PEGPL_OMR2MSKL, sa | 3);
+                dcr_write(port->dcrs, DCRO_PEGPL_OMR2MSKL,
+                                sa | DCRO_PEGPL_OMRxMSKL_VAL);
                 break;
         case 2:
                 out_le32(mbase + PECFG_POM2LAH, pciah);
@@ -1592,7 +1638,9 @@ static int __init ppc4xx_setup_one_pciex_POM(struct ppc4xx_pciex_port	*port,
                 dcr_write(port->dcrs, DCRO_PEGPL_OMR3BAL, lal);
                 dcr_write(port->dcrs, DCRO_PEGPL_OMR3MSKH, 0x7fffffff);
                 /* Note that 3 here means enabled | IO space !!! */
-                dcr_write(port->dcrs, DCRO_PEGPL_OMR3MSKL, sa | 3);
+                dcr_write(port->dcrs, DCRO_PEGPL_OMR3MSKL,
+                                sa | DCRO_PEGPL_OMR3MSKL_IO
+                                        | DCRO_PEGPL_OMRxMSKL_VAL);
                 break;
         }
 
@@ -1693,6 +1741,9 @@ static void __init ppc4xx_configure_pciex_PIMs(struct ppc4xx_pciex_port *port,
                 if (res->flags & IORESOURCE_PREFETCH)
                         sa |= 0x8;
 
+                if (of_device_is_compatible(port->node, "ibm,plb-pciex-460sx"))
+                        sa |= PCI_BASE_ADDRESS_MEM_TYPE_64;
+
                 out_le32(mbase + PECFG_BAR0HMPA, RES_TO_U32_HIGH(sa));
                 out_le32(mbase + PECFG_BAR0LMPA, RES_TO_U32_LOW(sa));
 
@@ -1854,6 +1905,10 @@ static void __init ppc4xx_pciex_port_setup_hose(struct ppc4xx_pciex_port *port)
         }
         out_le16(mbase + 0x202, val);
 
+        /* Enable Bus master, memory, and io space */
+        if (of_device_is_compatible(port->node, "ibm,plb-pciex-460sx"))
+                out_le16(mbase + 0x204, 0x7);
+
         if (!port->endpoint) {
                 /* Set Class Code to PCI-PCI bridge and Revision Id to 1 */
                 out_le32(mbase + 0x208, 0x06040001);
diff --git a/arch/powerpc/sysdev/ppc4xx_pci.h b/arch/powerpc/sysdev/ppc4xx_pci.h
index c39a134e8684..32ce763a375a 100644
--- a/arch/powerpc/sysdev/ppc4xx_pci.h
+++ b/arch/powerpc/sysdev/ppc4xx_pci.h
@@ -464,6 +464,18 @@
 #define PECFG_POM2LAL           0x390
 #define PECFG_POM2LAH           0x394
 
+/* 460sx only */
+#define PECFG_460SX_DLLSTA     0x3f8
+
+/* 460sx Bit Mappings */
+#define PECFG_460SX_DLLSTA_LINKUP        0x00000010
+#define DCRO_PEGPL_460SX_OMR1MSKL_UOT    0x00000004
+
+/* PEGPL Bit Mappings */
+#define DCRO_PEGPL_OMRxMSKL_VAL  0x00000001
+#define DCRO_PEGPL_OMR1MSKL_UOT  0x00000002
+#define DCRO_PEGPL_OMR3MSKL_IO   0x00000002
+
 /* SDR Bit Mappings */
 #define PESDRx_RCSSET_HLDPLB    0x10000000
 #define PESDRx_RCSSET_RSTGU     0x01000000
diff --git a/arch/powerpc/sysdev/ppc4xx_soc.c b/arch/powerpc/sysdev/ppc4xx_soc.c
index d3d6ce3c33b4..0debcc31ad70 100644
--- a/arch/powerpc/sysdev/ppc4xx_soc.c
+++ b/arch/powerpc/sysdev/ppc4xx_soc.c
@@ -115,7 +115,7 @@ static int __init ppc4xx_l2c_probe(void)
         }
 
         /* Install error handler */
-        if (request_irq(irq, l2c_error_handler, IRQF_DISABLED, "L2C", 0) < 0) {
+        if (request_irq(irq, l2c_error_handler, 0, "L2C", 0) < 0) {
                 printk(KERN_ERR "Cannot install L2C error handler"
                        ", cache is not enabled\n");
                 of_node_put(np);
diff --git a/arch/powerpc/sysdev/qe_lib/gpio.c b/arch/powerpc/sysdev/qe_lib/gpio.c
index 36bf845df127..e23f23cf9f5c 100644
--- a/arch/powerpc/sysdev/qe_lib/gpio.c
+++ b/arch/powerpc/sysdev/qe_lib/gpio.c
@@ -20,6 +20,7 @@
 #include <linux/of_gpio.h>
 #include <linux/gpio.h>
 #include <linux/slab.h>
+#include <linux/export.h>
 #include <asm/qe.h>
 
 struct qe_gpio_chip {
diff --git a/arch/powerpc/sysdev/qe_lib/ucc.c b/arch/powerpc/sysdev/qe_lib/ucc.c
index fa589b21dbcd..04677505f20f 100644
--- a/arch/powerpc/sysdev/qe_lib/ucc.c
+++ b/arch/powerpc/sysdev/qe_lib/ucc.c
@@ -18,7 +18,7 @@
 #include <linux/errno.h>
 #include <linux/stddef.h>
 #include <linux/spinlock.h>
-#include <linux/module.h>
+#include <linux/export.h>
 
 #include <asm/irq.h>
 #include <asm/io.h>
diff --git a/arch/powerpc/sysdev/qe_lib/ucc_fast.c b/arch/powerpc/sysdev/qe_lib/ucc_fast.c
index 25fbbfaa837d..fba02440d122 100644
--- a/arch/powerpc/sysdev/qe_lib/ucc_fast.c
+++ b/arch/powerpc/sysdev/qe_lib/ucc_fast.c
@@ -19,7 +19,7 @@
 #include <linux/stddef.h>
 #include <linux/interrupt.h>
 #include <linux/err.h>
-#include <linux/module.h>
+#include <linux/export.h>
 
 #include <asm/io.h>
 #include <asm/immap_qe.h>
diff --git a/arch/powerpc/sysdev/qe_lib/ucc_slow.c b/arch/powerpc/sysdev/qe_lib/ucc_slow.c
index e1d6a1340157..524c0ead941d 100644
--- a/arch/powerpc/sysdev/qe_lib/ucc_slow.c
+++ b/arch/powerpc/sysdev/qe_lib/ucc_slow.c
@@ -19,7 +19,7 @@
 #include <linux/stddef.h>
 #include <linux/interrupt.h>
 #include <linux/err.h>
-#include <linux/module.h>
+#include <linux/export.h>
 
 #include <asm/io.h>
 #include <asm/immap_qe.h>
diff --git a/arch/powerpc/sysdev/qe_lib/usb.c b/arch/powerpc/sysdev/qe_lib/usb.c
index 8105462078eb..9162828f5da7 100644
--- a/arch/powerpc/sysdev/qe_lib/usb.c
+++ b/arch/powerpc/sysdev/qe_lib/usb.c
@@ -15,6 +15,7 @@
 
 #include <linux/kernel.h>
 #include <linux/errno.h>
+#include <linux/export.h>
 #include <linux/io.h>
 #include <asm/immap_qe.h>
 #include <asm/qe.h>
diff --git a/arch/powerpc/sysdev/rtc_cmos_setup.c b/arch/powerpc/sysdev/rtc_cmos_setup.c
index c1879ebfd4f4..9afba924e94f 100644
--- a/arch/powerpc/sysdev/rtc_cmos_setup.c
+++ b/arch/powerpc/sysdev/rtc_cmos_setup.c
@@ -12,6 +12,7 @@
 #include <linux/platform_device.h>
 #include <linux/err.h>
 #include <linux/init.h>
+#include <linux/module.h>
 #include <linux/mc146818rtc.h>
 
 #include <asm/prom.h>
diff --git a/arch/powerpc/sysdev/scom.c b/arch/powerpc/sysdev/scom.c
index b2593ce30c9b..49a3ece1c6b3 100644
--- a/arch/powerpc/sysdev/scom.c
+++ b/arch/powerpc/sysdev/scom.c
@@ -21,6 +21,7 @@
 #include <linux/kernel.h>
 #include <linux/debugfs.h>
 #include <linux/slab.h>
+#include <linux/export.h>
 #include <asm/prom.h>
 #include <asm/scom.h>
 
diff --git a/arch/powerpc/sysdev/simple_gpio.c b/arch/powerpc/sysdev/simple_gpio.c
index b6defda5ccc9..ff5e73230a36 100644
--- a/arch/powerpc/sysdev/simple_gpio.c
+++ b/arch/powerpc/sysdev/simple_gpio.c
@@ -13,7 +13,6 @@
 
 #include <linux/init.h>
 #include <linux/kernel.h>
-#include <linux/module.h>
 #include <linux/spinlock.h>
 #include <linux/types.h>
 #include <linux/ioport.h>
diff --git a/arch/powerpc/sysdev/tsi108_dev.c b/arch/powerpc/sysdev/tsi108_dev.c
index 9f51f97abb5d..2370e1c63379 100644
--- a/arch/powerpc/sysdev/tsi108_dev.c
+++ b/arch/powerpc/sysdev/tsi108_dev.c
@@ -16,7 +16,7 @@
 #include <linux/major.h>
 #include <linux/delay.h>
 #include <linux/irq.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/device.h>
 #include <linux/platform_device.h>
 #include <linux/of_net.h>
diff --git a/arch/powerpc/sysdev/uic.c b/arch/powerpc/sysdev/uic.c
index 984cd2029158..3330feca7502 100644
--- a/arch/powerpc/sysdev/uic.c
+++ b/arch/powerpc/sysdev/uic.c
@@ -47,7 +47,7 @@ struct uic {
         int index;
         int dcrbase;
 
-        spinlock_t lock;
+        raw_spinlock_t lock;
 
         /* The remapper for this UIC */
         struct irq_host *irqhost;
@@ -61,14 +61,14 @@ static void uic_unmask_irq(struct irq_data *d)
         u32 er, sr;
 
         sr = 1 << (31-src);
-        spin_lock_irqsave(&uic->lock, flags);
+        raw_spin_lock_irqsave(&uic->lock, flags);
         /* ack level-triggered interrupts here */
         if (irqd_is_level_type(d))
                 mtdcr(uic->dcrbase + UIC_SR, sr);
         er = mfdcr(uic->dcrbase + UIC_ER);
         er |= sr;
         mtdcr(uic->dcrbase + UIC_ER, er);
-        spin_unlock_irqrestore(&uic->lock, flags);
+        raw_spin_unlock_irqrestore(&uic->lock, flags);
 }
 
 static void uic_mask_irq(struct irq_data *d)
@@ -78,11 +78,11 @@ static void uic_mask_irq(struct irq_data *d)
         unsigned long flags;
         u32 er;
 
-        spin_lock_irqsave(&uic->lock, flags);
+        raw_spin_lock_irqsave(&uic->lock, flags);
         er = mfdcr(uic->dcrbase + UIC_ER);
         er &= ~(1 << (31 - src));
         mtdcr(uic->dcrbase + UIC_ER, er);
-        spin_unlock_irqrestore(&uic->lock, flags);
+        raw_spin_unlock_irqrestore(&uic->lock, flags);
 }
 
 static void uic_ack_irq(struct irq_data *d)
@@ -91,9 +91,9 @@ static void uic_ack_irq(struct irq_data *d)
         unsigned int src = irqd_to_hwirq(d);
         unsigned long flags;
 
-        spin_lock_irqsave(&uic->lock, flags);
+        raw_spin_lock_irqsave(&uic->lock, flags);
         mtdcr(uic->dcrbase + UIC_SR, 1 << (31-src));
-        spin_unlock_irqrestore(&uic->lock, flags);
+        raw_spin_unlock_irqrestore(&uic->lock, flags);
 }
 
 static void uic_mask_ack_irq(struct irq_data *d)
@@ -104,7 +104,7 @@ static void uic_mask_ack_irq(struct irq_data *d)
         u32 er, sr;
 
         sr = 1 << (31-src);
-        spin_lock_irqsave(&uic->lock, flags);
+        raw_spin_lock_irqsave(&uic->lock, flags);
         er = mfdcr(uic->dcrbase + UIC_ER);
         er &= ~sr;
         mtdcr(uic->dcrbase + UIC_ER, er);
@@ -118,7 +118,7 @@ static void uic_mask_ack_irq(struct irq_data *d)
          */
         if (!irqd_is_level_type(d))
                 mtdcr(uic->dcrbase + UIC_SR, sr);
-        spin_unlock_irqrestore(&uic->lock, flags);
+        raw_spin_unlock_irqrestore(&uic->lock, flags);
 }
 
 static int uic_set_irq_type(struct irq_data *d, unsigned int flow_type)
@@ -152,7 +152,7 @@ static int uic_set_irq_type(struct irq_data *d, unsigned int flow_type)
 
         mask = ~(1 << (31 - src));
 
-        spin_lock_irqsave(&uic->lock, flags);
+        raw_spin_lock_irqsave(&uic->lock, flags);
         tr = mfdcr(uic->dcrbase + UIC_TR);
         pr = mfdcr(uic->dcrbase + UIC_PR);
         tr = (tr & mask) | (trigger << (31-src));
@@ -161,7 +161,7 @@ static int uic_set_irq_type(struct irq_data *d, unsigned int flow_type)
         mtdcr(uic->dcrbase + UIC_PR, pr);
         mtdcr(uic->dcrbase + UIC_TR, tr);
 
-        spin_unlock_irqrestore(&uic->lock, flags);
+        raw_spin_unlock_irqrestore(&uic->lock, flags);
 
         return 0;
 }
@@ -254,7 +254,7 @@ static struct uic * __init uic_init_one(struct device_node *node)
         if (! uic)
                 return NULL; /* FIXME: panic? */
 
-        spin_lock_init(&uic->lock);
+        raw_spin_lock_init(&uic->lock);
         indexp = of_get_property(node, "cell-index", &len);
         if (!indexp || (len != sizeof(u32))) {
                 printk(KERN_ERR "uic: Device node %s has missing or invalid "
diff --git a/arch/powerpc/sysdev/xics/Makefile b/arch/powerpc/sysdev/xics/Makefile
index b75a6059337f..c606aa8ba60a 100644
--- a/arch/powerpc/sysdev/xics/Makefile
+++ b/arch/powerpc/sysdev/xics/Makefile
@@ -4,3 +4,4 @@ obj-y				+= xics-common.o
 obj-$(CONFIG_PPC_ICP_NATIVE)    += icp-native.o
 obj-$(CONFIG_PPC_ICP_HV)        += icp-hv.o
 obj-$(CONFIG_PPC_ICS_RTAS)      += ics-rtas.o
+obj-$(CONFIG_PPC_POWERNV)       += ics-opal.o
diff --git a/arch/powerpc/sysdev/xics/icp-native.c b/arch/powerpc/sysdev/xics/icp-native.c
index 50e32afe392e..4c79b6fbee1c 100644
--- a/arch/powerpc/sysdev/xics/icp-native.c
+++ b/arch/powerpc/sysdev/xics/icp-native.c
@@ -276,7 +276,7 @@ static const struct icp_ops icp_native_ops = {
 #endif
 };
 
-int icp_native_init(void)
+int __init icp_native_init(void)
 {
         struct device_node *np;
         u32 indx = 0;
diff --git a/arch/powerpc/sysdev/xics/ics-opal.c b/arch/powerpc/sysdev/xics/ics-opal.c
new file mode 100644
index 000000000000..f7e8609df0d5
--- /dev/null
+++ b/arch/powerpc/sysdev/xics/ics-opal.c
@@ -0,0 +1,244 @@
+/*
+ * ICS backend for OPAL managed interrupts.
+ *
+ * Copyright 2011 IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#undef DEBUG
+
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/irq.h>
+#include <linux/smp.h>
+#include <linux/interrupt.h>
+#include <linux/init.h>
+#include <linux/cpu.h>
+#include <linux/of.h>
+#include <linux/spinlock.h>
+#include <linux/msi.h>
+
+#include <asm/prom.h>
+#include <asm/smp.h>
+#include <asm/machdep.h>
+#include <asm/irq.h>
+#include <asm/errno.h>
+#include <asm/xics.h>
+#include <asm/opal.h>
+#include <asm/firmware.h>
+
+static int ics_opal_mangle_server(int server)
+{
+        /* No link for now */
+        return server << 2;
+}
+
+static int ics_opal_unmangle_server(int server)
+{
+        /* No link for now */
+        return server >> 2;
+}
+
+static void ics_opal_unmask_irq(struct irq_data *d)
+{
+        unsigned int hw_irq = (unsigned int)irqd_to_hwirq(d);
+        int64_t rc;
+        int server;
+
+        pr_devel("ics-hal: unmask virq %d [hw 0x%x]\n", d->irq, hw_irq);
+
+        if (hw_irq == XICS_IPI || hw_irq == XICS_IRQ_SPURIOUS)
+                return;
+
+        server = xics_get_irq_server(d->irq, d->affinity, 0);
+        server = ics_opal_mangle_server(server);
+
+        rc = opal_set_xive(hw_irq, server, DEFAULT_PRIORITY);
+        if (rc != OPAL_SUCCESS)
+                pr_err("%s: opal_set_xive(irq=%d [hw 0x%x] server=%x)"
+                       " error %lld\n",
+                       __func__, d->irq, hw_irq, server, rc);
+}
+
+static unsigned int ics_opal_startup(struct irq_data *d)
+{
+#ifdef CONFIG_PCI_MSI
+        /*
+         * The generic MSI code returns with the interrupt disabled on the
+         * card, using the MSI mask bits. Firmware doesn't appear to unmask
+         * at that level, so we do it here by hand.
+         */
+        if (d->msi_desc)
+                unmask_msi_irq(d);
+#endif
+
+        /* unmask it */
+        ics_opal_unmask_irq(d);
+        return 0;
+}
+
+static void ics_opal_mask_real_irq(unsigned int hw_irq)
+{
+        int server = ics_opal_mangle_server(xics_default_server);
+        int64_t rc;
+
+        if (hw_irq == XICS_IPI)
+                return;
+
+        /* Have to set XIVE to 0xff to be able to remove a slot */
+        rc = opal_set_xive(hw_irq, server, 0xff);
+        if (rc != OPAL_SUCCESS)
+                pr_err("%s: opal_set_xive(0xff) irq=%u returned %lld\n",
+                       __func__, hw_irq, rc);
+}
+
+static void ics_opal_mask_irq(struct irq_data *d)
+{
+        unsigned int hw_irq = (unsigned int)irqd_to_hwirq(d);
+
+        pr_devel("ics-hal: mask virq %d [hw 0x%x]\n", d->irq, hw_irq);
+
+        if (hw_irq == XICS_IPI || hw_irq == XICS_IRQ_SPURIOUS)
+                return;
+        ics_opal_mask_real_irq(hw_irq);
+}
+
+static int ics_opal_set_affinity(struct irq_data *d,
+                                 const struct cpumask *cpumask,
+                                 bool force)
+{
+        unsigned int hw_irq = (unsigned int)irqd_to_hwirq(d);
+        int16_t server;
+        int8_t priority;
+        int64_t rc;
+        int wanted_server;
+
+        if (hw_irq == XICS_IPI || hw_irq == XICS_IRQ_SPURIOUS)
+                return -1;
+
+        rc = opal_get_xive(hw_irq, &server, &priority);
+        if (rc != OPAL_SUCCESS) {
+                pr_err("%s: opal_set_xive(irq=%d [hw 0x%x] server=%x)"
+                       " error %lld\n",
+                       __func__, d->irq, hw_irq, server, rc);
+                return -1;
+        }
+
+        wanted_server = xics_get_irq_server(d->irq, cpumask, 1);
+        if (wanted_server < 0) {
+                char cpulist[128];
+                cpumask_scnprintf(cpulist, sizeof(cpulist), cpumask);
+                pr_warning("%s: No online cpus in the mask %s for irq %d\n",
+                           __func__, cpulist, d->irq);
+                return -1;
+        }
+        server = ics_opal_mangle_server(wanted_server);
+
+        pr_devel("ics-hal: set-affinity irq %d [hw 0x%x] server: 0x%x/0x%x\n",
+                 d->irq, hw_irq, wanted_server, server);
+
+        rc = opal_set_xive(hw_irq, server, priority);
+        if (rc != OPAL_SUCCESS) {
+                pr_err("%s: opal_set_xive(irq=%d [hw 0x%x] server=%x)"
+                       " error %lld\n",
+                       __func__, d->irq, hw_irq, server, rc);
+                return -1;
+        }
+        return 0;
+}
+
+static struct irq_chip ics_opal_irq_chip = {
+        .name = "OPAL ICS",
+        .irq_startup = ics_opal_startup,
+        .irq_mask = ics_opal_mask_irq,
+        .irq_unmask = ics_opal_unmask_irq,
+        .irq_eoi = NULL, /* Patched at init time */
+        .irq_set_affinity = ics_opal_set_affinity
+};
+
+static int ics_opal_map(struct ics *ics, unsigned int virq);
+static void ics_opal_mask_unknown(struct ics *ics, unsigned long vec);
+static long ics_opal_get_server(struct ics *ics, unsigned long vec);
+
+static int ics_opal_host_match(struct ics *ics, struct device_node *node)
+{
+        return 1;
+}
+
+/* Only one global & state struct ics */
+static struct ics ics_hal = {
+        .map            = ics_opal_map,
+        .mask_unknown   = ics_opal_mask_unknown,
+        .get_server     = ics_opal_get_server,
+        .host_match     = ics_opal_host_match,
+};
+
+static int ics_opal_map(struct ics *ics, unsigned int virq)
+{
+        unsigned int hw_irq = (unsigned int)virq_to_hw(virq);
+        int64_t rc;
+        int16_t server;
+        int8_t priority;
+
+        if (WARN_ON(hw_irq == XICS_IPI || hw_irq == XICS_IRQ_SPURIOUS))
+                return -EINVAL;
+
+        /* Check if HAL knows about this interrupt */
+        rc = opal_get_xive(hw_irq, &server, &priority);
+        if (rc != OPAL_SUCCESS)
+                return -ENXIO;
+
+        irq_set_chip_and_handler(virq, &ics_opal_irq_chip, handle_fasteoi_irq);
+        irq_set_chip_data(virq, &ics_hal);
+
+        return 0;
+}
+
+static void ics_opal_mask_unknown(struct ics *ics, unsigned long vec)
+{
+        int64_t rc;
+        int16_t server;
+        int8_t priority;
+
+        /* Check if HAL knows about this interrupt */
+        rc = opal_get_xive(vec, &server, &priority);
+        if (rc != OPAL_SUCCESS)
+                return;
+
+        ics_opal_mask_real_irq(vec);
+}
+
+static long ics_opal_get_server(struct ics *ics, unsigned long vec)
+{
+        int64_t rc;
+        int16_t server;
+        int8_t priority;
+
+        /* Check if HAL knows about this interrupt */
+        rc = opal_get_xive(vec, &server, &priority);
+        if (rc != OPAL_SUCCESS)
+                return -1;
+        return ics_opal_unmangle_server(server);
+}
+
+int __init ics_opal_init(void)
+{
+        if (!firmware_has_feature(FW_FEATURE_OPAL))
+                return -ENODEV;
+
+        /* We need to patch our irq chip's EOI to point to the
+         * right ICP
+         */
+        ics_opal_irq_chip.irq_eoi = icp_ops->eoi;
+
+        /* Register ourselves */
+        xics_register_ics(&ics_hal);
+
+        pr_info("ICS OPAL backend registered\n");
+
+        return 0;
+}
diff --git a/arch/powerpc/sysdev/xics/xics-common.c b/arch/powerpc/sysdev/xics/xics-common.c
index 445c5a01b766..63762c672a03 100644
--- a/arch/powerpc/sysdev/xics/xics-common.c
+++ b/arch/powerpc/sysdev/xics/xics-common.c
@@ -134,11 +134,10 @@ static void xics_request_ipi(void)
         BUG_ON(ipi == NO_IRQ);
 
         /*
-         * IPIs are marked IRQF_DISABLED as they must run with irqs
-         * disabled, and PERCPU.  The handler was set in map.
+         * IPIs are marked IRQF_PERCPU. The handler was set in map.
          */
         BUG_ON(request_irq(ipi, icp_ops->ipi_action,
-                           IRQF_DISABLED|IRQF_PERCPU, "IPI", NULL));
+                           IRQF_PERCPU, "IPI", NULL));
 }
 
 int __init xics_smp_probe(void)
@@ -409,14 +408,10 @@ void __init xics_init(void)
         int rc = -1;
 
         /* Fist locate ICP */
-#ifdef CONFIG_PPC_ICP_HV
         if (firmware_has_feature(FW_FEATURE_LPAR))
                 rc = icp_hv_init();
-#endif
-#ifdef CONFIG_PPC_ICP_NATIVE
         if (rc < 0)
                 rc = icp_native_init();
-#endif
         if (rc < 0) {
                 pr_warning("XICS: Cannot find a Presentation Controller !\n");
                 return;
@@ -429,9 +424,9 @@ void __init xics_init(void)
         xics_ipi_chip.irq_eoi = icp_ops->eoi;
 
         /* Now locate ICS */
-#ifdef CONFIG_PPC_ICS_RTAS
         rc = ics_rtas_init();
-#endif
+        if (rc < 0)
+                rc = ics_opal_init();
         if (rc < 0)
                 pr_warning("XICS: Cannot find a Source Controller !\n");
 
diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c
index 42541bbcc7fa..03a217ae3be0 100644
--- a/arch/powerpc/xmon/xmon.c
+++ b/arch/powerpc/xmon/xmon.c
@@ -18,7 +18,7 @@
 #include <linux/delay.h>
 #include <linux/kallsyms.h>
 #include <linux/cpumask.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/sysrq.h>
 #include <linux/interrupt.h>
 #include <linux/irq.h>
@@ -340,8 +340,8 @@ int cpus_are_in_xmon(void)
 
 static inline int unrecoverable_excp(struct pt_regs *regs)
 {
-#ifdef CONFIG_4xx
-        /* We have no MSR_RI bit on 4xx, so we simply return false */
+#if defined(CONFIG_4xx) || defined(CONFIG_BOOK3E)
+        /* We have no MSR_RI bit on 4xx or Book3e, so we simply return false */
         return 0;
 #else
         return ((regs->msr & MSR_RI) == 0);