403 files changed, 14531 insertions, 16686 deletions

diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 1919634a9b32..d219ebecabf0 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -134,7 +134,9 @@ config PPC
         select HAVE_HW_BREAKPOINT if PERF_EVENTS && PPC_BOOK3S_64
         select HAVE_GENERIC_HARDIRQS
         select HAVE_SPARSE_IRQ
+        select SPARSE_IRQ
         select IRQ_PER_CPU
+        select IRQ_DOMAIN
         select GENERIC_IRQ_SHOW
         select GENERIC_IRQ_SHOW_LEVEL
         select IRQ_FORCED_THREADING
@@ -376,13 +378,16 @@ config CRASH_DUMP
           The same kernel binary can be used as production kernel and dump
           capture kernel.
 
-config PHYP_DUMP
-        bool "Hypervisor-assisted dump (EXPERIMENTAL)"
-        depends on PPC_PSERIES && EXPERIMENTAL
+config FA_DUMP
+        bool "Firmware-assisted dump"
+        depends on PPC64 && PPC_RTAS && CRASH_DUMP
         help
-          Hypervisor-assisted dump is meant to be a kdump replacement
-          offering robustness and speed not possible without system
-          hypervisor assistance.
+          A robust mechanism to get reliable kernel crash dump with
+          assistance from firmware. This approach does not use kexec,
+          instead firmware assists in booting the kdump kernel
+          while preserving memory contents. Firmware-assisted dump
+          is meant to be a kdump replacement offering robustness and
+          speed not possible without system firmware assistance.
 
           If unsure, say "N"
 
@@ -611,7 +616,7 @@ endmenu
 
 config ISA_DMA_API
         bool
-        default !PPC_ISERIES || PCI
+        default PCI
 
 menu "Bus options"
 
diff --git a/arch/powerpc/Kconfig.debug b/arch/powerpc/Kconfig.debug
index 4ccb2a009f74..72d55dbc6119 100644
--- a/arch/powerpc/Kconfig.debug
+++ b/arch/powerpc/Kconfig.debug
@@ -196,13 +196,6 @@ config PPC_EARLY_DEBUG_MAPLE
         help
           Select this to enable early debugging for Maple.
 
-config PPC_EARLY_DEBUG_ISERIES
-        bool "iSeries HV Console"
-        depends on PPC_ISERIES
-        help
-          Select this to enable early debugging for legacy iSeries. You need
-          to hit "Ctrl-x Ctrl-x" to see the messages on the console.
-
 config PPC_EARLY_DEBUG_PAS_REALMODE
         bool "PA Semi real mode"
         depends on PPC_PASEMI
diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile
index b8b105c01c64..6524c6e21896 100644
--- a/arch/powerpc/Makefile
+++ b/arch/powerpc/Makefile
@@ -157,6 +157,7 @@ core-y				+= arch/powerpc/kernel/ \
                                    arch/powerpc/net/
 core-$(CONFIG_XMON)             += arch/powerpc/xmon/
 core-$(CONFIG_KVM)              += arch/powerpc/kvm/
+core-$(CONFIG_PERF_EVENTS)      += arch/powerpc/perf/
 
 drivers-$(CONFIG_OPROFILE)      += arch/powerpc/oprofile/
 
diff --git a/arch/powerpc/boot/.gitignore b/arch/powerpc/boot/.gitignore
index 12da77ec0228..1c1aadc8c48f 100644
--- a/arch/powerpc/boot/.gitignore
+++ b/arch/powerpc/boot/.gitignore
@@ -27,7 +27,6 @@ zImage.bin.*
 zImage.chrp
 zImage.coff
 zImage.holly
-zImage.iseries
 zImage.*lds
 zImage.miboot
 zImage.pmac
diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile
index 8844a17ce8ed..e8461cb18d04 100644
--- a/arch/powerpc/boot/Makefile
+++ b/arch/powerpc/boot/Makefile
@@ -184,7 +184,6 @@ image-$(CONFIG_PPC_EFIKA)		+= zImage.chrp
 image-$(CONFIG_PPC_PMAC)                += zImage.pmac
 image-$(CONFIG_PPC_HOLLY)               += dtbImage.holly
 image-$(CONFIG_PPC_PRPMC2800)           += dtbImage.prpmc2800
-image-$(CONFIG_PPC_ISERIES)             += zImage.iseries
 image-$(CONFIG_DEFAULT_UIMAGE)          += uImage
 image-$(CONFIG_EPAPR_BOOT)              += zImage.epapr
 
@@ -247,7 +246,7 @@ image-$(CONFIG_ASP834x)			+= dtbImage.asp834x-redboot
 image-$(CONFIG_MPC8540_ADS)             += cuImage.mpc8540ads
 image-$(CONFIG_MPC8560_ADS)             += cuImage.mpc8560ads
 image-$(CONFIG_MPC85xx_CDS)             += cuImage.mpc8541cds \
-                                           cuImage.mpc8548cds \
+                                           cuImage.mpc8548cds_32b \
                                            cuImage.mpc8555cds
 image-$(CONFIG_MPC85xx_MDS)             += cuImage.mpc8568mds
 image-$(CONFIG_MPC85xx_DS)              += cuImage.mpc8544ds \
@@ -311,12 +310,6 @@ $(obj)/dtbImage.%: vmlinux $(wrapperbits) $(obj)/%.dtb
 $(obj)/vmlinux.strip: vmlinux
         $(STRIP) -s -R .comment $< -o $@
 
-# The iseries hypervisor won't take an ET_DYN executable, so this
-# changes the type (byte 17) in the file to ET_EXEC (2).
-$(obj)/zImage.iseries: vmlinux
-        $(STRIP) -s -R .comment $< -o $@
-        printf "\x02" | dd of=$@ conv=notrunc bs=1 seek=17
-
 $(obj)/uImage: vmlinux $(wrapperbits)
         $(call if_changed,wrap,uboot)
 
@@ -364,7 +357,7 @@ install: $(CONFIGURE) $(addprefix $(obj)/, $(image-y))
 # anything not in $(targets)
 clean-files += $(image-) $(initrd-) cuImage.* dtbImage.* treeImage.* \
         zImage zImage.initrd zImage.chrp zImage.coff zImage.holly \
-        zImage.iseries zImage.miboot zImage.pmac zImage.pseries \
+        zImage.miboot zImage.pmac zImage.pseries \
         zImage.maple simpleImage.* otheros.bld *.dtb
 
 # clean up files cached by wrapper
diff --git a/arch/powerpc/boot/dts/a4m072.dts b/arch/powerpc/boot/dts/a4m072.dts
new file mode 100644
index 000000000000..fabe7b7d5f13
--- /dev/null
+++ b/arch/powerpc/boot/dts/a4m072.dts
@@ -0,0 +1,168 @@
+/*
+ * a4m072 board Device Tree Source
+ *
+ * Copyright (C) 2011 DENX Software Engineering GmbH
+ * Heiko Schocher <hs@denx.de>
+ *
+ * Copyright (C) 2007 Semihalf
+ * Marian Balakowicz <m8@semihalf.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/ "mpc5200b.dtsi"
+
+/ {
+        model = "anonymous,a4m072";
+        compatible = "anonymous,a4m072";
+
+        soc5200@f0000000 {
+                #address-cells = <1>;
+                #size-cells = <1>;
+                compatible = "fsl,mpc5200b-immr";
+                ranges = <0 0xf0000000 0x0000c000>;
+                reg = <0xf0000000 0x00000100>;
+                bus-frequency = <0>; /* From boot loader */
+                system-frequency = <0>; /* From boot loader */
+
+                cdm@200 {
+                        fsl,init-ext-48mhz-en = <0x0>;
+                        fsl,init-fd-enable = <0x01>;
+                        fsl,init-fd-counters = <0x3333>;
+                };
+
+                timer@600 {
+                        fsl,has-wdt;
+                };
+
+                gpt3: timer@630 { /* General Purpose Timer in GPIO mode */
+                        compatible = "fsl,mpc5200b-gpt-gpio","fsl,mpc5200-gpt-gpio";
+                        gpio-controller;
+                        #gpio-cells = <2>;
+                };
+
+                gpt4: timer@640 { /* General Purpose Timer in GPIO mode */
+                        compatible = "fsl,mpc5200b-gpt-gpio","fsl,mpc5200-gpt-gpio";
+                        gpio-controller;
+                        #gpio-cells = <2>;
+                };
+
+                gpt5: timer@650 { /* General Purpose Timer in GPIO mode */
+                        compatible = "fsl,mpc5200b-gpt-gpio","fsl,mpc5200-gpt-gpio";
+                        gpio-controller;
+                        #gpio-cells = <2>;
+                };
+
+                spi@f00 {
+                        status = "disabled";
+                };
+
+                psc@2000 {
+                        compatible = "fsl,mpc5200b-psc-uart","fsl,mpc5200-psc-uart";
+                        reg = <0x2000 0x100>;
+                        interrupts = <2 1 0>;
+                };
+
+                psc@2200 {
+                        compatible = "fsl,mpc5200b-psc-uart","fsl,mpc5200-psc-uart";
+                        reg = <0x2200 0x100>;
+                        interrupts = <2 2 0>;
+                };
+
+                psc@2400 {
+                        compatible = "fsl,mpc5200b-psc-uart","fsl,mpc5200-psc-uart";
+                        reg = <0x2400 0x100>;
+                        interrupts = <2 3 0>;
+                };
+
+                psc@2600 {
+                        status = "disabled";
+                };
+
+                psc@2800 {
+                        status = "disabled";
+                };
+
+                psc@2c00 {
+                        compatible = "fsl,mpc5200b-psc-uart","fsl,mpc5200-psc-uart";
+                        reg = <0x2c00 0x100>;
+                        interrupts = <2 4 0>;
+                };
+
+                ethernet@3000 {
+                        phy-handle = <&phy0>;
+                };
+
+                mdio@3000 {
+                        phy0: ethernet-phy@1f {
+                                reg = <0x1f>;
+                                interrupts = <1 2 0>; /* IRQ 2 active low */
+                        };
+                };
+
+                i2c@3d00 {
+                        status = "disabled";
+                };
+
+                i2c@3d40 {
+                        hwmon@2e {
+                                compatible = "nsc,lm87";
+                                reg = <0x2e>;
+                        };
+                        rtc@51 {
+                                compatible = "nxp,rtc8564";
+                                reg = <0x51>;
+                        };
+                };
+        };
+
+        localbus {
+                compatible = "fsl,mpc5200b-lpb","simple-bus";
+                #address-cells = <2>;
+                #size-cells = <1>;
+                ranges = <0 0 0xfe000000 0x02000000
+                          1 0 0x62000000 0x00400000
+                          2 0 0x64000000 0x00200000
+                          3 0 0x66000000 0x01000000
+                          6 0 0x68000000 0x01000000
+                          7 0 0x6a000000 0x00000004>;
+
+                flash@0,0 {
+                        compatible = "cfi-flash";
+                        reg = <0 0 0x02000000>;
+                        bank-width = <2>;
+                        #size-cells = <1>;
+                        #address-cells = <1>;
+                };
+                sram0@1,0 {
+                        compatible = "mtd-ram";
+                        reg = <1 0x00000 0x00400000>;
+                        bank-width = <2>;
+                };
+        };
+
+        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 = <
+                                 /* IDSEL 0x16 */
+                                 0xc000 0 0 1 &mpc5200_pic 1 3 3
+                                 0xc000 0 0 2 &mpc5200_pic 1 3 3
+                                 0xc000 0 0 3 &mpc5200_pic 1 3 3
+                                 0xc000 0 0 4 &mpc5200_pic 1 3 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/bluestone.dts b/arch/powerpc/boot/dts/bluestone.dts
index 2a56a0dbd1f7..7bda373f10ef 100644
--- a/arch/powerpc/boot/dts/bluestone.dts
+++ b/arch/powerpc/boot/dts/bluestone.dts
@@ -33,7 +33,7 @@
         aliases {
                 ethernet0 = &EMAC0;
                 serial0 = &UART0;
-                //serial1 = &UART1; --gcl missing UART1 label
+                serial1 = &UART1;
         };
 
         cpus {
@@ -52,7 +52,7 @@
                         d-cache-size = <32768>;
                         dcr-controller;
                         dcr-access-method = "native";
-                        //next-level-cache = <&L2C0>; --gcl missing L2C0 label
+                        next-level-cache = <&L2C0>;
                 };
         };
 
@@ -117,6 +117,16 @@
                 dcr-reg = <0x00c 0x002>;
         };
 
+        L2C0: l2c {
+                compatible = "ibm,l2-cache-apm82181", "ibm,l2-cache";
+                dcr-reg = <0x020 0x008
+                           0x030 0x008>;
+                cache-line-size = <32>;
+                cache-size = <262144>;
+                interrupt-parent = <&UIC1>;
+                interrupts = <11 1>;
+        };
+
         plb {
                 compatible = "ibm,plb4";
                 #address-cells = <2>;
@@ -182,6 +192,53 @@
                                                 reg = <0x001a0000 0x00060000>;
                                         };
                                 };
+
+                                ndfc@1,0 {
+                                        compatible = "ibm,ndfc";
+                                        reg = <0x00000003 0x00000000 0x00002000>;
+                                        ccr = <0x00001000>;
+                                        bank-settings = <0x80002222>;
+                                        #address-cells = <1>;
+                                        #size-cells = <1>;
+                                        /* 2Gb Nand Flash */
+                                        nand {
+                                                #address-cells = <1>;
+                                                #size-cells = <1>;
+
+                                                partition@0 {
+                                                        label = "firmware";
+                                                        reg   = <0x00000000 0x00C00000>;
+                                                };
+                                                partition@c00000 {
+                                                        label = "environment";
+                                                        reg   = <0x00C00000 0x00B00000>;
+                                                };
+                                                partition@1700000 {
+                                                        label = "kernel";
+                                                        reg   = <0x01700000 0x00E00000>;
+                                                };
+                                                partition@2500000 {
+                                                        label = "root";
+                                                        reg   = <0x02500000 0x08200000>;
+                                                };
+                                                partition@a700000 {
+                                                        label = "device-tree";
+                                                        reg   = <0x0A700000 0x00B00000>;
+                                                };
+                                                partition@b200000 {
+                                                        label = "config";
+                                                        reg   = <0x0B200000 0x00D00000>;
+                                                };
+                                                partition@bf00000 {
+                                                        label = "diag";
+                                                        reg   = <0x0BF00000 0x00C00000>;
+                                                };
+                                                partition@cb00000 {
+                                                        label = "vendor";
+                                                        reg   = <0x0CB00000 0x3500000>;
+                                                };
+                                        };
+                                };
                         };
 
                         UART0: serial@ef600300 {
@@ -195,11 +252,36 @@
                                 interrupts = <0x1 0x4>;
                         };
 
+                        UART1: serial@ef600400 {
+                                device_type = "serial";
+                                compatible = "ns16550";
+                                reg = <0xef600400 0x00000008>;
+                                virtual-reg = <0xef600400>;
+                                clock-frequency = <0>; /* Filled in by U-Boot */
+                                current-speed = <0>; /* Filled in by U-Boot */
+                                interrupt-parent = <&UIC0>;
+                                interrupts = <0x1 0x4>;
+                        };
+
                         IIC0: i2c@ef600700 {
                                 compatible = "ibm,iic";
                                 reg = <0xef600700 0x00000014>;
                                 interrupt-parent = <&UIC0>;
                                 interrupts = <0x2 0x4>;
+                                #address-cells = <1>;
+                                #size-cells = <0>;
+                                rtc@68 {
+                                        compatible = "stm,m41t80";
+                                        reg = <0x68>;
+                                        interrupt-parent = <&UIC0>;
+                                        interrupts = <0x9 0x8>;
+                                };
+                                sttm@4C {
+                                        compatible = "adm,adm1032";
+                                        reg = <0x4C>;
+                                        interrupt-parent = <&UIC1>;
+                                        interrupts = <0x1E 0x8>; /* CPU_THERNAL_L */
+                                };
                         };
 
                         IIC1: i2c@ef600800 {
@@ -222,7 +304,7 @@
 
                         EMAC0: ethernet@ef600c00 {
                                 device_type = "network";
-                                compatible = "ibm,emac4sync";
+                                compatible = "ibm,emac-apm821xx", "ibm,emac4sync";
                                 interrupt-parent = <&EMAC0>;
                                 interrupts = <0x0 0x1>;
                                 #interrupt-cells = <1>;
@@ -250,5 +332,46 @@
                         };
                 };
 
+                PCIE0: pciex@d00000000 {
+                        device_type = "pci";
+                        #interrupt-cells = <1>;
+                        #size-cells = <2>;
+                        #address-cells = <3>;
+                        compatible = "ibm,plb-pciex-apm821xx", "ibm,plb-pciex";
+                        primary;
+                        port = <0x0>; /* port number */
+                        reg = <0x0000000d 0x00000000 0x20000000 /* Config space access */
+                               0x0000000c 0x08010000 0x00001000>;       /* Registers */
+                        dcr-reg = <0x100 0x020>;
+                        sdr-base = <0x300>;
+
+                        /* Outbound ranges, one memory and one IO,
+                         * later cannot be changed
+                         */
+                        ranges = <0x02000000 0x00000000 0x80000000 0x0000000e 0x00000000 0x00000000 0x80000000
+                                  0x02000000 0x00000000 0x00000000 0x0000000f 0x00000000 0x00000000 0x00100000
+                                  0x01000000 0x00000000 0x00000000 0x0000000f 0x80000000 0x00000000 0x00010000>;
+
+                        /* Inbound 2GB range starting at 0 */
+                        dma-ranges = <0x42000000 0x0 0x0 0x0 0x0 0x0 0x80000000>;
+
+                        /* This drives busses 40 to 0x7f */
+                        bus-range = <0x40 0x7f>;
+
+                        /* Legacy interrupts (note the weird polarity, the bridge seems
+                         * to invert PCIe legacy interrupts).
+                         * We are de-swizzling here because the numbers are actually for
+                         * port of the root complex virtual P2P bridge. But I want
+                         * to avoid putting a node for it in the tree, so the numbers
+                         * below are basically de-swizzled numbers.
+                         * The real slot is on idsel 0, so the swizzling is 1:1
+                         */
+                        interrupt-map-mask = <0x0 0x0 0x0 0x7>;
+                        interrupt-map = <
+                                0x0 0x0 0x0 0x1 &UIC3 0xc 0x4 /* swizzled int A */
+                                0x0 0x0 0x0 0x2 &UIC3 0xd 0x4 /* swizzled int B */
+                                0x0 0x0 0x0 0x3 &UIC3 0xe 0x4 /* swizzled int C */
+                                0x0 0x0 0x0 0x4 &UIC3 0xf 0x4 /* swizzled int D */>;
+                };
         };
 };
diff --git a/arch/powerpc/boot/dts/fsl/mpc8536si-post.dtsi b/arch/powerpc/boot/dts/fsl/mpc8536si-post.dtsi
index 89af62637707..c8b2daa40ac8 100644
--- a/arch/powerpc/boot/dts/fsl/mpc8536si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/mpc8536si-post.dtsi
@@ -202,7 +202,7 @@
 /include/ "pq3-etsec1-timer-0.dtsi"
 
         usb@22000 {
-                compatible = "fsl,mpc8536-usb2-mph", "fsl-usb2-mph";
+                compatible = "fsl-usb2-mph-v1.2", "fsl,mpc8536-usb2-mph", "fsl-usb2-mph";
                 reg = <0x22000 0x1000>;
                 #address-cells = <1>;
                 #size-cells = <0>;
@@ -210,7 +210,7 @@
         };
 
         usb@23000 {
-                compatible = "fsl,mpc8536-usb2-mph", "fsl-usb2-mph";
+                compatible = "fsl-usb2-mph-v1.2", "fsl,mpc8536-usb2-mph", "fsl-usb2-mph";
                 reg = <0x23000 0x1000>;
                 #address-cells = <1>;
                 #size-cells = <0>;
@@ -236,6 +236,10 @@
         };
 
 /include/ "pq3-esdhc-0.dtsi"
+        sdhc@2e000 {
+                compatible = "fsl,mpc8536-esdhc", "fsl,esdhc";
+        };
+
 /include/ "pq3-sec3.0-0.dtsi"
 /include/ "pq3-mpic.dtsi"
 /include/ "pq3-mpic-timer-B.dtsi"
diff --git a/arch/powerpc/boot/dts/fsl/mpc8548si-post.dtsi b/arch/powerpc/boot/dts/fsl/mpc8548si-post.dtsi
index 9d8023a69d7d..579d76cb8e32 100644
--- a/arch/powerpc/boot/dts/fsl/mpc8548si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/mpc8548si-post.dtsi
@@ -89,6 +89,21 @@
         };
 };
 
+&rio {
+        compatible = "fsl,srio";
+        interrupts = <48 2 0 0>;
+        #address-cells = <2>;
+        #size-cells = <2>;
+        fsl,srio-rmu-handle = <&rmu>;
+        ranges;
+
+        port1 {
+                #address-cells = <2>;
+                #size-cells = <2>;
+                cell-index = <1>;
+        };
+};
+
 &soc {
         #address-cells = <1>;
         #size-cells = <1>;
@@ -134,6 +149,7 @@
 
 /include/ "pq3-sec2.1-0.dtsi"
 /include/ "pq3-mpic.dtsi"
+/include/ "pq3-rmu-0.dtsi"
 
         global-utilities@e0000 {
                 compatible = "fsl,mpc8548-guts";
diff --git a/arch/powerpc/boot/dts/fsl/mpc8548si-pre.dtsi b/arch/powerpc/boot/dts/fsl/mpc8548si-pre.dtsi
index 289f1218d755..720422d83529 100644
--- a/arch/powerpc/boot/dts/fsl/mpc8548si-pre.dtsi
+++ b/arch/powerpc/boot/dts/fsl/mpc8548si-pre.dtsi
@@ -43,7 +43,9 @@
                 serial0 = &serial0;
                 serial1 = &serial1;
                 ethernet0 = &enet0;
-                ethernet1 = &enet2;
+                ethernet1 = &enet1;
+                ethernet2 = &enet2;
+                ethernet3 = &enet3;
                 pci0 = &pci0;
                 pci1 = &pci1;
                 pci2 = &pci2;
diff --git a/arch/powerpc/boot/dts/fsl/p1010si-post.dtsi b/arch/powerpc/boot/dts/fsl/p1010si-post.dtsi
index bd9e163c764b..0bde9ee8afaf 100644
--- a/arch/powerpc/boot/dts/fsl/p1010si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/p1010si-post.dtsi
@@ -156,9 +156,13 @@
 
 /include/ "pq3-dma-0.dtsi"
 /include/ "pq3-usb2-dr-0.dtsi"
+        usb@22000 {
+                compatible = "fsl-usb2-dr-v1.6", "fsl-usb2-dr";
+        };
 /include/ "pq3-esdhc-0.dtsi"
         sdhc@2e000 {
-                fsl,sdhci-auto-cmd12;
+                compatible = "fsl,p1010-esdhc", "fsl,esdhc";
+                sdhci,auto-cmd12;
         };
 
 /include/ "pq3-sec4.4-0.dtsi"
diff --git a/arch/powerpc/boot/dts/fsl/p1020si-post.dtsi b/arch/powerpc/boot/dts/fsl/p1020si-post.dtsi
index fc924c5ffebe..68cc5e7f6477 100644
--- a/arch/powerpc/boot/dts/fsl/p1020si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/p1020si-post.dtsi
@@ -142,9 +142,19 @@
 
 /include/ "pq3-dma-0.dtsi"
 /include/ "pq3-usb2-dr-0.dtsi"
+        usb@22000 {
+                compatible = "fsl-usb2-dr-v1.6", "fsl-usb2-dr";
+        };
 /include/ "pq3-usb2-dr-1.dtsi"
+        usb@23000 {
+                compatible = "fsl-usb2-dr-v1.6", "fsl-usb2-dr";
+        };
 
 /include/ "pq3-esdhc-0.dtsi"
+        sdhc@2e000 {
+                compatible = "fsl,p1020-esdhc", "fsl,esdhc";
+                sdhci,auto-cmd12;
+        };
 /include/ "pq3-sec3.3-0.dtsi"
 
 /include/ "pq3-mpic.dtsi"
diff --git a/arch/powerpc/boot/dts/fsl/p1021si-post.dtsi b/arch/powerpc/boot/dts/fsl/p1021si-post.dtsi
index 38ba54d1e32e..4252ef85fb7a 100644
--- a/arch/powerpc/boot/dts/fsl/p1021si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/p1021si-post.dtsi
@@ -142,8 +142,15 @@
 
 /include/ "pq3-dma-0.dtsi"
 /include/ "pq3-usb2-dr-0.dtsi"
+        usb@22000 {
+                compatible = "fsl-usb2-dr-v1.6", "fsl-usb2-dr";
+        };
 
 /include/ "pq3-esdhc-0.dtsi"
+        sdhc@2e000 {
+                sdhci,auto-cmd12;
+        };
+
 /include/ "pq3-sec3.3-0.dtsi"
 
 /include/ "pq3-mpic.dtsi"
diff --git a/arch/powerpc/boot/dts/fsl/p1022si-post.dtsi b/arch/powerpc/boot/dts/fsl/p1022si-post.dtsi
index 16239b199d0a..06216b8c0af5 100644
--- a/arch/powerpc/boot/dts/fsl/p1022si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/p1022si-post.dtsi
@@ -35,7 +35,11 @@
 &lbc {
         #address-cells = <2>;
         #size-cells = <1>;
-        compatible = "fsl,p1022-elbc", "fsl,elbc", "simple-bus";
+        /*
+         * The localbus on the P1022 is not a simple-bus because of the eLBC
+         * pin muxing when the DIU is enabled.
+         */
+        compatible = "fsl,p1022-elbc", "fsl,elbc";
         interrupts = <19 2 0 0>;
 };
 
@@ -199,11 +203,18 @@
 
 /include/ "pq3-dma-0.dtsi"
 /include/ "pq3-usb2-dr-0.dtsi"
+        usb@22000 {
+                compatible = "fsl-usb2-dr-v1.6", "fsl-usb2-dr";
+        };
 /include/ "pq3-usb2-dr-1.dtsi"
+        usb@23000 {
+                compatible = "fsl-usb2-dr-v1.6", "fsl-usb2-dr";
+        };
 
 /include/ "pq3-esdhc-0.dtsi"
         sdhc@2e000 {
-                fsl,sdhci-auto-cmd12;
+                compatible = "fsl,p1022-esdhc", "fsl,esdhc";
+                sdhci,auto-cmd12;
         };
 
 /include/ "pq3-sec3.3-0.dtsi"
diff --git a/arch/powerpc/boot/dts/fsl/p1023si-post.dtsi b/arch/powerpc/boot/dts/fsl/p1023si-post.dtsi
index b06bb4cc1fe8..941fa159cefb 100644
--- a/arch/powerpc/boot/dts/fsl/p1023si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/p1023si-post.dtsi
@@ -142,6 +142,9 @@
 
 /include/ "pq3-dma-0.dtsi"
 /include/ "pq3-usb2-dr-0.dtsi"
+        usb@22000 {
+                compatible = "fsl-usb2-dr-v1.6", "fsl-usb2-dr";
+        };
 
         crypto: crypto@300000 {
                 compatible = "fsl,sec-v4.2", "fsl,sec-v4.0";
diff --git a/arch/powerpc/boot/dts/fsl/p2020si-post.dtsi b/arch/powerpc/boot/dts/fsl/p2020si-post.dtsi
index c041050561a7..884e01bcb243 100644
--- a/arch/powerpc/boot/dts/fsl/p2020si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/p2020si-post.dtsi
@@ -171,6 +171,9 @@
 
 /include/ "pq3-dma-0.dtsi"
 /include/ "pq3-usb2-dr-0.dtsi"
+        usb@22000 {
+                compatible = "fsl-usb2-dr-v1.6", "fsl-usb2-dr";
+        };
 /include/ "pq3-etsec1-0.dtsi"
 /include/ "pq3-etsec1-timer-0.dtsi"
 
@@ -182,6 +185,10 @@
 /include/ "pq3-etsec1-1.dtsi"
 /include/ "pq3-etsec1-2.dtsi"
 /include/ "pq3-esdhc-0.dtsi"
+        sdhc@2e000 {
+                compatible = "fsl,p2020-esdhc", "fsl,esdhc";
+        };
+
 /include/ "pq3-sec3.1-0.dtsi"
 /include/ "pq3-mpic.dtsi"
 /include/ "pq3-mpic-timer-B.dtsi"
diff --git a/arch/powerpc/boot/dts/fsl/p2041si-post.dtsi b/arch/powerpc/boot/dts/fsl/p2041si-post.dtsi
index 234a399ddeb2..531eab82c6c9 100644
--- a/arch/powerpc/boot/dts/fsl/p2041si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/p2041si-post.dtsi
@@ -309,12 +309,14 @@
 /include/ "qoriq-gpio-0.dtsi"
 /include/ "qoriq-usb2-mph-0.dtsi"
                 usb0: usb@210000 {
+                        compatible = "fsl-usb2-mph-v1.6", "fsl,mpc85xx-usb2-mph", "fsl-usb2-mph";
                         phy_type = "utmi";
                         port0;
                 };
 
 /include/ "qoriq-usb2-dr-0.dtsi"
                 usb1: usb@211000 {
+                        compatible = "fsl-usb2-dr-v1.6", "fsl,mpc85xx-usb2-dr", "fsl-usb2-dr";
                         dr_mode = "host";
                         phy_type = "utmi";
                 };
diff --git a/arch/powerpc/boot/dts/fsl/p3041si-post.dtsi b/arch/powerpc/boot/dts/fsl/p3041si-post.dtsi
index d41d08de7f7e..af4ebc8009e3 100644
--- a/arch/powerpc/boot/dts/fsl/p3041si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/p3041si-post.dtsi
@@ -336,12 +336,14 @@
 /include/ "qoriq-gpio-0.dtsi"
 /include/ "qoriq-usb2-mph-0.dtsi"
                 usb0: usb@210000 {
+                        compatible = "fsl-usb2-mph-v1.6", "fsl-usb2-mph";
                         phy_type = "utmi";
                         port0;
                 };
 
 /include/ "qoriq-usb2-dr-0.dtsi"
                 usb1: usb@211000 {
+                        compatible = "fsl-usb2-dr-v1.6", "fsl,mpc85xx-usb2-dr", "fsl-usb2-dr";
                         dr_mode = "host";
                         phy_type = "utmi";
                 };
diff --git a/arch/powerpc/boot/dts/fsl/p3060si-post.dtsi b/arch/powerpc/boot/dts/fsl/p3060si-post.dtsi
index a63edd195ae5..b3e56929eee2 100644
--- a/arch/powerpc/boot/dts/fsl/p3060si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/p3060si-post.dtsi
@@ -291,6 +291,12 @@
 /include/ "qoriq-duart-1.dtsi"
 /include/ "qoriq-gpio-0.dtsi"
 /include/ "qoriq-usb2-mph-0.dtsi"
+        usb@210000 {
+                compatible = "fsl-usb2-mph-v2.2", "fsl,mpc85xx-usb2-mph", "fsl-usb2-mph";
+        };
 /include/ "qoriq-usb2-dr-0.dtsi"
+        usb@211000 {
+                compatible = "fsl-usb2-dr-v2.2", "fsl,mpc85xx-usb2-dr", "fsl-usb2-dr";
+        };
 /include/ "qoriq-sec4.1-0.dtsi"
 };
diff --git a/arch/powerpc/boot/dts/fsl/p5020si-post.dtsi b/arch/powerpc/boot/dts/fsl/p5020si-post.dtsi
index 914074b91a85..64b6abea8464 100644
--- a/arch/powerpc/boot/dts/fsl/p5020si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/p5020si-post.dtsi
@@ -339,12 +339,14 @@
 /include/ "qoriq-gpio-0.dtsi"
 /include/ "qoriq-usb2-mph-0.dtsi"
                 usb0: usb@210000 {
+                        compatible = "fsl-usb2-mph-v1.6", "fsl,mpc85xx-usb2-mph", "fsl-usb2-mph";
                         phy_type = "utmi";
                         port0;
                 };
 
 /include/ "qoriq-usb2-dr-0.dtsi"
                 usb1: usb@211000 {
+                        compatible = "fsl-usb2-dr-v1.6", "fsl,mpc85xx-usb2-dr", "fsl-usb2-dr";
                         dr_mode = "host";
                         phy_type = "utmi";
                 };
diff --git a/arch/powerpc/boot/dts/fsl/pq3-etsec1-0.dtsi b/arch/powerpc/boot/dts/fsl/pq3-etsec1-0.dtsi
index a1979ae334a7..3b0650a98478 100644
--- a/arch/powerpc/boot/dts/fsl/pq3-etsec1-0.dtsi
+++ b/arch/powerpc/boot/dts/fsl/pq3-etsec1-0.dtsi
@@ -1,7 +1,7 @@
 /*
  * PQ3 eTSEC device tree stub [ @ offsets 0x24000 ]
  *
- * Copyright 2011 Freescale Semiconductor Inc.
+ * Copyright 2011-2012 Freescale Semiconductor Inc.
  *
  * Redistribution and use in source and binary forms, with or without
  * modification, are permitted provided that the following conditions are met:
@@ -41,6 +41,7 @@ ethernet@24000 {
         compatible = "gianfar";
         reg = <0x24000 0x1000>;
         ranges = <0x0 0x24000 0x1000>;
+        fsl,magic-packet;
         local-mac-address = [ 00 00 00 00 00 00 ];
         interrupts = <29 2 0 0 30 2 0 0 34 2 0 0>;
 };
diff --git a/arch/powerpc/boot/dts/fsl/pq3-etsec1-1.dtsi b/arch/powerpc/boot/dts/fsl/pq3-etsec1-1.dtsi
index 4c4fdde1ec2a..96693b41f0f1 100644
--- a/arch/powerpc/boot/dts/fsl/pq3-etsec1-1.dtsi
+++ b/arch/powerpc/boot/dts/fsl/pq3-etsec1-1.dtsi
@@ -1,7 +1,7 @@
 /*
  * PQ3 eTSEC device tree stub [ @ offsets 0x25000 ]
  *
- * Copyright 2011 Freescale Semiconductor Inc.
+ * Copyright 2011-2012 Freescale Semiconductor Inc.
  *
  * Redistribution and use in source and binary forms, with or without
  * modification, are permitted provided that the following conditions are met:
@@ -41,6 +41,7 @@ ethernet@25000 {
         compatible = "gianfar";
         reg = <0x25000 0x1000>;
         ranges = <0x0 0x25000 0x1000>;
+        fsl,magic-packet;
         local-mac-address = [ 00 00 00 00 00 00 ];
         interrupts = <35 2 0 0 36 2 0 0 40 2 0 0>;
 };
diff --git a/arch/powerpc/boot/dts/fsl/pq3-etsec1-2.dtsi b/arch/powerpc/boot/dts/fsl/pq3-etsec1-2.dtsi
index 4b8ab438668a..6b3fab19da1f 100644
--- a/arch/powerpc/boot/dts/fsl/pq3-etsec1-2.dtsi
+++ b/arch/powerpc/boot/dts/fsl/pq3-etsec1-2.dtsi
@@ -1,7 +1,7 @@
 /*
  * PQ3 eTSEC device tree stub [ @ offsets 0x26000 ]
  *
- * Copyright 2011 Freescale Semiconductor Inc.
+ * Copyright 2011-2012 Freescale Semiconductor Inc.
  *
  * Redistribution and use in source and binary forms, with or without
  * modification, are permitted provided that the following conditions are met:
@@ -41,6 +41,7 @@ ethernet@26000 {
         compatible = "gianfar";
         reg = <0x26000 0x1000>;
         ranges = <0x0 0x26000 0x1000>;
+        fsl,magic-packet;
         local-mac-address = [ 00 00 00 00 00 00 ];
         interrupts = <31 2 0 0 32 2 0 0 33 2 0 0>;
 };
diff --git a/arch/powerpc/boot/dts/fsl/pq3-etsec1-3.dtsi b/arch/powerpc/boot/dts/fsl/pq3-etsec1-3.dtsi
index 40c9137729ae..0da592d93ddd 100644
--- a/arch/powerpc/boot/dts/fsl/pq3-etsec1-3.dtsi
+++ b/arch/powerpc/boot/dts/fsl/pq3-etsec1-3.dtsi
@@ -1,7 +1,7 @@
 /*
  * PQ3 eTSEC device tree stub [ @ offsets 0x27000 ]
  *
- * Copyright 2011 Freescale Semiconductor Inc.
+ * Copyright 2011-2012 Freescale Semiconductor Inc.
  *
  * Redistribution and use in source and binary forms, with or without
  * modification, are permitted provided that the following conditions are met:
@@ -41,6 +41,7 @@ ethernet@27000 {
         compatible = "gianfar";
         reg = <0x27000 0x1000>;
         ranges = <0x0 0x27000 0x1000>;
+        fsl,magic-packet;
         local-mac-address = [ 00 00 00 00 00 00 ];
         interrupts = <37 2 0 0 38 2 0 0 39 2 0 0>;
 };
diff --git a/arch/powerpc/boot/dts/fsl/pq3-mpic.dtsi b/arch/powerpc/boot/dts/fsl/pq3-mpic.dtsi
index 5c8046065844..fdedf7b1fe0f 100644
--- a/arch/powerpc/boot/dts/fsl/pq3-mpic.dtsi
+++ b/arch/powerpc/boot/dts/fsl/pq3-mpic.dtsi
@@ -39,6 +39,9 @@ mpic: pic@40000 {
         reg = <0x40000 0x40000>;
         compatible = "fsl,mpic";
         device_type = "open-pic";
+        big-endian;
+        single-cpu-affinity;
+        last-interrupt-source = <255>;
 };
 
 timer@41100 {
diff --git a/arch/powerpc/boot/dts/fsl/pq3-sec4.4-0.dtsi b/arch/powerpc/boot/dts/fsl/pq3-sec4.4-0.dtsi
index bf957a7fca2a..d4c9d5daab21 100644
--- a/arch/powerpc/boot/dts/fsl/pq3-sec4.4-0.dtsi
+++ b/arch/powerpc/boot/dts/fsl/pq3-sec4.4-0.dtsi
@@ -33,32 +33,32 @@
  */
 
 crypto@30000 {
-        compatible = "fsl,sec4.4", "fsl,sec4.0";
+        compatible = "fsl,sec-v4.4", "fsl,sec-v4.0";
         #address-cells = <1>;
         #size-cells = <1>;
         reg              = <0x30000 0x10000>;
         interrupts       = <58 2 0 0>;
 
         sec_jr0: jr@1000 {
-                compatible = "fsl,sec4.4-job-ring", "fsl,sec4.0-job-ring";
+                compatible = "fsl,sec-v4.4-job-ring", "fsl,sec-v4.0-job-ring";
                 reg        = <0x1000 0x1000>;
                 interrupts       = <45 2 0 0>;
         };
 
         sec_jr1: jr@2000 {
-                compatible = "fsl,sec4.4-job-ring", "fsl,sec4.0-job-ring";
+                compatible = "fsl,sec-v4.4-job-ring", "fsl,sec-v4.0-job-ring";
                 reg        = <0x2000 0x1000>;
                 interrupts       = <45 2 0 0>;
         };
 
         sec_jr2: jr@3000 {
-                compatible = "fsl,sec4.4-job-ring", "fsl,sec4.0-job-ring";
+                compatible = "fsl,sec-v4.4-job-ring", "fsl,sec-v4.0-job-ring";
                 reg        = <0x3000 0x1000>;
                 interrupts       = <45 2 0 0>;
         };
 
         sec_jr3: jr@4000 {
-                compatible = "fsl,sec4.4-job-ring", "fsl,sec4.0-job-ring";
+                compatible = "fsl,sec-v4.4-job-ring", "fsl,sec-v4.0-job-ring";
                 reg        = <0x4000 0x1000>;
                 interrupts       = <45 2 0 0>;
         };
diff --git a/arch/powerpc/boot/dts/fsl/qoriq-mpic.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-mpic.dtsi
index b9bada6a87dc..08f42271f86a 100644
--- a/arch/powerpc/boot/dts/fsl/qoriq-mpic.dtsi
+++ b/arch/powerpc/boot/dts/fsl/qoriq-mpic.dtsi
@@ -53,7 +53,7 @@ timer@41100 {
 
 msi0: msi@41600 {
         compatible = "fsl,mpic-msi";
-        reg = <0x41600 0x200>;
+        reg = <0x41600 0x200 0x44140 4>;
         msi-available-ranges = <0 0x100>;
         interrupts = <
                 0xe0 0 0 0
@@ -68,7 +68,7 @@ msi0: msi@41600 {
 
 msi1: msi@41800 {
         compatible = "fsl,mpic-msi";
-        reg = <0x41800 0x200>;
+        reg = <0x41800 0x200 0x45140 4>;
         msi-available-ranges = <0 0x100>;
         interrupts = <
                 0xe8 0 0 0
@@ -83,7 +83,7 @@ msi1: msi@41800 {
 
 msi2: msi@41a00 {
         compatible = "fsl,mpic-msi";
-        reg = <0x41a00 0x200>;
+        reg = <0x41a00 0x200 0x46140 4>;
         msi-available-ranges = <0 0x100>;
         interrupts = <
                 0xf0 0 0 0
diff --git a/arch/powerpc/boot/dts/ge_imp3a.dts b/arch/powerpc/boot/dts/ge_imp3a.dts
new file mode 100644
index 000000000000..fefae416a097
--- /dev/null
+++ b/arch/powerpc/boot/dts/ge_imp3a.dts
@@ -0,0 +1,255 @@
+/*
+ * GE IMP3A Device Tree Source
+ *
+ * Copyright 2010-2011 GE Intelligent Platforms Embedded Systems, 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.
+ *
+ * Based on: P2020 DS Device Tree Source
+ * Copyright 2009 Freescale Semiconductor Inc.
+ */
+
+/include/ "fsl/p2020si-pre.dtsi"
+
+/ {
+        model = "GE_IMP3A";
+        compatible = "ge,imp3a";
+
+        memory {
+                device_type = "memory";
+        };
+
+        lbc: localbus@fef05000 {
+                reg = <0 0xfef05000 0 0x1000>;
+
+                ranges = <0x0 0x0 0x0 0xff000000 0x01000000
+                          0x1 0x0 0x0 0xe0000000 0x08000000
+                          0x2 0x0 0x0 0xe8000000 0x08000000
+                          0x3 0x0 0x0 0xfc100000 0x00020000
+                          0x4 0x0 0x0 0xfc000000 0x00008000
+                          0x5 0x0 0x0 0xfc008000 0x00008000
+                          0x6 0x0 0x0 0xfee00000 0x00040000
+                          0x7 0x0 0x0 0xfee80000 0x00040000>;
+
+                /* nor@0,0 is a mirror of part of the memory in nor@1,0
+                nor@0,0 {
+                        #address-cells = <1>;
+                        #size-cells = <1>;
+                        compatible = "ge,imp3a-firmware-mirror", "cfi-flash";
+                        reg = <0x0 0x0 0x1000000>;
+                        bank-width = <2>;
+                        device-width = <1>;
+
+                        partition@0 {
+                                label = "firmware";
+                                reg = <0x0 0x1000000>;
+                                read-only;
+                        };
+                };
+                */
+
+                nor@1,0 {
+                        #address-cells = <1>;
+                        #size-cells = <1>;
+                        compatible = "ge,imp3a-paged-flash", "cfi-flash";
+                        reg = <0x1 0x0 0x8000000>;
+                        bank-width = <2>;
+                        device-width = <1>;
+
+                        partition@0 {
+                                label = "user";
+                                reg = <0x0 0x7800000>;
+                        };
+
+                        partition@7800000 {
+                                label = "firmware";
+                                reg = <0x7800000 0x800000>;
+                                read-only;
+                        };
+                };
+
+                nvram@3,0 {
+                        device_type = "nvram";
+                        compatible = "simtek,stk14ca8";
+                        reg = <0x3 0x0 0x20000>;
+                };
+
+                fpga@4,0 {
+                        compatible = "ge,imp3a-fpga-regs";
+                        reg = <0x4 0x0 0x20>;
+                };
+
+                gef_pic: pic@4,20 {
+                        #interrupt-cells = <1>;
+                        interrupt-controller;
+                        device_type = "interrupt-controller";
+                        compatible = "ge,imp3a-fpga-pic", "gef,fpga-pic-1.00";
+                        reg = <0x4 0x20 0x20>;
+                        interrupts = <6 7 0 0>;
+                };
+
+                gef_gpio: gpio@4,400 {
+                        #gpio-cells = <2>;
+                        compatible = "ge,imp3a-gpio";
+                        reg = <0x4 0x400 0x24>;
+                        gpio-controller;
+                };
+
+                wdt@4,800 {
+                        compatible = "ge,imp3a-fpga-wdt", "gef,fpga-wdt-1.00",
+                                "gef,fpga-wdt";
+                        reg = <0x4 0x800 0x8>;
+                        interrupts = <10 4>;
+                        interrupt-parent = <&gef_pic>;
+                };
+
+                /* Second watchdog available, driver currently supports one.
+                wdt@4,808 {
+                        compatible = "gef,imp3a-fpga-wdt", "gef,fpga-wdt-1.00",
+                                "gef,fpga-wdt";
+                        reg = <0x4 0x808 0x8>;
+                        interrupts = <9 4>;
+                        interrupt-parent = <&gef_pic>;
+                };
+                */
+
+                nand@6,0 {
+                        compatible = "fsl,elbc-fcm-nand";
+                        reg = <0x6 0x0 0x40000>;
+                };
+
+                nand@7,0 {
+                        compatible = "fsl,elbc-fcm-nand";
+                        reg = <0x7 0x0 0x40000>;
+                };
+        };
+
+        soc: soc@fef00000 {
+                ranges = <0x0 0 0xfef00000 0x100000>;
+
+                i2c@3000 {
+                        hwmon@48 {
+                                compatible = "national,lm92";
+                                reg = <0x48>;
+                        };
+
+                        hwmon@4c {
+                                compatible = "adi,adt7461";
+                                reg = <0x4c>;
+                        };
+
+                        rtc@51 {
+                                compatible = "epson,rx8581";
+                                reg = <0x51>;
+                        };
+
+                        eti@6b {
+                                compatible = "dallas,ds1682";
+                                reg = <0x6b>;
+                        };
+                };
+
+                usb@22000 {
+                        phy_type = "ulpi";
+                        dr_mode = "host";
+                };
+
+                mdio@24520 {
+                        phy0: ethernet-phy@0 {
+                                interrupt-parent = <&gef_pic>;
+                                interrupts = <0xc 0x4>;
+                                reg = <0x1>;
+                        };
+                        phy1: ethernet-phy@1 {
+                                interrupt-parent = <&gef_pic>;
+                                interrupts = <0xb 0x4>;
+                                reg = <0x2>;
+                        };
+                        tbi0: tbi-phy@11 {
+                                reg = <0x11>;
+                                device_type = "tbi-phy";
+                        };
+                };
+
+                mdio@25520 {
+                        tbi1: tbi-phy@11 {
+                                reg = <0x11>;
+                                device_type = "tbi-phy";
+                        };
+                };
+
+                mdio@26520 {
+                        status = "disabled";
+                };
+
+                enet0: ethernet@24000 {
+                        tbi-handle = <&tbi0>;
+                        phy-handle = <&phy0>;
+                        phy-connection-type = "gmii";
+                };
+
+                enet1: ethernet@25000 {
+                        tbi-handle = <&tbi1>;
+                        phy-handle = <&phy1>;
+                        phy-connection-type = "gmii";
+                };
+
+                enet2: ethernet@26000 {
+                        status = "disabled";
+                };
+        };
+
+        pci0: pcie@fef08000 {
+                ranges = <0x2000000 0x0 0xc0000000 0 0xc0000000 0x0 0x20000000
+                          0x1000000 0x0 0x00000000 0 0xfe020000 0x0 0x10000>;
+                reg = <0 0xfef08000 0 0x1000>;
+
+                pcie@0 {
+                        ranges = <0x2000000 0x0 0xc0000000
+                                  0x2000000 0x0 0xc0000000
+                                  0x0 0x20000000
+
+                                  0x1000000 0x0 0x0
+                                  0x1000000 0x0 0x0
+                                  0x0 0x10000>;
+                };
+        };
+
+        pci1: pcie@fef09000 {
+                reg = <0 0xfef09000 0 0x1000>;
+                ranges = <0x2000000 0x0 0xa0000000 0 0xa0000000 0x0 0x20000000
+                          0x1000000 0x0 0x00000000 0 0xfe010000 0x0 0x10000>;
+
+                pcie@0 {
+                        ranges = <0x2000000 0x0 0xa0000000
+                                  0x2000000 0x0 0xa0000000
+                                  0x0 0x20000000
+
+                                  0x1000000 0x0 0x0
+                                  0x1000000 0x0 0x0
+                                  0x0 0x10000>;
+                };
+
+        };
+
+        pci2: pcie@fef0a000 {
+                reg = <0 0xfef0a000 0 0x1000>;
+                ranges = <0x2000000 0x0 0x80000000 0 0x80000000 0x0 0x20000000
+                          0x1000000 0x0 0x00000000 0 0xfe000000 0x0 0x10000>;
+
+                pcie@0 {
+                        ranges = <0x2000000 0x0 0x80000000
+                                  0x2000000 0x0 0x80000000
+                                  0x0 0x20000000
+
+                                  0x1000000 0x0 0x0
+                                  0x1000000 0x0 0x0
+                                  0x0 0x10000>;
+                };
+        };
+};
+
+/include/ "fsl/p2020si-post.dtsi"
diff --git a/arch/powerpc/boot/dts/mpc836x_mds.dts b/arch/powerpc/boot/dts/mpc836x_mds.dts
index c0e450a551bf..81dd513d6308 100644
--- a/arch/powerpc/boot/dts/mpc836x_mds.dts
+++ b/arch/powerpc/boot/dts/mpc836x_mds.dts
@@ -405,6 +405,10 @@
                                 reg = <0x1>;
                                 device_type = "ethernet-phy";
                         };
+                        tbi-phy@2 {
+                                device_type = "tbi-phy";
+                                reg = <0x2>;
+                        };
                 };
 
                 qeic: interrupt-controller@80 {
diff --git a/arch/powerpc/boot/dts/mpc8536ds.dts b/arch/powerpc/boot/dts/mpc8536ds.dts
index c15881574fdc..19736222a0b9 100644
--- a/arch/powerpc/boot/dts/mpc8536ds.dts
+++ b/arch/powerpc/boot/dts/mpc8536ds.dts
@@ -1,7 +1,7 @@
 /*
  * MPC8536 DS Device Tree Source
  *
- * Copyright 2008 Freescale Semiconductor, Inc.
+ * Copyright 2008, 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
@@ -34,6 +34,10 @@
 
         lbc: localbus@ffe05000 {
                 reg = <0 0xffe05000 0 0x1000>;
+
+                ranges = <0x0 0x0 0x0 0xe8000000 0x08000000
+                          0x2 0x0 0x0 0xffa00000 0x00040000
+                          0x3 0x0 0x0 0xffdf0000 0x00008000>;
         };
 
         board_soc: soc: soc@ffe00000 {
diff --git a/arch/powerpc/boot/dts/mpc8536ds.dtsi b/arch/powerpc/boot/dts/mpc8536ds.dtsi
index 1462e4cf49d7..cc46dbd9746d 100644
--- a/arch/powerpc/boot/dts/mpc8536ds.dtsi
+++ b/arch/powerpc/boot/dts/mpc8536ds.dtsi
@@ -32,6 +32,99 @@
  * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  */
 
+&lbc {
+        nor@0,0 {
+                #address-cells = <1>;
+                #size-cells = <1>;
+                compatible = "cfi-flash";
+                reg = <0x0 0x0 0x8000000>;
+                bank-width = <2>;
+                device-width = <1>;
+
+                partition@0 {
+                        reg = <0x0 0x03000000>;
+                        label = "ramdisk-nor";
+                };
+
+                partition@3000000 {
+                        reg = <0x03000000 0x00e00000>;
+                        label = "diagnostic-nor";
+                        read-only;
+                };
+
+                partition@3e00000 {
+                        reg = <0x03e00000 0x00200000>;
+                        label = "dink-nor";
+                        read-only;
+                };
+
+                partition@4000000 {
+                        reg = <0x04000000 0x00400000>;
+                        label = "kernel-nor";
+                };
+
+                partition@4400000 {
+                        reg = <0x04400000 0x03b00000>;
+                        label = "fs-nor";
+                };
+
+                partition@7f00000 {
+                        reg = <0x07f00000 0x00080000>;
+                        label = "dtb-nor";
+                };
+
+                partition@7f80000 {
+                        reg = <0x07f80000 0x00080000>;
+                        label = "u-boot-nor";
+                        read-only;
+                };
+        };
+
+        nand@2,0 {
+                #address-cells = <1>;
+                #size-cells = <1>;
+                compatible = "fsl,mpc8536-fcm-nand",
+                             "fsl,elbc-fcm-nand";
+                reg = <0x2 0x0 0x40000>;
+
+                partition@0 {
+                        reg = <0x0 0x02000000>;
+                        label = "u-boot-nand";
+                        read-only;
+                };
+
+                partition@2000000 {
+                        reg = <0x02000000 0x10000000>;
+                        label = "fs-nand";
+                };
+
+                partition@12000000 {
+                        reg = <0x12000000 0x08000000>;
+                        label = "ramdisk-nand";
+                };
+
+                partition@1a000000 {
+                        reg = <0x1a000000 0x04000000>;
+                        label = "kernel-nand";
+                };
+
+                partition@1e000000 {
+                        reg = <0x1e000000 0x01000000>;
+                        label = "dtb-nand";
+                };
+
+                partition@1f000000 {
+                        reg = <0x1f000000 0x21000000>;
+                        label = "empty-nand";
+                };
+        };
+
+        board-control@3,0 {
+                compatible = "fsl,mpc8536ds-fpga-pixis";
+                reg = <0x3 0x0 0x8000>;
+        };
+};
+
 &board_soc {
         i2c@3100 {
                 rtc@68 {
diff --git a/arch/powerpc/boot/dts/mpc8536ds_36b.dts b/arch/powerpc/boot/dts/mpc8536ds_36b.dts
index 8f4b929b1d1d..f8a3b3413176 100644
--- a/arch/powerpc/boot/dts/mpc8536ds_36b.dts
+++ b/arch/powerpc/boot/dts/mpc8536ds_36b.dts
@@ -1,7 +1,7 @@
 /*
  * MPC8536DS Device Tree Source (36-bit address map)
  *
- * Copyright 2008-2009 Freescale Semiconductor, Inc.
+ * Copyright 2008-2009, 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
@@ -33,7 +33,11 @@
         };
 
         lbc: localbus@ffe05000 {
-                reg = <0 0xffe05000 0 0x1000>;
+                reg = <0xf 0xffe05000 0 0x1000>;
+
+                ranges = <0x0 0x0 0xf 0xe8000000 0x08000000
+                          0x2 0x0 0xf 0xffa00000 0x00040000
+                          0x3 0x0 0xf 0xffdf0000 0x00008000>;
         };
 
         board_soc: soc: soc@fffe00000 {
diff --git a/arch/powerpc/boot/dts/mpc8548cds.dts b/arch/powerpc/boot/dts/mpc8548cds.dts
deleted file mode 100644
index 07b8dae0f46e..000000000000
--- a/arch/powerpc/boot/dts/mpc8548cds.dts
+++ /dev/null
@@ -1,306 +0,0 @@
-/*
- * MPC8548 CDS Device Tree Source
- *
- * Copyright 2006, 2008 Freescale Semiconductor Inc.
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- */
-
-/include/ "fsl/mpc8548si-pre.dtsi"
-
-/ {
-        model = "MPC8548CDS";
-        compatible = "MPC8548CDS", "MPC85xxCDS";
-
-        aliases {
-                ethernet0 = &enet0;
-                ethernet1 = &enet1;
-                ethernet2 = &enet2;
-                ethernet3 = &enet3;
-                serial0 = &serial0;
-                serial1 = &serial1;
-                pci0 = &pci0;
-                pci1 = &pci1;
-                pci2 = &pci2;
-        };
-
-        memory {
-                device_type = "memory";
-                reg = <0 0 0x0 0x8000000>;      // 128M at 0x0
-        };
-
-        lbc: localbus@e0005000 {
-                reg = <0 0xe0005000 0 0x1000>;
-        };
-
-        soc: soc8548@e0000000 {
-                ranges = <0 0x0 0xe0000000 0x100000>;
-
-                i2c@3000 {
-                        eeprom@50 {
-                                compatible = "atmel,24c64";
-                                reg = <0x50>;
-                        };
-
-                        eeprom@56 {
-                                compatible = "atmel,24c64";
-                                reg = <0x56>;
-                        };
-
-                        eeprom@57 {
-                                compatible = "atmel,24c64";
-                                reg = <0x57>;
-                        };
-                };
-
-                i2c@3100 {
-                        eeprom@50 {
-                                compatible = "atmel,24c64";
-                                reg = <0x50>;
-                        };
-                };
-
-                enet0: ethernet@24000 {
-                        tbi-handle = <&tbi0>;
-                        phy-handle = <&phy0>;
-                };
-
-                mdio@24520 {
-                        phy0: ethernet-phy@0 {
-                                interrupts = <5 1 0 0>;
-                                reg = <0x0>;
-                                device_type = "ethernet-phy";
-                        };
-                        phy1: ethernet-phy@1 {
-                                interrupts = <5 1 0 0>;
-                                reg = <0x1>;
-                                device_type = "ethernet-phy";
-                        };
-                        phy2: ethernet-phy@2 {
-                                interrupts = <5 1 0 0>;
-                                reg = <0x2>;
-                                device_type = "ethernet-phy";
-                        };
-                        phy3: ethernet-phy@3 {
-                                interrupts = <5 1 0 0>;
-                                reg = <0x3>;
-                                device_type = "ethernet-phy";
-                        };
-                        tbi0: tbi-phy@11 {
-                                reg = <0x11>;
-                                device_type = "tbi-phy";
-                        };
-                };
-
-                enet1: ethernet@25000 {
-                        tbi-handle = <&tbi1>;
-                        phy-handle = <&phy1>;
-                };
-
-                mdio@25520 {
-                        tbi1: tbi-phy@11 {
-                                reg = <0x11>;
-                                device_type = "tbi-phy";
-                        };
-                };
-
-                enet2: ethernet@26000 {
-                        tbi-handle = <&tbi2>;
-                        phy-handle = <&phy2>;
-                };
-
-                mdio@26520 {
-                        tbi2: tbi-phy@11 {
-                                reg = <0x11>;
-                                device_type = "tbi-phy";
-                        };
-                };
-
-                enet3: ethernet@27000 {
-                        tbi-handle = <&tbi3>;
-                        phy-handle = <&phy3>;
-                };
-
-                mdio@27520 {
-                        tbi3: tbi-phy@11 {
-                                reg = <0x11>;
-                                device_type = "tbi-phy";
-                        };
-                };
-        };
-
-        pci0: pci@e0008000 {
-                reg = <0 0xe0008000 0 0x1000>;
-                ranges = <0x2000000 0x0 0x80000000 0 0x80000000 0x0 0x10000000
-                          0x1000000 0x0 0x00000000 0 0xe2000000 0x0 0x800000>;
-                clock-frequency = <66666666>;
-                interrupt-map-mask = <0xf800 0x0 0x0 0x7>;
-                interrupt-map = <
-                        /* IDSEL 0x4 (PCIX Slot 2) */
-                        0x2000 0x0 0x0 0x1 &mpic 0x0 0x1 0 0
-                        0x2000 0x0 0x0 0x2 &mpic 0x1 0x1 0 0
-                        0x2000 0x0 0x0 0x3 &mpic 0x2 0x1 0 0
-                        0x2000 0x0 0x0 0x4 &mpic 0x3 0x1 0 0
-
-                        /* IDSEL 0x5 (PCIX Slot 3) */
-                        0x2800 0x0 0x0 0x1 &mpic 0x1 0x1 0 0
-                        0x2800 0x0 0x0 0x2 &mpic 0x2 0x1 0 0
-                        0x2800 0x0 0x0 0x3 &mpic 0x3 0x1 0 0
-                        0x2800 0x0 0x0 0x4 &mpic 0x0 0x1 0 0
-
-                        /* IDSEL 0x6 (PCIX Slot 4) */
-                        0x3000 0x0 0x0 0x1 &mpic 0x2 0x1 0 0
-                        0x3000 0x0 0x0 0x2 &mpic 0x3 0x1 0 0
-                        0x3000 0x0 0x0 0x3 &mpic 0x0 0x1 0 0
-                        0x3000 0x0 0x0 0x4 &mpic 0x1 0x1 0 0
-
-                        /* IDSEL 0x8 (PCIX Slot 5) */
-                        0x4000 0x0 0x0 0x1 &mpic 0x0 0x1 0 0
-                        0x4000 0x0 0x0 0x2 &mpic 0x1 0x1 0 0
-                        0x4000 0x0 0x0 0x3 &mpic 0x2 0x1 0 0
-                        0x4000 0x0 0x0 0x4 &mpic 0x3 0x1 0 0
-
-                        /* IDSEL 0xC (Tsi310 bridge) */
-                        0x6000 0x0 0x0 0x1 &mpic 0x0 0x1 0 0
-                        0x6000 0x0 0x0 0x2 &mpic 0x1 0x1 0 0
-                        0x6000 0x0 0x0 0x3 &mpic 0x2 0x1 0 0
-                        0x6000 0x0 0x0 0x4 &mpic 0x3 0x1 0 0
-
-                        /* IDSEL 0x14 (Slot 2) */
-                        0xa000 0x0 0x0 0x1 &mpic 0x0 0x1 0 0
-                        0xa000 0x0 0x0 0x2 &mpic 0x1 0x1 0 0
-                        0xa000 0x0 0x0 0x3 &mpic 0x2 0x1 0 0
-                        0xa000 0x0 0x0 0x4 &mpic 0x3 0x1 0 0
-
-                        /* IDSEL 0x15 (Slot 3) */
-                        0xa800 0x0 0x0 0x1 &mpic 0x1 0x1 0 0
-                        0xa800 0x0 0x0 0x2 &mpic 0x2 0x1 0 0
-                        0xa800 0x0 0x0 0x3 &mpic 0x3 0x1 0 0
-                        0xa800 0x0 0x0 0x4 &mpic 0x0 0x1 0 0
-
-                        /* IDSEL 0x16 (Slot 4) */
-                        0xb000 0x0 0x0 0x1 &mpic 0x2 0x1 0 0
-                        0xb000 0x0 0x0 0x2 &mpic 0x3 0x1 0 0
-                        0xb000 0x0 0x0 0x3 &mpic 0x0 0x1 0 0
-                        0xb000 0x0 0x0 0x4 &mpic 0x1 0x1 0 0
-
-                        /* IDSEL 0x18 (Slot 5) */
-                        0xc000 0x0 0x0 0x1 &mpic 0x0 0x1 0 0
-                        0xc000 0x0 0x0 0x2 &mpic 0x1 0x1 0 0
-                        0xc000 0x0 0x0 0x3 &mpic 0x2 0x1 0 0
-                        0xc000 0x0 0x0 0x4 &mpic 0x3 0x1 0 0
-
-                        /* IDSEL 0x1C (Tsi310 bridge PCI primary) */
-                        0xe000 0x0 0x0 0x1 &mpic 0x0 0x1 0 0
-                        0xe000 0x0 0x0 0x2 &mpic 0x1 0x1 0 0
-                        0xe000 0x0 0x0 0x3 &mpic 0x2 0x1 0 0
-                        0xe000 0x0 0x0 0x4 &mpic 0x3 0x1 0 0>;
-
-                pci_bridge@1c {
-                        interrupt-map-mask = <0xf800 0x0 0x0 0x7>;
-                        interrupt-map = <
-
-                                /* IDSEL 0x00 (PrPMC Site) */
-                                0000 0x0 0x0 0x1 &mpic 0x0 0x1 0 0
-                                0000 0x0 0x0 0x2 &mpic 0x1 0x1 0 0
-                                0000 0x0 0x0 0x3 &mpic 0x2 0x1 0 0
-                                0000 0x0 0x0 0x4 &mpic 0x3 0x1 0 0
-
-                                /* IDSEL 0x04 (VIA chip) */
-                                0x2000 0x0 0x0 0x1 &mpic 0x0 0x1 0 0
-                                0x2000 0x0 0x0 0x2 &mpic 0x1 0x1 0 0
-                                0x2000 0x0 0x0 0x3 &mpic 0x2 0x1 0 0
-                                0x2000 0x0 0x0 0x4 &mpic 0x3 0x1 0 0
-
-                                /* IDSEL 0x05 (8139) */
-                                0x2800 0x0 0x0 0x1 &mpic 0x1 0x1 0 0
-
-                                /* IDSEL 0x06 (Slot 6) */
-                                0x3000 0x0 0x0 0x1 &mpic 0x2 0x1 0 0
-                                0x3000 0x0 0x0 0x2 &mpic 0x3 0x1 0 0
-                                0x3000 0x0 0x0 0x3 &mpic 0x0 0x1 0 0
-                                0x3000 0x0 0x0 0x4 &mpic 0x1 0x1 0 0
-
-                                /* IDESL 0x07 (Slot 7) */
-                                0x3800 0x0 0x0 0x1 &mpic 0x3 0x1 0 0
-                                0x3800 0x0 0x0 0x2 &mpic 0x0 0x1 0 0
-                                0x3800 0x0 0x0 0x3 &mpic 0x1 0x1 0 0
-                                0x3800 0x0 0x0 0x4 &mpic 0x2 0x1 0 0>;
-
-                        reg = <0xe000 0x0 0x0 0x0 0x0>;
-                        #interrupt-cells = <1>;
-                        #size-cells = <2>;
-                        #address-cells = <3>;
-                        ranges = <0x2000000 0x0 0x80000000
-                                  0x2000000 0x0 0x80000000
-                                  0x0 0x20000000
-                                  0x1000000 0x0 0x0
-                                  0x1000000 0x0 0x0
-                                  0x0 0x80000>;
-                        clock-frequency = <33333333>;
-
-                        isa@4 {
-                                device_type = "isa";
-                                #interrupt-cells = <2>;
-                                #size-cells = <1>;
-                                #address-cells = <2>;
-                                reg = <0x2000 0x0 0x0 0x0 0x0>;
-                                ranges = <0x1 0x0 0x1000000 0x0 0x0 0x1000>;
-                                interrupt-parent = <&i8259>;
-
-                                i8259: interrupt-controller@20 {
-                                        interrupt-controller;
-                                        device_type = "interrupt-controller";
-                                        reg = <0x1 0x20 0x2
-                                               0x1 0xa0 0x2
-                                               0x1 0x4d0 0x2>;
-                                        #address-cells = <0>;
-                                        #interrupt-cells = <2>;
-                                        compatible = "chrp,iic";
-                                        interrupts = <0 1 0 0>;
-                                        interrupt-parent = <&mpic>;
-                                };
-
-                                rtc@70 {
-                                        compatible = "pnpPNP,b00";
-                                        reg = <0x1 0x70 0x2>;
-                                };
-                        };
-                };
-        };
-
-        pci1: pci@e0009000 {
-                reg = <0 0xe0009000 0 0x1000>;
-                ranges = <0x2000000 0x0 0x90000000 0 0x90000000 0x0 0x10000000
-                          0x1000000 0x0 0x00000000 0 0xe2800000 0x0 0x800000>;
-                clock-frequency = <66666666>;
-                interrupt-map-mask = <0xf800 0x0 0x0 0x7>;
-                interrupt-map = <
-
-                        /* IDSEL 0x15 */
-                        0xa800 0x0 0x0 0x1 &mpic 0xb 0x1 0 0
-                        0xa800 0x0 0x0 0x2 &mpic 0x1 0x1 0 0
-                        0xa800 0x0 0x0 0x3 &mpic 0x2 0x1 0 0
-                        0xa800 0x0 0x0 0x4 &mpic 0x3 0x1 0 0>;
-        };
-
-        pci2: pcie@e000a000 {
-                reg = <0 0xe000a000 0 0x1000>;
-                ranges = <0x2000000 0x0 0xa0000000 0 0xa0000000 0x0 0x20000000
-                          0x1000000 0x0 0x00000000 0 0xe3000000 0x0 0x100000>;
-                pcie@0 {
-                        ranges = <0x2000000 0x0 0xa0000000
-                                  0x2000000 0x0 0xa0000000
-                                  0x0 0x20000000
-
-                                  0x1000000 0x0 0x0
-                                  0x1000000 0x0 0x0
-                                  0x0 0x100000>;
-                };
-        };
-};
-
-/include/ "fsl/mpc8548si-post.dtsi"
diff --git a/arch/powerpc/boot/dts/mpc8548cds.dtsi b/arch/powerpc/boot/dts/mpc8548cds.dtsi
new file mode 100644
index 000000000000..c61f525e4740
--- /dev/null
+++ b/arch/powerpc/boot/dts/mpc8548cds.dtsi
@@ -0,0 +1,306 @@
+/*
+ * MPC8548CDS Device Tree Source stub (no addresses or top-level ranges)
+ *
+ * Copyright 2012 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in the
+ *       documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Freescale Semiconductor nor the
+ *       names of its contributors may be used to endorse or promote products
+ *       derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+&board_lbc {
+        nor@0,0 {
+                #address-cells = <1>;
+                #size-cells = <1>;
+                compatible = "cfi-flash";
+                reg = <0x0 0x0 0x01000000>;
+                bank-width = <2>;
+                device-width = <2>;
+
+                partition@0 {
+                        reg = <0x0 0x0b00000>;
+                        label = "ramdisk-nor";
+                };
+
+                partition@300000 {
+                        reg = <0x0b00000 0x0400000>;
+                        label = "kernel-nor";
+                };
+
+                partition@700000 {
+                        reg = <0x0f00000 0x060000>;
+                        label = "dtb-nor";
+                };
+
+                partition@760000 {
+                        reg = <0x0f60000 0x020000>;
+                        label = "env-nor";
+                        read-only;
+                };
+
+                partition@780000 {
+                        reg = <0x0f80000 0x080000>;
+                        label = "u-boot-nor";
+                        read-only;
+                };
+        };
+
+        board-control@1,0 {
+                compatible = "fsl,mpc8548cds-fpga";
+                reg = <0x1 0x0 0x1000>;
+        };
+};
+
+&board_soc {
+        i2c@3000 {
+                eeprom@50 {
+                        compatible = "atmel,24c64";
+                        reg = <0x50>;
+                };
+
+                eeprom@56 {
+                        compatible = "atmel,24c64";
+                        reg = <0x56>;
+                };
+
+                eeprom@57 {
+                        compatible = "atmel,24c64";
+                        reg = <0x57>;
+                };
+        };
+
+        i2c@3100 {
+                eeprom@50 {
+                        compatible = "atmel,24c64";
+                        reg = <0x50>;
+                };
+        };
+
+        enet0: ethernet@24000 {
+                tbi-handle = <&tbi0>;
+                phy-handle = <&phy0>;
+        };
+
+        mdio@24520 {
+                phy0: ethernet-phy@0 {
+                        interrupts = <5 1 0 0>;
+                        reg = <0x0>;
+                        device_type = "ethernet-phy";
+                };
+                phy1: ethernet-phy@1 {
+                        interrupts = <5 1 0 0>;
+                        reg = <0x1>;
+                        device_type = "ethernet-phy";
+                };
+                phy2: ethernet-phy@2 {
+                        interrupts = <5 1 0 0>;
+                        reg = <0x2>;
+                        device_type = "ethernet-phy";
+                };
+                phy3: ethernet-phy@3 {
+                        interrupts = <5 1 0 0>;
+                        reg = <0x3>;
+                        device_type = "ethernet-phy";
+                };
+                tbi0: tbi-phy@11 {
+                        reg = <0x11>;
+                        device_type = "tbi-phy";
+                };
+        };
+
+        enet1: ethernet@25000 {
+                tbi-handle = <&tbi1>;
+                phy-handle = <&phy1>;
+        };
+
+        mdio@25520 {
+                tbi1: tbi-phy@11 {
+                        reg = <0x11>;
+                        device_type = "tbi-phy";
+                };
+        };
+
+        enet2: ethernet@26000 {
+                tbi-handle = <&tbi2>;
+                phy-handle = <&phy2>;
+        };
+
+        mdio@26520 {
+                tbi2: tbi-phy@11 {
+                        reg = <0x11>;
+                        device_type = "tbi-phy";
+                };
+        };
+
+        enet3: ethernet@27000 {
+                tbi-handle = <&tbi3>;
+                phy-handle = <&phy3>;
+        };
+
+        mdio@27520 {
+                tbi3: tbi-phy@11 {
+                        reg = <0x11>;
+                        device_type = "tbi-phy";
+                };
+        };
+};
+
+&board_pci0 {
+        interrupt-map-mask = <0xf800 0x0 0x0 0x7>;
+        interrupt-map = <
+                /* IDSEL 0x4 (PCIX Slot 2) */
+                0x2000 0x0 0x0 0x1 &mpic 0x0 0x1 0 0
+                0x2000 0x0 0x0 0x2 &mpic 0x1 0x1 0 0
+                0x2000 0x0 0x0 0x3 &mpic 0x2 0x1 0 0
+                0x2000 0x0 0x0 0x4 &mpic 0x3 0x1 0 0
+
+                /* IDSEL 0x5 (PCIX Slot 3) */
+                0x2800 0x0 0x0 0x1 &mpic 0x1 0x1 0 0
+                0x2800 0x0 0x0 0x2 &mpic 0x2 0x1 0 0
+                0x2800 0x0 0x0 0x3 &mpic 0x3 0x1 0 0
+                0x2800 0x0 0x0 0x4 &mpic 0x0 0x1 0 0
+
+                /* IDSEL 0x6 (PCIX Slot 4) */
+                0x3000 0x0 0x0 0x1 &mpic 0x2 0x1 0 0
+                0x3000 0x0 0x0 0x2 &mpic 0x3 0x1 0 0
+                0x3000 0x0 0x0 0x3 &mpic 0x0 0x1 0 0
+                0x3000 0x0 0x0 0x4 &mpic 0x1 0x1 0 0
+
+                /* IDSEL 0x8 (PCIX Slot 5) */
+                0x4000 0x0 0x0 0x1 &mpic 0x0 0x1 0 0
+                0x4000 0x0 0x0 0x2 &mpic 0x1 0x1 0 0
+                0x4000 0x0 0x0 0x3 &mpic 0x2 0x1 0 0
+                0x4000 0x0 0x0 0x4 &mpic 0x3 0x1 0 0
+
+                /* IDSEL 0xC (Tsi310 bridge) */
+                0x6000 0x0 0x0 0x1 &mpic 0x0 0x1 0 0
+                0x6000 0x0 0x0 0x2 &mpic 0x1 0x1 0 0
+                0x6000 0x0 0x0 0x3 &mpic 0x2 0x1 0 0
+                0x6000 0x0 0x0 0x4 &mpic 0x3 0x1 0 0
+
+                /* IDSEL 0x14 (Slot 2) */
+                0xa000 0x0 0x0 0x1 &mpic 0x0 0x1 0 0
+                0xa000 0x0 0x0 0x2 &mpic 0x1 0x1 0 0
+                0xa000 0x0 0x0 0x3 &mpic 0x2 0x1 0 0
+                0xa000 0x0 0x0 0x4 &mpic 0x3 0x1 0 0
+
+                /* IDSEL 0x15 (Slot 3) */
+                0xa800 0x0 0x0 0x1 &mpic 0x1 0x1 0 0
+                0xa800 0x0 0x0 0x2 &mpic 0x2 0x1 0 0
+                0xa800 0x0 0x0 0x3 &mpic 0x3 0x1 0 0
+                0xa800 0x0 0x0 0x4 &mpic 0x0 0x1 0 0
+
+                /* IDSEL 0x16 (Slot 4) */
+                0xb000 0x0 0x0 0x1 &mpic 0x2 0x1 0 0
+                0xb000 0x0 0x0 0x2 &mpic 0x3 0x1 0 0
+                0xb000 0x0 0x0 0x3 &mpic 0x0 0x1 0 0
+                0xb000 0x0 0x0 0x4 &mpic 0x1 0x1 0 0
+
+                /* IDSEL 0x18 (Slot 5) */
+                0xc000 0x0 0x0 0x1 &mpic 0x0 0x1 0 0
+                0xc000 0x0 0x0 0x2 &mpic 0x1 0x1 0 0
+                0xc000 0x0 0x0 0x3 &mpic 0x2 0x1 0 0
+                0xc000 0x0 0x0 0x4 &mpic 0x3 0x1 0 0
+
+                /* IDSEL 0x1C (Tsi310 bridge PCI primary) */
+                0xe000 0x0 0x0 0x1 &mpic 0x0 0x1 0 0
+                0xe000 0x0 0x0 0x2 &mpic 0x1 0x1 0 0
+                0xe000 0x0 0x0 0x3 &mpic 0x2 0x1 0 0
+                0xe000 0x0 0x0 0x4 &mpic 0x3 0x1 0 0>;
+
+        pci_bridge@1c {
+                interrupt-map-mask = <0xf800 0x0 0x0 0x7>;
+                interrupt-map = <
+
+                        /* IDSEL 0x00 (PrPMC Site) */
+                        0000 0x0 0x0 0x1 &mpic 0x0 0x1 0 0
+                        0000 0x0 0x0 0x2 &mpic 0x1 0x1 0 0
+                        0000 0x0 0x0 0x3 &mpic 0x2 0x1 0 0
+                        0000 0x0 0x0 0x4 &mpic 0x3 0x1 0 0
+
+                        /* IDSEL 0x04 (VIA chip) */
+                        0x2000 0x0 0x0 0x1 &mpic 0x0 0x1 0 0
+                        0x2000 0x0 0x0 0x2 &mpic 0x1 0x1 0 0
+                        0x2000 0x0 0x0 0x3 &mpic 0x2 0x1 0 0
+                        0x2000 0x0 0x0 0x4 &mpic 0x3 0x1 0 0
+
+                        /* IDSEL 0x05 (8139) */
+                        0x2800 0x0 0x0 0x1 &mpic 0x1 0x1 0 0
+
+                        /* IDSEL 0x06 (Slot 6) */
+                        0x3000 0x0 0x0 0x1 &mpic 0x2 0x1 0 0
+                        0x3000 0x0 0x0 0x2 &mpic 0x3 0x1 0 0
+                        0x3000 0x0 0x0 0x3 &mpic 0x0 0x1 0 0
+                        0x3000 0x0 0x0 0x4 &mpic 0x1 0x1 0 0
+
+                        /* IDESL 0x07 (Slot 7) */
+                        0x3800 0x0 0x0 0x1 &mpic 0x3 0x1 0 0
+                        0x3800 0x0 0x0 0x2 &mpic 0x0 0x1 0 0
+                        0x3800 0x0 0x0 0x3 &mpic 0x1 0x1 0 0
+                        0x3800 0x0 0x0 0x4 &mpic 0x2 0x1 0 0>;
+
+                reg = <0xe000 0x0 0x0 0x0 0x0>;
+                #interrupt-cells = <1>;
+                #size-cells = <2>;
+                #address-cells = <3>;
+                ranges = <0x2000000 0x0 0x80000000
+                          0x2000000 0x0 0x80000000
+                          0x0 0x20000000
+                          0x1000000 0x0 0x0
+                          0x1000000 0x0 0x0
+                          0x0 0x80000>;
+                clock-frequency = <33333333>;
+
+                isa@4 {
+                        device_type = "isa";
+                        #interrupt-cells = <2>;
+                        #size-cells = <1>;
+                        #address-cells = <2>;
+                        reg = <0x2000 0x0 0x0 0x0 0x0>;
+                        ranges = <0x1 0x0 0x1000000 0x0 0x0 0x1000>;
+                        interrupt-parent = <&i8259>;
+
+                        i8259: interrupt-controller@20 {
+                                interrupt-controller;
+                                device_type = "interrupt-controller";
+                                reg = <0x1 0x20 0x2
+                                       0x1 0xa0 0x2
+                                       0x1 0x4d0 0x2>;
+                                #address-cells = <0>;
+                                #interrupt-cells = <2>;
+                                compatible = "chrp,iic";
+                                interrupts = <0 1 0 0>;
+                                interrupt-parent = <&mpic>;
+                        };
+
+                        rtc@70 {
+                                compatible = "pnpPNP,b00";
+                                reg = <0x1 0x70 0x2>;
+                        };
+                };
+        };
+};
diff --git a/arch/powerpc/boot/dts/mpc8548cds_32b.dts b/arch/powerpc/boot/dts/mpc8548cds_32b.dts
new file mode 100644
index 000000000000..6fd63163fc6b
--- /dev/null
+++ b/arch/powerpc/boot/dts/mpc8548cds_32b.dts
@@ -0,0 +1,86 @@
+/*
+ * MPC8548 CDS Device Tree Source (32-bit address map)
+ *
+ * Copyright 2006, 2008, 2011-2012 Freescale Semiconductor Inc.
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ */
+
+/include/ "fsl/mpc8548si-pre.dtsi"
+
+/ {
+        model = "MPC8548CDS";
+        compatible = "MPC8548CDS", "MPC85xxCDS";
+
+        memory {
+                device_type = "memory";
+                reg = <0 0 0x0 0x8000000>;      // 128M at 0x0
+        };
+
+        board_lbc: lbc: localbus@e0005000 {
+                reg = <0 0xe0005000 0 0x1000>;
+
+                ranges = <0x0 0x0 0x0 0xff000000 0x01000000
+                          0x1 0x0 0x0 0xf8004000 0x00001000>;
+
+        };
+
+        board_soc: soc: soc8548@e0000000 {
+                ranges = <0 0x0 0xe0000000 0x100000>;
+        };
+
+        board_pci0: pci0: pci@e0008000 {
+                reg = <0 0xe0008000 0 0x1000>;
+                ranges = <0x2000000 0x0 0x80000000 0 0x80000000 0x0 0x10000000
+                          0x1000000 0x0 0x00000000 0 0xe2000000 0x0 0x800000>;
+                clock-frequency = <66666666>;
+        };
+
+        pci1: pci@e0009000 {
+                reg = <0 0xe0009000 0 0x1000>;
+                ranges = <0x2000000 0x0 0x90000000 0 0x90000000 0x0 0x10000000
+                          0x1000000 0x0 0x00000000 0 0xe2800000 0x0 0x800000>;
+                clock-frequency = <66666666>;
+                interrupt-map-mask = <0xf800 0x0 0x0 0x7>;
+                interrupt-map = <
+
+                        /* IDSEL 0x15 */
+                        0xa800 0x0 0x0 0x1 &mpic 0xb 0x1 0 0
+                        0xa800 0x0 0x0 0x2 &mpic 0x1 0x1 0 0
+                        0xa800 0x0 0x0 0x3 &mpic 0x2 0x1 0 0
+                        0xa800 0x0 0x0 0x4 &mpic 0x3 0x1 0 0>;
+        };
+
+        pci2: pcie@e000a000 {
+                reg = <0 0xe000a000 0 0x1000>;
+                ranges = <0x2000000 0x0 0xa0000000 0 0xa0000000 0x0 0x20000000
+                          0x1000000 0x0 0x00000000 0 0xe3000000 0x0 0x100000>;
+                pcie@0 {
+                        ranges = <0x2000000 0x0 0xa0000000
+                                  0x2000000 0x0 0xa0000000
+                                  0x0 0x20000000
+
+                                  0x1000000 0x0 0x0
+                                  0x1000000 0x0 0x0
+                                  0x0 0x100000>;
+                };
+        };
+
+        rio: rapidio@e00c0000 {
+                reg = <0x0 0xe00c0000 0x0 0x20000>;
+                port1 {
+                        ranges = <0x0 0x0 0x0 0xc0000000 0x0 0x20000000>;
+                };
+        };
+};
+
+/*
+ * mpc8548cds.dtsi must be last to ensure board_pci0 overrides pci0 settings
+ * for interrupt-map & interrupt-map-mask.
+ */
+
+/include/ "fsl/mpc8548si-post.dtsi"
+/include/ "mpc8548cds.dtsi"
diff --git a/arch/powerpc/boot/dts/mpc8548cds_36b.dts b/arch/powerpc/boot/dts/mpc8548cds_36b.dts
new file mode 100644
index 000000000000..10e551b11bd6
--- /dev/null
+++ b/arch/powerpc/boot/dts/mpc8548cds_36b.dts
@@ -0,0 +1,86 @@
+/*
+ * MPC8548 CDS Device Tree Source (36-bit address map)
+ *
+ * Copyright 2012 Freescale Semiconductor Inc.
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ */
+
+/include/ "fsl/mpc8548si-pre.dtsi"
+
+/ {
+        model = "MPC8548CDS";
+        compatible = "MPC8548CDS", "MPC85xxCDS";
+
+        memory {
+                device_type = "memory";
+                reg = <0 0 0x0 0x8000000>;      // 128M at 0x0
+        };
+
+        board_lbc: lbc: localbus@fe0005000 {
+                reg = <0xf 0xe0005000 0 0x1000>;
+
+                ranges = <0x0 0x0 0xf 0xff000000 0x01000000
+                          0x1 0x0 0xf 0xf8004000 0x00001000>;
+
+        };
+
+        board_soc: soc: soc8548@fe0000000 {
+                ranges = <0 0xf 0xe0000000 0x100000>;
+        };
+
+        board_pci0: pci0: pci@fe0008000 {
+                reg = <0xf 0xe0008000 0 0x1000>;
+                ranges = <0x2000000 0x0 0xe0000000 0xc 0x00000000 0x0 0x10000000
+                          0x1000000 0x0 0x00000000 0xf 0xe2000000 0x0 0x800000>;
+                clock-frequency = <66666666>;
+        };
+
+        pci1: pci@fe0009000 {
+                reg = <0xf 0xe0009000 0 0x1000>;
+                ranges = <0x2000000 0x0 0xe0000000 0xc 0x10000000 0x0 0x10000000
+                          0x1000000 0x0 0x00000000 0xf 0xe2800000 0x0 0x800000>;
+                clock-frequency = <66666666>;
+                interrupt-map-mask = <0xf800 0x0 0x0 0x7>;
+                interrupt-map = <
+
+                        /* IDSEL 0x15 */
+                        0xa800 0x0 0x0 0x1 &mpic 0xb 0x1 0 0
+                        0xa800 0x0 0x0 0x2 &mpic 0x1 0x1 0 0
+                        0xa800 0x0 0x0 0x3 &mpic 0x2 0x1 0 0
+                        0xa800 0x0 0x0 0x4 &mpic 0x3 0x1 0 0>;
+        };
+
+        pci2: pcie@fe000a000 {
+                reg = <0xf 0xe000a000 0 0x1000>;
+                ranges = <0x2000000 0x0 0xe0000000 0xc 0x20000000 0x0 0x20000000
+                          0x1000000 0x0 0x00000000 0xf 0xe3000000 0x0 0x100000>;
+                pcie@0 {
+                        ranges = <0x2000000 0x0 0xa0000000
+                                  0x2000000 0x0 0xa0000000
+                                  0x0 0x20000000
+
+                                  0x1000000 0x0 0x0
+                                  0x1000000 0x0 0x0
+                                  0x0 0x100000>;
+                };
+        };
+
+        rio: rapidio@fe00c0000 {
+                reg = <0xf 0xe00c0000 0x0 0x20000>;
+                port1 {
+                        ranges = <0x0 0x0 0xc 0x40000000 0x0 0x20000000>;
+                };
+        };
+};
+
+/*
+ * mpc8548cds.dtsi must be last to ensure board_pci0 overrides pci0 settings
+ * for interrupt-map & interrupt-map-mask.
+ */
+
+/include/ "fsl/mpc8548si-post.dtsi"
+/include/ "mpc8548cds.dtsi"
diff --git a/arch/powerpc/boot/dts/mpc8572ds.dtsi b/arch/powerpc/boot/dts/mpc8572ds.dtsi
index c3d4fac0532a..14178944e220 100644
--- a/arch/powerpc/boot/dts/mpc8572ds.dtsi
+++ b/arch/powerpc/boot/dts/mpc8572ds.dtsi
@@ -41,37 +41,47 @@
                 bank-width = <2>;
                 device-width = <1>;
 
-                ramdisk@0 {
+                partition@0 {
                         reg = <0x0 0x03000000>;
-                        read-only;
+                        label = "ramdisk-nor";
                 };
 
-                diagnostic@3000000 {
+                partition@3000000 {
                         reg = <0x03000000 0x00e00000>;
+                        label = "diagnostic-nor";
                         read-only;
                 };
 
-                dink@3e00000 {
+                partition@3e00000 {
                         reg = <0x03e00000 0x00200000>;
+                        label = "dink-nor";
                         read-only;
                 };
 
-                kernel@4000000 {
+                partition@4000000 {
                         reg = <0x04000000 0x00400000>;
-                        read-only;
+                        label = "kernel-nor";
                 };
 
-                jffs2@4400000 {
+                partition@4400000 {
                         reg = <0x04400000 0x03b00000>;
+                        label = "fs-nor";
+                };
+
+                partition@7f00000 {
+                        reg = <0x07f00000 0x00060000>;
+                        label = "dtb-nor";
                 };
 
-                dtb@7f00000 {
-                        reg = <0x07f00000 0x00080000>;
+                partition@7f60000 {
+                        reg = <0x07f60000 0x00020000>;
+                        label = "env-nor";
                         read-only;
                 };
 
-                u-boot@7f80000 {
+                partition@7f80000 {
                         reg = <0x07f80000 0x00080000>;
+                        label = "u-boot-nor";
                         read-only;
                 };
         };
@@ -83,31 +93,35 @@
                              "fsl,elbc-fcm-nand";
                 reg = <0x2 0x0 0x40000>;
 
-                u-boot@0 {
+                partition@0 {
                         reg = <0x0 0x02000000>;
+                        label = "u-boot-nand";
                         read-only;
                 };
 
-                jffs2@2000000 {
+                partition@2000000 {
                         reg = <0x02000000 0x10000000>;
+                        label = "fs-nand";
                 };
 
-                ramdisk@12000000 {
+                partition@12000000 {
                         reg = <0x12000000 0x08000000>;
-                        read-only;
+                        label = "ramdisk-nand";
                 };
 
-                kernel@1a000000 {
+                partition@1a000000 {
                         reg = <0x1a000000 0x04000000>;
+                        label = "kernel-nand";
                 };
 
-                dtb@1e000000 {
+                partition@1e000000 {
                         reg = <0x1e000000 0x01000000>;
-                        read-only;
+                        label = "dtb-nand";
                 };
 
-                empty@1f000000 {
+                partition@1f000000 {
                         reg = <0x1f000000 0x21000000>;
+                        label = "empty-nand";
                 };
         };
 
diff --git a/arch/powerpc/boot/dts/p1010rdb.dtsi b/arch/powerpc/boot/dts/p1010rdb.dtsi
index d4c4a7730285..49776143a1b8 100644
--- a/arch/powerpc/boot/dts/p1010rdb.dtsi
+++ b/arch/powerpc/boot/dts/p1010rdb.dtsi
@@ -138,7 +138,7 @@
                         #size-cells = <1>;
                         compatible = "spansion,s25sl12801";
                         reg = <0>;
-                        spi-max-frequency = <50000000>;
+                        spi-max-frequency = <40000000>;
 
                         partition@0 {
                                 /* 1MB for u-boot Bootloader Image */
@@ -196,7 +196,7 @@
                 };
 
                 tbi-phy@3 {
-                        device-type = "tbi-phy";
+                        device_type = "tbi-phy";
                         reg = <0x3>;
                 };
         };
diff --git a/arch/powerpc/boot/dts/p1020rdb-pc.dtsi b/arch/powerpc/boot/dts/p1020rdb-pc.dtsi
new file mode 100644
index 000000000000..c952cd37cf6d
--- /dev/null
+++ b/arch/powerpc/boot/dts/p1020rdb-pc.dtsi
@@ -0,0 +1,247 @@
+/*
+ * P1020 RDB-PC Device Tree Source stub (no addresses or top-level ranges)
+ *
+ * Copyright 2012 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in the
+ *       documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Freescale Semiconductor nor the
+ *       names of its contributors may be used to endorse or promote products
+ *       derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+&lbc {
+        nor@0,0 {
+                #address-cells = <1>;
+                #size-cells = <1>;
+                compatible = "cfi-flash";
+                reg = <0x0 0x0 0x1000000>;
+                bank-width = <2>;
+                device-width = <1>;
+
+                partition@0 {
+                        /* This location must not be altered  */
+                        /* 256KB for Vitesse 7385 Switch firmware */
+                        reg = <0x0 0x00040000>;
+                        label = "NOR Vitesse-7385 Firmware";
+                        read-only;
+                };
+
+                partition@40000 {
+                        /* 256KB for DTB Image */
+                        reg = <0x00040000 0x00040000>;
+                        label = "NOR DTB Image";
+                };
+
+                partition@80000 {
+                        /* 3.5 MB for Linux Kernel Image */
+                        reg = <0x00080000 0x00380000>;
+                        label = "NOR Linux Kernel Image";
+                };
+
+                partition@400000 {
+                        /* 11MB for JFFS2 based Root file System */
+                        reg = <0x00400000 0x00b00000>;
+                        label = "NOR JFFS2 Root File System";
+                };
+
+                partition@f00000 {
+                        /* This location must not be altered  */
+                        /* 512KB for u-boot Bootloader Image */
+                        /* 512KB for u-boot Environment Variables */
+                        reg = <0x00f00000 0x00100000>;
+                        label = "NOR U-Boot Image";
+                        read-only;
+                };
+        };
+
+        nand@1,0 {
+                #address-cells = <1>;
+                #size-cells = <1>;
+                compatible = "fsl,p1020-fcm-nand",
+                             "fsl,elbc-fcm-nand";
+                reg = <0x1 0x0 0x40000>;
+
+                partition@0 {
+                        /* This location must not be altered  */
+                        /* 1MB for u-boot Bootloader Image */
+                        reg = <0x0 0x00100000>;
+                        label = "NAND U-Boot Image";
+                        read-only;
+                };
+
+                partition@100000 {
+                        /* 1MB for DTB Image */
+                        reg = <0x00100000 0x00100000>;
+                        label = "NAND DTB Image";
+                };
+
+                partition@200000 {
+                        /* 4MB for Linux Kernel Image */
+                        reg = <0x00200000 0x00400000>;
+                        label = "NAND Linux Kernel Image";
+                };
+
+                partition@600000 {
+                        /* 4MB for Compressed Root file System Image */
+                        reg = <0x00600000 0x00400000>;
+                        label = "NAND Compressed RFS Image";
+                };
+
+                partition@a00000 {
+                        /* 7MB for JFFS2 based Root file System */
+                        reg = <0x00a00000 0x00700000>;
+                        label = "NAND JFFS2 Root File System";
+                };
+
+                partition@1100000 {
+                        /* 15MB for JFFS2 based Root file System */
+                        reg = <0x01100000 0x00f00000>;
+                        label = "NAND Writable User area";
+                };
+        };
+
+        L2switch@2,0 {
+                #address-cells = <1>;
+                #size-cells = <1>;
+                compatible = "vitesse-7385";
+                reg = <0x2 0x0 0x20000>;
+        };
+
+        cpld@3,0 {
+                #address-cells = <1>;
+                #size-cells = <1>;
+                compatible = "cpld";
+                reg = <0x3 0x0 0x20000>;
+                read-only;
+        };
+};
+
+&soc {
+        i2c@3000 {
+                rtc@68 {
+                        compatible = "pericom,pt7c4338";
+                        reg = <0x68>;
+                };
+        };
+
+        spi@7000 {
+                flash@0 {
+                        #address-cells = <1>;
+                        #size-cells = <1>;
+                        compatible = "spansion,s25sl12801";
+                        reg = <0>;
+                        spi-max-frequency = <40000000>; /* input clock */
+
+                        partition@u-boot {
+                                /* 512KB for u-boot Bootloader Image */
+                                reg = <0x0 0x00080000>;
+                                label = "u-boot";
+                                read-only;
+                        };
+
+                        partition@dtb {
+                                /* 512KB for DTB Image*/
+                                reg = <0x00080000 0x00080000>;
+                                label = "dtb";
+                        };
+
+                        partition@kernel {
+                                /* 4MB for Linux Kernel Image */
+                                reg = <0x00100000 0x00400000>;
+                                label = "kernel";
+                        };
+
+                        partition@fs {
+                                /* 4MB for Compressed RFS Image */
+                                reg = <0x00500000 0x00400000>;
+                                label = "file system";
+                        };
+
+                        partition@jffs-fs {
+                                /* 7MB for JFFS2 based RFS */
+                                reg = <0x00900000 0x00700000>;
+                                label = "file system jffs2";
+                        };
+                };
+        };
+
+        usb@22000 {
+                phy_type = "ulpi";
+        };
+
+        /* USB2 is shared with localbus, so it must be disabled
+           by default. We can't put 'status = "disabled";' here
+           since U-Boot doesn't clear the status property when
+           it enables USB2. OTOH, U-Boot does create a new node
+           when there isn't any. So, just comment it out.
+        usb@23000 {
+                phy_type = "ulpi";
+        };
+        */
+
+        mdio@24000 {
+                phy0: ethernet-phy@0 {
+                        interrupt-parent = <&mpic>;
+                        interrupts = <3 1>;
+                        reg = <0x0>;
+                };
+
+                phy1: ethernet-phy@1 {
+                        interrupt-parent = <&mpic>;
+                        interrupts = <2 1>;
+                        reg = <0x1>;
+                };
+
+                tbi0: tbi-phy@11 {
+                        device_type = "tbi-phy";
+                        reg = <0x11>;
+                };
+        };
+
+        mdio@25000 {
+                tbi1: tbi-phy@11 {
+                        reg = <0x11>;
+                        device_type = "tbi-phy";
+                };
+        };
+
+        enet0: ethernet@b0000 {
+                fixed-link = <1 1 1000 0 0>;
+                phy-connection-type = "rgmii-id";
+
+        };
+
+        enet1: ethernet@b1000 {
+                phy-handle = <&phy0>;
+                tbi-handle = <&tbi1>;
+                phy-connection-type = "sgmii";
+        };
+
+        enet2: ethernet@b2000 {
+                phy-handle = <&phy1>;
+                phy-connection-type = "rgmii-id";
+        };
+};
diff --git a/arch/powerpc/boot/dts/p1020rdb-pc_32b.dts b/arch/powerpc/boot/dts/p1020rdb-pc_32b.dts
new file mode 100644
index 000000000000..4de69b726dc5
--- /dev/null
+++ b/arch/powerpc/boot/dts/p1020rdb-pc_32b.dts
@@ -0,0 +1,90 @@
+/*
+ * P1020 RDB-PC Device Tree Source (32-bit address map)
+ *
+ * Copyright 2012 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in the
+ *       documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Freescale Semiconductor nor the
+ *       names of its contributors may be used to endorse or promote products
+ *       derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+/include/ "fsl/p1020si-pre.dtsi"
+/ {
+        model = "fsl,P1020RDB-PC";
+        compatible = "fsl,P1020RDB-PC";
+
+        memory {
+                device_type = "memory";
+        };
+
+        lbc: localbus@ffe05000 {
+                reg = <0 0xffe05000 0 0x1000>;
+
+                /* NOR, NAND Flashes and Vitesse 5 port L2 switch */
+                ranges = <0x0 0x0 0x0 0xef000000 0x01000000
+                          0x1 0x0 0x0 0xff800000 0x00040000
+                          0x2 0x0 0x0 0xffb00000 0x00020000
+                          0x3 0x0 0x0 0xffa00000 0x00020000>;
+        };
+
+        soc: soc@ffe00000 {
+                ranges = <0x0 0x0 0xffe00000 0x100000>;
+        };
+
+        pci0: pcie@ffe09000 {
+                ranges = <0x2000000 0x0 0xa0000000 0 0xa0000000 0x0 0x20000000
+                          0x1000000 0x0 0x00000000 0 0xffc10000 0x0 0x10000>;
+                reg = <0 0xffe09000 0 0x1000>;
+                pcie@0 {
+                        ranges = <0x2000000 0x0 0xa0000000
+                                  0x2000000 0x0 0xa0000000
+                                  0x0 0x20000000
+
+                                  0x1000000 0x0 0x0
+                                  0x1000000 0x0 0x0
+                                  0x0 0x100000>;
+                };
+        };
+
+        pci1: pcie@ffe0a000 {
+                reg = <0 0xffe0a000 0 0x1000>;
+                ranges = <0x2000000 0x0 0x80000000 0 0x80000000 0x0 0x20000000
+                          0x1000000 0x0 0x00000000 0 0xffc00000 0x0 0x10000>;
+                pcie@0 {
+                        ranges = <0x2000000 0x0 0x80000000
+                                  0x2000000 0x0 0x80000000
+                                  0x0 0x20000000
+
+                                  0x1000000 0x0 0x0
+                                  0x1000000 0x0 0x0
+                                  0x0 0x100000>;
+                };
+        };
+};
+
+/include/ "p1020rdb-pc.dtsi"
+/include/ "fsl/p1020si-post.dtsi"
diff --git a/arch/powerpc/boot/dts/p1020rdb-pc_36b.dts b/arch/powerpc/boot/dts/p1020rdb-pc_36b.dts
new file mode 100644
index 000000000000..5237da7441bc
--- /dev/null
+++ b/arch/powerpc/boot/dts/p1020rdb-pc_36b.dts
@@ -0,0 +1,90 @@
+/*
+ * P1020 RDB-PC Device Tree Source (36-bit address map)
+ *
+ * Copyright 2012 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in the
+ *       documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Freescale Semiconductor nor the
+ *       names of its contributors may be used to endorse or promote products
+ *       derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+/include/ "fsl/p1020si-pre.dtsi"
+/ {
+        model = "fsl,P1020RDB-PC";
+        compatible = "fsl,P1020RDB-PC";
+
+        memory {
+                device_type = "memory";
+        };
+
+        lbc: localbus@fffe05000 {
+                reg = <0xf 0xffe05000 0 0x1000>;
+
+                /* NOR, NAND Flashes and Vitesse 5 port L2 switch */
+                ranges = <0x0 0x0 0xf 0xef000000 0x01000000
+                          0x1 0x0 0xf 0xff800000 0x00040000
+                          0x2 0x0 0xf 0xffb00000 0x00040000
+                          0x3 0x0 0xf 0xffa00000 0x00020000>;
+        };
+
+        soc: soc@fffe00000 {
+                ranges = <0x0 0xf 0xffe00000 0x100000>;
+        };
+
+        pci0: pcie@fffe09000 {
+                reg = <0xf 0xffe09000 0 0x1000>;
+                ranges = <0x2000000 0x0 0xc0000000 0xc 0x20000000 0x0 0x20000000
+                          0x1000000 0x0 0x00000000 0xf 0xffc10000 0x0 0x10000>;
+                pcie@0 {
+                        ranges = <0x2000000 0x0 0xc0000000
+                                  0x2000000 0x0 0xc0000000
+                                  0x0 0x20000000
+
+                                  0x1000000 0x0 0x0
+                                  0x1000000 0x0 0x0
+                                  0x0 0x100000>;
+                };
+        };
+
+        pci1: pcie@fffe0a000 {
+                reg = <0xf 0xffe0a000 0 0x1000>;
+                ranges = <0x2000000 0x0 0x80000000 0xc 0x00000000 0x0 0x20000000
+                          0x1000000 0x0 0x00000000 0xf 0xffc00000 0x0 0x10000>;
+                pcie@0 {
+                        ranges = <0x2000000 0x0 0x80000000
+                                  0x2000000 0x0 0x80000000
+                                  0x0 0x20000000
+
+                                  0x1000000 0x0 0x0
+                                  0x1000000 0x0 0x0
+                                  0x0 0x100000>;
+                };
+        };
+};
+
+/include/ "p1020rdb-pc.dtsi"
+/include/ "fsl/p1020si-post.dtsi"
diff --git a/arch/powerpc/boot/dts/p1020rdb-pc_camp_core0.dts b/arch/powerpc/boot/dts/p1020rdb-pc_camp_core0.dts
new file mode 100644
index 000000000000..f411515937ec
--- /dev/null
+++ b/arch/powerpc/boot/dts/p1020rdb-pc_camp_core0.dts
@@ -0,0 +1,64 @@
+/*
+ * P1020 RDB-PC  Core0 Device Tree Source in CAMP mode.
+ *
+ * In CAMP mode, each core needs to have its own dts. Only mpic and L2 cache
+ * can be shared, all the other devices must be assigned to one core only.
+ * This dts file allows core0 to have memory, l2, i2c, spi, gpio, tdm, dma, usb,
+ * eth1, eth2, sdhc, crypto, global-util, message, pci0, pci1, msi.
+ *
+ * Please note to add "-b 0" for core0's dts compiling.
+ *
+ * Copyright 2012 Freescale Semiconductor Inc.
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ */
+
+/include/ "p1020rdb-pc_32b.dts"
+
+/ {
+        model = "fsl,P1020RDB-PC";
+        compatible = "fsl,P1020RDB-PC";
+
+        aliases {
+                ethernet1 = &enet1;
+                ethernet2 = &enet2;
+                serial0 = &serial0;
+                pci0 = &pci0;
+                pci1 = &pci1;
+        };
+
+        cpus {
+                PowerPC,P1020@1 {
+                        status = "disabled";
+                };
+        };
+
+        memory {
+                device_type = "memory";
+        };
+
+        localbus@ffe05000 {
+                status = "disabled";
+        };
+
+        soc@ffe00000 {
+                serial1: serial@4600 {
+                        status = "disabled";
+                };
+
+                enet0: ethernet@b0000 {
+                        status = "disabled";
+                };
+
+                mpic: pic@40000 {
+                        protected-sources = <
+                        42 29 30 34     /* serial1, enet0-queue-group0 */
+                        17 18 24 45     /* enet0-queue-group1, crypto */
+                        >;
+                        pic-no-reset;
+                };
+        };
+};
diff --git a/arch/powerpc/boot/dts/p1020rdb-pc_camp_core1.dts b/arch/powerpc/boot/dts/p1020rdb-pc_camp_core1.dts
new file mode 100644
index 000000000000..a91335ad82c2
--- /dev/null
+++ b/arch/powerpc/boot/dts/p1020rdb-pc_camp_core1.dts
@@ -0,0 +1,142 @@
+/*
+ * P1020 RDB-PC Core1 Device Tree Source in CAMP mode.
+ *
+ * In CAMP mode, each core needs to have its own dts. Only mpic and L2 cache
+ * can be shared, all the other devices must be assigned to one core only.
+ * This dts allows core1 to have l2, eth0, crypto.
+ *
+ * Please note to add "-b 1" for core1's dts compiling.
+ *
+ * Copyright 2012 Freescale Semiconductor Inc.
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ */
+
+/include/ "p1020rdb-pc_32b.dts"
+
+/ {
+        model = "fsl,P1020RDB-PC";
+        compatible = "fsl,P1020RDB-PC";
+
+        aliases {
+                ethernet0 = &enet0;
+                serial0 = &serial1;
+                };
+
+        cpus {
+                PowerPC,P1020@0 {
+                        status = "disabled";
+                };
+        };
+
+        memory {
+                device_type = "memory";
+        };
+
+        localbus@ffe05000 {
+                status = "disabled";
+        };
+
+        soc@ffe00000 {
+                ecm-law@0 {
+                        status = "disabled";
+                };
+
+                ecm@1000 {
+                        status = "disabled";
+                };
+
+                memory-controller@2000 {
+                        status = "disabled";
+                };
+
+                i2c@3000 {
+                        status = "disabled";
+                };
+
+                i2c@3100 {
+                        status = "disabled";
+                };
+
+                serial0: serial@4500 {
+                        status = "disabled";
+                };
+
+                spi@7000 {
+                        status = "disabled";
+                };
+
+                gpio: gpio-controller@f000 {
+                        status = "disabled";
+                };
+
+                dma@21300 {
+                        status = "disabled";
+                };
+
+                mdio@24000 {
+                        status = "disabled";
+                };
+
+                mdio@25000 {
+                        status = "disabled";
+                };
+
+                enet1: ethernet@b1000 {
+                        status = "disabled";
+                };
+
+                enet2: ethernet@b2000 {
+                        status = "disabled";
+                };
+
+                usb@22000 {
+                        status = "disabled";
+                };
+
+                sdhci@2e000 {
+                        status = "disabled";
+                };
+
+                mpic: pic@40000 {
+                        protected-sources = <
+                        16              /* ecm, mem, L2, pci0, pci1 */
+                        43 42 59        /* i2c, serial0, spi */
+                        47 63 62        /* gpio, tdm */
+                        20 21 22 23     /* dma */
+                        03 02           /* mdio */
+                        35 36 40        /* enet1-queue-group0 */
+                        51 52 67        /* enet1-queue-group1 */
+                        31 32 33        /* enet2-queue-group0 */
+                        25 26 27        /* enet2-queue-group1 */
+                        28 72 58        /* usb, sdhci, crypto */
+                        0xb0 0xb1 0xb2  /* message */
+                        0xb3 0xb4 0xb5
+                        0xb6 0xb7
+                        0xe0 0xe1 0xe2  /* msi */
+                        0xe3 0xe4 0xe5
+                        0xe6 0xe7               /* sdhci, crypto , pci */
+                        >;
+                        pic-no-reset;
+                };
+
+                msi@41600 {
+                        status = "disabled";
+                };
+
+                global-utilities@e0000 {        //global utilities block
+                        status = "disabled";
+                };
+        };
+
+        pci0: pcie@ffe09000 {
+                status = "disabled";
+        };
+
+        pci1: pcie@ffe0a000 {
+                status = "disabled";
+        };
+};
diff --git a/arch/powerpc/boot/dts/p1020rdb.dtsi b/arch/powerpc/boot/dts/p1020rdb.dtsi
index b5bd86f4baf2..1fb7e0e0940f 100644
--- a/arch/powerpc/boot/dts/p1020rdb.dtsi
+++ b/arch/powerpc/boot/dts/p1020rdb.dtsi
@@ -1,7 +1,7 @@
 /*
  * P1020 RDB Device Tree Source stub (no addresses or top-level ranges)
  *
- * Copyright 2011 Freescale Semiconductor Inc.
+ * Copyright 2011-2012 Freescale Semiconductor Inc.
  *
  * Redistribution and use in source and binary forms, with or without
  * modification, are permitted provided that the following conditions are met:
@@ -190,17 +190,16 @@
 
         usb@22000 {
                 phy_type = "ulpi";
+                dr_mode = "host";
         };
 
-        /* USB2 is shared with localbus, so it must be disabled
-           by default. We can't put 'status = "disabled";' here
-           since U-Boot doesn't clear the status property when
-           it enables USB2. OTOH, U-Boot does create a new node
-           when there isn't any. So, just comment it out.
+        /* USB2 is shared with localbus. It is used
+           only in case of SPI and SD boot after
+           appropriate device-tree fixup done by uboot */
         usb@23000 {
                 phy_type = "ulpi";
+                dr_mode = "host";
         };
-        */
 
         mdio@24000 {
                 phy0: ethernet-phy@0 {
diff --git a/arch/powerpc/boot/dts/p1021mds.dts b/arch/powerpc/boot/dts/p1021mds.dts
index d9540791e434..97116f198a37 100644
--- a/arch/powerpc/boot/dts/p1021mds.dts
+++ b/arch/powerpc/boot/dts/p1021mds.dts
@@ -1,7 +1,7 @@
 /*
  * P1021 MDS Device Tree Source
  *
- * Copyright 2010 Freescale Semiconductor Inc.
+ * Copyright 2010,2012 Freescale Semiconductor Inc.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms of the GNU General Public License as published by the
@@ -151,6 +151,7 @@
 
                 usb@22000 {
                         phy_type = "ulpi";
+                        dr_mode = "host";
                 };
 
                 mdio@24000 {
diff --git a/arch/powerpc/boot/dts/p1021rdb.dts b/arch/powerpc/boot/dts/p1021rdb.dts
new file mode 100644
index 000000000000..90b6b4caa273
--- /dev/null
+++ b/arch/powerpc/boot/dts/p1021rdb.dts
@@ -0,0 +1,96 @@
+/*
+ * P1021 RDB Device Tree Source
+ *
+ * Copyright 2011 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in the
+ *       documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Freescale Semiconductor nor the
+ *       names of its contributors may be used to endorse or promote products
+ *       derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor "AS IS" AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+/include/ "fsl/p1021si-pre.dtsi"
+/ {
+        model = "fsl,P1021RDB";
+        compatible = "fsl,P1021RDB-PC";
+
+        memory {
+                device_type = "memory";
+        };
+
+        lbc: localbus@ffe05000 {
+                reg = <0 0xffe05000 0 0x1000>;
+
+                /* NOR, NAND Flashes and Vitesse 5 port L2 switch */
+                ranges = <0x0 0x0 0x0 0xef000000 0x01000000
+                          0x1 0x0 0x0 0xff800000 0x00040000
+                          0x2 0x0 0x0 0xffb00000 0x00020000>;
+        };
+
+        soc: soc@ffe00000 {
+                ranges = <0x0 0x0 0xffe00000 0x100000>;
+        };
+
+        pci0: pcie@ffe09000 {
+                ranges = <0x2000000 0x0 0xa0000000 0 0xa0000000 0x0 0x20000000
+                          0x1000000 0x0 0x00000000 0 0xffc10000 0x0 0x10000>;
+                reg = <0 0xffe09000 0 0x1000>;
+                pcie@0 {
+                        ranges = <0x2000000 0x0 0xa0000000
+                                  0x2000000 0x0 0xa0000000
+                                  0x0 0x20000000
+
+                                  0x1000000 0x0 0x0
+                                  0x1000000 0x0 0x0
+                                  0x0 0x100000>;
+                };
+        };
+
+        pci1: pcie@ffe0a000 {
+                reg = <0 0xffe0a000 0 0x1000>;
+                ranges = <0x2000000 0x0 0x80000000 0 0x80000000 0x0 0x20000000
+                          0x1000000 0x0 0x00000000 0 0xffc00000 0x0 0x10000>;
+                pcie@0 {
+                        ranges = <0x2000000 0x0 0x80000000
+                                  0x2000000 0x0 0x80000000
+                                  0x0 0x20000000
+
+                                  0x1000000 0x0 0x0
+                                  0x1000000 0x0 0x0
+                                  0x0 0x100000>;
+                };
+        };
+
+        qe: qe@ffe80000 {
+                ranges = <0x0 0x0 0xffe80000 0x40000>;
+                reg = <0 0xffe80000 0 0x480>;
+                brg-frequency = <0>;
+                bus-frequency = <0>;
+        };
+};
+
+/include/ "p1021rdb.dtsi"
+/include/ "fsl/p1021si-post.dtsi"
diff --git a/arch/powerpc/boot/dts/p1021rdb.dtsi b/arch/powerpc/boot/dts/p1021rdb.dtsi
new file mode 100644
index 000000000000..b973461ab751
--- /dev/null
+++ b/arch/powerpc/boot/dts/p1021rdb.dtsi
@@ -0,0 +1,236 @@
+/*
+ * P1021 RDB Device Tree Source stub (no addresses or top-level ranges)
+ *
+ * Copyright 2011 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in the
+ *       documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Freescale Semiconductor nor the
+ *       names of its contributors may be used to endorse or promote products
+ *       derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+&lbc {
+        nor@0,0 {
+                #address-cells = <1>;
+                #size-cells = <1>;
+                compatible = "cfi-flash";
+                reg = <0x0 0x0 0x1000000>;
+                bank-width = <2>;
+                device-width = <1>;
+
+                partition@0 {
+                        /* This location must not be altered  */
+                        /* 256KB for Vitesse 7385 Switch firmware */
+                        reg = <0x0 0x00040000>;
+                        label = "NOR Vitesse-7385 Firmware";
+                        read-only;
+                };
+
+                partition@40000 {
+                        /* 256KB for DTB Image */
+                        reg = <0x00040000 0x00040000>;
+                        label = "NOR DTB Image";
+                };
+
+                partition@80000 {
+                        /* 3.5 MB for Linux Kernel Image */
+                        reg = <0x00080000 0x00380000>;
+                        label = "NOR Linux Kernel Image";
+                };
+
+                partition@400000 {
+                        /* 11MB for JFFS2 based Root file System */
+                        reg = <0x00400000 0x00b00000>;
+                        label = "NOR JFFS2 Root File System";
+                };
+
+                partition@f00000 {
+                        /* This location must not be altered  */
+                        /* 512KB for u-boot Bootloader Image */
+                        /* 512KB for u-boot Environment Variables */
+                        reg = <0x00f00000 0x00100000>;
+                        label = "NOR U-Boot Image";
+                };
+        };
+
+        nand@1,0 {
+                #address-cells = <1>;
+                #size-cells = <1>;
+                compatible = "fsl,p1021-fcm-nand",
+                             "fsl,elbc-fcm-nand";
+                reg = <0x1 0x0 0x40000>;
+
+                partition@0 {
+                        /* This location must not be altered  */
+                        /* 1MB for u-boot Bootloader Image */
+                        reg = <0x0 0x00100000>;
+                        label = "NAND U-Boot Image";
+                        read-only;
+                };
+
+                partition@100000 {
+                        /* 1MB for DTB Image */
+                        reg = <0x00100000 0x00100000>;
+                        label = "NAND DTB Image";
+                };
+
+                partition@200000 {
+                        /* 4MB for Linux Kernel Image */
+                        reg = <0x00200000 0x00400000>;
+                        label = "NAND Linux Kernel Image";
+                };
+
+                partition@600000 {
+                        /* 4MB for Compressed Root file System Image */
+                        reg = <0x00600000 0x00400000>;
+                        label = "NAND Compressed RFS Image";
+                };
+
+                partition@a00000 {
+                        /* 7MB for JFFS2 based Root file System */
+                        reg = <0x00a00000 0x00700000>;
+                        label = "NAND JFFS2 Root File System";
+                };
+
+                partition@1100000 {
+                        /* 15MB for User Writable Area  */
+                        reg = <0x01100000 0x00f00000>;
+                        label = "NAND Writable User area";
+                };
+        };
+
+        L2switch@2,0 {
+                #address-cells = <1>;
+                #size-cells = <1>;
+                compatible = "vitesse-7385";
+                reg = <0x2 0x0 0x20000>;
+        };
+};
+
+&soc {
+        i2c@3000 {
+                rtc@68 {
+                        compatible = "pericom,pt7c4338";
+                        reg = <0x68>;
+                };
+        };
+
+        spi@7000 {
+                flash@0 {
+                        #address-cells = <1>;
+                        #size-cells = <1>;
+                        compatible = "spansion,s25sl12801";
+                        reg = <0>;
+                        spi-max-frequency = <40000000>; /* input clock */
+
+                        partition@u-boot {
+                                /* 512KB for u-boot Bootloader Image */
+                                reg = <0x0 0x00080000>;
+                                label = "SPI Flash U-Boot Image";
+                                read-only;
+                        };
+
+                        partition@dtb {
+                                /* 512KB for DTB Image */
+                                reg = <0x00080000 0x00080000>;
+                                label = "SPI Flash DTB Image";
+                        };
+
+                        partition@kernel {
+                                /* 4MB for Linux Kernel Image */
+                                reg = <0x00100000 0x00400000>;
+                                label = "SPI Flash Linux Kernel Image";
+                        };
+
+                        partition@fs {
+                                /* 4MB for Compressed RFS Image */
+                                reg = <0x00500000 0x00400000>;
+                                label = "SPI Flash Compressed RFSImage";
+                        };
+
+                        partition@jffs-fs {
+                                /* 7MB for JFFS2 based RFS */
+                                reg = <0x00900000 0x00700000>;
+                                label = "SPI Flash JFFS2 RFS";
+                        };
+                };
+        };
+
+        usb@22000 {
+                phy_type = "ulpi";
+        };
+
+        mdio@24000 {
+                phy0: ethernet-phy@0 {
+                        interrupt-parent = <&mpic>;
+                        interrupts = <3 1 0 0>;
+                        reg = <0x0>;
+                };
+
+                phy1: ethernet-phy@1 {
+                        interrupt-parent = <&mpic>;
+                        interrupts = <2 1 0 0>;
+                        reg = <0x1>;
+                };
+
+                tbi0: tbi-phy@11 {
+                        reg = <0x11>;
+                        device_type = "tbi-phy";
+                };
+        };
+
+        mdio@25000 {
+                tbi1: tbi-phy@11 {
+                        reg = <0x11>;
+                        device_type = "tbi-phy";
+                };
+        };
+
+        mdio@26000 {
+                tbi2: tbi-phy@11 {
+                        reg = <0x11>;
+                        device_type = "tbi-phy";
+                };
+        };
+
+        enet0: ethernet@b0000 {
+                fixed-link = <1 1 1000 0 0>;
+                phy-connection-type = "rgmii-id";
+
+        };
+
+        enet1: ethernet@b1000 {
+                phy-handle = <&phy0>;
+                tbi-handle = <&tbi1>;
+                phy-connection-type = "sgmii";
+        };
+
+        enet2: ethernet@b2000 {
+                phy-handle = <&phy1>;
+                tbi-handle = <&tbi2>;
+                phy-connection-type = "rgmii-id";
+        };
+};
diff --git a/arch/powerpc/boot/dts/p1021rdb_36b.dts b/arch/powerpc/boot/dts/p1021rdb_36b.dts
new file mode 100644
index 000000000000..ea6d8b5fa10b
--- /dev/null
+++ b/arch/powerpc/boot/dts/p1021rdb_36b.dts
@@ -0,0 +1,96 @@
+/*
+ * P1021 RDB Device Tree Source (36-bit address map)
+ *
+ * Copyright 2011 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in the
+ *       documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Freescale Semiconductor nor the
+ *       names of its contributors may be used to endorse or promote products
+ *       derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor "AS IS" AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+/include/ "fsl/p1021si-pre.dtsi"
+/ {
+        model = "fsl,P1021RDB";
+        compatible = "fsl,P1021RDB-PC";
+
+        memory {
+                device_type = "memory";
+        };
+
+        lbc: localbus@fffe05000 {
+                reg = <0xf 0xffe05000 0 0x1000>;
+
+                /* NOR, NAND Flashes and Vitesse 5 port L2 switch */
+                ranges = <0x0 0x0 0xf 0xef000000 0x01000000
+                          0x1 0x0 0xf 0xff800000 0x00040000
+                          0x2 0x0 0xf 0xffb00000 0x00020000>;
+        };
+
+        soc: soc@fffe00000 {
+                ranges = <0x0 0xf 0xffe00000 0x100000>;
+        };
+
+        pci0: pcie@fffe09000 {
+                ranges = <0x2000000 0x0 0xc0000000 0xc 0x20000000 0x0 0x20000000
+                          0x1000000 0x0 0x00000000 0xf 0xffc10000 0x0 0x10000>;
+                reg = <0xf 0xffe09000 0 0x1000>;
+                pcie@0 {
+                        ranges = <0x2000000 0x0 0xa0000000
+                                  0x2000000 0x0 0xa0000000
+                                  0x0 0x20000000
+
+                                  0x1000000 0x0 0x0
+                                  0x1000000 0x0 0x0
+                                  0x0 0x100000>;
+                };
+        };
+
+        pci1: pcie@fffe0a000 {
+                reg = <0xf 0xffe0a000 0 0x1000>;
+                ranges = <0x2000000 0x0 0x80000000 0xc 0x00000000 0x0 0x20000000
+                          0x1000000 0x0 0x00000000 0xf 0xffc00000 0x0 0x10000>;
+                pcie@0 {
+                        ranges = <0x2000000 0x0 0xc0000000
+                                  0x2000000 0x0 0xc0000000
+                                  0x0 0x20000000
+
+                                  0x1000000 0x0 0x0
+                                  0x1000000 0x0 0x0
+                                  0x0 0x100000>;
+                };
+        };
+
+        qe: qe@fffe80000 {
+                ranges = <0x0 0xf 0xffe80000 0x40000>;
+                reg = <0xf 0xffe80000 0 0x480>;
+                brg-frequency = <0>;
+                bus-frequency = <0>;
+        };
+};
+
+/include/ "p1021rdb.dtsi"
+/include/ "fsl/p1021si-post.dtsi"
diff --git a/arch/powerpc/boot/dts/p1022ds.dts b/arch/powerpc/boot/dts/p1022ds.dts
deleted file mode 100644
index ef95717db4bc..000000000000
--- a/arch/powerpc/boot/dts/p1022ds.dts
+++ /dev/null
@@ -1,274 +0,0 @@
-/*
- * P1022 DS 36Bit Physical Address Map Device Tree Source
- *
- * Copyright 2010 Freescale Semiconductor, 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/ "fsl/p1022si-pre.dtsi"
-/ {
-        model = "fsl,P1022DS";
-        compatible = "fsl,P1022DS";
-
-        memory {
-                device_type = "memory";
-        };
-
-        lbc: localbus@fffe05000 {
-                reg = <0xf 0xffe05000 0 0x1000>;
-                ranges = <0x0 0x0 0xf 0xe8000000 0x08000000
-                          0x1 0x0 0xf 0xe0000000 0x08000000
-                          0x2 0x0 0xf 0xff800000 0x00040000
-                          0x3 0x0 0xf 0xffdf0000 0x00008000>;
-
-                /*
-                 * This node is used to access the pixis via "indirect" mode,
-                 * which is done by writing the pixis register index to chip
-                 * select 0 and the value to/from chip select 1.  Indirect
-                 * mode is the only way to access the pixis when DIU video
-                 * is enabled.  Note that this assumes that the first column
-                 * of the 'ranges' property above is the chip select number.
-                 */
-                board-control@0,0 {
-                        compatible = "fsl,p1022ds-indirect-pixis";
-                        reg = <0x0 0x0 1        /* CS0 */
-                               0x1 0x0 1>;      /* CS1 */
-                };
-
-                nor@0,0 {
-                        #address-cells = <1>;
-                        #size-cells = <1>;
-                        compatible = "cfi-flash";
-                        reg = <0x0 0x0 0x8000000>;
-                        bank-width = <2>;
-                        device-width = <1>;
-
-                        partition@0 {
-                                reg = <0x0 0x03000000>;
-                                label = "ramdisk-nor";
-                                read-only;
-                        };
-
-                        partition@3000000 {
-                                reg = <0x03000000 0x00e00000>;
-                                label = "diagnostic-nor";
-                                read-only;
-                        };
-
-                        partition@3e00000 {
-                                reg = <0x03e00000 0x00200000>;
-                                label = "dink-nor";
-                                read-only;
-                        };
-
-                        partition@4000000 {
-                                reg = <0x04000000 0x00400000>;
-                                label = "kernel-nor";
-                                read-only;
-                        };
-
-                        partition@4400000 {
-                                reg = <0x04400000 0x03b00000>;
-                                label = "jffs2-nor";
-                        };
-
-                        partition@7f00000 {
-                                reg = <0x07f00000 0x00080000>;
-                                label = "dtb-nor";
-                                read-only;
-                        };
-
-                        partition@7f80000 {
-                                reg = <0x07f80000 0x00080000>;
-                                label = "u-boot-nor";
-                                read-only;
-                        };
-                };
-
-                nand@2,0 {
-                        #address-cells = <1>;
-                        #size-cells = <1>;
-                        compatible = "fsl,elbc-fcm-nand";
-                        reg = <0x2 0x0 0x40000>;
-
-                        partition@0 {
-                                reg = <0x0 0x02000000>;
-                                label = "u-boot-nand";
-                                read-only;
-                        };
-
-                        partition@2000000 {
-                                reg = <0x02000000 0x10000000>;
-                                label = "jffs2-nand";
-                        };
-
-                        partition@12000000 {
-                                reg = <0x12000000 0x10000000>;
-                                label = "ramdisk-nand";
-                                read-only;
-                        };
-
-                        partition@22000000 {
-                                reg = <0x22000000 0x04000000>;
-                                label = "kernel-nand";
-                        };
-
-                        partition@26000000 {
-                                reg = <0x26000000 0x01000000>;
-                                label = "dtb-nand";
-                                read-only;
-                        };
-
-                        partition@27000000 {
-                                reg = <0x27000000 0x19000000>;
-                                label = "reserved-nand";
-                        };
-                };
-
-                board-control@3,0 {
-                        compatible = "fsl,p1022ds-fpga", "fsl,fpga-ngpixis";
-                        reg = <3 0 0x30>;
-                        interrupt-parent = <&mpic>;
-                        /*
-                         * IRQ8 is generated if the "EVENT" switch is pressed
-                         * and PX_CTL[EVESEL] is set to 00.
-                         */
-                        interrupts = <8 8 0 0>;
-                };
-        };
-
-        soc: soc@fffe00000 {
-                ranges = <0x0 0xf 0xffe00000 0x100000>;
-
-                i2c@3100 {
-                        wm8776:codec@1a {
-                                compatible = "wlf,wm8776";
-                                reg = <0x1a>;
-                                /*
-                                 * clock-frequency will be set by U-Boot if
-                                 * the clock is enabled.
-                                 */
-                        };
-                };
-
-                spi@7000 {
-                        flash@0 {
-                                #address-cells = <1>;
-                                #size-cells = <1>;
-                                compatible = "spansion,s25sl12801";
-                                reg = <0>;
-                                spi-max-frequency = <40000000>; /* input clock */
-
-                                partition@0 {
-                                        label = "u-boot-spi";
-                                        reg = <0x00000000 0x00100000>;
-                                        read-only;
-                                };
-                                partition@100000 {
-                                        label = "kernel-spi";
-                                        reg = <0x00100000 0x00500000>;
-                                        read-only;
-                                };
-                                partition@600000 {
-                                        label = "dtb-spi";
-                                        reg = <0x00600000 0x00100000>;
-                                        read-only;
-                                };
-                                partition@700000 {
-                                        label = "file system-spi";
-                                        reg = <0x00700000 0x00900000>;
-                                };
-                        };
-                };
-
-                ssi@15000 {
-                        fsl,mode = "i2s-slave";
-                        codec-handle = <&wm8776>;
-                        fsl,ssi-asynchronous;
-                };
-
-                usb@22000 {
-                        phy_type = "ulpi";
-                };
-
-                usb@23000 {
-                        status = "disabled";
-                };
-
-                mdio@24000 {
-                        phy0: ethernet-phy@0 {
-                                interrupts = <3 1 0 0>;
-                                reg = <0x1>;
-                        };
-                        phy1: ethernet-phy@1 {
-                                interrupts = <9 1 0 0>;
-                                reg = <0x2>;
-                        };
-                        tbi-phy@2 {
-                                device_type = "tbi-phy";
-                                reg = <0x2>;
-                        };
-                };
-
-                ethernet@b0000 {
-                        phy-handle = <&phy0>;
-                        phy-connection-type = "rgmii-id";
-                };
-
-                ethernet@b1000 {
-                        phy-handle = <&phy1>;
-                        phy-connection-type = "rgmii-id";
-                };
-        };
-
-        pci0: pcie@fffe09000 {
-                reg = <0xf 0xffe09000 0 0x1000>;
-                ranges = <0x2000000 0x0 0xe0000000 0xc 0x20000000 0x0 0x20000000
-                          0x1000000 0x0 0x00000000 0xf 0xffc10000 0x0 0x10000>;
-                pcie@0 {
-                        ranges = <0x2000000 0x0 0xe0000000
-                                  0x2000000 0x0 0xe0000000
-                                  0x0 0x20000000
-
-                                  0x1000000 0x0 0x0
-                                  0x1000000 0x0 0x0
-                                  0x0 0x100000>;
-                };
-        };
-
-        pci1: pcie@fffe0a000 {
-                reg = <0xf 0xffe0a000 0 0x1000>;
-                ranges = <0x2000000 0x0 0xe0000000 0xc 0x40000000 0x0 0x20000000
-                          0x1000000 0x0 0x00000000 0xf 0xffc20000 0x0 0x10000>;
-                pcie@0 {
-                        reg = <0x0 0x0 0x0 0x0 0x0>;
-                        ranges = <0x2000000 0x0 0xe0000000
-                                  0x2000000 0x0 0xe0000000
-                                  0x0 0x20000000
-
-                                  0x1000000 0x0 0x0
-                                  0x1000000 0x0 0x0
-                                  0x0 0x100000>;
-                };
-        };
-
-        pci2: pcie@fffe0b000 {
-                reg = <0xf 0xffe0b000 0 0x1000>;
-                ranges = <0x2000000 0x0 0xe0000000 0xc 0x00000000 0x0 0x20000000
-                          0x1000000 0x0 0x00000000 0xf 0xffc00000 0x0 0x10000>;
-                pcie@0 {
-                        ranges = <0x2000000 0x0 0xe0000000
-                                  0x2000000 0x0 0xe0000000
-                                  0x0 0x20000000
-
-                                  0x1000000 0x0 0x0
-                                  0x1000000 0x0 0x0
-                                  0x0 0x100000>;
-                };
-        };
-};
-
-/include/ "fsl/p1022si-post.dtsi"
diff --git a/arch/powerpc/boot/dts/p1022ds.dtsi b/arch/powerpc/boot/dts/p1022ds.dtsi
new file mode 100644
index 000000000000..7cdb505036bb
--- /dev/null
+++ b/arch/powerpc/boot/dts/p1022ds.dtsi
@@ -0,0 +1,234 @@
+/*
+ * P1022 DS Device Tree Source stub (no addresses or top-level ranges)
+ *
+ * Copyright 2012 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in the
+ *       documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Freescale Semiconductor nor the
+ *       names of its contributors may be used to endorse or promote products
+ *       derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor "AS IS" AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+&board_lbc {
+        /*
+         * This node is used to access the pixis via "indirect" mode,
+         * which is done by writing the pixis register index to chip
+         * select 0 and the value to/from chip select 1.  Indirect
+         * mode is the only way to access the pixis when DIU video
+         * is enabled.  Note that this assumes that the first column
+         * of the 'ranges' property above is the chip select number.
+         */
+        board-control@0,0 {
+                compatible = "fsl,p1022ds-indirect-pixis";
+                reg = <0x0 0x0 1        /* CS0 */
+                       0x1 0x0 1>;      /* CS1 */
+                interrupt-parent = <&mpic>;
+                interrupts = <8 0 0 0>;
+        };
+
+        nor@0,0 {
+                #address-cells = <1>;
+                #size-cells = <1>;
+                compatible = "cfi-flash";
+                reg = <0x0 0x0 0x8000000>;
+                bank-width = <2>;
+                device-width = <1>;
+
+                partition@0 {
+                        reg = <0x0 0x03000000>;
+                        label = "ramdisk-nor";
+                        read-only;
+                };
+
+                partition@3000000 {
+                        reg = <0x03000000 0x00e00000>;
+                        label = "diagnostic-nor";
+                        read-only;
+                };
+
+                partition@3e00000 {
+                        reg = <0x03e00000 0x00200000>;
+                        label = "dink-nor";
+                        read-only;
+                };
+
+                partition@4000000 {
+                        reg = <0x04000000 0x00400000>;
+                        label = "kernel-nor";
+                        read-only;
+                };
+
+                partition@4400000 {
+                        reg = <0x04400000 0x03b00000>;
+                        label = "jffs2-nor";
+                };
+
+                partition@7f00000 {
+                        reg = <0x07f00000 0x00080000>;
+                        label = "dtb-nor";
+                        read-only;
+                };
+
+                partition@7f80000 {
+                        reg = <0x07f80000 0x00080000>;
+                        label = "u-boot-nor";
+                        read-only;
+                };
+        };
+
+        nand@2,0 {
+                #address-cells = <1>;
+                #size-cells = <1>;
+                compatible = "fsl,elbc-fcm-nand";
+                reg = <0x2 0x0 0x40000>;
+
+                partition@0 {
+                        reg = <0x0 0x02000000>;
+                        label = "u-boot-nand";
+                        read-only;
+                };
+
+                partition@2000000 {
+                        reg = <0x02000000 0x10000000>;
+                        label = "jffs2-nand";
+                };
+
+                partition@12000000 {
+                        reg = <0x12000000 0x10000000>;
+                        label = "ramdisk-nand";
+                        read-only;
+                };
+
+                partition@22000000 {
+                        reg = <0x22000000 0x04000000>;
+                        label = "kernel-nand";
+                };
+
+                partition@26000000 {
+                        reg = <0x26000000 0x01000000>;
+                        label = "dtb-nand";
+                        read-only;
+                };
+
+                partition@27000000 {
+                        reg = <0x27000000 0x19000000>;
+                        label = "reserved-nand";
+                };
+        };
+
+        board-control@3,0 {
+                compatible = "fsl,p1022ds-fpga", "fsl,fpga-ngpixis";
+                reg = <3 0 0x30>;
+                interrupt-parent = <&mpic>;
+                /*
+                 * IRQ8 is generated if the "EVENT" switch is pressed
+                 * and PX_CTL[EVESEL] is set to 00.
+                 */
+                interrupts = <8 0 0 0>;
+        };
+};
+
+&board_soc {
+        i2c@3100 {
+                wm8776:codec@1a {
+                        compatible = "wlf,wm8776";
+                        reg = <0x1a>;
+                        /*
+                         * clock-frequency will be set by U-Boot if
+                         * the clock is enabled.
+                         */
+                };
+        };
+
+        spi@7000 {
+                flash@0 {
+                        #address-cells = <1>;
+                        #size-cells = <1>;
+                        compatible = "spansion,s25sl12801";
+                        reg = <0>;
+                        spi-max-frequency = <40000000>; /* input clock */
+
+                        partition@0 {
+                                label = "u-boot-spi";
+                                reg = <0x00000000 0x00100000>;
+                                read-only;
+                        };
+                        partition@100000 {
+                                label = "kernel-spi";
+                                reg = <0x00100000 0x00500000>;
+                                read-only;
+                        };
+                        partition@600000 {
+                                label = "dtb-spi";
+                                reg = <0x00600000 0x00100000>;
+                                read-only;
+                        };
+                        partition@700000 {
+                                label = "file system-spi";
+                                reg = <0x00700000 0x00900000>;
+                        };
+                };
+        };
+
+        ssi@15000 {
+                fsl,mode = "i2s-slave";
+                codec-handle = <&wm8776>;
+                fsl,ssi-asynchronous;
+        };
+
+        usb@22000 {
+                phy_type = "ulpi";
+        };
+
+        usb@23000 {
+                status = "disabled";
+        };
+
+        mdio@24000 {
+                phy0: ethernet-phy@0 {
+                        interrupts = <3 1 0 0>;
+                        reg = <0x1>;
+                };
+                phy1: ethernet-phy@1 {
+                        interrupts = <9 1 0 0>;
+                        reg = <0x2>;
+                };
+                tbi-phy@2 {
+                        device_type = "tbi-phy";
+                        reg = <0x2>;
+                };
+        };
+
+        ethernet@b0000 {
+                phy-handle = <&phy0>;
+                phy-connection-type = "rgmii-id";
+        };
+
+        ethernet@b1000 {
+                phy-handle = <&phy1>;
+                phy-connection-type = "rgmii-id";
+        };
+};
diff --git a/arch/powerpc/boot/dts/p1022ds_32b.dts b/arch/powerpc/boot/dts/p1022ds_32b.dts
new file mode 100644
index 000000000000..d96cae00a9e3
--- /dev/null
+++ b/arch/powerpc/boot/dts/p1022ds_32b.dts
@@ -0,0 +1,103 @@
+/*
+ * P1022 DS 32-bit Physical Address Map Device Tree Source
+ *
+ * Copyright 2012 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in the
+ *       documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Freescale Semiconductor nor the
+ *       names of its contributors may be used to endorse or promote products
+ *       derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor "AS IS" AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+/include/ "fsl/p1022si-pre.dtsi"
+/ {
+        model = "fsl,P1022DS";
+        compatible = "fsl,P1022DS";
+
+        memory {
+                device_type = "memory";
+        };
+
+        board_lbc: lbc: localbus@ffe05000 {
+                ranges = <0x0 0x0 0x0 0xe8000000 0x08000000
+                          0x1 0x0 0x0 0xe0000000 0x08000000
+                          0x2 0x0 0x0 0xff800000 0x00040000
+                          0x3 0x0 0x0 0xffdf0000 0x00008000>;
+                reg = <0x0 0xffe05000 0 0x1000>;
+        };
+
+        board_soc: soc: soc@ffe00000 {
+                ranges = <0x0 0x0 0xffe00000 0x100000>;
+        };
+
+        pci0: pcie@ffe09000 {
+                ranges = <0x2000000 0x0 0xe0000000 0 0xa0000000 0x0 0x20000000
+                          0x1000000 0x0 0x00000000 0 0xffc10000 0x0 0x10000>;
+                reg = <0x0 0xffe09000 0 0x1000>;
+                pcie@0 {
+                        ranges = <0x2000000 0x0 0xe0000000
+                                  0x2000000 0x0 0xe0000000
+                                  0x0 0x20000000
+
+                                  0x1000000 0x0 0x0
+                                  0x1000000 0x0 0x0
+                                  0x0 0x100000>;
+                };
+        };
+
+        pci1: pcie@ffe0a000 {
+                ranges = <0x2000000 0x0 0xe0000000 0 0xc0000000 0x0 0x20000000
+                          0x1000000 0x0 0x00000000 0 0xffc20000 0x0 0x10000>;
+                reg = <0 0xffe0a000 0 0x1000>;
+                pcie@0 {
+                        ranges = <0x2000000 0x0 0xe0000000
+                                  0x2000000 0x0 0xe0000000
+                                  0x0 0x20000000
+
+                                  0x1000000 0x0 0x0
+                                  0x1000000 0x0 0x0
+                                  0x0 0x100000>;
+                };
+        };
+
+        pci2: pcie@ffe0b000 {
+                ranges = <0x2000000 0x0 0xe0000000 0 0x80000000 0x0 0x20000000
+                          0x1000000 0x0 0x00000000 0 0xffc00000 0x0 0x10000>;
+                reg = <0 0xffe0b000 0 0x1000>;
+                pcie@0 {
+                        ranges = <0x2000000 0x0 0xe0000000
+                                  0x2000000 0x0 0xe0000000
+                                  0x0 0x20000000
+
+                                  0x1000000 0x0 0x0
+                                  0x1000000 0x0 0x0
+                                  0x0 0x100000>;
+                };
+        };
+};
+
+/include/ "fsl/p1022si-post.dtsi"
+/include/ "p1022ds.dtsi"
diff --git a/arch/powerpc/boot/dts/p1022ds_36b.dts b/arch/powerpc/boot/dts/p1022ds_36b.dts
new file mode 100644
index 000000000000..f7aacce40bf6
--- /dev/null
+++ b/arch/powerpc/boot/dts/p1022ds_36b.dts
@@ -0,0 +1,103 @@
+/*
+ * P1022 DS 36-bit Physical Address Map Device Tree Source
+ *
+ * Copyright 2012 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in the
+ *       documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Freescale Semiconductor nor the
+ *       names of its contributors may be used to endorse or promote products
+ *       derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor "AS IS" AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+/include/ "fsl/p1022si-pre.dtsi"
+/ {
+        model = "fsl,P1022DS";
+        compatible = "fsl,P1022DS";
+
+        memory {
+                device_type = "memory";
+        };
+
+        board_lbc: lbc: localbus@fffe05000 {
+                ranges = <0x0 0x0 0xf 0xe8000000 0x08000000
+                          0x1 0x0 0xf 0xe0000000 0x08000000
+                          0x2 0x0 0xf 0xff800000 0x00040000
+                          0x3 0x0 0xf 0xffdf0000 0x00008000>;
+                reg = <0xf 0xffe05000 0 0x1000>;
+        };
+
+        board_soc: soc: soc@fffe00000 {
+                ranges = <0x0 0xf 0xffe00000 0x100000>;
+        };
+
+        pci0: pcie@fffe09000 {
+                ranges = <0x2000000 0x0 0xe0000000 0xc 0x20000000 0x0 0x20000000
+                          0x1000000 0x0 0x00000000 0xf 0xffc10000 0x0 0x10000>;
+                reg = <0xf 0xffe09000 0 0x1000>;
+                pcie@0 {
+                        ranges = <0x2000000 0x0 0xe0000000
+                                  0x2000000 0x0 0xe0000000
+                                  0x0 0x20000000
+
+                                  0x1000000 0x0 0x0
+                                  0x1000000 0x0 0x0
+                                  0x0 0x100000>;
+                };
+        };
+
+        pci1: pcie@fffe0a000 {
+                ranges = <0x2000000 0x0 0xe0000000 0xc 0x40000000 0x0 0x20000000
+                          0x1000000 0x0 0x00000000 0xf 0xffc20000 0x0 0x10000>;
+                reg = <0xf 0xffe0a000 0 0x1000>;
+                pcie@0 {
+                        ranges = <0x2000000 0x0 0xe0000000
+                                  0x2000000 0x0 0xe0000000
+                                  0x0 0x20000000
+
+                                  0x1000000 0x0 0x0
+                                  0x1000000 0x0 0x0
+                                  0x0 0x100000>;
+                };
+        };
+
+        pci2: pcie@fffe0b000 {
+                ranges = <0x2000000 0x0 0xe0000000 0xc 0x00000000 0x0 0x20000000
+                          0x1000000 0x0 0x00000000 0xf 0xffc00000 0x0 0x10000>;
+                reg = <0xf 0xffe0b000 0 0x1000>;
+                pcie@0 {
+                        ranges = <0x2000000 0x0 0xe0000000
+                                  0x2000000 0x0 0xe0000000
+                                  0x0 0x20000000
+
+                                  0x1000000 0x0 0x0
+                                  0x1000000 0x0 0x0
+                                  0x0 0x100000>;
+                };
+        };
+};
+
+/include/ "fsl/p1022si-post.dtsi"
+/include/ "p1022ds.dtsi"
diff --git a/arch/powerpc/boot/dts/p1025rdb.dtsi b/arch/powerpc/boot/dts/p1025rdb.dtsi
new file mode 100644
index 000000000000..cf3676fc714b
--- /dev/null
+++ b/arch/powerpc/boot/dts/p1025rdb.dtsi
@@ -0,0 +1,286 @@
+/*
+ * P1025 RDB Device Tree Source stub (no addresses or top-level ranges)
+ *
+ * Copyright 2011 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in the
+ *       documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Freescale Semiconductor nor the
+ *       names of its contributors may be used to endorse or promote products
+ *       derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+&lbc {
+        nor@0,0 {
+                #address-cells = <1>;
+                #size-cells = <1>;
+                compatible = "cfi-flash";
+                reg = <0x0 0x0 0x1000000>;
+                bank-width = <2>;
+                device-width = <1>;
+
+                partition@0 {
+                        /* This location must not be altered  */
+                        /* 256KB for Vitesse 7385 Switch firmware */
+                        reg = <0x0 0x00040000>;
+                        label = "NOR Vitesse-7385 Firmware";
+                        read-only;
+                };
+
+                partition@40000 {
+                        /* 256KB for DTB Image */
+                        reg = <0x00040000 0x00040000>;
+                        label = "NOR DTB Image";
+                };
+
+                partition@80000 {
+                        /* 3.5 MB for Linux Kernel Image */
+                        reg = <0x00080000 0x00380000>;
+                        label = "NOR Linux Kernel Image";
+                };
+
+                partition@400000 {
+                        /* 11MB for JFFS2 based Root file System */
+                        reg = <0x00400000 0x00b00000>;
+                        label = "NOR JFFS2 Root File System";
+                };
+
+                partition@f00000 {
+                        /* This location must not be altered  */
+                        /* 512KB for u-boot Bootloader Image */
+                        /* 512KB for u-boot Environment Variables */
+                        reg = <0x00f00000 0x00100000>;
+                        label = "NOR U-Boot Image";
+                        read-only;
+                };
+        };
+
+        nand@1,0 {
+                #address-cells = <1>;
+                #size-cells = <1>;
+                compatible = "fsl,p1025-fcm-nand",
+                             "fsl,elbc-fcm-nand";
+                reg = <0x1 0x0 0x40000>;
+
+                partition@0 {
+                        /* This location must not be altered  */
+                        /* 1MB for u-boot Bootloader Image */
+                        reg = <0x0 0x00100000>;
+                        label = "NAND U-Boot Image";
+                        read-only;
+                };
+
+                partition@100000 {
+                        /* 1MB for DTB Image */
+                        reg = <0x00100000 0x00100000>;
+                        label = "NAND DTB Image";
+                };
+
+                partition@200000 {
+                        /* 4MB for Linux Kernel Image */
+                        reg = <0x00200000 0x00400000>;
+                        label = "NAND Linux Kernel Image";
+                };
+
+                partition@600000 {
+                        /* 4MB for Compressed Root file System Image */
+                        reg = <0x00600000 0x00400000>;
+                        label = "NAND Compressed RFS Image";
+                };
+
+                partition@a00000 {
+                        /* 7MB for JFFS2 based Root file System */
+                        reg = <0x00a00000 0x00700000>;
+                        label = "NAND JFFS2 Root File System";
+                };
+
+                partition@1100000 {
+                        /* 15MB for JFFS2 based Root file System */
+                        reg = <0x01100000 0x00f00000>;
+                        label = "NAND Writable User area";
+                };
+        };
+
+};
+
+&soc {
+        i2c@3000 {
+                rtc@68 {
+                        compatible = "dallas,ds1339";
+                        reg = <0x68>;
+                };
+        };
+
+        spi@7000 {
+                flash@0 {
+                        #address-cells = <1>;
+                        #size-cells = <1>;
+                        compatible = "spansion,s25sl12801";
+                        reg = <0>;
+                        spi-max-frequency = <40000000>; /* input clock */
+
+                        partition@u-boot {
+                                /* 512KB for u-boot Bootloader Image */
+                                reg = <0x0 0x00080000>;
+                                label = "u-boot";
+                                read-only;
+                        };
+
+                        partition@dtb {
+                                /* 512KB for DTB Image */
+                                reg = <0x00080000 0x00080000>;
+                                label = "dtb";
+                        };
+
+                        partition@kernel {
+                                /* 4MB for Linux Kernel Image */
+                                reg = <0x00100000 0x00400000>;
+                                label = "kernel";
+                        };
+
+                        partition@fs {
+                                /* 4MB for Compressed RFS Image */
+                                reg = <0x00500000 0x00400000>;
+                                label = "file system";
+                        };
+
+                        partition@jffs-fs {
+                                /* 7MB for JFFS2 based RFS */
+                                reg = <0x00900000 0x00700000>;
+                                label = "file system jffs2";
+                        };
+                };
+        };
+
+        usb@22000 {
+                phy_type = "ulpi";
+        };
+
+        /* USB2 is shared with localbus, so it must be disabled
+           by default. We can't put 'status = "disabled";' here
+           since U-Boot doesn't clear the status property when
+           it enables USB2. OTOH, U-Boot does create a new node
+           when there isn't any. So, just comment it out.
+        usb@23000 {
+                phy_type = "ulpi";
+        };
+        */
+
+        mdio@24000 {
+                phy0: ethernet-phy@0 {
+                        interrupt-parent = <&mpic>;
+                        interrupts = <3 1>;
+                        reg = <0x0>;
+                };
+
+                phy1: ethernet-phy@1 {
+                        interrupt-parent = <&mpic>;
+                        interrupts = <2 1>;
+                        reg = <0x1>;
+                };
+
+                tbi0: tbi-phy@11 {
+                        reg = <0x11>;
+                        device_type = "tbi-phy";
+                };
+        };
+
+        mdio@25000 {
+                tbi1: tbi-phy@11 {
+                        reg = <0x11>;
+                        device_type = "tbi-phy";
+                };
+        };
+
+        mdio@26000 {
+                tbi2: tbi-phy@11 {
+                        reg = <0x11>;
+                        device_type = "tbi-phy";
+                };
+        };
+
+        enet0: ethernet@b0000 {
+                fixed-link = <1 1 1000 0 0>;
+                phy-connection-type = "rgmii-id";
+
+        };
+
+        enet1: ethernet@b1000 {
+                phy-handle = <&phy0>;
+                tbi-handle = <&tbi1>;
+                phy-connection-type = "sgmii";
+        };
+
+        enet2: ethernet@b2000 {
+                phy-handle = <&phy1>;
+                phy-connection-type = "rgmii-id";
+        };
+
+        par_io@e0100 {
+                #address-cells = <1>;
+                #size-cells = <1>;
+                reg = <0xe0100 0x60>;
+                ranges = <0x0 0xe0100 0x60>;
+                device_type = "par_io";
+                num-ports = <3>;
+                pio1: ucc_pin@01 {
+                        pio-map = <
+                /* port  pin  dir  open_drain  assignment  has_irq */
+                                0x1  0x13 0x1  0x0  0x1  0x0    /* QE_MUX_MDC */
+                                0x1  0x14 0x3  0x0  0x1  0x0    /* QE_MUX_MDIO */
+                                0x0  0x17 0x2  0x0  0x2  0x0    /* CLK12 */
+                                0x0  0x18 0x2  0x0  0x1  0x0    /* CLK9 */
+                                0x0  0x7  0x1  0x0  0x2  0x0    /* ENET1_TXD0_SER1_TXD0 */
+                                0x0  0x9  0x1  0x0  0x2  0x0    /* ENET1_TXD1_SER1_TXD1 */
+                                0x0  0xb  0x1  0x0  0x2  0x0    /* ENET1_TXD2_SER1_TXD2 */
+                                0x0  0xc  0x1  0x0  0x2  0x0    /* ENET1_TXD3_SER1_TXD3 */
+                                0x0  0x6  0x2  0x0  0x2  0x0    /* ENET1_RXD0_SER1_RXD0 */
+                                0x0  0xa  0x2  0x0  0x2  0x0    /* ENET1_RXD1_SER1_RXD1 */
+                                0x0  0xe  0x2  0x0  0x2  0x0    /* ENET1_RXD2_SER1_RXD2 */
+                                0x0  0xf  0x2  0x0  0x2  0x0    /* ENET1_RXD3_SER1_RXD3 */
+                                0x0  0x5  0x1  0x0  0x2  0x0    /* ENET1_TX_EN_SER1_RTS_B */
+                                0x0  0xd  0x1  0x0  0x2  0x0    /* ENET1_TX_ER */
+                                0x0  0x4  0x2  0x0  0x2  0x0    /* ENET1_RX_DV_SER1_CTS_B */
+                                0x0  0x8  0x2  0x0  0x2  0x0    /* ENET1_RX_ER_SER1_CD_B */
+                                0x0  0x11 0x2  0x0  0x2  0x0    /* ENET1_CRS */
+                                0x0  0x10 0x2  0x0  0x2  0x0>;    /* ENET1_COL */
+                };
+
+                pio2: ucc_pin@02 {
+                        pio-map = <
+                /* port  pin  dir  open_drain  assignment  has_irq */
+                                0x1  0x13 0x1  0x0  0x1  0x0    /* QE_MUX_MDC */
+                                0x1  0x14 0x3  0x0  0x1  0x0    /* QE_MUX_MDIO */
+                                0x1  0xb  0x2  0x0  0x1  0x0    /* CLK13 */
+                                0x1  0x7  0x1  0x0  0x2  0x0    /* ENET5_TXD0_SER5_TXD0 */
+                                0x1  0xa  0x1  0x0  0x2  0x0    /* ENET5_TXD1_SER5_TXD1 */
+                                0x1  0x6  0x2  0x0  0x2  0x0    /* ENET5_RXD0_SER5_RXD0 */
+                                0x1  0x9  0x2  0x0  0x2  0x0    /* ENET5_RXD1_SER5_RXD1 */
+                                0x1  0x5  0x1  0x0  0x2  0x0    /* ENET5_TX_EN_SER5_RTS_B */
+                                0x1  0x4  0x2  0x0  0x2  0x0    /* ENET5_RX_DV_SER5_CTS_B */
+                                0x1  0x8  0x2  0x0  0x2  0x0>;    /* ENET5_RX_ER_SER5_CD_B */
+                };
+        };
+};
diff --git a/arch/powerpc/boot/dts/p1025rdb_32b.dts b/arch/powerpc/boot/dts/p1025rdb_32b.dts
new file mode 100644
index 000000000000..ac5729c14eda
--- /dev/null
+++ b/arch/powerpc/boot/dts/p1025rdb_32b.dts
@@ -0,0 +1,135 @@
+/*
+ * P1025 RDB Device Tree Source (32-bit address map)
+ *
+ * Copyright 2011 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in the
+ *       documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Freescale Semiconductor nor the
+ *       names of its contributors may be used to endorse or promote products
+ *       derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+/include/ "fsl/p1021si-pre.dtsi"
+/ {
+        model = "fsl,P1025RDB";
+        compatible = "fsl,P1025RDB";
+
+        memory {
+                device_type = "memory";
+        };
+
+        lbc: localbus@ffe05000 {
+                reg = <0 0xffe05000 0 0x1000>;
+
+                /* NOR, NAND Flashes */
+                ranges = <0x0 0x0 0x0 0xef000000 0x01000000
+                          0x1 0x0 0x0 0xff800000 0x00040000>;
+        };
+
+        soc: soc@ffe00000 {
+                ranges = <0x0 0x0 0xffe00000 0x100000>;
+        };
+
+        pci0: pcie@ffe09000 {
+                ranges = <0x2000000 0x0 0xe0000000 0 0xe0000000 0x0 0x20000000
+                          0x1000000 0x0 0x00000000 0 0xffc10000 0x0 0x10000>;
+                reg = <0 0xffe09000 0 0x1000>;
+                pcie@0 {
+                        ranges = <0x2000000 0x0 0xe0000000
+                                  0x2000000 0x0 0xe0000000
+                                  0x0 0x20000000
+
+                                  0x1000000 0x0 0x0
+                                  0x1000000 0x0 0x0
+                                  0x0 0x100000>;
+                };
+        };
+
+        pci1: pcie@ffe0a000 {
+                reg = <0 0xffe0a000 0 0x1000>;
+                ranges = <0x2000000 0x0 0xe0000000 0 0xe0000000 0x0 0x20000000
+                          0x1000000 0x0 0x00000000 0 0xffc00000 0x0 0x10000>;
+                pcie@0 {
+                        ranges = <0x2000000 0x0 0xe0000000
+                                  0x2000000 0x0 0xe0000000
+                                  0x0 0x20000000
+
+                                  0x1000000 0x0 0x0
+                                  0x1000000 0x0 0x0
+                                  0x0 0x100000>;
+                };
+        };
+
+        qe: qe@ffe80000 {
+                ranges = <0x0 0x0 0xffe80000 0x40000>;
+                reg = <0 0xffe80000 0 0x480>;
+                brg-frequency = <0>;
+                bus-frequency = <0>;
+                status = "disabled"; /* no firmware loaded */
+
+                enet3: ucc@2000 {
+                        device_type = "network";
+                        compatible = "ucc_geth";
+                        rx-clock-name = "clk12";
+                        tx-clock-name = "clk9";
+                        pio-handle = <&pio1>;
+                        phy-handle = <&qe_phy0>;
+                        phy-connection-type = "mii";
+                };
+
+                mdio@2120 {
+                        qe_phy0: ethernet-phy@0 {
+                                interrupt-parent = <&mpic>;
+                                interrupts = <4 1 0 0>;
+                                reg = <0x6>;
+                                device_type = "ethernet-phy";
+                        };
+                        qe_phy1: ethernet-phy@03 {
+                                interrupt-parent = <&mpic>;
+                                interrupts = <5 1 0 0>;
+                                reg = <0x3>;
+                                device_type = "ethernet-phy";
+                        };
+                        tbi-phy@11 {
+                                reg = <0x11>;
+                                device_type = "tbi-phy";
+                        };
+                };
+
+                enet4: ucc@2400 {
+                        device_type = "network";
+                        compatible = "ucc_geth";
+                        rx-clock-name = "none";
+                        tx-clock-name = "clk13";
+                        pio-handle = <&pio2>;
+                        phy-handle = <&qe_phy1>;
+                        phy-connection-type = "rmii";
+                };
+        };
+};
+
+/include/ "p1025rdb.dtsi"
+/include/ "fsl/p1021si-post.dtsi"
diff --git a/arch/powerpc/boot/dts/p1025rdb_36b.dts b/arch/powerpc/boot/dts/p1025rdb_36b.dts
new file mode 100644
index 000000000000..4ce4bfa0eda4
--- /dev/null
+++ b/arch/powerpc/boot/dts/p1025rdb_36b.dts
@@ -0,0 +1,88 @@
+/*
+ * P1025 RDB Device Tree Source (36-bit address map)
+ *
+ * Copyright 2011 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in the
+ *       documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Freescale Semiconductor nor the
+ *       names of its contributors may be used to endorse or promote products
+ *       derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+/include/ "fsl/p1021si-pre.dtsi"
+/ {
+        model = "fsl,P1025RDB";
+        compatible = "fsl,P1025RDB";
+
+        memory {
+                device_type = "memory";
+        };
+
+        lbc: localbus@fffe05000 {
+                reg = <0xf 0xffe05000 0 0x1000>;
+
+                /* NOR, NAND Flashes */
+                ranges = <0x0 0x0 0xf 0xef000000 0x01000000
+                          0x1 0x0 0xf 0xff800000 0x00040000>;
+        };
+
+        soc: soc@fffe00000 {
+                ranges = <0x0 0xf 0xffe00000 0x100000>;
+        };
+
+        pci0: pcie@fffe09000 {
+                reg = <0xf 0xffe09000 0 0x1000>;
+                ranges = <0x2000000 0x0 0xe0000000 0xe 0x20000000 0x0 0x20000000
+                          0x1000000 0x0 0x00000000 0xf 0xffc10000 0x0 0x10000>;
+                pcie@0 {
+                        ranges = <0x2000000 0x0 0xe0000000
+                                  0x2000000 0x0 0xe0000000
+                                  0x0 0x20000000
+
+                                  0x1000000 0x0 0x0
+                                  0x1000000 0x0 0x0
+                                  0x0 0x100000>;
+                };
+        };
+
+        pci1: pcie@fffe0a000 {
+                reg = <0xf 0xffe0a000 0 0x1000>;
+                ranges = <0x2000000 0x0 0xe0000000 0xc 0x00000000 0x0 0x20000000
+                          0x1000000 0x0 0x00000000 0xf 0xffc00000 0x0 0x10000>;
+                pcie@0 {
+                        ranges = <0x2000000 0x0 0xe0000000
+                                  0x2000000 0x0 0xe0000000
+                                  0x0 0x20000000
+
+                                  0x1000000 0x0 0x0
+                                  0x1000000 0x0 0x0
+                                  0x0 0x100000>;
+                };
+        };
+};
+
+/include/ "p1025rdb.dtsi"
+/include/ "fsl/p1021si-post.dtsi"
diff --git a/arch/powerpc/boot/dts/p2020ds.dtsi b/arch/powerpc/boot/dts/p2020ds.dtsi
index c1cf6cef4dd6..d3b939c573b0 100644
--- a/arch/powerpc/boot/dts/p2020ds.dtsi
+++ b/arch/powerpc/boot/dts/p2020ds.dtsi
@@ -1,7 +1,7 @@
 /*
  * P2020DS Device Tree Source stub (no addresses or top-level ranges)
  *
- * Copyright 2011 Freescale Semiconductor Inc.
+ * Copyright 2011-2012 Freescale Semiconductor Inc.
  *
  * Redistribution and use in source and binary forms, with or without
  * modification, are permitted provided that the following conditions are met:
@@ -134,6 +134,7 @@
 &board_soc {
         usb@22000 {
                 phy_type = "ulpi";
+                dr_mode = "host";
         };
 
         mdio@24520 {
diff --git a/arch/powerpc/boot/dts/p2020rdb-pc.dtsi b/arch/powerpc/boot/dts/p2020rdb-pc.dtsi
new file mode 100644
index 000000000000..c21d1c7d16cd
--- /dev/null
+++ b/arch/powerpc/boot/dts/p2020rdb-pc.dtsi
@@ -0,0 +1,241 @@
+/*
+ * P2020 RDB-PC Device Tree Source stub (no addresses or top-level ranges)
+ *
+ * Copyright 2011 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in the
+ *       documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Freescale Semiconductor nor the
+ *       names of its contributors may be used to endorse or promote products
+ *       derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+&lbc {
+        nor@0,0 {
+                #address-cells = <1>;
+                #size-cells = <1>;
+                compatible = "cfi-flash";
+                reg = <0x0 0x0 0x1000000>;
+                bank-width = <2>;
+                device-width = <1>;
+
+                partition@0 {
+                        /* This location must not be altered  */
+                        /* 256KB for Vitesse 7385 Switch firmware */
+                        reg = <0x0 0x00040000>;
+                        label = "NOR Vitesse-7385 Firmware";
+                        read-only;
+                };
+
+                partition@40000 {
+                        /* 256KB for DTB Image */
+                        reg = <0x00040000 0x00040000>;
+                        label = "NOR DTB Image";
+                };
+
+                partition@80000 {
+                        /* 3.5 MB for Linux Kernel Image */
+                        reg = <0x00080000 0x00380000>;
+                        label = "NOR Linux Kernel Image";
+                };
+
+                partition@400000 {
+                        /* 11MB for JFFS2 based Root file System */
+                        reg = <0x00400000 0x00b00000>;
+                        label = "NOR JFFS2 Root File System";
+                };
+
+                partition@f00000 {
+                        /* This location must not be altered  */
+                        /* 512KB for u-boot Bootloader Image */
+                        /* 512KB for u-boot Environment Variables */
+                        reg = <0x00f00000 0x00100000>;
+                        label = "NOR U-Boot Image";
+                        read-only;
+                };
+        };
+
+        nand@1,0 {
+                #address-cells = <1>;
+                #size-cells = <1>;
+                compatible = "fsl,p2020-fcm-nand",
+                                 "fsl,elbc-fcm-nand";
+                reg = <0x1 0x0 0x40000>;
+
+                partition@0 {
+                        /* This location must not be altered  */
+                        /* 1MB for u-boot Bootloader Image */
+                        reg = <0x0 0x00100000>;
+                        label = "NAND U-Boot Image";
+                        read-only;
+                };
+
+                partition@100000 {
+                        /* 1MB for DTB Image */
+                        reg = <0x00100000 0x00100000>;
+                        label = "NAND DTB Image";
+                };
+
+                partition@200000 {
+                        /* 4MB for Linux Kernel Image */
+                        reg = <0x00200000 0x00400000>;
+                        label = "NAND Linux Kernel Image";
+                };
+
+                partition@600000 {
+                        /* 4MB for Compressed Root file System Image */
+                        reg = <0x00600000 0x00400000>;
+                        label = "NAND Compressed RFS Image";
+                };
+
+                partition@a00000 {
+                        /* 7MB for JFFS2 based Root file System */
+                        reg = <0x00a00000 0x00700000>;
+                        label = "NAND JFFS2 Root File System";
+                };
+
+                partition@1100000 {
+                        /* 15MB for JFFS2 based Root file System */
+                        reg = <0x01100000 0x00f00000>;
+                        label = "NAND Writable User area";
+                };
+        };
+
+        L2switch@2,0 {
+                #address-cells = <1>;
+                #size-cells = <1>;
+                compatible = "vitesse-7385";
+                reg = <0x2 0x0 0x20000>;
+        };
+
+        cpld@3,0 {
+                #address-cells = <1>;
+                #size-cells = <1>;
+                compatible = "cpld";
+                reg = <0x3 0x0 0x20000>;
+                read-only;
+        };
+};
+
+&soc {
+        i2c@3000 {
+                rtc@68 {
+                        compatible = "pericom,pt7c4338";
+                        reg = <0x68>;
+                };
+        };
+
+        spi@7000 {
+                flash@0 {
+                        #address-cells = <1>;
+                        #size-cells = <1>;
+                        compatible = "spansion,m25p80";
+                        reg = <0>;
+                        spi-max-frequency = <40000000>;
+
+                        partition@0 {
+                                /* 512KB for u-boot Bootloader Image */
+                                reg = <0x0 0x00080000>;
+                                label = "SPI U-Boot Image";
+                                read-only;
+                        };
+
+                        partition@80000 {
+                                /* 512KB for DTB Image */
+                                reg = <0x00080000 0x00080000>;
+                                label = "SPI DTB Image";
+                        };
+
+                        partition@100000 {
+                                /* 4MB for Linux Kernel Image */
+                                reg = <0x00100000 0x00400000>;
+                                label = "SPI Linux Kernel Image";
+                        };
+
+                        partition@500000 {
+                                /* 4MB for Compressed RFS Image */
+                                reg = <0x00500000 0x00400000>;
+                                label = "SPI Compressed RFS Image";
+                        };
+
+                        partition@900000 {
+                                /* 7MB for JFFS2 based RFS */
+                                reg = <0x00900000 0x00700000>;
+                                label = "SPI JFFS2 RFS";
+                        };
+                };
+        };
+
+        usb@22000 {
+                phy_type = "ulpi";
+        };
+
+        mdio@24520 {
+                phy0: ethernet-phy@0 {
+                        interrupts = <3 1 0 0>;
+                        reg = <0x0>;
+                        };
+                phy1: ethernet-phy@1 {
+                        interrupts = <2 1 0 0>;
+                        reg = <0x1>;
+                        };
+        };
+
+        mdio@25520 {
+                tbi0: tbi-phy@11 {
+                        reg = <0x11>;
+                        device_type = "tbi-phy";
+                };
+        };
+
+        mdio@26520 {
+                status = "disabled";
+        };
+
+        ptp_clock@24e00 {
+                fsl,tclk-period = <5>;
+                fsl,tmr-prsc = <200>;
+                fsl,tmr-add = <0xCCCCCCCD>;
+                fsl,tmr-fiper1 = <0x3B9AC9FB>;
+                fsl,tmr-fiper2 = <0x0001869B>;
+                fsl,max-adj = <249999999>;
+        };
+
+        enet0: ethernet@24000 {
+                fixed-link = <1 1 1000 0 0>;
+                phy-connection-type = "rgmii-id";
+        };
+
+        enet1: ethernet@25000 {
+                tbi-handle = <&tbi0>;
+                phy-handle = <&phy0>;
+                phy-connection-type = "sgmii";
+        };
+
+        enet2: ethernet@26000 {
+                phy-handle = <&phy1>;
+                phy-connection-type = "rgmii-id";
+        };
+};
diff --git a/arch/powerpc/boot/dts/p2020rdb-pc_32b.dts b/arch/powerpc/boot/dts/p2020rdb-pc_32b.dts
new file mode 100644
index 000000000000..852e5b27485d
--- /dev/null
+++ b/arch/powerpc/boot/dts/p2020rdb-pc_32b.dts
@@ -0,0 +1,96 @@
+/*
+ * P2020 RDB-PC 32Bit Physical Address Map Device Tree Source
+ *
+ * Copyright 2011 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in the
+ *       documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Freescale Semiconductor nor the
+ *       names of its contributors may be used to endorse or promote products
+ *       derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+/include/ "fsl/p2020si-pre.dtsi"
+
+/ {
+        model = "fsl,P2020RDB";
+        compatible = "fsl,P2020RDB-PC";
+
+        memory {
+                device_type = "memory";
+        };
+
+        lbc: localbus@ffe05000 {
+                reg = <0 0xffe05000 0 0x1000>;
+
+                /* NOR and NAND Flashes */
+                ranges = <0x0 0x0 0x0 0xef000000 0x01000000
+                          0x1 0x0 0x0 0xff800000 0x00040000
+                          0x2 0x0 0x0 0xffb00000 0x00020000
+                          0x3 0x0 0x0 0xffa00000 0x00020000>;
+        };
+
+        soc: soc@ffe00000 {
+                ranges = <0x0 0x0 0xffe00000 0x100000>;
+        };
+
+        pci0: pcie@ffe08000 {
+                reg = <0 0xffe08000 0 0x1000>;
+                status = "disabled";
+        };
+
+        pci1: pcie@ffe09000 {
+                reg = <0 0xffe09000 0 0x1000>;
+                ranges = <0x2000000 0x0 0xe0000000 0 0xa0000000 0x0 0x20000000
+                          0x1000000 0x0 0x00000000 0 0xffc10000 0x0 0x10000>;
+                pcie@0 {
+                        ranges = <0x2000000 0x0 0xe0000000
+                                  0x2000000 0x0 0xe0000000
+                                  0x0 0x20000000
+
+                                  0x1000000 0x0 0x0
+                                  0x1000000 0x0 0x0
+                                  0x0 0x100000>;
+                };
+        };
+
+        pci2: pcie@ffe0a000 {
+                reg = <0 0xffe0a000 0 0x1000>;
+                ranges = <0x2000000 0x0 0xe0000000 0 0x80000000 0x0 0x20000000
+                          0x1000000 0x0 0x00000000 0 0xffc00000 0x0 0x10000>;
+                pcie@0 {
+                        ranges = <0x2000000 0x0 0xe0000000
+                                  0x2000000 0x0 0xe0000000
+                                  0x0 0x20000000
+
+                                  0x1000000 0x0 0x0
+                                  0x1000000 0x0 0x0
+                                  0x0 0x100000>;
+                };
+        };
+};
+
+/include/ "p2020rdb-pc.dtsi"
+/include/ "fsl/p2020si-post.dtsi"
diff --git a/arch/powerpc/boot/dts/p2020rdb-pc_36b.dts b/arch/powerpc/boot/dts/p2020rdb-pc_36b.dts
new file mode 100644
index 000000000000..b5a56ca51cf7
--- /dev/null
+++ b/arch/powerpc/boot/dts/p2020rdb-pc_36b.dts
@@ -0,0 +1,96 @@
+/*
+ * P2020 RDB-PC 36Bit Physical Address Map Device Tree Source
+ *
+ * Copyright 2011 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in the
+ *       documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Freescale Semiconductor nor the
+ *       names of its contributors may be used to endorse or promote products
+ *       derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+/include/ "fsl/p2020si-pre.dtsi"
+
+/ {
+        model = "fsl,P2020RDB";
+        compatible = "fsl,P2020RDB-PC";
+
+        memory {
+                device_type = "memory";
+        };
+
+        lbc: localbus@fffe05000 {
+                reg = <0xf 0xffe05000 0 0x1000>;
+
+                /* NOR and NAND Flashes */
+                ranges = <0x0 0x0 0xf 0xef000000 0x01000000
+                          0x1 0x0 0xf 0xff800000 0x00040000
+                          0x2 0x0 0xf 0xffb00000 0x00020000
+                          0x3 0x0 0xf 0xffa00000 0x00020000>;
+        };
+
+        soc: soc@fffe00000 {
+                ranges = <0x0 0xf 0xffe00000 0x100000>;
+        };
+
+        pci0: pcie@fffe08000 {
+                reg = <0xf 0xffe08000 0 0x1000>;
+                status = "disabled";
+        };
+
+        pci1: pcie@fffe09000 {
+                reg = <0xf 0xffe09000 0 0x1000>;
+                ranges = <0x2000000 0x0 0xe0000000 0xc 0x20000000 0x0 0x20000000
+                          0x1000000 0x0 0x00000000 0xf 0xffc10000 0x0 0x10000>;
+                pcie@0 {
+                        ranges = <0x2000000 0x0 0xe0000000
+                                  0x2000000 0x0 0xe0000000
+                                  0x0 0x20000000
+
+                                  0x1000000 0x0 0x0
+                                  0x1000000 0x0 0x0
+                                  0x0 0x100000>;
+                };
+        };
+
+        pci2: pcie@fffe0a000 {
+                reg = <0xf 0xffe0a000 0 0x1000>;
+                ranges = <0x2000000 0x0 0xe0000000 0xc 0x00000000 0x0 0x20000000
+                          0x1000000 0x0 0x00000000 0xf 0xffc00000 0x0 0x10000>;
+                pcie@0 {
+                        ranges = <0x2000000 0x0 0xe0000000
+                                  0x2000000 0x0 0xe0000000
+                                  0x0 0x20000000
+
+                                  0x1000000 0x0 0x0
+                                  0x1000000 0x0 0x0
+                                  0x0 0x100000>;
+                };
+        };
+};
+
+/include/ "p2020rdb-pc.dtsi"
+/include/ "fsl/p2020si-post.dtsi"
diff --git a/arch/powerpc/boot/dts/p2020rdb.dts b/arch/powerpc/boot/dts/p2020rdb.dts
index 26759a591712..153bc76bb48e 100644
--- a/arch/powerpc/boot/dts/p2020rdb.dts
+++ b/arch/powerpc/boot/dts/p2020rdb.dts
@@ -1,7 +1,7 @@
 /*
  * P2020 RDB Device Tree Source
  *
- * Copyright 2009-2011 Freescale Semiconductor Inc.
+ * Copyright 2009-2012 Freescale Semiconductor Inc.
  *
  * This program is free software; you can redistribute  it and/or modify it
  * under  the terms of  the GNU General  Public License as published by the
@@ -34,7 +34,7 @@
 
                 /* NOR and NAND Flashes */
                 ranges = <0x0 0x0 0x0 0xef000000 0x01000000
-                          0x1 0x0 0x0 0xffa00000 0x00040000
+                          0x1 0x0 0x0 0xff800000 0x00040000
                           0x2 0x0 0x0 0xffb00000 0x00020000>;
 
                 nor@0,0 {
@@ -157,7 +157,7 @@
                                 #size-cells = <1>;
                                 compatible = "spansion,s25sl12801";
                                 reg = <0>;
-                                spi-max-frequency = <50000000>;
+                                spi-max-frequency = <40000000>;
 
                                 partition@0 {
                                         /* 512KB for u-boot Bootloader Image */
@@ -197,6 +197,7 @@
 
                 usb@22000 {
                         phy_type = "ulpi";
+                        dr_mode = "host";
                 };
 
                 mdio@24520 {
diff --git a/arch/powerpc/boot/wrapper b/arch/powerpc/boot/wrapper
index f090e6d2907e..6761c746048d 100755
--- a/arch/powerpc/boot/wrapper
+++ b/arch/powerpc/boot/wrapper
@@ -144,6 +144,7 @@ tmp=$tmpdir/zImage.$$.o
 ksection=.kernel:vmlinux.strip
 isection=.kernel:initrd
 link_address='0x400000'
+make_space=y
 
 case "$platform" in
 pseries)
@@ -210,6 +211,7 @@ ps3)
     ksection=.kernel:vmlinux.bin
     isection=.kernel:initrd
     link_address=''
+    make_space=n
     pie=
     ;;
 ep88xc|ep405|ep8248e)
@@ -278,17 +280,19 @@ else
     rm -f $vmz.$$
 fi
 
-# Round the size to next higher MB limit
-round_size=$(((strip_size + 0xfffff) & 0xfff00000))
+if [ "$make_space" = "y" ]; then
+        # Round the size to next higher MB limit
+        round_size=$(((strip_size + 0xfffff) & 0xfff00000))
 
-round_size=0x$(printf "%x" $round_size)
-link_addr=$(printf "%d" $link_address)
+        round_size=0x$(printf "%x" $round_size)
+        link_addr=$(printf "%d" $link_address)
 
-if [ $link_addr -lt $strip_size ]; then
-    echo "INFO: Uncompressed kernel (size 0x$(printf "%x\n" $strip_size))" \
-                "overlaps the address of the wrapper($link_address)"
-    echo "INFO: Fixing the link_address of wrapper to ($round_size)"
-    link_address=$round_size
+        if [ $link_addr -lt $strip_size ]; then
+            echo "INFO: Uncompressed kernel (size 0x$(printf "%x\n" $strip_size))" \
+                        "overlaps the address of the wrapper($link_address)"
+            echo "INFO: Fixing the link_address of wrapper to ($round_size)"
+            link_address=$round_size
+        fi
 fi
 
 vmz="$vmz$gzip"
diff --git a/arch/powerpc/configs/85xx/ge_imp3a_defconfig b/arch/powerpc/configs/85xx/ge_imp3a_defconfig
new file mode 100644
index 000000000000..f8c51a4ab995
--- /dev/null
+++ b/arch/powerpc/configs/85xx/ge_imp3a_defconfig
@@ -0,0 +1,257 @@
+CONFIG_PPC_85xx=y
+CONFIG_SMP=y
+CONFIG_NR_CPUS=2
+CONFIG_EXPERIMENTAL=y
+CONFIG_SYSVIPC=y
+CONFIG_POSIX_MQUEUE=y
+CONFIG_BSD_PROCESS_ACCT=y
+CONFIG_BSD_PROCESS_ACCT_V3=y
+CONFIG_SPARSE_IRQ=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+# CONFIG_UTS_NS is not set
+# CONFIG_IPC_NS is not set
+# CONFIG_USER_NS is not set
+# CONFIG_PID_NS is not set
+# CONFIG_NET_NS is not set
+CONFIG_SYSFS_DEPRECATED=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+CONFIG_RELAY=y
+CONFIG_BLK_DEV_INITRD=y
+CONFIG_PERF_EVENTS=y
+CONFIG_SLAB=y
+CONFIG_MODULES=y
+CONFIG_MODULE_UNLOAD=y
+# CONFIG_BLK_DEV_BSG is not set
+CONFIG_GE_IMP3A=y
+CONFIG_QUICC_ENGINE=y
+CONFIG_QE_GPIO=y
+CONFIG_CPM2=y
+CONFIG_HIGHMEM=y
+CONFIG_HIGH_RES_TIMERS=y
+CONFIG_HZ_1000=y
+CONFIG_PREEMPT=y
+# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
+CONFIG_BINFMT_MISC=m
+CONFIG_MATH_EMULATION=y
+CONFIG_IRQ_ALL_CPUS=y
+CONFIG_FORCE_MAX_ZONEORDER=17
+CONFIG_PCI=y
+CONFIG_PCIEPORTBUS=y
+CONFIG_PCI_MSI=y
+CONFIG_PCCARD=y
+# CONFIG_PCMCIA_LOAD_CIS is not set
+CONFIG_YENTA=y
+CONFIG_NET=y
+CONFIG_PACKET=y
+CONFIG_UNIX=y
+CONFIG_XFRM_USER=m
+CONFIG_NET_KEY=y
+CONFIG_INET=y
+CONFIG_IP_MULTICAST=y
+CONFIG_IP_ADVANCED_ROUTER=y
+CONFIG_IP_MULTIPLE_TABLES=y
+CONFIG_IP_ROUTE_MULTIPATH=y
+CONFIG_IP_ROUTE_VERBOSE=y
+CONFIG_IP_PNP=y
+CONFIG_IP_PNP_DHCP=y
+CONFIG_IP_PNP_BOOTP=y
+CONFIG_IP_PNP_RARP=y
+CONFIG_NET_IPIP=m
+CONFIG_IP_MROUTE=y
+CONFIG_IP_PIMSM_V1=y
+CONFIG_IP_PIMSM_V2=y
+CONFIG_SYN_COOKIES=y
+CONFIG_INET_AH=m
+CONFIG_INET_ESP=m
+CONFIG_INET_IPCOMP=m
+# CONFIG_INET_XFRM_MODE_BEET is not set
+CONFIG_INET6_AH=m
+CONFIG_INET6_IPCOMP=m
+CONFIG_IPV6_TUNNEL=m
+CONFIG_NET_PKTGEN=m
+CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
+CONFIG_MTD=y
+CONFIG_MTD_OF_PARTS=y
+CONFIG_MTD_CHAR=y
+CONFIG_MTD_BLOCK=y
+CONFIG_MTD_CFI=y
+CONFIG_MTD_JEDECPROBE=y
+CONFIG_MTD_CFI_INTELEXT=y
+CONFIG_MTD_CFI_AMDSTD=y
+CONFIG_MTD_PHYSMAP_OF=y
+CONFIG_MTD_NAND=y
+CONFIG_MTD_NAND_FSL_ELBC=y
+CONFIG_PROC_DEVICETREE=y
+CONFIG_BLK_DEV_LOOP=m
+CONFIG_BLK_DEV_CRYPTOLOOP=m
+CONFIG_BLK_DEV_NBD=m
+CONFIG_BLK_DEV_RAM=y
+CONFIG_BLK_DEV_RAM_SIZE=131072
+CONFIG_MISC_DEVICES=y
+CONFIG_DS1682=y
+CONFIG_BLK_DEV_SD=y
+CONFIG_CHR_DEV_ST=y
+CONFIG_BLK_DEV_SR=y
+CONFIG_ATA=y
+CONFIG_SATA_AHCI=y
+CONFIG_SATA_SIL24=y
+# CONFIG_ATA_SFF is not set
+CONFIG_NETDEVICES=y
+CONFIG_BONDING=m
+CONFIG_DUMMY=m
+CONFIG_NETCONSOLE=y
+CONFIG_NETPOLL_TRAP=y
+CONFIG_TUN=m
+# CONFIG_NET_VENDOR_3COM is not set
+CONFIG_FS_ENET=y
+CONFIG_UCC_GETH=y
+CONFIG_GIANFAR=y
+CONFIG_PPP=m
+CONFIG_PPP_BSDCOMP=m
+CONFIG_PPP_DEFLATE=m
+CONFIG_PPP_FILTER=y
+CONFIG_PPP_MULTILINK=y
+CONFIG_PPPOE=m
+CONFIG_PPP_ASYNC=m
+CONFIG_PPP_SYNC_TTY=m
+CONFIG_SLIP=m
+CONFIG_SLIP_COMPRESSED=y
+CONFIG_SLIP_SMART=y
+CONFIG_SLIP_MODE_SLIP6=y
+# CONFIG_INPUT_KEYBOARD is not set
+# CONFIG_INPUT_MOUSE is not set
+# CONFIG_SERIO is not set
+# CONFIG_LEGACY_PTYS is not set
+CONFIG_SERIAL_8250=y
+CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_SERIAL_8250_NR_UARTS=2
+CONFIG_SERIAL_8250_RUNTIME_UARTS=2
+CONFIG_SERIAL_8250_EXTENDED=y
+CONFIG_SERIAL_8250_MANY_PORTS=y
+CONFIG_SERIAL_8250_DETECT_IRQ=y
+CONFIG_SERIAL_8250_RSA=y
+CONFIG_SERIAL_QE=m
+CONFIG_NVRAM=y
+CONFIG_I2C=y
+CONFIG_I2C_CHARDEV=y
+CONFIG_I2C_CPM=m
+CONFIG_I2C_MPC=y
+CONFIG_GPIO_SYSFS=y
+CONFIG_GPIO_GE_FPGA=y
+CONFIG_SENSORS_LM90=y
+CONFIG_SENSORS_LM92=y
+CONFIG_WATCHDOG=y
+CONFIG_GEF_WDT=y
+CONFIG_VIDEO_OUTPUT_CONTROL=m
+CONFIG_HID_DRAGONRISE=y
+CONFIG_HID_GYRATION=y
+CONFIG_HID_TWINHAN=y
+CONFIG_HID_ORTEK=y
+CONFIG_HID_PANTHERLORD=y
+CONFIG_HID_PETALYNX=y
+CONFIG_HID_SAMSUNG=y
+CONFIG_HID_SONY=y
+CONFIG_HID_SUNPLUS=y
+CONFIG_HID_GREENASIA=y
+CONFIG_HID_SMARTJOYPLUS=y
+CONFIG_HID_TOPSEED=y
+CONFIG_HID_THRUSTMASTER=y
+CONFIG_HID_ZEROPLUS=y
+CONFIG_USB=y
+CONFIG_USB_DEVICEFS=y
+CONFIG_USB_EHCI_HCD=y
+# CONFIG_USB_EHCI_TT_NEWSCHED is not set
+CONFIG_USB_EHCI_FSL=y
+CONFIG_USB_OHCI_HCD=y
+CONFIG_USB_OHCI_HCD_PPC_OF_BE=y
+CONFIG_USB_OHCI_HCD_PPC_OF_LE=y
+CONFIG_USB_STORAGE=y
+CONFIG_EDAC=y
+CONFIG_EDAC_MM_EDAC=y
+CONFIG_EDAC_MPC85XX=y
+CONFIG_RTC_CLASS=y
+# CONFIG_RTC_INTF_PROC is not set
+CONFIG_RTC_DRV_RX8581=y
+CONFIG_DMADEVICES=y
+CONFIG_FSL_DMA=y
+# CONFIG_NET_DMA is not set
+CONFIG_EXT2_FS=y
+CONFIG_EXT2_FS_XATTR=y
+CONFIG_EXT2_FS_POSIX_ACL=y
+CONFIG_EXT3_FS=y
+# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
+CONFIG_EXT3_FS_POSIX_ACL=y
+CONFIG_EXT4_FS=y
+CONFIG_FUSE_FS=y
+CONFIG_ISO9660_FS=y
+CONFIG_JOLIET=y
+CONFIG_ZISOFS=y
+CONFIG_UDF_FS=y
+CONFIG_MSDOS_FS=y
+CONFIG_VFAT_FS=y
+CONFIG_FAT_DEFAULT_CODEPAGE=850
+CONFIG_FAT_DEFAULT_IOCHARSET="ascii"
+CONFIG_NTFS_FS=y
+CONFIG_PROC_KCORE=y
+CONFIG_TMPFS=y
+CONFIG_JFFS2_FS=y
+CONFIG_NFS_FS=y
+CONFIG_NFS_V3=y
+CONFIG_NFS_V4=y
+CONFIG_ROOT_NFS=y
+CONFIG_NFSD=y
+CONFIG_NFSD_V4=y
+CONFIG_CIFS=m
+CONFIG_CIFS_XATTR=y
+CONFIG_CIFS_POSIX=y
+CONFIG_NLS_CODEPAGE_437=y
+CONFIG_NLS_CODEPAGE_737=m
+CONFIG_NLS_CODEPAGE_775=m
+CONFIG_NLS_CODEPAGE_850=y
+CONFIG_NLS_CODEPAGE_852=m
+CONFIG_NLS_CODEPAGE_855=m
+CONFIG_NLS_CODEPAGE_857=m
+CONFIG_NLS_CODEPAGE_860=m
+CONFIG_NLS_CODEPAGE_861=m
+CONFIG_NLS_CODEPAGE_862=m
+CONFIG_NLS_CODEPAGE_863=m
+CONFIG_NLS_CODEPAGE_864=m
+CONFIG_NLS_CODEPAGE_865=m
+CONFIG_NLS_CODEPAGE_866=m
+CONFIG_NLS_CODEPAGE_869=m
+CONFIG_NLS_CODEPAGE_936=m
+CONFIG_NLS_CODEPAGE_950=m
+CONFIG_NLS_CODEPAGE_932=m
+CONFIG_NLS_CODEPAGE_949=m
+CONFIG_NLS_CODEPAGE_874=m
+CONFIG_NLS_ISO8859_8=m
+CONFIG_NLS_CODEPAGE_1250=m
+CONFIG_NLS_CODEPAGE_1251=m
+CONFIG_NLS_ASCII=y
+CONFIG_NLS_ISO8859_1=y
+CONFIG_NLS_ISO8859_2=m
+CONFIG_NLS_ISO8859_3=m
+CONFIG_NLS_ISO8859_4=m
+CONFIG_NLS_ISO8859_5=m
+CONFIG_NLS_ISO8859_6=m
+CONFIG_NLS_ISO8859_7=m
+CONFIG_NLS_ISO8859_9=m
+CONFIG_NLS_ISO8859_13=m
+CONFIG_NLS_ISO8859_14=m
+CONFIG_NLS_ISO8859_15=y
+CONFIG_NLS_KOI8_R=m
+CONFIG_NLS_KOI8_U=m
+CONFIG_NLS_UTF8=y
+CONFIG_CRC_CCITT=y
+CONFIG_CRC_T10DIF=y
+CONFIG_LIBCRC32C=y
+CONFIG_MAGIC_SYSRQ=y
+CONFIG_SYSCTL_SYSCALL_CHECK=y
+CONFIG_CRYPTO_CBC=y
+CONFIG_CRYPTO_MD5=y
+CONFIG_CRYPTO_SHA256=m
+CONFIG_CRYPTO_SHA512=m
+CONFIG_CRYPTO_DES=y
+# CONFIG_CRYPTO_ANSI_CPRNG is not set
+CONFIG_CRYPTO_DEV_TALITOS=y
diff --git a/arch/powerpc/configs/86xx/gef_ppc9a_defconfig b/arch/powerpc/configs/86xx/gef_ppc9a_defconfig
index d41857a5152d..da731c2fe984 100644
--- a/arch/powerpc/configs/86xx/gef_ppc9a_defconfig
+++ b/arch/powerpc/configs/86xx/gef_ppc9a_defconfig
@@ -131,6 +131,7 @@ CONFIG_I2C=y
 CONFIG_I2C_CHARDEV=y
 CONFIG_I2C_MPC=y
 CONFIG_GPIO_SYSFS=y
+CONFIG_GPIO_GE_FPGA=y
 CONFIG_SENSORS_LM90=y
 CONFIG_SENSORS_LM92=y
 CONFIG_WATCHDOG=y
diff --git a/arch/powerpc/configs/86xx/gef_sbc310_defconfig b/arch/powerpc/configs/86xx/gef_sbc310_defconfig
index 38303ec11bcd..2149360a1e62 100644
--- a/arch/powerpc/configs/86xx/gef_sbc310_defconfig
+++ b/arch/powerpc/configs/86xx/gef_sbc310_defconfig
@@ -132,6 +132,7 @@ CONFIG_I2C=y
 CONFIG_I2C_CHARDEV=y
 CONFIG_I2C_MPC=y
 CONFIG_GPIO_SYSFS=y
+CONFIG_GPIO_GE_FPGA=y
 CONFIG_SENSORS_LM90=y
 CONFIG_SENSORS_LM92=y
 CONFIG_WATCHDOG=y
diff --git a/arch/powerpc/configs/86xx/gef_sbc610_defconfig b/arch/powerpc/configs/86xx/gef_sbc610_defconfig
index 98533973d20f..af2e8e1edba6 100644
--- a/arch/powerpc/configs/86xx/gef_sbc610_defconfig
+++ b/arch/powerpc/configs/86xx/gef_sbc610_defconfig
@@ -183,6 +183,8 @@ CONFIG_NVRAM=y
 CONFIG_I2C=y
 CONFIG_I2C_CHARDEV=y
 CONFIG_I2C_MPC=y
+CONFIG_GPIO_SYSFS=y
+CONFIG_GPIO_GE_FPGA=y
 CONFIG_SENSORS_LM90=y
 CONFIG_SENSORS_LM92=y
 CONFIG_WATCHDOG=y
diff --git a/arch/powerpc/configs/iseries_defconfig b/arch/powerpc/configs/iseries_defconfig
deleted file mode 100644
index 27c46d679968..000000000000
--- a/arch/powerpc/configs/iseries_defconfig
+++ /dev/null
@@ -1,236 +0,0 @@
-CONFIG_PPC64=y
-CONFIG_SMP=y
-CONFIG_EXPERIMENTAL=y
-CONFIG_SYSVIPC=y
-CONFIG_POSIX_MQUEUE=y
-CONFIG_AUDIT=y
-CONFIG_AUDITSYSCALL=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_BLK_DEV_INITRD=y
-# CONFIG_COMPAT_BRK is not set
-CONFIG_MODULES=y
-CONFIG_MODULE_UNLOAD=y
-CONFIG_MODVERSIONS=y
-CONFIG_MODULE_SRCVERSION_ALL=y
-# CONFIG_PPC_PSERIES is not set
-CONFIG_LPARCFG=y
-CONFIG_PPC_ISERIES=y
-CONFIG_VIODASD=y
-CONFIG_VIOCD=m
-CONFIG_VIOTAPE=m
-# CONFIG_PPC_PMAC is not set
-CONFIG_NO_HZ=y
-CONFIG_HIGH_RES_TIMERS=y
-CONFIG_IRQ_ALL_CPUS=y
-# CONFIG_MIGRATION is not set
-CONFIG_PACKET=y
-CONFIG_UNIX=y
-CONFIG_XFRM_USER=m
-CONFIG_XFRM_SUB_POLICY=y
-CONFIG_NET_KEY=m
-CONFIG_INET=y
-CONFIG_IP_MULTICAST=y
-CONFIG_NET_IPIP=y
-CONFIG_SYN_COOKIES=y
-CONFIG_INET_AH=m
-CONFIG_INET_ESP=m
-CONFIG_INET_IPCOMP=m
-CONFIG_INET_XFRM_MODE_BEET=m
-# CONFIG_INET_LRO is not set
-# CONFIG_IPV6 is not set
-CONFIG_NETFILTER=y
-CONFIG_NETFILTER_NETLINK_QUEUE=m
-CONFIG_NETFILTER_NETLINK_LOG=m
-CONFIG_NF_CONNTRACK=m
-CONFIG_NF_CONNTRACK_EVENTS=y
-# CONFIG_NF_CT_PROTO_SCTP is not set
-CONFIG_NF_CONNTRACK_FTP=m
-CONFIG_NF_CONNTRACK_IRC=m
-CONFIG_NF_CONNTRACK_TFTP=m
-CONFIG_NF_CT_NETLINK=m
-CONFIG_NETFILTER_TPROXY=m
-CONFIG_NETFILTER_XT_TARGET_CLASSIFY=m
-CONFIG_NETFILTER_XT_TARGET_CONNMARK=m
-CONFIG_NETFILTER_XT_TARGET_DSCP=m
-CONFIG_NETFILTER_XT_TARGET_MARK=m
-CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m
-CONFIG_NETFILTER_XT_TARGET_TPROXY=m
-CONFIG_NETFILTER_XT_TARGET_TCPOPTSTRIP=m
-CONFIG_NETFILTER_XT_MATCH_COMMENT=m
-CONFIG_NETFILTER_XT_MATCH_CONNMARK=m
-CONFIG_NETFILTER_XT_MATCH_CONNTRACK=m
-CONFIG_NETFILTER_XT_MATCH_DSCP=m
-CONFIG_NETFILTER_XT_MATCH_IPRANGE=m
-CONFIG_NETFILTER_XT_MATCH_LENGTH=m
-CONFIG_NETFILTER_XT_MATCH_LIMIT=m
-CONFIG_NETFILTER_XT_MATCH_MAC=m
-CONFIG_NETFILTER_XT_MATCH_MARK=m
-CONFIG_NETFILTER_XT_MATCH_OWNER=m
-CONFIG_NETFILTER_XT_MATCH_PKTTYPE=m
-CONFIG_NETFILTER_XT_MATCH_RATEEST=m
-CONFIG_NETFILTER_XT_MATCH_REALM=m
-CONFIG_NETFILTER_XT_MATCH_RECENT=m
-CONFIG_NETFILTER_XT_MATCH_STRING=m
-CONFIG_NETFILTER_XT_MATCH_TCPMSS=m
-CONFIG_NETFILTER_XT_MATCH_TIME=m
-CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_IP_NF_QUEUE=m
-CONFIG_IP_NF_IPTABLES=m
-CONFIG_IP_NF_MATCH_ADDRTYPE=m
-CONFIG_IP_NF_MATCH_ECN=m
-CONFIG_IP_NF_MATCH_TTL=m
-CONFIG_IP_NF_FILTER=m
-CONFIG_IP_NF_TARGET_REJECT=m
-CONFIG_IP_NF_TARGET_LOG=m
-CONFIG_IP_NF_TARGET_ULOG=m
-CONFIG_NF_NAT=m
-CONFIG_IP_NF_TARGET_MASQUERADE=m
-CONFIG_IP_NF_TARGET_NETMAP=m
-CONFIG_IP_NF_TARGET_REDIRECT=m
-CONFIG_IP_NF_MANGLE=m
-CONFIG_IP_NF_TARGET_CLUSTERIP=m
-CONFIG_IP_NF_TARGET_ECN=m
-CONFIG_IP_NF_TARGET_TTL=m
-CONFIG_IP_NF_RAW=m
-CONFIG_IP_NF_ARPTABLES=m
-CONFIG_IP_NF_ARPFILTER=m
-CONFIG_IP_NF_ARP_MANGLE=m
-CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
-CONFIG_PROC_DEVICETREE=y
-CONFIG_BLK_DEV_LOOP=y
-CONFIG_BLK_DEV_NBD=m
-CONFIG_BLK_DEV_RAM=y
-CONFIG_BLK_DEV_RAM_SIZE=65536
-CONFIG_SCSI=y
-CONFIG_BLK_DEV_SD=y
-CONFIG_CHR_DEV_ST=y
-CONFIG_BLK_DEV_SR=y
-CONFIG_BLK_DEV_SR_VENDOR=y
-CONFIG_CHR_DEV_SG=y
-CONFIG_SCSI_MULTI_LUN=y
-CONFIG_SCSI_CONSTANTS=y
-CONFIG_SCSI_SPI_ATTRS=y
-CONFIG_SCSI_FC_ATTRS=y
-CONFIG_SCSI_SAS_LIBSAS=m
-CONFIG_SCSI_IBMVSCSI=m
-CONFIG_MD=y
-CONFIG_BLK_DEV_MD=y
-CONFIG_MD_LINEAR=y
-CONFIG_MD_RAID0=y
-CONFIG_MD_RAID1=y
-CONFIG_MD_RAID10=m
-CONFIG_MD_MULTIPATH=m
-CONFIG_MD_FAULTY=m
-CONFIG_BLK_DEV_DM=y
-CONFIG_DM_CRYPT=m
-CONFIG_DM_SNAPSHOT=m
-CONFIG_DM_MIRROR=m
-CONFIG_DM_ZERO=m
-CONFIG_NETDEVICES=y
-CONFIG_DUMMY=m
-CONFIG_BONDING=m
-CONFIG_TUN=m
-CONFIG_NET_ETHERNET=y
-CONFIG_NET_PCI=y
-CONFIG_PCNET32=y
-CONFIG_E100=y
-CONFIG_ACENIC=m
-CONFIG_E1000=m
-CONFIG_ISERIES_VETH=y
-CONFIG_PPP=m
-CONFIG_PPP_ASYNC=m
-CONFIG_PPP_SYNC_TTY=m
-CONFIG_PPP_DEFLATE=m
-CONFIG_PPP_BSDCOMP=m
-CONFIG_PPPOE=m
-CONFIG_NETCONSOLE=y
-CONFIG_NETPOLL_TRAP=y
-# CONFIG_INPUT_MOUSEDEV_PSAUX is not set
-# CONFIG_INPUT_KEYBOARD is not set
-# CONFIG_INPUT_MOUSE is not set
-# CONFIG_SERIO is not set
-CONFIG_SERIAL_ICOM=m
-# CONFIG_HW_RANDOM is not set
-CONFIG_GEN_RTC=y
-CONFIG_RAW_DRIVER=y
-# CONFIG_HWMON is not set
-# CONFIG_HID_SUPPORT is not set
-# CONFIG_USB_SUPPORT is not set
-CONFIG_EXT2_FS=y
-CONFIG_EXT2_FS_XATTR=y
-CONFIG_EXT2_FS_POSIX_ACL=y
-CONFIG_EXT2_FS_SECURITY=y
-CONFIG_EXT2_FS_XIP=y
-CONFIG_EXT3_FS=y
-CONFIG_EXT3_FS_POSIX_ACL=y
-CONFIG_EXT3_FS_SECURITY=y
-CONFIG_EXT4_FS=y
-CONFIG_REISERFS_FS=y
-CONFIG_REISERFS_FS_XATTR=y
-CONFIG_REISERFS_FS_POSIX_ACL=y
-CONFIG_REISERFS_FS_SECURITY=y
-CONFIG_JFS_FS=m
-CONFIG_JFS_POSIX_ACL=y
-CONFIG_JFS_SECURITY=y
-CONFIG_XFS_FS=m
-CONFIG_XFS_POSIX_ACL=y
-CONFIG_GFS2_FS=m
-CONFIG_AUTOFS_FS=m
-CONFIG_ISO9660_FS=y
-CONFIG_JOLIET=y
-CONFIG_ZISOFS=y
-CONFIG_UDF_FS=m
-CONFIG_MSDOS_FS=y
-CONFIG_VFAT_FS=y
-CONFIG_PROC_KCORE=y
-CONFIG_TMPFS=y
-CONFIG_TMPFS_POSIX_ACL=y
-CONFIG_CRAMFS=y
-CONFIG_NFS_FS=y
-CONFIG_NFS_V3=y
-CONFIG_NFS_V3_ACL=y
-CONFIG_NFS_V4=y
-CONFIG_NFSD=m
-CONFIG_NFSD_V3_ACL=y
-CONFIG_NFSD_V4=y
-CONFIG_RPCSEC_GSS_SPKM3=m
-CONFIG_CIFS=m
-CONFIG_CIFS_XATTR=y
-CONFIG_CIFS_POSIX=y
-CONFIG_NLS_CODEPAGE_437=y
-CONFIG_NLS_ASCII=y
-CONFIG_NLS_ISO8859_1=y
-CONFIG_DLM=m
-CONFIG_CRC_T10DIF=y
-CONFIG_MAGIC_SYSRQ=y
-CONFIG_DEBUG_FS=y
-CONFIG_DEBUG_KERNEL=y
-# CONFIG_RCU_CPU_STALL_DETECTOR is not set
-CONFIG_LATENCYTOP=y
-CONFIG_SYSCTL_SYSCALL_CHECK=y
-CONFIG_DEBUG_STACKOVERFLOW=y
-CONFIG_DEBUG_STACK_USAGE=y
-CONFIG_CRYPTO_NULL=m
-CONFIG_CRYPTO_TEST=m
-CONFIG_CRYPTO_ECB=m
-CONFIG_CRYPTO_PCBC=m
-CONFIG_CRYPTO_HMAC=y
-CONFIG_CRYPTO_MD4=m
-CONFIG_CRYPTO_MICHAEL_MIC=m
-CONFIG_CRYPTO_SHA256=m
-CONFIG_CRYPTO_SHA512=m
-CONFIG_CRYPTO_TGR192=m
-CONFIG_CRYPTO_WP512=m
-CONFIG_CRYPTO_AES=m
-CONFIG_CRYPTO_ANUBIS=m
-CONFIG_CRYPTO_ARC4=m
-CONFIG_CRYPTO_BLOWFISH=m
-CONFIG_CRYPTO_CAST6=m
-CONFIG_CRYPTO_KHAZAD=m
-CONFIG_CRYPTO_SEED=m
-CONFIG_CRYPTO_SERPENT=m
-CONFIG_CRYPTO_TEA=m
-CONFIG_CRYPTO_TWOFISH=m
-# 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 2a1320fb2723..6640a35bebb7 100644
--- a/arch/powerpc/configs/mpc5200_defconfig
+++ b/arch/powerpc/configs/mpc5200_defconfig
@@ -1,8 +1,8 @@
 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_MODULES=y
 CONFIG_MODULE_UNLOAD=y
 # CONFIG_BLK_DEV_BSG is not set
@@ -13,15 +13,12 @@ CONFIG_PPC_EFIKA=y
 CONFIG_PPC_LITE5200=y
 CONFIG_PPC_MEDIA5200=y
 CONFIG_PPC_MPC5200_BUGFIX=y
-CONFIG_PPC_MPC5200_GPIO=y
 CONFIG_PPC_MPC5200_LPBFIFO=m
 # CONFIG_PPC_PMAC is not set
 CONFIG_PPC_BESTCOMM=y
 CONFIG_SIMPLE_GPIO=y
 CONFIG_NO_HZ=y
 CONFIG_HIGH_RES_TIMERS=y
-CONFIG_SPARSE_IRQ=y
-CONFIG_PM=y
 CONFIG_NET=y
 CONFIG_PACKET=y
 CONFIG_UNIX=y
@@ -36,23 +33,20 @@ CONFIG_SYN_COOKIES=y
 # CONFIG_IPV6 is not set
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 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_RAM=y
 CONFIG_MTD_ROM=y
 CONFIG_MTD_PHYSMAP_OF=y
+CONFIG_MTD_PLATRAM=y
 CONFIG_MTD_UBI=m
 CONFIG_PROC_DEVICETREE=y
 CONFIG_BLK_DEV_LOOP=y
 CONFIG_BLK_DEV_RAM=y
 CONFIG_BLK_DEV_RAM_SIZE=32768
-CONFIG_MISC_DEVICES=y
 CONFIG_EEPROM_AT24=y
 CONFIG_SCSI_TGT=y
 CONFIG_BLK_DEV_SD=y
@@ -61,11 +55,10 @@ CONFIG_ATA=y
 CONFIG_PATA_MPC52xx=y
 CONFIG_PATA_PLATFORM=y
 CONFIG_NETDEVICES=y
-CONFIG_LXT_PHY=y
-CONFIG_NET_ETHERNET=y
 CONFIG_FEC_MPC52xx=y
-# CONFIG_NETDEV_1000 is not set
-# CONFIG_NETDEV_10000 is not set
+CONFIG_AMD_PHY=y
+CONFIG_LXT_PHY=y
+CONFIG_FIXED_PHY=y
 # CONFIG_INPUT_KEYBOARD is not set
 # CONFIG_INPUT_MOUSE is not set
 # CONFIG_SERIO is not set
@@ -80,11 +73,17 @@ CONFIG_SPI_GPIO=m
 CONFIG_SPI_MPC52xx=m
 CONFIG_SPI_MPC52xx_PSC=m
 CONFIG_SPI_SPIDEV=m
+CONFIG_GPIO_SYSFS=y
+CONFIG_SENSORS_LM80=y
+CONFIG_SENSORS_LM87=m
 CONFIG_WATCHDOG=y
+CONFIG_MFD_SM501=m
 CONFIG_DRM=y
 CONFIG_VIDEO_OUTPUT_CONTROL=y
 CONFIG_FB=y
+CONFIG_FB_FOREIGN_ENDIAN=y
 CONFIG_FB_RADEON=y
+CONFIG_FB_SM501=m
 # CONFIG_VGA_CONSOLE is not set
 CONFIG_FRAMEBUFFER_CONSOLE=y
 CONFIG_LOGO=y
@@ -124,10 +123,11 @@ CONFIG_USB_STORAGE=y
 CONFIG_NEW_LEDS=y
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_DS1307=y
+CONFIG_RTC_DRV_DS1374=y
+CONFIG_RTC_DRV_PCF8563=m
 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
@@ -145,5 +145,4 @@ CONFIG_PRINTK_TIME=y
 CONFIG_DEBUG_KERNEL=y
 CONFIG_DETECT_HUNG_TASK=y
 CONFIG_DEBUG_INFO=y
-# CONFIG_RCU_CPU_STALL_DETECTOR is not set
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
diff --git a/arch/powerpc/configs/mpc85xx_defconfig b/arch/powerpc/configs/mpc85xx_defconfig
index f37a2ab48881..5fb0c8a94811 100644
--- a/arch/powerpc/configs/mpc85xx_defconfig
+++ b/arch/powerpc/configs/mpc85xx_defconfig
@@ -1,4 +1,5 @@
 CONFIG_PPC_85xx=y
+CONFIG_PHYS_64BIT=y
 CONFIG_EXPERIMENTAL=y
 CONFIG_SYSVIPC=y
 CONFIG_POSIX_MQUEUE=y
diff --git a/arch/powerpc/configs/mpc85xx_smp_defconfig b/arch/powerpc/configs/mpc85xx_smp_defconfig
index abdcd317cda7..fb51bc90edd2 100644
--- a/arch/powerpc/configs/mpc85xx_smp_defconfig
+++ b/arch/powerpc/configs/mpc85xx_smp_defconfig
@@ -1,4 +1,5 @@
 CONFIG_PPC_85xx=y
+CONFIG_PHYS_64BIT=y
 CONFIG_SMP=y
 CONFIG_NR_CPUS=8
 CONFIG_EXPERIMENTAL=y
diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig
index 2156e077859b..1acf65026773 100644
--- a/arch/powerpc/configs/ppc64_defconfig
+++ b/arch/powerpc/configs/ppc64_defconfig
@@ -24,10 +24,6 @@ CONFIG_PPC_SPLPAR=y
 CONFIG_SCANLOG=m
 CONFIG_PPC_SMLPAR=y
 CONFIG_DTL=y
-CONFIG_PPC_ISERIES=y
-CONFIG_VIODASD=y
-CONFIG_VIOCD=m
-CONFIG_VIOTAPE=m
 CONFIG_PPC_MAPLE=y
 CONFIG_PPC_PASEMI=y
 CONFIG_PPC_PASEMI_IOMMU=y
@@ -259,7 +255,6 @@ CONFIG_PASEMI_MAC=y
 CONFIG_MLX4_EN=m
 CONFIG_QLGE=m
 CONFIG_BE2NET=m
-CONFIG_ISERIES_VETH=m
 CONFIG_PPP=m
 CONFIG_PPP_ASYNC=m
 CONFIG_PPP_SYNC_TTY=m
diff --git a/arch/powerpc/include/asm/abs_addr.h b/arch/powerpc/include/asm/abs_addr.h
index 5ab0b71531be..9d92ba04b033 100644
--- a/arch/powerpc/include/asm/abs_addr.h
+++ b/arch/powerpc/include/asm/abs_addr.h
@@ -17,7 +17,6 @@
 #include <asm/types.h>
 #include <asm/page.h>
 #include <asm/prom.h>
-#include <asm/firmware.h>
 
 struct mschunks_map {
         unsigned long num_chunks;
@@ -46,30 +45,12 @@ static inline unsigned long addr_to_chunk(unsigned long addr)
 
 static inline unsigned long phys_to_abs(unsigned long pa)
 {
-        unsigned long chunk;
-
-        /* This is a no-op on non-iSeries */
-        if (!firmware_has_feature(FW_FEATURE_ISERIES))
-                return pa;
-
-        chunk = addr_to_chunk(pa);
-
-        if (chunk < mschunks_map.num_chunks)
-                chunk = mschunks_map.mapping[chunk];
-
-        return chunk_to_addr(chunk) + (pa & MSCHUNKS_OFFSET_MASK);
+        return pa;
 }
 
 /* Convenience macros */
 #define virt_to_abs(va) phys_to_abs(__pa(va))
 #define abs_to_virt(aa) __va(aa)
 
-/*
- * Converts Virtual Address to Real Address for
- * Legacy iSeries Hypervisor calls
- */
-#define iseries_hv_addr(virtaddr)       \
-        (0x8000000000000000UL | virt_to_abs(virtaddr))
-
 #endif /* __KERNEL__ */
 #endif /* _ASM_POWERPC_ABS_ADDR_H */
diff --git a/arch/powerpc/include/asm/atomic.h b/arch/powerpc/include/asm/atomic.h
index 02e41b53488d..14174e838ad9 100644
--- a/arch/powerpc/include/asm/atomic.h
+++ b/arch/powerpc/include/asm/atomic.h
@@ -212,6 +212,36 @@ static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u)
         return t;
 }
 
+/**
+ * atomic_inc_not_zero - increment unless the number is zero
+ * @v: pointer of type atomic_t
+ *
+ * Atomically increments @v by 1, so long as @v is non-zero.
+ * Returns non-zero if @v was non-zero, and zero otherwise.
+ */
+static __inline__ int atomic_inc_not_zero(atomic_t *v)
+{
+        int t1, t2;
+
+        __asm__ __volatile__ (
+        PPC_ATOMIC_ENTRY_BARRIER
+"1:     lwarx   %0,0,%2         # atomic_inc_not_zero\n\
+        cmpwi   0,%0,0\n\
+        beq-    2f\n\
+        addic   %1,%0,1\n"
+        PPC405_ERR77(0,%2)
+"       stwcx.  %1,0,%2\n\
+        bne-    1b\n"
+        PPC_ATOMIC_EXIT_BARRIER
+        "\n\
+2:"
+        : "=&r" (t1), "=&r" (t2)
+        : "r" (&v->counter)
+        : "cc", "xer", "memory");
+
+        return t1;
+}
+#define atomic_inc_not_zero(v) atomic_inc_not_zero((v))
 
 #define atomic_sub_and_test(a, v)       (atomic_sub_return((a), (v)) == 0)
 #define atomic_dec_and_test(v)          (atomic_dec_return((v)) == 0)
@@ -467,7 +497,34 @@ static __inline__ int atomic64_add_unless(atomic64_t *v, long a, long u)
         return t != u;
 }
 
-#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0)
+/**
+ * atomic_inc64_not_zero - increment unless the number is zero
+ * @v: pointer of type atomic64_t
+ *
+ * Atomically increments @v by 1, so long as @v is non-zero.
+ * Returns non-zero if @v was non-zero, and zero otherwise.
+ */
+static __inline__ long atomic64_inc_not_zero(atomic64_t *v)
+{
+        long t1, t2;
+
+        __asm__ __volatile__ (
+        PPC_ATOMIC_ENTRY_BARRIER
+"1:     ldarx   %0,0,%2         # atomic64_inc_not_zero\n\
+        cmpdi   0,%0,0\n\
+        beq-    2f\n\
+        addic   %1,%0,1\n\
+        stdcx.  %1,0,%2\n\
+        bne-    1b\n"
+        PPC_ATOMIC_EXIT_BARRIER
+        "\n\
+2:"
+        : "=&r" (t1), "=&r" (t2)
+        : "r" (&v->counter)
+        : "cc", "xer", "memory");
+
+        return t1;
+}
 
 #endif /* __powerpc64__ */
 
diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h
index ad55a1ccb9fb..b9219e99bd2a 100644
--- a/arch/powerpc/include/asm/cputable.h
+++ b/arch/powerpc/include/asm/cputable.h
@@ -390,6 +390,10 @@ extern const char *powerpc_base_platform;
             CPU_FTR_L2CSR | CPU_FTR_LWSYNC | CPU_FTR_NOEXECUTE | \
             CPU_FTR_DBELL | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \
             CPU_FTR_DEBUG_LVL_EXC)
+#define CPU_FTRS_E6500  (CPU_FTR_USE_TB | CPU_FTR_NODSISRALIGN | \
+            CPU_FTR_L2CSR | CPU_FTR_LWSYNC | CPU_FTR_NOEXECUTE | \
+            CPU_FTR_DBELL | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \
+            CPU_FTR_DEBUG_LVL_EXC)
 #define CPU_FTRS_GENERIC_32     (CPU_FTR_COMMON | CPU_FTR_NODSISRALIGN)
 
 /* 64-bit CPUs */
@@ -442,7 +446,7 @@ extern const char *powerpc_base_platform;
 
 #ifdef __powerpc64__
 #ifdef CONFIG_PPC_BOOK3E
-#define CPU_FTRS_POSSIBLE       (CPU_FTRS_E5500 | CPU_FTRS_A2)
+#define CPU_FTRS_POSSIBLE       (CPU_FTRS_E6500 | CPU_FTRS_E5500 | CPU_FTRS_A2)
 #else
 #define CPU_FTRS_POSSIBLE       \
             (CPU_FTRS_POWER3 | CPU_FTRS_RS64 | CPU_FTRS_POWER4 |        \
@@ -483,7 +487,7 @@ enum {
 #endif
 #ifdef CONFIG_E500
             CPU_FTRS_E500 | CPU_FTRS_E500_2 | CPU_FTRS_E500MC |
-            CPU_FTRS_E5500 |
+            CPU_FTRS_E5500 | CPU_FTRS_E6500 |
 #endif
             0,
 };
@@ -491,7 +495,7 @@ enum {
 
 #ifdef __powerpc64__
 #ifdef CONFIG_PPC_BOOK3E
-#define CPU_FTRS_ALWAYS         (CPU_FTRS_E5500 & CPU_FTRS_A2)
+#define CPU_FTRS_ALWAYS         (CPU_FTRS_E6500 & CPU_FTRS_E5500 & CPU_FTRS_A2)
 #else
 #define CPU_FTRS_ALWAYS         \
             (CPU_FTRS_POWER3 & CPU_FTRS_RS64 & CPU_FTRS_POWER4 &        \
@@ -528,7 +532,7 @@ enum {
 #endif
 #ifdef CONFIG_E500
             CPU_FTRS_E500 & CPU_FTRS_E500_2 & CPU_FTRS_E500MC &
-            CPU_FTRS_E5500 &
+            CPU_FTRS_E5500 & CPU_FTRS_E6500 &
 #endif
             CPU_FTRS_POSSIBLE,
 };
diff --git a/arch/powerpc/include/asm/device.h b/arch/powerpc/include/asm/device.h
index d57c08acedfc..63d5ca49cece 100644
--- a/arch/powerpc/include/asm/device.h
+++ b/arch/powerpc/include/asm/device.h
@@ -31,6 +31,9 @@ struct dev_archdata {
 #ifdef CONFIG_SWIOTLB
         dma_addr_t              max_direct_dma_addr;
 #endif
+#ifdef CONFIG_EEH
+        struct eeh_dev          *edev;
+#endif
 };
 
 struct pdev_archdata {
diff --git a/arch/powerpc/include/asm/dma.h b/arch/powerpc/include/asm/dma.h
index a7e06e25c708..adadb9943610 100644
--- a/arch/powerpc/include/asm/dma.h
+++ b/arch/powerpc/include/asm/dma.h
@@ -34,8 +34,6 @@
 /* Doesn't really apply... */
 #define MAX_DMA_ADDRESS         (~0UL)
 
-#if !defined(CONFIG_PPC_ISERIES) || defined(CONFIG_PCI)
-
 #ifdef HAVE_REALLY_SLOW_DMA_CONTROLLER
 #define dma_outb        outb_p
 #else
@@ -354,7 +352,5 @@ extern int isa_dma_bridge_buggy;
 #define isa_dma_bridge_buggy    (0)
 #endif
 
-#endif  /* !defined(CONFIG_PPC_ISERIES) || defined(CONFIG_PCI) */
-
 #endif /* __KERNEL__ */
 #endif  /* _ASM_POWERPC_DMA_H */
diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h
index 66ea9b8b95c5..d60f99814ffb 100644
--- a/arch/powerpc/include/asm/eeh.h
+++ b/arch/powerpc/include/asm/eeh.h
@@ -1,6 +1,6 @@
 /*
- * eeh.h
  * Copyright (C) 2001  Dave Engebretsen & Todd Inglett IBM Corporation.
+ * Copyright 2001-2012 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
@@ -31,44 +31,105 @@ struct device_node;
 
 #ifdef CONFIG_EEH
 
-extern int eeh_subsystem_enabled;
+/*
+ * The struct is used to trace EEH state for the associated
+ * PCI device node or PCI device. In future, it might
+ * represent PE as well so that the EEH device to form
+ * another tree except the currently existing tree of PCI
+ * buses and PCI devices
+ */
+#define EEH_MODE_SUPPORTED      (1<<0)  /* EEH supported on the device  */
+#define EEH_MODE_NOCHECK        (1<<1)  /* EEH check should be skipped  */
+#define EEH_MODE_ISOLATED       (1<<2)  /* The device has been isolated */
+#define EEH_MODE_RECOVERING     (1<<3)  /* Recovering the device        */
+#define EEH_MODE_IRQ_DISABLED   (1<<4)  /* Interrupt disabled           */
+
+struct eeh_dev {
+        int mode;                       /* EEH mode                     */
+        int class_code;                 /* Class code of the device     */
+        int config_addr;                /* Config address               */
+        int pe_config_addr;             /* PE config address            */
+        int check_count;                /* Times of ignored error       */
+        int freeze_count;               /* Times of froze up            */
+        int false_positives;            /* Times of reported #ff's      */
+        u32 config_space[16];           /* Saved PCI config space       */
+        struct pci_controller *phb;     /* Associated PHB               */
+        struct device_node *dn;         /* Associated device node       */
+        struct pci_dev *pdev;           /* Associated PCI device        */
+};
+
+static inline struct device_node *eeh_dev_to_of_node(struct eeh_dev *edev)
+{
+        return edev->dn;
+}
+
+static inline struct pci_dev *eeh_dev_to_pci_dev(struct eeh_dev *edev)
+{
+        return edev->pdev;
+}
 
-/* Values for eeh_mode bits in device_node */
-#define EEH_MODE_SUPPORTED     (1<<0)
-#define EEH_MODE_NOCHECK       (1<<1)
-#define EEH_MODE_ISOLATED      (1<<2)
-#define EEH_MODE_RECOVERING    (1<<3)
-#define EEH_MODE_IRQ_DISABLED  (1<<4)
+/*
+ * The struct is used to trace the registered EEH operation
+ * callback functions. Actually, those operation callback
+ * functions are heavily platform dependent. That means the
+ * platform should register its own EEH operation callback
+ * functions before any EEH further operations.
+ */
+#define EEH_OPT_DISABLE         0       /* EEH disable  */
+#define EEH_OPT_ENABLE          1       /* EEH enable   */
+#define EEH_OPT_THAW_MMIO       2       /* MMIO enable  */
+#define EEH_OPT_THAW_DMA        3       /* DMA enable   */
+#define EEH_STATE_UNAVAILABLE   (1 << 0)        /* State unavailable    */
+#define EEH_STATE_NOT_SUPPORT   (1 << 1)        /* EEH not supported    */
+#define EEH_STATE_RESET_ACTIVE  (1 << 2)        /* Active reset         */
+#define EEH_STATE_MMIO_ACTIVE   (1 << 3)        /* Active MMIO          */
+#define EEH_STATE_DMA_ACTIVE    (1 << 4)        /* Active DMA           */
+#define EEH_STATE_MMIO_ENABLED  (1 << 5)        /* MMIO enabled         */
+#define EEH_STATE_DMA_ENABLED   (1 << 6)        /* DMA enabled          */
+#define EEH_RESET_DEACTIVATE    0       /* Deactivate the PE reset      */
+#define EEH_RESET_HOT           1       /* Hot reset                    */
+#define EEH_RESET_FUNDAMENTAL   3       /* Fundamental reset            */
+#define EEH_LOG_TEMP            1       /* EEH temporary error log      */
+#define EEH_LOG_PERM            2       /* EEH permanent error log      */
+
+struct eeh_ops {
+        char *name;
+        int (*init)(void);
+        int (*set_option)(struct device_node *dn, int option);
+        int (*get_pe_addr)(struct device_node *dn);
+        int (*get_state)(struct device_node *dn, int *state);
+        int (*reset)(struct device_node *dn, int option);
+        int (*wait_state)(struct device_node *dn, int max_wait);
+        int (*get_log)(struct device_node *dn, int severity, char *drv_log, unsigned long len);
+        int (*configure_bridge)(struct device_node *dn);
+        int (*read_config)(struct device_node *dn, int where, int size, u32 *val);
+        int (*write_config)(struct device_node *dn, int where, int size, u32 val);
+};
+
+extern struct eeh_ops *eeh_ops;
+extern int eeh_subsystem_enabled;
 
-/* Max number of EEH freezes allowed before we consider the device
- * to be permanently disabled. */
+/*
+ * Max number of EEH freezes allowed before we consider the device
+ * to be permanently disabled.
+ */
 #define EEH_MAX_ALLOWED_FREEZES 5
 
+void * __devinit eeh_dev_init(struct device_node *dn, void *data);
+void __devinit eeh_dev_phb_init_dynamic(struct pci_controller *phb);
+void __init eeh_dev_phb_init(void);
 void __init eeh_init(void);
+#ifdef CONFIG_PPC_PSERIES
+int __init eeh_pseries_init(void);
+#endif
+int __init eeh_ops_register(struct eeh_ops *ops);
+int __exit eeh_ops_unregister(const char *name);
 unsigned long eeh_check_failure(const volatile void __iomem *token,
                                 unsigned long val);
 int eeh_dn_check_failure(struct device_node *dn, struct pci_dev *dev);
 void __init pci_addr_cache_build(void);
-
-/**
- * eeh_add_device_early
- * eeh_add_device_late
- *
- * Perform eeh initialization for devices added after boot.
- * Call eeh_add_device_early before doing any i/o to the
- * device (including config space i/o).  Call eeh_add_device_late
- * to finish the eeh setup for this device.
- */
 void eeh_add_device_tree_early(struct device_node *);
 void eeh_add_device_tree_late(struct pci_bus *);
-
-/**
- * eeh_remove_device_recursive - undo EEH for device & children.
- * @dev: pci device to be removed
- *
- * As above, this removes the device; it also removes child
- * pci devices as well.
- */
 void eeh_remove_bus_device(struct pci_dev *);
 
 /**
@@ -87,8 +148,25 @@ void eeh_remove_bus_device(struct pci_dev *);
 #define EEH_IO_ERROR_VALUE(size)        (~0U >> ((4 - (size)) * 8))
 
 #else /* !CONFIG_EEH */
+
+static inline void *eeh_dev_init(struct device_node *dn, void *data)
+{
+        return NULL;
+}
+
+static inline void eeh_dev_phb_init_dynamic(struct pci_controller *phb) { }
+
+static inline void eeh_dev_phb_init(void) { }
+
 static inline void eeh_init(void) { }
 
+#ifdef CONFIG_PPC_PSERIES
+static inline int eeh_pseries_init(void)
+{
+        return 0;
+}
+#endif /* CONFIG_PPC_PSERIES */
+
 static inline unsigned long eeh_check_failure(const volatile void __iomem *token, unsigned long val)
 {
         return val;
diff --git a/arch/powerpc/include/asm/eeh_event.h b/arch/powerpc/include/asm/eeh_event.h
index cc3cb04539ac..c68b012b7797 100644
--- a/arch/powerpc/include/asm/eeh_event.h
+++ b/arch/powerpc/include/asm/eeh_event.h
@@ -1,6 +1,4 @@
 /*
- *      eeh_event.h
- *
  * 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
@@ -22,32 +20,19 @@
 #define ASM_POWERPC_EEH_EVENT_H
 #ifdef __KERNEL__
 
-/** EEH event -- structure holding pci controller data that describes
- *  a change in the isolation status of a PCI slot.  A pointer
- *  to this struct is passed as the data pointer in a notify callback.
+/*
+ * structure holding pci controller data that describes a
+ * change in the isolation status of a PCI slot.  A pointer
+ * to this struct is passed as the data pointer in a notify
+ * callback.
  */
 struct eeh_event {
-        struct list_head     list;
-        struct device_node      *dn;   /* struct device node */
-        struct pci_dev       *dev;  /* affected device */
+        struct list_head        list;   /* to form event queue  */
+        struct eeh_dev          *edev;  /* EEH device           */
 };
 
-/**
- * eeh_send_failure_event - generate a PCI error event
- * @dev pci device
- *
- * This routine builds a PCI error event which will be delivered
- * to all listeners on the eeh_notifier_chain.
- *
- * This routine can be called within an interrupt context;
- * the actual event will be delivered in a normal context
- * (from a workqueue).
- */
-int eeh_send_failure_event (struct device_node *dn,
-                            struct pci_dev *dev);
-
-/* Main recovery function */
-struct pci_dn * handle_eeh_events (struct eeh_event *);
+int eeh_send_failure_event(struct eeh_dev *edev);
+struct eeh_dev *handle_eeh_events(struct eeh_event *);
 
 #endif /* __KERNEL__ */
 #endif /* ASM_POWERPC_EEH_EVENT_H */
diff --git a/arch/powerpc/include/asm/ehv_pic.h b/arch/powerpc/include/asm/ehv_pic.h
index a9e1f4f796f6..dc7d48e3ea90 100644
--- a/arch/powerpc/include/asm/ehv_pic.h
+++ b/arch/powerpc/include/asm/ehv_pic.h
@@ -25,7 +25,7 @@
 
 struct ehv_pic {
         /* The remapper for this EHV_PIC */
-        struct irq_host *irqhost;
+        struct irq_domain       *irqhost;
 
         /* The "linux" controller struct */
         struct irq_chip hc_irq;
diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h
index 8057f4f6980f..548da3aa0a30 100644
--- a/arch/powerpc/include/asm/exception-64s.h
+++ b/arch/powerpc/include/asm/exception-64s.h
@@ -232,23 +232,30 @@ label##_hv:						\
         EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, label##_common,    \
                                  EXC_HV, KVMTEST, vec)
 
-#define __SOFTEN_TEST(h)                                                \
+/* This associate vector numbers with bits in paca->irq_happened */
+#define SOFTEN_VALUE_0x500      PACA_IRQ_EE
+#define SOFTEN_VALUE_0x502      PACA_IRQ_EE
+#define SOFTEN_VALUE_0x900      PACA_IRQ_DEC
+#define SOFTEN_VALUE_0x982      PACA_IRQ_DEC
+
+#define __SOFTEN_TEST(h, vec)                                           \
         lbz     r10,PACASOFTIRQEN(r13);                                 \
         cmpwi   r10,0;                                                  \
+        li      r10,SOFTEN_VALUE_##vec;                                 \
         beq     masked_##h##interrupt
-#define _SOFTEN_TEST(h) __SOFTEN_TEST(h)
+#define _SOFTEN_TEST(h, vec)    __SOFTEN_TEST(h, vec)
 
 #define SOFTEN_TEST_PR(vec)                                             \
         KVMTEST_PR(vec);                                                \
-        _SOFTEN_TEST(EXC_STD)
+        _SOFTEN_TEST(EXC_STD, vec)
 
 #define SOFTEN_TEST_HV(vec)                                             \
         KVMTEST(vec);                                                   \
-        _SOFTEN_TEST(EXC_HV)
+        _SOFTEN_TEST(EXC_HV, vec)
 
 #define SOFTEN_TEST_HV_201(vec)                                         \
         KVMTEST(vec);                                                   \
-        _SOFTEN_TEST(EXC_STD)
+        _SOFTEN_TEST(EXC_STD, vec)
 
 #define __MASKABLE_EXCEPTION_PSERIES(vec, label, h, extra)              \
         HMT_MEDIUM;                                                     \
@@ -272,73 +279,55 @@ label##_hv:								\
         _MASKABLE_EXCEPTION_PSERIES(vec, label,                         \
                                     EXC_HV, SOFTEN_TEST_HV)
 
-#ifdef CONFIG_PPC_ISERIES
-#define DISABLE_INTS                            \
-        li      r11,0;                          \
-        stb     r11,PACASOFTIRQEN(r13);         \
-BEGIN_FW_FTR_SECTION;                           \
-        stb     r11,PACAHARDIRQEN(r13);         \
-END_FW_FTR_SECTION_IFCLR(FW_FEATURE_ISERIES);   \
-        TRACE_DISABLE_INTS;                     \
-BEGIN_FW_FTR_SECTION;                           \
-        mfmsr   r10;                            \
-        ori     r10,r10,MSR_EE;                 \
-        mtmsrd  r10,1;                          \
-END_FW_FTR_SECTION_IFSET(FW_FEATURE_ISERIES)
-#else
-#define DISABLE_INTS                            \
-        li      r11,0;                          \
-        stb     r11,PACASOFTIRQEN(r13);         \
-        stb     r11,PACAHARDIRQEN(r13);         \
-        TRACE_DISABLE_INTS
-#endif /* CONFIG_PPC_ISERIES */
+/*
+ * Our exception common code can be passed various "additions"
+ * to specify the behaviour of interrupts, whether to kick the
+ * runlatch, etc...
+ */
+
+/* Exception addition: Hard disable interrupts */
+#define DISABLE_INTS    SOFT_DISABLE_INTS(r10,r11)
 
+/* Exception addition: Keep interrupt state */
 #define ENABLE_INTS                             \
+        ld      r11,PACAKMSR(r13);              \
         ld      r12,_MSR(r1);                   \
-        mfmsr   r11;                            \
         rlwimi  r11,r12,0,MSR_EE;               \
         mtmsrd  r11,1
 
-#define STD_EXCEPTION_COMMON(trap, label, hdlr)         \
-        .align  7;                                      \
-        .globl label##_common;                          \
-label##_common:                                         \
-        EXCEPTION_PROLOG_COMMON(trap, PACA_EXGEN);      \
-        DISABLE_INTS;                                   \
-        bl      .save_nvgprs;                           \
-        addi    r3,r1,STACK_FRAME_OVERHEAD;             \
-        bl      hdlr;                                   \
-        b       .ret_from_except
+#define ADD_NVGPRS                              \
+        bl      .save_nvgprs
+
+#define RUNLATCH_ON                             \
+BEGIN_FTR_SECTION                               \
+        clrrdi  r3,r1,THREAD_SHIFT;             \
+        ld      r4,TI_LOCAL_FLAGS(r3);          \
+        andi.   r0,r4,_TLF_RUNLATCH;            \
+        beql    ppc64_runlatch_on_trampoline;   \
+END_FTR_SECTION_IFSET(CPU_FTR_CTRL)
+
+#define EXCEPTION_COMMON(trap, label, hdlr, ret, additions)     \
+        .align  7;                                              \
+        .globl label##_common;                                  \
+label##_common:                                                 \
+        EXCEPTION_PROLOG_COMMON(trap, PACA_EXGEN);              \
+        additions;                                              \
+        addi    r3,r1,STACK_FRAME_OVERHEAD;                     \
+        bl      hdlr;                                           \
+        b       ret
+
+#define STD_EXCEPTION_COMMON(trap, label, hdlr)                 \
+        EXCEPTION_COMMON(trap, label, hdlr, ret_from_except,    \
+                         ADD_NVGPRS;DISABLE_INTS)
 
 /*
  * Like STD_EXCEPTION_COMMON, but for exceptions that can occur
- * in the idle task and therefore need the special idle handling.
+ * in the idle task and therefore need the special idle handling
+ * (finish nap and runlatch)
  */
-#define STD_EXCEPTION_COMMON_IDLE(trap, label, hdlr)    \
-        .align  7;                                      \
-        .globl label##_common;                          \
-label##_common:                                         \
-        EXCEPTION_PROLOG_COMMON(trap, PACA_EXGEN);      \
-        FINISH_NAP;                                     \
-        DISABLE_INTS;                                   \
-        bl      .save_nvgprs;                           \
-        addi    r3,r1,STACK_FRAME_OVERHEAD;             \
-        bl      hdlr;                                   \
-        b       .ret_from_except
-
-#define STD_EXCEPTION_COMMON_LITE(trap, label, hdlr)    \
-        .align  7;                                      \
-        .globl label##_common;                          \
-label##_common:                                         \
-        EXCEPTION_PROLOG_COMMON(trap, PACA_EXGEN);      \
-        FINISH_NAP;                                     \
-        DISABLE_INTS;                                   \
-BEGIN_FTR_SECTION                                       \
-        bl      .ppc64_runlatch_on;                     \
-END_FTR_SECTION_IFSET(CPU_FTR_CTRL)                     \
-        addi    r3,r1,STACK_FRAME_OVERHEAD;             \
-        bl      hdlr;                                   \
-        b       .ret_from_except_lite
+#define STD_EXCEPTION_COMMON_ASYNC(trap, label, hdlr)             \
+        EXCEPTION_COMMON(trap, label, hdlr, ret_from_except_lite, \
+                         FINISH_NAP;RUNLATCH_ON;DISABLE_INTS)
 
 /*
  * When the idle code in power4_idle puts the CPU into NAP mode,
diff --git a/arch/powerpc/include/asm/fadump.h b/arch/powerpc/include/asm/fadump.h
new file mode 100644
index 000000000000..88dbf9659185
--- /dev/null
+++ b/arch/powerpc/include/asm/fadump.h
@@ -0,0 +1,218 @@
+/*
+ * Firmware Assisted dump header file.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ * Copyright 2011 IBM Corporation
+ * Author: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
+ */
+
+#ifndef __PPC64_FA_DUMP_H__
+#define __PPC64_FA_DUMP_H__
+
+#ifdef CONFIG_FA_DUMP
+
+/*
+ * The RMA region will be saved for later dumping when kernel crashes.
+ * RMA is Real Mode Area, the first block of logical memory address owned
+ * by logical partition, containing the storage that may be accessed with
+ * translate off.
+ */
+#define RMA_START       0x0
+#define RMA_END         (ppc64_rma_size)
+
+/*
+ * On some Power systems where RMO is 128MB, it still requires minimum of
+ * 256MB for kernel to boot successfully. When kdump infrastructure is
+ * configured to save vmcore over network, we run into OOM issue while
+ * loading modules related to network setup. Hence we need aditional 64M
+ * of memory to avoid OOM issue.
+ */
+#define MIN_BOOT_MEM    (((RMA_END < (0x1UL << 28)) ? (0x1UL << 28) : RMA_END) \
+                        + (0x1UL << 26))
+
+#define memblock_num_regions(memblock_type)     (memblock.memblock_type.cnt)
+
+#ifndef ELF_CORE_EFLAGS
+#define ELF_CORE_EFLAGS 0
+#endif
+
+/* Firmware provided dump sections */
+#define FADUMP_CPU_STATE_DATA   0x0001
+#define FADUMP_HPTE_REGION      0x0002
+#define FADUMP_REAL_MODE_REGION 0x0011
+
+/* Dump request flag */
+#define FADUMP_REQUEST_FLAG     0x00000001
+
+/* FAD commands */
+#define FADUMP_REGISTER         1
+#define FADUMP_UNREGISTER       2
+#define FADUMP_INVALIDATE       3
+
+/* Dump status flag */
+#define FADUMP_ERROR_FLAG       0x2000
+
+#define FADUMP_CPU_ID_MASK      ((1UL << 32) - 1)
+
+#define CPU_UNKNOWN             (~((u32)0))
+
+/* Utility macros */
+#define SKIP_TO_NEXT_CPU(reg_entry)                     \
+({                                                      \
+        while (reg_entry->reg_id != REG_ID("CPUEND"))   \
+                reg_entry++;                            \
+        reg_entry++;                                    \
+})
+
+/* Kernel Dump section info */
+struct fadump_section {
+        u32     request_flag;
+        u16     source_data_type;
+        u16     error_flags;
+        u64     source_address;
+        u64     source_len;
+        u64     bytes_dumped;
+        u64     destination_address;
+};
+
+/* ibm,configure-kernel-dump header. */
+struct fadump_section_header {
+        u32     dump_format_version;
+        u16     dump_num_sections;
+        u16     dump_status_flag;
+        u32     offset_first_dump_section;
+
+        /* Fields for disk dump option. */
+        u32     dd_block_size;
+        u64     dd_block_offset;
+        u64     dd_num_blocks;
+        u32     dd_offset_disk_path;
+
+        /* Maximum time allowed to prevent an automatic dump-reboot. */
+        u32     max_time_auto;
+};
+
+/*
+ * Firmware Assisted dump memory structure. This structure is required for
+ * registering future kernel dump with power firmware through rtas call.
+ *
+ * No disk dump option. Hence disk dump path string section is not included.
+ */
+struct fadump_mem_struct {
+        struct fadump_section_header    header;
+
+        /* Kernel dump sections */
+        struct fadump_section           cpu_state_data;
+        struct fadump_section           hpte_region;
+        struct fadump_section           rmr_region;
+};
+
+/* Firmware-assisted dump configuration details. */
+struct fw_dump {
+        unsigned long   cpu_state_data_size;
+        unsigned long   hpte_region_size;
+        unsigned long   boot_memory_size;
+        unsigned long   reserve_dump_area_start;
+        unsigned long   reserve_dump_area_size;
+        /* cmd line option during boot */
+        unsigned long   reserve_bootvar;
+
+        unsigned long   fadumphdr_addr;
+        unsigned long   cpu_notes_buf;
+        unsigned long   cpu_notes_buf_size;
+
+        int             ibm_configure_kernel_dump;
+
+        unsigned long   fadump_enabled:1;
+        unsigned long   fadump_supported:1;
+        unsigned long   dump_active:1;
+        unsigned long   dump_registered:1;
+};
+
+/*
+ * Copy the ascii values for first 8 characters from a string into u64
+ * variable at their respective indexes.
+ * e.g.
+ *  The string "FADMPINF" will be converted into 0x4641444d50494e46
+ */
+static inline u64 str_to_u64(const char *str)
+{
+        u64 val = 0;
+        int i;
+
+        for (i = 0; i < sizeof(val); i++)
+                val = (*str) ? (val << 8) | *str++ : val << 8;
+        return val;
+}
+#define STR_TO_HEX(x)   str_to_u64(x)
+#define REG_ID(x)       str_to_u64(x)
+
+#define FADUMP_CRASH_INFO_MAGIC         STR_TO_HEX("FADMPINF")
+#define REGSAVE_AREA_MAGIC              STR_TO_HEX("REGSAVE")
+
+/* The firmware-assisted dump format.
+ *
+ * The register save area is an area in the partition's memory used to preserve
+ * the register contents (CPU state data) for the active CPUs during a firmware
+ * assisted dump. The dump format contains register save area header followed
+ * by register entries. Each list of registers for a CPU starts with
+ * "CPUSTRT" and ends with "CPUEND".
+ */
+
+/* Register save area header. */
+struct fadump_reg_save_area_header {
+        u64             magic_number;
+        u32             version;
+        u32             num_cpu_offset;
+};
+
+/* Register entry. */
+struct fadump_reg_entry {
+        u64             reg_id;
+        u64             reg_value;
+};
+
+/* fadump crash info structure */
+struct fadump_crash_info_header {
+        u64             magic_number;
+        u64             elfcorehdr_addr;
+        u32             crashing_cpu;
+        struct pt_regs  regs;
+        struct cpumask  cpu_online_mask;
+};
+
+/* Crash memory ranges */
+#define INIT_CRASHMEM_RANGES    (INIT_MEMBLOCK_REGIONS + 2)
+
+struct fad_crash_memory_ranges {
+        unsigned long long      base;
+        unsigned long long      size;
+};
+
+extern int early_init_dt_scan_fw_dump(unsigned long node,
+                const char *uname, int depth, void *data);
+extern int fadump_reserve_mem(void);
+extern int setup_fadump(void);
+extern int is_fadump_active(void);
+extern void crash_fadump(struct pt_regs *, const char *);
+extern void fadump_cleanup(void);
+
+extern void vmcore_cleanup(void);
+#else   /* CONFIG_FA_DUMP */
+static inline int is_fadump_active(void) { return 0; }
+static inline void crash_fadump(struct pt_regs *regs, const char *str) { }
+#endif
+#endif
diff --git a/arch/powerpc/include/asm/firmware.h b/arch/powerpc/include/asm/firmware.h
index 14db29b18d0e..ad0b751b0d78 100644
--- a/arch/powerpc/include/asm/firmware.h
+++ b/arch/powerpc/include/asm/firmware.h
@@ -41,7 +41,6 @@
 #define FW_FEATURE_XDABR        ASM_CONST(0x0000000000040000)
 #define FW_FEATURE_MULTITCE     ASM_CONST(0x0000000000080000)
 #define FW_FEATURE_SPLPAR       ASM_CONST(0x0000000000100000)
-#define FW_FEATURE_ISERIES      ASM_CONST(0x0000000000200000)
 #define FW_FEATURE_LPAR         ASM_CONST(0x0000000000400000)
 #define FW_FEATURE_PS3_LV1      ASM_CONST(0x0000000000800000)
 #define FW_FEATURE_BEAT         ASM_CONST(0x0000000001000000)
@@ -65,8 +64,6 @@ enum {
                 FW_FEATURE_MULTITCE | FW_FEATURE_SPLPAR | FW_FEATURE_LPAR |
                 FW_FEATURE_CMO | FW_FEATURE_VPHN | FW_FEATURE_XCMO,
         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,
@@ -79,9 +76,6 @@ enum {
 #ifdef CONFIG_PPC_PSERIES
                 FW_FEATURE_PSERIES_POSSIBLE |
 #endif
-#ifdef CONFIG_PPC_ISERIES
-                FW_FEATURE_ISERIES_POSSIBLE |
-#endif
 #ifdef CONFIG_PPC_POWERNV
                 FW_FEATURE_POWERNV_POSSIBLE |
 #endif
@@ -99,9 +93,6 @@ enum {
 #ifdef CONFIG_PPC_PSERIES
                 FW_FEATURE_PSERIES_ALWAYS &
 #endif
-#ifdef CONFIG_PPC_ISERIES
-                FW_FEATURE_ISERIES_ALWAYS &
-#endif
 #ifdef CONFIG_PPC_POWERNV
                 FW_FEATURE_POWERNV_ALWAYS &
 #endif
diff --git a/arch/powerpc/include/asm/fsl_guts.h b/arch/powerpc/include/asm/fsl_guts.h
index bebd12463ec9..ce04530d2000 100644
--- a/arch/powerpc/include/asm/fsl_guts.h
+++ b/arch/powerpc/include/asm/fsl_guts.h
@@ -4,7 +4,7 @@
  * Authors: Jeff Brown
  *          Timur Tabi <timur@freescale.com>
  *
- * Copyright 2004,2007 Freescale Semiconductor, Inc
+ * Copyright 2004,2007,2012 Freescale Semiconductor, Inc
  *
  * This program is free software; you can redistribute  it and/or modify it
  * under  the terms of  the GNU General  Public License as published by the
@@ -114,6 +114,10 @@ struct ccsr_guts_86xx {
         __be32  srds2cr1;       /* 0x.0f44 - SerDes2 Control Register 0 */
 } __attribute__ ((packed));
 
+
+/* Alternate function signal multiplex control */
+#define MPC85xx_PMUXCR_QE(x) (0x8000 >> (x))
+
 #ifdef CONFIG_PPC_86xx
 
 #define CCSR_GUTS_DMACR_DEV_SSI 0       /* DMA controller/channel set to SSI */
diff --git a/arch/powerpc/include/asm/highmem.h b/arch/powerpc/include/asm/highmem.h
index dbc264010d0b..caaf6e00630d 100644
--- a/arch/powerpc/include/asm/highmem.h
+++ b/arch/powerpc/include/asm/highmem.h
@@ -79,7 +79,7 @@ static inline void kunmap(struct page *page)
         kunmap_high(page);
 }
 
-static inline void *__kmap_atomic(struct page *page)
+static inline void *kmap_atomic(struct page *page)
 {
         return kmap_atomic_prot(page, kmap_prot);
 }
diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h
index bb712c9488b3..51010bfc792e 100644
--- a/arch/powerpc/include/asm/hw_irq.h
+++ b/arch/powerpc/include/asm/hw_irq.h
@@ -11,6 +11,27 @@
 #include <asm/ptrace.h>
 #include <asm/processor.h>
 
+#ifdef CONFIG_PPC64
+
+/*
+ * PACA flags in paca->irq_happened.
+ *
+ * This bits are set when interrupts occur while soft-disabled
+ * and allow a proper replay. Additionally, PACA_IRQ_HARD_DIS
+ * is set whenever we manually hard disable.
+ */
+#define PACA_IRQ_HARD_DIS       0x01
+#define PACA_IRQ_DBELL          0x02
+#define PACA_IRQ_EE             0x04
+#define PACA_IRQ_DEC            0x08 /* Or FIT */
+#define PACA_IRQ_EE_EDGE        0x10 /* BookE only */
+
+#endif /* CONFIG_PPC64 */
+
+#ifndef __ASSEMBLY__
+
+extern void __replay_interrupt(unsigned int vector);
+
 extern void timer_interrupt(struct pt_regs *);
 
 #ifdef CONFIG_PPC64
@@ -42,7 +63,6 @@ static inline unsigned long arch_local_irq_disable(void)
 }
 
 extern void arch_local_irq_restore(unsigned long);
-extern void iseries_handle_interrupts(void);
 
 static inline void arch_local_irq_enable(void)
 {
@@ -68,16 +88,33 @@ static inline bool arch_irqs_disabled(void)
 #define __hard_irq_enable()     asm volatile("wrteei 1" : : : "memory");
 #define __hard_irq_disable()    asm volatile("wrteei 0" : : : "memory");
 #else
-#define __hard_irq_enable()     __mtmsrd(mfmsr() | MSR_EE, 1)
-#define __hard_irq_disable()    __mtmsrd(mfmsr() & ~MSR_EE, 1)
+#define __hard_irq_enable()     __mtmsrd(local_paca->kernel_msr | MSR_EE, 1)
+#define __hard_irq_disable()    __mtmsrd(local_paca->kernel_msr, 1)
 #endif
 
-#define  hard_irq_disable()                     \
-        do {                                    \
-                __hard_irq_disable();           \
-                get_paca()->soft_enabled = 0;   \
-                get_paca()->hard_enabled = 0;   \
-        } while(0)
+static inline void hard_irq_disable(void)
+{
+        __hard_irq_disable();
+        get_paca()->soft_enabled = 0;
+        get_paca()->irq_happened |= PACA_IRQ_HARD_DIS;
+}
+
+/*
+ * This is called by asynchronous interrupts to conditionally
+ * re-enable hard interrupts when soft-disabled after having
+ * cleared the source of the interrupt
+ */
+static inline void may_hard_irq_enable(void)
+{
+        get_paca()->irq_happened &= ~PACA_IRQ_HARD_DIS;
+        if (!(get_paca()->irq_happened & PACA_IRQ_EE))
+                __hard_irq_enable();
+}
+
+static inline bool arch_irq_disabled_regs(struct pt_regs *regs)
+{
+        return !regs->softe;
+}
 
 #else /* CONFIG_PPC64 */
 
@@ -139,6 +176,13 @@ static inline bool arch_irqs_disabled(void)
 
 #define hard_irq_disable()              arch_local_irq_disable()
 
+static inline bool arch_irq_disabled_regs(struct pt_regs *regs)
+{
+        return !(regs->msr & MSR_EE);
+}
+
+static inline void may_hard_irq_enable(void) { }
+
 #endif /* CONFIG_PPC64 */
 
 #define ARCH_IRQ_INIT_FLAGS     IRQ_NOREQUEST
@@ -149,5 +193,6 @@ static inline bool arch_irqs_disabled(void)
  */
 struct irq_chip;
 
+#endif  /* __ASSEMBLY__ */
 #endif  /* __KERNEL__ */
 #endif  /* _ASM_POWERPC_HW_IRQ_H */
diff --git a/arch/powerpc/include/asm/i8259.h b/arch/powerpc/include/asm/i8259.h
index 105ade297aad..c3fdfbd5a673 100644
--- a/arch/powerpc/include/asm/i8259.h
+++ b/arch/powerpc/include/asm/i8259.h
@@ -6,7 +6,7 @@
 
 extern void i8259_init(struct device_node *node, unsigned long intack_addr);
 extern unsigned int i8259_irq(void);
-extern struct irq_host *i8259_get_host(void);
+extern struct irq_domain *i8259_get_host(void);
 
 #endif /* __KERNEL__ */
 #endif /* _ASM_POWERPC_I8259_H */
diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h
index edfc9803ec91..957a83f43646 100644
--- a/arch/powerpc/include/asm/iommu.h
+++ b/arch/powerpc/include/asm/iommu.h
@@ -112,7 +112,6 @@ extern void iommu_unmap_page(struct iommu_table *tbl, dma_addr_t dma_handle,
                              struct dma_attrs *attrs);
 
 extern void iommu_init_early_pSeries(void);
-extern void iommu_init_early_iSeries(void);
 extern void iommu_init_early_dart(void);
 extern void iommu_init_early_pasemi(void);
 
diff --git a/arch/powerpc/include/asm/irq.h b/arch/powerpc/include/asm/irq.h
index c0e1bc319e35..cf417e510736 100644
--- a/arch/powerpc/include/asm/irq.h
+++ b/arch/powerpc/include/asm/irq.h
@@ -9,6 +9,7 @@
  * 2 of the License, or (at your option) any later version.
  */
 
+#include <linux/irqdomain.h>
 #include <linux/threads.h>
 #include <linux/list.h>
 #include <linux/radix-tree.h>
@@ -26,267 +27,15 @@ extern atomic_t ppc_n_lost_interrupts;
 /* This number is used when no interrupt has been assigned */
 #define NO_IRQ                  (0)
 
-/* This is a special irq number to return from get_irq() to tell that
- * no interrupt happened _and_ ignore it (don't count it as bad). Some
- * platforms like iSeries rely on that.
- */
-#define NO_IRQ_IGNORE           ((unsigned int)-1)
-
 /* Total number of virq in the platform */
 #define NR_IRQS         CONFIG_NR_IRQS
 
-/* Number of irqs reserved for the legacy controller */
-#define NUM_ISA_INTERRUPTS      16
-
 /* Same thing, used by the generic IRQ code */
 #define NR_IRQS_LEGACY          NUM_ISA_INTERRUPTS
 
-/* This type is the placeholder for a hardware interrupt number. It has to
- * be big enough to enclose whatever representation is used by a given
- * platform.
- */
-typedef unsigned long irq_hw_number_t;
-
-/* Interrupt controller "host" data structure. This could be defined as a
- * irq domain controller. That is, it handles the mapping between hardware
- * and virtual interrupt numbers for a given interrupt domain. The host
- * structure is generally created by the PIC code for a given PIC instance
- * (though a host can cover more than one PIC if they have a flat number
- * model). It's the host callbacks that are responsible for setting the
- * irq_chip on a given irq_desc after it's been mapped.
- *
- * The host code and data structures are fairly agnostic to the fact that
- * we use an open firmware device-tree. We do have references to struct
- * device_node in two places: in irq_find_host() to find the host matching
- * a given interrupt controller node, and of course as an argument to its
- * counterpart host->ops->match() callback. However, those are treated as
- * generic pointers by the core and the fact that it's actually a device-node
- * pointer is purely a convention between callers and implementation. This
- * code could thus be used on other architectures by replacing those two
- * by some sort of arch-specific void * "token" used to identify interrupt
- * controllers.
- */
-struct irq_host;
-struct radix_tree_root;
-
-/* Functions below are provided by the host and called whenever a new mapping
- * is created or an old mapping is disposed. The host can then proceed to
- * whatever internal data structures management is required. It also needs
- * to setup the irq_desc when returning from map().
- */
-struct irq_host_ops {
-        /* Match an interrupt controller device node to a host, returns
-         * 1 on a match
-         */
-        int (*match)(struct irq_host *h, struct device_node *node);
-
-        /* Create or update a mapping between a virtual irq number and a hw
-         * irq number. This is called only once for a given mapping.
-         */
-        int (*map)(struct irq_host *h, unsigned int virq, irq_hw_number_t hw);
-
-        /* Dispose of such a mapping */
-        void (*unmap)(struct irq_host *h, unsigned int virq);
-
-        /* Translate device-tree interrupt specifier from raw format coming
-         * from the firmware to a irq_hw_number_t (interrupt line number) and
-         * type (sense) that can be passed to set_irq_type(). In the absence
-         * of this callback, irq_create_of_mapping() and irq_of_parse_and_map()
-         * will return the hw number in the first cell and IRQ_TYPE_NONE for
-         * the type (which amount to keeping whatever default value the
-         * interrupt controller has for that line)
-         */
-        int (*xlate)(struct irq_host *h, struct device_node *ctrler,
-                     const u32 *intspec, unsigned int intsize,
-                     irq_hw_number_t *out_hwirq, unsigned int *out_type);
-};
-
-struct irq_host {
-        struct list_head        link;
-
-        /* type of reverse mapping technique */
-        unsigned int            revmap_type;
-#define IRQ_HOST_MAP_LEGACY     0 /* legacy 8259, gets irqs 1..15 */
-#define IRQ_HOST_MAP_NOMAP      1 /* no fast reverse mapping */
-#define IRQ_HOST_MAP_LINEAR     2 /* linear map of interrupts */
-#define IRQ_HOST_MAP_TREE       3 /* radix tree */
-        union {
-                struct {
-                        unsigned int size;
-                        unsigned int *revmap;
-                } linear;
-                struct radix_tree_root tree;
-        } revmap_data;
-        struct irq_host_ops     *ops;
-        void                    *host_data;
-        irq_hw_number_t         inval_irq;
-
-        /* Optional device node pointer */
-        struct device_node      *of_node;
-};
-
 struct irq_data;
 extern irq_hw_number_t irqd_to_hwirq(struct irq_data *d);
 extern irq_hw_number_t virq_to_hw(unsigned int virq);
-extern bool virq_is_host(unsigned int virq, struct irq_host *host);
-
-/**
- * irq_alloc_host - Allocate a new irq_host data structure
- * @of_node: optional device-tree node of the interrupt controller
- * @revmap_type: type of reverse mapping to use
- * @revmap_arg: for IRQ_HOST_MAP_LINEAR linear only: size of the map
- * @ops: map/unmap host callbacks
- * @inval_irq: provide a hw number in that host space that is always invalid
- *
- * Allocates and initialize and irq_host structure. Note that in the case of
- * IRQ_HOST_MAP_LEGACY, the map() callback will be called before this returns
- * for all legacy interrupts except 0 (which is always the invalid irq for
- * a legacy controller). For a IRQ_HOST_MAP_LINEAR, the map is allocated by
- * this call as well. For a IRQ_HOST_MAP_TREE, the radix tree will be allocated
- * later during boot automatically (the reverse mapping will use the slow path
- * until that happens).
- */
-extern struct irq_host *irq_alloc_host(struct device_node *of_node,
-                                       unsigned int revmap_type,
-                                       unsigned int revmap_arg,
-                                       struct irq_host_ops *ops,
-                                       irq_hw_number_t inval_irq);
-
-
-/**
- * irq_find_host - Locates a host for a given device node
- * @node: device-tree node of the interrupt controller
- */
-extern struct irq_host *irq_find_host(struct device_node *node);
-
-
-/**
- * irq_set_default_host - Set a "default" host
- * @host: default host pointer
- *
- * For convenience, it's possible to set a "default" host that will be used
- * whenever NULL is passed to irq_create_mapping(). It makes life easier for
- * platforms that want to manipulate a few hard coded interrupt numbers that
- * aren't properly represented in the device-tree.
- */
-extern void irq_set_default_host(struct irq_host *host);
-
-
-/**
- * irq_set_virq_count - Set the maximum number of virt irqs
- * @count: number of linux virtual irqs, capped with NR_IRQS
- *
- * This is mainly for use by platforms like iSeries who want to program
- * the virtual irq number in the controller to avoid the reverse mapping
- */
-extern void irq_set_virq_count(unsigned int count);
-
-
-/**
- * irq_create_mapping - Map a hardware interrupt into linux virq space
- * @host: host owning this hardware interrupt or NULL for default host
- * @hwirq: hardware irq number in that host space
- *
- * Only one mapping per hardware interrupt is permitted. Returns a linux
- * virq number.
- * If the sense/trigger is to be specified, set_irq_type() should be called
- * on the number returned from that call.
- */
-extern unsigned int irq_create_mapping(struct irq_host *host,
-                                       irq_hw_number_t hwirq);
-
-
-/**
- * irq_dispose_mapping - Unmap an interrupt
- * @virq: linux virq number of the interrupt to unmap
- */
-extern void irq_dispose_mapping(unsigned int virq);
-
-/**
- * irq_find_mapping - Find a linux virq from an hw irq number.
- * @host: host owning this hardware interrupt
- * @hwirq: hardware irq number in that host space
- *
- * This is a slow path, for use by generic code. It's expected that an
- * irq controller implementation directly calls the appropriate low level
- * mapping function.
- */
-extern unsigned int irq_find_mapping(struct irq_host *host,
-                                     irq_hw_number_t hwirq);
-
-/**
- * irq_create_direct_mapping - Allocate a virq for direct mapping
- * @host: host to allocate the virq for or NULL for default host
- *
- * This routine is used for irq controllers which can choose the hardware
- * interrupt numbers they generate. In such a case it's simplest to use
- * the linux virq as the hardware interrupt number.
- */
-extern unsigned int irq_create_direct_mapping(struct irq_host *host);
-
-/**
- * irq_radix_revmap_insert - Insert a hw irq to linux virq number mapping.
- * @host: host owning this hardware interrupt
- * @virq: linux irq number
- * @hwirq: hardware irq number in that host space
- *
- * This is for use by irq controllers that use a radix tree reverse
- * mapping for fast lookup.
- */
-extern void irq_radix_revmap_insert(struct irq_host *host, unsigned int virq,
-                                    irq_hw_number_t hwirq);
-
-/**
- * irq_radix_revmap_lookup - Find a linux virq from a hw irq number.
- * @host: host owning this hardware interrupt
- * @hwirq: hardware irq number in that host space
- *
- * This is a fast path, for use by irq controller code that uses radix tree
- * revmaps
- */
-extern unsigned int irq_radix_revmap_lookup(struct irq_host *host,
-                                            irq_hw_number_t hwirq);
-
-/**
- * irq_linear_revmap - Find a linux virq from a hw irq number.
- * @host: host owning this hardware interrupt
- * @hwirq: hardware irq number in that host space
- *
- * This is a fast path, for use by irq controller code that uses linear
- * revmaps. It does fallback to the slow path if the revmap doesn't exist
- * yet and will create the revmap entry with appropriate locking
- */
-
-extern unsigned int irq_linear_revmap(struct irq_host *host,
-                                      irq_hw_number_t hwirq);
-
-
-
-/**
- * irq_alloc_virt - Allocate virtual irq numbers
- * @host: host owning these new virtual irqs
- * @count: number of consecutive numbers to allocate
- * @hint: pass a hint number, the allocator will try to use a 1:1 mapping
- *
- * This is a low level function that is used internally by irq_create_mapping()
- * and that can be used by some irq controllers implementations for things
- * like allocating ranges of numbers for MSIs. The revmaps are left untouched.
- */
-extern unsigned int irq_alloc_virt(struct irq_host *host,
-                                   unsigned int count,
-                                   unsigned int hint);
-
-/**
- * irq_free_virt - Free virtual irq numbers
- * @virq: virtual irq number of the first interrupt to free
- * @count: number of interrupts to free
- *
- * This function is the opposite of irq_alloc_virt. It will not clear reverse
- * maps, this should be done previously by unmap'ing the interrupt. In fact,
- * all interrupts covered by the range being freed should have been unmapped
- * prior to calling this.
- */
-extern void irq_free_virt(unsigned int virq, unsigned int count);
 
 /**
  * irq_early_init - Init irq remapping subsystem
diff --git a/arch/powerpc/include/asm/irqflags.h b/arch/powerpc/include/asm/irqflags.h
index b0b06d85788d..6f9b6e23dc5a 100644
--- a/arch/powerpc/include/asm/irqflags.h
+++ b/arch/powerpc/include/asm/irqflags.h
@@ -39,24 +39,31 @@
 #define TRACE_ENABLE_INTS       TRACE_WITH_FRAME_BUFFER(.trace_hardirqs_on)
 #define TRACE_DISABLE_INTS      TRACE_WITH_FRAME_BUFFER(.trace_hardirqs_off)
 
-#define TRACE_AND_RESTORE_IRQ_PARTIAL(en,skip)          \
-        cmpdi   en,0;                                   \
-        bne     95f;                                    \
-        stb     en,PACASOFTIRQEN(r13);                  \
-        TRACE_WITH_FRAME_BUFFER(.trace_hardirqs_off)    \
-        b       skip;                                   \
-95:     TRACE_WITH_FRAME_BUFFER(.trace_hardirqs_on)     \
-        li      en,1;
-#define TRACE_AND_RESTORE_IRQ(en)               \
-        TRACE_AND_RESTORE_IRQ_PARTIAL(en,96f);  \
-        stb     en,PACASOFTIRQEN(r13);          \
-96:
+/*
+ * This is used by assembly code to soft-disable interrupts
+ */
+#define SOFT_DISABLE_INTS(__rA, __rB)           \
+        lbz     __rA,PACASOFTIRQEN(r13);        \
+        lbz     __rB,PACAIRQHAPPENED(r13);      \
+        cmpwi   cr0,__rA,0;                     \
+        li      __rA,0;                         \
+        ori     __rB,__rB,PACA_IRQ_HARD_DIS;    \
+        stb     __rB,PACAIRQHAPPENED(r13);      \
+        beq     44f;                            \
+        stb     __rA,PACASOFTIRQEN(r13);        \
+        TRACE_DISABLE_INTS;                     \
+44:
+
 #else
 #define TRACE_ENABLE_INTS
 #define TRACE_DISABLE_INTS
-#define TRACE_AND_RESTORE_IRQ_PARTIAL(en,skip)
-#define TRACE_AND_RESTORE_IRQ(en)               \
-        stb     en,PACASOFTIRQEN(r13)
+
+#define SOFT_DISABLE_INTS(__rA, __rB)           \
+        lbz     __rA,PACAIRQHAPPENED(r13);      \
+        li      __rB,0;                         \
+        ori     __rA,__rA,PACA_IRQ_HARD_DIS;    \
+        stb     __rB,PACASOFTIRQEN(r13);        \
+        stb     __rA,PACAIRQHAPPENED(r13)
 #endif
 #endif
 
diff --git a/arch/powerpc/include/asm/iseries/alpaca.h b/arch/powerpc/include/asm/iseries/alpaca.h
deleted file mode 100644
index c0cce6727a69..000000000000
--- a/arch/powerpc/include/asm/iseries/alpaca.h
+++ /dev/null
@@ -1,31 +0,0 @@
-/*
- * Copyright © 2008  Stephen Rothwell 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.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
- */
-#ifndef _ASM_POWERPC_ISERIES_ALPACA_H
-#define _ASM_POWERPC_ISERIES_ALPACA_H
-
-/*
- * This is the part of the paca that the iSeries hypervisor
- * needs to be statically initialised. Immediately after boot
- * we switch to the normal Linux paca.
- */
-struct alpaca {
-        struct lppaca *lppaca_ptr;      /* Pointer to LpPaca for PLIC */
-        const void *reg_save_ptr;       /* Pointer to LpRegSave for PLIC */
-};
-
-#endif /* _ASM_POWERPC_ISERIES_ALPACA_H */
diff --git a/arch/powerpc/include/asm/iseries/hv_call.h b/arch/powerpc/include/asm/iseries/hv_call.h
deleted file mode 100644
index 162d653ad51f..000000000000
--- a/arch/powerpc/include/asm/iseries/hv_call.h
+++ /dev/null
@@ -1,111 +0,0 @@
-/*
- * Copyright (C) 2001  Mike Corrigan 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.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
- *
- * This file contains the "hypervisor call" interface which is used to
- * drive the hypervisor from the OS.
- */
-#ifndef _ASM_POWERPC_ISERIES_HV_CALL_H
-#define _ASM_POWERPC_ISERIES_HV_CALL_H
-
-#include <asm/iseries/hv_call_sc.h>
-#include <asm/iseries/hv_types.h>
-#include <asm/paca.h>
-
-/* Type of yield for HvCallBaseYieldProcessor */
-#define HvCall_YieldTimed       0       /* Yield until specified time (tb) */
-#define HvCall_YieldToActive    1       /* Yield until all active procs have run */
-#define HvCall_YieldToProc      2       /* Yield until the specified processor has run */
-
-/* interrupt masks for setEnabledInterrupts */
-#define HvCall_MaskIPI          0x00000001
-#define HvCall_MaskLpEvent      0x00000002
-#define HvCall_MaskLpProd       0x00000004
-#define HvCall_MaskTimeout      0x00000008
-
-/* Log buffer formats */
-#define HvCall_LogBuffer_ASCII          0
-#define HvCall_LogBuffer_EBCDIC         1
-
-#define HvCallBaseAckDeferredInts                       HvCallBase +  0
-#define HvCallBaseCpmPowerOff                           HvCallBase +  1
-#define HvCallBaseGetHwPatch                            HvCallBase +  2
-#define HvCallBaseReIplSpAttn                           HvCallBase +  3
-#define HvCallBaseSetASR                                HvCallBase +  4
-#define HvCallBaseSetASRAndRfi                          HvCallBase +  5
-#define HvCallBaseSetIMR                                HvCallBase +  6
-#define HvCallBaseSendIPI                               HvCallBase +  7
-#define HvCallBaseTerminateMachine                      HvCallBase +  8
-#define HvCallBaseTerminateMachineSrc                   HvCallBase +  9
-#define HvCallBaseProcessPlicInterrupts                 HvCallBase + 10
-#define HvCallBaseIsPrimaryCpmOrMsdIpl                  HvCallBase + 11
-#define HvCallBaseSetVirtualSIT                         HvCallBase + 12
-#define HvCallBaseVaryOffThisProcessor                  HvCallBase + 13
-#define HvCallBaseVaryOffMemoryChunk                    HvCallBase + 14
-#define HvCallBaseVaryOffInteractivePercentage          HvCallBase + 15
-#define HvCallBaseSendLpProd                            HvCallBase + 16
-#define HvCallBaseSetEnabledInterrupts                  HvCallBase + 17
-#define HvCallBaseYieldProcessor                        HvCallBase + 18
-#define HvCallBaseVaryOffSharedProcUnits                HvCallBase + 19
-#define HvCallBaseSetVirtualDecr                        HvCallBase + 20
-#define HvCallBaseClearLogBuffer                        HvCallBase + 21
-#define HvCallBaseGetLogBufferCodePage                  HvCallBase + 22
-#define HvCallBaseGetLogBufferFormat                    HvCallBase + 23
-#define HvCallBaseGetLogBufferLength                    HvCallBase + 24
-#define HvCallBaseReadLogBuffer                         HvCallBase + 25
-#define HvCallBaseSetLogBufferFormatAndCodePage         HvCallBase + 26
-#define HvCallBaseWriteLogBuffer                        HvCallBase + 27
-#define HvCallBaseRouter28                              HvCallBase + 28
-#define HvCallBaseRouter29                              HvCallBase + 29
-#define HvCallBaseRouter30                              HvCallBase + 30
-#define HvCallBaseSetDebugBus                           HvCallBase + 31
-
-#define HvCallCcSetDABR                                 HvCallCc + 7
-
-static inline void HvCall_setVirtualDecr(void)
-{
-        /*
-         * Ignore any error return codes - most likely means that the
-         * target value for the LP has been increased and this vary off
-         * would bring us below the new target.
-         */
-        HvCall0(HvCallBaseSetVirtualDecr);
-}
-
-static inline void HvCall_yieldProcessor(unsigned typeOfYield, u64 yieldParm)
-{
-        HvCall2(HvCallBaseYieldProcessor, typeOfYield, yieldParm);
-}
-
-static inline void HvCall_setEnabledInterrupts(u64 enabledInterrupts)
-{
-        HvCall1(HvCallBaseSetEnabledInterrupts, enabledInterrupts);
-}
-
-static inline void HvCall_setLogBufferFormatAndCodepage(int format,
-                u32 codePage)
-{
-        HvCall2(HvCallBaseSetLogBufferFormatAndCodePage, format, codePage);
-}
-
-extern void HvCall_writeLogBuffer(const void *buffer, u64 bufLen);
-
-static inline void HvCall_sendIPI(struct paca_struct *targetPaca)
-{
-        HvCall1(HvCallBaseSendIPI, targetPaca->paca_index);
-}
-
-#endif /* _ASM_POWERPC_ISERIES_HV_CALL_H */
diff --git a/arch/powerpc/include/asm/iseries/hv_call_event.h b/arch/powerpc/include/asm/iseries/hv_call_event.h
deleted file mode 100644
index cc029d388e11..000000000000
--- a/arch/powerpc/include/asm/iseries/hv_call_event.h
+++ /dev/null
@@ -1,201 +0,0 @@
-/*
- * Copyright (C) 2001  Mike Corrigan 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.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
- *
- * This file contains the "hypervisor call" interface which is used to
- * drive the hypervisor from the OS.
- */
-#ifndef _ASM_POWERPC_ISERIES_HV_CALL_EVENT_H
-#define _ASM_POWERPC_ISERIES_HV_CALL_EVENT_H
-
-#include <linux/types.h>
-#include <linux/dma-mapping.h>
-
-#include <asm/iseries/hv_call_sc.h>
-#include <asm/iseries/hv_types.h>
-#include <asm/abs_addr.h>
-
-struct HvLpEvent;
-
-typedef u8 HvLpEvent_Type;
-typedef u8 HvLpEvent_AckInd;
-typedef u8 HvLpEvent_AckType;
-
-typedef u8 HvLpDma_Direction;
-typedef u8 HvLpDma_AddressType;
-
-typedef u64 HvLpEvent_Rc;
-typedef u64 HvLpDma_Rc;
-
-#define HvCallEventAckLpEvent                           HvCallEvent +  0
-#define HvCallEventCancelLpEvent                        HvCallEvent +  1
-#define HvCallEventCloseLpEventPath                     HvCallEvent +  2
-#define HvCallEventDmaBufList                           HvCallEvent +  3
-#define HvCallEventDmaSingle                            HvCallEvent +  4
-#define HvCallEventDmaToSp                              HvCallEvent +  5
-#define HvCallEventGetOverflowLpEvents                  HvCallEvent +  6
-#define HvCallEventGetSourceLpInstanceId                HvCallEvent +  7
-#define HvCallEventGetTargetLpInstanceId                HvCallEvent +  8
-#define HvCallEventOpenLpEventPath                      HvCallEvent +  9
-#define HvCallEventSetLpEventStack                      HvCallEvent + 10
-#define HvCallEventSignalLpEvent                        HvCallEvent + 11
-#define HvCallEventSignalLpEventParms                   HvCallEvent + 12
-#define HvCallEventSetInterLpQueueIndex                 HvCallEvent + 13
-#define HvCallEventSetLpEventQueueInterruptProc         HvCallEvent + 14
-#define HvCallEventRouter15                             HvCallEvent + 15
-
-static inline void HvCallEvent_getOverflowLpEvents(u8 queueIndex)
-{
-        HvCall1(HvCallEventGetOverflowLpEvents, queueIndex);
-}
-
-static inline void HvCallEvent_setInterLpQueueIndex(u8 queueIndex)
-{
-        HvCall1(HvCallEventSetInterLpQueueIndex, queueIndex);
-}
-
-static inline void HvCallEvent_setLpEventStack(u8 queueIndex,
-                char *eventStackAddr, u32 eventStackSize)
-{
-        HvCall3(HvCallEventSetLpEventStack, queueIndex,
-                        virt_to_abs(eventStackAddr), eventStackSize);
-}
-
-static inline void HvCallEvent_setLpEventQueueInterruptProc(u8 queueIndex,
-                u16 lpLogicalProcIndex)
-{
-        HvCall2(HvCallEventSetLpEventQueueInterruptProc, queueIndex,
-                        lpLogicalProcIndex);
-}
-
-static inline HvLpEvent_Rc HvCallEvent_signalLpEvent(struct HvLpEvent *event)
-{
-        return HvCall1(HvCallEventSignalLpEvent, virt_to_abs(event));
-}
-
-static inline HvLpEvent_Rc HvCallEvent_signalLpEventFast(HvLpIndex targetLp,
-                HvLpEvent_Type type, u16 subtype, HvLpEvent_AckInd ackInd,
-                HvLpEvent_AckType ackType, HvLpInstanceId sourceInstanceId,
-                HvLpInstanceId targetInstanceId, u64 correlationToken,
-                u64 eventData1, u64 eventData2, u64 eventData3,
-                u64 eventData4, u64 eventData5)
-{
-        /* Pack the misc bits into a single Dword to pass to PLIC */
-        union {
-                struct {
-                        u8              ack_and_target;
-                        u8              type;
-                        u16             subtype;
-                        HvLpInstanceId  src_inst;
-                        HvLpInstanceId  target_inst;
-                } parms;
-                u64             dword;
-        } packed;
-
-        packed.parms.ack_and_target = (ackType << 7) | (ackInd << 6) | targetLp;
-        packed.parms.type = type;
-        packed.parms.subtype = subtype;
-        packed.parms.src_inst = sourceInstanceId;
-        packed.parms.target_inst = targetInstanceId;
-
-        return HvCall7(HvCallEventSignalLpEventParms, packed.dword,
-                        correlationToken, eventData1, eventData2,
-                        eventData3, eventData4, eventData5);
-}
-
-extern void *iseries_hv_alloc(size_t size, dma_addr_t *dma_handle, gfp_t flag);
-extern void iseries_hv_free(size_t size, void *vaddr, dma_addr_t dma_handle);
-extern dma_addr_t iseries_hv_map(void *vaddr, size_t size,
-                        enum dma_data_direction direction);
-extern void iseries_hv_unmap(dma_addr_t dma_handle, size_t size,
-                        enum dma_data_direction direction);
-
-static inline HvLpEvent_Rc HvCallEvent_ackLpEvent(struct HvLpEvent *event)
-{
-        return HvCall1(HvCallEventAckLpEvent, virt_to_abs(event));
-}
-
-static inline HvLpEvent_Rc HvCallEvent_cancelLpEvent(struct HvLpEvent *event)
-{
-        return HvCall1(HvCallEventCancelLpEvent, virt_to_abs(event));
-}
-
-static inline HvLpInstanceId HvCallEvent_getSourceLpInstanceId(
-                HvLpIndex targetLp, HvLpEvent_Type type)
-{
-        return HvCall2(HvCallEventGetSourceLpInstanceId, targetLp, type);
-}
-
-static inline HvLpInstanceId HvCallEvent_getTargetLpInstanceId(
-                HvLpIndex targetLp, HvLpEvent_Type type)
-{
-        return HvCall2(HvCallEventGetTargetLpInstanceId, targetLp, type);
-}
-
-static inline void HvCallEvent_openLpEventPath(HvLpIndex targetLp,
-                HvLpEvent_Type type)
-{
-        HvCall2(HvCallEventOpenLpEventPath, targetLp, type);
-}
-
-static inline void HvCallEvent_closeLpEventPath(HvLpIndex targetLp,
-                HvLpEvent_Type type)
-{
-        HvCall2(HvCallEventCloseLpEventPath, targetLp, type);
-}
-
-static inline HvLpDma_Rc HvCallEvent_dmaBufList(HvLpEvent_Type type,
-                HvLpIndex remoteLp, HvLpDma_Direction direction,
-                HvLpInstanceId localInstanceId,
-                HvLpInstanceId remoteInstanceId,
-                HvLpDma_AddressType localAddressType,
-                HvLpDma_AddressType remoteAddressType,
-                /* Do these need to be converted to absolute addresses? */
-                u64 localBufList, u64 remoteBufList, u32 transferLength)
-{
-        /* Pack the misc bits into a single Dword to pass to PLIC */
-        union {
-                struct {
-                        u8              flags;
-                        HvLpIndex       remote;
-                        u8              type;
-                        u8              reserved;
-                        HvLpInstanceId  local_inst;
-                        HvLpInstanceId  remote_inst;
-                } parms;
-                u64             dword;
-        } packed;
-
-        packed.parms.flags = (direction << 7) |
-                (localAddressType << 6) | (remoteAddressType << 5);
-        packed.parms.remote = remoteLp;
-        packed.parms.type = type;
-        packed.parms.reserved = 0;
-        packed.parms.local_inst = localInstanceId;
-        packed.parms.remote_inst = remoteInstanceId;
-
-        return HvCall4(HvCallEventDmaBufList, packed.dword, localBufList,
-                        remoteBufList, transferLength);
-}
-
-static inline HvLpDma_Rc HvCallEvent_dmaToSp(void *local, u32 remote,
-                u32 length, HvLpDma_Direction dir)
-{
-        return HvCall4(HvCallEventDmaToSp, virt_to_abs(local), remote,
-                        length, dir);
-}
-
-#endif /* _ASM_POWERPC_ISERIES_HV_CALL_EVENT_H */
diff --git a/arch/powerpc/include/asm/iseries/hv_call_sc.h b/arch/powerpc/include/asm/iseries/hv_call_sc.h
deleted file mode 100644
index f5d210959250..000000000000
--- a/arch/powerpc/include/asm/iseries/hv_call_sc.h
+++ /dev/null
@@ -1,50 +0,0 @@
-/*
- * Copyright (C) 2001  Mike Corrigan 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.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
- */
-#ifndef _ASM_POWERPC_ISERIES_HV_CALL_SC_H
-#define _ASM_POWERPC_ISERIES_HV_CALL_SC_H
-
-#include <linux/types.h>
-
-#define HvCallBase              0x8000000000000000ul
-#define HvCallCc                0x8001000000000000ul
-#define HvCallCfg               0x8002000000000000ul
-#define HvCallEvent             0x8003000000000000ul
-#define HvCallHpt               0x8004000000000000ul
-#define HvCallPci               0x8005000000000000ul
-#define HvCallSm                0x8007000000000000ul
-#define HvCallXm                0x8009000000000000ul
-
-extern u64 HvCall0(u64);
-extern u64 HvCall1(u64, u64);
-extern u64 HvCall2(u64, u64, u64);
-extern u64 HvCall3(u64, u64, u64, u64);
-extern u64 HvCall4(u64, u64, u64, u64, u64);
-extern u64 HvCall5(u64, u64, u64, u64, u64, u64);
-extern u64 HvCall6(u64, u64, u64, u64, u64, u64, u64);
-extern u64 HvCall7(u64, u64, u64, u64, u64, u64, u64, u64);
-
-extern u64 HvCall0Ret16(u64, void *);
-extern u64 HvCall1Ret16(u64, void *, u64);
-extern u64 HvCall2Ret16(u64, void *, u64, u64);
-extern u64 HvCall3Ret16(u64, void *, u64, u64, u64);
-extern u64 HvCall4Ret16(u64, void *, u64, u64, u64, u64);
-extern u64 HvCall5Ret16(u64, void *, u64, u64, u64, u64, u64);
-extern u64 HvCall6Ret16(u64, void *, u64, u64, u64, u64, u64, u64);
-extern u64 HvCall7Ret16(u64, void *, u64, u64 ,u64 ,u64 ,u64 ,u64 ,u64);
-
-#endif /* _ASM_POWERPC_ISERIES_HV_CALL_SC_H */
diff --git a/arch/powerpc/include/asm/iseries/hv_call_xm.h b/arch/powerpc/include/asm/iseries/hv_call_xm.h
deleted file mode 100644
index 392ac3f54df0..000000000000
--- a/arch/powerpc/include/asm/iseries/hv_call_xm.h
+++ /dev/null
@@ -1,61 +0,0 @@
-/*
- * This file contains the "hypervisor call" interface which is used to
- * drive the hypervisor from SLIC.
- */
-#ifndef _ASM_POWERPC_ISERIES_HV_CALL_XM_H
-#define _ASM_POWERPC_ISERIES_HV_CALL_XM_H
-
-#include <asm/iseries/hv_call_sc.h>
-#include <asm/iseries/hv_types.h>
-
-#define HvCallXmGetTceTableParms        HvCallXm +  0
-#define HvCallXmTestBus                 HvCallXm +  1
-#define HvCallXmConnectBusUnit          HvCallXm +  2
-#define HvCallXmLoadTod                 HvCallXm +  8
-#define HvCallXmTestBusUnit             HvCallXm +  9
-#define HvCallXmSetTce                  HvCallXm + 11
-#define HvCallXmSetTces                 HvCallXm + 13
-
-static inline void HvCallXm_getTceTableParms(u64 cb)
-{
-        HvCall1(HvCallXmGetTceTableParms, cb);
-}
-
-static inline u64 HvCallXm_setTce(u64 tceTableToken, u64 tceOffset, u64 tce)
-{
-        return HvCall3(HvCallXmSetTce, tceTableToken, tceOffset, tce);
-}
-
-static inline u64 HvCallXm_setTces(u64 tceTableToken, u64 tceOffset,
-                u64 numTces, u64 tce1, u64 tce2, u64 tce3, u64 tce4)
-{
-        return HvCall7(HvCallXmSetTces, tceTableToken, tceOffset, numTces,
-                             tce1, tce2, tce3, tce4);
-}
-
-static inline u64 HvCallXm_testBus(u16 busNumber)
-{
-        return HvCall1(HvCallXmTestBus, busNumber);
-}
-
-static inline u64 HvCallXm_testBusUnit(u16 busNumber, u8 subBusNumber,
-                u8 deviceId)
-{
-        return HvCall2(HvCallXmTestBusUnit, busNumber,
-                        (subBusNumber << 8) | deviceId);
-}
-
-static inline u64 HvCallXm_connectBusUnit(u16 busNumber, u8 subBusNumber,
-                u8 deviceId, u64 interruptToken)
-{
-        return HvCall5(HvCallXmConnectBusUnit, busNumber,
-                        (subBusNumber << 8) | deviceId, interruptToken, 0,
-                        0 /* HvLpConfig::mapDsaToQueueIndex(HvLpDSA(busNumber, xBoard, xCard)) */);
-}
-
-static inline u64 HvCallXm_loadTod(void)
-{
-        return HvCall0(HvCallXmLoadTod);
-}
-
-#endif /* _ASM_POWERPC_ISERIES_HV_CALL_XM_H */
diff --git a/arch/powerpc/include/asm/iseries/hv_lp_config.h b/arch/powerpc/include/asm/iseries/hv_lp_config.h
deleted file mode 100644
index a006fd1e4a2c..000000000000
--- a/arch/powerpc/include/asm/iseries/hv_lp_config.h
+++ /dev/null
@@ -1,128 +0,0 @@
-/*
- * Copyright (C) 2001  Mike Corrigan 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.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
- */
-#ifndef _ASM_POWERPC_ISERIES_HV_LP_CONFIG_H
-#define _ASM_POWERPC_ISERIES_HV_LP_CONFIG_H
-
-/*
- * This file contains the interface to the LPAR configuration data
- * to determine which resources should be allocated to each partition.
- */
-
-#include <asm/iseries/hv_call_sc.h>
-#include <asm/iseries/hv_types.h>
-
-enum {
-        HvCallCfg_Cur   = 0,
-        HvCallCfg_Init  = 1,
-        HvCallCfg_Max   = 2,
-        HvCallCfg_Min   = 3
-};
-
-#define HvCallCfgGetSystemPhysicalProcessors            HvCallCfg +  6
-#define HvCallCfgGetPhysicalProcessors                  HvCallCfg +  7
-#define HvCallCfgGetMsChunks                            HvCallCfg +  9
-#define HvCallCfgGetSharedPoolIndex                     HvCallCfg + 20
-#define HvCallCfgGetSharedProcUnits                     HvCallCfg + 21
-#define HvCallCfgGetNumProcsInSharedPool                HvCallCfg + 22
-#define HvCallCfgGetVirtualLanIndexMap                  HvCallCfg + 30
-#define HvCallCfgGetHostingLpIndex                      HvCallCfg + 32
-
-extern HvLpIndex HvLpConfig_getLpIndex_outline(void);
-extern HvLpIndex HvLpConfig_getLpIndex(void);
-extern HvLpIndex HvLpConfig_getPrimaryLpIndex(void);
-
-static inline u64 HvLpConfig_getMsChunks(void)
-{
-        return HvCall2(HvCallCfgGetMsChunks, HvLpConfig_getLpIndex(),
-                        HvCallCfg_Cur);
-}
-
-static inline u64 HvLpConfig_getSystemPhysicalProcessors(void)
-{
-        return HvCall0(HvCallCfgGetSystemPhysicalProcessors);
-}
-
-static inline u64 HvLpConfig_getNumProcsInSharedPool(HvLpSharedPoolIndex sPI)
-{
-        return (u16)HvCall1(HvCallCfgGetNumProcsInSharedPool, sPI);
-}
-
-static inline u64 HvLpConfig_getPhysicalProcessors(void)
-{
-        return HvCall2(HvCallCfgGetPhysicalProcessors, HvLpConfig_getLpIndex(),
-                        HvCallCfg_Cur);
-}
-
-static inline HvLpSharedPoolIndex HvLpConfig_getSharedPoolIndex(void)
-{
-        return HvCall1(HvCallCfgGetSharedPoolIndex, HvLpConfig_getLpIndex());
-}
-
-static inline u64 HvLpConfig_getSharedProcUnits(void)
-{
-        return HvCall2(HvCallCfgGetSharedProcUnits, HvLpConfig_getLpIndex(),
-                        HvCallCfg_Cur);
-}
-
-static inline u64 HvLpConfig_getMaxSharedProcUnits(void)
-{
-        return HvCall2(HvCallCfgGetSharedProcUnits, HvLpConfig_getLpIndex(),
-                        HvCallCfg_Max);
-}
-
-static inline u64 HvLpConfig_getMaxPhysicalProcessors(void)
-{
-        return HvCall2(HvCallCfgGetPhysicalProcessors, HvLpConfig_getLpIndex(),
-                        HvCallCfg_Max);
-}
-
-static inline HvLpVirtualLanIndexMap HvLpConfig_getVirtualLanIndexMapForLp(
-                HvLpIndex lp)
-{
-        /*
-         * This is a new function in V5R1 so calls to this on older
-         * hypervisors will return -1
-         */
-        u64 retVal = HvCall1(HvCallCfgGetVirtualLanIndexMap, lp);
-        if (retVal == -1)
-                retVal = 0;
-        return retVal;
-}
-
-static inline HvLpVirtualLanIndexMap HvLpConfig_getVirtualLanIndexMap(void)
-{
-        return HvLpConfig_getVirtualLanIndexMapForLp(
-                        HvLpConfig_getLpIndex_outline());
-}
-
-static inline int HvLpConfig_doLpsCommunicateOnVirtualLan(HvLpIndex lp1,
-                HvLpIndex lp2)
-{
-        HvLpVirtualLanIndexMap virtualLanIndexMap1 =
-                HvLpConfig_getVirtualLanIndexMapForLp(lp1);
-        HvLpVirtualLanIndexMap virtualLanIndexMap2 =
-                HvLpConfig_getVirtualLanIndexMapForLp(lp2);
-        return ((virtualLanIndexMap1 & virtualLanIndexMap2) != 0);
-}
-
-static inline HvLpIndex HvLpConfig_getHostingLpIndex(HvLpIndex lp)
-{
-        return HvCall1(HvCallCfgGetHostingLpIndex, lp);
-}
-
-#endif /* _ASM_POWERPC_ISERIES_HV_LP_CONFIG_H */
diff --git a/arch/powerpc/include/asm/iseries/hv_lp_event.h b/arch/powerpc/include/asm/iseries/hv_lp_event.h
deleted file mode 100644
index 8f5da7d77202..000000000000
--- a/arch/powerpc/include/asm/iseries/hv_lp_event.h
+++ /dev/null
@@ -1,162 +0,0 @@
-/*
- * Copyright (C) 2001  Mike Corrigan 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.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
- */
-
-/* This file contains the class for HV events in the system. */
-
-#ifndef _ASM_POWERPC_ISERIES_HV_LP_EVENT_H
-#define _ASM_POWERPC_ISERIES_HV_LP_EVENT_H
-
-#include <asm/types.h>
-#include <asm/ptrace.h>
-#include <asm/iseries/hv_types.h>
-#include <asm/iseries/hv_call_event.h>
-
-/*
- * HvLpEvent is the structure for Lp Event messages passed between
- * partitions through PLIC.
- */
-
-struct HvLpEvent {
-        u8      flags;                  /* Event flags                x00-x00 */
-        u8      xType;                  /* Type of message            x01-x01 */
-        u16     xSubtype;               /* Subtype for event          x02-x03 */
-        u8      xSourceLp;              /* Source LP                  x04-x04 */
-        u8      xTargetLp;              /* Target LP                  x05-x05 */
-        u8      xSizeMinus1;            /* Size of Derived class - 1  x06-x06 */
-        u8      xRc;                    /* RC for Ack flows           x07-x07 */
-        u16     xSourceInstanceId;      /* Source sides instance id   x08-x09 */
-        u16     xTargetInstanceId;      /* Target sides instance id   x0A-x0B */
-        union {
-                u32     xSubtypeData;   /* Data usable by the subtype x0C-x0F */
-                u16     xSubtypeDataShort[2];   /* Data as 2 shorts */
-                u8      xSubtypeDataChar[4];    /* Data as 4 chars */
-        } x;
-
-        u64     xCorrelationToken;      /* Unique value for source/type x10-x17 */
-};
-
-typedef void (*LpEventHandler)(struct HvLpEvent *);
-
-/* Register a handler for an event type - returns 0 on success */
-extern int HvLpEvent_registerHandler(HvLpEvent_Type eventType,
-                LpEventHandler hdlr);
-
-/*
- * Unregister a handler for an event type
- *
- * This call will sleep until the handler being removed is guaranteed to
- * be no longer executing on any CPU. Do not call with locks held.
- *
- *  returns 0 on success
- *  Unregister will fail if there are any paths open for the type
- */
-extern int HvLpEvent_unregisterHandler(HvLpEvent_Type eventType);
-
-/*
- * Open an Lp Event Path for an event type
- * returns 0 on success
- * openPath will fail if there is no handler registered for the event type.
- * The lpIndex specified is the partition index for the target partition
- * (for VirtualIo, VirtualLan and SessionMgr) other types specify zero)
- */
-extern int HvLpEvent_openPath(HvLpEvent_Type eventType, HvLpIndex lpIndex);
-
-/*
- * Close an Lp Event Path for a type and partition
- * returns 0 on success
- */
-extern int HvLpEvent_closePath(HvLpEvent_Type eventType, HvLpIndex lpIndex);
-
-#define HvLpEvent_Type_Hypervisor 0
-#define HvLpEvent_Type_MachineFac 1
-#define HvLpEvent_Type_SessionMgr 2
-#define HvLpEvent_Type_SpdIo      3
-#define HvLpEvent_Type_VirtualBus 4
-#define HvLpEvent_Type_PciIo      5
-#define HvLpEvent_Type_RioIo      6
-#define HvLpEvent_Type_VirtualLan 7
-#define HvLpEvent_Type_VirtualIo  8
-#define HvLpEvent_Type_NumTypes   9
-
-#define HvLpEvent_Rc_Good 0
-#define HvLpEvent_Rc_BufferNotAvailable 1
-#define HvLpEvent_Rc_Cancelled 2
-#define HvLpEvent_Rc_GenericError 3
-#define HvLpEvent_Rc_InvalidAddress 4
-#define HvLpEvent_Rc_InvalidPartition 5
-#define HvLpEvent_Rc_InvalidSize 6
-#define HvLpEvent_Rc_InvalidSubtype 7
-#define HvLpEvent_Rc_InvalidSubtypeData 8
-#define HvLpEvent_Rc_InvalidType 9
-#define HvLpEvent_Rc_PartitionDead 10
-#define HvLpEvent_Rc_PathClosed 11
-#define HvLpEvent_Rc_SubtypeError 12
-
-#define HvLpEvent_Function_Ack 0
-#define HvLpEvent_Function_Int 1
-
-#define HvLpEvent_AckInd_NoAck 0
-#define HvLpEvent_AckInd_DoAck 1
-
-#define HvLpEvent_AckType_ImmediateAck 0
-#define HvLpEvent_AckType_DeferredAck 1
-
-#define HV_LP_EVENT_INT                 0x01
-#define HV_LP_EVENT_DO_ACK              0x02
-#define HV_LP_EVENT_DEFERRED_ACK        0x04
-#define HV_LP_EVENT_VALID               0x80
-
-#define HvLpDma_Direction_LocalToRemote 0
-#define HvLpDma_Direction_RemoteToLocal 1
-
-#define HvLpDma_AddressType_TceIndex 0
-#define HvLpDma_AddressType_RealAddress 1
-
-#define HvLpDma_Rc_Good 0
-#define HvLpDma_Rc_Error 1
-#define HvLpDma_Rc_PartitionDead 2
-#define HvLpDma_Rc_PathClosed 3
-#define HvLpDma_Rc_InvalidAddress 4
-#define HvLpDma_Rc_InvalidLength 5
-
-static inline int hvlpevent_is_valid(struct HvLpEvent *h)
-{
-        return h->flags & HV_LP_EVENT_VALID;
-}
-
-static inline void hvlpevent_invalidate(struct HvLpEvent *h)
-{
-        h->flags &= ~ HV_LP_EVENT_VALID;
-}
-
-static inline int hvlpevent_is_int(struct HvLpEvent *h)
-{
-        return h->flags & HV_LP_EVENT_INT;
-}
-
-static inline int hvlpevent_is_ack(struct HvLpEvent *h)
-{
-        return !hvlpevent_is_int(h);
-}
-
-static inline int hvlpevent_need_ack(struct HvLpEvent *h)
-{
-        return h->flags & HV_LP_EVENT_DO_ACK;
-}
-
-#endif /* _ASM_POWERPC_ISERIES_HV_LP_EVENT_H */
diff --git a/arch/powerpc/include/asm/iseries/hv_types.h b/arch/powerpc/include/asm/iseries/hv_types.h
deleted file mode 100644
index c3e6d2a1d1c3..000000000000
--- a/arch/powerpc/include/asm/iseries/hv_types.h
+++ /dev/null
@@ -1,112 +0,0 @@
-/*
- * Copyright (C) 2001  Mike Corrigan 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.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
- */
-#ifndef _ASM_POWERPC_ISERIES_HV_TYPES_H
-#define _ASM_POWERPC_ISERIES_HV_TYPES_H
-
-/*
- * General typedefs for the hypervisor.
- */
-
-#include <asm/types.h>
-
-typedef u8      HvLpIndex;
-typedef u16     HvLpInstanceId;
-typedef u64     HvLpTOD;
-typedef u64     HvLpSystemSerialNum;
-typedef u8      HvLpDeviceSerialNum[12];
-typedef u16     HvLpSanHwSet;
-typedef u16     HvLpBus;
-typedef u16     HvLpBoard;
-typedef u16     HvLpCard;
-typedef u8      HvLpDeviceType[4];
-typedef u8      HvLpDeviceModel[3];
-typedef u64     HvIoToken;
-typedef u8      HvLpName[8];
-typedef u32     HvIoId;
-typedef u64     HvRealMemoryIndex;
-typedef u32     HvLpIndexMap;   /* Must hold HVMAXARCHITECTEDLPS bits!!! */
-typedef u16     HvLpVrmIndex;
-typedef u32     HvXmGenerationId;
-typedef u8      HvLpBusPool;
-typedef u8      HvLpSharedPoolIndex;
-typedef u16     HvLpSharedProcUnitsX100;
-typedef u8      HvLpVirtualLanIndex;
-typedef u16     HvLpVirtualLanIndexMap; /* Must hold HVMAXARCHITECTEDVIRTUALLANS bits!!! */
-typedef u16     HvBusNumber;    /* Hypervisor Bus Number */
-typedef u8      HvSubBusNumber; /* Hypervisor SubBus Number */
-typedef u8      HvAgentId;      /* Hypervisor DevFn */
-
-
-#define HVMAXARCHITECTEDLPS             32
-#define HVMAXARCHITECTEDVIRTUALLANS     16
-#define HVMAXARCHITECTEDVIRTUALDISKS    32
-#define HVMAXARCHITECTEDVIRTUALCDROMS   8
-#define HVMAXARCHITECTEDVIRTUALTAPES    8
-#define HVCHUNKSIZE                     (256 * 1024)
-#define HVPAGESIZE                      (4 * 1024)
-#define HVLPMINMEGSPRIMARY              256
-#define HVLPMINMEGSSECONDARY            64
-#define HVCHUNKSPERMEG                  4
-#define HVPAGESPERMEG                   256
-#define HVPAGESPERCHUNK                 64
-
-#define HvLpIndexInvalid                ((HvLpIndex)0xff)
-
-/*
- * Enums for the sub-components under PLIC
- * Used in HvCall  and HvPrimaryCall
- */
-enum {
-        HvCallCompId = 0,
-        HvCallCpuCtlsCompId = 1,
-        HvCallCfgCompId = 2,
-        HvCallEventCompId = 3,
-        HvCallHptCompId = 4,
-        HvCallPciCompId = 5,
-        HvCallSlmCompId = 6,
-        HvCallSmCompId = 7,
-        HvCallSpdCompId = 8,
-        HvCallXmCompId = 9,
-        HvCallRioCompId = 10,
-        HvCallRsvd3CompId = 11,
-        HvCallRsvd2CompId = 12,
-        HvCallRsvd1CompId = 13,
-        HvCallMaxCompId = 14,
-        HvPrimaryCallCompId = 0,
-        HvPrimaryCallCfgCompId = 1,
-        HvPrimaryCallPciCompId = 2,
-        HvPrimaryCallSmCompId = 3,
-        HvPrimaryCallSpdCompId = 4,
-        HvPrimaryCallXmCompId = 5,
-        HvPrimaryCallRioCompId = 6,
-        HvPrimaryCallRsvd7CompId = 7,
-        HvPrimaryCallRsvd6CompId = 8,
-        HvPrimaryCallRsvd5CompId = 9,
-        HvPrimaryCallRsvd4CompId = 10,
-        HvPrimaryCallRsvd3CompId = 11,
-        HvPrimaryCallRsvd2CompId = 12,
-        HvPrimaryCallRsvd1CompId = 13,
-        HvPrimaryCallMaxCompId = HvCallMaxCompId
-};
-
-struct HvLpBufferList {
-        u64 addr;
-        u64 len;
-};
-
-#endif /* _ASM_POWERPC_ISERIES_HV_TYPES_H */
diff --git a/arch/powerpc/include/asm/iseries/iommu.h b/arch/powerpc/include/asm/iseries/iommu.h
deleted file mode 100644
index 1b9692c60899..000000000000
--- a/arch/powerpc/include/asm/iseries/iommu.h
+++ /dev/null
@@ -1,37 +0,0 @@
-#ifndef _ASM_POWERPC_ISERIES_IOMMU_H
-#define _ASM_POWERPC_ISERIES_IOMMU_H
-
-/*
- * Copyright (C) 2005  Stephen Rothwell, 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.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the:
- * Free Software Foundation, Inc.,
- * 59 Temple Place, Suite 330,
- * Boston, MA  02111-1307  USA
- */
-
-struct pci_dev;
-struct vio_dev;
-struct device_node;
-struct iommu_table;
-
-/* Get table parameters from HV */
-extern void iommu_table_getparms_iSeries(unsigned long busno,
-                unsigned char slotno, unsigned char virtbus,
-                struct iommu_table *tbl);
-
-extern struct iommu_table *vio_build_iommu_table_iseries(struct vio_dev *dev);
-extern void iommu_vio_init(void);
-
-#endif /* _ASM_POWERPC_ISERIES_IOMMU_H */
diff --git a/arch/powerpc/include/asm/iseries/it_lp_queue.h b/arch/powerpc/include/asm/iseries/it_lp_queue.h
deleted file mode 100644
index 428278838821..000000000000
--- a/arch/powerpc/include/asm/iseries/it_lp_queue.h
+++ /dev/null
@@ -1,78 +0,0 @@
-/*
- * Copyright (C) 2001  Mike Corrigan 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.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
- */
-#ifndef _ASM_POWERPC_ISERIES_IT_LP_QUEUE_H
-#define _ASM_POWERPC_ISERIES_IT_LP_QUEUE_H
-
-/*
- *      This control block defines the simple LP queue structure that is
- *      shared between the hypervisor (PLIC) and the OS in order to send
- *      events to an LP.
- */
-
-#include <asm/types.h>
-#include <asm/ptrace.h>
-
-#define IT_LP_MAX_QUEUES        8
-
-#define IT_LP_NOT_USED          0       /* Queue will not be used by PLIC */
-#define IT_LP_DEDICATED_IO      1       /* Queue dedicated to IO processor specified */
-#define IT_LP_DEDICATED_LP      2       /* Queue dedicated to LP specified */
-#define IT_LP_SHARED            3       /* Queue shared for both IO and LP */
-
-#define IT_LP_EVENT_STACK_SIZE  4096
-#define IT_LP_EVENT_MAX_SIZE    256
-#define IT_LP_EVENT_ALIGN       64
-
-struct hvlpevent_queue {
-/*
- * The hq_current_event is the pointer to the next event stack entry
- * that will become valid.  The OS must peek at this entry to determine
- * if it is valid.  PLIC will set the valid indicator as the very last
- * store into that entry.
- *
- * When the OS has completed processing of the event then it will mark
- * the event as invalid so that PLIC knows it can store into that event
- * location again.
- *
- * If the event stack fills and there are overflow events, then PLIC
- * will set the hq_overflow_pending flag in which case the OS will
- * have to fetch the additional LP events once they have drained the
- * event stack.
- *
- * The first 16-bytes are known by both the OS and PLIC.  The remainder
- * of the cache line is for use by the OS.
- */
-        u8              hq_overflow_pending;    /* 0x00 Overflow events are pending */
-        u8              hq_status;              /* 0x01 DedicatedIo or DedicatedLp or NotUsed */
-        u16             hq_proc_index;          /* 0x02 Logical Proc Index for correlation */
-        u8              hq_reserved1[12];       /* 0x04 */
-        char            *hq_current_event;      /* 0x10 */
-        char            *hq_last_event;         /* 0x18 */
-        char            *hq_event_stack;        /* 0x20 */
-        u8              hq_index;               /* 0x28 unique sequential index. */
-        u8              hq_reserved2[3];        /* 0x29-2b */
-        spinlock_t      hq_lock;
-};
-
-extern struct hvlpevent_queue hvlpevent_queue;
-
-extern int hvlpevent_is_pending(void);
-extern void process_hvlpevents(void);
-extern void setup_hvlpevent_queue(void);
-
-#endif /* _ASM_POWERPC_ISERIES_IT_LP_QUEUE_H */
diff --git a/arch/powerpc/include/asm/iseries/lpar_map.h b/arch/powerpc/include/asm/iseries/lpar_map.h
deleted file mode 100644
index 5e9f3e128ee2..000000000000
--- a/arch/powerpc/include/asm/iseries/lpar_map.h
+++ /dev/null
@@ -1,85 +0,0 @@
-/*
- * Copyright (C) 2001  Mike Corrigan 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.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
- */
-#ifndef _ASM_POWERPC_ISERIES_LPAR_MAP_H
-#define _ASM_POWERPC_ISERIES_LPAR_MAP_H
-
-#ifndef __ASSEMBLY__
-
-#include <asm/types.h>
-
-#endif
-
-/*
- * The iSeries hypervisor will set up mapping for one or more
- * ESID/VSID pairs (in SLB/segment registers) and will set up
- * mappings of one or more ranges of pages to VAs.
- * We will have the hypervisor set up the ESID->VSID mapping
- * for the four kernel segments (C-F).  With shared processors,
- * the hypervisor will clear all segment registers and reload
- * these four whenever the processor is switched from one
- * partition to another.
- */
-
-/* The Vsid and Esid identified below will be used by the hypervisor
- * to set up a memory mapping for part of the load area before giving
- * control to the Linux kernel.  The load area is 64 MB, but this must
- * not attempt to map the whole load area.  The Hashed Page Table may
- * need to be located within the load area (if the total partition size
- * is 64 MB), but cannot be mapped.  Typically, this should specify
- * to map half (32 MB) of the load area.
- *
- * The hypervisor will set up page table entries for the number of
- * pages specified.
- *
- * In 32-bit mode, the hypervisor will load all four of the
- * segment registers (identified by the low-order four bits of the
- * Esid field.  In 64-bit mode, the hypervisor will load one SLB
- * entry to map the Esid to the Vsid.
-*/
-
-#define HvEsidsToMap    2
-#define HvRangesToMap   1
-
-/* Hypervisor initially maps 32MB of the load area */
-#define HvPagesToMap    8192
-
-#ifndef __ASSEMBLY__
-struct LparMap {
-        u64     xNumberEsids;   // Number of ESID/VSID pairs
-        u64     xNumberRanges;  // Number of VA ranges to map
-        u64     xSegmentTableOffs; // Page number within load area of seg table
-        u64     xRsvd[5];
-        struct {
-                u64     xKernelEsid;    // Esid used to map kernel load
-                u64     xKernelVsid;    // Vsid used to map kernel load
-        } xEsids[HvEsidsToMap];
-        struct {
-                u64     xPages;         // Number of pages to be mapped
-                u64     xOffset;        // Offset from start of load area
-                u64     xVPN;           // Virtual Page Number
-        } xRanges[HvRangesToMap];
-};
-
-extern const struct LparMap     xLparMap;
-
-#endif /* __ASSEMBLY__ */
-
-/* the fixed address where the LparMap exists */
-#define LPARMAP_PHYS            0x7000
-
-#endif /* _ASM_POWERPC_ISERIES_LPAR_MAP_H */
diff --git a/arch/powerpc/include/asm/iseries/mf.h b/arch/powerpc/include/asm/iseries/mf.h
deleted file mode 100644
index eb851a9c9e5c..000000000000
--- a/arch/powerpc/include/asm/iseries/mf.h
+++ /dev/null
@@ -1,51 +0,0 @@
-/*
- * Copyright (C) 2001  Troy D. Armstrong IBM Corporation
- * Copyright (C) 2004  Stephen Rothwell IBM Corporation
- *
- * This modules exists as an interface between a Linux secondary partition
- * running on an iSeries and the primary partition's Virtual Service
- * Processor (VSP) object.  The VSP has final authority over powering on/off
- * all partitions in the iSeries.  It also provides miscellaneous low-level
- * machine facility type operations.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
- */
-#ifndef _ASM_POWERPC_ISERIES_MF_H
-#define _ASM_POWERPC_ISERIES_MF_H
-
-#include <linux/types.h>
-
-#include <asm/iseries/hv_types.h>
-#include <asm/iseries/hv_call_event.h>
-
-struct rtc_time;
-
-typedef void (*MFCompleteHandler)(void *clientToken, int returnCode);
-
-extern void mf_allocate_lp_events(HvLpIndex targetLp, HvLpEvent_Type type,
-                unsigned size, unsigned amount, MFCompleteHandler hdlr,
-                void *userToken);
-extern void mf_deallocate_lp_events(HvLpIndex targetLp, HvLpEvent_Type type,
-                unsigned count, MFCompleteHandler hdlr, void *userToken);
-
-extern void mf_power_off(void);
-extern void mf_reboot(char *cmd);
-
-extern void mf_display_src(u32 word);
-extern void mf_display_progress(u16 value);
-
-extern void mf_init(void);
-
-#endif /* _ASM_POWERPC_ISERIES_MF_H */
diff --git a/arch/powerpc/include/asm/iseries/vio.h b/arch/powerpc/include/asm/iseries/vio.h
deleted file mode 100644
index f9ac0d00b951..000000000000
--- a/arch/powerpc/include/asm/iseries/vio.h
+++ /dev/null
@@ -1,265 +0,0 @@
-/* -*- linux-c -*-
- *
- *  iSeries Virtual I/O Message Path header
- *
- *  Authors: Dave Boutcher <boutcher@us.ibm.com>
- *           Ryan Arnold <ryanarn@us.ibm.com>
- *           Colin Devilbiss <devilbis@us.ibm.com>
- *
- * (C) Copyright 2000 IBM Corporation
- *
- * This header file is used by the iSeries virtual I/O device
- * drivers.  It defines the interfaces to the common functions
- * (implemented in drivers/char/viopath.h) as well as defining
- * common functions and structures.  Currently (at the time I
- * wrote this comment) the iSeries virtual I/O device drivers
- * that use this are
- *   drivers/block/viodasd.c
- *   drivers/char/viocons.c
- *   drivers/char/viotape.c
- *   drivers/cdrom/viocd.c
- *
- * The iSeries virtual ethernet support (veth.c) uses a whole
- * different set of functions.
- *
- * 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) anyu later version.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software Foundation,
- * Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
- *
- */
-#ifndef _ASM_POWERPC_ISERIES_VIO_H
-#define _ASM_POWERPC_ISERIES_VIO_H
-
-#include <asm/iseries/hv_types.h>
-#include <asm/iseries/hv_lp_event.h>
-
-/*
- * iSeries virtual I/O events use the subtype field in
- * HvLpEvent to figure out what kind of vio event is coming
- * in.  We use a table to route these, and this defines
- * the maximum number of distinct subtypes
- */
-#define VIO_MAX_SUBTYPES 8
-
-#define VIOMAXBLOCKDMA  12
-
-struct open_data {
-        u64     disk_size;
-        u16     max_disk;
-        u16     cylinders;
-        u16     tracks;
-        u16     sectors;
-        u16     bytes_per_sector;
-};
-
-struct rw_data {
-        u64     offset;
-        struct {
-                u32     token;
-                u32     reserved;
-                u64     len;
-        } dma_info[VIOMAXBLOCKDMA];
-};
-
-struct vioblocklpevent {
-        struct HvLpEvent        event;
-        u32                     reserved;
-        u16                     version;
-        u16                     sub_result;
-        u16                     disk;
-        u16                     flags;
-        union {
-                struct open_data        open_data;
-                struct rw_data          rw_data;
-                u64                     changed;
-        } u;
-};
-
-#define vioblockflags_ro   0x0001
-
-enum vioblocksubtype {
-        vioblockopen = 0x0001,
-        vioblockclose = 0x0002,
-        vioblockread = 0x0003,
-        vioblockwrite = 0x0004,
-        vioblockflush = 0x0005,
-        vioblockcheck = 0x0007
-};
-
-struct viocdlpevent {
-        struct HvLpEvent        event;
-        u32                     reserved;
-        u16                     version;
-        u16                     sub_result;
-        u16                     disk;
-        u16                     flags;
-        u32                     token;
-        u64                     offset;         /* On open, max number of disks */
-        u64                     len;            /* On open, size of the disk */
-        u32                     block_size;     /* Only set on open */
-        u32                     media_size;     /* Only set on open */
-};
-
-enum viocdsubtype {
-        viocdopen = 0x0001,
-        viocdclose = 0x0002,
-        viocdread = 0x0003,
-        viocdwrite = 0x0004,
-        viocdlockdoor = 0x0005,
-        viocdgetinfo = 0x0006,
-        viocdcheck = 0x0007
-};
-
-struct viotapelpevent {
-        struct HvLpEvent event;
-        u32 reserved;
-        u16 version;
-        u16 sub_type_result;
-        u16 tape;
-        u16 flags;
-        u32 token;
-        u64 len;
-        union {
-                struct {
-                        u32 tape_op;
-                        u32 count;
-                } op;
-                struct {
-                        u32 type;
-                        u32 resid;
-                        u32 dsreg;
-                        u32 gstat;
-                        u32 erreg;
-                        u32 file_no;
-                        u32 block_no;
-                } get_status;
-                struct {
-                        u32 block_no;
-                } get_pos;
-        } u;
-};
-
-enum viotapesubtype {
-        viotapeopen = 0x0001,
-        viotapeclose = 0x0002,
-        viotaperead = 0x0003,
-        viotapewrite = 0x0004,
-        viotapegetinfo = 0x0005,
-        viotapeop = 0x0006,
-        viotapegetpos = 0x0007,
-        viotapesetpos = 0x0008,
-        viotapegetstatus = 0x0009
-};
-
-/*
- * Each subtype can register a handler to process their events.
- * The handler must have this interface.
- */
-typedef void (vio_event_handler_t) (struct HvLpEvent * event);
-
-extern int viopath_open(HvLpIndex remoteLp, int subtype, int numReq);
-extern int viopath_close(HvLpIndex remoteLp, int subtype, int numReq);
-extern int vio_setHandler(int subtype, vio_event_handler_t * beh);
-extern int vio_clearHandler(int subtype);
-extern int viopath_isactive(HvLpIndex lp);
-extern HvLpInstanceId viopath_sourceinst(HvLpIndex lp);
-extern HvLpInstanceId viopath_targetinst(HvLpIndex lp);
-extern void vio_set_hostlp(void);
-extern void *vio_get_event_buffer(int subtype);
-extern void vio_free_event_buffer(int subtype, void *buffer);
-
-extern struct vio_dev *vio_create_viodasd(u32 unit);
-
-extern HvLpIndex viopath_hostLp;
-extern HvLpIndex viopath_ourLp;
-
-#define VIOCHAR_MAX_DATA        200
-
-#define VIOMAJOR_SUBTYPE_MASK   0xff00
-#define VIOMINOR_SUBTYPE_MASK   0x00ff
-#define VIOMAJOR_SUBTYPE_SHIFT  8
-
-#define VIOVERSION              0x0101
-
-/*
- * This is the general structure for VIO errors; each module should have
- * a table of them, and each table should be terminated by an entry of
- * { 0, 0, NULL }.  Then, to find a specific error message, a module
- * should pass its local table and the return code.
- */
-struct vio_error_entry {
-        u16 rc;
-        int errno;
-        const char *msg;
-};
-extern const struct vio_error_entry *vio_lookup_rc(
-                const struct vio_error_entry *local_table, u16 rc);
-
-enum viosubtypes {
-        viomajorsubtype_monitor = 0x0100,
-        viomajorsubtype_blockio = 0x0200,
-        viomajorsubtype_chario = 0x0300,
-        viomajorsubtype_config = 0x0400,
-        viomajorsubtype_cdio = 0x0500,
-        viomajorsubtype_tape = 0x0600,
-        viomajorsubtype_scsi = 0x0700
-};
-
-enum vioconfigsubtype {
-        vioconfigget = 0x0001,
-};
-
-enum viorc {
-        viorc_good = 0x0000,
-        viorc_noConnection = 0x0001,
-        viorc_noReceiver = 0x0002,
-        viorc_noBufferAvailable = 0x0003,
-        viorc_invalidMessageType = 0x0004,
-        viorc_invalidRange = 0x0201,
-        viorc_invalidToken = 0x0202,
-        viorc_DMAError = 0x0203,
-        viorc_useError = 0x0204,
-        viorc_releaseError = 0x0205,
-        viorc_invalidDisk = 0x0206,
-        viorc_openRejected = 0x0301
-};
-
-/*
- * The structure of the events that flow between us and OS/400 for chario
- * events.  You can't mess with this unless the OS/400 side changes too.
- */
-struct viocharlpevent {
-        struct HvLpEvent event;
-        u32 reserved;
-        u16 version;
-        u16 subtype_result_code;
-        u8 virtual_device;
-        u8 len;
-        u8 data[VIOCHAR_MAX_DATA];
-};
-
-#define VIOCHAR_WINDOW          10
-
-enum viocharsubtype {
-        viocharopen = 0x0001,
-        viocharclose = 0x0002,
-        viochardata = 0x0003,
-        viocharack = 0x0004,
-        viocharconfig = 0x0005
-};
-
-enum viochar_rc {
-        viochar_rc_ebusy = 1
-};
-
-#endif /* _ASM_POWERPC_ISERIES_VIO_H */
diff --git a/arch/powerpc/include/asm/jump_label.h b/arch/powerpc/include/asm/jump_label.h
index 938986e412f1..ae098c438f00 100644
--- a/arch/powerpc/include/asm/jump_label.h
+++ b/arch/powerpc/include/asm/jump_label.h
@@ -17,7 +17,7 @@
 #define JUMP_ENTRY_TYPE         stringify_in_c(FTR_ENTRY_LONG)
 #define JUMP_LABEL_NOP_SIZE     4
 
-static __always_inline bool arch_static_branch(struct jump_label_key *key)
+static __always_inline bool arch_static_branch(struct static_key *key)
 {
         asm goto("1:\n\t"
                  "nop\n\t"
diff --git a/arch/powerpc/include/asm/keylargo.h b/arch/powerpc/include/asm/keylargo.h
index fc195d0b3c34..2156315d8a90 100644
--- a/arch/powerpc/include/asm/keylargo.h
+++ b/arch/powerpc/include/asm/keylargo.h
@@ -21,7 +21,7 @@
 #define KEYLARGO_FCR4           0x48
 #define KEYLARGO_FCR5           0x4c    /* Pangea only */
 
-/* K2 aditional FCRs */
+/* K2 additional FCRs */
 #define K2_FCR6                 0x34
 #define K2_FCR7                 0x30
 #define K2_FCR8                 0x2c
diff --git a/arch/powerpc/include/asm/kvm.h b/arch/powerpc/include/asm/kvm.h
index f7727d91ac6b..b921c3f48928 100644
--- a/arch/powerpc/include/asm/kvm.h
+++ b/arch/powerpc/include/asm/kvm.h
@@ -265,12 +265,9 @@ struct kvm_debug_exit_arch {
 struct kvm_guest_debug_arch {
 };
 
-#define KVM_REG_MASK            0x001f
-#define KVM_REG_EXT_MASK        0xffe0
-#define KVM_REG_GPR             0x0000
-#define KVM_REG_FPR             0x0020
-#define KVM_REG_QPR             0x0040
-#define KVM_REG_FQPR            0x0060
+/* definition of registers in kvm_run */
+struct kvm_sync_regs {
+};
 
 #define KVM_INTERRUPT_SET       -1U
 #define KVM_INTERRUPT_UNSET     -2U
@@ -292,4 +289,41 @@ struct kvm_allocate_rma {
         __u64 rma_size;
 };
 
+struct kvm_book3e_206_tlb_entry {
+        __u32 mas8;
+        __u32 mas1;
+        __u64 mas2;
+        __u64 mas7_3;
+};
+
+struct kvm_book3e_206_tlb_params {
+        /*
+         * For mmu types KVM_MMU_FSL_BOOKE_NOHV and KVM_MMU_FSL_BOOKE_HV:
+         *
+         * - The number of ways of TLB0 must be a power of two between 2 and
+         *   16.
+         * - TLB1 must be fully associative.
+         * - The size of TLB0 must be a multiple of the number of ways, and
+         *   the number of sets must be a power of two.
+         * - The size of TLB1 may not exceed 64 entries.
+         * - TLB0 supports 4 KiB pages.
+         * - The page sizes supported by TLB1 are as indicated by
+         *   TLB1CFG (if MMUCFG[MAVN] = 0) or TLB1PS (if MMUCFG[MAVN] = 1)
+         *   as returned by KVM_GET_SREGS.
+         * - TLB2 and TLB3 are reserved, and their entries in tlb_sizes[]
+         *   and tlb_ways[] must be zero.
+         *
+         * tlb_ways[n] = tlb_sizes[n] means the array is fully associative.
+         *
+         * KVM will adjust TLBnCFG based on the sizes configured here,
+         * though arrays greater than 2048 entries will have TLBnCFG[NENTRY]
+         * set to zero.
+         */
+        __u32 tlb_sizes[4];
+        __u32 tlb_ways[4];
+        __u32 reserved[8];
+};
+
+#define KVM_REG_PPC_HIOR        (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x1)
+
 #endif /* __LINUX_KVM_POWERPC_H */
diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h
index 69c7377d2071..aa795ccef294 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_explicit;             /* HIOR is set by ioctl, 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];
@@ -119,6 +121,11 @@ extern void kvmppc_mmu_book3s_hv_init(struct kvm_vcpu *vcpu);
 extern int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *pte);
 extern int kvmppc_mmu_map_segment(struct kvm_vcpu *vcpu, ulong eaddr);
 extern void kvmppc_mmu_flush_segments(struct kvm_vcpu *vcpu);
+extern int kvmppc_book3s_hv_page_fault(struct kvm_run *run,
+                        struct kvm_vcpu *vcpu, unsigned long addr,
+                        unsigned long status);
+extern long kvmppc_hv_find_lock_hpte(struct kvm *kvm, gva_t eaddr,
+                        unsigned long slb_v, unsigned long valid);
 
 extern void kvmppc_mmu_hpte_cache_map(struct kvm_vcpu *vcpu, struct hpte_cache *pte);
 extern struct hpte_cache *kvmppc_mmu_hpte_cache_next(struct kvm_vcpu *vcpu);
@@ -138,6 +145,21 @@ extern void kvmppc_set_bat(struct kvm_vcpu *vcpu, struct kvmppc_bat *bat,
 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_add_revmap_chain(struct kvm *kvm, struct revmap_entry *rev,
+                        unsigned long *rmap, long pte_index, int realmode);
+extern void kvmppc_invalidate_hpte(struct kvm *kvm, unsigned long *hptep,
+                        unsigned long pte_index);
+void kvmppc_clear_ref_hpte(struct kvm *kvm, unsigned long *hptep,
+                        unsigned long pte_index);
+extern void *kvmppc_pin_guest_page(struct kvm *kvm, unsigned long addr,
+                        unsigned long *nb_ret);
+extern void kvmppc_unpin_guest_page(struct kvm *kvm, void *addr);
+extern long kvmppc_virtmode_h_enter(struct kvm_vcpu *vcpu, unsigned long flags,
+                        long pte_index, unsigned long pteh, unsigned long ptel);
+extern long kvmppc_h_enter(struct kvm_vcpu *vcpu, unsigned long flags,
+                        long pte_index, unsigned long pteh, unsigned long ptel);
+extern long kvmppc_hv_get_dirty_log(struct kvm *kvm,
+                        struct kvm_memory_slot *memslot);
 
 extern void kvmppc_entry_trampoline(void);
 extern void kvmppc_hv_entry_trampoline(void);
@@ -183,7 +205,9 @@ static inline void kvmppc_update_int_pending(struct kvm_vcpu *vcpu,
 static inline void kvmppc_set_gpr(struct kvm_vcpu *vcpu, int num, ulong val)
 {
         if ( num < 14 ) {
-                to_svcpu(vcpu)->gpr[num] = val;
+                struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
+                svcpu->gpr[num] = val;
+                svcpu_put(svcpu);
                 to_book3s(vcpu)->shadow_vcpu->gpr[num] = val;
         } else
                 vcpu->arch.gpr[num] = val;
@@ -191,80 +215,120 @@ static inline void kvmppc_set_gpr(struct kvm_vcpu *vcpu, int num, ulong val)
 
 static inline ulong kvmppc_get_gpr(struct kvm_vcpu *vcpu, int num)
 {
-        if ( num < 14 )
-                return to_svcpu(vcpu)->gpr[num];
-        else
+        if ( num < 14 ) {
+                struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
+                ulong r = svcpu->gpr[num];
+                svcpu_put(svcpu);
+                return r;
+        } else
                 return vcpu->arch.gpr[num];
 }
 
 static inline void kvmppc_set_cr(struct kvm_vcpu *vcpu, u32 val)
 {
-        to_svcpu(vcpu)->cr = val;
+        struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
+        svcpu->cr = val;
+        svcpu_put(svcpu);
         to_book3s(vcpu)->shadow_vcpu->cr = val;
 }
 
 static inline u32 kvmppc_get_cr(struct kvm_vcpu *vcpu)
 {
-        return to_svcpu(vcpu)->cr;
+        struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
+        u32 r;
+        r = svcpu->cr;
+        svcpu_put(svcpu);
+        return r;
 }
 
 static inline void kvmppc_set_xer(struct kvm_vcpu *vcpu, u32 val)
 {
-        to_svcpu(vcpu)->xer = val;
+        struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
+        svcpu->xer = val;
         to_book3s(vcpu)->shadow_vcpu->xer = val;
+        svcpu_put(svcpu);
 }
 
 static inline u32 kvmppc_get_xer(struct kvm_vcpu *vcpu)
 {
-        return to_svcpu(vcpu)->xer;
+        struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
+        u32 r;
+        r = svcpu->xer;
+        svcpu_put(svcpu);
+        return r;
 }
 
 static inline void kvmppc_set_ctr(struct kvm_vcpu *vcpu, ulong val)
 {
-        to_svcpu(vcpu)->ctr = val;
+        struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
+        svcpu->ctr = val;
+        svcpu_put(svcpu);
 }
 
 static inline ulong kvmppc_get_ctr(struct kvm_vcpu *vcpu)
 {
-        return to_svcpu(vcpu)->ctr;
+        struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
+        ulong r;
+        r = svcpu->ctr;
+        svcpu_put(svcpu);
+        return r;
 }
 
 static inline void kvmppc_set_lr(struct kvm_vcpu *vcpu, ulong val)
 {
-        to_svcpu(vcpu)->lr = val;
+        struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
+        svcpu->lr = val;
+        svcpu_put(svcpu);
 }
 
 static inline ulong kvmppc_get_lr(struct kvm_vcpu *vcpu)
 {
-        return to_svcpu(vcpu)->lr;
+        struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
+        ulong r;
+        r = svcpu->lr;
+        svcpu_put(svcpu);
+        return r;
 }
 
 static inline void kvmppc_set_pc(struct kvm_vcpu *vcpu, ulong val)
 {
-        to_svcpu(vcpu)->pc = val;
+        struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
+        svcpu->pc = val;
+        svcpu_put(svcpu);
 }
 
 static inline ulong kvmppc_get_pc(struct kvm_vcpu *vcpu)
 {
-        return to_svcpu(vcpu)->pc;
+        struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
+        ulong r;
+        r = svcpu->pc;
+        svcpu_put(svcpu);
+        return r;
 }
 
 static inline u32 kvmppc_get_last_inst(struct kvm_vcpu *vcpu)
 {
         ulong pc = kvmppc_get_pc(vcpu);
-        struct kvmppc_book3s_shadow_vcpu *svcpu = to_svcpu(vcpu);
+        struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
+        u32 r;
 
         /* Load the instruction manually if it failed to do so in the
          * exit path */
         if (svcpu->last_inst == KVM_INST_FETCH_FAILED)
                 kvmppc_ld(vcpu, &pc, sizeof(u32), &svcpu->last_inst, false);
 
-        return svcpu->last_inst;
+        r = svcpu->last_inst;
+        svcpu_put(svcpu);
+        return r;
 }
 
 static inline ulong kvmppc_get_fault_dar(struct kvm_vcpu *vcpu)
 {
-        return to_svcpu(vcpu)->fault_dar;
+        struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
+        ulong r;
+        r = svcpu->fault_dar;
+        svcpu_put(svcpu);
+        return r;
 }
 
 static inline bool kvmppc_critical_section(struct kvm_vcpu *vcpu)
diff --git a/arch/powerpc/include/asm/kvm_book3s_32.h b/arch/powerpc/include/asm/kvm_book3s_32.h
index de604db135f5..38040ff82063 100644
--- a/arch/powerpc/include/asm/kvm_book3s_32.h
+++ b/arch/powerpc/include/asm/kvm_book3s_32.h
@@ -20,11 +20,15 @@
 #ifndef __ASM_KVM_BOOK3S_32_H__
 #define __ASM_KVM_BOOK3S_32_H__
 
-static inline struct kvmppc_book3s_shadow_vcpu *to_svcpu(struct kvm_vcpu *vcpu)
+static inline struct kvmppc_book3s_shadow_vcpu *svcpu_get(struct kvm_vcpu *vcpu)
 {
         return to_book3s(vcpu)->shadow_vcpu;
 }
 
+static inline void svcpu_put(struct kvmppc_book3s_shadow_vcpu *svcpu)
+{
+}
+
 #define PTE_SIZE        12
 #define VSID_ALL        0
 #define SR_INVALID      0x00000001      /* VSID 1 should always be unused */
diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h
index d0ac94f98f9e..b0c08b142770 100644
--- a/arch/powerpc/include/asm/kvm_book3s_64.h
+++ b/arch/powerpc/include/asm/kvm_book3s_64.h
@@ -21,14 +21,56 @@
 #define __ASM_KVM_BOOK3S_64_H__
 
 #ifdef CONFIG_KVM_BOOK3S_PR
-static inline struct kvmppc_book3s_shadow_vcpu *to_svcpu(struct kvm_vcpu *vcpu)
+static inline struct kvmppc_book3s_shadow_vcpu *svcpu_get(struct kvm_vcpu *vcpu)
 {
+        preempt_disable();
         return &get_paca()->shadow_vcpu;
 }
+
+static inline void svcpu_put(struct kvmppc_book3s_shadow_vcpu *svcpu)
+{
+        preempt_enable();
+}
 #endif
 
 #define SPAPR_TCE_SHIFT         12
 
+#ifdef CONFIG_KVM_BOOK3S_64_HV
+/* For now use fixed-size 16MB page table */
+#define HPT_ORDER       24
+#define HPT_NPTEG       (1ul << (HPT_ORDER - 7))        /* 128B per pteg */
+#define HPT_NPTE        (HPT_NPTEG << 3)                /* 8 PTEs per PTEG */
+#define HPT_HASH_MASK   (HPT_NPTEG - 1)
+#endif
+
+#define VRMA_VSID       0x1ffffffUL     /* 1TB VSID reserved for VRMA */
+
+/*
+ * We use a lock bit in HPTE dword 0 to synchronize updates and
+ * accesses to each HPTE, and another bit to indicate non-present
+ * HPTEs.
+ */
+#define HPTE_V_HVLOCK   0x40UL
+#define HPTE_V_ABSENT   0x20UL
+
+static inline long try_lock_hpte(unsigned long *hpte, unsigned long bits)
+{
+        unsigned long tmp, old;
+
+        asm volatile("  ldarx   %0,0,%2\n"
+                     "  and.    %1,%0,%3\n"
+                     "  bne     2f\n"
+                     "  ori     %0,%0,%4\n"
+                     "  stdcx.  %0,0,%2\n"
+                     "  beq+    2f\n"
+                     "  li      %1,%3\n"
+                     "2:        isync"
+                     : "=&r" (tmp), "=&r" (old)
+                     : "r" (hpte), "r" (bits), "i" (HPTE_V_HVLOCK)
+                     : "cc", "memory");
+        return old == 0;
+}
+
 static inline unsigned long compute_tlbie_rb(unsigned long v, unsigned long r,
                                              unsigned long pte_index)
 {
@@ -62,4 +104,140 @@ static inline unsigned long compute_tlbie_rb(unsigned long v, unsigned long r,
         return rb;
 }
 
+static inline unsigned long hpte_page_size(unsigned long h, unsigned long l)
+{
+        /* only handle 4k, 64k and 16M pages for now */
+        if (!(h & HPTE_V_LARGE))
+                return 1ul << 12;               /* 4k page */
+        if ((l & 0xf000) == 0x1000 && cpu_has_feature(CPU_FTR_ARCH_206))
+                return 1ul << 16;               /* 64k page */
+        if ((l & 0xff000) == 0)
+                return 1ul << 24;               /* 16M page */
+        return 0;                               /* error */
+}
+
+static inline unsigned long hpte_rpn(unsigned long ptel, unsigned long psize)
+{
+        return ((ptel & HPTE_R_RPN) & ~(psize - 1)) >> PAGE_SHIFT;
+}
+
+static inline int hpte_is_writable(unsigned long ptel)
+{
+        unsigned long pp = ptel & (HPTE_R_PP0 | HPTE_R_PP);
+
+        return pp != PP_RXRX && pp != PP_RXXX;
+}
+
+static inline unsigned long hpte_make_readonly(unsigned long ptel)
+{
+        if ((ptel & HPTE_R_PP0) || (ptel & HPTE_R_PP) == PP_RWXX)
+                ptel = (ptel & ~HPTE_R_PP) | PP_RXXX;
+        else
+                ptel |= PP_RXRX;
+        return ptel;
+}
+
+static inline int hpte_cache_flags_ok(unsigned long ptel, unsigned long io_type)
+{
+        unsigned int wimg = ptel & HPTE_R_WIMG;
+
+        /* Handle SAO */
+        if (wimg == (HPTE_R_W | HPTE_R_I | HPTE_R_M) &&
+            cpu_has_feature(CPU_FTR_ARCH_206))
+                wimg = HPTE_R_M;
+
+        if (!io_type)
+                return wimg == HPTE_R_M;
+
+        return (wimg & (HPTE_R_W | HPTE_R_I)) == io_type;
+}
+
+/*
+ * Lock and read a linux PTE.  If it's present and writable, atomically
+ * set dirty and referenced bits and return the PTE, otherwise return 0.
+ */
+static inline pte_t kvmppc_read_update_linux_pte(pte_t *p, int writing)
+{
+        pte_t pte, tmp;
+
+        /* wait until _PAGE_BUSY is clear then set it atomically */
+        __asm__ __volatile__ (
+                "1:     ldarx   %0,0,%3\n"
+                "       andi.   %1,%0,%4\n"
+                "       bne-    1b\n"
+                "       ori     %1,%0,%4\n"
+                "       stdcx.  %1,0,%3\n"
+                "       bne-    1b"
+                : "=&r" (pte), "=&r" (tmp), "=m" (*p)
+                : "r" (p), "i" (_PAGE_BUSY)
+                : "cc");
+
+        if (pte_present(pte)) {
+                pte = pte_mkyoung(pte);
+                if (writing && pte_write(pte))
+                        pte = pte_mkdirty(pte);
+        }
+
+        *p = pte;       /* clears _PAGE_BUSY */
+
+        return pte;
+}
+
+/* Return HPTE cache control bits corresponding to Linux pte bits */
+static inline unsigned long hpte_cache_bits(unsigned long pte_val)
+{
+#if _PAGE_NO_CACHE == HPTE_R_I && _PAGE_WRITETHRU == HPTE_R_W
+        return pte_val & (HPTE_R_W | HPTE_R_I);
+#else
+        return ((pte_val & _PAGE_NO_CACHE) ? HPTE_R_I : 0) +
+                ((pte_val & _PAGE_WRITETHRU) ? HPTE_R_W : 0);
+#endif
+}
+
+static inline bool hpte_read_permission(unsigned long pp, unsigned long key)
+{
+        if (key)
+                return PP_RWRX <= pp && pp <= PP_RXRX;
+        return 1;
+}
+
+static inline bool hpte_write_permission(unsigned long pp, unsigned long key)
+{
+        if (key)
+                return pp == PP_RWRW;
+        return pp <= PP_RWRW;
+}
+
+static inline int hpte_get_skey_perm(unsigned long hpte_r, unsigned long amr)
+{
+        unsigned long skey;
+
+        skey = ((hpte_r & HPTE_R_KEY_HI) >> 57) |
+                ((hpte_r & HPTE_R_KEY_LO) >> 9);
+        return (amr >> (62 - 2 * skey)) & 3;
+}
+
+static inline void lock_rmap(unsigned long *rmap)
+{
+        do {
+                while (test_bit(KVMPPC_RMAP_LOCK_BIT, rmap))
+                        cpu_relax();
+        } while (test_and_set_bit_lock(KVMPPC_RMAP_LOCK_BIT, rmap));
+}
+
+static inline void unlock_rmap(unsigned long *rmap)
+{
+        __clear_bit_unlock(KVMPPC_RMAP_LOCK_BIT, rmap);
+}
+
+static inline bool slot_is_aligned(struct kvm_memory_slot *memslot,
+                                   unsigned long pagesize)
+{
+        unsigned long mask = (pagesize >> PAGE_SHIFT) - 1;
+
+        if (pagesize <= PAGE_SIZE)
+                return 1;
+        return !(memslot->base_gfn & mask) && !(memslot->npages & mask);
+}
+
 #endif /* __ASM_KVM_BOOK3S_64_H__ */
diff --git a/arch/powerpc/include/asm/kvm_e500.h b/arch/powerpc/include/asm/kvm_e500.h
index adbfca9dd100..8cd50a514271 100644
--- a/arch/powerpc/include/asm/kvm_e500.h
+++ b/arch/powerpc/include/asm/kvm_e500.h
@@ -22,46 +22,55 @@
 #define E500_PID_NUM   3
 #define E500_TLB_NUM   2
 
-struct tlbe{
-        u32 mas1;
-        u32 mas2;
-        u32 mas3;
-        u32 mas7;
-};
-
 #define E500_TLB_VALID 1
 #define E500_TLB_DIRTY 2
 
-struct tlbe_priv {
+struct tlbe_ref {
         pfn_t pfn;
         unsigned int flags; /* E500_TLB_* */
 };
 
+struct tlbe_priv {
+        struct tlbe_ref ref; /* TLB0 only -- TLB1 uses tlb_refs */
+};
+
 struct vcpu_id_table;
 
+struct kvmppc_e500_tlb_params {
+        int entries, ways, sets;
+};
+
 struct kvmppc_vcpu_e500 {
-        /* Unmodified copy of the guest's TLB. */
-        struct tlbe *gtlb_arch[E500_TLB_NUM];
+        /* Unmodified copy of the guest's TLB -- shared with host userspace. */
+        struct kvm_book3e_206_tlb_entry *gtlb_arch;
+
+        /* Starting entry number in gtlb_arch[] */
+        int gtlb_offset[E500_TLB_NUM];
 
         /* KVM internal information associated with each guest TLB entry */
         struct tlbe_priv *gtlb_priv[E500_TLB_NUM];
 
-        unsigned int gtlb_size[E500_TLB_NUM];
+        struct kvmppc_e500_tlb_params gtlb_params[E500_TLB_NUM];
+
         unsigned int gtlb_nv[E500_TLB_NUM];
 
+        /*
+         * information associated with each host TLB entry --
+         * TLB1 only for now.  If/when guest TLB1 entries can be
+         * mapped with host TLB0, this will be used for that too.
+         *
+         * We don't want to use this for guest TLB0 because then we'd
+         * have the overhead of doing the translation again even if
+         * the entry is still in the guest TLB (e.g. we swapped out
+         * and back, and our host TLB entries got evicted).
+         */
+        struct tlbe_ref *tlb_refs[E500_TLB_NUM];
+        unsigned int host_tlb1_nv;
+
         u32 host_pid[E500_PID_NUM];
         u32 pid[E500_PID_NUM];
         u32 svr;
 
-        u32 mas0;
-        u32 mas1;
-        u32 mas2;
-        u32 mas3;
-        u32 mas4;
-        u32 mas5;
-        u32 mas6;
-        u32 mas7;
-
         /* vcpu id table */
         struct vcpu_id_table *idt;
 
@@ -73,6 +82,9 @@ struct kvmppc_vcpu_e500 {
         u32 tlb1cfg;
         u64 mcar;
 
+        struct page **shared_tlb_pages;
+        int num_shared_tlb_pages;
+
         struct kvm_vcpu vcpu;
 };
 
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index bf8af5d5d5dc..52eb9c1f4fe0 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -32,17 +32,32 @@
 #include <linux/atomic.h>
 #include <asm/kvm_asm.h>
 #include <asm/processor.h>
+#include <asm/page.h>
 
 #define KVM_MAX_VCPUS           NR_CPUS
 #define KVM_MAX_VCORES          NR_CPUS
 #define KVM_MEMORY_SLOTS 32
 /* memory slots that does not exposed to userspace */
 #define KVM_PRIVATE_MEM_SLOTS 4
+#define KVM_MEM_SLOTS_NUM (KVM_MEMORY_SLOTS + KVM_PRIVATE_MEM_SLOTS)
 
 #ifdef CONFIG_KVM_MMIO
 #define KVM_COALESCED_MMIO_PAGE_OFFSET 1
 #endif
 
+#ifdef CONFIG_KVM_BOOK3S_64_HV
+#include <linux/mmu_notifier.h>
+
+#define KVM_ARCH_WANT_MMU_NOTIFIER
+
+struct kvm;
+extern int kvm_unmap_hva(struct kvm *kvm, unsigned long hva);
+extern int kvm_age_hva(struct kvm *kvm, unsigned long hva);
+extern int kvm_test_age_hva(struct kvm *kvm, unsigned long hva);
+extern void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte);
+
+#endif
+
 /* We don't currently support large pages. */
 #define KVM_HPAGE_GFN_SHIFT(x)  0
 #define KVM_NR_PAGE_SIZES       1
@@ -158,34 +173,72 @@ struct kvmppc_spapr_tce_table {
         struct page *pages[0];
 };
 
-struct kvmppc_rma_info {
+struct kvmppc_linear_info {
         void            *base_virt;
         unsigned long    base_pfn;
         unsigned long    npages;
         struct list_head list;
-        atomic_t         use_count;
+        atomic_t         use_count;
+        int              type;
+};
+
+/*
+ * The reverse mapping array has one entry for each HPTE,
+ * which stores the guest's view of the second word of the HPTE
+ * (including the guest physical address of the mapping),
+ * plus forward and backward pointers in a doubly-linked ring
+ * of HPTEs that map the same host page.  The pointers in this
+ * ring are 32-bit HPTE indexes, to save space.
+ */
+struct revmap_entry {
+        unsigned long guest_rpte;
+        unsigned int forw, back;
+};
+
+/*
+ * We use the top bit of each memslot->rmap entry as a lock bit,
+ * and bit 32 as a present flag.  The bottom 32 bits are the
+ * index in the guest HPT of a HPTE that points to the page.
+ */
+#define KVMPPC_RMAP_LOCK_BIT    63
+#define KVMPPC_RMAP_RC_SHIFT    32
+#define KVMPPC_RMAP_REFERENCED  (HPTE_R_R << KVMPPC_RMAP_RC_SHIFT)
+#define KVMPPC_RMAP_CHANGED     (HPTE_R_C << KVMPPC_RMAP_RC_SHIFT)
+#define KVMPPC_RMAP_PRESENT     0x100000000ul
+#define KVMPPC_RMAP_INDEX       0xfffffffful
+
+/* Low-order bits in kvm->arch.slot_phys[][] */
+#define KVMPPC_PAGE_ORDER_MASK  0x1f
+#define KVMPPC_PAGE_NO_CACHE    HPTE_R_I        /* 0x20 */
+#define KVMPPC_PAGE_WRITETHRU   HPTE_R_W        /* 0x40 */
+#define KVMPPC_GOT_PAGE         0x80
+
+struct kvm_arch_memory_slot {
 };
 
 struct kvm_arch {
 #ifdef CONFIG_KVM_BOOK3S_64_HV
         unsigned long hpt_virt;
-        unsigned long ram_npages;
-        unsigned long ram_psize;
-        unsigned long ram_porder;
-        struct kvmppc_pginfo *ram_pginfo;
+        struct revmap_entry *revmap;
         unsigned int lpid;
         unsigned int host_lpid;
         unsigned long host_lpcr;
         unsigned long sdr1;
         unsigned long host_sdr1;
         int tlbie_lock;
-        int n_rma_pages;
         unsigned long lpcr;
         unsigned long rmor;
-        struct kvmppc_rma_info *rma;
+        struct kvmppc_linear_info *rma;
+        unsigned long vrma_slb_v;
+        int rma_setup_done;
+        int using_mmu_notifiers;
         struct list_head spapr_tce_tables;
+        spinlock_t slot_phys_lock;
+        unsigned long *slot_phys[KVM_MEM_SLOTS_NUM];
+        int slot_npages[KVM_MEM_SLOTS_NUM];
         unsigned short last_vcpu[NR_CPUS];
         struct kvmppc_vcore *vcores[KVM_MAX_VCORES];
+        struct kvmppc_linear_info *hpt_li;
 #endif /* CONFIG_KVM_BOOK3S_64_HV */
 };
 
@@ -318,10 +371,6 @@ struct kvm_vcpu_arch {
         u32 vrsave; /* also USPRG0 */
         u32 mmucr;
         ulong shadow_msr;
-        ulong sprg4;
-        ulong sprg5;
-        ulong sprg6;
-        ulong sprg7;
         ulong csrr0;
         ulong csrr1;
         ulong dsrr0;
@@ -329,16 +378,14 @@ struct kvm_vcpu_arch {
         ulong mcsrr0;
         ulong mcsrr1;
         ulong mcsr;
-        ulong esr;
         u32 dec;
         u32 decar;
         u32 tbl;
         u32 tbu;
         u32 tcr;
-        u32 tsr;
+        ulong tsr; /* we need to perform set/clr_bits() which requires ulong */
         u32 ivor[64];
         ulong ivpr;
-        u32 pir;
         u32 pvr;
 
         u32 shadow_pid;
@@ -427,9 +474,14 @@ struct kvm_vcpu_arch {
 #ifdef CONFIG_KVM_BOOK3S_64_HV
         struct kvm_vcpu_arch_shared shregs;
 
+        unsigned long pgfault_addr;
+        long pgfault_index;
+        unsigned long pgfault_hpte[2];
+
         struct list_head run_list;
         struct task_struct *run_task;
         struct kvm_run *kvm_run;
+        pgd_t *pgdir;
 #endif
 };
 
@@ -438,4 +490,12 @@ struct kvm_vcpu_arch {
 #define KVMPPC_VCPU_BUSY_IN_HOST        1
 #define KVMPPC_VCPU_RUNNABLE            2
 
+/* Values for vcpu->arch.io_gpr */
+#define KVM_MMIO_REG_MASK       0x001f
+#define KVM_MMIO_REG_EXT_MASK   0xffe0
+#define KVM_MMIO_REG_GPR        0x0000
+#define KVM_MMIO_REG_FPR        0x0020
+#define KVM_MMIO_REG_QPR        0x0040
+#define KVM_MMIO_REG_FQPR       0x0060
+
 #endif /* __POWERPC_KVM_HOST_H__ */
diff --git a/arch/powerpc/include/asm/kvm_para.h b/arch/powerpc/include/asm/kvm_para.h
index 50533f9adf40..7b754e743003 100644
--- a/arch/powerpc/include/asm/kvm_para.h
+++ b/arch/powerpc/include/asm/kvm_para.h
@@ -22,6 +22,16 @@
 
 #include <linux/types.h>
 
+/*
+ * Additions to this struct must only occur at the end, and should be
+ * accompanied by a KVM_MAGIC_FEAT flag to advertise that they are present
+ * (albeit not necessarily relevant to the current target hardware platform).
+ *
+ * Struct fields are always 32 or 64 bit aligned, depending on them being 32
+ * or 64 bit wide respectively.
+ *
+ * See Documentation/virtual/kvm/ppc-pv.txt
+ */
 struct kvm_vcpu_arch_shared {
         __u64 scratch1;
         __u64 scratch2;
@@ -33,11 +43,35 @@ struct kvm_vcpu_arch_shared {
         __u64 sprg3;
         __u64 srr0;
         __u64 srr1;
-        __u64 dar;
+        __u64 dar;              /* dear on BookE */
         __u64 msr;
         __u32 dsisr;
         __u32 int_pending;      /* Tells the guest if we have an interrupt */
         __u32 sr[16];
+        __u32 mas0;
+        __u32 mas1;
+        __u64 mas7_3;
+        __u64 mas2;
+        __u32 mas4;
+        __u32 mas6;
+        __u32 esr;
+        __u32 pir;
+
+        /*
+         * SPRG4-7 are user-readable, so we can only keep these consistent
+         * between the shared area and the real registers when there's an
+         * intervening exit to KVM.  This also applies to SPRG3 on some
+         * chips.
+         *
+         * This suffices for access by guest userspace, since in PR-mode
+         * KVM, an exit must occur when changing the guest's MSR[PR].
+         * If the guest kernel writes to SPRG3-7 via the shared area, it
+         * must also use the shared area for reading while in kernel space.
+         */
+        __u64 sprg4;
+        __u64 sprg5;
+        __u64 sprg6;
+        __u64 sprg7;
 };
 
 #define KVM_SC_MAGIC_R0         0x4b564d21 /* "KVM!" */
@@ -47,7 +81,10 @@ struct kvm_vcpu_arch_shared {
 
 #define KVM_FEATURE_MAGIC_PAGE  1
 
-#define KVM_MAGIC_FEAT_SR       (1 << 0)
+#define KVM_MAGIC_FEAT_SR               (1 << 0)
+
+/* MASn, ESR, PIR, and high SPRGs */
+#define KVM_MAGIC_FEAT_MAS0_TO_SPRG7    (1 << 1)
 
 #ifdef __KERNEL__
 
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index 46efd1a265c9..9d6dee0f7d48 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 void kvmppc_decrementer_func(unsigned long data);
 extern int kvmppc_sanity_check(struct kvm_vcpu *vcpu);
 
 /* Core-specific hooks */
@@ -94,7 +95,7 @@ extern int kvmppc_core_vcpu_translate(struct kvm_vcpu *vcpu,
 extern void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu);
 extern void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu);
 
-extern void kvmppc_core_deliver_interrupts(struct kvm_vcpu *vcpu);
+extern void kvmppc_core_prepare_to_enter(struct kvm_vcpu *vcpu);
 extern int kvmppc_core_pending_dec(struct kvm_vcpu *vcpu);
 extern void kvmppc_core_queue_program(struct kvm_vcpu *vcpu, ulong flags);
 extern void kvmppc_core_queue_dec(struct kvm_vcpu *vcpu);
@@ -120,15 +121,17 @@ extern long kvmppc_alloc_hpt(struct kvm *kvm);
 extern void kvmppc_free_hpt(struct kvm *kvm);
 extern long kvmppc_prepare_vrma(struct kvm *kvm,
                                 struct kvm_userspace_memory_region *mem);
-extern void kvmppc_map_vrma(struct kvm *kvm,
-                            struct kvm_userspace_memory_region *mem);
+extern void kvmppc_map_vrma(struct kvm_vcpu *vcpu,
+                        struct kvm_memory_slot *memslot, unsigned long porder);
 extern int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu);
 extern long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
                                 struct kvm_create_spapr_tce *args);
 extern long kvm_vm_ioctl_allocate_rma(struct kvm *kvm,
                                 struct kvm_allocate_rma *rma);
-extern struct kvmppc_rma_info *kvm_alloc_rma(void);
-extern void kvm_release_rma(struct kvmppc_rma_info *ri);
+extern struct kvmppc_linear_info *kvm_alloc_rma(void);
+extern void kvm_release_rma(struct kvmppc_linear_info *ri);
+extern struct kvmppc_linear_info *kvm_alloc_hpt(void);
+extern void kvm_release_hpt(struct kvmppc_linear_info *li);
 extern int kvmppc_core_init_vm(struct kvm *kvm);
 extern void kvmppc_core_destroy_vm(struct kvm *kvm);
 extern int kvmppc_core_prepare_memory_region(struct kvm *kvm,
@@ -175,6 +178,9 @@ int kvmppc_core_set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs);
 void kvmppc_get_sregs_ivor(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs);
 int kvmppc_set_sregs_ivor(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs);
 
+int kvm_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg);
+int kvm_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg);
+
 void kvmppc_set_pid(struct kvm_vcpu *vcpu, u32 pid);
 
 #ifdef CONFIG_KVM_BOOK3S_64_HV
@@ -183,14 +189,19 @@ static inline void kvmppc_set_xics_phys(int cpu, unsigned long addr)
         paca[cpu].kvm_hstate.xics_phys = addr;
 }
 
-extern void kvm_rma_init(void);
+extern void kvm_linear_init(void);
 
 #else
 static inline void kvmppc_set_xics_phys(int cpu, unsigned long addr)
 {}
 
-static inline void kvm_rma_init(void)
+static inline void kvm_linear_init(void)
 {}
 #endif
 
+int kvm_vcpu_ioctl_config_tlb(struct kvm_vcpu *vcpu,
+                              struct kvm_config_tlb *cfg);
+int kvm_vcpu_ioctl_dirty_tlb(struct kvm_vcpu *vcpu,
+                             struct kvm_dirty_tlb *cfg);
+
 #endif /* __POWERPC_KVM_PPC_H__ */
diff --git a/arch/powerpc/include/asm/lppaca.h b/arch/powerpc/include/asm/lppaca.h
index e0298d26ce5d..a76254af0aaa 100644
--- a/arch/powerpc/include/asm/lppaca.h
+++ b/arch/powerpc/include/asm/lppaca.h
@@ -41,15 +41,7 @@
  * We only have to have statically allocated lppaca structs on
  * legacy iSeries, which supports at most 64 cpus.
  */
-#ifdef CONFIG_PPC_ISERIES
-#if NR_CPUS < 64
-#define NR_LPPACAS      NR_CPUS
-#else
-#define NR_LPPACAS      64
-#endif
-#else /* not iSeries */
 #define NR_LPPACAS      1
-#endif
 
 
 /* The Hypervisor barfs if the lppaca crosses a page boundary.  A 1k
diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h
index bf37931d1ad6..42ce570812c1 100644
--- a/arch/powerpc/include/asm/machdep.h
+++ b/arch/powerpc/include/asm/machdep.h
@@ -99,9 +99,7 @@ struct machdep_calls {
 
         void            (*init_IRQ)(void);
 
-        /* Return an irq, or NO_IRQ to indicate there are none pending.
-         * If for some reason there is no irq, but the interrupt
-         * shouldn't be counted as spurious, return NO_IRQ_IGNORE. */
+        /* Return an irq, or NO_IRQ to indicate there are none pending. */
         unsigned int    (*get_irq)(void);
 
         /* PCI stuff */
diff --git a/arch/powerpc/include/asm/mmu-book3e.h b/arch/powerpc/include/asm/mmu-book3e.h
index f5f89cafebd0..cdb5421877e2 100644
--- a/arch/powerpc/include/asm/mmu-book3e.h
+++ b/arch/powerpc/include/asm/mmu-book3e.h
@@ -41,9 +41,10 @@
 /* MAS registers bit definitions */
 
 #define MAS0_TLBSEL(x)          (((x) << 28) & 0x30000000)
-#define MAS0_ESEL(x)            (((x) << 16) & 0x0FFF0000)
-#define MAS0_NV(x)              ((x) & 0x00000FFF)
 #define MAS0_ESEL_MASK          0x0FFF0000
+#define MAS0_ESEL_SHIFT         16
+#define MAS0_ESEL(x)            (((x) << MAS0_ESEL_SHIFT) & MAS0_ESEL_MASK)
+#define MAS0_NV(x)              ((x) & 0x00000FFF)
 #define MAS0_HES                0x00004000
 #define MAS0_WQ_ALLWAYS         0x00000000
 #define MAS0_WQ_COND            0x00001000
@@ -167,6 +168,7 @@
 #define TLBnCFG_MAXSIZE         0x000f0000      /* Maximum Page Size (v1.0) */
 #define TLBnCFG_MAXSIZE_SHIFT   16
 #define TLBnCFG_ASSOC           0xff000000      /* Associativity */
+#define TLBnCFG_ASSOC_SHIFT     24
 
 /* TLBnPS encoding */
 #define TLBnPS_4K               0x00000004
diff --git a/arch/powerpc/include/asm/mmu-hash64.h b/arch/powerpc/include/asm/mmu-hash64.h
index 412ba493cb98..1c65a59881ea 100644
--- a/arch/powerpc/include/asm/mmu-hash64.h
+++ b/arch/powerpc/include/asm/mmu-hash64.h
@@ -108,11 +108,11 @@ extern char initial_stab[];
 #define HPTE_V_VRMA_MASK        ASM_CONST(0x4001ffffff000000)
 
 /* Values for PP (assumes Ks=0, Kp=1) */
-/* pp0 will always be 0 for linux     */
 #define PP_RWXX 0       /* Supervisor read/write, User none */
 #define PP_RWRX 1       /* Supervisor read/write, User read */
 #define PP_RWRW 2       /* Supervisor read/write, User read/write */
 #define PP_RXRX 3       /* Supervisor read,       User read */
+#define PP_RXXX (HPTE_R_PP0 | 2)        /* Supervisor read, user none */
 
 #ifndef __ASSEMBLY__
 
@@ -267,7 +267,6 @@ extern void demote_segment_4k(struct mm_struct *mm, unsigned long addr);
 
 extern void hpte_init_native(void);
 extern void hpte_init_lpar(void);
-extern void hpte_init_iSeries(void);
 extern void hpte_init_beat(void);
 extern void hpte_init_beat_v3(void);
 
@@ -325,9 +324,6 @@ extern void slb_set_size(u16 size);
  * WARNING - If you change these you must make sure the asm
  * implementations in slb_allocate (slb_low.S), do_stab_bolted
  * (head.S) and ASM_VSID_SCRAMBLE (below) are changed accordingly.
- *
- * You'll also need to change the precomputed VSID values in head.S
- * which are used by the iSeries firmware.
  */
 
 #define VSID_MULTIPLIER_256M    ASM_CONST(200730139)    /* 28-bit prime */
@@ -484,14 +480,6 @@ static inline unsigned long get_vsid(unsigned long context, unsigned long ea,
                              | (ea >> SID_SHIFT_1T), 1T);
 }
 
-/*
- * This is only used on legacy iSeries in lparmap.c,
- * hence the 256MB segment assumption.
- */
-#define VSID_SCRAMBLE(pvsid)    (((pvsid) * VSID_MULTIPLIER_256M) %     \
-                                 VSID_MODULUS_256M)
-#define KERNEL_VSID(ea)         VSID_SCRAMBLE(GET_ESID(ea))
-
 #endif /* __ASSEMBLY__ */
 
 #endif /* _ASM_POWERPC_MMU_HASH64_H_ */
diff --git a/arch/powerpc/include/asm/mpic.h b/arch/powerpc/include/asm/mpic.h
index 67b4d9837236..c65b9294376e 100644
--- a/arch/powerpc/include/asm/mpic.h
+++ b/arch/powerpc/include/asm/mpic.h
@@ -255,7 +255,7 @@ struct mpic
         struct device_node *node;
 
         /* The remapper for this MPIC */
-        struct irq_host         *irqhost;
+        struct irq_domain       *irqhost;
 
         /* The "linux" controller struct */
         struct irq_chip         hc_irq;
@@ -273,7 +273,6 @@ struct mpic
         unsigned int            isu_size;
         unsigned int            isu_shift;
         unsigned int            isu_mask;
-        unsigned int            irq_count;
         /* Number of sources */
         unsigned int            num_sources;
         /* default senses array */
@@ -349,8 +348,6 @@ struct mpic
 #define MPIC_U3_HT_IRQS                 0x00000004
 /* Broken IPI registers (autodetected) */
 #define MPIC_BROKEN_IPI                 0x00000008
-/* MPIC wants a reset */
-#define MPIC_WANTS_RESET                0x00000010
 /* Spurious vector requires EOI */
 #define MPIC_SPV_EOI                    0x00000020
 /* No passthrough disable */
@@ -363,15 +360,11 @@ struct mpic
 #define MPIC_ENABLE_MCK                 0x00000200
 /* Disable bias among target selection, spread interrupts evenly */
 #define MPIC_NO_BIAS                    0x00000400
-/* Ignore NIRQS as reported by FRR */
-#define MPIC_BROKEN_FRR_NIRQS           0x00000800
 /* Destination only supports a single CPU at a time */
 #define MPIC_SINGLE_DEST_CPU            0x00001000
 /* Enable CoreInt delivery of interrupts */
 #define MPIC_ENABLE_COREINT             0x00002000
-/* Disable resetting of the MPIC.
- * NOTE: This flag trumps MPIC_WANTS_RESET.
- */
+/* Do not reset the MPIC during initialization */
 #define MPIC_NO_RESET                   0x00004000
 /* Freescale MPIC (compatible includes "fsl,mpic") */
 #define MPIC_FSL                        0x00008000
diff --git a/arch/powerpc/include/asm/mpic_msgr.h b/arch/powerpc/include/asm/mpic_msgr.h
new file mode 100644
index 000000000000..3ec37dc9003e
--- /dev/null
+++ b/arch/powerpc/include/asm/mpic_msgr.h
@@ -0,0 +1,132 @@
+/*
+ * Copyright 2011-2012, Meador Inge, Mentor Graphics 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; version 2 of the
+ * License.
+ *
+ */
+
+#ifndef _ASM_MPIC_MSGR_H
+#define _ASM_MPIC_MSGR_H
+
+#include <linux/types.h>
+#include <linux/spinlock.h>
+
+struct mpic_msgr {
+        u32 __iomem *base;
+        u32 __iomem *mer;
+        int irq;
+        unsigned char in_use;
+        raw_spinlock_t lock;
+        int num;
+};
+
+/* Get a message register
+ *
+ * @reg_num:    the MPIC message register to get
+ *
+ * A pointer to the message register is returned.  If
+ * the message register asked for is already in use, then
+ * EBUSY is returned.  If the number given is not associated
+ * with an actual message register, then ENODEV is returned.
+ * Successfully getting the register marks it as in use.
+ */
+extern struct mpic_msgr *mpic_msgr_get(unsigned int reg_num);
+
+/* Relinquish a message register
+ *
+ * @msgr:       the message register to return
+ *
+ * Disables the given message register and marks it as free.
+ * After this call has completed successully the message
+ * register is available to be acquired by a call to
+ * mpic_msgr_get.
+ */
+extern void mpic_msgr_put(struct mpic_msgr *msgr);
+
+/* Enable a message register
+ *
+ * @msgr:       the message register to enable
+ *
+ * The given message register is enabled for sending
+ * messages.
+ */
+extern void mpic_msgr_enable(struct mpic_msgr *msgr);
+
+/* Disable a message register
+ *
+ * @msgr:       the message register to disable
+ *
+ * The given message register is disabled for sending
+ * messages.
+ */
+extern void mpic_msgr_disable(struct mpic_msgr *msgr);
+
+/* Write a message to a message register
+ *
+ * @msgr:       the message register to write to
+ * @message:    the message to write
+ *
+ * The given 32-bit message is written to the given message
+ * register.  Writing to an enabled message registers fires
+ * an interrupt.
+ */
+static inline void mpic_msgr_write(struct mpic_msgr *msgr, u32 message)
+{
+        out_be32(msgr->base, message);
+}
+
+/* Read a message from a message register
+ *
+ * @msgr:       the message register to read from
+ *
+ * Returns the 32-bit value currently in the given message register.
+ * Upon reading the register any interrupts for that register are
+ * cleared.
+ */
+static inline u32 mpic_msgr_read(struct mpic_msgr *msgr)
+{
+        return in_be32(msgr->base);
+}
+
+/* Clear a message register
+ *
+ * @msgr:       the message register to clear
+ *
+ * Clears any interrupts associated with the given message register.
+ */
+static inline void mpic_msgr_clear(struct mpic_msgr *msgr)
+{
+        (void) mpic_msgr_read(msgr);
+}
+
+/* Set the destination CPU for the message register
+ *
+ * @msgr:       the message register whose destination is to be set
+ * @cpu_num:    the Linux CPU number to bind the message register to
+ *
+ * Note that the CPU number given is the CPU number used by the kernel
+ * and *not* the actual hardware CPU number.
+ */
+static inline void mpic_msgr_set_destination(struct mpic_msgr *msgr,
+                                             u32 cpu_num)
+{
+        out_be32(msgr->base, 1 << get_hard_smp_processor_id(cpu_num));
+}
+
+/* Get the IRQ number for the message register
+ * @msgr:       the message register whose IRQ is to be returned
+ *
+ * Returns the IRQ number associated with the given message register.
+ * NO_IRQ is returned if this message register is not capable of
+ * receiving interrupts.  What message register can and cannot receive
+ * interrupts is specified in the device tree for the system.
+ */
+static inline int mpic_msgr_get_irq(struct mpic_msgr *msgr)
+{
+        return msgr->irq;
+}
+
+#endif
diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h
index 269c05a36d91..daf813fea91f 100644
--- a/arch/powerpc/include/asm/paca.h
+++ b/arch/powerpc/include/asm/paca.h
@@ -132,7 +132,7 @@ struct paca_struct {
         u64 saved_msr;                  /* MSR saved here by enter_rtas */
         u16 trap_save;                  /* Used when bad stack is encountered */
         u8 soft_enabled;                /* irq soft-enable flag */
-        u8 hard_enabled;                /* set if irqs are enabled in MSR */
+        u8 irq_happened;                /* irq happened while soft-disabled */
         u8 io_sync;                     /* writel() needs spin_unlock sync */
         u8 irq_work_pending;            /* IRQ_WORK interrupt while soft-disable */
         u8 nap_state_lost;              /* NV GPR values lost in power7_idle */
diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h
index 5d487657322e..ac39e6a3b25a 100644
--- a/arch/powerpc/include/asm/pci-bridge.h
+++ b/arch/powerpc/include/asm/pci-bridge.h
@@ -155,14 +155,7 @@ struct pci_dn {
 
         struct  pci_dev *pcidev;        /* back-pointer to the pci device */
 #ifdef CONFIG_EEH
-        int     class_code;             /* pci device class */
-        int     eeh_mode;               /* See eeh.h for possible EEH_MODEs */
-        int     eeh_config_addr;
-        int     eeh_pe_config_addr; /* new-style partition endpoint address */
-        int     eeh_check_count;        /* # times driver ignored error */
-        int     eeh_freeze_count;       /* # times this device froze up. */
-        int     eeh_false_positives;    /* # times this device reported #ff's */
-        u32     config_space[16];       /* saved PCI config space */
+        struct eeh_dev *edev;           /* eeh device */
 #endif
 #define IODA_INVALID_PE         (-1)
 #ifdef CONFIG_PPC_POWERNV
@@ -185,6 +178,13 @@ static inline int pci_device_from_OF_node(struct device_node *np,
         return 0;
 }
 
+#if defined(CONFIG_EEH)
+static inline struct eeh_dev *of_node_to_eeh_dev(struct device_node *dn)
+{
+        return PCI_DN(dn)->edev;
+}
+#endif
+
 /** Find the bus corresponding to the indicated device node */
 extern struct pci_bus *pcibios_find_pci_bus(struct device_node *dn);
 
diff --git a/arch/powerpc/include/asm/pci.h b/arch/powerpc/include/asm/pci.h
index f54b3d26ce9d..6653f2743c4e 100644
--- a/arch/powerpc/include/asm/pci.h
+++ b/arch/powerpc/include/asm/pci.h
@@ -154,14 +154,6 @@ extern int pci_mmap_legacy_page_range(struct pci_bus *bus,
 
 #endif /* CONFIG_PPC64 */
 
-extern void pcibios_resource_to_bus(struct pci_dev *dev,
-                        struct pci_bus_region *region,
-                        struct resource *res);
-
-extern void pcibios_bus_to_resource(struct pci_dev *dev,
-                        struct resource *res,
-                        struct pci_bus_region *region);
-
 extern void pcibios_claim_one_bus(struct pci_bus *b);
 
 extern void pcibios_finish_adding_to_bus(struct pci_bus *bus);
@@ -190,6 +182,7 @@ extern void pci_resource_to_user(const struct pci_dev *dev, int bar,
                                  const struct resource *rsrc,
                                  resource_size_t *start, resource_size_t *end);
 
+extern resource_size_t pcibios_io_space_offset(struct pci_controller *hose);
 extern void pcibios_setup_bus_devices(struct pci_bus *bus);
 extern void pcibios_setup_bus_self(struct pci_bus *bus);
 extern void pcibios_setup_phb_io_space(struct pci_controller *hose);
diff --git a/arch/powerpc/include/asm/perf_event_server.h b/arch/powerpc/include/asm/perf_event_server.h
index 8f1df1208d23..078019b5b353 100644
--- a/arch/powerpc/include/asm/perf_event_server.h
+++ b/arch/powerpc/include/asm/perf_event_server.h
@@ -47,6 +47,8 @@ struct power_pmu {
  */
 #define PPMU_LIMITED_PMC5_6     1       /* PMC5/6 have limited function */
 #define PPMU_ALT_SIPR           2       /* uses alternate posn for SIPR/HV */
+#define PPMU_NO_SIPR            4       /* no SIPR/HV in MMCRA at all */
+#define PPMU_NO_CONT_SAMPLING   8       /* no continuous sampling */
 
 /*
  * Values for flags to get_alternatives()
@@ -61,8 +63,6 @@ struct pt_regs;
 extern unsigned long perf_misc_flags(struct pt_regs *regs);
 extern unsigned long perf_instruction_pointer(struct pt_regs *regs);
 
-#define PERF_EVENT_INDEX_OFFSET 1
-
 /*
  * Only override the default definitions in include/linux/perf_event.h
  * if we have hardware PMU support.
diff --git a/arch/powerpc/include/asm/phyp_dump.h b/arch/powerpc/include/asm/phyp_dump.h
deleted file mode 100644
index fa74c6c3e106..000000000000
--- a/arch/powerpc/include/asm/phyp_dump.h
+++ /dev/null
@@ -1,47 +0,0 @@
-/*
- * Hypervisor-assisted dump
- *
- * Linas Vepstas, Manish Ahuja 2008
- * Copyright 2008 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 _PPC64_PHYP_DUMP_H
-#define _PPC64_PHYP_DUMP_H
-
-#ifdef CONFIG_PHYP_DUMP
-
-/* The RMR region will be saved for later dumping
- * whenever the kernel crashes. Set this to 256MB. */
-#define PHYP_DUMP_RMR_START 0x0
-#define PHYP_DUMP_RMR_END   (1UL<<28)
-
-struct phyp_dump {
-        /* Memory that is reserved during very early boot. */
-        unsigned long init_reserve_start;
-        unsigned long init_reserve_size;
-        /* cmd line options during boot */
-        unsigned long reserve_bootvar;
-        unsigned long phyp_dump_at_boot;
-        /* Check status during boot if dump supported, active & present*/
-        unsigned long phyp_dump_configured;
-        unsigned long phyp_dump_is_active;
-        /* store cpu & hpte size */
-        unsigned long cpu_state_size;
-        unsigned long hpte_region_size;
-        /* previous scratch area values */
-        unsigned long reserved_scratch_addr;
-        unsigned long reserved_scratch_size;
-};
-
-extern struct phyp_dump *phyp_dump_info;
-
-int early_init_dt_scan_phyp_dump(unsigned long node,
-                const char *uname, int depth, void *data);
-
-#endif /* CONFIG_PHYP_DUMP */
-#endif /* _PPC64_PHYP_DUMP_H */
diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h
index e980faae4225..d81f99430fe7 100644
--- a/arch/powerpc/include/asm/ppc-opcode.h
+++ b/arch/powerpc/include/asm/ppc-opcode.h
@@ -45,6 +45,7 @@
 #define PPC_INST_MFSPR_DSCR_MASK        0xfc1fffff
 #define PPC_INST_MTSPR_DSCR             0x7c1103a6
 #define PPC_INST_MTSPR_DSCR_MASK        0xfc1fffff
+#define PPC_INST_SLBFEE                 0x7c0007a7
 
 #define PPC_INST_STRING                 0x7c00042a
 #define PPC_INST_STRING_MASK            0xfc0007fe
@@ -183,7 +184,8 @@
                                         __PPC_RS(t) | __PPC_RA(a) | __PPC_RB(b))
 #define PPC_ERATSX_DOT(t, a, w) stringify_in_c(.long PPC_INST_ERATSX_DOT | \
                                         __PPC_RS(t) | __PPC_RA(a) | __PPC_RB(b))
-
+#define PPC_SLBFEE_DOT(t, b)    stringify_in_c(.long PPC_INST_SLBFEE | \
+                                        __PPC_RT(t) | __PPC_RB(b))
 
 /*
  * Define what the VSX XX1 form instructions will look like, then add
diff --git a/arch/powerpc/include/asm/ppc-pci.h b/arch/powerpc/include/asm/ppc-pci.h
index 43268f15004e..80fa704d410f 100644
--- a/arch/powerpc/include/asm/ppc-pci.h
+++ b/arch/powerpc/include/asm/ppc-pci.h
@@ -45,94 +45,21 @@ extern void init_pci_config_tokens (void);
 extern unsigned long get_phb_buid (struct device_node *);
 extern int rtas_setup_phb(struct pci_controller *phb);
 
-extern unsigned long pci_probe_only;
-
-/* ---- EEH internal-use-only related routines ---- */
 #ifdef CONFIG_EEH
 
+void pci_addr_cache_build(void);
 void pci_addr_cache_insert_device(struct pci_dev *dev);
 void pci_addr_cache_remove_device(struct pci_dev *dev);
-void pci_addr_cache_build(void);
-struct pci_dev *pci_get_device_by_addr(unsigned long addr);
-
-/**
- * eeh_slot_error_detail -- record and EEH error condition to the log
- * @pdn:      pci device node
- * @severity: EEH_LOG_TEMP_FAILURE or EEH_LOG_PERM_FAILURE
- *
- * Obtains the EEH error details from the RTAS subsystem,
- * and then logs these details with the RTAS error log system.
- */
-#define EEH_LOG_TEMP_FAILURE 1
-#define EEH_LOG_PERM_FAILURE 2
-void eeh_slot_error_detail (struct pci_dn *pdn, int severity);
-
-/**
- * rtas_pci_enable - enable IO transfers for this slot
- * @pdn:       pci device node
- * @function:  either EEH_THAW_MMIO or EEH_THAW_DMA 
- *
- * Enable I/O transfers to this slot 
- */
-#define EEH_THAW_MMIO 2
-#define EEH_THAW_DMA  3
-int rtas_pci_enable(struct pci_dn *pdn, int function);
-
-/**
- * rtas_set_slot_reset -- unfreeze a frozen slot
- * @pdn:       pci device node
- *
- * Clear the EEH-frozen condition on a slot.  This routine
- * does this by asserting the PCI #RST line for 1/8th of
- * a second; this routine will sleep while the adapter is
- * being reset.
- *
- * Returns a non-zero value if the reset failed.
- */
-int rtas_set_slot_reset (struct pci_dn *);
-int eeh_wait_for_slot_status(struct pci_dn *pdn, int max_wait_msecs);
-
-/** 
- * eeh_restore_bars - Restore device configuration info.
- * @pdn:       pci device node
- *
- * A reset of a PCI device will clear out its config space.
- * This routines will restore the config space for this
- * device, and is children, to values previously obtained
- * from the firmware.
- */
-void eeh_restore_bars(struct pci_dn *);
-
-/**
- * rtas_configure_bridge -- firmware initialization of pci bridge
- * @pdn:       pci device node
- *
- * Ask the firmware to configure all PCI bridges devices
- * located behind the indicated node. Required after a
- * pci device reset. Does essentially the same hing as
- * eeh_restore_bars, but for brdges, and lets firmware 
- * do the work.
- */
-void rtas_configure_bridge(struct pci_dn *);
-
+struct pci_dev *pci_addr_cache_get_device(unsigned long addr);
+void eeh_slot_error_detail(struct eeh_dev *edev, int severity);
+int eeh_pci_enable(struct eeh_dev *edev, int function);
+int eeh_reset_pe(struct eeh_dev *);
+void eeh_restore_bars(struct eeh_dev *);
 int rtas_write_config(struct pci_dn *, int where, int size, u32 val);
 int rtas_read_config(struct pci_dn *, int where, int size, u32 *val);
-
-/**
- * eeh_mark_slot -- set mode flags for pertition endpoint
- * @pdn:       pci device node
- *
- * mark and clear slots: find "partition endpoint" PE and set or 
- * clear the flags for each subnode of the PE.
- */
-void eeh_mark_slot (struct device_node *dn, int mode_flag);
-void eeh_clear_slot (struct device_node *dn, int mode_flag);
-
-/**
- * find_device_pe -- Find the associated "Partiationable Endpoint" PE
- * @pdn:       pci device node
- */
-struct device_node * find_device_pe(struct device_node *dn);
+void eeh_mark_slot(struct device_node *dn, int mode_flag);
+void eeh_clear_slot(struct device_node *dn, int mode_flag);
+struct device_node *eeh_find_device_pe(struct device_node *dn);
 
 void eeh_sysfs_add_device(struct pci_dev *pdev);
 void eeh_sysfs_remove_device(struct pci_dev *pdev);
@@ -142,6 +69,11 @@ static inline const char *eeh_pci_name(struct pci_dev *pdev)
         return pdev ? pci_name(pdev) : "<null>";
 } 
 
+static inline const char *eeh_driver_name(struct pci_dev *pdev)
+{
+        return (pdev && pdev->driver) ? pdev->driver->name : "<null>";
+}
+
 #endif /* CONFIG_EEH */
 
 #else /* CONFIG_PCI */
diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h
index 368f72f79808..50f73aa2ba21 100644
--- a/arch/powerpc/include/asm/ppc_asm.h
+++ b/arch/powerpc/include/asm/ppc_asm.h
@@ -60,6 +60,8 @@ BEGIN_FW_FTR_SECTION;							\
         cmpd    cr1,r11,r10;                                            \
         beq+    cr1,33f;                                                \
         bl      .accumulate_stolen_time;                                \
+        ld      r12,_MSR(r1);                                           \
+        andi.   r10,r12,MSR_PR;         /* Restore cr0 (coming from user) */ \
 33:                                                                     \
 END_FW_FTR_SECTION_IFSET(FW_FEATURE_SPLPAR)
 
diff --git a/arch/powerpc/include/asm/ptrace.h b/arch/powerpc/include/asm/ptrace.h
index 78a205162fd7..84cc7840cd18 100644
--- a/arch/powerpc/include/asm/ptrace.h
+++ b/arch/powerpc/include/asm/ptrace.h
@@ -83,8 +83,18 @@ struct pt_regs {
 
 #ifndef __ASSEMBLY__
 
-#define instruction_pointer(regs) ((regs)->nip)
-#define user_stack_pointer(regs) ((regs)->gpr[1])
+#define GET_IP(regs)            ((regs)->nip)
+#define GET_USP(regs)           ((regs)->gpr[1])
+#define GET_FP(regs)            (0)
+#define SET_FP(regs, val)
+
+#ifdef CONFIG_SMP
+extern unsigned long profile_pc(struct pt_regs *regs);
+#define profile_pc profile_pc
+#endif
+
+#include <asm-generic/ptrace.h>
+
 #define kernel_stack_pointer(regs) ((regs)->gpr[1])
 static inline int is_syscall_success(struct pt_regs *regs)
 {
@@ -99,12 +109,6 @@ static inline long regs_return_value(struct pt_regs *regs)
                 return -regs->gpr[3];
 }
 
-#ifdef CONFIG_SMP
-extern unsigned long profile_pc(struct pt_regs *regs);
-#else
-#define profile_pc(regs) instruction_pointer(regs)
-#endif
-
 #ifdef __powerpc64__
 #define user_mode(regs) ((((regs)->msr) >> MSR_PR_LG) & 0x1)
 #else
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index 7fdc2c0b7fa0..9d7f0fb69028 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -216,6 +216,7 @@
 #define   DSISR_ISSTORE         0x02000000      /* access was a store */
 #define   DSISR_DABRMATCH       0x00400000      /* hit data breakpoint */
 #define   DSISR_NOSEGMENT       0x00200000      /* STAB/SLB miss */
+#define   DSISR_KEYFAULT        0x00200000      /* Key fault */
 #define SPRN_TBRL       0x10C   /* Time Base Read Lower Register (user, R/O) */
 #define SPRN_TBRU       0x10D   /* Time Base Read Upper Register (user, R/O) */
 #define SPRN_TBWL       0x11C   /* Time Base Lower Register (super, R/W) */
@@ -237,6 +238,7 @@
 #define   LPCR_ISL      (1ul << (63-2))
 #define   LPCR_VC_SH    (63-2)
 #define   LPCR_DPFD_SH  (63-11)
+#define   LPCR_VRMASD   (0x1ful << (63-16))
 #define   LPCR_VRMA_L   (1ul << (63-12))
 #define   LPCR_VRMA_LP0 (1ul << (63-15))
 #define   LPCR_VRMA_LP1 (1ul << (63-16))
@@ -493,6 +495,9 @@
 #define SPRN_SPRG7      0x117   /* Special Purpose Register General 7 */
 #define SPRN_SRR0       0x01A   /* Save/Restore Register 0 */
 #define SPRN_SRR1       0x01B   /* Save/Restore Register 1 */
+#define   SRR1_ISI_NOPT         0x40000000 /* ISI: Not found in hash */
+#define   SRR1_ISI_N_OR_G       0x10000000 /* ISI: Access is no-exec or G */
+#define   SRR1_ISI_PROT         0x08000000 /* ISI: Other protection fault */
 #define   SRR1_WAKEMASK         0x00380000 /* reason for wakeup */
 #define   SRR1_WAKESYSERR       0x00300000 /* System error */
 #define   SRR1_WAKEEE           0x00200000 /* External interrupt */
@@ -1079,30 +1084,12 @@
 
 #define proc_trap()     asm volatile("trap")
 
-#ifdef CONFIG_PPC64
-
-extern void ppc64_runlatch_on(void);
-extern void __ppc64_runlatch_off(void);
-
-#define ppc64_runlatch_off()                                    \
-        do {                                                    \
-                if (cpu_has_feature(CPU_FTR_CTRL) &&            \
-                    test_thread_flag(TIF_RUNLATCH))             \
-                        __ppc64_runlatch_off();                 \
-        } while (0)
+#define __get_SP()      ({unsigned long sp; \
+                        asm volatile("mr %0,1": "=r" (sp)); sp;})
 
 extern unsigned long scom970_read(unsigned int address);
 extern void scom970_write(unsigned int address, unsigned long value);
 
-#else
-#define ppc64_runlatch_on()
-#define ppc64_runlatch_off()
-
-#endif /* CONFIG_PPC64 */
-
-#define __get_SP()      ({unsigned long sp; \
-                        asm volatile("mr %0,1": "=r" (sp)); sp;})
-
 struct pt_regs;
 
 extern void ppc_save_regs(struct pt_regs *regs);
diff --git a/arch/powerpc/include/asm/reg_booke.h b/arch/powerpc/include/asm/reg_booke.h
index 500fe1dc43e6..8a97aa7289d3 100644
--- a/arch/powerpc/include/asm/reg_booke.h
+++ b/arch/powerpc/include/asm/reg_booke.h
@@ -62,6 +62,7 @@
 #define SPRN_DVC2       0x13F   /* Data Value Compare Register 2 */
 #define SPRN_MAS8       0x155   /* MMU Assist Register 8 */
 #define SPRN_TLB0PS     0x158   /* TLB 0 Page Size Register */
+#define SPRN_TLB1PS     0x159   /* TLB 1 Page Size Register */
 #define SPRN_MAS5_MAS6  0x15c   /* MMU Assist Register 5 || 6 */
 #define SPRN_MAS8_MAS1  0x15d   /* MMU Assist Register 8 || 1 */
 #define SPRN_EPTCFG     0x15e   /* Embedded Page Table Config */
diff --git a/arch/powerpc/include/asm/rtas.h b/arch/powerpc/include/asm/rtas.h
index 01c143bb77ae..f0a4db31ecb6 100644
--- a/arch/powerpc/include/asm/rtas.h
+++ b/arch/powerpc/include/asm/rtas.h
@@ -74,7 +74,6 @@ struct rtas_suspend_me_data {
 /* RTAS event classes */
 #define RTAS_INTERNAL_ERROR             0x80000000 /* set bit 0 */
 #define RTAS_EPOW_WARNING               0x40000000 /* set bit 1 */
-#define RTAS_POWERMGM_EVENTS            0x20000000 /* set bit 2 */
 #define RTAS_HOTPLUG_EVENTS             0x10000000 /* set bit 3 */
 #define RTAS_IO_EVENTS                  0x08000000 /* set bit 4 */
 #define RTAS_EVENT_SCAN_ALL_EVENTS      0xffffffff
@@ -204,6 +203,39 @@ struct rtas_ext_event_log_v6 {
                                         /* Variable length.             */
 };
 
+/* pSeries event log format */
+
+/* Two bytes ASCII section IDs */
+#define PSERIES_ELOG_SECT_ID_PRIV_HDR           (('P' << 8) | 'H')
+#define PSERIES_ELOG_SECT_ID_USER_HDR           (('U' << 8) | 'H')
+#define PSERIES_ELOG_SECT_ID_PRIMARY_SRC        (('P' << 8) | 'S')
+#define PSERIES_ELOG_SECT_ID_EXTENDED_UH        (('E' << 8) | 'H')
+#define PSERIES_ELOG_SECT_ID_FAILING_MTMS       (('M' << 8) | 'T')
+#define PSERIES_ELOG_SECT_ID_SECONDARY_SRC      (('S' << 8) | 'S')
+#define PSERIES_ELOG_SECT_ID_DUMP_LOCATOR       (('D' << 8) | 'H')
+#define PSERIES_ELOG_SECT_ID_FW_ERROR           (('S' << 8) | 'W')
+#define PSERIES_ELOG_SECT_ID_IMPACT_PART_ID     (('L' << 8) | 'P')
+#define PSERIES_ELOG_SECT_ID_LOGIC_RESOURCE_ID  (('L' << 8) | 'R')
+#define PSERIES_ELOG_SECT_ID_HMC_ID             (('H' << 8) | 'M')
+#define PSERIES_ELOG_SECT_ID_EPOW               (('E' << 8) | 'P')
+#define PSERIES_ELOG_SECT_ID_IO_EVENT           (('I' << 8) | 'E')
+#define PSERIES_ELOG_SECT_ID_MANUFACT_INFO      (('M' << 8) | 'I')
+#define PSERIES_ELOG_SECT_ID_CALL_HOME          (('C' << 8) | 'H')
+#define PSERIES_ELOG_SECT_ID_USER_DEF           (('U' << 8) | 'D')
+
+/* Vendor specific Platform Event Log Format, Version 6, section header */
+struct pseries_errorlog {
+        uint16_t id;                    /* 0x00 2-byte ASCII section ID */
+        uint16_t length;                /* 0x02 Section length in bytes */
+        uint8_t version;                /* 0x04 Section version         */
+        uint8_t subtype;                /* 0x05 Section subtype         */
+        uint16_t creator_component;     /* 0x06 Creator component ID    */
+        uint8_t data[];                 /* 0x08 Start of section data   */
+};
+
+struct pseries_errorlog *get_pseries_errorlog(struct rtas_error_log *log,
+                                              uint16_t section_id);
+
 /*
  * This can be set by the rtas_flash module so that it can get called
  * as the absolutely last thing before the kernel terminates.
diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h
index adba970ce918..ebc24dc5b1a1 100644
--- a/arch/powerpc/include/asm/smp.h
+++ b/arch/powerpc/include/asm/smp.h
@@ -122,7 +122,6 @@ extern void smp_muxed_ipi_set_data(int cpu, unsigned long data);
 extern void smp_muxed_ipi_message_pass(int cpu, int msg);
 extern irqreturn_t smp_ipi_demux(void);
 
-void smp_init_iSeries(void);
 void smp_init_pSeries(void);
 void smp_init_cell(void);
 void smp_init_celleb(void);
diff --git a/arch/powerpc/include/asm/socket.h b/arch/powerpc/include/asm/socket.h
index 2fc2af8fbf59..3d5179bb122f 100644
--- a/arch/powerpc/include/asm/socket.h
+++ b/arch/powerpc/include/asm/socket.h
@@ -71,5 +71,9 @@
 
 #define SO_WIFI_STATUS          41
 #define SCM_WIFI_STATUS         SO_WIFI_STATUS
+#define SO_PEEK_OFF             42
+
+/* Instruct lower device to use last 4-bytes of skb data as FCS */
+#define SO_NOFCS                43
 
 #endif  /* _ASM_POWERPC_SOCKET_H */
diff --git a/arch/powerpc/include/asm/spinlock.h b/arch/powerpc/include/asm/spinlock.h
index f9611bd69ed2..7124fc06ad47 100644
--- a/arch/powerpc/include/asm/spinlock.h
+++ b/arch/powerpc/include/asm/spinlock.h
@@ -23,7 +23,6 @@
 #ifdef CONFIG_PPC64
 #include <asm/paca.h>
 #include <asm/hvcall.h>
-#include <asm/iseries/hv_call.h>
 #endif
 #include <asm/asm-compat.h>
 #include <asm/synch.h>
@@ -95,12 +94,12 @@ static inline int arch_spin_trylock(arch_spinlock_t *lock)
  * value.
  */
 
-#if defined(CONFIG_PPC_SPLPAR) || defined(CONFIG_PPC_ISERIES)
+#if defined(CONFIG_PPC_SPLPAR)
 /* We only yield to the hypervisor if we are in shared processor mode */
 #define SHARED_PROCESSOR (get_lppaca()->shared_proc)
 extern void __spin_yield(arch_spinlock_t *lock);
 extern void __rw_yield(arch_rwlock_t *lock);
-#else /* SPLPAR || ISERIES */
+#else /* SPLPAR */
 #define __spin_yield(x) barrier()
 #define __rw_yield(x)   barrier()
 #define SHARED_PROCESSOR        0
diff --git a/arch/powerpc/include/asm/system.h b/arch/powerpc/include/asm/system.h
index c377457d1b89..a02883d5af43 100644
--- a/arch/powerpc/include/asm/system.h
+++ b/arch/powerpc/include/asm/system.h
@@ -550,5 +550,43 @@ extern void reloc_got2(unsigned long);
 
 extern struct dentry *powerpc_debugfs_root;
 
+#ifdef CONFIG_PPC64
+
+extern void __ppc64_runlatch_on(void);
+extern void __ppc64_runlatch_off(void);
+
+/*
+ * We manually hard enable-disable, this is called
+ * in the idle loop and we don't want to mess up
+ * with soft-disable/enable & interrupt replay.
+ */
+#define ppc64_runlatch_off()                                    \
+        do {                                                    \
+                if (cpu_has_feature(CPU_FTR_CTRL) &&            \
+                    test_thread_local_flags(_TLF_RUNLATCH)) {   \
+                        unsigned long msr = mfmsr();            \
+                        __hard_irq_disable();                   \
+                        __ppc64_runlatch_off();                 \
+                        if (msr & MSR_EE)                       \
+                                __hard_irq_enable();            \
+                }                                               \
+        } while (0)
+
+#define ppc64_runlatch_on()                                     \
+        do {                                                    \
+                if (cpu_has_feature(CPU_FTR_CTRL) &&            \
+                    !test_thread_local_flags(_TLF_RUNLATCH)) {  \
+                        unsigned long msr = mfmsr();            \
+                        __hard_irq_disable();                   \
+                        __ppc64_runlatch_on();                  \
+                        if (msr & MSR_EE)                       \
+                                __hard_irq_enable();            \
+                }                                               \
+        } while (0)
+#else
+#define ppc64_runlatch_on()
+#define ppc64_runlatch_off()
+#endif /* CONFIG_PPC64 */
+
 #endif /* __KERNEL__ */
 #endif /* _ASM_POWERPC_SYSTEM_H */
diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h
index 964714940961..4a741c7efd02 100644
--- a/arch/powerpc/include/asm/thread_info.h
+++ b/arch/powerpc/include/asm/thread_info.h
@@ -110,7 +110,6 @@ static inline struct thread_info *current_thread_info(void)
 #define TIF_NOERROR             12      /* Force successful syscall return */
 #define TIF_NOTIFY_RESUME       13      /* callback before returning to user */
 #define TIF_SYSCALL_TRACEPOINT  15      /* syscall tracepoint instrumentation */
-#define TIF_RUNLATCH            16      /* Is the runlatch enabled? */
 
 /* as above, but as bit values */
 #define _TIF_SYSCALL_TRACE      (1<<TIF_SYSCALL_TRACE)
@@ -141,11 +140,13 @@ static inline struct thread_info *current_thread_info(void)
 #define TLF_SLEEPING            1       /* suspend code enabled SLEEP mode */
 #define TLF_RESTORE_SIGMASK     2       /* Restore signal mask in do_signal */
 #define TLF_LAZY_MMU            3       /* tlb_batch is active */
+#define TLF_RUNLATCH            4       /* Is the runlatch enabled? */
 
 #define _TLF_NAPPING            (1 << TLF_NAPPING)
 #define _TLF_SLEEPING           (1 << TLF_SLEEPING)
 #define _TLF_RESTORE_SIGMASK    (1 << TLF_RESTORE_SIGMASK)
 #define _TLF_LAZY_MMU           (1 << TLF_LAZY_MMU)
+#define _TLF_RUNLATCH           (1 << TLF_RUNLATCH)
 
 #ifndef __ASSEMBLY__
 #define HAVE_SET_RESTORE_SIGMASK        1
@@ -156,6 +157,12 @@ static inline void set_restore_sigmask(void)
         set_bit(TIF_SIGPENDING, &ti->flags);
 }
 
+static inline bool test_thread_local_flags(unsigned int flags)
+{
+        struct thread_info *ti = current_thread_info();
+        return (ti->local_flags & flags) != 0;
+}
+
 #ifdef CONFIG_PPC64
 #define is_32bit_task() (test_thread_flag(TIF_32BIT))
 #else
diff --git a/arch/powerpc/include/asm/time.h b/arch/powerpc/include/asm/time.h
index 7eb10fb96cd0..2136f58a54e8 100644
--- a/arch/powerpc/include/asm/time.h
+++ b/arch/powerpc/include/asm/time.h
@@ -18,11 +18,6 @@
 #include <linux/percpu.h>
 
 #include <asm/processor.h>
-#ifdef CONFIG_PPC_ISERIES
-#include <asm/paca.h>
-#include <asm/firmware.h>
-#include <asm/iseries/hv_call.h>
-#endif
 
 /* time.c */
 extern unsigned long tb_ticks_per_jiffy;
@@ -167,15 +162,6 @@ static inline void set_dec(int val)
 #ifndef CONFIG_BOOKE
         --val;
 #endif
-#ifdef CONFIG_PPC_ISERIES
-        if (firmware_has_feature(FW_FEATURE_ISERIES) &&
-                        get_lppaca()->shared_proc) {
-                get_lppaca()->virtual_decr = val;
-                if (get_dec() > val)
-                        HvCall_setVirtualDecr();
-                return;
-        }
-#endif
         mtspr(SPRN_DEC, val);
 #endif /* not 40x or 8xx_CPU6 */
 }
@@ -217,7 +203,6 @@ DECLARE_PER_CPU(struct cpu_usage, cpu_usage_array);
 #endif
 
 extern void secondary_cpu_time_init(void);
-extern void iSeries_time_init_early(void);
 
 DECLARE_PER_CPU(u64, decrementers_next_tb);
 
diff --git a/arch/powerpc/include/asm/udbg.h b/arch/powerpc/include/asm/udbg.h
index 8338aef5a4d3..b3038817b8dc 100644
--- a/arch/powerpc/include/asm/udbg.h
+++ b/arch/powerpc/include/asm/udbg.h
@@ -44,7 +44,6 @@ extern void __init udbg_init_debug_lpar_hvsi(void);
 extern void __init udbg_init_pmac_realmode(void);
 extern void __init udbg_init_maple_realmode(void);
 extern void __init udbg_init_pas_realmode(void);
-extern void __init udbg_init_iseries(void);
 extern void __init udbg_init_rtas_panel(void);
 extern void __init udbg_init_rtas_console(void);
 extern void __init udbg_init_debug_beat(void);
diff --git a/arch/powerpc/include/asm/vio.h b/arch/powerpc/include/asm/vio.h
index 0a290a195946..6bfd5ffe1d4f 100644
--- a/arch/powerpc/include/asm/vio.h
+++ b/arch/powerpc/include/asm/vio.h
@@ -69,6 +69,7 @@ struct vio_dev {
 };
 
 struct vio_driver {
+        const char *name;
         const struct vio_device_id *id_table;
         int (*probe)(struct vio_dev *dev, const struct vio_device_id *id);
         int (*remove)(struct vio_dev *dev);
@@ -76,10 +77,17 @@ struct vio_driver {
          * be loaded in a CMO environment if it uses DMA.
          */
         unsigned long (*get_desired_dma)(struct vio_dev *dev);
+        const struct dev_pm_ops *pm;
         struct device_driver driver;
 };
 
-extern int vio_register_driver(struct vio_driver *drv);
+extern int __vio_register_driver(struct vio_driver *drv, struct module *owner,
+                                 const char *mod_name);
+/*
+ * vio_register_driver must be a macro so that KBUILD_MODNAME can be expanded
+ */
+#define vio_register_driver(driver)             \
+        __vio_register_driver(driver, THIS_MODULE, KBUILD_MODNAME)
 extern void vio_unregister_driver(struct vio_driver *drv);
 
 extern int vio_cmo_entitlement_update(size_t);
diff --git a/arch/powerpc/include/asm/xics.h b/arch/powerpc/include/asm/xics.h
index c48de98ba94e..4ae9a09c3b89 100644
--- a/arch/powerpc/include/asm/xics.h
+++ b/arch/powerpc/include/asm/xics.h
@@ -86,7 +86,7 @@ struct ics {
 extern unsigned int xics_default_server;
 extern unsigned int xics_default_distrib_server;
 extern unsigned int xics_interrupt_server_size;
-extern struct irq_host *xics_host;
+extern struct irq_domain *xics_host;
 
 struct xics_cppr {
         unsigned char stack[MAX_NUM_PRIORITIES];
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index ee728e433aa2..f5808a35688c 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -60,6 +60,7 @@ obj-$(CONFIG_IBMVIO)		+= vio.o
 obj-$(CONFIG_IBMEBUS)           += ibmebus.o
 obj-$(CONFIG_GENERIC_TBSYNC)    += smp-tbsync.o
 obj-$(CONFIG_CRASH_DUMP)        += crash_dump.o
+obj-$(CONFIG_FA_DUMP)           += fadump.o
 ifeq ($(CONFIG_PPC32),y)
 obj-$(CONFIG_E500)              += idle_e500.o
 endif
@@ -113,15 +114,6 @@ obj-$(CONFIG_PPC_IO_WORKAROUNDS)	+= io-workarounds.o
 obj-$(CONFIG_DYNAMIC_FTRACE)    += ftrace.o
 obj-$(CONFIG_FUNCTION_GRAPH_TRACER)     += ftrace.o
 obj-$(CONFIG_FTRACE_SYSCALLS)   += ftrace.o
-obj-$(CONFIG_PERF_EVENTS)       += perf_callchain.o
-
-obj-$(CONFIG_PPC_PERF_CTRS)     += perf_event.o
-obj64-$(CONFIG_PPC_PERF_CTRS)   += power4-pmu.o ppc970-pmu.o power5-pmu.o \
-                                   power5+-pmu.o power6-pmu.o power7-pmu.o
-obj32-$(CONFIG_PPC_PERF_CTRS)   += mpc7450-pmu.o
-
-obj-$(CONFIG_FSL_EMB_PERF_EVENT) += perf_event_fsl_emb.o
-obj-$(CONFIG_FSL_EMB_PERF_EVENT_E500) += e500-pmu.o
 
 obj-$(CONFIG_8XX_MINIMAL_FPEMU) += softemu8xx.o
 
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 04caee7d9bc1..34b8afe94a50 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -46,9 +46,6 @@
 #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
@@ -147,7 +144,7 @@ int main(void)
         DEFINE(PACAKBASE, offsetof(struct paca_struct, kernelbase));
         DEFINE(PACAKMSR, offsetof(struct paca_struct, kernel_msr));
         DEFINE(PACASOFTIRQEN, offsetof(struct paca_struct, soft_enabled));
-        DEFINE(PACAHARDIRQEN, offsetof(struct paca_struct, hard_enabled));
+        DEFINE(PACAIRQHAPPENED, offsetof(struct paca_struct, irq_happened));
         DEFINE(PACACONTEXTID, offsetof(struct paca_struct, context.id));
 #ifdef CONFIG_PPC_MM_SLICES
         DEFINE(PACALOWSLICESPSIZE, offsetof(struct paca_struct,
@@ -384,17 +381,6 @@ int main(void)
         DEFINE(BUG_ENTRY_SIZE, sizeof(struct bug_entry));
 #endif
 
-#ifdef CONFIG_PPC_ISERIES
-        /* the assembler miscalculates the VSID values */
-        DEFINE(PAGE_OFFSET_ESID, GET_ESID(PAGE_OFFSET));
-        DEFINE(PAGE_OFFSET_VSID, KERNEL_VSID(PAGE_OFFSET));
-        DEFINE(VMALLOC_START_ESID, GET_ESID(VMALLOC_START));
-        DEFINE(VMALLOC_START_VSID, KERNEL_VSID(VMALLOC_START));
-
-        /* alpaca */
-        DEFINE(ALPACA_SIZE, sizeof(struct alpaca));
-#endif
-
         DEFINE(PGD_TABLE_SIZE, PGD_TABLE_SIZE);
         DEFINE(PTE_SIZE, sizeof(pte_t));
 
@@ -426,16 +412,23 @@ int main(void)
         DEFINE(VCPU_SPRG2, offsetof(struct kvm_vcpu, arch.shregs.sprg2));
         DEFINE(VCPU_SPRG3, offsetof(struct kvm_vcpu, arch.shregs.sprg3));
 #endif
-        DEFINE(VCPU_SPRG4, offsetof(struct kvm_vcpu, arch.sprg4));
-        DEFINE(VCPU_SPRG5, offsetof(struct kvm_vcpu, arch.sprg5));
-        DEFINE(VCPU_SPRG6, offsetof(struct kvm_vcpu, arch.sprg6));
-        DEFINE(VCPU_SPRG7, offsetof(struct kvm_vcpu, arch.sprg7));
+        DEFINE(VCPU_SHARED_SPRG4, offsetof(struct kvm_vcpu_arch_shared, sprg4));
+        DEFINE(VCPU_SHARED_SPRG5, offsetof(struct kvm_vcpu_arch_shared, sprg5));
+        DEFINE(VCPU_SHARED_SPRG6, offsetof(struct kvm_vcpu_arch_shared, sprg6));
+        DEFINE(VCPU_SHARED_SPRG7, offsetof(struct kvm_vcpu_arch_shared, sprg7));
         DEFINE(VCPU_SHADOW_PID, offsetof(struct kvm_vcpu, arch.shadow_pid));
         DEFINE(VCPU_SHADOW_PID1, offsetof(struct kvm_vcpu, arch.shadow_pid1));
         DEFINE(VCPU_SHARED, offsetof(struct kvm_vcpu, arch.shared));
         DEFINE(VCPU_SHARED_MSR, offsetof(struct kvm_vcpu_arch_shared, msr));
         DEFINE(VCPU_SHADOW_MSR, offsetof(struct kvm_vcpu, arch.shadow_msr));
 
+        DEFINE(VCPU_SHARED_MAS0, offsetof(struct kvm_vcpu_arch_shared, mas0));
+        DEFINE(VCPU_SHARED_MAS1, offsetof(struct kvm_vcpu_arch_shared, mas1));
+        DEFINE(VCPU_SHARED_MAS2, offsetof(struct kvm_vcpu_arch_shared, mas2));
+        DEFINE(VCPU_SHARED_MAS7_3, offsetof(struct kvm_vcpu_arch_shared, mas7_3));
+        DEFINE(VCPU_SHARED_MAS4, offsetof(struct kvm_vcpu_arch_shared, mas4));
+        DEFINE(VCPU_SHARED_MAS6, offsetof(struct kvm_vcpu_arch_shared, mas6));
+
         /* book3s */
 #ifdef CONFIG_KVM_BOOK3S_64_HV
         DEFINE(KVM_LPID, offsetof(struct kvm, arch.lpid));
@@ -448,6 +441,7 @@ int main(void)
         DEFINE(KVM_LAST_VCPU, offsetof(struct kvm, arch.last_vcpu));
         DEFINE(KVM_LPCR, offsetof(struct kvm, arch.lpcr));
         DEFINE(KVM_RMOR, offsetof(struct kvm, arch.rmor));
+        DEFINE(KVM_VRMA_SLB_V, offsetof(struct kvm, arch.vrma_slb_v));
         DEFINE(VCPU_DSISR, offsetof(struct kvm_vcpu, arch.shregs.dsisr));
         DEFINE(VCPU_DAR, offsetof(struct kvm_vcpu, arch.shregs.dar));
 #endif
diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index 81db9e2a8a20..138ae183c440 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -1816,7 +1816,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .platform               = "ppc440",
         },
         { /* 464 in APM821xx */
-                .pvr_mask               = 0xffffff00,
+                .pvr_mask               = 0xfffffff0,
                 .pvr_value              = 0x12C41C80,
                 .cpu_name               = "APM821XX",
                 .cpu_features           = CPU_FTRS_44X,
@@ -2019,6 +2019,24 @@ static struct cpu_spec __initdata cpu_specs[] = {
                 .machine_check          = machine_check_e500mc,
                 .platform               = "ppce5500",
         },
+        {       /* e6500 */
+                .pvr_mask               = 0xffff0000,
+                .pvr_value              = 0x80400000,
+                .cpu_name               = "e6500",
+                .cpu_features           = CPU_FTRS_E6500,
+                .cpu_user_features      = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU,
+                .mmu_features           = MMU_FTR_TYPE_FSL_E | MMU_FTR_BIG_PHYS |
+                        MMU_FTR_USE_TLBILX,
+                .icache_bsize           = 64,
+                .dcache_bsize           = 64,
+                .num_pmcs               = 4,
+                .oprofile_cpu_type      = "ppc/e6500",
+                .oprofile_type          = PPC_OPROFILE_FSL_EMB,
+                .cpu_setup              = __setup_cpu_e5500,
+                .cpu_restore            = __restore_cpu_e5500,
+                .machine_check          = machine_check_e500mc,
+                .platform               = "ppce6500",
+        },
 #ifdef CONFIG_PPC32
         {       /* default match */
                 .pvr_mask               = 0x00000000,
diff --git a/arch/powerpc/kernel/crash.c b/arch/powerpc/kernel/crash.c
index 28be3452e67a..abef75176c07 100644
--- a/arch/powerpc/kernel/crash.c
+++ b/arch/powerpc/kernel/crash.c
@@ -46,7 +46,6 @@
 
 /* This keeps a track of which one is the crashing cpu. */
 int crashing_cpu = -1;
-static atomic_t cpus_in_crash;
 static int time_to_dump;
 
 #define CRASH_HANDLER_MAX 3
@@ -66,6 +65,7 @@ static int handle_fault(struct pt_regs *regs)
 
 #ifdef CONFIG_SMP
 
+static atomic_t cpus_in_crash;
 void crash_ipi_callback(struct pt_regs *regs)
 {
         static cpumask_t cpus_state_saved = CPU_MASK_NONE;
diff --git a/arch/powerpc/kernel/dbell.c b/arch/powerpc/kernel/dbell.c
index 2cc451aaaca7..5b25c8060fd6 100644
--- a/arch/powerpc/kernel/dbell.c
+++ b/arch/powerpc/kernel/dbell.c
@@ -37,6 +37,8 @@ void doorbell_exception(struct pt_regs *regs)
 
         irq_enter();
 
+        may_hard_irq_enable();
+
         smp_ipi_demux();
 
         irq_exit();
diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index 4f80cf1ce77b..3e57a00b8cba 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -1213,7 +1213,7 @@ do_user_signal:			/* r10 contains MSR_KERNEL here */
         stw     r3,_TRAP(r1)
 2:      addi    r3,r1,STACK_FRAME_OVERHEAD
         mr      r4,r9
-        bl      do_signal
+        bl      do_notify_resume
         REST_NVGPRS(r1)
         b       recheck
 
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index d834425186ae..f8a7a1a1a9f4 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -32,6 +32,7 @@
 #include <asm/ptrace.h>
 #include <asm/irqflags.h>
 #include <asm/ftrace.h>
+#include <asm/hw_irq.h>
 
 /*
  * System calls.
@@ -115,39 +116,33 @@ BEGIN_FW_FTR_SECTION
 END_FW_FTR_SECTION_IFSET(FW_FEATURE_SPLPAR)
 #endif /* CONFIG_VIRT_CPU_ACCOUNTING && CONFIG_PPC_SPLPAR */
 
-#ifdef CONFIG_TRACE_IRQFLAGS
-        bl      .trace_hardirqs_on
-        REST_GPR(0,r1)
-        REST_4GPRS(3,r1)
-        REST_2GPRS(7,r1)
-        addi    r9,r1,STACK_FRAME_OVERHEAD
-        ld      r12,_MSR(r1)
-#endif /* CONFIG_TRACE_IRQFLAGS */
-        li      r10,1
-        stb     r10,PACASOFTIRQEN(r13)
-        stb     r10,PACAHARDIRQEN(r13)
-        std     r10,SOFTE(r1)
-#ifdef CONFIG_PPC_ISERIES
-BEGIN_FW_FTR_SECTION
-        /* Hack for handling interrupts when soft-enabling on iSeries */
-        cmpdi   cr1,r0,0x5555           /* syscall 0x5555 */
-        andi.   r10,r12,MSR_PR          /* from kernel */
-        crand   4*cr0+eq,4*cr1+eq,4*cr0+eq
-        bne     2f
-        b       hardware_interrupt_entry
-2:
-END_FW_FTR_SECTION_IFSET(FW_FEATURE_ISERIES)
-#endif /* CONFIG_PPC_ISERIES */
+        /*
+         * A syscall should always be called with interrupts enabled
+         * so we just unconditionally hard-enable here. When some kind
+         * of irq tracing is used, we additionally check that condition
+         * is correct
+         */
+#if defined(CONFIG_TRACE_IRQFLAGS) && defined(CONFIG_BUG)
+        lbz     r10,PACASOFTIRQEN(r13)
+        xori    r10,r10,1
+1:      tdnei   r10,0
+        EMIT_BUG_ENTRY 1b,__FILE__,__LINE__,BUGFLAG_WARNING
+#endif
 
-        /* Hard enable interrupts */
 #ifdef CONFIG_PPC_BOOK3E
         wrteei  1
 #else
-        mfmsr   r11
+        ld      r11,PACAKMSR(r13)
         ori     r11,r11,MSR_EE
         mtmsrd  r11,1
 #endif /* CONFIG_PPC_BOOK3E */
 
+        /* We do need to set SOFTE in the stack frame or the return
+         * from interrupt will be painful
+         */
+        li      r10,1
+        std     r10,SOFTE(r1)
+
 #ifdef SHOW_SYSCALLS
         bl      .do_show_syscall
         REST_GPR(0,r1)
@@ -198,16 +193,14 @@ syscall_exit:
         andi.   r10,r8,MSR_RI
         beq-    unrecov_restore
 #endif
-
-        /* Disable interrupts so current_thread_info()->flags can't change,
+        /*
+         * Disable interrupts so current_thread_info()->flags can't change,
          * and so that we don't get interrupted after loading SRR0/1.
          */
 #ifdef CONFIG_PPC_BOOK3E
         wrteei  0
 #else
-        mfmsr   r10
-        rldicl  r10,r10,48,1
-        rotldi  r10,r10,16
+        ld      r10,PACAKMSR(r13)
         mtmsrd  r10,1
 #endif /* CONFIG_PPC_BOOK3E */
 
@@ -319,7 +312,7 @@ syscall_exit_work:
 #ifdef CONFIG_PPC_BOOK3E
         wrteei  1
 #else
-        mfmsr   r10
+        ld      r10,PACAKMSR(r13)
         ori     r10,r10,MSR_EE
         mtmsrd  r10,1
 #endif /* CONFIG_PPC_BOOK3E */
@@ -565,10 +558,8 @@ _GLOBAL(ret_from_except_lite)
 #ifdef CONFIG_PPC_BOOK3E
         wrteei  0
 #else
-        mfmsr   r10             /* Get current interrupt state */
-        rldicl  r9,r10,48,1     /* clear MSR_EE */
-        rotldi  r9,r9,16
-        mtmsrd  r9,1            /* Update machine state */
+        ld      r10,PACAKMSR(r13) /* Get kernel MSR without EE */
+        mtmsrd  r10,1             /* Update machine state */
 #endif /* CONFIG_PPC_BOOK3E */
 
 #ifdef CONFIG_PREEMPT
@@ -591,25 +582,74 @@ _GLOBAL(ret_from_except_lite)
         ld      r4,TI_FLAGS(r9)
         andi.   r0,r4,_TIF_USER_WORK_MASK
         bne     do_work
-#endif
+#endif /* !CONFIG_PREEMPT */
 
+        .globl  fast_exc_return_irq
+fast_exc_return_irq:
 restore:
-BEGIN_FW_FTR_SECTION
+        /*
+         * This is the main kernel exit path, we first check if we
+         * have to change our interrupt state.
+         */
         ld      r5,SOFTE(r1)
-FW_FTR_SECTION_ELSE
-        b       .Liseries_check_pending_irqs
-ALT_FW_FTR_SECTION_END_IFCLR(FW_FEATURE_ISERIES)
-2:
-        TRACE_AND_RESTORE_IRQ(r5);
+        lbz     r6,PACASOFTIRQEN(r13)
+        cmpwi   cr1,r5,0
+        cmpw    cr0,r5,r6
+        beq     cr0,4f
+
+        /* We do, handle disable first, which is easy */
+        bne     cr1,3f;
+        li      r0,0
+        stb     r0,PACASOFTIRQEN(r13);
+        TRACE_DISABLE_INTS
+        b       4f
 
-        /* extract EE bit and use it to restore paca->hard_enabled */
-        ld      r3,_MSR(r1)
-        rldicl  r4,r3,49,63             /* r0 = (r3 >> 15) & 1 */
-        stb     r4,PACAHARDIRQEN(r13)
+3:      /*
+         * We are about to soft-enable interrupts (we are hard disabled
+         * at this point). We check if there's anything that needs to
+         * be replayed first.
+         */
+        lbz     r0,PACAIRQHAPPENED(r13)
+        cmpwi   cr0,r0,0
+        bne-    restore_check_irq_replay
 
+        /*
+         * Get here when nothing happened while soft-disabled, just
+         * soft-enable and move-on. We will hard-enable as a side
+         * effect of rfi
+         */
+restore_no_replay:
+        TRACE_ENABLE_INTS
+        li      r0,1
+        stb     r0,PACASOFTIRQEN(r13);
+
+        /*
+         * Final return path. BookE is handled in a different file
+         */
+4:
 #ifdef CONFIG_PPC_BOOK3E
         b       .exception_return_book3e
 #else
+        /*
+         * Clear the reservation. If we know the CPU tracks the address of
+         * the reservation then we can potentially save some cycles and use
+         * a larx. On POWER6 and POWER7 this is significantly faster.
+         */
+BEGIN_FTR_SECTION
+        stdcx.  r0,0,r1         /* to clear the reservation */
+FTR_SECTION_ELSE
+        ldarx   r4,0,r1
+ALT_FTR_SECTION_END_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS)
+
+        /*
+         * Some code path such as load_up_fpu or altivec return directly
+         * here. They run entirely hard disabled and do not alter the
+         * interrupt state. They also don't use lwarx/stwcx. and thus
+         * are known not to leave dangling reservations.
+         */
+        .globl  fast_exception_return
+fast_exception_return:
+        ld      r3,_MSR(r1)
         ld      r4,_CTR(r1)
         ld      r0,_LINK(r1)
         mtctr   r4
@@ -623,28 +663,18 @@ ALT_FW_FTR_SECTION_END_IFCLR(FW_FEATURE_ISERIES)
         beq-    unrecov_restore
 
         /*
-         * Clear the reservation. If we know the CPU tracks the address of
-         * the reservation then we can potentially save some cycles and use
-         * a larx. On POWER6 and POWER7 this is significantly faster.
-         */
-BEGIN_FTR_SECTION
-        stdcx.  r0,0,r1         /* to clear the reservation */
-FTR_SECTION_ELSE
-        ldarx   r4,0,r1
-ALT_FTR_SECTION_END_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS)
-
-        /*
          * Clear RI before restoring r13.  If we are returning to
          * userspace and we take an exception after restoring r13,
          * we end up corrupting the userspace r13 value.
          */
-        mfmsr   r4
-        andc    r4,r4,r0        /* r0 contains MSR_RI here */
+        ld      r4,PACAKMSR(r13) /* Get kernel MSR without EE */
+        andc    r4,r4,r0         /* r0 contains MSR_RI here */
         mtmsrd  r4,1
 
         /*
          * r13 is our per cpu area, only restore it if we are returning to
-         * userspace
+         * userspace the value stored in the stack frame may belong to
+         * another CPU.
          */
         andi.   r0,r3,MSR_PR
         beq     1f
@@ -669,30 +699,55 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS)
 
 #endif /* CONFIG_PPC_BOOK3E */
 
-.Liseries_check_pending_irqs:
-#ifdef CONFIG_PPC_ISERIES
-        ld      r5,SOFTE(r1)
-        cmpdi   0,r5,0
-        beq     2b
-        /* Check for pending interrupts (iSeries) */
-        ld      r3,PACALPPACAPTR(r13)
-        ld      r3,LPPACAANYINT(r3)
-        cmpdi   r3,0
-        beq+    2b                      /* skip do_IRQ if no interrupts */
-
-        li      r3,0
-        stb     r3,PACASOFTIRQEN(r13)   /* ensure we are soft-disabled */
-#ifdef CONFIG_TRACE_IRQFLAGS
-        bl      .trace_hardirqs_off
-        mfmsr   r10
-#endif
-        ori     r10,r10,MSR_EE
-        mtmsrd  r10                     /* hard-enable again */
-        addi    r3,r1,STACK_FRAME_OVERHEAD
-        bl      .do_IRQ
-        b       .ret_from_except_lite           /* loop back and handle more */
-#endif
+        /*
+         * Something did happen, check if a re-emit is needed
+         * (this also clears paca->irq_happened)
+         */
+restore_check_irq_replay:
+        /* XXX: We could implement a fast path here where we check
+         * for irq_happened being just 0x01, in which case we can
+         * clear it and return. That means that we would potentially
+         * miss a decrementer having wrapped all the way around.
+         *
+         * Still, this might be useful for things like hash_page
+         */
+        bl      .__check_irq_replay
+        cmpwi   cr0,r3,0
+        beq     restore_no_replay
+ 
+        /*
+         * We need to re-emit an interrupt. We do so by re-using our
+         * existing exception frame. We first change the trap value,
+         * but we need to ensure we preserve the low nibble of it
+         */
+        ld      r4,_TRAP(r1)
+        clrldi  r4,r4,60
+        or      r4,r4,r3
+        std     r4,_TRAP(r1)
 
+        /*
+         * Then find the right handler and call it. Interrupts are
+         * still soft-disabled and we keep them that way.
+        */
+        cmpwi   cr0,r3,0x500
+        bne     1f
+        addi    r3,r1,STACK_FRAME_OVERHEAD;
+        bl      .do_IRQ
+        b       .ret_from_except
+1:      cmpwi   cr0,r3,0x900
+        bne     1f
+        addi    r3,r1,STACK_FRAME_OVERHEAD;
+        bl      .timer_interrupt
+        b       .ret_from_except
+#ifdef CONFIG_PPC_BOOK3E
+1:      cmpwi   cr0,r3,0x280
+        bne     1f
+        addi    r3,r1,STACK_FRAME_OVERHEAD;
+        bl      .doorbell_exception
+        b       .ret_from_except
+#endif /* CONFIG_PPC_BOOK3E */
+1:      b       .ret_from_except /* What else to do here ? */
+ 
 do_work:
 #ifdef CONFIG_PREEMPT
         andi.   r0,r3,MSR_PR    /* Returning to user mode? */
@@ -705,31 +760,22 @@ do_work:
         crandc  eq,cr1*4+eq,eq
         bne     restore
 
-        /* Here we are preempting the current task.
-         *
-         * Ensure interrupts are soft-disabled. We also properly mark
-         * the PACA to reflect the fact that they are hard-disabled
-         * and trace the change
+        /*
+         * Here we are preempting the current task. We want to make
+         * sure we are soft-disabled first
          */
-        li      r0,0
-        stb     r0,PACASOFTIRQEN(r13)
-        stb     r0,PACAHARDIRQEN(r13)
-        TRACE_DISABLE_INTS
-
-        /* Call the scheduler with soft IRQs off */
+        SOFT_DISABLE_INTS(r3,r4)
 1:      bl      .preempt_schedule_irq
 
         /* Hard-disable interrupts again (and update PACA) */
 #ifdef CONFIG_PPC_BOOK3E
         wrteei  0
 #else
-        mfmsr   r10
-        rldicl  r10,r10,48,1
-        rotldi  r10,r10,16
+        ld      r10,PACAKMSR(r13) /* Get kernel MSR without EE */
         mtmsrd  r10,1
 #endif /* CONFIG_PPC_BOOK3E */
-        li      r0,0
-        stb     r0,PACAHARDIRQEN(r13)
+        li      r0,PACA_IRQ_HARD_DIS
+        stb     r0,PACAIRQHAPPENED(r13)
 
         /* Re-test flags and eventually loop */
         clrrdi  r9,r1,THREAD_SHIFT
@@ -751,12 +797,14 @@ user_work:
 
         andi.   r0,r4,_TIF_NEED_RESCHED
         beq     1f
+        bl      .restore_interrupts
         bl      .schedule
         b       .ret_from_except_lite
 
 1:      bl      .save_nvgprs
+        bl      .restore_interrupts
         addi    r3,r1,STACK_FRAME_OVERHEAD
-        bl      .do_signal
+        bl      .do_notify_resume
         b       .ret_from_except
 
 unrecov_restore:
diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S
index 429983c06f91..7215cc2495df 100644
--- a/arch/powerpc/kernel/exceptions-64e.S
+++ b/arch/powerpc/kernel/exceptions-64e.S
@@ -24,6 +24,7 @@
 #include <asm/ptrace.h>
 #include <asm/ppc-opcode.h>
 #include <asm/mmu.h>
+#include <asm/hw_irq.h>
 
 /* XXX This will ultimately add space for a special exception save
  *     structure used to save things like SRR0/SRR1, SPRGs, MAS, etc...
@@ -77,59 +78,55 @@
 #define SPRN_MC_SRR1    SPRN_MCSRR1
 
 #define NORMAL_EXCEPTION_PROLOG(n, addition)                                \
-        EXCEPTION_PROLOG(n, GEN, addition##_GEN)
+        EXCEPTION_PROLOG(n, GEN, addition##_GEN(n))
 
 #define CRIT_EXCEPTION_PROLOG(n, addition)                                  \
-        EXCEPTION_PROLOG(n, CRIT, addition##_CRIT)
+        EXCEPTION_PROLOG(n, CRIT, addition##_CRIT(n))
 
 #define DBG_EXCEPTION_PROLOG(n, addition)                                   \
-        EXCEPTION_PROLOG(n, DBG, addition##_DBG)
+        EXCEPTION_PROLOG(n, DBG, addition##_DBG(n))
 
 #define MC_EXCEPTION_PROLOG(n, addition)                                    \
-        EXCEPTION_PROLOG(n, MC, addition##_MC)
+        EXCEPTION_PROLOG(n, MC, addition##_MC(n))
 
 
 /* Variants of the "addition" argument for the prolog
  */
-#define PROLOG_ADDITION_NONE_GEN
-#define PROLOG_ADDITION_NONE_CRIT
-#define PROLOG_ADDITION_NONE_DBG
-#define PROLOG_ADDITION_NONE_MC
+#define PROLOG_ADDITION_NONE_GEN(n)
+#define PROLOG_ADDITION_NONE_CRIT(n)
+#define PROLOG_ADDITION_NONE_DBG(n)
+#define PROLOG_ADDITION_NONE_MC(n)
 
-#define PROLOG_ADDITION_MASKABLE_GEN                                        \
+#define PROLOG_ADDITION_MASKABLE_GEN(n)                                     \
         lbz     r11,PACASOFTIRQEN(r13); /* are irqs soft-disabled ? */      \
         cmpwi   cr0,r11,0;              /* yes -> go out of line */         \
-        beq     masked_interrupt_book3e;
+        beq     masked_interrupt_book3e_##n
 
-#define PROLOG_ADDITION_2REGS_GEN                                           \
+#define PROLOG_ADDITION_2REGS_GEN(n)                                        \
         std     r14,PACA_EXGEN+EX_R14(r13);                                 \
         std     r15,PACA_EXGEN+EX_R15(r13)
 
-#define PROLOG_ADDITION_1REG_GEN                                            \
+#define PROLOG_ADDITION_1REG_GEN(n)                                         \
         std     r14,PACA_EXGEN+EX_R14(r13);
 
-#define PROLOG_ADDITION_2REGS_CRIT                                          \
+#define PROLOG_ADDITION_2REGS_CRIT(n)                                       \
         std     r14,PACA_EXCRIT+EX_R14(r13);                                \
         std     r15,PACA_EXCRIT+EX_R15(r13)
 
-#define PROLOG_ADDITION_2REGS_DBG                                           \
+#define PROLOG_ADDITION_2REGS_DBG(n)                                        \
         std     r14,PACA_EXDBG+EX_R14(r13);                                 \
         std     r15,PACA_EXDBG+EX_R15(r13)
 
-#define PROLOG_ADDITION_2REGS_MC                                            \
+#define PROLOG_ADDITION_2REGS_MC(n)                                         \
         std     r14,PACA_EXMC+EX_R14(r13);                                  \
         std     r15,PACA_EXMC+EX_R15(r13)
 
-#define PROLOG_ADDITION_DOORBELL_GEN                                        \
-        lbz     r11,PACASOFTIRQEN(r13); /* are irqs soft-disabled ? */      \
-        cmpwi   cr0,r11,0;              /* yes -> go out of line */         \
-        beq     masked_doorbell_book3e
-
 
 /* Core exception code for all exceptions except TLB misses.
  * XXX: Needs to make SPRN_SPRG_GEN depend on exception type
  */
 #define EXCEPTION_COMMON(n, excf, ints)                                     \
+exc_##n##_common:                                                           \
         std     r0,GPR0(r1);            /* save r0 in stackframe */         \
         std     r2,GPR2(r1);            /* save r2 in stackframe */         \
         SAVE_4GPRS(3, r1);              /* save r3 - r6 in stackframe */    \
@@ -167,20 +164,21 @@
         std     r0,RESULT(r1);          /* clear regs->result */            \
         ints;
 
-/* Variants for the "ints" argument */
+/* Variants for the "ints" argument. This one does nothing when we want
+ * to keep interrupts in their original state
+ */
 #define INTS_KEEP
-#define INTS_DISABLE_SOFT                                                   \
-        stb     r0,PACASOFTIRQEN(r13);  /* mark interrupts soft-disabled */ \
-        TRACE_DISABLE_INTS;
-#define INTS_DISABLE_HARD                                                   \
-        stb     r0,PACAHARDIRQEN(r13); /* and hard disabled */
-#define INTS_DISABLE_ALL                                                    \
-        INTS_DISABLE_SOFT                                                   \
-        INTS_DISABLE_HARD
-
-/* This is called by exceptions that used INTS_KEEP (that is did not clear
- * neither soft nor hard IRQ indicators in the PACA. This will restore MSR:EE
- * to it's previous value
+
+/* This second version is meant for exceptions that don't immediately
+ * hard-enable. We set a bit in paca->irq_happened to ensure that
+ * a subsequent call to arch_local_irq_restore() will properly
+ * hard-enable and avoid the fast-path
+ */
+#define INTS_DISABLE    SOFT_DISABLE_INTS(r3,r4)
+
+/* This is called by exceptions that used INTS_KEEP (that did not touch
+ * irq indicators in the PACA). This will restore MSR:EE to it's previous
+ * value
  *
  * XXX In the long run, we may want to open-code it in order to separate the
  *     load from the wrtee, thus limiting the latency caused by the dependency
@@ -238,7 +236,7 @@ exc_##n##_bad_stack:							    \
 #define MASKABLE_EXCEPTION(trapnum, label, hdlr, ack)                   \
         START_EXCEPTION(label);                                         \
         NORMAL_EXCEPTION_PROLOG(trapnum, PROLOG_ADDITION_MASKABLE)      \
-        EXCEPTION_COMMON(trapnum, PACA_EXGEN, INTS_DISABLE_ALL)         \
+        EXCEPTION_COMMON(trapnum, PACA_EXGEN, INTS_DISABLE)             \
         ack(r8);                                                        \
         CHECK_NAPPING();                                                \
         addi    r3,r1,STACK_FRAME_OVERHEAD;                             \
@@ -289,7 +287,7 @@ interrupt_end_book3e:
 /* Critical Input Interrupt */
         START_EXCEPTION(critical_input);
         CRIT_EXCEPTION_PROLOG(0x100, PROLOG_ADDITION_NONE)
-//      EXCEPTION_COMMON(0x100, PACA_EXCRIT, INTS_DISABLE_ALL)
+//      EXCEPTION_COMMON(0x100, PACA_EXCRIT, INTS_DISABLE)
 //      bl      special_reg_save_crit
 //      CHECK_NAPPING();
 //      addi    r3,r1,STACK_FRAME_OVERHEAD
@@ -300,7 +298,7 @@ interrupt_end_book3e:
 /* Machine Check Interrupt */
         START_EXCEPTION(machine_check);
         CRIT_EXCEPTION_PROLOG(0x200, PROLOG_ADDITION_NONE)
-//      EXCEPTION_COMMON(0x200, PACA_EXMC, INTS_DISABLE_ALL)
+//      EXCEPTION_COMMON(0x200, PACA_EXMC, INTS_DISABLE)
 //      bl      special_reg_save_mc
 //      addi    r3,r1,STACK_FRAME_OVERHEAD
 //      CHECK_NAPPING();
@@ -313,7 +311,7 @@ interrupt_end_book3e:
         NORMAL_EXCEPTION_PROLOG(0x300, PROLOG_ADDITION_2REGS)
         mfspr   r14,SPRN_DEAR
         mfspr   r15,SPRN_ESR
-        EXCEPTION_COMMON(0x300, PACA_EXGEN, INTS_KEEP)
+        EXCEPTION_COMMON(0x300, PACA_EXGEN, INTS_DISABLE)
         b       storage_fault_common
 
 /* Instruction Storage Interrupt */
@@ -321,7 +319,7 @@ interrupt_end_book3e:
         NORMAL_EXCEPTION_PROLOG(0x400, PROLOG_ADDITION_2REGS)
         li      r15,0
         mr      r14,r10
-        EXCEPTION_COMMON(0x400, PACA_EXGEN, INTS_KEEP)
+        EXCEPTION_COMMON(0x400, PACA_EXGEN, INTS_DISABLE)
         b       storage_fault_common
 
 /* External Input Interrupt */
@@ -339,12 +337,11 @@ interrupt_end_book3e:
         START_EXCEPTION(program);
         NORMAL_EXCEPTION_PROLOG(0x700, PROLOG_ADDITION_1REG)
         mfspr   r14,SPRN_ESR
-        EXCEPTION_COMMON(0x700, PACA_EXGEN, INTS_DISABLE_SOFT)
+        EXCEPTION_COMMON(0x700, PACA_EXGEN, INTS_DISABLE)
         std     r14,_DSISR(r1)
         addi    r3,r1,STACK_FRAME_OVERHEAD
         ld      r14,PACA_EXGEN+EX_R14(r13)
         bl      .save_nvgprs
-        INTS_RESTORE_HARD
         bl      .program_check_exception
         b       .ret_from_except
 
@@ -353,15 +350,16 @@ interrupt_end_book3e:
         NORMAL_EXCEPTION_PROLOG(0x800, PROLOG_ADDITION_NONE)
         /* we can probably do a shorter exception entry for that one... */
         EXCEPTION_COMMON(0x800, PACA_EXGEN, INTS_KEEP)
-        bne     1f                      /* if from user, just load it up */
+        ld      r12,_MSR(r1)
+        andi.   r0,r12,MSR_PR;
+        beq-    1f
+        bl      .load_up_fpu
+        b       fast_exception_return
+1:      INTS_DISABLE
         bl      .save_nvgprs
         addi    r3,r1,STACK_FRAME_OVERHEAD
-        INTS_RESTORE_HARD
         bl      .kernel_fp_unavailable_exception
-        BUG_OPCODE
-1:      ld      r12,_MSR(r1)
-        bl      .load_up_fpu
-        b       fast_exception_return
+        b       .ret_from_except
 
 /* Decrementer Interrupt */
         MASKABLE_EXCEPTION(0x900, decrementer, .timer_interrupt, ACK_DEC)
@@ -372,7 +370,7 @@ interrupt_end_book3e:
 /* Watchdog Timer Interrupt */
         START_EXCEPTION(watchdog);
         CRIT_EXCEPTION_PROLOG(0x9f0, PROLOG_ADDITION_NONE)
-//      EXCEPTION_COMMON(0x9f0, PACA_EXCRIT, INTS_DISABLE_ALL)
+//      EXCEPTION_COMMON(0x9f0, PACA_EXCRIT, INTS_DISABLE)
 //      bl      special_reg_save_crit
 //      CHECK_NAPPING();
 //      addi    r3,r1,STACK_FRAME_OVERHEAD
@@ -391,10 +389,9 @@ interrupt_end_book3e:
 /* Auxiliary Processor Unavailable Interrupt */
         START_EXCEPTION(ap_unavailable);
         NORMAL_EXCEPTION_PROLOG(0xf20, PROLOG_ADDITION_NONE)
-        EXCEPTION_COMMON(0xf20, PACA_EXGEN, INTS_KEEP)
-        addi    r3,r1,STACK_FRAME_OVERHEAD
+        EXCEPTION_COMMON(0xf20, PACA_EXGEN, INTS_DISABLE)
         bl      .save_nvgprs
-        INTS_RESTORE_HARD
+        addi    r3,r1,STACK_FRAME_OVERHEAD
         bl      .unknown_exception
         b       .ret_from_except
 
@@ -450,7 +447,7 @@ interrupt_end_book3e:
         mfspr   r15,SPRN_SPRG_CRIT_SCRATCH
         mtspr   SPRN_SPRG_GEN_SCRATCH,r15
         mfspr   r14,SPRN_DBSR
-        EXCEPTION_COMMON(0xd00, PACA_EXCRIT, INTS_DISABLE_ALL)
+        EXCEPTION_COMMON(0xd00, PACA_EXCRIT, INTS_DISABLE)
         std     r14,_DSISR(r1)
         addi    r3,r1,STACK_FRAME_OVERHEAD
         mr      r4,r14
@@ -465,7 +462,7 @@ kernel_dbg_exc:
 
 /* Debug exception as a debug interrupt*/
         START_EXCEPTION(debug_debug);
-        DBG_EXCEPTION_PROLOG(0xd00, PROLOG_ADDITION_2REGS)
+        DBG_EXCEPTION_PROLOG(0xd08, PROLOG_ADDITION_2REGS)
 
         /*
          * If there is a single step or branch-taken exception in an
@@ -515,7 +512,7 @@ kernel_dbg_exc:
         mfspr   r15,SPRN_SPRG_DBG_SCRATCH
         mtspr   SPRN_SPRG_GEN_SCRATCH,r15
         mfspr   r14,SPRN_DBSR
-        EXCEPTION_COMMON(0xd00, PACA_EXDBG, INTS_DISABLE_ALL)
+        EXCEPTION_COMMON(0xd08, PACA_EXDBG, INTS_DISABLE)
         std     r14,_DSISR(r1)
         addi    r3,r1,STACK_FRAME_OVERHEAD
         mr      r4,r14
@@ -525,21 +522,20 @@ kernel_dbg_exc:
         bl      .DebugException
         b       .ret_from_except
 
-        MASKABLE_EXCEPTION(0x260, perfmon, .performance_monitor_exception, ACK_NONE)
-
-/* Doorbell interrupt */
-        START_EXCEPTION(doorbell)
-        NORMAL_EXCEPTION_PROLOG(0x2070, PROLOG_ADDITION_DOORBELL)
-        EXCEPTION_COMMON(0x2070, PACA_EXGEN, INTS_DISABLE_ALL)
-        CHECK_NAPPING()
+        START_EXCEPTION(perfmon);
+        NORMAL_EXCEPTION_PROLOG(0x260, PROLOG_ADDITION_NONE)
+        EXCEPTION_COMMON(0x260, PACA_EXGEN, INTS_DISABLE)
         addi    r3,r1,STACK_FRAME_OVERHEAD
-        bl      .doorbell_exception
+        bl      .performance_monitor_exception
         b       .ret_from_except_lite
 
+/* Doorbell interrupt */
+        MASKABLE_EXCEPTION(0x280, doorbell, .doorbell_exception, ACK_NONE)
+
 /* Doorbell critical Interrupt */
         START_EXCEPTION(doorbell_crit);
-        CRIT_EXCEPTION_PROLOG(0x2080, PROLOG_ADDITION_NONE)
-//      EXCEPTION_COMMON(0x2080, PACA_EXCRIT, INTS_DISABLE_ALL)
+        CRIT_EXCEPTION_PROLOG(0x2a0, PROLOG_ADDITION_NONE)
+//      EXCEPTION_COMMON(0x2a0, PACA_EXCRIT, INTS_DISABLE)
 //      bl      special_reg_save_crit
 //      CHECK_NAPPING();
 //      addi    r3,r1,STACK_FRAME_OVERHEAD
@@ -547,36 +543,114 @@ kernel_dbg_exc:
 //      b       ret_from_crit_except
         b       .
 
+/* Guest Doorbell */
         MASKABLE_EXCEPTION(0x2c0, guest_doorbell, .unknown_exception, ACK_NONE)
-        MASKABLE_EXCEPTION(0x2e0, guest_doorbell_crit, .unknown_exception, ACK_NONE)
-        MASKABLE_EXCEPTION(0x310, hypercall, .unknown_exception, ACK_NONE)
-        MASKABLE_EXCEPTION(0x320, ehpriv, .unknown_exception, ACK_NONE)
 
+/* Guest Doorbell critical Interrupt */
+        START_EXCEPTION(guest_doorbell_crit);
+        CRIT_EXCEPTION_PROLOG(0x2e0, PROLOG_ADDITION_NONE)
+//      EXCEPTION_COMMON(0x2e0, PACA_EXCRIT, INTS_DISABLE)
+//      bl      special_reg_save_crit
+//      CHECK_NAPPING();
+//      addi    r3,r1,STACK_FRAME_OVERHEAD
+//      bl      .guest_doorbell_critical_exception
+//      b       ret_from_crit_except
+        b       .
+
+/* Hypervisor call */
+        START_EXCEPTION(hypercall);
+        NORMAL_EXCEPTION_PROLOG(0x310, PROLOG_ADDITION_NONE)
+        EXCEPTION_COMMON(0x310, PACA_EXGEN, INTS_KEEP)
+        addi    r3,r1,STACK_FRAME_OVERHEAD
+        bl      .save_nvgprs
+        INTS_RESTORE_HARD
+        bl      .unknown_exception
+        b       .ret_from_except
+
+/* Embedded Hypervisor priviledged  */
+        START_EXCEPTION(ehpriv);
+        NORMAL_EXCEPTION_PROLOG(0x320, PROLOG_ADDITION_NONE)
+        EXCEPTION_COMMON(0x320, PACA_EXGEN, INTS_KEEP)
+        addi    r3,r1,STACK_FRAME_OVERHEAD
+        bl      .save_nvgprs
+        INTS_RESTORE_HARD
+        bl      .unknown_exception
+        b       .ret_from_except
 
 /*
- * An interrupt came in while soft-disabled; clear EE in SRR1,
- * clear paca->hard_enabled and return.
+ * An interrupt came in while soft-disabled; We mark paca->irq_happened
+ * accordingly and if the interrupt is level sensitive, we hard disable
  */
-masked_doorbell_book3e:
-        mtcr    r10
-        /* Resend the doorbell to fire again when ints enabled */
-        mfspr   r10,SPRN_PIR
-        PPC_MSGSND(r10)
-        b       masked_interrupt_book3e_common
 
-masked_interrupt_book3e:
+masked_interrupt_book3e_0x500:
+        /* XXX When adding support for EPR, use PACA_IRQ_EE_EDGE */
+        li      r11,PACA_IRQ_EE
+        b       masked_interrupt_book3e_full_mask
+
+masked_interrupt_book3e_0x900:
+        ACK_DEC(r11);
+        li      r11,PACA_IRQ_DEC
+        b       masked_interrupt_book3e_no_mask
+masked_interrupt_book3e_0x980:
+        ACK_FIT(r11);
+        li      r11,PACA_IRQ_DEC
+        b       masked_interrupt_book3e_no_mask
+masked_interrupt_book3e_0x280:
+masked_interrupt_book3e_0x2c0:
+        li      r11,PACA_IRQ_DBELL
+        b       masked_interrupt_book3e_no_mask
+
+masked_interrupt_book3e_no_mask:
+        mtcr    r10
+        lbz     r10,PACAIRQHAPPENED(r13)
+        or      r10,r10,r11
+        stb     r10,PACAIRQHAPPENED(r13)
+        b       1f
+masked_interrupt_book3e_full_mask:
         mtcr    r10
-masked_interrupt_book3e_common:
-        stb     r11,PACAHARDIRQEN(r13)
+        lbz     r10,PACAIRQHAPPENED(r13)
+        or      r10,r10,r11
+        stb     r10,PACAIRQHAPPENED(r13)
         mfspr   r10,SPRN_SRR1
         rldicl  r11,r10,48,1            /* clear MSR_EE */
         rotldi  r10,r11,16
         mtspr   SPRN_SRR1,r10
-        ld      r10,PACA_EXGEN+EX_R10(r13);     /* restore registers */
+1:      ld      r10,PACA_EXGEN+EX_R10(r13);
         ld      r11,PACA_EXGEN+EX_R11(r13);
         mfspr   r13,SPRN_SPRG_GEN_SCRATCH;
         rfi
         b       .
+/*
+ * Called from arch_local_irq_enable when an interrupt needs
+ * to be resent. r3 contains either 0x500,0x900,0x260 or 0x280
+ * to indicate the kind of interrupt. MSR:EE is already off.
+ * We generate a stackframe like if a real interrupt had happened.
+ *
+ * Note: While MSR:EE is off, we need to make sure that _MSR
+ * in the generated frame has EE set to 1 or the exception
+ * handler will not properly re-enable them.
+ */
+_GLOBAL(__replay_interrupt)
+        /* We are going to jump to the exception common code which
+         * will retrieve various register values from the PACA which
+         * we don't give a damn about.
+         */
+        mflr    r10
+        mfmsr   r11
+        mfcr    r4
+        mtspr   SPRN_SPRG_GEN_SCRATCH,r13;
+        std     r1,PACA_EXGEN+EX_R1(r13);
+        stw     r4,PACA_EXGEN+EX_CR(r13);
+        ori     r11,r11,MSR_EE
+        subi    r1,r1,INT_FRAME_SIZE;
+        cmpwi   cr0,r3,0x500
+        beq     exc_0x500_common
+        cmpwi   cr0,r3,0x900
+        beq     exc_0x900_common
+        cmpwi   cr0,r3,0x280
+        beq     exc_0x280_common
+        blr
+
 
 /*
  * This is called from 0x300 and 0x400 handlers after the prologs with
@@ -591,7 +665,6 @@ storage_fault_common:
         mr      r5,r15
         ld      r14,PACA_EXGEN+EX_R14(r13)
         ld      r15,PACA_EXGEN+EX_R15(r13)
-        INTS_RESTORE_HARD
         bl      .do_page_fault
         cmpdi   r3,0
         bne-    1f
@@ -680,6 +753,8 @@ BAD_STACK_TRAMPOLINE(0x000)
 BAD_STACK_TRAMPOLINE(0x100)
 BAD_STACK_TRAMPOLINE(0x200)
 BAD_STACK_TRAMPOLINE(0x260)
+BAD_STACK_TRAMPOLINE(0x280)
+BAD_STACK_TRAMPOLINE(0x2a0)
 BAD_STACK_TRAMPOLINE(0x2c0)
 BAD_STACK_TRAMPOLINE(0x2e0)
 BAD_STACK_TRAMPOLINE(0x300)
@@ -697,11 +772,10 @@ BAD_STACK_TRAMPOLINE(0xa00)
 BAD_STACK_TRAMPOLINE(0xb00)
 BAD_STACK_TRAMPOLINE(0xc00)
 BAD_STACK_TRAMPOLINE(0xd00)
+BAD_STACK_TRAMPOLINE(0xd08)
 BAD_STACK_TRAMPOLINE(0xe00)
 BAD_STACK_TRAMPOLINE(0xf00)
 BAD_STACK_TRAMPOLINE(0xf20)
-BAD_STACK_TRAMPOLINE(0x2070)
-BAD_STACK_TRAMPOLINE(0x2080)
 
         .globl  bad_stack_book3e
 bad_stack_book3e:
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index d4be7bb3dbdf..cb705fdbb458 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -12,6 +12,7 @@
  *
  */
 
+#include <asm/hw_irq.h>
 #include <asm/exception-64s.h>
 #include <asm/ptrace.h>
 
@@ -19,7 +20,7 @@
  * We layout physical memory as follows:
  * 0x0000 - 0x00ff : Secondary processor spin code
  * 0x0100 - 0x2fff : pSeries Interrupt prologs
- * 0x3000 - 0x5fff : interrupt support, iSeries and common interrupt prologs
+ * 0x3000 - 0x5fff : interrupt support common interrupt prologs
  * 0x6000 - 0x6fff : Initial (CPU0) segment table
  * 0x7000 - 0x7fff : FWNMI data area
  * 0x8000 -        : Early init and support code
@@ -100,14 +101,14 @@ data_access_not_stab:
 END_MMU_FTR_SECTION_IFCLR(MMU_FTR_SLB)
 #endif
         EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, data_access_common, EXC_STD,
-                                 KVMTEST_PR, 0x300)
+                                 KVMTEST, 0x300)
 
         . = 0x380
         .globl data_access_slb_pSeries
 data_access_slb_pSeries:
         HMT_MEDIUM
         SET_SCRATCH0(r13)
-        EXCEPTION_PROLOG_1(PACA_EXSLB, KVMTEST_PR, 0x380)
+        EXCEPTION_PROLOG_1(PACA_EXSLB, KVMTEST, 0x380)
         std     r3,PACA_EXSLB+EX_R3(r13)
         mfspr   r3,SPRN_DAR
 #ifdef __DISABLED__
@@ -329,8 +330,8 @@ do_stab_bolted_pSeries:
         EXCEPTION_PROLOG_PSERIES_1(.do_stab_bolted, EXC_STD)
 #endif /* CONFIG_POWER4_ONLY */
 
-        KVM_HANDLER_PR_SKIP(PACA_EXGEN, EXC_STD, 0x300)
-        KVM_HANDLER_PR_SKIP(PACA_EXSLB, EXC_STD, 0x380)
+        KVM_HANDLER_SKIP(PACA_EXGEN, EXC_STD, 0x300)
+        KVM_HANDLER_SKIP(PACA_EXSLB, EXC_STD, 0x380)
         KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0x400)
         KVM_HANDLER_PR(PACA_EXSLB, EXC_STD, 0x480)
         KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0x900)
@@ -356,34 +357,60 @@ do_stab_bolted_pSeries:
         KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0xf40)
 
 /*
- * An interrupt came in while soft-disabled; clear EE in SRR1,
- * clear paca->hard_enabled and return.
+ * An interrupt came in while soft-disabled. We set paca->irq_happened,
+ * then, if it was a decrementer interrupt, we bump the dec to max and
+ * and return, else we hard disable and return. This is called with
+ * r10 containing the value to OR to the paca field.
  */
-masked_interrupt:
-        stb     r10,PACAHARDIRQEN(r13)
-        mtcrf   0x80,r9
-        ld      r9,PACA_EXGEN+EX_R9(r13)
-        mfspr   r10,SPRN_SRR1
-        rldicl  r10,r10,48,1            /* clear MSR_EE */
-        rotldi  r10,r10,16
-        mtspr   SPRN_SRR1,r10
-        ld      r10,PACA_EXGEN+EX_R10(r13)
-        GET_SCRATCH0(r13)
-        rfid
+#define MASKED_INTERRUPT(_H)                            \
+masked_##_H##interrupt:                                 \
+        std     r11,PACA_EXGEN+EX_R11(r13);             \
+        lbz     r11,PACAIRQHAPPENED(r13);               \
+        or      r11,r11,r10;                            \
+        stb     r11,PACAIRQHAPPENED(r13);               \
+        andi.   r10,r10,PACA_IRQ_DEC;                   \
+        beq     1f;                                     \
+        lis     r10,0x7fff;                             \
+        ori     r10,r10,0xffff;                         \
+        mtspr   SPRN_DEC,r10;                           \
+        b       2f;                                     \
+1:      mfspr   r10,SPRN_##_H##SRR1;                    \
+        rldicl  r10,r10,48,1; /* clear MSR_EE */        \
+        rotldi  r10,r10,16;                             \
+        mtspr   SPRN_##_H##SRR1,r10;                    \
+2:      mtcrf   0x80,r9;                                \
+        ld      r9,PACA_EXGEN+EX_R9(r13);               \
+        ld      r10,PACA_EXGEN+EX_R10(r13);             \
+        ld      r11,PACA_EXGEN+EX_R11(r13);             \
+        GET_SCRATCH0(r13);                              \
+        ##_H##rfid;                                     \
         b       .
+        
+        MASKED_INTERRUPT()
+        MASKED_INTERRUPT(H)
 
-masked_Hinterrupt:
-        stb     r10,PACAHARDIRQEN(r13)
-        mtcrf   0x80,r9
-        ld      r9,PACA_EXGEN+EX_R9(r13)
-        mfspr   r10,SPRN_HSRR1
-        rldicl  r10,r10,48,1            /* clear MSR_EE */
-        rotldi  r10,r10,16
-        mtspr   SPRN_HSRR1,r10
-        ld      r10,PACA_EXGEN+EX_R10(r13)
-        GET_SCRATCH0(r13)
-        hrfid
-        b       .
+/*
+ * Called from arch_local_irq_enable when an interrupt needs
+ * to be resent. r3 contains 0x500 or 0x900 to indicate which
+ * kind of interrupt. MSR:EE is already off. We generate a
+ * stackframe like if a real interrupt had happened.
+ *
+ * Note: While MSR:EE is off, we need to make sure that _MSR
+ * in the generated frame has EE set to 1 or the exception
+ * handler will not properly re-enable them.
+ */
+_GLOBAL(__replay_interrupt)
+        /* We are going to jump to the exception common code which
+         * will retrieve various register values from the PACA which
+         * we don't give a damn about, so we don't bother storing them.
+         */
+        mfmsr   r12
+        mflr    r11
+        mfcr    r9
+        ori     r12,r12,MSR_EE
+        andi.   r3,r3,0x0800
+        bne     decrementer_common
+        b       hardware_interrupt_common
 
 #ifdef CONFIG_PPC_PSERIES
 /*
@@ -458,14 +485,15 @@ machine_check_common:
         bl      .machine_check_exception
         b       .ret_from_except
 
-        STD_EXCEPTION_COMMON_LITE(0x900, decrementer, .timer_interrupt)
+        STD_EXCEPTION_COMMON_ASYNC(0x500, hardware_interrupt, do_IRQ)
+        STD_EXCEPTION_COMMON_ASYNC(0x900, decrementer, .timer_interrupt)
         STD_EXCEPTION_COMMON(0xa00, trap_0a, .unknown_exception)
         STD_EXCEPTION_COMMON(0xb00, trap_0b, .unknown_exception)
         STD_EXCEPTION_COMMON(0xd00, single_step, .single_step_exception)
         STD_EXCEPTION_COMMON(0xe00, trap_0e, .unknown_exception)
         STD_EXCEPTION_COMMON(0xe40, emulation_assist, .program_check_exception)
         STD_EXCEPTION_COMMON(0xe60, hmi_exception, .unknown_exception)
-        STD_EXCEPTION_COMMON_IDLE(0xf00, performance_monitor, .performance_monitor_exception)
+        STD_EXCEPTION_COMMON_ASYNC(0xf00, performance_monitor, .performance_monitor_exception)
         STD_EXCEPTION_COMMON(0x1300, instruction_breakpoint, .instruction_breakpoint_exception)
 #ifdef CONFIG_ALTIVEC
         STD_EXCEPTION_COMMON(0x1700, altivec_assist, .altivec_assist_exception)
@@ -482,6 +510,9 @@ machine_check_common:
 system_call_entry:
         b       system_call_common
 
+ppc64_runlatch_on_trampoline:
+        b       .__ppc64_runlatch_on
+
 /*
  * Here we have detected that the kernel stack pointer is bad.
  * R9 contains the saved CR, r13 points to the paca,
@@ -555,6 +586,8 @@ data_access_common:
         mfspr   r10,SPRN_DSISR
         stw     r10,PACA_EXGEN+EX_DSISR(r13)
         EXCEPTION_PROLOG_COMMON(0x300, PACA_EXGEN)
+        DISABLE_INTS
+        ld      r12,_MSR(r1)
         ld      r3,PACA_EXGEN+EX_DAR(r13)
         lwz     r4,PACA_EXGEN+EX_DSISR(r13)
         li      r5,0x300
@@ -569,6 +602,7 @@ h_data_storage_common:
         stw     r10,PACA_EXGEN+EX_DSISR(r13)
         EXCEPTION_PROLOG_COMMON(0xe00, PACA_EXGEN)
         bl      .save_nvgprs
+        DISABLE_INTS
         addi    r3,r1,STACK_FRAME_OVERHEAD
         bl      .unknown_exception
         b       .ret_from_except
@@ -577,6 +611,8 @@ h_data_storage_common:
         .globl instruction_access_common
 instruction_access_common:
         EXCEPTION_PROLOG_COMMON(0x400, PACA_EXGEN)
+        DISABLE_INTS
+        ld      r12,_MSR(r1)
         ld      r3,_NIP(r1)
         andis.  r4,r12,0x5820
         li      r5,0x400
@@ -672,12 +708,6 @@ _GLOBAL(slb_miss_realmode)
         ld      r10,PACA_EXSLB+EX_LR(r13)
         ld      r3,PACA_EXSLB+EX_R3(r13)
         lwz     r9,PACA_EXSLB+EX_CCR(r13)       /* get saved CR */
-#ifdef CONFIG_PPC_ISERIES
-BEGIN_FW_FTR_SECTION
-        ld      r11,PACALPPACAPTR(r13)
-        ld      r11,LPPACASRR0(r11)             /* get SRR0 value */
-END_FW_FTR_SECTION_IFSET(FW_FEATURE_ISERIES)
-#endif /* CONFIG_PPC_ISERIES */
 
         mtlr    r10
 
@@ -690,12 +720,6 @@ END_FW_FTR_SECTION_IFSET(FW_FEATURE_ISERIES)
         mtcrf   0x01,r9         /* slb_allocate uses cr0 and cr7 */
 .machine        pop
 
-#ifdef CONFIG_PPC_ISERIES
-BEGIN_FW_FTR_SECTION
-        mtspr   SPRN_SRR0,r11
-        mtspr   SPRN_SRR1,r12
-END_FW_FTR_SECTION_IFSET(FW_FEATURE_ISERIES)
-#endif /* CONFIG_PPC_ISERIES */
         ld      r9,PACA_EXSLB+EX_R9(r13)
         ld      r10,PACA_EXSLB+EX_R10(r13)
         ld      r11,PACA_EXSLB+EX_R11(r13)
@@ -704,13 +728,7 @@ END_FW_FTR_SECTION_IFSET(FW_FEATURE_ISERIES)
         rfid
         b       .       /* prevent speculative execution */
 
-2:
-#ifdef CONFIG_PPC_ISERIES
-BEGIN_FW_FTR_SECTION
-        b       unrecov_slb
-END_FW_FTR_SECTION_IFSET(FW_FEATURE_ISERIES)
-#endif /* CONFIG_PPC_ISERIES */
-        mfspr   r11,SPRN_SRR0
+2:      mfspr   r11,SPRN_SRR0
         ld      r10,PACAKBASE(r13)
         LOAD_HANDLER(r10,unrecov_slb)
         mtspr   SPRN_SRR0,r10
@@ -727,20 +745,6 @@ unrecov_slb:
         bl      .unrecoverable_exception
         b       1b
 
-        .align  7
-        .globl hardware_interrupt_common
-        .globl hardware_interrupt_entry
-hardware_interrupt_common:
-        EXCEPTION_PROLOG_COMMON(0x500, PACA_EXGEN)
-        FINISH_NAP
-hardware_interrupt_entry:
-        DISABLE_INTS
-BEGIN_FTR_SECTION
-        bl      .ppc64_runlatch_on
-END_FTR_SECTION_IFSET(CPU_FTR_CTRL)
-        addi    r3,r1,STACK_FRAME_OVERHEAD
-        bl      .do_IRQ
-        b       .ret_from_except_lite
 
 #ifdef CONFIG_PPC_970_NAP
 power4_fixup_nap:
@@ -774,8 +778,8 @@ alignment_common:
 program_check_common:
         EXCEPTION_PROLOG_COMMON(0x700, PACA_EXGEN)
         bl      .save_nvgprs
+        DISABLE_INTS
         addi    r3,r1,STACK_FRAME_OVERHEAD
-        ENABLE_INTS
         bl      .program_check_exception
         b       .ret_from_except
 
@@ -785,8 +789,8 @@ fp_unavailable_common:
         EXCEPTION_PROLOG_COMMON(0x800, PACA_EXGEN)
         bne     1f                      /* if from user, just load it up */
         bl      .save_nvgprs
+        DISABLE_INTS
         addi    r3,r1,STACK_FRAME_OVERHEAD
-        ENABLE_INTS
         bl      .kernel_fp_unavailable_exception
         BUG_OPCODE
 1:      bl      .load_up_fpu
@@ -805,8 +809,8 @@ BEGIN_FTR_SECTION
 END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
 #endif
         bl      .save_nvgprs
+        DISABLE_INTS
         addi    r3,r1,STACK_FRAME_OVERHEAD
-        ENABLE_INTS
         bl      .altivec_unavailable_exception
         b       .ret_from_except
 
@@ -816,13 +820,14 @@ vsx_unavailable_common:
         EXCEPTION_PROLOG_COMMON(0xf40, PACA_EXGEN)
 #ifdef CONFIG_VSX
 BEGIN_FTR_SECTION
-        bne     .load_up_vsx
+        beq     1f
+        b       .load_up_vsx
 1:
 END_FTR_SECTION_IFSET(CPU_FTR_VSX)
 #endif
         bl      .save_nvgprs
+        DISABLE_INTS
         addi    r3,r1,STACK_FRAME_OVERHEAD
-        ENABLE_INTS
         bl      .vsx_unavailable_exception
         b       .ret_from_except
 
@@ -831,66 +836,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX)
 __end_handlers:
 
 /*
- * Return from an exception with minimal checks.
- * The caller is assumed to have done EXCEPTION_PROLOG_COMMON.
- * If interrupts have been enabled, or anything has been
- * done that might have changed the scheduling status of
- * any task or sent any task a signal, you should use
- * ret_from_except or ret_from_except_lite instead of this.
- */
-fast_exc_return_irq:                    /* restores irq state too */
-        ld      r3,SOFTE(r1)
-        TRACE_AND_RESTORE_IRQ(r3);
-        ld      r12,_MSR(r1)
-        rldicl  r4,r12,49,63            /* get MSR_EE to LSB */
-        stb     r4,PACAHARDIRQEN(r13)   /* restore paca->hard_enabled */
-        b       1f
-
-        .globl  fast_exception_return
-fast_exception_return:
-        ld      r12,_MSR(r1)
-1:      ld      r11,_NIP(r1)
-        andi.   r3,r12,MSR_RI           /* check if RI is set */
-        beq-    unrecov_fer
-
-#ifdef CONFIG_VIRT_CPU_ACCOUNTING
-        andi.   r3,r12,MSR_PR
-        beq     2f
-        ACCOUNT_CPU_USER_EXIT(r3, r4)
-2:
-#endif
-
-        ld      r3,_CCR(r1)
-        ld      r4,_LINK(r1)
-        ld      r5,_CTR(r1)
-        ld      r6,_XER(r1)
-        mtcr    r3
-        mtlr    r4
-        mtctr   r5
-        mtxer   r6
-        REST_GPR(0, r1)
-        REST_8GPRS(2, r1)
-
-        mfmsr   r10
-        rldicl  r10,r10,48,1            /* clear EE */
-        rldicr  r10,r10,16,61           /* clear RI (LE is 0 already) */
-        mtmsrd  r10,1
-
-        mtspr   SPRN_SRR1,r12
-        mtspr   SPRN_SRR0,r11
-        REST_4GPRS(10, r1)
-        ld      r1,GPR1(r1)
-        rfid
-        b       .       /* prevent speculative execution */
-
-unrecov_fer:
-        bl      .save_nvgprs
-1:      addi    r3,r1,STACK_FRAME_OVERHEAD
-        bl      .unrecoverable_exception
-        b       1b
-
-
-/*
  * Hash table stuff
  */
         .align  7
@@ -912,28 +857,6 @@ END_MMU_FTR_SECTION_IFCLR(MMU_FTR_SLB)
         lwz     r0,TI_PREEMPT(r11)      /* If we're in an "NMI" */
         andis.  r0,r0,NMI_MASK@h        /* (i.e. an irq when soft-disabled) */
         bne     77f                     /* then don't call hash_page now */
-
-        /*
-         * On iSeries, we soft-disable interrupts here, then
-         * hard-enable interrupts so that the hash_page code can spin on
-         * the hash_table_lock without problems on a shared processor.
-         */
-        DISABLE_INTS
-
-        /*
-         * Currently, trace_hardirqs_off() will be called by DISABLE_INTS
-         * and will clobber volatile registers when irq tracing is enabled
-         * so we need to reload them. It may be possible to be smarter here
-         * and move the irq tracing elsewhere but let's keep it simple for
-         * now
-         */
-#ifdef CONFIG_TRACE_IRQFLAGS
-        ld      r3,_DAR(r1)
-        ld      r4,_DSISR(r1)
-        ld      r5,_TRAP(r1)
-        ld      r12,_MSR(r1)
-        clrrdi  r5,r5,4
-#endif /* CONFIG_TRACE_IRQFLAGS */
         /*
          * We need to set the _PAGE_USER bit if MSR_PR is set or if we are
          * accessing a userspace segment (even from the kernel). We assume
@@ -951,62 +874,25 @@ END_MMU_FTR_SECTION_IFCLR(MMU_FTR_SLB)
          * r4 contains the required access permissions
          * r5 contains the trap number
          *
-         * at return r3 = 0 for success
+         * at return r3 = 0 for success, 1 for page fault, negative for error
          */
         bl      .hash_page              /* build HPTE if possible */
         cmpdi   r3,0                    /* see if hash_page succeeded */
 
-BEGIN_FW_FTR_SECTION
-        /*
-         * If we had interrupts soft-enabled at the point where the
-         * DSI/ISI occurred, and an interrupt came in during hash_page,
-         * handle it now.
-         * We jump to ret_from_except_lite rather than fast_exception_return
-         * because ret_from_except_lite will check for and handle pending
-         * interrupts if necessary.
-         */
-        beq     13f
-END_FW_FTR_SECTION_IFSET(FW_FEATURE_ISERIES)
-
-BEGIN_FW_FTR_SECTION
-        /*
-         * Here we have interrupts hard-disabled, so it is sufficient
-         * to restore paca->{soft,hard}_enable and get out.
-         */
+        /* Success */
         beq     fast_exc_return_irq     /* Return from exception on success */
-END_FW_FTR_SECTION_IFCLR(FW_FEATURE_ISERIES)
 
-        /* For a hash failure, we don't bother re-enabling interrupts */
-        ble-    12f
-
-        /*
-         * hash_page couldn't handle it, set soft interrupt enable back
-         * to what it was before the trap.  Note that .arch_local_irq_restore
-         * handles any interrupts pending at this point.
-         */
-        ld      r3,SOFTE(r1)
-        TRACE_AND_RESTORE_IRQ_PARTIAL(r3, 11f)
-        bl      .arch_local_irq_restore
-        b       11f
-
-/* We have a data breakpoint exception - handle it */
-handle_dabr_fault:
-        bl      .save_nvgprs
-        ld      r4,_DAR(r1)
-        ld      r5,_DSISR(r1)
-        addi    r3,r1,STACK_FRAME_OVERHEAD
-        bl      .do_dabr
-        b       .ret_from_except_lite
+        /* Error */
+        blt-    13f
 
 /* Here we have a page fault that hash_page can't handle. */
 handle_page_fault:
-        ENABLE_INTS
 11:     ld      r4,_DAR(r1)
         ld      r5,_DSISR(r1)
         addi    r3,r1,STACK_FRAME_OVERHEAD
         bl      .do_page_fault
         cmpdi   r3,0
-        beq+    13f
+        beq+    12f
         bl      .save_nvgprs
         mr      r5,r3
         addi    r3,r1,STACK_FRAME_OVERHEAD
@@ -1014,12 +900,20 @@ handle_page_fault:
         bl      .bad_page_fault
         b       .ret_from_except
 
-13:     b       .ret_from_except_lite
+/* We have a data breakpoint exception - handle it */
+handle_dabr_fault:
+        bl      .save_nvgprs
+        ld      r4,_DAR(r1)
+        ld      r5,_DSISR(r1)
+        addi    r3,r1,STACK_FRAME_OVERHEAD
+        bl      .do_dabr
+12:     b       .ret_from_except_lite
+
 
 /* We have a page fault that hash_page could handle but HV refused
  * the PTE insertion
  */
-12:     bl      .save_nvgprs
+13:     bl      .save_nvgprs
         mr      r5,r3
         addi    r3,r1,STACK_FRAME_OVERHEAD
         ld      r4,_DAR(r1)
@@ -1141,51 +1035,19 @@ _GLOBAL(do_stab_bolted)
         .= 0x7000
         .globl fwnmi_data_area
 fwnmi_data_area:
-#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
-         * both pSeries and iSeries */
-#ifdef CONFIG_PPC_ISERIES
-        . = LPARMAP_PHYS
-        .globl xLparMap
-xLparMap:
-        .quad   HvEsidsToMap            /* xNumberEsids */
-        .quad   HvRangesToMap           /* xNumberRanges */
-        .quad   STAB0_PAGE              /* xSegmentTableOffs */
-        .zero   40                      /* xRsvd */
-        /* xEsids (HvEsidsToMap entries of 2 quads) */
-        .quad   PAGE_OFFSET_ESID        /* xKernelEsid */
-        .quad   PAGE_OFFSET_VSID        /* xKernelVsid */
-        .quad   VMALLOC_START_ESID      /* xKernelEsid */
-        .quad   VMALLOC_START_VSID      /* xKernelVsid */
-        /* xRanges (HvRangesToMap entries of 3 quads) */
-        .quad   HvPagesToMap            /* xPages */
-        .quad   0                       /* xOffset */
-        .quad   PAGE_OFFSET_VSID << (SID_SHIFT - HW_PAGE_SHIFT) /* xVPN */
-
-#endif /* CONFIG_PPC_ISERIES */
-
-#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 /* defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV) */
 
-/*
- * Space for CPU0's segment table.
- *
- * On iSeries, the hypervisor must fill in at least one entry before
- * we get control (with relocate on).  The address is given to the hv
- * as a page number (see xLparMap above), so this must be at a
- * fixed address (the linker can't compute (u64)&initial_stab >>
- * PAGE_SHIFT).
- */
-        . = STAB0_OFFSET        /* 0x8000 */
+/* Space for CPU0's segment table */
+        .balign 4096
         .globl initial_stab
 initial_stab:
         .space  4096
+
 #ifdef CONFIG_PPC_POWERNV
 _GLOBAL(opal_mc_secondary_handler)
         HMT_MEDIUM
diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c
new file mode 100644
index 000000000000..cfe7a38708c3
--- /dev/null
+++ b/arch/powerpc/kernel/fadump.c
@@ -0,0 +1,1315 @@
+/*
+ * Firmware Assisted dump: A robust mechanism to get reliable kernel crash
+ * dump with assistance from firmware. This approach does not use kexec,
+ * instead firmware assists in booting the kdump kernel while preserving
+ * memory contents. The most of the code implementation has been adapted
+ * from phyp assisted dump implementation written by Linas Vepstas and
+ * Manish Ahuja
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ * Copyright 2011 IBM Corporation
+ * Author: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
+ */
+
+#undef DEBUG
+#define pr_fmt(fmt) "fadump: " fmt
+
+#include <linux/string.h>
+#include <linux/memblock.h>
+#include <linux/delay.h>
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
+#include <linux/crash_dump.h>
+#include <linux/kobject.h>
+#include <linux/sysfs.h>
+
+#include <asm/page.h>
+#include <asm/prom.h>
+#include <asm/rtas.h>
+#include <asm/fadump.h>
+
+static struct fw_dump fw_dump;
+static struct fadump_mem_struct fdm;
+static const struct fadump_mem_struct *fdm_active;
+
+static DEFINE_MUTEX(fadump_mutex);
+struct fad_crash_memory_ranges crash_memory_ranges[INIT_CRASHMEM_RANGES];
+int crash_mem_ranges;
+
+/* Scan the Firmware Assisted dump configuration details. */
+int __init early_init_dt_scan_fw_dump(unsigned long node,
+                        const char *uname, int depth, void *data)
+{
+        __be32 *sections;
+        int i, num_sections;
+        unsigned long size;
+        const int *token;
+
+        if (depth != 1 || strcmp(uname, "rtas") != 0)
+                return 0;
+
+        /*
+         * Check if Firmware Assisted dump is supported. if yes, check
+         * if dump has been initiated on last reboot.
+         */
+        token = of_get_flat_dt_prop(node, "ibm,configure-kernel-dump", NULL);
+        if (!token)
+                return 0;
+
+        fw_dump.fadump_supported = 1;
+        fw_dump.ibm_configure_kernel_dump = *token;
+
+        /*
+         * The 'ibm,kernel-dump' rtas node is present only if there is
+         * dump data waiting for us.
+         */
+        fdm_active = of_get_flat_dt_prop(node, "ibm,kernel-dump", NULL);
+        if (fdm_active)
+                fw_dump.dump_active = 1;
+
+        /* Get the sizes required to store dump data for the firmware provided
+         * dump sections.
+         * For each dump section type supported, a 32bit cell which defines
+         * the ID of a supported section followed by two 32 bit cells which
+         * gives teh size of the section in bytes.
+         */
+        sections = of_get_flat_dt_prop(node, "ibm,configure-kernel-dump-sizes",
+                                        &size);
+
+        if (!sections)
+                return 0;
+
+        num_sections = size / (3 * sizeof(u32));
+
+        for (i = 0; i < num_sections; i++, sections += 3) {
+                u32 type = (u32)of_read_number(sections, 1);
+
+                switch (type) {
+                case FADUMP_CPU_STATE_DATA:
+                        fw_dump.cpu_state_data_size =
+                                        of_read_ulong(&sections[1], 2);
+                        break;
+                case FADUMP_HPTE_REGION:
+                        fw_dump.hpte_region_size =
+                                        of_read_ulong(&sections[1], 2);
+                        break;
+                }
+        }
+        return 1;
+}
+
+int is_fadump_active(void)
+{
+        return fw_dump.dump_active;
+}
+
+/* Print firmware assisted dump configurations for debugging purpose. */
+static void fadump_show_config(void)
+{
+        pr_debug("Support for firmware-assisted dump (fadump): %s\n",
+                        (fw_dump.fadump_supported ? "present" : "no support"));
+
+        if (!fw_dump.fadump_supported)
+                return;
+
+        pr_debug("Fadump enabled    : %s\n",
+                                (fw_dump.fadump_enabled ? "yes" : "no"));
+        pr_debug("Dump Active       : %s\n",
+                                (fw_dump.dump_active ? "yes" : "no"));
+        pr_debug("Dump section sizes:\n");
+        pr_debug("    CPU state data size: %lx\n", fw_dump.cpu_state_data_size);
+        pr_debug("    HPTE region size   : %lx\n", fw_dump.hpte_region_size);
+        pr_debug("Boot memory size  : %lx\n", fw_dump.boot_memory_size);
+}
+
+static unsigned long init_fadump_mem_struct(struct fadump_mem_struct *fdm,
+                                unsigned long addr)
+{
+        if (!fdm)
+                return 0;
+
+        memset(fdm, 0, sizeof(struct fadump_mem_struct));
+        addr = addr & PAGE_MASK;
+
+        fdm->header.dump_format_version = 0x00000001;
+        fdm->header.dump_num_sections = 3;
+        fdm->header.dump_status_flag = 0;
+        fdm->header.offset_first_dump_section =
+                (u32)offsetof(struct fadump_mem_struct, cpu_state_data);
+
+        /*
+         * Fields for disk dump option.
+         * We are not using disk dump option, hence set these fields to 0.
+         */
+        fdm->header.dd_block_size = 0;
+        fdm->header.dd_block_offset = 0;
+        fdm->header.dd_num_blocks = 0;
+        fdm->header.dd_offset_disk_path = 0;
+
+        /* set 0 to disable an automatic dump-reboot. */
+        fdm->header.max_time_auto = 0;
+
+        /* Kernel dump sections */
+        /* cpu state data section. */
+        fdm->cpu_state_data.request_flag = FADUMP_REQUEST_FLAG;
+        fdm->cpu_state_data.source_data_type = FADUMP_CPU_STATE_DATA;
+        fdm->cpu_state_data.source_address = 0;
+        fdm->cpu_state_data.source_len = fw_dump.cpu_state_data_size;
+        fdm->cpu_state_data.destination_address = addr;
+        addr += fw_dump.cpu_state_data_size;
+
+        /* hpte region section */
+        fdm->hpte_region.request_flag = FADUMP_REQUEST_FLAG;
+        fdm->hpte_region.source_data_type = FADUMP_HPTE_REGION;
+        fdm->hpte_region.source_address = 0;
+        fdm->hpte_region.source_len = fw_dump.hpte_region_size;
+        fdm->hpte_region.destination_address = addr;
+        addr += fw_dump.hpte_region_size;
+
+        /* RMA region section */
+        fdm->rmr_region.request_flag = FADUMP_REQUEST_FLAG;
+        fdm->rmr_region.source_data_type = FADUMP_REAL_MODE_REGION;
+        fdm->rmr_region.source_address = RMA_START;
+        fdm->rmr_region.source_len = fw_dump.boot_memory_size;
+        fdm->rmr_region.destination_address = addr;
+        addr += fw_dump.boot_memory_size;
+
+        return addr;
+}
+
+/**
+ * fadump_calculate_reserve_size(): reserve variable boot area 5% of System RAM
+ *
+ * Function to find the largest memory size we need to reserve during early
+ * boot process. This will be the size of the memory that is required for a
+ * kernel to boot successfully.
+ *
+ * This function has been taken from phyp-assisted dump feature implementation.
+ *
+ * returns larger of 256MB or 5% rounded down to multiples of 256MB.
+ *
+ * TODO: Come up with better approach to find out more accurate memory size
+ * that is required for a kernel to boot successfully.
+ *
+ */
+static inline unsigned long fadump_calculate_reserve_size(void)
+{
+        unsigned long size;
+
+        /*
+         * Check if the size is specified through fadump_reserve_mem= cmdline
+         * option. If yes, then use that.
+         */
+        if (fw_dump.reserve_bootvar)
+                return fw_dump.reserve_bootvar;
+
+        /* divide by 20 to get 5% of value */
+        size = memblock_end_of_DRAM() / 20;
+
+        /* round it down in multiples of 256 */
+        size = size & ~0x0FFFFFFFUL;
+
+        /* Truncate to memory_limit. We don't want to over reserve the memory.*/
+        if (memory_limit && size > memory_limit)
+                size = memory_limit;
+
+        return (size > MIN_BOOT_MEM ? size : MIN_BOOT_MEM);
+}
+
+/*
+ * Calculate the total memory size required to be reserved for
+ * firmware-assisted dump registration.
+ */
+static unsigned long get_fadump_area_size(void)
+{
+        unsigned long size = 0;
+
+        size += fw_dump.cpu_state_data_size;
+        size += fw_dump.hpte_region_size;
+        size += fw_dump.boot_memory_size;
+        size += sizeof(struct fadump_crash_info_header);
+        size += sizeof(struct elfhdr); /* ELF core header.*/
+        size += sizeof(struct elf_phdr); /* place holder for cpu notes */
+        /* Program headers for crash memory regions. */
+        size += sizeof(struct elf_phdr) * (memblock_num_regions(memory) + 2);
+
+        size = PAGE_ALIGN(size);
+        return size;
+}
+
+int __init fadump_reserve_mem(void)
+{
+        unsigned long base, size, memory_boundary;
+
+        if (!fw_dump.fadump_enabled)
+                return 0;
+
+        if (!fw_dump.fadump_supported) {
+                printk(KERN_INFO "Firmware-assisted dump is not supported on"
+                                " this hardware\n");
+                fw_dump.fadump_enabled = 0;
+                return 0;
+        }
+        /*
+         * Initialize boot memory size
+         * If dump is active then we have already calculated the size during
+         * first kernel.
+         */
+        if (fdm_active)
+                fw_dump.boot_memory_size = fdm_active->rmr_region.source_len;
+        else
+                fw_dump.boot_memory_size = fadump_calculate_reserve_size();
+
+        /*
+         * Calculate the memory boundary.
+         * If memory_limit is less than actual memory boundary then reserve
+         * the memory for fadump beyond the memory_limit and adjust the
+         * memory_limit accordingly, so that the running kernel can run with
+         * specified memory_limit.
+         */
+        if (memory_limit && memory_limit < memblock_end_of_DRAM()) {
+                size = get_fadump_area_size();
+                if ((memory_limit + size) < memblock_end_of_DRAM())
+                        memory_limit += size;
+                else
+                        memory_limit = memblock_end_of_DRAM();
+                printk(KERN_INFO "Adjusted memory_limit for firmware-assisted"
+                                " dump, now %#016llx\n",
+                                (unsigned long long)memory_limit);
+        }
+        if (memory_limit)
+                memory_boundary = memory_limit;
+        else
+                memory_boundary = memblock_end_of_DRAM();
+
+        if (fw_dump.dump_active) {
+                printk(KERN_INFO "Firmware-assisted dump is active.\n");
+                /*
+                 * If last boot has crashed then reserve all the memory
+                 * above boot_memory_size so that we don't touch it until
+                 * dump is written to disk by userspace tool. This memory
+                 * will be released for general use once the dump is saved.
+                 */
+                base = fw_dump.boot_memory_size;
+                size = memory_boundary - base;
+                memblock_reserve(base, size);
+                printk(KERN_INFO "Reserved %ldMB of memory at %ldMB "
+                                "for saving crash dump\n",
+                                (unsigned long)(size >> 20),
+                                (unsigned long)(base >> 20));
+
+                fw_dump.fadumphdr_addr =
+                                fdm_active->rmr_region.destination_address +
+                                fdm_active->rmr_region.source_len;
+                pr_debug("fadumphdr_addr = %p\n",
+                                (void *) fw_dump.fadumphdr_addr);
+        } else {
+                /* Reserve the memory at the top of memory. */
+                size = get_fadump_area_size();
+                base = memory_boundary - size;
+                memblock_reserve(base, size);
+                printk(KERN_INFO "Reserved %ldMB of memory at %ldMB "
+                                "for firmware-assisted dump\n",
+                                (unsigned long)(size >> 20),
+                                (unsigned long)(base >> 20));
+        }
+        fw_dump.reserve_dump_area_start = base;
+        fw_dump.reserve_dump_area_size = size;
+        return 1;
+}
+
+/* Look for fadump= cmdline option. */
+static int __init early_fadump_param(char *p)
+{
+        if (!p)
+                return 1;
+
+        if (strncmp(p, "on", 2) == 0)
+                fw_dump.fadump_enabled = 1;
+        else if (strncmp(p, "off", 3) == 0)
+                fw_dump.fadump_enabled = 0;
+
+        return 0;
+}
+early_param("fadump", early_fadump_param);
+
+/* Look for fadump_reserve_mem= cmdline option */
+static int __init early_fadump_reserve_mem(char *p)
+{
+        if (p)
+                fw_dump.reserve_bootvar = memparse(p, &p);
+        return 0;
+}
+early_param("fadump_reserve_mem", early_fadump_reserve_mem);
+
+static void register_fw_dump(struct fadump_mem_struct *fdm)
+{
+        int rc;
+        unsigned int wait_time;
+
+        pr_debug("Registering for firmware-assisted kernel dump...\n");
+
+        /* TODO: Add upper time limit for the delay */
+        do {
+                rc = rtas_call(fw_dump.ibm_configure_kernel_dump, 3, 1, NULL,
+                        FADUMP_REGISTER, fdm,
+                        sizeof(struct fadump_mem_struct));
+
+                wait_time = rtas_busy_delay_time(rc);
+                if (wait_time)
+                        mdelay(wait_time);
+
+        } while (wait_time);
+
+        switch (rc) {
+        case -1:
+                printk(KERN_ERR "Failed to register firmware-assisted kernel"
+                        " dump. Hardware Error(%d).\n", rc);
+                break;
+        case -3:
+                printk(KERN_ERR "Failed to register firmware-assisted kernel"
+                        " dump. Parameter Error(%d).\n", rc);
+                break;
+        case -9:
+                printk(KERN_ERR "firmware-assisted kernel dump is already "
+                        " registered.");
+                fw_dump.dump_registered = 1;
+                break;
+        case 0:
+                printk(KERN_INFO "firmware-assisted kernel dump registration"
+                        " is successful\n");
+                fw_dump.dump_registered = 1;
+                break;
+        }
+}
+
+void crash_fadump(struct pt_regs *regs, const char *str)
+{
+        struct fadump_crash_info_header *fdh = NULL;
+
+        if (!fw_dump.dump_registered || !fw_dump.fadumphdr_addr)
+                return;
+
+        fdh = __va(fw_dump.fadumphdr_addr);
+        crashing_cpu = smp_processor_id();
+        fdh->crashing_cpu = crashing_cpu;
+        crash_save_vmcoreinfo();
+
+        if (regs)
+                fdh->regs = *regs;
+        else
+                ppc_save_regs(&fdh->regs);
+
+        fdh->cpu_online_mask = *cpu_online_mask;
+
+        /* Call ibm,os-term rtas call to trigger firmware assisted dump */
+        rtas_os_term((char *)str);
+}
+
+#define GPR_MASK        0xffffff0000000000
+static inline int fadump_gpr_index(u64 id)
+{
+        int i = -1;
+        char str[3];
+
+        if ((id & GPR_MASK) == REG_ID("GPR")) {
+                /* get the digits at the end */
+                id &= ~GPR_MASK;
+                id >>= 24;
+                str[2] = '\0';
+                str[1] = id & 0xff;
+                str[0] = (id >> 8) & 0xff;
+                sscanf(str, "%d", &i);
+                if (i > 31)
+                        i = -1;
+        }
+        return i;
+}
+
+static inline void fadump_set_regval(struct pt_regs *regs, u64 reg_id,
+                                                                u64 reg_val)
+{
+        int i;
+
+        i = fadump_gpr_index(reg_id);
+        if (i >= 0)
+                regs->gpr[i] = (unsigned long)reg_val;
+        else if (reg_id == REG_ID("NIA"))
+                regs->nip = (unsigned long)reg_val;
+        else if (reg_id == REG_ID("MSR"))
+                regs->msr = (unsigned long)reg_val;
+        else if (reg_id == REG_ID("CTR"))
+                regs->ctr = (unsigned long)reg_val;
+        else if (reg_id == REG_ID("LR"))
+                regs->link = (unsigned long)reg_val;
+        else if (reg_id == REG_ID("XER"))
+                regs->xer = (unsigned long)reg_val;
+        else if (reg_id == REG_ID("CR"))
+                regs->ccr = (unsigned long)reg_val;
+        else if (reg_id == REG_ID("DAR"))
+                regs->dar = (unsigned long)reg_val;
+        else if (reg_id == REG_ID("DSISR"))
+                regs->dsisr = (unsigned long)reg_val;
+}
+
+static struct fadump_reg_entry*
+fadump_read_registers(struct fadump_reg_entry *reg_entry, struct pt_regs *regs)
+{
+        memset(regs, 0, sizeof(struct pt_regs));
+
+        while (reg_entry->reg_id != REG_ID("CPUEND")) {
+                fadump_set_regval(regs, reg_entry->reg_id,
+                                        reg_entry->reg_value);
+                reg_entry++;
+        }
+        reg_entry++;
+        return reg_entry;
+}
+
+static u32 *fadump_append_elf_note(u32 *buf, char *name, unsigned type,
+                                                void *data, size_t data_len)
+{
+        struct elf_note note;
+
+        note.n_namesz = strlen(name) + 1;
+        note.n_descsz = data_len;
+        note.n_type   = type;
+        memcpy(buf, &note, sizeof(note));
+        buf += (sizeof(note) + 3)/4;
+        memcpy(buf, name, note.n_namesz);
+        buf += (note.n_namesz + 3)/4;
+        memcpy(buf, data, note.n_descsz);
+        buf += (note.n_descsz + 3)/4;
+
+        return buf;
+}
+
+static void fadump_final_note(u32 *buf)
+{
+        struct elf_note note;
+
+        note.n_namesz = 0;
+        note.n_descsz = 0;
+        note.n_type   = 0;
+        memcpy(buf, &note, sizeof(note));
+}
+
+static u32 *fadump_regs_to_elf_notes(u32 *buf, struct pt_regs *regs)
+{
+        struct elf_prstatus prstatus;
+
+        memset(&prstatus, 0, sizeof(prstatus));
+        /*
+         * FIXME: How do i get PID? Do I really need it?
+         * prstatus.pr_pid = ????
+         */
+        elf_core_copy_kernel_regs(&prstatus.pr_reg, regs);
+        buf = fadump_append_elf_note(buf, KEXEC_CORE_NOTE_NAME, NT_PRSTATUS,
+                                &prstatus, sizeof(prstatus));
+        return buf;
+}
+
+static void fadump_update_elfcore_header(char *bufp)
+{
+        struct elfhdr *elf;
+        struct elf_phdr *phdr;
+
+        elf = (struct elfhdr *)bufp;
+        bufp += sizeof(struct elfhdr);
+
+        /* First note is a place holder for cpu notes info. */
+        phdr = (struct elf_phdr *)bufp;
+
+        if (phdr->p_type == PT_NOTE) {
+                phdr->p_paddr = fw_dump.cpu_notes_buf;
+                phdr->p_offset  = phdr->p_paddr;
+                phdr->p_filesz  = fw_dump.cpu_notes_buf_size;
+                phdr->p_memsz = fw_dump.cpu_notes_buf_size;
+        }
+        return;
+}
+
+static void *fadump_cpu_notes_buf_alloc(unsigned long size)
+{
+        void *vaddr;
+        struct page *page;
+        unsigned long order, count, i;
+
+        order = get_order(size);
+        vaddr = (void *)__get_free_pages(GFP_KERNEL|__GFP_ZERO, order);
+        if (!vaddr)
+                return NULL;
+
+        count = 1 << order;
+        page = virt_to_page(vaddr);
+        for (i = 0; i < count; i++)
+                SetPageReserved(page + i);
+        return vaddr;
+}
+
+static void fadump_cpu_notes_buf_free(unsigned long vaddr, unsigned long size)
+{
+        struct page *page;
+        unsigned long order, count, i;
+
+        order = get_order(size);
+        count = 1 << order;
+        page = virt_to_page(vaddr);
+        for (i = 0; i < count; i++)
+                ClearPageReserved(page + i);
+        __free_pages(page, order);
+}
+
+/*
+ * Read CPU state dump data and convert it into ELF notes.
+ * The CPU dump starts with magic number "REGSAVE". NumCpusOffset should be
+ * used to access the data to allow for additional fields to be added without
+ * affecting compatibility. Each list of registers for a CPU starts with
+ * "CPUSTRT" and ends with "CPUEND". Each register entry is of 16 bytes,
+ * 8 Byte ASCII identifier and 8 Byte register value. The register entry
+ * with identifier "CPUSTRT" and "CPUEND" contains 4 byte cpu id as part
+ * of register value. For more details refer to PAPR document.
+ *
+ * Only for the crashing cpu we ignore the CPU dump data and get exact
+ * state from fadump crash info structure populated by first kernel at the
+ * time of crash.
+ */
+static int __init fadump_build_cpu_notes(const struct fadump_mem_struct *fdm)
+{
+        struct fadump_reg_save_area_header *reg_header;
+        struct fadump_reg_entry *reg_entry;
+        struct fadump_crash_info_header *fdh = NULL;
+        void *vaddr;
+        unsigned long addr;
+        u32 num_cpus, *note_buf;
+        struct pt_regs regs;
+        int i, rc = 0, cpu = 0;
+
+        if (!fdm->cpu_state_data.bytes_dumped)
+                return -EINVAL;
+
+        addr = fdm->cpu_state_data.destination_address;
+        vaddr = __va(addr);
+
+        reg_header = vaddr;
+        if (reg_header->magic_number != REGSAVE_AREA_MAGIC) {
+                printk(KERN_ERR "Unable to read register save area.\n");
+                return -ENOENT;
+        }
+        pr_debug("--------CPU State Data------------\n");
+        pr_debug("Magic Number: %llx\n", reg_header->magic_number);
+        pr_debug("NumCpuOffset: %x\n", reg_header->num_cpu_offset);
+
+        vaddr += reg_header->num_cpu_offset;
+        num_cpus = *((u32 *)(vaddr));
+        pr_debug("NumCpus     : %u\n", num_cpus);
+        vaddr += sizeof(u32);
+        reg_entry = (struct fadump_reg_entry *)vaddr;
+
+        /* Allocate buffer to hold cpu crash notes. */
+        fw_dump.cpu_notes_buf_size = num_cpus * sizeof(note_buf_t);
+        fw_dump.cpu_notes_buf_size = PAGE_ALIGN(fw_dump.cpu_notes_buf_size);
+        note_buf = fadump_cpu_notes_buf_alloc(fw_dump.cpu_notes_buf_size);
+        if (!note_buf) {
+                printk(KERN_ERR "Failed to allocate 0x%lx bytes for "
+                        "cpu notes buffer\n", fw_dump.cpu_notes_buf_size);
+                return -ENOMEM;
+        }
+        fw_dump.cpu_notes_buf = __pa(note_buf);
+
+        pr_debug("Allocated buffer for cpu notes of size %ld at %p\n",
+                        (num_cpus * sizeof(note_buf_t)), note_buf);
+
+        if (fw_dump.fadumphdr_addr)
+                fdh = __va(fw_dump.fadumphdr_addr);
+
+        for (i = 0; i < num_cpus; i++) {
+                if (reg_entry->reg_id != REG_ID("CPUSTRT")) {
+                        printk(KERN_ERR "Unable to read CPU state data\n");
+                        rc = -ENOENT;
+                        goto error_out;
+                }
+                /* Lower 4 bytes of reg_value contains logical cpu id */
+                cpu = reg_entry->reg_value & FADUMP_CPU_ID_MASK;
+                if (!cpumask_test_cpu(cpu, &fdh->cpu_online_mask)) {
+                        SKIP_TO_NEXT_CPU(reg_entry);
+                        continue;
+                }
+                pr_debug("Reading register data for cpu %d...\n", cpu);
+                if (fdh && fdh->crashing_cpu == cpu) {
+                        regs = fdh->regs;
+                        note_buf = fadump_regs_to_elf_notes(note_buf, &regs);
+                        SKIP_TO_NEXT_CPU(reg_entry);
+                } else {
+                        reg_entry++;
+                        reg_entry = fadump_read_registers(reg_entry, &regs);
+                        note_buf = fadump_regs_to_elf_notes(note_buf, &regs);
+                }
+        }
+        fadump_final_note(note_buf);
+
+        pr_debug("Updating elfcore header (%llx) with cpu notes\n",
+                                                        fdh->elfcorehdr_addr);
+        fadump_update_elfcore_header((char *)__va(fdh->elfcorehdr_addr));
+        return 0;
+
+error_out:
+        fadump_cpu_notes_buf_free((unsigned long)__va(fw_dump.cpu_notes_buf),
+                                        fw_dump.cpu_notes_buf_size);
+        fw_dump.cpu_notes_buf = 0;
+        fw_dump.cpu_notes_buf_size = 0;
+        return rc;
+
+}
+
+/*
+ * Validate and process the dump data stored by firmware before exporting
+ * it through '/proc/vmcore'.
+ */
+static int __init process_fadump(const struct fadump_mem_struct *fdm_active)
+{
+        struct fadump_crash_info_header *fdh;
+        int rc = 0;
+
+        if (!fdm_active || !fw_dump.fadumphdr_addr)
+                return -EINVAL;
+
+        /* Check if the dump data is valid. */
+        if ((fdm_active->header.dump_status_flag == FADUMP_ERROR_FLAG) ||
+                        (fdm_active->cpu_state_data.error_flags != 0) ||
+                        (fdm_active->rmr_region.error_flags != 0)) {
+                printk(KERN_ERR "Dump taken by platform is not valid\n");
+                return -EINVAL;
+        }
+        if ((fdm_active->rmr_region.bytes_dumped !=
+                        fdm_active->rmr_region.source_len) ||
+                        !fdm_active->cpu_state_data.bytes_dumped) {
+                printk(KERN_ERR "Dump taken by platform is incomplete\n");
+                return -EINVAL;
+        }
+
+        /* Validate the fadump crash info header */
+        fdh = __va(fw_dump.fadumphdr_addr);
+        if (fdh->magic_number != FADUMP_CRASH_INFO_MAGIC) {
+                printk(KERN_ERR "Crash info header is not valid.\n");
+                return -EINVAL;
+        }
+
+        rc = fadump_build_cpu_notes(fdm_active);
+        if (rc)
+                return rc;
+
+        /*
+         * We are done validating dump info and elfcore header is now ready
+         * to be exported. set elfcorehdr_addr so that vmcore module will
+         * export the elfcore header through '/proc/vmcore'.
+         */
+        elfcorehdr_addr = fdh->elfcorehdr_addr;
+
+        return 0;
+}
+
+static inline void fadump_add_crash_memory(unsigned long long base,
+                                        unsigned long long end)
+{
+        if (base == end)
+                return;
+
+        pr_debug("crash_memory_range[%d] [%#016llx-%#016llx], %#llx bytes\n",
+                crash_mem_ranges, base, end - 1, (end - base));
+        crash_memory_ranges[crash_mem_ranges].base = base;
+        crash_memory_ranges[crash_mem_ranges].size = end - base;
+        crash_mem_ranges++;
+}
+
+static void fadump_exclude_reserved_area(unsigned long long start,
+                                        unsigned long long end)
+{
+        unsigned long long ra_start, ra_end;
+
+        ra_start = fw_dump.reserve_dump_area_start;
+        ra_end = ra_start + fw_dump.reserve_dump_area_size;
+
+        if ((ra_start < end) && (ra_end > start)) {
+                if ((start < ra_start) && (end > ra_end)) {
+                        fadump_add_crash_memory(start, ra_start);
+                        fadump_add_crash_memory(ra_end, end);
+                } else if (start < ra_start) {
+                        fadump_add_crash_memory(start, ra_start);
+                } else if (ra_end < end) {
+                        fadump_add_crash_memory(ra_end, end);
+                }
+        } else
+                fadump_add_crash_memory(start, end);
+}
+
+static int fadump_init_elfcore_header(char *bufp)
+{
+        struct elfhdr *elf;
+
+        elf = (struct elfhdr *) bufp;
+        bufp += sizeof(struct elfhdr);
+        memcpy(elf->e_ident, ELFMAG, SELFMAG);
+        elf->e_ident[EI_CLASS] = ELF_CLASS;
+        elf->e_ident[EI_DATA] = ELF_DATA;
+        elf->e_ident[EI_VERSION] = EV_CURRENT;
+        elf->e_ident[EI_OSABI] = ELF_OSABI;
+        memset(elf->e_ident+EI_PAD, 0, EI_NIDENT-EI_PAD);
+        elf->e_type = ET_CORE;
+        elf->e_machine = ELF_ARCH;
+        elf->e_version = EV_CURRENT;
+        elf->e_entry = 0;
+        elf->e_phoff = sizeof(struct elfhdr);
+        elf->e_shoff = 0;
+        elf->e_flags = ELF_CORE_EFLAGS;
+        elf->e_ehsize = sizeof(struct elfhdr);
+        elf->e_phentsize = sizeof(struct elf_phdr);
+        elf->e_phnum = 0;
+        elf->e_shentsize = 0;
+        elf->e_shnum = 0;
+        elf->e_shstrndx = 0;
+
+        return 0;
+}
+
+/*
+ * Traverse through memblock structure and setup crash memory ranges. These
+ * ranges will be used create PT_LOAD program headers in elfcore header.
+ */
+static void fadump_setup_crash_memory_ranges(void)
+{
+        struct memblock_region *reg;
+        unsigned long long start, end;
+
+        pr_debug("Setup crash memory ranges.\n");
+        crash_mem_ranges = 0;
+        /*
+         * add the first memory chunk (RMA_START through boot_memory_size) as
+         * a separate memory chunk. The reason is, at the time crash firmware
+         * will move the content of this memory chunk to different location
+         * specified during fadump registration. We need to create a separate
+         * program header for this chunk with the correct offset.
+         */
+        fadump_add_crash_memory(RMA_START, fw_dump.boot_memory_size);
+
+        for_each_memblock(memory, reg) {
+                start = (unsigned long long)reg->base;
+                end = start + (unsigned long long)reg->size;
+                if (start == RMA_START && end >= fw_dump.boot_memory_size)
+                        start = fw_dump.boot_memory_size;
+
+                /* add this range excluding the reserved dump area. */
+                fadump_exclude_reserved_area(start, end);
+        }
+}
+
+/*
+ * If the given physical address falls within the boot memory region then
+ * return the relocated address that points to the dump region reserved
+ * for saving initial boot memory contents.
+ */
+static inline unsigned long fadump_relocate(unsigned long paddr)
+{
+        if (paddr > RMA_START && paddr < fw_dump.boot_memory_size)
+                return fdm.rmr_region.destination_address + paddr;
+        else
+                return paddr;
+}
+
+static int fadump_create_elfcore_headers(char *bufp)
+{
+        struct elfhdr *elf;
+        struct elf_phdr *phdr;
+        int i;
+
+        fadump_init_elfcore_header(bufp);
+        elf = (struct elfhdr *)bufp;
+        bufp += sizeof(struct elfhdr);
+
+        /*
+         * setup ELF PT_NOTE, place holder for cpu notes info. The notes info
+         * will be populated during second kernel boot after crash. Hence
+         * this PT_NOTE will always be the first elf note.
+         *
+         * NOTE: Any new ELF note addition should be placed after this note.
+         */
+        phdr = (struct elf_phdr *)bufp;
+        bufp += sizeof(struct elf_phdr);
+        phdr->p_type = PT_NOTE;
+        phdr->p_flags = 0;
+        phdr->p_vaddr = 0;
+        phdr->p_align = 0;
+
+        phdr->p_offset = 0;
+        phdr->p_paddr = 0;
+        phdr->p_filesz = 0;
+        phdr->p_memsz = 0;
+
+        (elf->e_phnum)++;
+
+        /* setup ELF PT_NOTE for vmcoreinfo */
+        phdr = (struct elf_phdr *)bufp;
+        bufp += sizeof(struct elf_phdr);
+        phdr->p_type    = PT_NOTE;
+        phdr->p_flags   = 0;
+        phdr->p_vaddr   = 0;
+        phdr->p_align   = 0;
+
+        phdr->p_paddr   = fadump_relocate(paddr_vmcoreinfo_note());
+        phdr->p_offset  = phdr->p_paddr;
+        phdr->p_memsz   = vmcoreinfo_max_size;
+        phdr->p_filesz  = vmcoreinfo_max_size;
+
+        /* Increment number of program headers. */
+        (elf->e_phnum)++;
+
+        /* setup PT_LOAD sections. */
+
+        for (i = 0; i < crash_mem_ranges; i++) {
+                unsigned long long mbase, msize;
+                mbase = crash_memory_ranges[i].base;
+                msize = crash_memory_ranges[i].size;
+
+                if (!msize)
+                        continue;
+
+                phdr = (struct elf_phdr *)bufp;
+                bufp += sizeof(struct elf_phdr);
+                phdr->p_type    = PT_LOAD;
+                phdr->p_flags   = PF_R|PF_W|PF_X;
+                phdr->p_offset  = mbase;
+
+                if (mbase == RMA_START) {
+                        /*
+                         * The entire RMA region will be moved by firmware
+                         * to the specified destination_address. Hence set
+                         * the correct offset.
+                         */
+                        phdr->p_offset = fdm.rmr_region.destination_address;
+                }
+
+                phdr->p_paddr = mbase;
+                phdr->p_vaddr = (unsigned long)__va(mbase);
+                phdr->p_filesz = msize;
+                phdr->p_memsz = msize;
+                phdr->p_align = 0;
+
+                /* Increment number of program headers. */
+                (elf->e_phnum)++;
+        }
+        return 0;
+}
+
+static unsigned long init_fadump_header(unsigned long addr)
+{
+        struct fadump_crash_info_header *fdh;
+
+        if (!addr)
+                return 0;
+
+        fw_dump.fadumphdr_addr = addr;
+        fdh = __va(addr);
+        addr += sizeof(struct fadump_crash_info_header);
+
+        memset(fdh, 0, sizeof(struct fadump_crash_info_header));
+        fdh->magic_number = FADUMP_CRASH_INFO_MAGIC;
+        fdh->elfcorehdr_addr = addr;
+        /* We will set the crashing cpu id in crash_fadump() during crash. */
+        fdh->crashing_cpu = CPU_UNKNOWN;
+
+        return addr;
+}
+
+static void register_fadump(void)
+{
+        unsigned long addr;
+        void *vaddr;
+
+        /*
+         * If no memory is reserved then we can not register for firmware-
+         * assisted dump.
+         */
+        if (!fw_dump.reserve_dump_area_size)
+                return;
+
+        fadump_setup_crash_memory_ranges();
+
+        addr = fdm.rmr_region.destination_address + fdm.rmr_region.source_len;
+        /* Initialize fadump crash info header. */
+        addr = init_fadump_header(addr);
+        vaddr = __va(addr);
+
+        pr_debug("Creating ELF core headers at %#016lx\n", addr);
+        fadump_create_elfcore_headers(vaddr);
+
+        /* register the future kernel dump with firmware. */
+        register_fw_dump(&fdm);
+}
+
+static int fadump_unregister_dump(struct fadump_mem_struct *fdm)
+{
+        int rc = 0;
+        unsigned int wait_time;
+
+        pr_debug("Un-register firmware-assisted dump\n");
+
+        /* TODO: Add upper time limit for the delay */
+        do {
+                rc = rtas_call(fw_dump.ibm_configure_kernel_dump, 3, 1, NULL,
+                        FADUMP_UNREGISTER, fdm,
+                        sizeof(struct fadump_mem_struct));
+
+                wait_time = rtas_busy_delay_time(rc);
+                if (wait_time)
+                        mdelay(wait_time);
+        } while (wait_time);
+
+        if (rc) {
+                printk(KERN_ERR "Failed to un-register firmware-assisted dump."
+                        " unexpected error(%d).\n", rc);
+                return rc;
+        }
+        fw_dump.dump_registered = 0;
+        return 0;
+}
+
+static int fadump_invalidate_dump(struct fadump_mem_struct *fdm)
+{
+        int rc = 0;
+        unsigned int wait_time;
+
+        pr_debug("Invalidating firmware-assisted dump registration\n");
+
+        /* TODO: Add upper time limit for the delay */
+        do {
+                rc = rtas_call(fw_dump.ibm_configure_kernel_dump, 3, 1, NULL,
+                        FADUMP_INVALIDATE, fdm,
+                        sizeof(struct fadump_mem_struct));
+
+                wait_time = rtas_busy_delay_time(rc);
+                if (wait_time)
+                        mdelay(wait_time);
+        } while (wait_time);
+
+        if (rc) {
+                printk(KERN_ERR "Failed to invalidate firmware-assisted dump "
+                        "rgistration. unexpected error(%d).\n", rc);
+                return rc;
+        }
+        fw_dump.dump_active = 0;
+        fdm_active = NULL;
+        return 0;
+}
+
+void fadump_cleanup(void)
+{
+        /* Invalidate the registration only if dump is active. */
+        if (fw_dump.dump_active) {
+                init_fadump_mem_struct(&fdm,
+                        fdm_active->cpu_state_data.destination_address);
+                fadump_invalidate_dump(&fdm);
+        }
+}
+
+/*
+ * Release the memory that was reserved in early boot to preserve the memory
+ * contents. The released memory will be available for general use.
+ */
+static void fadump_release_memory(unsigned long begin, unsigned long end)
+{
+        unsigned long addr;
+        unsigned long ra_start, ra_end;
+
+        ra_start = fw_dump.reserve_dump_area_start;
+        ra_end = ra_start + fw_dump.reserve_dump_area_size;
+
+        for (addr = begin; addr < end; addr += PAGE_SIZE) {
+                /*
+                 * exclude the dump reserve area. Will reuse it for next
+                 * fadump registration.
+                 */
+                if (addr <= ra_end && ((addr + PAGE_SIZE) > ra_start))
+                        continue;
+
+                ClearPageReserved(pfn_to_page(addr >> PAGE_SHIFT));
+                init_page_count(pfn_to_page(addr >> PAGE_SHIFT));
+                free_page((unsigned long)__va(addr));
+                totalram_pages++;
+        }
+}
+
+static void fadump_invalidate_release_mem(void)
+{
+        unsigned long reserved_area_start, reserved_area_end;
+        unsigned long destination_address;
+
+        mutex_lock(&fadump_mutex);
+        if (!fw_dump.dump_active) {
+                mutex_unlock(&fadump_mutex);
+                return;
+        }
+
+        destination_address = fdm_active->cpu_state_data.destination_address;
+        fadump_cleanup();
+        mutex_unlock(&fadump_mutex);
+
+        /*
+         * Save the current reserved memory bounds we will require them
+         * later for releasing the memory for general use.
+         */
+        reserved_area_start = fw_dump.reserve_dump_area_start;
+        reserved_area_end = reserved_area_start +
+                        fw_dump.reserve_dump_area_size;
+        /*
+         * Setup reserve_dump_area_start and its size so that we can
+         * reuse this reserved memory for Re-registration.
+         */
+        fw_dump.reserve_dump_area_start = destination_address;
+        fw_dump.reserve_dump_area_size = get_fadump_area_size();
+
+        fadump_release_memory(reserved_area_start, reserved_area_end);
+        if (fw_dump.cpu_notes_buf) {
+                fadump_cpu_notes_buf_free(
+                                (unsigned long)__va(fw_dump.cpu_notes_buf),
+                                fw_dump.cpu_notes_buf_size);
+                fw_dump.cpu_notes_buf = 0;
+                fw_dump.cpu_notes_buf_size = 0;
+        }
+        /* Initialize the kernel dump memory structure for FAD registration. */
+        init_fadump_mem_struct(&fdm, fw_dump.reserve_dump_area_start);
+}
+
+static ssize_t fadump_release_memory_store(struct kobject *kobj,
+                                        struct kobj_attribute *attr,
+                                        const char *buf, size_t count)
+{
+        if (!fw_dump.dump_active)
+                return -EPERM;
+
+        if (buf[0] == '1') {
+                /*
+                 * Take away the '/proc/vmcore'. We are releasing the dump
+                 * memory, hence it will not be valid anymore.
+                 */
+                vmcore_cleanup();
+                fadump_invalidate_release_mem();
+
+        } else
+                return -EINVAL;
+        return count;
+}
+
+static ssize_t fadump_enabled_show(struct kobject *kobj,
+                                        struct kobj_attribute *attr,
+                                        char *buf)
+{
+        return sprintf(buf, "%d\n", fw_dump.fadump_enabled);
+}
+
+static ssize_t fadump_register_show(struct kobject *kobj,
+                                        struct kobj_attribute *attr,
+                                        char *buf)
+{
+        return sprintf(buf, "%d\n", fw_dump.dump_registered);
+}
+
+static ssize_t fadump_register_store(struct kobject *kobj,
+                                        struct kobj_attribute *attr,
+                                        const char *buf, size_t count)
+{
+        int ret = 0;
+
+        if (!fw_dump.fadump_enabled || fdm_active)
+                return -EPERM;
+
+        mutex_lock(&fadump_mutex);
+
+        switch (buf[0]) {
+        case '0':
+                if (fw_dump.dump_registered == 0) {
+                        ret = -EINVAL;
+                        goto unlock_out;
+                }
+                /* Un-register Firmware-assisted dump */
+                fadump_unregister_dump(&fdm);
+                break;
+        case '1':
+                if (fw_dump.dump_registered == 1) {
+                        ret = -EINVAL;
+                        goto unlock_out;
+                }
+                /* Register Firmware-assisted dump */
+                register_fadump();
+                break;
+        default:
+                ret = -EINVAL;
+                break;
+        }
+
+unlock_out:
+        mutex_unlock(&fadump_mutex);
+        return ret < 0 ? ret : count;
+}
+
+static int fadump_region_show(struct seq_file *m, void *private)
+{
+        const struct fadump_mem_struct *fdm_ptr;
+
+        if (!fw_dump.fadump_enabled)
+                return 0;
+
+        mutex_lock(&fadump_mutex);
+        if (fdm_active)
+                fdm_ptr = fdm_active;
+        else {
+                mutex_unlock(&fadump_mutex);
+                fdm_ptr = &fdm;
+        }
+
+        seq_printf(m,
+                        "CPU : [%#016llx-%#016llx] %#llx bytes, "
+                        "Dumped: %#llx\n",
+                        fdm_ptr->cpu_state_data.destination_address,
+                        fdm_ptr->cpu_state_data.destination_address +
+                        fdm_ptr->cpu_state_data.source_len - 1,
+                        fdm_ptr->cpu_state_data.source_len,
+                        fdm_ptr->cpu_state_data.bytes_dumped);
+        seq_printf(m,
+                        "HPTE: [%#016llx-%#016llx] %#llx bytes, "
+                        "Dumped: %#llx\n",
+                        fdm_ptr->hpte_region.destination_address,
+                        fdm_ptr->hpte_region.destination_address +
+                        fdm_ptr->hpte_region.source_len - 1,
+                        fdm_ptr->hpte_region.source_len,
+                        fdm_ptr->hpte_region.bytes_dumped);
+        seq_printf(m,
+                        "DUMP: [%#016llx-%#016llx] %#llx bytes, "
+                        "Dumped: %#llx\n",
+                        fdm_ptr->rmr_region.destination_address,
+                        fdm_ptr->rmr_region.destination_address +
+                        fdm_ptr->rmr_region.source_len - 1,
+                        fdm_ptr->rmr_region.source_len,
+                        fdm_ptr->rmr_region.bytes_dumped);
+
+        if (!fdm_active ||
+                (fw_dump.reserve_dump_area_start ==
+                fdm_ptr->cpu_state_data.destination_address))
+                goto out;
+
+        /* Dump is active. Show reserved memory region. */
+        seq_printf(m,
+                        "    : [%#016llx-%#016llx] %#llx bytes, "
+                        "Dumped: %#llx\n",
+                        (unsigned long long)fw_dump.reserve_dump_area_start,
+                        fdm_ptr->cpu_state_data.destination_address - 1,
+                        fdm_ptr->cpu_state_data.destination_address -
+                        fw_dump.reserve_dump_area_start,
+                        fdm_ptr->cpu_state_data.destination_address -
+                        fw_dump.reserve_dump_area_start);
+out:
+        if (fdm_active)
+                mutex_unlock(&fadump_mutex);
+        return 0;
+}
+
+static struct kobj_attribute fadump_release_attr = __ATTR(fadump_release_mem,
+                                                0200, NULL,
+                                                fadump_release_memory_store);
+static struct kobj_attribute fadump_attr = __ATTR(fadump_enabled,
+                                                0444, fadump_enabled_show,
+                                                NULL);
+static struct kobj_attribute fadump_register_attr = __ATTR(fadump_registered,
+                                                0644, fadump_register_show,
+                                                fadump_register_store);
+
+static int fadump_region_open(struct inode *inode, struct file *file)
+{
+        return single_open(file, fadump_region_show, inode->i_private);
+}
+
+static const struct file_operations fadump_region_fops = {
+        .open    = fadump_region_open,
+        .read    = seq_read,
+        .llseek  = seq_lseek,
+        .release = single_release,
+};
+
+static void fadump_init_files(void)
+{
+        struct dentry *debugfs_file;
+        int rc = 0;
+
+        rc = sysfs_create_file(kernel_kobj, &fadump_attr.attr);
+        if (rc)
+                printk(KERN_ERR "fadump: unable to create sysfs file"
+                        " fadump_enabled (%d)\n", rc);
+
+        rc = sysfs_create_file(kernel_kobj, &fadump_register_attr.attr);
+        if (rc)
+                printk(KERN_ERR "fadump: unable to create sysfs file"
+                        " fadump_registered (%d)\n", rc);
+
+        debugfs_file = debugfs_create_file("fadump_region", 0444,
+                                        powerpc_debugfs_root, NULL,
+                                        &fadump_region_fops);
+        if (!debugfs_file)
+                printk(KERN_ERR "fadump: unable to create debugfs file"
+                                " fadump_region\n");
+
+        if (fw_dump.dump_active) {
+                rc = sysfs_create_file(kernel_kobj, &fadump_release_attr.attr);
+                if (rc)
+                        printk(KERN_ERR "fadump: unable to create sysfs file"
+                                " fadump_release_mem (%d)\n", rc);
+        }
+        return;
+}
+
+/*
+ * Prepare for firmware-assisted dump.
+ */
+int __init setup_fadump(void)
+{
+        if (!fw_dump.fadump_enabled)
+                return 0;
+
+        if (!fw_dump.fadump_supported) {
+                printk(KERN_ERR "Firmware-assisted dump is not supported on"
+                        " this hardware\n");
+                return 0;
+        }
+
+        fadump_show_config();
+        /*
+         * If dump data is available then see if it is valid and prepare for
+         * saving it to the disk.
+         */
+        if (fw_dump.dump_active) {
+                /*
+                 * if dump process fails then invalidate the registration
+                 * and release memory before proceeding for re-registration.
+                 */
+                if (process_fadump(fdm_active) < 0)
+                        fadump_invalidate_release_mem();
+        }
+        /* Initialize the kernel dump memory structure for FAD registration. */
+        else if (fw_dump.reserve_dump_area_size)
+                init_fadump_mem_struct(&fdm, fw_dump.reserve_dump_area_start);
+        fadump_init_files();
+
+        return 1;
+}
+subsys_initcall(setup_fadump);
diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_32.S
index 0654dba2c1f1..dc0488b6f6e1 100644
--- a/arch/powerpc/kernel/head_32.S
+++ b/arch/powerpc/kernel/head_32.S
@@ -395,7 +395,7 @@ DataAccess:
         bl      hash_page
 1:      lwz     r5,_DSISR(r11)          /* get DSISR value */
         mfspr   r4,SPRN_DAR
-        EXC_XFER_EE_LITE(0x300, handle_page_fault)
+        EXC_XFER_LITE(0x300, handle_page_fault)
 
 
 /* Instruction access exception. */
@@ -410,7 +410,7 @@ InstructionAccess:
         bl      hash_page
 1:      mr      r4,r12
         mr      r5,r9
-        EXC_XFER_EE_LITE(0x400, handle_page_fault)
+        EXC_XFER_LITE(0x400, handle_page_fault)
 
 /* External interrupt */
         EXCEPTION(0x500, HardwareInterrupt, do_IRQ, EXC_XFER_LITE)
diff --git a/arch/powerpc/kernel/head_40x.S b/arch/powerpc/kernel/head_40x.S
index 872a6af83bad..4989661b710b 100644
--- a/arch/powerpc/kernel/head_40x.S
+++ b/arch/powerpc/kernel/head_40x.S
@@ -394,7 +394,7 @@ label:
         NORMAL_EXCEPTION_PROLOG
         mr      r4,r12                  /* Pass SRR0 as arg2 */
         li      r5,0                    /* Pass zero as arg3 */
-        EXC_XFER_EE_LITE(0x400, handle_page_fault)
+        EXC_XFER_LITE(0x400, handle_page_fault)
 
 /* 0x0500 - External Interrupt Exception */
         EXCEPTION(0x0500, HardwareInterrupt, do_IRQ, EXC_XFER_LITE)
@@ -747,7 +747,7 @@ DataAccess:
         mfspr   r5,SPRN_ESR             /* Grab the ESR, save it, pass arg3 */
         stw     r5,_ESR(r11)
         mfspr   r4,SPRN_DEAR            /* Grab the DEAR, save it, pass arg2 */
-        EXC_XFER_EE_LITE(0x300, handle_page_fault)
+        EXC_XFER_LITE(0x300, handle_page_fault)
 
 /* Other PowerPC processors, namely those derived from the 6xx-series
  * have vectors from 0x2100 through 0x2F00 defined, but marked as reserved.
diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S
index 06c7251c1bf7..58bddee8e1e8 100644
--- a/arch/powerpc/kernel/head_64.S
+++ b/arch/powerpc/kernel/head_64.S
@@ -32,13 +32,13 @@
 #include <asm/cputable.h>
 #include <asm/setup.h>
 #include <asm/hvcall.h>
-#include <asm/iseries/lpar_map.h>
 #include <asm/thread_info.h>
 #include <asm/firmware.h>
 #include <asm/page_64.h>
 #include <asm/irqflags.h>
 #include <asm/kvm_book3s_asm.h>
 #include <asm/ptrace.h>
+#include <asm/hw_irq.h>
 
 /* The physical memory is laid out such that the secondary processor
  * spin code sits at 0x0000...0x00ff. On server, the vectors follow
@@ -57,10 +57,6 @@
  *      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)
- *   2. The kernel is entered at system_reset_iSeries
- *
  *  For Book3E processors:
  *   1. The MMU is on running in AS0 in a state defined in ePAPR
  *   2. The kernel is entered at __start
@@ -93,15 +89,6 @@ __secondary_hold_spinloop:
 __secondary_hold_acknowledge:
         .llong  0x0
 
-#ifdef CONFIG_PPC_ISERIES
-        /*
-         * At offset 0x20, there is a pointer to iSeries LPAR data.
-         * This is required by the hypervisor
-         */
-        . = 0x20
-        .llong hvReleaseData-KERNELBASE
-#endif /* CONFIG_PPC_ISERIES */
-
 #ifdef CONFIG_RELOCATABLE
         /* This flag is set to 1 by a loader if the kernel should run
          * at the loaded address instead of the linked address.  This
@@ -564,7 +551,8 @@ _GLOBAL(pmac_secondary_start)
          */
         li      r0,0
         stb     r0,PACASOFTIRQEN(r13)
-        stb     r0,PACAHARDIRQEN(r13)
+        li      r0,PACA_IRQ_HARD_DIS
+        stb     r0,PACAIRQHAPPENED(r13)
 
         /* Create a temp kernel stack for use before relocation is on.  */
         ld      r1,PACAEMERGSP(r13)
@@ -582,7 +570,7 @@ _GLOBAL(pmac_secondary_start)
  *   1. Processor number
  *   2. Segment table pointer (virtual address)
  * On entry the following are set:
- *   r1        = stack pointer.  vaddr for iSeries, raddr (temp stack) for pSeries
+ *   r1        = stack pointer (real addr of temp stack)
  *   r24       = cpu# (in Linux terms)
  *   r13       = paca virtual address
  *   SPRG_PACA = paca virtual address
@@ -595,7 +583,7 @@ __secondary_start:
         /* Set thread priority to MEDIUM */
         HMT_MEDIUM
 
-        /* Initialize the kernel stack.  Just a repeat for iSeries.      */
+        /* Initialize the kernel stack */
         LOAD_REG_ADDR(r3, current_set)
         sldi    r28,r24,3               /* get current_set[cpu#]         */
         ldx     r14,r3,r28
@@ -615,20 +603,16 @@ __secondary_start:
         li      r7,0
         mtlr    r7
 
+        /* Mark interrupts soft and hard disabled (they might be enabled
+         * in the PACA when doing hotplug)
+         */
+        stb     r7,PACASOFTIRQEN(r13)
+        li      r0,PACA_IRQ_HARD_DIS
+        stb     r0,PACAIRQHAPPENED(r13)
+
         /* enable MMU and jump to start_secondary */
         LOAD_REG_ADDR(r3, .start_secondary_prolog)
         LOAD_REG_IMMEDIATE(r4, MSR_KERNEL)
-#ifdef CONFIG_PPC_ISERIES
-BEGIN_FW_FTR_SECTION
-        ori     r4,r4,MSR_EE
-        li      r8,1
-        stb     r8,PACAHARDIRQEN(r13)
-END_FW_FTR_SECTION_IFSET(FW_FEATURE_ISERIES)
-#endif
-BEGIN_FW_FTR_SECTION
-        stb     r7,PACAHARDIRQEN(r13)
-END_FW_FTR_SECTION_IFCLR(FW_FEATURE_ISERIES)
-        stb     r7,PACASOFTIRQEN(r13)
 
         mtspr   SPRN_SRR0,r3
         mtspr   SPRN_SRR1,r4
@@ -771,22 +755,18 @@ _INIT_GLOBAL(start_here_common)
         /* Load the TOC (virtual address) */
         ld      r2,PACATOC(r13)
 
+        /* Do more system initializations in virtual mode */
         bl      .setup_system
 
-        /* Load up the kernel context */
-5:
-        li      r5,0
-        stb     r5,PACASOFTIRQEN(r13)   /* Soft Disabled */
-#ifdef CONFIG_PPC_ISERIES
-BEGIN_FW_FTR_SECTION
-        mfmsr   r5
-        ori     r5,r5,MSR_EE            /* Hard Enabled on iSeries*/
-        mtmsrd  r5
-        li      r5,1
-END_FW_FTR_SECTION_IFSET(FW_FEATURE_ISERIES)
-#endif
-        stb     r5,PACAHARDIRQEN(r13)   /* Hard Disabled on others */
+        /* Mark interrupts soft and hard disabled (they might be enabled
+         * in the PACA when doing hotplug)
+         */
+        li      r0,0
+        stb     r0,PACASOFTIRQEN(r13)
+        li      r0,PACA_IRQ_HARD_DIS
+        stb     r0,PACAIRQHAPPENED(r13)
 
+        /* Generic kernel entry */
         bl      .start_kernel
 
         /* Not reached */
diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S
index b68cb173ba2c..b2a5860accfb 100644
--- a/arch/powerpc/kernel/head_8xx.S
+++ b/arch/powerpc/kernel/head_8xx.S
@@ -220,7 +220,7 @@ DataAccess:
         mfspr   r4,SPRN_DAR
         li      r10,0x00f0
         mtspr   SPRN_DAR,r10    /* Tag DAR, to be used in DTLB Error */
-        EXC_XFER_EE_LITE(0x300, handle_page_fault)
+        EXC_XFER_LITE(0x300, handle_page_fault)
 
 /* Instruction access exception.
  * This is "never generated" by the MPC8xx.  We jump to it for other
@@ -231,7 +231,7 @@ InstructionAccess:
         EXCEPTION_PROLOG
         mr      r4,r12
         mr      r5,r9
-        EXC_XFER_EE_LITE(0x400, handle_page_fault)
+        EXC_XFER_LITE(0x400, handle_page_fault)
 
 /* External interrupt */
         EXCEPTION(0x500, HardwareInterrupt, do_IRQ, EXC_XFER_LITE)
diff --git a/arch/powerpc/kernel/head_booke.h b/arch/powerpc/kernel/head_booke.h
index fc921bf62e15..0e4175388f47 100644
--- a/arch/powerpc/kernel/head_booke.h
+++ b/arch/powerpc/kernel/head_booke.h
@@ -359,7 +359,7 @@ label:
         mfspr   r5,SPRN_ESR;            /* Grab the ESR and save it */        \
         stw     r5,_ESR(r11);                                                 \
         mfspr   r4,SPRN_DEAR;           /* Grab the DEAR */                   \
-        EXC_XFER_EE_LITE(0x0300, handle_page_fault)
+        EXC_XFER_LITE(0x0300, handle_page_fault)
 
 #define INSTRUCTION_STORAGE_EXCEPTION                                         \
         START_EXCEPTION(InstructionStorage)                                   \
@@ -368,7 +368,7 @@ label:
         stw     r5,_ESR(r11);                                                 \
         mr      r4,r12;                 /* Pass SRR0 as arg2 */               \
         li      r5,0;                   /* Pass zero as arg3 */               \
-        EXC_XFER_EE_LITE(0x0400, handle_page_fault)
+        EXC_XFER_LITE(0x0400, handle_page_fault)
 
 #define ALIGNMENT_EXCEPTION                                                   \
         START_EXCEPTION(Alignment)                                            \
diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S
index d5d78c4ceef6..28e62598d0e8 100644
--- a/arch/powerpc/kernel/head_fsl_booke.S
+++ b/arch/powerpc/kernel/head_fsl_booke.S
@@ -319,7 +319,7 @@ interrupt_base:
         mfspr   r4,SPRN_DEAR            /* Grab the DEAR, save it, pass arg2 */
         andis.  r10,r5,(ESR_ILK|ESR_DLK)@h
         bne     1f
-        EXC_XFER_EE_LITE(0x0300, handle_page_fault)
+        EXC_XFER_LITE(0x0300, handle_page_fault)
 1:
         addi    r3,r1,STACK_FRAME_OVERHEAD
         EXC_XFER_EE_LITE(0x0300, CacheLockingException)
diff --git a/arch/powerpc/kernel/ibmebus.c b/arch/powerpc/kernel/ibmebus.c
index d39ae606ff8d..79bb282e6501 100644
--- a/arch/powerpc/kernel/ibmebus.c
+++ b/arch/powerpc/kernel/ibmebus.c
@@ -713,7 +713,7 @@ static struct dev_pm_ops ibmebus_bus_dev_pm_ops = {
 
 struct bus_type ibmebus_bus_type = {
         .name      = "ibmebus",
-        .uevent    = of_device_uevent,
+        .uevent    = of_device_uevent_modalias,
         .bus_attrs = ibmebus_bus_attrs,
         .match     = ibmebus_bus_bus_match,
         .probe     = ibmebus_bus_device_probe,
diff --git a/arch/powerpc/kernel/idle.c b/arch/powerpc/kernel/idle.c
index 0a48bf5db6c8..e8e821146f38 100644
--- a/arch/powerpc/kernel/idle.c
+++ b/arch/powerpc/kernel/idle.c
@@ -84,7 +84,11 @@ void cpu_idle(void)
 
                                 start_critical_timings();
 
-                                local_irq_enable();
+                                /* Some power_save functions return with
+                                 * interrupts enabled, some don't.
+                                 */
+                                if (irqs_disabled())
+                                        local_irq_enable();
                                 set_thread_flag(TIF_POLLING_NRFLAG);
 
                         } else {
@@ -101,11 +105,11 @@ void cpu_idle(void)
                 ppc64_runlatch_on();
                 rcu_idle_exit();
                 tick_nohz_idle_exit();
-                preempt_enable_no_resched();
-                if (cpu_should_die())
+                if (cpu_should_die()) {
+                        sched_preempt_enable_no_resched();
                         cpu_die();
-                schedule();
-                preempt_disable();
+                }
+                schedule_preempt_disabled();
         }
 }
 
diff --git a/arch/powerpc/kernel/idle_book3e.S b/arch/powerpc/kernel/idle_book3e.S
index 16c002d6bdf1..ff007b59448d 100644
--- a/arch/powerpc/kernel/idle_book3e.S
+++ b/arch/powerpc/kernel/idle_book3e.S
@@ -29,43 +29,30 @@ _GLOBAL(book3e_idle)
         wrteei  0
 
         /* Now check if an interrupt came in while we were soft disabled
-         * since we may otherwise lose it (doorbells etc...). We know
-         * that since PACAHARDIRQEN will have been cleared in that case.
+         * since we may otherwise lose it (doorbells etc...).
          */
-        lbz     r3,PACAHARDIRQEN(r13)
+        lbz     r3,PACAIRQHAPPENED(r13)
         cmpwi   cr0,r3,0
-        beqlr
+        bnelr
 
-        /* Now we are going to mark ourselves as soft and hard enables in
+        /* Now we are going to mark ourselves as soft and hard enabled in
          * order to be able to take interrupts while asleep. We inform lockdep
          * of that. We don't actually turn interrupts on just yet tho.
          */
 #ifdef CONFIG_TRACE_IRQFLAGS
         stdu    r1,-128(r1)
         bl      .trace_hardirqs_on
+        addi    r1,r1,128
 #endif
         li      r0,1
         stb     r0,PACASOFTIRQEN(r13)
-        stb     r0,PACAHARDIRQEN(r13)
         
         /* Interrupts will make use return to LR, so get something we want
          * in there
          */
         bl      1f
 
-        /* Hard disable interrupts again */
-        wrteei  0
-
-        /* Mark them off again in the PACA as well */
-        li      r0,0
-        stb     r0,PACASOFTIRQEN(r13)
-        stb     r0,PACAHARDIRQEN(r13)
-
-        /* Tell lockdep about it */
-#ifdef CONFIG_TRACE_IRQFLAGS
-        bl      .trace_hardirqs_off
-        addi    r1,r1,128
-#endif
+        /* And return (interrupts are on) */
         ld      r0,16(r1)
         mtlr    r0
         blr
diff --git a/arch/powerpc/kernel/idle_power4.S b/arch/powerpc/kernel/idle_power4.S
index ba3195478600..2c71b0fc9f91 100644
--- a/arch/powerpc/kernel/idle_power4.S
+++ b/arch/powerpc/kernel/idle_power4.S
@@ -14,6 +14,7 @@
 #include <asm/thread_info.h>
 #include <asm/ppc_asm.h>
 #include <asm/asm-offsets.h>
+#include <asm/irqflags.h>
 
 #undef DEBUG
 
@@ -29,14 +30,31 @@ END_FTR_SECTION_IFCLR(CPU_FTR_CAN_NAP)
         cmpwi   0,r4,0
         beqlr
 
-        /* Go to NAP now */
+        /* Hard disable interrupts */
         mfmsr   r7
         rldicl  r0,r7,48,1
         rotldi  r0,r0,16
-        mtmsrd  r0,1                    /* hard-disable interrupts */
+        mtmsrd  r0,1
+
+        /* Check if something happened while soft-disabled */
+        lbz     r0,PACAIRQHAPPENED(r13)
+        cmpwi   cr0,r0,0
+        bnelr
+
+        /* Soft-enable interrupts */
+#ifdef CONFIG_TRACE_IRQFLAGS
+        mflr    r0
+        std     r0,16(r1)
+        stdu    r1,-128(r1)
+        bl      .trace_hardirqs_on
+        addi    r1,r1,128
+        ld      r0,16(r1)
+        mtlr    r0
+        mfmsr   r7
+#endif /* CONFIG_TRACE_IRQFLAGS */
+
         li      r0,1
         stb     r0,PACASOFTIRQEN(r13)   /* we'll hard-enable shortly */
-        stb     r0,PACAHARDIRQEN(r13)
 BEGIN_FTR_SECTION
         DSSALL
         sync
diff --git a/arch/powerpc/kernel/idle_power7.S b/arch/powerpc/kernel/idle_power7.S
index fcdff198da4b..0cdc9a392839 100644
--- a/arch/powerpc/kernel/idle_power7.S
+++ b/arch/powerpc/kernel/idle_power7.S
@@ -1,5 +1,5 @@
 /*
- *  This file contains the power_save function for 970-family CPUs.
+ *  This file contains the power_save function for Power7 CPUs.
  *
  *  This program is free software; you can redistribute it and/or
  *  modify it under the terms of the GNU General Public License
@@ -15,6 +15,7 @@
 #include <asm/ppc_asm.h>
 #include <asm/asm-offsets.h>
 #include <asm/ppc-opcode.h>
+#include <asm/hw_irq.h>
 
 #undef DEBUG
 
@@ -51,9 +52,25 @@ _GLOBAL(power7_idle)
         rldicl  r9,r9,48,1
         rotldi  r9,r9,16
         mtmsrd  r9,1                    /* hard-disable interrupts */
+
+        /* Check if something happened while soft-disabled */
+        lbz     r0,PACAIRQHAPPENED(r13)
+        cmpwi   cr0,r0,0
+        beq     1f
+        addi    r1,r1,INT_FRAME_SIZE
+        ld      r0,16(r1)
+        mtlr    r0
+        blr
+
+1:      /* We mark irqs hard disabled as this is the state we'll
+         * be in when returning and we need to tell arch_local_irq_restore()
+         * about it
+         */
+        li      r0,PACA_IRQ_HARD_DIS
+        stb     r0,PACAIRQHAPPENED(r13)
+
+        /* We haven't lost state ... yet */
         li      r0,0
-        stb     r0,PACASOFTIRQEN(r13)   /* we'll hard-enable shortly */
-        stb     r0,PACAHARDIRQEN(r13)
         stb     r0,PACA_NAPSTATELOST(r13)
 
         /* Continue saving state */
diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index 0cfcf98aafca..359f078571c7 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -39,6 +39,7 @@
 #include <asm/pci-bridge.h>
 #include <asm/machdep.h>
 #include <asm/kdump.h>
+#include <asm/fadump.h>
 
 #define DBG(...)
 
@@ -445,7 +446,12 @@ void iommu_unmap_sg(struct iommu_table *tbl, struct scatterlist *sglist,
 
 static void iommu_table_clear(struct iommu_table *tbl)
 {
-        if (!is_kdump_kernel()) {
+        /*
+         * In case of firmware assisted dump system goes through clean
+         * reboot process at the time of system crash. Hence it's safe to
+         * clear the TCE entries if firmware assisted dump is active.
+         */
+        if (!is_kdump_kernel() || is_fadump_active()) {
                 /* Clear the table in case firmware left allocations in it */
                 ppc_md.tce_free(tbl, tbl->it_offset, tbl->it_size);
                 return;
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 701d4aceb4f4..cea2d9f3ae4e 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -93,20 +93,16 @@ extern int tau_interrupts(int);
 
 #ifdef CONFIG_PPC64
 
-#ifndef CONFIG_SPARSE_IRQ
-EXPORT_SYMBOL(irq_desc);
-#endif
-
 int distribute_irqs = 1;
 
-static inline notrace unsigned long get_hard_enabled(void)
+static inline notrace unsigned long get_irq_happened(void)
 {
-        unsigned long enabled;
+        unsigned long happened;
 
         __asm__ __volatile__("lbz %0,%1(13)"
-        : "=r" (enabled) : "i" (offsetof(struct paca_struct, hard_enabled)));
+        : "=r" (happened) : "i" (offsetof(struct paca_struct, irq_happened)));
 
-        return enabled;
+        return happened;
 }
 
 static inline notrace void set_soft_enabled(unsigned long enable)
@@ -115,84 +111,162 @@ static inline notrace void set_soft_enabled(unsigned long enable)
         : : "r" (enable), "i" (offsetof(struct paca_struct, soft_enabled)));
 }
 
-static inline notrace void decrementer_check_overflow(void)
+static inline notrace int decrementer_check_overflow(void)
 {
-        u64 now = get_tb_or_rtc();
-        u64 *next_tb = &__get_cpu_var(decrementers_next_tb);
-
+        u64 now = get_tb_or_rtc();
+        u64 *next_tb = &__get_cpu_var(decrementers_next_tb);
+ 
         if (now >= *next_tb)
                 set_dec(1);
+        return now >= *next_tb;
 }
 
-notrace void arch_local_irq_restore(unsigned long en)
+/* This is called whenever we are re-enabling interrupts
+ * and returns either 0 (nothing to do) or 500/900 if there's
+ * either an EE or a DEC to generate.
+ *
+ * This is called in two contexts: From arch_local_irq_restore()
+ * before soft-enabling interrupts, and from the exception exit
+ * path when returning from an interrupt from a soft-disabled to
+ * a soft enabled context. In both case we have interrupts hard
+ * disabled.
+ *
+ * We take care of only clearing the bits we handled in the
+ * PACA irq_happened field since we can only re-emit one at a
+ * time and we don't want to "lose" one.
+ */
+notrace unsigned int __check_irq_replay(void)
 {
         /*
-         * get_paca()->soft_enabled = en;
-         * Is it ever valid to use local_irq_restore(0) when soft_enabled is 1?
-         * That was allowed before, and in such a case we do need to take care
-         * that gcc will set soft_enabled directly via r13, not choose to use
-         * an intermediate register, lest we're preempted to a different cpu.
+         * We use local_paca rather than get_paca() to avoid all
+         * the debug_smp_processor_id() business in this low level
+         * function
          */
-        set_soft_enabled(en);
-        if (!en)
-                return;
+        unsigned char happened = local_paca->irq_happened;
 
-#ifdef CONFIG_PPC_STD_MMU_64
-        if (firmware_has_feature(FW_FEATURE_ISERIES)) {
-                /*
-                 * Do we need to disable preemption here?  Not really: in the
-                 * unlikely event that we're preempted to a different cpu in
-                 * between getting r13, loading its lppaca_ptr, and loading
-                 * its any_int, we might call iseries_handle_interrupts without
-                 * an interrupt pending on the new cpu, but that's no disaster,
-                 * is it?  And the business of preempting us off the old cpu
-                 * would itself involve a local_irq_restore which handles the
-                 * interrupt to that cpu.
-                 *
-                 * But use "local_paca->lppaca_ptr" instead of "get_lppaca()"
-                 * to avoid any preemption checking added into get_paca().
-                 */
-                if (local_paca->lppaca_ptr->int_dword.any_int)
-                        iseries_handle_interrupts();
+        /* Clear bit 0 which we wouldn't clear otherwise */
+        local_paca->irq_happened &= ~PACA_IRQ_HARD_DIS;
+
+        /*
+         * Force the delivery of pending soft-disabled interrupts on PS3.
+         * Any HV call will have this side effect.
+         */
+        if (firmware_has_feature(FW_FEATURE_PS3_LV1)) {
+                u64 tmp, tmp2;
+                lv1_get_version_info(&tmp, &tmp2);
         }
-#endif /* CONFIG_PPC_STD_MMU_64 */
 
         /*
-         * if (get_paca()->hard_enabled) return;
-         * But again we need to take care that gcc gets hard_enabled directly
-         * via r13, not choose to use an intermediate register, lest we're
-         * preempted to a different cpu in between the two instructions.
+         * We may have missed a decrementer interrupt. We check the
+         * decrementer itself rather than the paca irq_happened field
+         * in case we also had a rollover while hard disabled
+         */
+        local_paca->irq_happened &= ~PACA_IRQ_DEC;
+        if (decrementer_check_overflow())
+                return 0x900;
+
+        /* Finally check if an external interrupt happened */
+        local_paca->irq_happened &= ~PACA_IRQ_EE;
+        if (happened & PACA_IRQ_EE)
+                return 0x500;
+
+#ifdef CONFIG_PPC_BOOK3E
+        /* Finally check if an EPR external interrupt happened
+         * this bit is typically set if we need to handle another
+         * "edge" interrupt from within the MPIC "EPR" handler
+         */
+        local_paca->irq_happened &= ~PACA_IRQ_EE_EDGE;
+        if (happened & PACA_IRQ_EE_EDGE)
+                return 0x500;
+
+        local_paca->irq_happened &= ~PACA_IRQ_DBELL;
+        if (happened & PACA_IRQ_DBELL)
+                return 0x280;
+#endif /* CONFIG_PPC_BOOK3E */
+
+        /* There should be nothing left ! */
+        BUG_ON(local_paca->irq_happened != 0);
+
+        return 0;
+}
+
+notrace void arch_local_irq_restore(unsigned long en)
+{
+        unsigned char irq_happened;
+        unsigned int replay;
+
+        /* Write the new soft-enabled value */
+        set_soft_enabled(en);
+        if (!en)
+                return;
+        /*
+         * From this point onward, we can take interrupts, preempt,
+         * etc... unless we got hard-disabled. We check if an event
+         * happened. If none happened, we know we can just return.
+         *
+         * We may have preempted before the check below, in which case
+         * we are checking the "new" CPU instead of the old one. This
+         * is only a problem if an event happened on the "old" CPU.
+         *
+         * External interrupt events will have caused interrupts to
+         * be hard-disabled, so there is no problem, we
+         * cannot have preempted.
          */
-        if (get_hard_enabled())
+        irq_happened = get_irq_happened();
+        if (!irq_happened)
                 return;
 
         /*
-         * Need to hard-enable interrupts here.  Since currently disabled,
-         * no need to take further asm precautions against preemption; but
-         * use local_paca instead of get_paca() to avoid preemption checking.
+         * We need to hard disable to get a trusted value from
+         * __check_irq_replay(). We also need to soft-disable
+         * again to avoid warnings in there due to the use of
+         * per-cpu variables.
+         *
+         * We know that if the value in irq_happened is exactly 0x01
+         * then we are already hard disabled (there are other less
+         * common cases that we'll ignore for now), so we skip the
+         * (expensive) mtmsrd.
          */
-        local_paca->hard_enabled = en;
+        if (unlikely(irq_happened != PACA_IRQ_HARD_DIS))
+                __hard_irq_disable();
+        set_soft_enabled(0);
 
         /*
-         * Trigger the decrementer if we have a pending event. Some processors
-         * only trigger on edge transitions of the sign bit. We might also
-         * have disabled interrupts long enough that the decrementer wrapped
-         * to positive.
+         * Check if anything needs to be re-emitted. We haven't
+         * soft-enabled yet to avoid warnings in decrementer_check_overflow
+         * accessing per-cpu variables
          */
-        decrementer_check_overflow();
+        replay = __check_irq_replay();
+
+        /* We can soft-enable now */
+        set_soft_enabled(1);
 
         /*
-         * Force the delivery of pending soft-disabled interrupts on PS3.
-         * Any HV call will have this side effect.
+         * And replay if we have to. This will return with interrupts
+         * hard-enabled.
          */
-        if (firmware_has_feature(FW_FEATURE_PS3_LV1)) {
-                u64 tmp, tmp2;
-                lv1_get_version_info(&tmp, &tmp2);
+        if (replay) {
+                __replay_interrupt(replay);
+                return;
         }
 
+        /* Finally, let's ensure we are hard enabled */
         __hard_irq_enable();
 }
 EXPORT_SYMBOL(arch_local_irq_restore);
+
+/*
+ * This is specifically called by assembly code to re-enable interrupts
+ * if they are currently disabled. This is typically called before
+ * schedule() or do_signal() when returning to userspace. We do it
+ * in C to avoid the burden of dealing with lockdep etc...
+ */
+void restore_interrupts(void)
+{
+        if (irqs_disabled())
+                local_irq_enable();
+}
+
 #endif /* CONFIG_PPC64 */
 
 int arch_show_interrupts(struct seq_file *p, int prec)
@@ -360,25 +434,25 @@ void do_IRQ(struct pt_regs *regs)
 
         check_stack_overflow();
 
+        /*
+         * Query the platform PIC for the interrupt & ack it.
+         *
+         * This will typically lower the interrupt line to the CPU
+         */
         irq = ppc_md.get_irq();
 
-        if (irq != NO_IRQ && irq != NO_IRQ_IGNORE)
+        /* We can hard enable interrupts now */
+        may_hard_irq_enable();
+
+        /* And finally process it */
+        if (irq != NO_IRQ)
                 handle_one_irq(irq);
-        else if (irq != NO_IRQ_IGNORE)
+        else
                 __get_cpu_var(irq_stat).spurious_irqs++;
 
         irq_exit();
         set_irq_regs(old_regs);
 
-#ifdef CONFIG_PPC_ISERIES
-        if (firmware_has_feature(FW_FEATURE_ISERIES) &&
-                        get_lppaca()->int_dword.fields.decr_int) {
-                get_lppaca()->int_dword.fields.decr_int = 0;
-                /* Signal a fake decrementer interrupt */
-                timer_interrupt(regs);
-        }
-#endif
-
         trace_irq_exit(regs);
 }
 
@@ -486,409 +560,19 @@ void do_softirq(void)
         local_irq_restore(flags);
 }
 
-
-/*
- * IRQ controller and virtual interrupts
- */
-
-/* The main irq map itself is an array of NR_IRQ entries containing the
- * associate host and irq number. An entry with a host of NULL is free.
- * An entry can be allocated if it's free, the allocator always then sets
- * hwirq first to the host's invalid irq number and then fills ops.
- */
-struct irq_map_entry {
-        irq_hw_number_t hwirq;
-        struct irq_host *host;
-};
-
-static LIST_HEAD(irq_hosts);
-static DEFINE_RAW_SPINLOCK(irq_big_lock);
-static DEFINE_MUTEX(revmap_trees_mutex);
-static struct irq_map_entry irq_map[NR_IRQS];
-static unsigned int irq_virq_count = NR_IRQS;
-static struct irq_host *irq_default_host;
-
 irq_hw_number_t irqd_to_hwirq(struct irq_data *d)
 {
-        return irq_map[d->irq].hwirq;
+        return d->hwirq;
 }
 EXPORT_SYMBOL_GPL(irqd_to_hwirq);
 
 irq_hw_number_t virq_to_hw(unsigned int virq)
 {
-        return irq_map[virq].hwirq;
+        struct irq_data *irq_data = irq_get_irq_data(virq);
+        return WARN_ON(!irq_data) ? 0 : irq_data->hwirq;
 }
 EXPORT_SYMBOL_GPL(virq_to_hw);
 
-bool virq_is_host(unsigned int virq, struct irq_host *host)
-{
-        return irq_map[virq].host == host;
-}
-EXPORT_SYMBOL_GPL(virq_is_host);
-
-static int default_irq_host_match(struct irq_host *h, struct device_node *np)
-{
-        return h->of_node != NULL && h->of_node == np;
-}
-
-struct irq_host *irq_alloc_host(struct device_node *of_node,
-                                unsigned int revmap_type,
-                                unsigned int revmap_arg,
-                                struct irq_host_ops *ops,
-                                irq_hw_number_t inval_irq)
-{
-        struct irq_host *host;
-        unsigned int size = sizeof(struct irq_host);
-        unsigned int i;
-        unsigned int *rmap;
-        unsigned long flags;
-
-        /* Allocate structure and revmap table if using linear mapping */
-        if (revmap_type == IRQ_HOST_MAP_LINEAR)
-                size += revmap_arg * sizeof(unsigned int);
-        host = kzalloc(size, GFP_KERNEL);
-        if (host == NULL)
-                return NULL;
-
-        /* Fill structure */
-        host->revmap_type = revmap_type;
-        host->inval_irq = inval_irq;
-        host->ops = ops;
-        host->of_node = of_node_get(of_node);
-
-        if (host->ops->match == NULL)
-                host->ops->match = default_irq_host_match;
-
-        raw_spin_lock_irqsave(&irq_big_lock, flags);
-
-        /* If it's a legacy controller, check for duplicates and
-         * mark it as allocated (we use irq 0 host pointer for that
-         */
-        if (revmap_type == IRQ_HOST_MAP_LEGACY) {
-                if (irq_map[0].host != NULL) {
-                        raw_spin_unlock_irqrestore(&irq_big_lock, flags);
-                        of_node_put(host->of_node);
-                        kfree(host);
-                        return NULL;
-                }
-                irq_map[0].host = host;
-        }
-
-        list_add(&host->link, &irq_hosts);
-        raw_spin_unlock_irqrestore(&irq_big_lock, flags);
-
-        /* Additional setups per revmap type */
-        switch(revmap_type) {
-        case IRQ_HOST_MAP_LEGACY:
-                /* 0 is always the invalid number for legacy */
-                host->inval_irq = 0;
-                /* setup us as the host for all legacy interrupts */
-                for (i = 1; i < NUM_ISA_INTERRUPTS; i++) {
-                        irq_map[i].hwirq = i;
-                        smp_wmb();
-                        irq_map[i].host = host;
-                        smp_wmb();
-
-                        /* Legacy flags are left to default at this point,
-                         * one can then use irq_create_mapping() to
-                         * explicitly change them
-                         */
-                        ops->map(host, i, i);
-
-                        /* Clear norequest flags */
-                        irq_clear_status_flags(i, IRQ_NOREQUEST);
-                }
-                break;
-        case IRQ_HOST_MAP_LINEAR:
-                rmap = (unsigned int *)(host + 1);
-                for (i = 0; i < revmap_arg; i++)
-                        rmap[i] = NO_IRQ;
-                host->revmap_data.linear.size = revmap_arg;
-                smp_wmb();
-                host->revmap_data.linear.revmap = rmap;
-                break;
-        case IRQ_HOST_MAP_TREE:
-                INIT_RADIX_TREE(&host->revmap_data.tree, GFP_KERNEL);
-                break;
-        default:
-                break;
-        }
-
-        pr_debug("irq: Allocated host of type %d @0x%p\n", revmap_type, host);
-
-        return host;
-}
-
-struct irq_host *irq_find_host(struct device_node *node)
-{
-        struct irq_host *h, *found = NULL;
-        unsigned long flags;
-
-        /* We might want to match the legacy controller last since
-         * it might potentially be set to match all interrupts in
-         * the absence of a device node. This isn't a problem so far
-         * yet though...
-         */
-        raw_spin_lock_irqsave(&irq_big_lock, flags);
-        list_for_each_entry(h, &irq_hosts, link)
-                if (h->ops->match(h, node)) {
-                        found = h;
-                        break;
-                }
-        raw_spin_unlock_irqrestore(&irq_big_lock, flags);
-        return found;
-}
-EXPORT_SYMBOL_GPL(irq_find_host);
-
-void irq_set_default_host(struct irq_host *host)
-{
-        pr_debug("irq: Default host set to @0x%p\n", host);
-
-        irq_default_host = host;
-}
-
-void irq_set_virq_count(unsigned int count)
-{
-        pr_debug("irq: Trying to set virq count to %d\n", count);
-
-        BUG_ON(count < NUM_ISA_INTERRUPTS);
-        if (count < NR_IRQS)
-                irq_virq_count = count;
-}
-
-static int irq_setup_virq(struct irq_host *host, unsigned int virq,
-                            irq_hw_number_t hwirq)
-{
-        int res;
-
-        res = irq_alloc_desc_at(virq, 0);
-        if (res != virq) {
-                pr_debug("irq: -> allocating desc failed\n");
-                goto error;
-        }
-
-        /* map it */
-        smp_wmb();
-        irq_map[virq].hwirq = hwirq;
-        smp_mb();
-
-        if (host->ops->map(host, virq, hwirq)) {
-                pr_debug("irq: -> mapping failed, freeing\n");
-                goto errdesc;
-        }
-
-        irq_clear_status_flags(virq, IRQ_NOREQUEST);
-
-        return 0;
-
-errdesc:
-        irq_free_descs(virq, 1);
-error:
-        irq_free_virt(virq, 1);
-        return -1;
-}
-
-unsigned int irq_create_direct_mapping(struct irq_host *host)
-{
-        unsigned int virq;
-
-        if (host == NULL)
-                host = irq_default_host;
-
-        BUG_ON(host == NULL);
-        WARN_ON(host->revmap_type != IRQ_HOST_MAP_NOMAP);
-
-        virq = irq_alloc_virt(host, 1, 0);
-        if (virq == NO_IRQ) {
-                pr_debug("irq: create_direct virq allocation failed\n");
-                return NO_IRQ;
-        }
-
-        pr_debug("irq: create_direct obtained virq %d\n", virq);
-
-        if (irq_setup_virq(host, virq, virq))
-                return NO_IRQ;
-
-        return virq;
-}
-
-unsigned int irq_create_mapping(struct irq_host *host,
-                                irq_hw_number_t hwirq)
-{
-        unsigned int virq, hint;
-
-        pr_debug("irq: irq_create_mapping(0x%p, 0x%lx)\n", host, hwirq);
-
-        /* Look for default host if nececssary */
-        if (host == NULL)
-                host = irq_default_host;
-        if (host == NULL) {
-                printk(KERN_WARNING "irq_create_mapping called for"
-                       " NULL host, hwirq=%lx\n", hwirq);
-                WARN_ON(1);
-                return NO_IRQ;
-        }
-        pr_debug("irq: -> using host @%p\n", host);
-
-        /* Check if mapping already exists */
-        virq = irq_find_mapping(host, hwirq);
-        if (virq != NO_IRQ) {
-                pr_debug("irq: -> existing mapping on virq %d\n", virq);
-                return virq;
-        }
-
-        /* Get a virtual interrupt number */
-        if (host->revmap_type == IRQ_HOST_MAP_LEGACY) {
-                /* Handle legacy */
-                virq = (unsigned int)hwirq;
-                if (virq == 0 || virq >= NUM_ISA_INTERRUPTS)
-                        return NO_IRQ;
-                return virq;
-        } else {
-                /* Allocate a virtual interrupt number */
-                hint = hwirq % irq_virq_count;
-                virq = irq_alloc_virt(host, 1, hint);
-                if (virq == NO_IRQ) {
-                        pr_debug("irq: -> virq allocation failed\n");
-                        return NO_IRQ;
-                }
-        }
-
-        if (irq_setup_virq(host, virq, hwirq))
-                return NO_IRQ;
-
-        pr_debug("irq: irq %lu on host %s mapped to virtual irq %u\n",
-                hwirq, host->of_node ? host->of_node->full_name : "null", virq);
-
-        return virq;
-}
-EXPORT_SYMBOL_GPL(irq_create_mapping);
-
-unsigned int irq_create_of_mapping(struct device_node *controller,
-                                   const u32 *intspec, unsigned int intsize)
-{
-        struct irq_host *host;
-        irq_hw_number_t hwirq;
-        unsigned int type = IRQ_TYPE_NONE;
-        unsigned int virq;
-
-        if (controller == NULL)
-                host = irq_default_host;
-        else
-                host = irq_find_host(controller);
-        if (host == NULL) {
-                printk(KERN_WARNING "irq: no irq host found for %s !\n",
-                       controller->full_name);
-                return NO_IRQ;
-        }
-
-        /* If host has no translation, then we assume interrupt line */
-        if (host->ops->xlate == NULL)
-                hwirq = intspec[0];
-        else {
-                if (host->ops->xlate(host, controller, intspec, intsize,
-                                     &hwirq, &type))
-                        return NO_IRQ;
-        }
-
-        /* Create mapping */
-        virq = irq_create_mapping(host, hwirq);
-        if (virq == NO_IRQ)
-                return virq;
-
-        /* Set type if specified and different than the current one */
-        if (type != IRQ_TYPE_NONE &&
-            type != (irqd_get_trigger_type(irq_get_irq_data(virq))))
-                irq_set_irq_type(virq, type);
-        return virq;
-}
-EXPORT_SYMBOL_GPL(irq_create_of_mapping);
-
-void irq_dispose_mapping(unsigned int virq)
-{
-        struct irq_host *host;
-        irq_hw_number_t hwirq;
-
-        if (virq == NO_IRQ)
-                return;
-
-        host = irq_map[virq].host;
-        if (WARN_ON(host == NULL))
-                return;
-
-        /* Never unmap legacy interrupts */
-        if (host->revmap_type == IRQ_HOST_MAP_LEGACY)
-                return;
-
-        irq_set_status_flags(virq, IRQ_NOREQUEST);
-
-        /* remove chip and handler */
-        irq_set_chip_and_handler(virq, NULL, NULL);
-
-        /* Make sure it's completed */
-        synchronize_irq(virq);
-
-        /* Tell the PIC about it */
-        if (host->ops->unmap)
-                host->ops->unmap(host, virq);
-        smp_mb();
-
-        /* Clear reverse map */
-        hwirq = irq_map[virq].hwirq;
-        switch(host->revmap_type) {
-        case IRQ_HOST_MAP_LINEAR:
-                if (hwirq < host->revmap_data.linear.size)
-                        host->revmap_data.linear.revmap[hwirq] = NO_IRQ;
-                break;
-        case IRQ_HOST_MAP_TREE:
-                mutex_lock(&revmap_trees_mutex);
-                radix_tree_delete(&host->revmap_data.tree, hwirq);
-                mutex_unlock(&revmap_trees_mutex);
-                break;
-        }
-
-        /* Destroy map */
-        smp_mb();
-        irq_map[virq].hwirq = host->inval_irq;
-
-        irq_free_descs(virq, 1);
-        /* Free it */
-        irq_free_virt(virq, 1);
-}
-EXPORT_SYMBOL_GPL(irq_dispose_mapping);
-
-unsigned int irq_find_mapping(struct irq_host *host,
-                              irq_hw_number_t hwirq)
-{
-        unsigned int i;
-        unsigned int hint = hwirq % irq_virq_count;
-
-        /* Look for default host if nececssary */
-        if (host == NULL)
-                host = irq_default_host;
-        if (host == NULL)
-                return NO_IRQ;
-
-        /* legacy -> bail early */
-        if (host->revmap_type == IRQ_HOST_MAP_LEGACY)
-                return hwirq;
-
-        /* Slow path does a linear search of the map */
-        if (hint < NUM_ISA_INTERRUPTS)
-                hint = NUM_ISA_INTERRUPTS;
-        i = hint;
-        do  {
-                if (irq_map[i].host == host &&
-                    irq_map[i].hwirq == hwirq)
-                        return i;
-                i++;
-                if (i >= irq_virq_count)
-                        i = NUM_ISA_INTERRUPTS;
-        } while(i != hint);
-        return NO_IRQ;
-}
-EXPORT_SYMBOL_GPL(irq_find_mapping);
-
 #ifdef CONFIG_SMP
 int irq_choose_cpu(const struct cpumask *mask)
 {
@@ -925,232 +609,11 @@ int irq_choose_cpu(const struct cpumask *mask)
 }
 #endif
 
-unsigned int irq_radix_revmap_lookup(struct irq_host *host,
-                                     irq_hw_number_t hwirq)
-{
-        struct irq_map_entry *ptr;
-        unsigned int virq;
-
-        if (WARN_ON_ONCE(host->revmap_type != IRQ_HOST_MAP_TREE))
-                return irq_find_mapping(host, hwirq);
-
-        /*
-         * The ptr returned references the static global irq_map.
-         * but freeing an irq can delete nodes along the path to
-         * do the lookup via call_rcu.
-         */
-        rcu_read_lock();
-        ptr = radix_tree_lookup(&host->revmap_data.tree, hwirq);
-        rcu_read_unlock();
-
-        /*
-         * If found in radix tree, then fine.
-         * Else fallback to linear lookup - this should not happen in practice
-         * as it means that we failed to insert the node in the radix tree.
-         */
-        if (ptr)
-                virq = ptr - irq_map;
-        else
-                virq = irq_find_mapping(host, hwirq);
-
-        return virq;
-}
-
-void irq_radix_revmap_insert(struct irq_host *host, unsigned int virq,
-                             irq_hw_number_t hwirq)
-{
-        if (WARN_ON(host->revmap_type != IRQ_HOST_MAP_TREE))
-                return;
-
-        if (virq != NO_IRQ) {
-                mutex_lock(&revmap_trees_mutex);
-                radix_tree_insert(&host->revmap_data.tree, hwirq,
-                                  &irq_map[virq]);
-                mutex_unlock(&revmap_trees_mutex);
-        }
-}
-
-unsigned int irq_linear_revmap(struct irq_host *host,
-                               irq_hw_number_t hwirq)
-{
-        unsigned int *revmap;
-
-        if (WARN_ON_ONCE(host->revmap_type != IRQ_HOST_MAP_LINEAR))
-                return irq_find_mapping(host, hwirq);
-
-        /* Check revmap bounds */
-        if (unlikely(hwirq >= host->revmap_data.linear.size))
-                return irq_find_mapping(host, hwirq);
-
-        /* Check if revmap was allocated */
-        revmap = host->revmap_data.linear.revmap;
-        if (unlikely(revmap == NULL))
-                return irq_find_mapping(host, hwirq);
-
-        /* Fill up revmap with slow path if no mapping found */
-        if (unlikely(revmap[hwirq] == NO_IRQ))
-                revmap[hwirq] = irq_find_mapping(host, hwirq);
-
-        return revmap[hwirq];
-}
-
-unsigned int irq_alloc_virt(struct irq_host *host,
-                            unsigned int count,
-                            unsigned int hint)
-{
-        unsigned long flags;
-        unsigned int i, j, found = NO_IRQ;
-
-        if (count == 0 || count > (irq_virq_count - NUM_ISA_INTERRUPTS))
-                return NO_IRQ;
-
-        raw_spin_lock_irqsave(&irq_big_lock, flags);
-
-        /* Use hint for 1 interrupt if any */
-        if (count == 1 && hint >= NUM_ISA_INTERRUPTS &&
-            hint < irq_virq_count && irq_map[hint].host == NULL) {
-                found = hint;
-                goto hint_found;
-        }
-
-        /* Look for count consecutive numbers in the allocatable
-         * (non-legacy) space
-         */
-        for (i = NUM_ISA_INTERRUPTS, j = 0; i < irq_virq_count; i++) {
-                if (irq_map[i].host != NULL)
-                        j = 0;
-                else
-                        j++;
-
-                if (j == count) {
-                        found = i - count + 1;
-                        break;
-                }
-        }
-        if (found == NO_IRQ) {
-                raw_spin_unlock_irqrestore(&irq_big_lock, flags);
-                return NO_IRQ;
-        }
- hint_found:
-        for (i = found; i < (found + count); i++) {
-                irq_map[i].hwirq = host->inval_irq;
-                smp_wmb();
-                irq_map[i].host = host;
-        }
-        raw_spin_unlock_irqrestore(&irq_big_lock, flags);
-        return found;
-}
-
-void irq_free_virt(unsigned int virq, unsigned int count)
-{
-        unsigned long flags;
-        unsigned int i;
-
-        WARN_ON (virq < NUM_ISA_INTERRUPTS);
-        WARN_ON (count == 0 || (virq + count) > irq_virq_count);
-
-        if (virq < NUM_ISA_INTERRUPTS) {
-                if (virq + count < NUM_ISA_INTERRUPTS)
-                        return;
-                count  =- NUM_ISA_INTERRUPTS - virq;
-                virq = NUM_ISA_INTERRUPTS;
-        }
-
-        if (count > irq_virq_count || virq > irq_virq_count - count) {
-                if (virq > irq_virq_count)
-                        return;
-                count = irq_virq_count - virq;
-        }
-
-        raw_spin_lock_irqsave(&irq_big_lock, flags);
-        for (i = virq; i < (virq + count); i++) {
-                struct irq_host *host;
-
-                host = irq_map[i].host;
-                irq_map[i].hwirq = host->inval_irq;
-                smp_wmb();
-                irq_map[i].host = NULL;
-        }
-        raw_spin_unlock_irqrestore(&irq_big_lock, flags);
-}
-
 int arch_early_irq_init(void)
 {
         return 0;
 }
 
-#ifdef CONFIG_VIRQ_DEBUG
-static int virq_debug_show(struct seq_file *m, void *private)
-{
-        unsigned long flags;
-        struct irq_desc *desc;
-        const char *p;
-        static const char none[] = "none";
-        void *data;
-        int i;
-
-        seq_printf(m, "%-5s  %-7s  %-15s  %-18s  %s\n", "virq", "hwirq",
-                      "chip name", "chip data", "host name");
-
-        for (i = 1; i < nr_irqs; i++) {
-                desc = irq_to_desc(i);
-                if (!desc)
-                        continue;
-
-                raw_spin_lock_irqsave(&desc->lock, flags);
-
-                if (desc->action && desc->action->handler) {
-                        struct irq_chip *chip;
-
-                        seq_printf(m, "%5d  ", i);
-                        seq_printf(m, "0x%05lx  ", irq_map[i].hwirq);
-
-                        chip = irq_desc_get_chip(desc);
-                        if (chip && chip->name)
-                                p = chip->name;
-                        else
-                                p = none;
-                        seq_printf(m, "%-15s  ", p);
-
-                        data = irq_desc_get_chip_data(desc);
-                        seq_printf(m, "0x%16p  ", data);
-
-                        if (irq_map[i].host && irq_map[i].host->of_node)
-                                p = irq_map[i].host->of_node->full_name;
-                        else
-                                p = none;
-                        seq_printf(m, "%s\n", p);
-                }
-
-                raw_spin_unlock_irqrestore(&desc->lock, flags);
-        }
-
-        return 0;
-}
-
-static int virq_debug_open(struct inode *inode, struct file *file)
-{
-        return single_open(file, virq_debug_show, inode->i_private);
-}
-
-static const struct file_operations virq_debug_fops = {
-        .open = virq_debug_open,
-        .read = seq_read,
-        .llseek = seq_lseek,
-        .release = single_release,
-};
-
-static int __init irq_debugfs_init(void)
-{
-        if (debugfs_create_file("virq_mapping", S_IRUGO, powerpc_debugfs_root,
-                                 NULL, &virq_debug_fops) == NULL)
-                return -ENOMEM;
-
-        return 0;
-}
-__initcall(irq_debugfs_init);
-#endif /* CONFIG_VIRQ_DEBUG */
-
 #ifdef CONFIG_PPC64
 static int __init setup_noirqdistrib(char *str)
 {
diff --git a/arch/powerpc/kernel/isa-bridge.c b/arch/powerpc/kernel/isa-bridge.c
index 479752901ec6..d45ec58703ce 100644
--- a/arch/powerpc/kernel/isa-bridge.c
+++ b/arch/powerpc/kernel/isa-bridge.c
@@ -29,7 +29,6 @@
 #include <asm/pci-bridge.h>
 #include <asm/machdep.h>
 #include <asm/ppc-pci.h>
-#include <asm/firmware.h>
 
 unsigned long isa_io_base;      /* NULL if no ISA bus */
 EXPORT_SYMBOL(isa_io_base);
@@ -261,8 +260,6 @@ static struct notifier_block isa_bridge_notifier = {
  */
 static int __init isa_bridge_init(void)
 {
-        if (firmware_has_feature(FW_FEATURE_ISERIES))
-                return 0;
         bus_register_notifier(&pci_bus_type, &isa_bridge_notifier);
         return 0;
 }
diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c
index 2985338d0e10..62bdf2389669 100644
--- a/arch/powerpc/kernel/kvm.c
+++ b/arch/powerpc/kernel/kvm.c
@@ -1,5 +1,6 @@
 /*
  * Copyright (C) 2010 SUSE Linux Products GmbH. All rights reserved.
+ * Copyright 2010-2011 Freescale Semiconductor, Inc.
  *
  * Authors:
  *     Alexander Graf <agraf@suse.de>
@@ -29,6 +30,7 @@
 #include <asm/sections.h>
 #include <asm/cacheflush.h>
 #include <asm/disassemble.h>
+#include <asm/ppc-opcode.h>
 
 #define KVM_MAGIC_PAGE          (-4096L)
 #define magic_var(x) KVM_MAGIC_PAGE + offsetof(struct kvm_vcpu_arch_shared, x)
@@ -41,34 +43,30 @@
 #define KVM_INST_B              0x48000000
 #define KVM_INST_B_MASK         0x03ffffff
 #define KVM_INST_B_MAX          0x01ffffff
+#define KVM_INST_LI             0x38000000
 
 #define KVM_MASK_RT             0x03e00000
 #define KVM_RT_30               0x03c00000
 #define KVM_MASK_RB             0x0000f800
 #define KVM_INST_MFMSR          0x7c0000a6
-#define KVM_INST_MFSPR_SPRG0    0x7c1042a6
-#define KVM_INST_MFSPR_SPRG1    0x7c1142a6
-#define KVM_INST_MFSPR_SPRG2    0x7c1242a6
-#define KVM_INST_MFSPR_SPRG3    0x7c1342a6
-#define KVM_INST_MFSPR_SRR0     0x7c1a02a6
-#define KVM_INST_MFSPR_SRR1     0x7c1b02a6
-#define KVM_INST_MFSPR_DAR      0x7c1302a6
-#define KVM_INST_MFSPR_DSISR    0x7c1202a6
-
-#define KVM_INST_MTSPR_SPRG0    0x7c1043a6
-#define KVM_INST_MTSPR_SPRG1    0x7c1143a6
-#define KVM_INST_MTSPR_SPRG2    0x7c1243a6
-#define KVM_INST_MTSPR_SPRG3    0x7c1343a6
-#define KVM_INST_MTSPR_SRR0     0x7c1a03a6
-#define KVM_INST_MTSPR_SRR1     0x7c1b03a6
-#define KVM_INST_MTSPR_DAR      0x7c1303a6
-#define KVM_INST_MTSPR_DSISR    0x7c1203a6
+
+#define SPR_FROM                0
+#define SPR_TO                  0x100
+
+#define KVM_INST_SPR(sprn, moveto) (0x7c0002a6 | \
+                                    (((sprn) & 0x1f) << 16) | \
+                                    (((sprn) & 0x3e0) << 6) | \
+                                    (moveto))
+
+#define KVM_INST_MFSPR(sprn)    KVM_INST_SPR(sprn, SPR_FROM)
+#define KVM_INST_MTSPR(sprn)    KVM_INST_SPR(sprn, SPR_TO)
 
 #define KVM_INST_TLBSYNC        0x7c00046c
 #define KVM_INST_MTMSRD_L0      0x7c000164
 #define KVM_INST_MTMSRD_L1      0x7c010164
 #define KVM_INST_MTMSR          0x7c000124
 
+#define KVM_INST_WRTEE          0x7c000106
 #define KVM_INST_WRTEEI_0       0x7c000146
 #define KVM_INST_WRTEEI_1       0x7c008146
 
@@ -270,26 +268,27 @@ static void kvm_patch_ins_mtmsr(u32 *inst, u32 rt)
 
 #ifdef CONFIG_BOOKE
 
-extern u32 kvm_emulate_wrteei_branch_offs;
-extern u32 kvm_emulate_wrteei_ee_offs;
-extern u32 kvm_emulate_wrteei_len;
-extern u32 kvm_emulate_wrteei[];
+extern u32 kvm_emulate_wrtee_branch_offs;
+extern u32 kvm_emulate_wrtee_reg_offs;
+extern u32 kvm_emulate_wrtee_orig_ins_offs;
+extern u32 kvm_emulate_wrtee_len;
+extern u32 kvm_emulate_wrtee[];
 
-static void kvm_patch_ins_wrteei(u32 *inst)
+static void kvm_patch_ins_wrtee(u32 *inst, u32 rt, int imm_one)
 {
         u32 *p;
         int distance_start;
         int distance_end;
         ulong next_inst;
 
-        p = kvm_alloc(kvm_emulate_wrteei_len * 4);
+        p = kvm_alloc(kvm_emulate_wrtee_len * 4);
         if (!p)
                 return;
 
         /* Find out where we are and put everything there */
         distance_start = (ulong)p - (ulong)inst;
         next_inst = ((ulong)inst + 4);
-        distance_end = next_inst - (ulong)&p[kvm_emulate_wrteei_branch_offs];
+        distance_end = next_inst - (ulong)&p[kvm_emulate_wrtee_branch_offs];
 
         /* Make sure we only write valid b instructions */
         if (distance_start > KVM_INST_B_MAX) {
@@ -298,10 +297,65 @@ static void kvm_patch_ins_wrteei(u32 *inst)
         }
 
         /* Modify the chunk to fit the invocation */
-        memcpy(p, kvm_emulate_wrteei, kvm_emulate_wrteei_len * 4);
-        p[kvm_emulate_wrteei_branch_offs] |= distance_end & KVM_INST_B_MASK;
-        p[kvm_emulate_wrteei_ee_offs] |= (*inst & MSR_EE);
-        flush_icache_range((ulong)p, (ulong)p + kvm_emulate_wrteei_len * 4);
+        memcpy(p, kvm_emulate_wrtee, kvm_emulate_wrtee_len * 4);
+        p[kvm_emulate_wrtee_branch_offs] |= distance_end & KVM_INST_B_MASK;
+
+        if (imm_one) {
+                p[kvm_emulate_wrtee_reg_offs] =
+                        KVM_INST_LI | __PPC_RT(30) | MSR_EE;
+        } else {
+                /* Make clobbered registers work too */
+                switch (get_rt(rt)) {
+                case 30:
+                        kvm_patch_ins_ll(&p[kvm_emulate_wrtee_reg_offs],
+                                         magic_var(scratch2), KVM_RT_30);
+                        break;
+                case 31:
+                        kvm_patch_ins_ll(&p[kvm_emulate_wrtee_reg_offs],
+                                         magic_var(scratch1), KVM_RT_30);
+                        break;
+                default:
+                        p[kvm_emulate_wrtee_reg_offs] |= rt;
+                        break;
+                }
+        }
+
+        p[kvm_emulate_wrtee_orig_ins_offs] = *inst;
+        flush_icache_range((ulong)p, (ulong)p + kvm_emulate_wrtee_len * 4);
+
+        /* Patch the invocation */
+        kvm_patch_ins_b(inst, distance_start);
+}
+
+extern u32 kvm_emulate_wrteei_0_branch_offs;
+extern u32 kvm_emulate_wrteei_0_len;
+extern u32 kvm_emulate_wrteei_0[];
+
+static void kvm_patch_ins_wrteei_0(u32 *inst)
+{
+        u32 *p;
+        int distance_start;
+        int distance_end;
+        ulong next_inst;
+
+        p = kvm_alloc(kvm_emulate_wrteei_0_len * 4);
+        if (!p)
+                return;
+
+        /* Find out where we are and put everything there */
+        distance_start = (ulong)p - (ulong)inst;
+        next_inst = ((ulong)inst + 4);
+        distance_end = next_inst - (ulong)&p[kvm_emulate_wrteei_0_branch_offs];
+
+        /* Make sure we only write valid b instructions */
+        if (distance_start > KVM_INST_B_MAX) {
+                kvm_patching_worked = false;
+                return;
+        }
+
+        memcpy(p, kvm_emulate_wrteei_0, kvm_emulate_wrteei_0_len * 4);
+        p[kvm_emulate_wrteei_0_branch_offs] |= distance_end & KVM_INST_B_MASK;
+        flush_icache_range((ulong)p, (ulong)p + kvm_emulate_wrteei_0_len * 4);
 
         /* Patch the invocation */
         kvm_patch_ins_b(inst, distance_start);
@@ -380,56 +434,191 @@ static void kvm_check_ins(u32 *inst, u32 features)
         case KVM_INST_MFMSR:
                 kvm_patch_ins_ld(inst, magic_var(msr), inst_rt);
                 break;
-        case KVM_INST_MFSPR_SPRG0:
+        case KVM_INST_MFSPR(SPRN_SPRG0):
                 kvm_patch_ins_ld(inst, magic_var(sprg0), inst_rt);
                 break;
-        case KVM_INST_MFSPR_SPRG1:
+        case KVM_INST_MFSPR(SPRN_SPRG1):
                 kvm_patch_ins_ld(inst, magic_var(sprg1), inst_rt);
                 break;
-        case KVM_INST_MFSPR_SPRG2:
+        case KVM_INST_MFSPR(SPRN_SPRG2):
                 kvm_patch_ins_ld(inst, magic_var(sprg2), inst_rt);
                 break;
-        case KVM_INST_MFSPR_SPRG3:
+        case KVM_INST_MFSPR(SPRN_SPRG3):
                 kvm_patch_ins_ld(inst, magic_var(sprg3), inst_rt);
                 break;
-        case KVM_INST_MFSPR_SRR0:
+        case KVM_INST_MFSPR(SPRN_SRR0):
                 kvm_patch_ins_ld(inst, magic_var(srr0), inst_rt);
                 break;
-        case KVM_INST_MFSPR_SRR1:
+        case KVM_INST_MFSPR(SPRN_SRR1):
                 kvm_patch_ins_ld(inst, magic_var(srr1), inst_rt);
                 break;
-        case KVM_INST_MFSPR_DAR:
+#ifdef CONFIG_BOOKE
+        case KVM_INST_MFSPR(SPRN_DEAR):
+#else
+        case KVM_INST_MFSPR(SPRN_DAR):
+#endif
                 kvm_patch_ins_ld(inst, magic_var(dar), inst_rt);
                 break;
-        case KVM_INST_MFSPR_DSISR:
+        case KVM_INST_MFSPR(SPRN_DSISR):
                 kvm_patch_ins_lwz(inst, magic_var(dsisr), inst_rt);
                 break;
 
+#ifdef CONFIG_PPC_BOOK3E_MMU
+        case KVM_INST_MFSPR(SPRN_MAS0):
+                if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+                        kvm_patch_ins_lwz(inst, magic_var(mas0), inst_rt);
+                break;
+        case KVM_INST_MFSPR(SPRN_MAS1):
+                if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+                        kvm_patch_ins_lwz(inst, magic_var(mas1), inst_rt);
+                break;
+        case KVM_INST_MFSPR(SPRN_MAS2):
+                if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+                        kvm_patch_ins_ld(inst, magic_var(mas2), inst_rt);
+                break;
+        case KVM_INST_MFSPR(SPRN_MAS3):
+                if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+                        kvm_patch_ins_lwz(inst, magic_var(mas7_3) + 4, inst_rt);
+                break;
+        case KVM_INST_MFSPR(SPRN_MAS4):
+                if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+                        kvm_patch_ins_lwz(inst, magic_var(mas4), inst_rt);
+                break;
+        case KVM_INST_MFSPR(SPRN_MAS6):
+                if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+                        kvm_patch_ins_lwz(inst, magic_var(mas6), inst_rt);
+                break;
+        case KVM_INST_MFSPR(SPRN_MAS7):
+                if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+                        kvm_patch_ins_lwz(inst, magic_var(mas7_3), inst_rt);
+                break;
+#endif /* CONFIG_PPC_BOOK3E_MMU */
+
+        case KVM_INST_MFSPR(SPRN_SPRG4):
+#ifdef CONFIG_BOOKE
+        case KVM_INST_MFSPR(SPRN_SPRG4R):
+#endif
+                if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+                        kvm_patch_ins_ld(inst, magic_var(sprg4), inst_rt);
+                break;
+        case KVM_INST_MFSPR(SPRN_SPRG5):
+#ifdef CONFIG_BOOKE
+        case KVM_INST_MFSPR(SPRN_SPRG5R):
+#endif
+                if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+                        kvm_patch_ins_ld(inst, magic_var(sprg5), inst_rt);
+                break;
+        case KVM_INST_MFSPR(SPRN_SPRG6):
+#ifdef CONFIG_BOOKE
+        case KVM_INST_MFSPR(SPRN_SPRG6R):
+#endif
+                if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+                        kvm_patch_ins_ld(inst, magic_var(sprg6), inst_rt);
+                break;
+        case KVM_INST_MFSPR(SPRN_SPRG7):
+#ifdef CONFIG_BOOKE
+        case KVM_INST_MFSPR(SPRN_SPRG7R):
+#endif
+                if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+                        kvm_patch_ins_ld(inst, magic_var(sprg7), inst_rt);
+                break;
+
+#ifdef CONFIG_BOOKE
+        case KVM_INST_MFSPR(SPRN_ESR):
+                if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+                        kvm_patch_ins_lwz(inst, magic_var(esr), inst_rt);
+                break;
+#endif
+
+        case KVM_INST_MFSPR(SPRN_PIR):
+                if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+                        kvm_patch_ins_lwz(inst, magic_var(pir), inst_rt);
+                break;
+
+
         /* Stores */
-        case KVM_INST_MTSPR_SPRG0:
+        case KVM_INST_MTSPR(SPRN_SPRG0):
                 kvm_patch_ins_std(inst, magic_var(sprg0), inst_rt);
                 break;
-        case KVM_INST_MTSPR_SPRG1:
+        case KVM_INST_MTSPR(SPRN_SPRG1):
                 kvm_patch_ins_std(inst, magic_var(sprg1), inst_rt);
                 break;
-        case KVM_INST_MTSPR_SPRG2:
+        case KVM_INST_MTSPR(SPRN_SPRG2):
                 kvm_patch_ins_std(inst, magic_var(sprg2), inst_rt);
                 break;
-        case KVM_INST_MTSPR_SPRG3:
+        case KVM_INST_MTSPR(SPRN_SPRG3):
                 kvm_patch_ins_std(inst, magic_var(sprg3), inst_rt);
                 break;
-        case KVM_INST_MTSPR_SRR0:
+        case KVM_INST_MTSPR(SPRN_SRR0):
                 kvm_patch_ins_std(inst, magic_var(srr0), inst_rt);
                 break;
-        case KVM_INST_MTSPR_SRR1:
+        case KVM_INST_MTSPR(SPRN_SRR1):
                 kvm_patch_ins_std(inst, magic_var(srr1), inst_rt);
                 break;
-        case KVM_INST_MTSPR_DAR:
+#ifdef CONFIG_BOOKE
+        case KVM_INST_MTSPR(SPRN_DEAR):
+#else
+        case KVM_INST_MTSPR(SPRN_DAR):
+#endif
                 kvm_patch_ins_std(inst, magic_var(dar), inst_rt);
                 break;
-        case KVM_INST_MTSPR_DSISR:
+        case KVM_INST_MTSPR(SPRN_DSISR):
                 kvm_patch_ins_stw(inst, magic_var(dsisr), inst_rt);
                 break;
+#ifdef CONFIG_PPC_BOOK3E_MMU
+        case KVM_INST_MTSPR(SPRN_MAS0):
+                if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+                        kvm_patch_ins_stw(inst, magic_var(mas0), inst_rt);
+                break;
+        case KVM_INST_MTSPR(SPRN_MAS1):
+                if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+                        kvm_patch_ins_stw(inst, magic_var(mas1), inst_rt);
+                break;
+        case KVM_INST_MTSPR(SPRN_MAS2):
+                if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+                        kvm_patch_ins_std(inst, magic_var(mas2), inst_rt);
+                break;
+        case KVM_INST_MTSPR(SPRN_MAS3):
+                if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+                        kvm_patch_ins_stw(inst, magic_var(mas7_3) + 4, inst_rt);
+                break;
+        case KVM_INST_MTSPR(SPRN_MAS4):
+                if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+                        kvm_patch_ins_stw(inst, magic_var(mas4), inst_rt);
+                break;
+        case KVM_INST_MTSPR(SPRN_MAS6):
+                if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+                        kvm_patch_ins_stw(inst, magic_var(mas6), inst_rt);
+                break;
+        case KVM_INST_MTSPR(SPRN_MAS7):
+                if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+                        kvm_patch_ins_stw(inst, magic_var(mas7_3), inst_rt);
+                break;
+#endif /* CONFIG_PPC_BOOK3E_MMU */
+
+        case KVM_INST_MTSPR(SPRN_SPRG4):
+                if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+                        kvm_patch_ins_std(inst, magic_var(sprg4), inst_rt);
+                break;
+        case KVM_INST_MTSPR(SPRN_SPRG5):
+                if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+                        kvm_patch_ins_std(inst, magic_var(sprg5), inst_rt);
+                break;
+        case KVM_INST_MTSPR(SPRN_SPRG6):
+                if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+                        kvm_patch_ins_std(inst, magic_var(sprg6), inst_rt);
+                break;
+        case KVM_INST_MTSPR(SPRN_SPRG7):
+                if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+                        kvm_patch_ins_std(inst, magic_var(sprg7), inst_rt);
+                break;
+
+#ifdef CONFIG_BOOKE
+        case KVM_INST_MTSPR(SPRN_ESR):
+                if (features & KVM_MAGIC_FEAT_MAS0_TO_SPRG7)
+                        kvm_patch_ins_stw(inst, magic_var(esr), inst_rt);
+                break;
+#endif
 
         /* Nops */
         case KVM_INST_TLBSYNC:
@@ -444,6 +633,11 @@ static void kvm_check_ins(u32 *inst, u32 features)
         case KVM_INST_MTMSRD_L0:
                 kvm_patch_ins_mtmsr(inst, inst_rt);
                 break;
+#ifdef CONFIG_BOOKE
+        case KVM_INST_WRTEE:
+                kvm_patch_ins_wrtee(inst, inst_rt, 0);
+                break;
+#endif
         }
 
         switch (inst_no_rt & ~KVM_MASK_RB) {
@@ -461,13 +655,19 @@ static void kvm_check_ins(u32 *inst, u32 features)
         switch (_inst) {
 #ifdef CONFIG_BOOKE
         case KVM_INST_WRTEEI_0:
+                kvm_patch_ins_wrteei_0(inst);
+                break;
+
         case KVM_INST_WRTEEI_1:
-                kvm_patch_ins_wrteei(inst);
+                kvm_patch_ins_wrtee(inst, 0, 1);
                 break;
 #endif
         }
 }
 
+extern u32 kvm_template_start[];
+extern u32 kvm_template_end[];
+
 static void kvm_use_magic_page(void)
 {
         u32 *p;
@@ -488,8 +688,23 @@ static void kvm_use_magic_page(void)
         start = (void*)_stext;
         end = (void*)_etext;
 
-        for (p = start; p < end; p++)
+        /*
+         * Being interrupted in the middle of patching would
+         * be bad for SPRG4-7, which KVM can't keep in sync
+         * with emulated accesses because reads don't trap.
+         */
+        local_irq_disable();
+
+        for (p = start; p < end; p++) {
+                /* Avoid patching the template code */
+                if (p >= kvm_template_start && p < kvm_template_end) {
+                        p = kvm_template_end - 1;
+                        continue;
+                }
                 kvm_check_ins(p, features);
+        }
+
+        local_irq_enable();
 
         printk(KERN_INFO "KVM: Live patching for a fast VM %s\n",
                          kvm_patching_worked ? "worked" : "failed");
diff --git a/arch/powerpc/kernel/kvm_emul.S b/arch/powerpc/kernel/kvm_emul.S
index f2b1b2523e61..e291cf3cf954 100644
--- a/arch/powerpc/kernel/kvm_emul.S
+++ b/arch/powerpc/kernel/kvm_emul.S
@@ -13,6 +13,7 @@
  * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
  *
  * Copyright SUSE Linux Products GmbH 2010
+ * Copyright 2010-2011 Freescale Semiconductor, Inc.
  *
  * Authors: Alexander Graf <agraf@suse.de>
  */
@@ -65,6 +66,9 @@ kvm_hypercall_start:
            shared->critical == r1 and r2 is always != r1 */             \
         STL64(r2, KVM_MAGIC_PAGE + KVM_MAGIC_CRITICAL, 0);
 
+.global kvm_template_start
+kvm_template_start:
+
 .global kvm_emulate_mtmsrd
 kvm_emulate_mtmsrd:
 
@@ -167,6 +171,9 @@ maybe_stay_in_guest:
 kvm_emulate_mtmsr_reg2:
         ori     r30, r0, 0
 
+        /* Put MSR into magic page because we don't call mtmsr */
+        STL64(r30, KVM_MAGIC_PAGE + KVM_MAGIC_MSR, 0)
+
         /* Check if we have to fetch an interrupt */
         lwz     r31, (KVM_MAGIC_PAGE + KVM_MAGIC_INT)(0)
         cmpwi   r31, 0
@@ -174,15 +181,10 @@ kvm_emulate_mtmsr_reg2:
 
         /* Check if we may trigger an interrupt */
         andi.   r31, r30, MSR_EE
-        beq     no_mtmsr
-
-        b       do_mtmsr
+        bne     do_mtmsr
 
 no_mtmsr:
 
-        /* Put MSR into magic page because we don't call mtmsr */
-        STL64(r30, KVM_MAGIC_PAGE + KVM_MAGIC_MSR, 0)
-
         SCRATCH_RESTORE
 
         /* Go back to caller */
@@ -210,24 +212,80 @@ kvm_emulate_mtmsr_orig_ins_offs:
 kvm_emulate_mtmsr_len:
         .long (kvm_emulate_mtmsr_end - kvm_emulate_mtmsr) / 4
 
+/* also used for wrteei 1 */
+.global kvm_emulate_wrtee
+kvm_emulate_wrtee:
+
+        SCRATCH_SAVE
+
+        /* Fetch old MSR in r31 */
+        LL64(r31, KVM_MAGIC_PAGE + KVM_MAGIC_MSR, 0)
+
+        /* Insert new MSR[EE] */
+kvm_emulate_wrtee_reg:
+        ori     r30, r0, 0
+        rlwimi  r31, r30, 0, MSR_EE
+
+        /*
+         * If MSR[EE] is now set, check for a pending interrupt.
+         * We could skip this if MSR[EE] was already on, but that
+         * should be rare, so don't bother.
+         */
+        andi.   r30, r30, MSR_EE
+
+        /* Put MSR into magic page because we don't call wrtee */
+        STL64(r31, KVM_MAGIC_PAGE + KVM_MAGIC_MSR, 0)
+
+        beq     no_wrtee
+
+        /* Check if we have to fetch an interrupt */
+        lwz     r30, (KVM_MAGIC_PAGE + KVM_MAGIC_INT)(0)
+        cmpwi   r30, 0
+        bne     do_wrtee
+
+no_wrtee:
+        SCRATCH_RESTORE
+
+        /* Go back to caller */
+kvm_emulate_wrtee_branch:
+        b       .
+
+do_wrtee:
+        SCRATCH_RESTORE
 
+        /* Just fire off the wrtee if it's critical */
+kvm_emulate_wrtee_orig_ins:
+        wrtee   r0
 
-.global kvm_emulate_wrteei
-kvm_emulate_wrteei:
+        b       kvm_emulate_wrtee_branch
 
+kvm_emulate_wrtee_end:
+
+.global kvm_emulate_wrtee_branch_offs
+kvm_emulate_wrtee_branch_offs:
+        .long (kvm_emulate_wrtee_branch - kvm_emulate_wrtee) / 4
+
+.global kvm_emulate_wrtee_reg_offs
+kvm_emulate_wrtee_reg_offs:
+        .long (kvm_emulate_wrtee_reg - kvm_emulate_wrtee) / 4
+
+.global kvm_emulate_wrtee_orig_ins_offs
+kvm_emulate_wrtee_orig_ins_offs:
+        .long (kvm_emulate_wrtee_orig_ins - kvm_emulate_wrtee) / 4
+
+.global kvm_emulate_wrtee_len
+kvm_emulate_wrtee_len:
+        .long (kvm_emulate_wrtee_end - kvm_emulate_wrtee) / 4
+
+.global kvm_emulate_wrteei_0
+kvm_emulate_wrteei_0:
         SCRATCH_SAVE
 
         /* Fetch old MSR in r31 */
         LL64(r31, KVM_MAGIC_PAGE + KVM_MAGIC_MSR, 0)
 
         /* Remove MSR_EE from old MSR */
-        li      r30, 0
-        ori     r30, r30, MSR_EE
-        andc    r31, r31, r30
-
-        /* OR new MSR_EE onto the old MSR */
-kvm_emulate_wrteei_ee:
-        ori     r31, r31, 0
+        rlwinm  r31, r31, 0, ~MSR_EE
 
         /* Write new MSR value back */
         STL64(r31, KVM_MAGIC_PAGE + KVM_MAGIC_MSR, 0)
@@ -235,22 +293,17 @@ kvm_emulate_wrteei_ee:
         SCRATCH_RESTORE
 
         /* Go back to caller */
-kvm_emulate_wrteei_branch:
+kvm_emulate_wrteei_0_branch:
         b       .
-kvm_emulate_wrteei_end:
-
-.global kvm_emulate_wrteei_branch_offs
-kvm_emulate_wrteei_branch_offs:
-        .long (kvm_emulate_wrteei_branch - kvm_emulate_wrteei) / 4
+kvm_emulate_wrteei_0_end:
 
-.global kvm_emulate_wrteei_ee_offs
-kvm_emulate_wrteei_ee_offs:
-        .long (kvm_emulate_wrteei_ee - kvm_emulate_wrteei) / 4
-
-.global kvm_emulate_wrteei_len
-kvm_emulate_wrteei_len:
-        .long (kvm_emulate_wrteei_end - kvm_emulate_wrteei) / 4
+.global kvm_emulate_wrteei_0_branch_offs
+kvm_emulate_wrteei_0_branch_offs:
+        .long (kvm_emulate_wrteei_0_branch - kvm_emulate_wrteei_0) / 4
 
+.global kvm_emulate_wrteei_0_len
+kvm_emulate_wrteei_0_len:
+        .long (kvm_emulate_wrteei_0_end - kvm_emulate_wrteei_0) / 4
 
 .global kvm_emulate_mtsrin
 kvm_emulate_mtsrin:
@@ -300,3 +353,6 @@ kvm_emulate_mtsrin_orig_ins_offs:
 .global kvm_emulate_mtsrin_len
 kvm_emulate_mtsrin_len:
         .long (kvm_emulate_mtsrin_end - kvm_emulate_mtsrin) / 4
+
+.global kvm_template_end
+kvm_template_end:
diff --git a/arch/powerpc/kernel/legacy_serial.c b/arch/powerpc/kernel/legacy_serial.c
index 3fea3689527e..bedd12e1cfbc 100644
--- a/arch/powerpc/kernel/legacy_serial.c
+++ b/arch/powerpc/kernel/legacy_serial.c
@@ -442,8 +442,10 @@ static void __init fixup_port_irq(int index,
 
         port->irq = virq;
 
+#ifdef CONFIG_SERIAL_8250_FSL
         if (of_device_is_compatible(np, "fsl,ns16550"))
                 port->handle_irq = fsl8250_handle_irq;
+#endif
 }
 
 static void __init fixup_port_pio(int index,
diff --git a/arch/powerpc/kernel/lparcfg.c b/arch/powerpc/kernel/lparcfg.c
index 578f35f18723..ac12bd80ad95 100644
--- a/arch/powerpc/kernel/lparcfg.c
+++ b/arch/powerpc/kernel/lparcfg.c
@@ -26,7 +26,6 @@
 #include <linux/seq_file.h>
 #include <linux/slab.h>
 #include <asm/uaccess.h>
-#include <asm/iseries/hv_lp_config.h>
 #include <asm/lppaca.h>
 #include <asm/hvcall.h>
 #include <asm/firmware.h>
@@ -55,80 +54,14 @@ static unsigned long get_purr(void)
         int cpu;
 
         for_each_possible_cpu(cpu) {
-                if (firmware_has_feature(FW_FEATURE_ISERIES))
-                        sum_purr += lppaca_of(cpu).emulated_time_base;
-                else {
-                        struct cpu_usage *cu;
+                struct cpu_usage *cu;
 
-                        cu = &per_cpu(cpu_usage_array, cpu);
-                        sum_purr += cu->current_tb;
-                }
+                cu = &per_cpu(cpu_usage_array, cpu);
+                sum_purr += cu->current_tb;
         }
         return sum_purr;
 }
 
-#ifdef CONFIG_PPC_ISERIES
-
-/*
- * Methods used to fetch LPAR data when running on an iSeries platform.
- */
-static int iseries_lparcfg_data(struct seq_file *m, void *v)
-{
-        unsigned long pool_id;
-        int shared, entitled_capacity, max_entitled_capacity;
-        int processors, max_processors;
-        unsigned long purr = get_purr();
-
-        shared = (int)(local_paca->lppaca_ptr->shared_proc);
-
-        seq_printf(m, "system_active_processors=%d\n",
-                   (int)HvLpConfig_getSystemPhysicalProcessors());
-
-        seq_printf(m, "system_potential_processors=%d\n",
-                   (int)HvLpConfig_getSystemPhysicalProcessors());
-
-        processors = (int)HvLpConfig_getPhysicalProcessors();
-        seq_printf(m, "partition_active_processors=%d\n", processors);
-
-        max_processors = (int)HvLpConfig_getMaxPhysicalProcessors();
-        seq_printf(m, "partition_potential_processors=%d\n", max_processors);
-
-        if (shared) {
-                entitled_capacity = HvLpConfig_getSharedProcUnits();
-                max_entitled_capacity = HvLpConfig_getMaxSharedProcUnits();
-        } else {
-                entitled_capacity = processors * 100;
-                max_entitled_capacity = max_processors * 100;
-        }
-        seq_printf(m, "partition_entitled_capacity=%d\n", entitled_capacity);
-
-        seq_printf(m, "partition_max_entitled_capacity=%d\n",
-                   max_entitled_capacity);
-
-        if (shared) {
-                pool_id = HvLpConfig_getSharedPoolIndex();
-                seq_printf(m, "pool=%d\n", (int)pool_id);
-                seq_printf(m, "pool_capacity=%d\n",
-                           (int)(HvLpConfig_getNumProcsInSharedPool(pool_id) *
-                                 100));
-                seq_printf(m, "purr=%ld\n", purr);
-        }
-
-        seq_printf(m, "shared_processor_mode=%d\n", shared);
-
-        return 0;
-}
-
-#else                           /* CONFIG_PPC_ISERIES */
-
-static int iseries_lparcfg_data(struct seq_file *m, void *v)
-{
-        return 0;
-}
-
-#endif                          /* CONFIG_PPC_ISERIES */
-
-#ifdef CONFIG_PPC_PSERIES
 /*
  * Methods used to fetch LPAR data when running on a pSeries platform.
  */
@@ -648,8 +581,7 @@ static ssize_t lparcfg_write(struct file *file, const char __user * buf,
         u8 new_weight, *new_weight_ptr = &new_weight;
         ssize_t retval;
 
-        if (!firmware_has_feature(FW_FEATURE_SPLPAR) ||
-                        firmware_has_feature(FW_FEATURE_ISERIES))
+        if (!firmware_has_feature(FW_FEATURE_SPLPAR))
                 return -EINVAL;
 
         if (count > kbuf_sz)
@@ -709,21 +641,6 @@ static ssize_t lparcfg_write(struct file *file, const char __user * buf,
         return retval;
 }
 
-#else                           /* CONFIG_PPC_PSERIES */
-
-static int pseries_lparcfg_data(struct seq_file *m, void *v)
-{
-        return 0;
-}
-
-static ssize_t lparcfg_write(struct file *file, const char __user * buf,
-                             size_t count, loff_t * off)
-{
-        return -EINVAL;
-}
-
-#endif                          /* CONFIG_PPC_PSERIES */
-
 static int lparcfg_data(struct seq_file *m, void *v)
 {
         struct device_node *rootdn;
@@ -738,19 +655,11 @@ static int lparcfg_data(struct seq_file *m, void *v)
         rootdn = of_find_node_by_path("/");
         if (rootdn) {
                 tmp = of_get_property(rootdn, "model", NULL);
-                if (tmp) {
+                if (tmp)
                         model = tmp;
-                        /* Skip "IBM," - see platforms/iseries/dt.c */
-                        if (firmware_has_feature(FW_FEATURE_ISERIES))
-                                model += 4;
-                }
                 tmp = of_get_property(rootdn, "system-id", NULL);
-                if (tmp) {
+                if (tmp)
                         system_id = tmp;
-                        /* Skip "IBM," - see platforms/iseries/dt.c */
-                        if (firmware_has_feature(FW_FEATURE_ISERIES))
-                                system_id += 4;
-                }
                 lp_index_ptr = of_get_property(rootdn, "ibm,partition-no",
                                         NULL);
                 if (lp_index_ptr)
@@ -761,8 +670,6 @@ static int lparcfg_data(struct seq_file *m, void *v)
         seq_printf(m, "system_type=%s\n", model);
         seq_printf(m, "partition_id=%d\n", (int)lp_index);
 
-        if (firmware_has_feature(FW_FEATURE_ISERIES))
-                return iseries_lparcfg_data(m, v);
         return pseries_lparcfg_data(m, v);
 }
 
@@ -786,8 +693,7 @@ static int __init lparcfg_init(void)
         umode_t mode = S_IRUSR | S_IRGRP | S_IROTH;
 
         /* Allow writing if we have FW_FEATURE_SPLPAR */
-        if (firmware_has_feature(FW_FEATURE_SPLPAR) &&
-                        !firmware_has_feature(FW_FEATURE_ISERIES))
+        if (firmware_has_feature(FW_FEATURE_SPLPAR))
                 mode |= S_IWUSR;
 
         ent = proc_create("powerpc/lparcfg", mode, NULL, &lparcfg_fops);
diff --git a/arch/powerpc/kernel/misc.S b/arch/powerpc/kernel/misc.S
index b69463ec2010..ba16874fe294 100644
--- a/arch/powerpc/kernel/misc.S
+++ b/arch/powerpc/kernel/misc.S
@@ -5,7 +5,6 @@
  * Largely rewritten by Cort Dougan (cort@cs.nmt.edu)
  * and Paul Mackerras.
  *
- * Adapted for iSeries by Mike Corrigan (mikejc@us.ibm.com)
  * PPC64 updates by Dave Engebretsen (engebret@us.ibm.com)
  *
  * setjmp/longjmp code by Paul Mackerras.
diff --git a/arch/powerpc/kernel/of_platform.c b/arch/powerpc/kernel/of_platform.c
index e1612dfb4a93..2049f2d00ffe 100644
--- a/arch/powerpc/kernel/of_platform.c
+++ b/arch/powerpc/kernel/of_platform.c
@@ -21,12 +21,13 @@
 #include <linux/of.h>
 #include <linux/of_device.h>
 #include <linux/of_platform.h>
+#include <linux/atomic.h>
 
 #include <asm/errno.h>
 #include <asm/topology.h>
 #include <asm/pci-bridge.h>
 #include <asm/ppc-pci.h>
-#include <linux/atomic.h>
+#include <asm/eeh.h>
 
 #ifdef CONFIG_PPC_OF_PLATFORM_PCI
 
@@ -66,6 +67,9 @@ static int __devinit of_pci_phb_probe(struct platform_device *dev)
         /* Init pci_dn data structures */
         pci_devs_phb_init_dynamic(phb);
 
+        /* Create EEH devices for the PHB */
+        eeh_dev_phb_init_dynamic(phb);
+
         /* Register devices with EEH */
 #ifdef CONFIG_EEH
         if (dev->dev.of_node->child)
diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c
index 41456ff55e14..0bb1f98613ba 100644
--- a/arch/powerpc/kernel/paca.c
+++ b/arch/powerpc/kernel/paca.c
@@ -11,13 +11,10 @@
 #include <linux/export.h>
 #include <linux/memblock.h>
 
-#include <asm/firmware.h>
 #include <asm/lppaca.h>
 #include <asm/paca.h>
 #include <asm/sections.h>
 #include <asm/pgtable.h>
-#include <asm/iseries/lpar_map.h>
-#include <asm/iseries/hv_types.h>
 #include <asm/kexec.h>
 
 /* This symbol is provided by the linker - let it fill in the paca
@@ -30,8 +27,8 @@ extern unsigned long __toc_start;
  * The structure which the hypervisor knows about - this structure
  * should not cross a page boundary.  The vpa_init/register_vpa call
  * is now known to fail if the lppaca structure crosses a page
- * boundary.  The lppaca is also used on legacy iSeries and POWER5
- * pSeries boxes.  The lppaca is 640 bytes long, and cannot readily
+ * boundary.  The lppaca is also used on POWER5 pSeries boxes.
+ * The lppaca is 640 bytes long, and cannot readily
  * change since the hypervisor knows its layout, so a 1kB alignment
  * will suffice to ensure that it doesn't cross a page boundary.
  */
@@ -183,12 +180,9 @@ void __init allocate_pacas(void)
         /*
          * We can't take SLB misses on the paca, and we want to access them
          * in real mode, so allocate them within the RMA and also within
-         * the first segment. On iSeries they must be within the area mapped
-         * by the HV, which is HvPagesToMap * HVPAGESIZE bytes.
+         * the first segment.
          */
         limit = min(0x10000000ULL, ppc64_rma_size);
-        if (firmware_has_feature(FW_FEATURE_ISERIES))
-                limit = min(limit, HvPagesToMap * HVPAGESIZE);
 
         paca_size = PAGE_ALIGN(sizeof(struct paca_struct) * nr_cpu_ids);
 
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index cce98d76e905..8e78e93c8185 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -38,7 +38,6 @@
 #include <asm/byteorder.h>
 #include <asm/machdep.h>
 #include <asm/ppc-pci.h>
-#include <asm/firmware.h>
 #include <asm/eeh.h>
 
 static DEFINE_SPINLOCK(hose_spinlock);
@@ -50,9 +49,6 @@ static int global_phb_number;		/* Global phb counter */
 /* ISA Memory physical address */
 resource_size_t isa_mem_base;
 
-/* Default PCI flags is 0 on ppc32, modified at boot on ppc64 */
-unsigned int pci_flags = 0;
-
 
 static struct dma_map_ops *pci_dma_ops = &dma_direct_ops;
 
@@ -219,20 +215,6 @@ static int pci_read_irq_line(struct pci_dev *pci_dev)
         struct of_irq oirq;
         unsigned int virq;
 
-        /* The current device-tree that iSeries generates from the HV
-         * PCI informations doesn't contain proper interrupt routing,
-         * and all the fallback would do is print out crap, so we
-         * don't attempt to resolve the interrupts here at all, some
-         * iSeries specific fixup does it.
-         *
-         * In the long run, we will hopefully fix the generated device-tree
-         * instead.
-         */
-#ifdef CONFIG_PPC_ISERIES
-        if (firmware_has_feature(FW_FEATURE_ISERIES))
-                return -1;
-#endif
-
         pr_debug("PCI: Try to map irq for %s...\n", pci_name(pci_dev));
 
 #ifdef DEBUG
@@ -849,60 +831,6 @@ int pci_proc_domain(struct pci_bus *bus)
         return 1;
 }
 
-void pcibios_resource_to_bus(struct pci_dev *dev, struct pci_bus_region *region,
-                             struct resource *res)
-{
-        resource_size_t offset = 0, mask = (resource_size_t)-1;
-        struct pci_controller *hose = pci_bus_to_host(dev->bus);
-
-        if (!hose)
-                return;
-        if (res->flags & IORESOURCE_IO) {
-                offset = (unsigned long)hose->io_base_virt - _IO_BASE;
-                mask = 0xffffffffu;
-        } else if (res->flags & IORESOURCE_MEM)
-                offset = hose->pci_mem_offset;
-
-        region->start = (res->start - offset) & mask;
-        region->end = (res->end - offset) & mask;
-}
-EXPORT_SYMBOL(pcibios_resource_to_bus);
-
-void pcibios_bus_to_resource(struct pci_dev *dev, struct resource *res,
-                             struct pci_bus_region *region)
-{
-        resource_size_t offset = 0, mask = (resource_size_t)-1;
-        struct pci_controller *hose = pci_bus_to_host(dev->bus);
-
-        if (!hose)
-                return;
-        if (res->flags & IORESOURCE_IO) {
-                offset = (unsigned long)hose->io_base_virt - _IO_BASE;
-                mask = 0xffffffffu;
-        } else if (res->flags & IORESOURCE_MEM)
-                offset = hose->pci_mem_offset;
-        res->start = (region->start + offset) & mask;
-        res->end = (region->end + offset) & mask;
-}
-EXPORT_SYMBOL(pcibios_bus_to_resource);
-
-/* Fixup a bus resource into a linux resource */
-static void __devinit fixup_resource(struct resource *res, struct pci_dev *dev)
-{
-        struct pci_controller *hose = pci_bus_to_host(dev->bus);
-        resource_size_t offset = 0, mask = (resource_size_t)-1;
-
-        if (res->flags & IORESOURCE_IO) {
-                offset = (unsigned long)hose->io_base_virt - _IO_BASE;
-                mask = 0xffffffffu;
-        } else if (res->flags & IORESOURCE_MEM)
-                offset = hose->pci_mem_offset;
-
-        res->start = (res->start + offset) & mask;
-        res->end = (res->end + offset) & mask;
-}
-
-
 /* This header fixup will do the resource fixup for all devices as they are
  * probed, but not for bridge ranges
  */
@@ -942,18 +870,11 @@ static void __devinit pcibios_fixup_resources(struct pci_dev *dev)
                         continue;
                 }
 
-                pr_debug("PCI:%s Resource %d %016llx-%016llx [%x] fixup...\n",
+                pr_debug("PCI:%s Resource %d %016llx-%016llx [%x]\n",
                          pci_name(dev), i,
                          (unsigned long long)res->start,\
                          (unsigned long long)res->end,
                          (unsigned int)res->flags);
-
-                fixup_resource(res, dev);
-
-                pr_debug("PCI:%s            %016llx-%016llx\n",
-                         pci_name(dev),
-                         (unsigned long long)res->start,
-                         (unsigned long long)res->end);
         }
 
         /* Call machine specific resource fixup */
@@ -1055,27 +976,18 @@ static void __devinit pcibios_fixup_bridge(struct pci_bus *bus)
                         continue;
                 }
 
-                pr_debug("PCI:%s Bus rsrc %d %016llx-%016llx [%x] fixup...\n",
+                pr_debug("PCI:%s Bus rsrc %d %016llx-%016llx [%x]\n",
                          pci_name(dev), i,
                          (unsigned long long)res->start,\
                          (unsigned long long)res->end,
                          (unsigned int)res->flags);
 
-                /* Perform fixup */
-                fixup_resource(res, dev);
-
                 /* Try to detect uninitialized P2P bridge resources,
                  * and clear them out so they get re-assigned later
                  */
                 if (pcibios_uninitialized_bridge_resource(bus, res)) {
                         res->flags = 0;
                         pr_debug("PCI:%s            (unassigned)\n", pci_name(dev));
-                } else {
-
-                        pr_debug("PCI:%s            %016llx-%016llx\n",
-                                 pci_name(dev),
-                                 (unsigned long long)res->start,
-                                 (unsigned long long)res->end);
                 }
         }
 }
@@ -1565,6 +1477,11 @@ int pcibios_enable_device(struct pci_dev *dev, int mask)
         return pci_enable_resources(dev, mask);
 }
 
+resource_size_t pcibios_io_space_offset(struct pci_controller *hose)
+{
+        return (unsigned long) hose->io_base_virt - _IO_BASE;
+}
+
 static void __devinit pcibios_setup_phb_resources(struct pci_controller *hose, struct list_head *resources)
 {
         struct resource *res;
@@ -1589,7 +1506,7 @@ static void __devinit pcibios_setup_phb_resources(struct pci_controller *hose, s
                  (unsigned long long)res->start,
                  (unsigned long long)res->end,
                  (unsigned long)res->flags);
-        pci_add_resource(resources, res);
+        pci_add_resource_offset(resources, res, pcibios_io_space_offset(hose));
 
         /* Hookup PHB Memory resources */
         for (i = 0; i < 3; ++i) {
@@ -1612,7 +1529,7 @@ static void __devinit pcibios_setup_phb_resources(struct pci_controller *hose, s
                          (unsigned long long)res->start,
                          (unsigned long long)res->end,
                          (unsigned long)res->flags);
-                pci_add_resource(resources, res);
+                pci_add_resource_offset(resources, res, hose->pci_mem_offset);
         }
 
         pr_debug("PCI: PHB MEM offset     = %016llx\n",
diff --git a/arch/powerpc/kernel/pci_32.c b/arch/powerpc/kernel/pci_32.c
index fdd1a3d951dc..4b06ec5a502e 100644
--- a/arch/powerpc/kernel/pci_32.c
+++ b/arch/powerpc/kernel/pci_32.c
@@ -219,9 +219,9 @@ void __devinit pcibios_setup_phb_io_space(struct pci_controller *hose)
         struct resource *res = &hose->io_resource;
 
         /* Fixup IO space offset */
-        io_offset = (unsigned long)hose->io_base_virt - isa_io_base;
-        res->start = (res->start + io_offset) & 0xffffffffu;
-        res->end = (res->end + io_offset) & 0xffffffffu;
+        io_offset = pcibios_io_space_offset(hose);
+        res->start += io_offset;
+        res->end += io_offset;
 }
 
 static int __init pcibios_init(void)
diff --git a/arch/powerpc/kernel/pci_64.c b/arch/powerpc/kernel/pci_64.c
index 3318d39b7d4c..94a54f61d341 100644
--- a/arch/powerpc/kernel/pci_64.c
+++ b/arch/powerpc/kernel/pci_64.c
@@ -33,8 +33,6 @@
 #include <asm/machdep.h>
 #include <asm/ppc-pci.h>
 
-unsigned long pci_probe_only = 1;
-
 /* pci_io_base -- the base address from which io bars are offsets.
  * This is the lowest I/O base address (so bar values are always positive),
  * and it *must* be the start of ISA space if an ISA bus exists because
@@ -55,9 +53,6 @@ static int __init pcibios_init(void)
          */
         ppc_md.phys_mem_access_prot = pci_phys_mem_access_prot;
 
-        if (pci_probe_only)
-                pci_add_flags(PCI_PROBE_ONLY);
-
         /* On ppc64, we always enable PCI domains and we keep domain 0
          * backward compatible in /proc for video cards
          */
@@ -173,7 +168,7 @@ static int __devinit pcibios_map_phb_io_space(struct pci_controller *hose)
                 return -ENOMEM;
 
         /* Fixup hose IO resource */
-        io_virt_offset = (unsigned long)hose->io_base_virt - _IO_BASE;
+        io_virt_offset = pcibios_io_space_offset(hose);
         hose->io_resource.start += io_virt_offset;
         hose->io_resource.end += io_virt_offset;
 
diff --git a/arch/powerpc/kernel/pci_of_scan.c b/arch/powerpc/kernel/pci_of_scan.c
index b37d0b5a796e..89dde171a6fa 100644
--- a/arch/powerpc/kernel/pci_of_scan.c
+++ b/arch/powerpc/kernel/pci_of_scan.c
@@ -75,6 +75,7 @@ static void of_pci_parse_addrs(struct device_node *node, struct pci_dev *dev)
 {
         u64 base, size;
         unsigned int flags;
+        struct pci_bus_region region;
         struct resource *res;
         const u32 *addrs;
         u32 i;
@@ -106,10 +107,11 @@ static void of_pci_parse_addrs(struct device_node *node, struct pci_dev *dev)
                         printk(KERN_ERR "PCI: bad cfg reg num 0x%x\n", i);
                         continue;
                 }
-                res->start = base;
-                res->end = base + size - 1;
                 res->flags = flags;
                 res->name = pci_name(dev);
+                region.start = base;
+                region.end = base + size - 1;
+                pcibios_bus_to_resource(dev, res, &region);
         }
 }
 
@@ -209,6 +211,7 @@ void __devinit of_scan_pci_bridge(struct pci_dev *dev)
         struct pci_bus *bus;
         const u32 *busrange, *ranges;
         int len, i, mode;
+        struct pci_bus_region region;
         struct resource *res;
         unsigned int flags;
         u64 size;
@@ -270,9 +273,10 @@ void __devinit of_scan_pci_bridge(struct pci_dev *dev)
                         res = bus->resource[i];
                         ++i;
                 }
-                res->start = of_read_number(&ranges[1], 2);
-                res->end = res->start + size - 1;
                 res->flags = flags;
+                region.start = of_read_number(&ranges[1], 2);
+                region.end = region.start + size - 1;
+                pcibios_bus_to_resource(dev, res, &region);
         }
         sprintf(bus->name, "PCI Bus %04x:%02x", pci_domain_nr(bus),
                 bus->number);
diff --git a/arch/powerpc/kernel/pmc.c b/arch/powerpc/kernel/pmc.c
index a841a9d136a2..58eaa3ddf7b9 100644
--- a/arch/powerpc/kernel/pmc.c
+++ b/arch/powerpc/kernel/pmc.c
@@ -13,6 +13,7 @@
  */
 
 #include <linux/errno.h>
+#include <linux/bug.h>
 #include <linux/spinlock.h>
 #include <linux/export.h>
 
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index ebe5766781aa..e40707032ac3 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -566,12 +566,12 @@ static void show_instructions(struct pt_regs *regs)
                  */
                 if (!__kernel_text_address(pc) ||
                      __get_user(instr, (unsigned int __user *)pc)) {
-                        printk("XXXXXXXX ");
+                        printk(KERN_CONT "XXXXXXXX ");
                 } else {
                         if (regs->nip == pc)
-                                printk("<%08x> ", instr);
+                                printk(KERN_CONT "<%08x> ", instr);
                         else
-                                printk("%08x ", instr);
+                                printk(KERN_CONT "%08x ", instr);
                 }
 
                 pc += sizeof(int);
@@ -647,6 +647,9 @@ void show_regs(struct pt_regs * regs)
         printk("MSR: "REG" ", regs->msr);
         printbits(regs->msr, msr_bits);
         printk("  CR: %08lx  XER: %08lx\n", regs->ccr, regs->xer);
+#ifdef CONFIG_PPC64
+        printk("SOFTE: %ld\n", regs->softe);
+#endif
         trap = TRAP(regs);
         if ((regs->trap != 0xc00) && cpu_has_feature(CPU_FTR_CFAR))
                 printk("CFAR: "REG"\n", regs->orig_gpr3);
@@ -1220,34 +1223,32 @@ void dump_stack(void)
 EXPORT_SYMBOL(dump_stack);
 
 #ifdef CONFIG_PPC64
-void ppc64_runlatch_on(void)
+/* Called with hard IRQs off */
+void __ppc64_runlatch_on(void)
 {
+        struct thread_info *ti = current_thread_info();
         unsigned long ctrl;
 
-        if (cpu_has_feature(CPU_FTR_CTRL) && !test_thread_flag(TIF_RUNLATCH)) {
-                HMT_medium();
-
-                ctrl = mfspr(SPRN_CTRLF);
-                ctrl |= CTRL_RUNLATCH;
-                mtspr(SPRN_CTRLT, ctrl);
+        ctrl = mfspr(SPRN_CTRLF);
+        ctrl |= CTRL_RUNLATCH;
+        mtspr(SPRN_CTRLT, ctrl);
 
-                set_thread_flag(TIF_RUNLATCH);
-        }
+        ti->local_flags |= TLF_RUNLATCH;
 }
 
+/* Called with hard IRQs off */
 void __ppc64_runlatch_off(void)
 {
+        struct thread_info *ti = current_thread_info();
         unsigned long ctrl;
 
-        HMT_medium();
-
-        clear_thread_flag(TIF_RUNLATCH);
+        ti->local_flags &= ~TLF_RUNLATCH;
 
         ctrl = mfspr(SPRN_CTRLF);
         ctrl &= ~CTRL_RUNLATCH;
         mtspr(SPRN_CTRLT, ctrl);
 }
-#endif
+#endif /* CONFIG_PPC64 */
 
 #if THREAD_SHIFT < PAGE_SHIFT
 
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index abe405dab34d..89e850af3dd6 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -52,9 +52,9 @@
 #include <asm/machdep.h>
 #include <asm/pSeries_reconfig.h>
 #include <asm/pci-bridge.h>
-#include <asm/phyp_dump.h>
 #include <asm/kexec.h>
 #include <asm/opal.h>
+#include <asm/fadump.h>
 
 #include <mm/mmu_decl.h>
 
@@ -615,86 +615,6 @@ static void __init early_reserve_mem(void)
         }
 }
 
-#ifdef CONFIG_PHYP_DUMP
-/**
- * phyp_dump_calculate_reserve_size() - reserve variable boot area 5% or arg
- *
- * Function to find the largest size we need to reserve
- * during early boot process.
- *
- * It either looks for boot param and returns that OR
- * returns larger of 256 or 5% rounded down to multiples of 256MB.
- *
- */
-static inline unsigned long phyp_dump_calculate_reserve_size(void)
-{
-        unsigned long tmp;
-
-        if (phyp_dump_info->reserve_bootvar)
-                return phyp_dump_info->reserve_bootvar;
-
-        /* divide by 20 to get 5% of value */
-        tmp = memblock_end_of_DRAM();
-        do_div(tmp, 20);
-
-        /* round it down in multiples of 256 */
-        tmp = tmp & ~0x0FFFFFFFUL;
-
-        return (tmp > PHYP_DUMP_RMR_END ? tmp : PHYP_DUMP_RMR_END);
-}
-
-/**
- * phyp_dump_reserve_mem() - reserve all not-yet-dumped mmemory
- *
- * This routine may reserve memory regions in the kernel only
- * if the system is supported and a dump was taken in last
- * boot instance or if the hardware is supported and the
- * scratch area needs to be setup. In other instances it returns
- * without reserving anything. The memory in case of dump being
- * active is freed when the dump is collected (by userland tools).
- */
-static void __init phyp_dump_reserve_mem(void)
-{
-        unsigned long base, size;
-        unsigned long variable_reserve_size;
-
-        if (!phyp_dump_info->phyp_dump_configured) {
-                printk(KERN_ERR "Phyp-dump not supported on this hardware\n");
-                return;
-        }
-
-        if (!phyp_dump_info->phyp_dump_at_boot) {
-                printk(KERN_INFO "Phyp-dump disabled at boot time\n");
-                return;
-        }
-
-        variable_reserve_size = phyp_dump_calculate_reserve_size();
-
-        if (phyp_dump_info->phyp_dump_is_active) {
-                /* Reserve *everything* above RMR.Area freed by userland tools*/
-                base = variable_reserve_size;
-                size = memblock_end_of_DRAM() - base;
-
-                /* XXX crashed_ram_end is wrong, since it may be beyond
-                 * the memory_limit, it will need to be adjusted. */
-                memblock_reserve(base, size);
-
-                phyp_dump_info->init_reserve_start = base;
-                phyp_dump_info->init_reserve_size = size;
-        } else {
-                size = phyp_dump_info->cpu_state_size +
-                        phyp_dump_info->hpte_region_size +
-                        variable_reserve_size;
-                base = memblock_end_of_DRAM() - size;
-                memblock_reserve(base, size);
-                phyp_dump_info->init_reserve_start = base;
-                phyp_dump_info->init_reserve_size = size;
-        }
-}
-#else
-static inline void __init phyp_dump_reserve_mem(void) {}
-#endif /* CONFIG_PHYP_DUMP  && CONFIG_PPC_RTAS */
-
 void __init early_init_devtree(void *params)
 {
         phys_addr_t limit;
@@ -714,9 +634,9 @@ void __init early_init_devtree(void *params)
         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);
+#ifdef CONFIG_FA_DUMP
+        /* scan tree to see if dump is active during last boot */
+        of_scan_flat_dt(early_init_dt_scan_fw_dump, NULL);
 #endif
 
         /* Pre-initialize the cmd_line with the content of boot_commmand_line,
@@ -750,9 +670,15 @@ void __init early_init_devtree(void *params)
         if (PHYSICAL_START > MEMORY_START)
                 memblock_reserve(MEMORY_START, 0x8000);
         reserve_kdump_trampoline();
-        reserve_crashkernel();
+#ifdef CONFIG_FA_DUMP
+        /*
+         * If we fail to reserve memory for firmware-assisted dump then
+         * fallback to kexec based kdump.
+         */
+        if (fadump_reserve_mem() == 0)
+#endif
+                reserve_crashkernel();
         early_reserve_mem();
-        phyp_dump_reserve_mem();
 
         /*
          * Ensure that total memory size is page-aligned, because otherwise
diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index eca626ea3f23..ea4e311e09d2 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -48,14 +48,6 @@
 #include <linux/linux_logo.h>
 
 /*
- * Properties whose value is longer than this get excluded from our
- * copy of the device tree. This value does need to be big enough to
- * ensure that we don't lose things like the interrupt-map property
- * on a PCI-PCI bridge.
- */
-#define MAX_PROPERTY_LENGTH     (1UL * 1024 * 1024)
-
-/*
  * Eventually bump that one up
  */
 #define DEVTREE_CHUNK_SIZE      0x100000
@@ -455,7 +447,7 @@ static void __init __attribute__((noreturn)) prom_panic(const char *reason)
         if (RELOC(of_platform) == PLATFORM_POWERMAC)
                 asm("trap\n");
 
-        /* ToDo: should put up an SRC here on p/iSeries */
+        /* ToDo: should put up an SRC here on pSeries */
         call_prom("exit", 0, 0);
 
         for (;;)                        /* should never get here */
@@ -2273,13 +2265,6 @@ static void __init scan_dt_build_struct(phandle node, unsigned long *mem_start,
                 /* sanity checks */
                 if (l == PROM_ERROR)
                         continue;
-                if (l > MAX_PROPERTY_LENGTH) {
-                        prom_printf("WARNING: ignoring large property ");
-                        /* It seems OF doesn't null-terminate the path :-( */
-                        prom_printf("[%s] ", path);
-                        prom_printf("%s length 0x%x\n", RELOC(pname), l);
-                        continue;
-                }
 
                 /* push property head */
                 dt_push_token(OF_DT_PROP, mem_start, mem_end);
diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c
index 517b1d8f455b..4d1a7babe342 100644
--- a/arch/powerpc/kernel/rtas.c
+++ b/arch/powerpc/kernel/rtas.c
@@ -716,7 +716,6 @@ static int __rtas_suspend_last_cpu(struct rtas_suspend_me_data *data, int wake_w
         int cpu;
 
         slb_set_size(SLB_MIN_SIZE);
-        stop_topology_update();
         printk(KERN_DEBUG "calling ibm,suspend-me on cpu %i\n", smp_processor_id());
 
         while (rc == H_MULTI_THREADS_ACTIVE && !atomic_read(&data->done) &&
@@ -732,7 +731,6 @@ static int __rtas_suspend_last_cpu(struct rtas_suspend_me_data *data, int wake_w
                 rc = atomic_read(&data->error);
 
         atomic_set(&data->error, rc);
-        start_topology_update();
         pSeries_coalesce_init();
 
         if (wake_when_done) {
@@ -846,6 +844,7 @@ int rtas_ibm_suspend_me(struct rtas_args *args)
         atomic_set(&data.error, 0);
         data.token = rtas_token("ibm,suspend-me");
         data.complete = &done;
+        stop_topology_update();
 
         /* Call function on all CPUs.  One of us will make the
          * rtas call
@@ -858,6 +857,8 @@ int rtas_ibm_suspend_me(struct rtas_args *args)
         if (atomic_read(&data.error) != 0)
                 printk(KERN_ERR "Error doing global join\n");
 
+        start_topology_update();
+
         return atomic_read(&data.error);
 }
 #else /* CONFIG_PPC_PSERIES */
@@ -867,6 +868,40 @@ int rtas_ibm_suspend_me(struct rtas_args *args)
 }
 #endif
 
+/**
+ * Find a specific pseries error log in an RTAS extended event log.
+ * @log: RTAS error/event log
+ * @section_id: two character section identifier
+ *
+ * Returns a pointer to the specified errorlog or NULL if not found.
+ */
+struct pseries_errorlog *get_pseries_errorlog(struct rtas_error_log *log,
+                                              uint16_t section_id)
+{
+        struct rtas_ext_event_log_v6 *ext_log =
+                (struct rtas_ext_event_log_v6 *)log->buffer;
+        struct pseries_errorlog *sect;
+        unsigned char *p, *log_end;
+
+        /* Check that we understand the format */
+        if (log->extended_log_length < sizeof(struct rtas_ext_event_log_v6) ||
+            ext_log->log_format != RTAS_V6EXT_LOG_FORMAT_EVENT_LOG ||
+            ext_log->company_id != RTAS_V6EXT_COMPANY_ID_IBM)
+                return NULL;
+
+        log_end = log->buffer + log->extended_log_length;
+        p = ext_log->vendor_log;
+
+        while (p < log_end) {
+                sect = (struct pseries_errorlog *)p;
+                if (sect->id == section_id)
+                        return sect;
+                p += sect->length;
+        }
+
+        return NULL;
+}
+
 asmlinkage int ppc_rtas(struct rtas_args __user *uargs)
 {
         struct rtas_args args;
diff --git a/arch/powerpc/kernel/rtas_pci.c b/arch/powerpc/kernel/rtas_pci.c
index 6cd8f0196b6d..179af906dcda 100644
--- a/arch/powerpc/kernel/rtas_pci.c
+++ b/arch/powerpc/kernel/rtas_pci.c
@@ -275,8 +275,11 @@ void __init find_and_init_phbs(void)
         of_node_put(root);
         pci_devs_phb_init();
 
+        /* Create EEH devices for all PHBs */
+        eeh_dev_phb_init();
+
         /*
-         * pci_probe_only and pci_assign_all_buses can be set via properties
+         * PCI_PROBE_ONLY and PCI_REASSIGN_ALL_BUS can be set via properties
          * in chosen.
          */
         if (of_chosen) {
@@ -284,8 +287,12 @@ void __init find_and_init_phbs(void)
 
                 prop = of_get_property(of_chosen,
                                 "linux,pci-probe-only", NULL);
-                if (prop)
-                        pci_probe_only = *prop;
+                if (prop) {
+                        if (*prop)
+                                pci_add_flags(PCI_PROBE_ONLY);
+                        else
+                                pci_clear_flags(PCI_PROBE_ONLY);
+                }
 
 #ifdef CONFIG_PPC32 /* Will be made generic soon */
                 prop = of_get_property(of_chosen,
diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index 77bb77da05c1..b0ebdeab9494 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -61,6 +61,7 @@
 #include <asm/xmon.h>
 #include <asm/cputhreads.h>
 #include <mm/mmu_decl.h>
+#include <asm/fadump.h>
 
 #include "setup.h"
 
@@ -109,6 +110,14 @@ EXPORT_SYMBOL(ppc_do_canonicalize_irqs);
 /* also used by kexec */
 void machine_shutdown(void)
 {
+#ifdef CONFIG_FA_DUMP
+        /*
+         * if fadump is active, cleanup the fadump registration before we
+         * shutdown.
+         */
+        fadump_cleanup();
+#endif
+
         if (ppc_md.machine_shutdown)
                 ppc_md.machine_shutdown();
 }
@@ -639,6 +648,11 @@ EXPORT_SYMBOL(check_legacy_ioport);
 static int ppc_panic_event(struct notifier_block *this,
                              unsigned long event, void *ptr)
 {
+        /*
+         * If firmware-assisted dump has been registered then trigger
+         * firmware-assisted dump and let firmware handle everything else.
+         */
+        crash_fadump(NULL, ptr);
         ppc_md.panic(ptr);  /* May not return */
         return NOTIFY_DONE;
 }
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 4cb8f1e9d044..4721b0c8d7b7 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -598,7 +598,7 @@ void __init setup_arch(char **cmdline_p)
         /* Initialize the MMU context management stuff */
         mmu_context_init();
 
-        kvm_rma_init();
+        kvm_linear_init();
 
         ppc64_boot_msg(0x15, "Setup Done");
 }
diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c
index 2300426e531a..7006b7f4267a 100644
--- a/arch/powerpc/kernel/signal.c
+++ b/arch/powerpc/kernel/signal.c
@@ -11,6 +11,7 @@
 
 #include <linux/tracehook.h>
 #include <linux/signal.h>
+#include <linux/key.h>
 #include <asm/hw_breakpoint.h>
 #include <asm/uaccess.h>
 #include <asm/unistd.h>
@@ -56,10 +57,7 @@ void __user * get_sigframe(struct k_sigaction *ka, struct pt_regs *regs,
 void restore_sigmask(sigset_t *set)
 {
         sigdelsetmask(set, ~_BLOCKABLE);
-        spin_lock_irq(&current->sighand->siglock);
-        current->blocked = *set;
-        recalc_sigpending();
-        spin_unlock_irq(&current->sighand->siglock);
+        set_current_blocked(set);
 }
 
 static void check_syscall_restart(struct pt_regs *regs, struct k_sigaction *ka,
@@ -113,8 +111,9 @@ static void check_syscall_restart(struct pt_regs *regs, struct k_sigaction *ka,
         }
 }
 
-static int do_signal_pending(sigset_t *oldset, struct pt_regs *regs)
+static int do_signal(struct pt_regs *regs)
 {
+        sigset_t *oldset;
         siginfo_t info;
         int signr;
         struct k_sigaction ka;
@@ -123,7 +122,7 @@ static int do_signal_pending(sigset_t *oldset, struct pt_regs *regs)
 
         if (current_thread_info()->local_flags & _TLF_RESTORE_SIGMASK)
                 oldset = &current->saved_sigmask;
-        else if (!oldset)
+        else
                 oldset = &current->blocked;
 
         signr = get_signal_to_deliver(&info, &ka, regs, NULL);
@@ -167,13 +166,7 @@ static int do_signal_pending(sigset_t *oldset, struct pt_regs *regs)
 
         regs->trap = 0;
         if (ret) {
-                spin_lock_irq(&current->sighand->siglock);
-                sigorsets(&current->blocked, &current->blocked,
-                          &ka.sa.sa_mask);
-                if (!(ka.sa.sa_flags & SA_NODEFER))
-                        sigaddset(&current->blocked, signr);
-                recalc_sigpending();
-                spin_unlock_irq(&current->sighand->siglock);
+                block_sigmask(&ka, signr);
 
                 /*
                  * A signal was successfully delivered; the saved sigmask is in
@@ -191,14 +184,16 @@ static int do_signal_pending(sigset_t *oldset, struct pt_regs *regs)
         return ret;
 }
 
-void do_signal(struct pt_regs *regs, unsigned long thread_info_flags)
+void do_notify_resume(struct pt_regs *regs, unsigned long thread_info_flags)
 {
         if (thread_info_flags & _TIF_SIGPENDING)
-                do_signal_pending(NULL, regs);
+                do_signal(regs);
 
         if (thread_info_flags & _TIF_NOTIFY_RESUME) {
                 clear_thread_flag(TIF_NOTIFY_RESUME);
                 tracehook_notify_resume(regs);
+                if (current->replacement_session_keyring)
+                        key_replace_session_keyring();
         }
 }
 
diff --git a/arch/powerpc/kernel/signal.h b/arch/powerpc/kernel/signal.h
index 6c0ddfc0603e..8dde973aaaf5 100644
--- a/arch/powerpc/kernel/signal.h
+++ b/arch/powerpc/kernel/signal.h
@@ -12,7 +12,7 @@
 
 #define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP)))
 
-extern void do_signal(struct pt_regs *regs, unsigned long thread_info_flags);
+extern void do_notify_resume(struct pt_regs *regs, unsigned long thread_info_flags);
 
 extern void __user * get_sigframe(struct k_sigaction *ka, struct pt_regs *regs,
                                   size_t frame_size, int is_32);
diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c
index 836a5a19eb2c..e061ef5dd449 100644
--- a/arch/powerpc/kernel/signal_32.c
+++ b/arch/powerpc/kernel/signal_32.c
@@ -242,12 +242,13 @@ static inline int restore_general_regs(struct pt_regs *regs,
  */
 long sys_sigsuspend(old_sigset_t mask)
 {
-        mask &= _BLOCKABLE;
-        spin_lock_irq(&current->sighand->siglock);
+        sigset_t blocked;
+
         current->saved_sigmask = current->blocked;
-        siginitset(&current->blocked, mask);
-        recalc_sigpending();
-        spin_unlock_irq(&current->sighand->siglock);
+
+        mask &= _BLOCKABLE;
+        siginitset(&blocked, mask);
+        set_current_blocked(&blocked);
 
         current->state = TASK_INTERRUPTIBLE;
         schedule();
diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c
index 883e74c0d1b3..0c683d376b1c 100644
--- a/arch/powerpc/kernel/sysfs.c
+++ b/arch/powerpc/kernel/sysfs.c
@@ -12,7 +12,6 @@
 #include <asm/current.h>
 #include <asm/processor.h>
 #include <asm/cputable.h>
-#include <asm/firmware.h>
 #include <asm/hvcall.h>
 #include <asm/prom.h>
 #include <asm/machdep.h>
@@ -341,8 +340,7 @@ static void __cpuinit register_cpu_online(unsigned int cpu)
         int i, nattrs;
 
 #ifdef CONFIG_PPC64
-        if (!firmware_has_feature(FW_FEATURE_ISERIES) &&
-                        cpu_has_feature(CPU_FTR_SMT))
+        if (cpu_has_feature(CPU_FTR_SMT))
                 device_create_file(s, &dev_attr_smt_snooze_delay);
 #endif
 
@@ -414,8 +412,7 @@ static void unregister_cpu_online(unsigned int cpu)
         BUG_ON(!c->hotpluggable);
 
 #ifdef CONFIG_PPC64
-        if (!firmware_has_feature(FW_FEATURE_ISERIES) &&
-                        cpu_has_feature(CPU_FTR_SMT))
+        if (cpu_has_feature(CPU_FTR_SMT))
                 device_remove_file(s, &dev_attr_smt_snooze_delay);
 #endif
 
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 567dd7c3ac2a..2c42cd72d0f5 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -17,8 +17,7 @@
  *
  * TODO (not necessarily in this file):
  * - improve precision and reproducibility of timebase frequency
- * measurement at boot time. (for iSeries, we calibrate the timebase
- * against the Titan chip's clock.)
+ * measurement at boot time.
  * - for astronomical applications: add a new function to get
  * non ambiguous timestamps even around leap seconds. This needs
  * a new timestamp format and a good name.
@@ -70,10 +69,6 @@
 #include <asm/vdso_datapage.h>
 #include <asm/firmware.h>
 #include <asm/cputime.h>
-#ifdef CONFIG_PPC_ISERIES
-#include <asm/iseries/it_lp_queue.h>
-#include <asm/iseries/hv_call_xm.h>
-#endif
 
 /* powerpc clocksource/clockevent code */
 
@@ -117,14 +112,6 @@ static struct clock_event_device decrementer_clockevent = {
 DEFINE_PER_CPU(u64, decrementers_next_tb);
 static DEFINE_PER_CPU(struct clock_event_device, decrementers);
 
-#ifdef CONFIG_PPC_ISERIES
-static unsigned long __initdata iSeries_recal_titan;
-static signed long __initdata iSeries_recal_tb;
-
-/* Forward declaration is only needed for iSereis compiles */
-static void __init clocksource_init(void);
-#endif
-
 #define XSEC_PER_SEC (1024*1024)
 
 #ifdef CONFIG_PPC64
@@ -259,7 +246,6 @@ void accumulate_stolen_time(void)
         u64 sst, ust;
 
         u8 save_soft_enabled = local_paca->soft_enabled;
-        u8 save_hard_enabled = local_paca->hard_enabled;
 
         /* We are called early in the exception entry, before
          * soft/hard_enabled are sync'ed to the expected state
@@ -268,7 +254,6 @@ void accumulate_stolen_time(void)
          * complain
          */
         local_paca->soft_enabled = 0;
-        local_paca->hard_enabled = 0;
 
         sst = scan_dispatch_log(local_paca->starttime_user);
         ust = scan_dispatch_log(local_paca->starttime);
@@ -277,7 +262,6 @@ void accumulate_stolen_time(void)
         local_paca->stolen_time += ust + sst;
 
         local_paca->soft_enabled = save_soft_enabled;
-        local_paca->hard_enabled = save_hard_enabled;
 }
 
 static inline u64 calculate_stolen_time(u64 stop_tb)
@@ -426,74 +410,6 @@ unsigned long profile_pc(struct pt_regs *regs)
 EXPORT_SYMBOL(profile_pc);
 #endif
 
-#ifdef CONFIG_PPC_ISERIES
-
-/* 
- * This function recalibrates the timebase based on the 49-bit time-of-day
- * value in the Titan chip.  The Titan is much more accurate than the value
- * returned by the service processor for the timebase frequency.
- */
-
-static int __init iSeries_tb_recal(void)
-{
-        unsigned long titan, tb;
-
-        /* Make sure we only run on iSeries */
-        if (!firmware_has_feature(FW_FEATURE_ISERIES))
-                return -ENODEV;
-
-        tb = get_tb();
-        titan = HvCallXm_loadTod();
-        if ( iSeries_recal_titan ) {
-                unsigned long tb_ticks = tb - iSeries_recal_tb;
-                unsigned long titan_usec = (titan - iSeries_recal_titan) >> 12;
-                unsigned long new_tb_ticks_per_sec   = (tb_ticks * USEC_PER_SEC)/titan_usec;
-                unsigned long new_tb_ticks_per_jiffy =
-                        DIV_ROUND_CLOSEST(new_tb_ticks_per_sec, HZ);
-                long tick_diff = new_tb_ticks_per_jiffy - tb_ticks_per_jiffy;
-                char sign = '+';                
-                /* make sure tb_ticks_per_sec and tb_ticks_per_jiffy are consistent */
-                new_tb_ticks_per_sec = new_tb_ticks_per_jiffy * HZ;
-
-                if ( tick_diff < 0 ) {
-                        tick_diff = -tick_diff;
-                        sign = '-';
-                }
-                if ( tick_diff ) {
-                        if ( tick_diff < tb_ticks_per_jiffy/25 ) {
-                                printk( "Titan recalibrate: new tb_ticks_per_jiffy = %lu (%c%ld)\n",
-                                                new_tb_ticks_per_jiffy, sign, tick_diff );
-                                tb_ticks_per_jiffy = new_tb_ticks_per_jiffy;
-                                tb_ticks_per_sec   = new_tb_ticks_per_sec;
-                                calc_cputime_factors();
-                                vdso_data->tb_ticks_per_sec = tb_ticks_per_sec;
-                                setup_cputime_one_jiffy();
-                        }
-                        else {
-                                printk( "Titan recalibrate: FAILED (difference > 4 percent)\n"
-                                        "                   new tb_ticks_per_jiffy = %lu\n"
-                                        "                   old tb_ticks_per_jiffy = %lu\n",
-                                        new_tb_ticks_per_jiffy, tb_ticks_per_jiffy );
-                        }
-                }
-        }
-        iSeries_recal_titan = titan;
-        iSeries_recal_tb = tb;
-
-        /* Called here as now we know accurate values for the timebase */
-        clocksource_init();
-        return 0;
-}
-late_initcall(iSeries_tb_recal);
-
-/* Called from platform early init */
-void __init iSeries_time_init_early(void)
-{
-        iSeries_recal_tb = get_tb();
-        iSeries_recal_titan = HvCallXm_loadTod();
-}
-#endif /* CONFIG_PPC_ISERIES */
-
 #ifdef CONFIG_IRQ_WORK
 
 /*
@@ -550,16 +466,6 @@ void arch_irq_work_raise(void)
 #endif /* CONFIG_IRQ_WORK */
 
 /*
- * For iSeries shared processors, we have to let the hypervisor
- * set the hardware decrementer.  We set a virtual decrementer
- * in the lppaca and call the hypervisor if the virtual
- * decrementer is less than the current value in the hardware
- * decrementer. (almost always the new decrementer value will
- * be greater than the current hardware decementer so the hypervisor
- * call will not be needed)
- */
-
-/*
  * timer_interrupt - gets called when the decrementer overflows,
  * with interrupts disabled.
  */
@@ -580,6 +486,11 @@ void timer_interrupt(struct pt_regs * regs)
         if (!cpu_online(smp_processor_id()))
                 return;
 
+        /* Conditionally hard-enable interrupts now that the DEC has been
+         * bumped to its maximum value
+         */
+        may_hard_irq_enable();
+
         trace_timer_interrupt_entry(regs);
 
         __get_cpu_var(irq_stat).timer_irqs++;
@@ -597,20 +508,10 @@ void timer_interrupt(struct pt_regs * regs)
                 irq_work_run();
         }
 
-#ifdef CONFIG_PPC_ISERIES
-        if (firmware_has_feature(FW_FEATURE_ISERIES))
-                get_lppaca()->int_dword.fields.decr_int = 0;
-#endif
-
         *next_tb = ~(u64)0;
         if (evt->event_handler)
                 evt->event_handler(evt);
 
-#ifdef CONFIG_PPC_ISERIES
-        if (firmware_has_feature(FW_FEATURE_ISERIES) && hvlpevent_is_pending())
-                process_hvlpevents();
-#endif
-
 #ifdef CONFIG_PPC64
         /* collect purr register values often, for accurate calculations */
         if (firmware_has_feature(FW_FEATURE_SPLPAR)) {
@@ -982,9 +883,8 @@ void __init time_init(void)
          */
         start_cpu_decrementer();
 
-        /* Register the clocksource, if we're not running on iSeries */
-        if (!firmware_has_feature(FW_FEATURE_ISERIES))
-                clocksource_init();
+        /* Register the clocksource */
+        clocksource_init();
 
         init_decrementer_clockevent();
 }
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index c091527efd89..a750409ccc4e 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -57,6 +57,7 @@
 #include <asm/kexec.h>
 #include <asm/ppc-opcode.h>
 #include <asm/rio.h>
+#include <asm/fadump.h>
 
 #if defined(CONFIG_DEBUGGER) || defined(CONFIG_KEXEC)
 int (*__debugger)(struct pt_regs *regs) __read_mostly;
@@ -145,6 +146,8 @@ static void __kprobes oops_end(unsigned long flags, struct pt_regs *regs,
                 arch_spin_unlock(&die_lock);
         raw_local_irq_restore(flags);
 
+        crash_fadump(regs, "die oops");
+
         /*
          * A system reset (0x100) is a request to dump, so we always send
          * it through the crashdump code.
@@ -244,6 +247,9 @@ void _exception(int signr, struct pt_regs *regs, int code, unsigned long addr)
                                    addr, regs->nip, regs->link, code);
         }
 
+        if (!arch_irq_disabled_regs(regs))
+                local_irq_enable();
+
         memset(&info, 0, sizeof(info));
         info.si_signo = signr;
         info.si_code = code;
diff --git a/arch/powerpc/kernel/udbg.c b/arch/powerpc/kernel/udbg.c
index 57fa2c0a531c..c39c1ca77f46 100644
--- a/arch/powerpc/kernel/udbg.c
+++ b/arch/powerpc/kernel/udbg.c
@@ -46,9 +46,6 @@ void __init udbg_early_init(void)
 #elif defined(CONFIG_PPC_EARLY_DEBUG_MAPLE)
         /* Maple real mode debug */
         udbg_init_maple_realmode();
-#elif defined(CONFIG_PPC_EARLY_DEBUG_ISERIES)
-        /* For iSeries - hit Ctrl-x Ctrl-x to see the output */
-        udbg_init_iseries();
 #elif defined(CONFIG_PPC_EARLY_DEBUG_BEAT)
         udbg_init_debug_beat();
 #elif defined(CONFIG_PPC_EARLY_DEBUG_PAS_REALMODE)
diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c
index 7d14bb697d40..972cca278f98 100644
--- a/arch/powerpc/kernel/vdso.c
+++ b/arch/powerpc/kernel/vdso.c
@@ -263,17 +263,11 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
          * the "data" page of the vDSO or you'll stop getting kernel updates
          * and your nice userland gettimeofday will be totally dead.
          * It's fine to use that for setting breakpoints in the vDSO code
-         * pages though
-         *
-         * Make sure the vDSO gets into every core dump.
-         * Dumping its contents makes post-mortem fully interpretable later
-         * without matching up the same kernel and hardware config to see
-         * what PC values meant.
+         * pages though.
          */
         rc = install_special_mapping(mm, vdso_base, vdso_pages << PAGE_SHIFT,
                                      VM_READ|VM_EXEC|
-                                     VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC|
-                                     VM_ALWAYSDUMP,
+                                     VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC,
                                      vdso_pagelist);
         if (rc) {
                 current->mm->context.vdso_base = 0;
@@ -727,10 +721,10 @@ static int __init vdso_init(void)
         vdso_data->version.minor = SYSTEMCFG_MINOR;
         vdso_data->processor = mfspr(SPRN_PVR);
         /*
-         * Fake the old platform number for pSeries and iSeries and add
+         * Fake the old platform number for pSeries and add
          * in LPAR bit if necessary
          */
-        vdso_data->platform = machine_is(iseries) ? 0x200 : 0x100;
+        vdso_data->platform = 0x100;
         if (firmware_has_feature(FW_FEATURE_LPAR))
                 vdso_data->platform |= 1;
         vdso_data->physicalMemorySize = memblock_phys_mem_size();
diff --git a/arch/powerpc/kernel/vio.c b/arch/powerpc/kernel/vio.c
index 8b086299ba25..b2f7c8480bf6 100644
--- a/arch/powerpc/kernel/vio.c
+++ b/arch/powerpc/kernel/vio.c
@@ -34,11 +34,6 @@
 #include <asm/abs_addr.h>
 #include <asm/page.h>
 #include <asm/hvcall.h>
-#include <asm/iseries/vio.h>
-#include <asm/iseries/hv_types.h>
-#include <asm/iseries/hv_lp_config.h>
-#include <asm/iseries/hv_call_xm.h>
-#include <asm/iseries/iommu.h>
 
 static struct bus_type vio_bus_type;
 
@@ -1042,7 +1037,6 @@ static void vio_cmo_sysfs_init(void)
         vio_bus_type.bus_attrs = vio_cmo_bus_attrs;
 }
 #else /* CONFIG_PPC_SMLPAR */
-/* Dummy functions for iSeries platform */
 int vio_cmo_entitlement_update(size_t new_entitlement) { return 0; }
 void vio_cmo_set_dev_desired(struct vio_dev *viodev, size_t desired) {}
 static int vio_cmo_bus_probe(struct vio_dev *viodev) { return 0; }
@@ -1060,9 +1054,6 @@ static struct iommu_table *vio_build_iommu_table(struct vio_dev *dev)
         struct iommu_table *tbl;
         unsigned long offset, size;
 
-        if (firmware_has_feature(FW_FEATURE_ISERIES))
-                return vio_build_iommu_table_iseries(dev);
-
         dma_window = of_get_property(dev->dev.of_node,
                                   "ibm,my-dma-window", NULL);
         if (!dma_window)
@@ -1168,17 +1159,21 @@ static int vio_bus_remove(struct device *dev)
  * vio_register_driver: - Register a new vio driver
  * @drv:        The vio_driver structure to be registered.
  */
-int vio_register_driver(struct vio_driver *viodrv)
+int __vio_register_driver(struct vio_driver *viodrv, struct module *owner,
+                          const char *mod_name)
 {
-        printk(KERN_DEBUG "%s: driver %s registering\n", __func__,
-                viodrv->driver.name);
+        pr_debug("%s: driver %s registering\n", __func__, viodrv->name);
 
         /* fill in 'struct driver' fields */
+        viodrv->driver.name = viodrv->name;
+        viodrv->driver.pm = viodrv->pm;
         viodrv->driver.bus = &vio_bus_type;
+        viodrv->driver.owner = owner;
+        viodrv->driver.mod_name = mod_name;
 
         return driver_register(&viodrv->driver);
 }
-EXPORT_SYMBOL(vio_register_driver);
+EXPORT_SYMBOL(__vio_register_driver);
 
 /**
  * vio_unregister_driver - Remove registration of vio driver.
@@ -1195,8 +1190,7 @@ static void __devinit vio_dev_release(struct device *dev)
 {
         struct iommu_table *tbl = get_iommu_table_base(dev);
 
-        /* iSeries uses a common table for all vio devices */
-        if (!firmware_has_feature(FW_FEATURE_ISERIES) && tbl)
+        if (tbl)
                 iommu_free_table(tbl, dev->of_node ?
                         dev->of_node->full_name : dev_name(dev));
         of_node_put(dev->of_node);
@@ -1244,12 +1238,6 @@ struct vio_dev *vio_register_device_node(struct device_node *of_node)
         viodev->name = of_node->name;
         viodev->type = of_node->type;
         viodev->unit_address = *unit_address;
-        if (firmware_has_feature(FW_FEATURE_ISERIES)) {
-                unit_address = of_get_property(of_node,
-                                "linux,unit_address", NULL);
-                if (unit_address != NULL)
-                        viodev->unit_address = *unit_address;
-        }
         viodev->dev.of_node = of_node_get(of_node);
 
         if (firmware_has_feature(FW_FEATURE_CMO))
diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S
index 710a54005dfb..65d1c08cf09e 100644
--- a/arch/powerpc/kernel/vmlinux.lds.S
+++ b/arch/powerpc/kernel/vmlinux.lds.S
@@ -109,11 +109,6 @@ SECTIONS
                 __ptov_table_begin = .;
                 *(.ptov_fixup);
                 __ptov_table_end = .;
-#ifdef CONFIG_PPC_ISERIES
-                __dt_strings_start = .;
-                *(.dt_strings);
-                __dt_strings_end = .;
-#endif
         }
 
         .init.setup : AT(ADDR(.init.setup) - LOAD_OFFSET) {
diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig
index 78133deb4b64..8f64709ae331 100644
--- a/arch/powerpc/kvm/Kconfig
+++ b/arch/powerpc/kvm/Kconfig
@@ -69,6 +69,7 @@ config KVM_BOOK3S_64
 config KVM_BOOK3S_64_HV
         bool "KVM support for POWER7 and PPC970 using hypervisor mode in host"
         depends on KVM_BOOK3S_64
+        select MMU_NOTIFIER
         ---help---
           Support running unmodified book3s_64 guest kernels in
           virtual machines on POWER7 and PPC970 processors that have
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index e41ac6f7dcf1..7d54f4ed6d96 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -258,7 +258,7 @@ static bool clear_irqprio(struct kvm_vcpu *vcpu, unsigned int priority)
         return true;
 }
 
-void kvmppc_core_deliver_interrupts(struct kvm_vcpu *vcpu)
+void kvmppc_core_prepare_to_enter(struct kvm_vcpu *vcpu)
 {
         unsigned long *pending = &vcpu->arch.pending_exceptions;
         unsigned long old_pending = vcpu->arch.pending_exceptions;
@@ -423,10 +423,10 @@ int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
         regs->sprg1 = vcpu->arch.shared->sprg1;
         regs->sprg2 = vcpu->arch.shared->sprg2;
         regs->sprg3 = vcpu->arch.shared->sprg3;
-        regs->sprg4 = vcpu->arch.sprg4;
-        regs->sprg5 = vcpu->arch.sprg5;
-        regs->sprg6 = vcpu->arch.sprg6;
-        regs->sprg7 = vcpu->arch.sprg7;
+        regs->sprg4 = vcpu->arch.shared->sprg4;
+        regs->sprg5 = vcpu->arch.shared->sprg5;
+        regs->sprg6 = vcpu->arch.shared->sprg6;
+        regs->sprg7 = vcpu->arch.shared->sprg7;
 
         for (i = 0; i < ARRAY_SIZE(regs->gpr); i++)
                 regs->gpr[i] = kvmppc_get_gpr(vcpu, i);
@@ -450,10 +450,10 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
         vcpu->arch.shared->sprg1 = regs->sprg1;
         vcpu->arch.shared->sprg2 = regs->sprg2;
         vcpu->arch.shared->sprg3 = regs->sprg3;
-        vcpu->arch.sprg4 = regs->sprg4;
-        vcpu->arch.sprg5 = regs->sprg5;
-        vcpu->arch.sprg6 = regs->sprg6;
-        vcpu->arch.sprg7 = regs->sprg7;
+        vcpu->arch.shared->sprg4 = regs->sprg4;
+        vcpu->arch.shared->sprg5 = regs->sprg5;
+        vcpu->arch.shared->sprg6 = regs->sprg6;
+        vcpu->arch.shared->sprg7 = regs->sprg7;
 
         for (i = 0; i < ARRAY_SIZE(regs->gpr); i++)
                 kvmppc_set_gpr(vcpu, i, regs->gpr[i]);
@@ -477,41 +477,10 @@ int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu,
         return 0;
 }
 
-/*
- * Get (and clear) the dirty memory log for a memory slot.
- */
-int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
-                                      struct kvm_dirty_log *log)
+void kvmppc_decrementer_func(unsigned long data)
 {
-        struct kvm_memory_slot *memslot;
-        struct kvm_vcpu *vcpu;
-        ulong ga, ga_end;
-        int is_dirty = 0;
-        int r;
-        unsigned long n;
-
-        mutex_lock(&kvm->slots_lock);
-
-        r = kvm_get_dirty_log(kvm, log, &is_dirty);
-        if (r)
-                goto out;
-
-        /* If nothing is dirty, don't bother messing with page tables. */
-        if (is_dirty) {
-                memslot = id_to_memslot(kvm->memslots, log->slot);
+        struct kvm_vcpu *vcpu = (struct kvm_vcpu *)data;
 
-                ga = memslot->base_gfn << PAGE_SHIFT;
-                ga_end = ga + (memslot->npages << PAGE_SHIFT);
-
-                kvm_for_each_vcpu(n, vcpu, kvm)
-                        kvmppc_mmu_pte_pflush(vcpu, ga, ga_end);
-
-                n = kvm_dirty_bitmap_bytes(memslot);
-                memset(memslot->dirty_bitmap, 0, n);
-        }
-
-        r = 0;
-out:
-        mutex_unlock(&kvm->slots_lock);
-        return r;
+        kvmppc_core_queue_dec(vcpu);
+        kvm_vcpu_kick(vcpu);
 }
diff --git a/arch/powerpc/kvm/book3s_32_mmu_host.c b/arch/powerpc/kvm/book3s_32_mmu_host.c
index 9fecbfbce773..f922c29bb234 100644
--- a/arch/powerpc/kvm/book3s_32_mmu_host.c
+++ b/arch/powerpc/kvm/book3s_32_mmu_host.c
@@ -151,13 +151,15 @@ int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte)
         bool primary = false;
         bool evict = false;
         struct hpte_cache *pte;
+        int r = 0;
 
         /* Get host physical address for gpa */
         hpaddr = kvmppc_gfn_to_pfn(vcpu, orig_pte->raddr >> PAGE_SHIFT);
         if (is_error_pfn(hpaddr)) {
                 printk(KERN_INFO "Couldn't get guest page for gfn %lx!\n",
                                  orig_pte->eaddr);
-                return -EINVAL;
+                r = -EINVAL;
+                goto out;
         }
         hpaddr <<= PAGE_SHIFT;
 
@@ -249,7 +251,8 @@ next_pteg:
 
         kvmppc_mmu_hpte_cache_map(vcpu, pte);
 
-        return 0;
+out:
+        return r;
 }
 
 static struct kvmppc_sid_map *create_sid_map(struct kvm_vcpu *vcpu, u64 gvsid)
@@ -297,12 +300,14 @@ int kvmppc_mmu_map_segment(struct kvm_vcpu *vcpu, ulong eaddr)
         u64 gvsid;
         u32 sr;
         struct kvmppc_sid_map *map;
-        struct kvmppc_book3s_shadow_vcpu *svcpu = to_svcpu(vcpu);
+        struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
+        int r = 0;
 
         if (vcpu->arch.mmu.esid_to_vsid(vcpu, esid, &gvsid)) {
                 /* Invalidate an entry */
                 svcpu->sr[esid] = SR_INVALID;
-                return -ENOENT;
+                r = -ENOENT;
+                goto out;
         }
 
         map = find_sid_vsid(vcpu, gvsid);
@@ -315,17 +320,21 @@ int kvmppc_mmu_map_segment(struct kvm_vcpu *vcpu, ulong eaddr)
 
         dprintk_sr("MMU: mtsr %d, 0x%x\n", esid, sr);
 
-        return 0;
+out:
+        svcpu_put(svcpu);
+        return r;
 }
 
 void kvmppc_mmu_flush_segments(struct kvm_vcpu *vcpu)
 {
         int i;
-        struct kvmppc_book3s_shadow_vcpu *svcpu = to_svcpu(vcpu);
+        struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
 
         dprintk_sr("MMU: flushing all segments (%d)\n", ARRAY_SIZE(svcpu->sr));
         for (i = 0; i < ARRAY_SIZE(svcpu->sr); i++)
                 svcpu->sr[i] = SR_INVALID;
+
+        svcpu_put(svcpu);
 }
 
 void kvmppc_mmu_destroy(struct kvm_vcpu *vcpu)
diff --git a/arch/powerpc/kvm/book3s_64_mmu_host.c b/arch/powerpc/kvm/book3s_64_mmu_host.c
index fa2f08434ba5..6f87f39a1ac2 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_host.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_host.c
@@ -88,12 +88,14 @@ int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte)
         int vflags = 0;
         int attempt = 0;
         struct kvmppc_sid_map *map;
+        int r = 0;
 
         /* Get host physical address for gpa */
         hpaddr = kvmppc_gfn_to_pfn(vcpu, orig_pte->raddr >> PAGE_SHIFT);
         if (is_error_pfn(hpaddr)) {
                 printk(KERN_INFO "Couldn't get guest page for gfn %lx!\n", orig_pte->eaddr);
-                return -EINVAL;
+                r = -EINVAL;
+                goto out;
         }
         hpaddr <<= PAGE_SHIFT;
         hpaddr |= orig_pte->raddr & (~0xfffULL & ~PAGE_MASK);
@@ -110,7 +112,8 @@ int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte)
                 printk(KERN_ERR "KVM: Segment map for 0x%llx (0x%lx) failed\n",
                                 vsid, orig_pte->eaddr);
                 WARN_ON(true);
-                return -EINVAL;
+                r = -EINVAL;
+                goto out;
         }
 
         vsid = map->host_vsid;
@@ -131,8 +134,10 @@ map_again:
 
         /* In case we tried normal mapping already, let's nuke old entries */
         if (attempt > 1)
-                if (ppc_md.hpte_remove(hpteg) < 0)
-                        return -1;
+                if (ppc_md.hpte_remove(hpteg) < 0) {
+                        r = -1;
+                        goto out;
+                }
 
         ret = ppc_md.hpte_insert(hpteg, va, hpaddr, rflags, vflags, MMU_PAGE_4K, MMU_SEGSIZE_256M);
 
@@ -162,7 +167,8 @@ map_again:
                 kvmppc_mmu_hpte_cache_map(vcpu, pte);
         }
 
-        return 0;
+out:
+        return r;
 }
 
 static struct kvmppc_sid_map *create_sid_map(struct kvm_vcpu *vcpu, u64 gvsid)
@@ -207,25 +213,30 @@ static struct kvmppc_sid_map *create_sid_map(struct kvm_vcpu *vcpu, u64 gvsid)
 
 static int kvmppc_mmu_next_segment(struct kvm_vcpu *vcpu, ulong esid)
 {
+        struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
         int i;
         int max_slb_size = 64;
         int found_inval = -1;
         int r;
 
-        if (!to_svcpu(vcpu)->slb_max)
-                to_svcpu(vcpu)->slb_max = 1;
+        if (!svcpu->slb_max)
+                svcpu->slb_max = 1;
 
         /* Are we overwriting? */
-        for (i = 1; i < to_svcpu(vcpu)->slb_max; i++) {
-                if (!(to_svcpu(vcpu)->slb[i].esid & SLB_ESID_V))
+        for (i = 1; i < svcpu->slb_max; i++) {
+                if (!(svcpu->slb[i].esid & SLB_ESID_V))
                         found_inval = i;
-                else if ((to_svcpu(vcpu)->slb[i].esid & ESID_MASK) == esid)
-                        return i;
+                else if ((svcpu->slb[i].esid & ESID_MASK) == esid) {
+                        r = i;
+                        goto out;
+                }
         }
 
         /* Found a spare entry that was invalidated before */
-        if (found_inval > 0)
-                return found_inval;
+        if (found_inval > 0) {
+                r = found_inval;
+                goto out;
+        }
 
         /* No spare invalid entry, so create one */
 
@@ -233,30 +244,35 @@ static int kvmppc_mmu_next_segment(struct kvm_vcpu *vcpu, ulong esid)
                 max_slb_size = mmu_slb_size;
 
         /* Overflowing -> purge */
-        if ((to_svcpu(vcpu)->slb_max) == max_slb_size)
+        if ((svcpu->slb_max) == max_slb_size)
                 kvmppc_mmu_flush_segments(vcpu);
 
-        r = to_svcpu(vcpu)->slb_max;
-        to_svcpu(vcpu)->slb_max++;
+        r = svcpu->slb_max;
+        svcpu->slb_max++;
 
+out:
+        svcpu_put(svcpu);
         return r;
 }
 
 int kvmppc_mmu_map_segment(struct kvm_vcpu *vcpu, ulong eaddr)
 {
+        struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
         u64 esid = eaddr >> SID_SHIFT;
         u64 slb_esid = (eaddr & ESID_MASK) | SLB_ESID_V;
         u64 slb_vsid = SLB_VSID_USER;
         u64 gvsid;
         int slb_index;
         struct kvmppc_sid_map *map;
+        int r = 0;
 
         slb_index = kvmppc_mmu_next_segment(vcpu, eaddr & ESID_MASK);
 
         if (vcpu->arch.mmu.esid_to_vsid(vcpu, esid, &gvsid)) {
                 /* Invalidate an entry */
-                to_svcpu(vcpu)->slb[slb_index].esid = 0;
-                return -ENOENT;
+                svcpu->slb[slb_index].esid = 0;
+                r = -ENOENT;
+                goto out;
         }
 
         map = find_sid_vsid(vcpu, gvsid);
@@ -269,18 +285,22 @@ int kvmppc_mmu_map_segment(struct kvm_vcpu *vcpu, ulong eaddr)
         slb_vsid &= ~SLB_VSID_KP;
         slb_esid |= slb_index;
 
-        to_svcpu(vcpu)->slb[slb_index].esid = slb_esid;
-        to_svcpu(vcpu)->slb[slb_index].vsid = slb_vsid;
+        svcpu->slb[slb_index].esid = slb_esid;
+        svcpu->slb[slb_index].vsid = slb_vsid;
 
         trace_kvm_book3s_slbmte(slb_vsid, slb_esid);
 
-        return 0;
+out:
+        svcpu_put(svcpu);
+        return r;
 }
 
 void kvmppc_mmu_flush_segments(struct kvm_vcpu *vcpu)
 {
-        to_svcpu(vcpu)->slb_max = 1;
-        to_svcpu(vcpu)->slb[0].esid = 0;
+        struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
+        svcpu->slb_max = 1;
+        svcpu->slb[0].esid = 0;
+        svcpu_put(svcpu);
 }
 
 void kvmppc_mmu_destroy(struct kvm_vcpu *vcpu)
diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index bc3a2ea94217..ddc485a529f2 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -23,6 +23,7 @@
 #include <linux/gfp.h>
 #include <linux/slab.h>
 #include <linux/hugetlb.h>
+#include <linux/vmalloc.h>
 
 #include <asm/tlbflush.h>
 #include <asm/kvm_ppc.h>
@@ -33,15 +34,6 @@
 #include <asm/ppc-opcode.h>
 #include <asm/cputable.h>
 
-/* For now use fixed-size 16MB page table */
-#define HPT_ORDER       24
-#define HPT_NPTEG       (1ul << (HPT_ORDER - 7))        /* 128B per pteg */
-#define HPT_HASH_MASK   (HPT_NPTEG - 1)
-
-/* Pages in the VRMA are 16MB pages */
-#define VRMA_PAGE_ORDER 24
-#define VRMA_VSID       0x1ffffffUL     /* 1TB VSID reserved for VRMA */
-
 /* POWER7 has 10-bit LPIDs, PPC970 has 6-bit LPIDs */
 #define MAX_LPID_970    63
 #define NR_LPIDS        (LPID_RSVD + 1)
@@ -51,21 +43,41 @@ long kvmppc_alloc_hpt(struct kvm *kvm)
 {
         unsigned long hpt;
         unsigned long lpid;
+        struct revmap_entry *rev;
+        struct kvmppc_linear_info *li;
+
+        /* Allocate guest's hashed page table */
+        li = kvm_alloc_hpt();
+        if (li) {
+                /* using preallocated memory */
+                hpt = (ulong)li->base_virt;
+                kvm->arch.hpt_li = li;
+        } else {
+                /* using dynamic memory */
+                hpt = __get_free_pages(GFP_KERNEL|__GFP_ZERO|__GFP_REPEAT|
+                                       __GFP_NOWARN, HPT_ORDER - PAGE_SHIFT);
+        }
 
-        hpt = __get_free_pages(GFP_KERNEL|__GFP_ZERO|__GFP_REPEAT|__GFP_NOWARN,
-                               HPT_ORDER - PAGE_SHIFT);
         if (!hpt) {
                 pr_err("kvm_alloc_hpt: Couldn't alloc HPT\n");
                 return -ENOMEM;
         }
         kvm->arch.hpt_virt = hpt;
 
+        /* Allocate reverse map array */
+        rev = vmalloc(sizeof(struct revmap_entry) * HPT_NPTE);
+        if (!rev) {
+                pr_err("kvmppc_alloc_hpt: Couldn't alloc reverse map array\n");
+                goto out_freehpt;
+        }
+        kvm->arch.revmap = rev;
+
+        /* Allocate the guest's logical partition ID */
         do {
                 lpid = find_first_zero_bit(lpid_inuse, NR_LPIDS);
                 if (lpid >= NR_LPIDS) {
                         pr_err("kvm_alloc_hpt: No LPIDs free\n");
-                        free_pages(hpt, HPT_ORDER - PAGE_SHIFT);
-                        return -ENOMEM;
+                        goto out_freeboth;
                 }
         } while (test_and_set_bit(lpid, lpid_inuse));
 
@@ -74,37 +86,64 @@ long kvmppc_alloc_hpt(struct kvm *kvm)
 
         pr_info("KVM guest htab at %lx, LPID %lx\n", hpt, lpid);
         return 0;
+
+ out_freeboth:
+        vfree(rev);
+ out_freehpt:
+        free_pages(hpt, HPT_ORDER - PAGE_SHIFT);
+        return -ENOMEM;
 }
 
 void kvmppc_free_hpt(struct kvm *kvm)
 {
         clear_bit(kvm->arch.lpid, lpid_inuse);
-        free_pages(kvm->arch.hpt_virt, HPT_ORDER - PAGE_SHIFT);
+        vfree(kvm->arch.revmap);
+        if (kvm->arch.hpt_li)
+                kvm_release_hpt(kvm->arch.hpt_li);
+        else
+                free_pages(kvm->arch.hpt_virt, HPT_ORDER - PAGE_SHIFT);
+}
+
+/* Bits in first HPTE dword for pagesize 4k, 64k or 16M */
+static inline unsigned long hpte0_pgsize_encoding(unsigned long pgsize)
+{
+        return (pgsize > 0x1000) ? HPTE_V_LARGE : 0;
+}
+
+/* Bits in second HPTE dword for pagesize 4k, 64k or 16M */
+static inline unsigned long hpte1_pgsize_encoding(unsigned long pgsize)
+{
+        return (pgsize == 0x10000) ? 0x1000 : 0;
 }
 
-void kvmppc_map_vrma(struct kvm *kvm, struct kvm_userspace_memory_region *mem)
+void kvmppc_map_vrma(struct kvm_vcpu *vcpu, struct kvm_memory_slot *memslot,
+                     unsigned long porder)
 {
         unsigned long i;
-        unsigned long npages = kvm->arch.ram_npages;
-        unsigned long pfn;
-        unsigned long *hpte;
-        unsigned long hash;
-        struct kvmppc_pginfo *pginfo = kvm->arch.ram_pginfo;
+        unsigned long npages;
+        unsigned long hp_v, hp_r;
+        unsigned long addr, hash;
+        unsigned long psize;
+        unsigned long hp0, hp1;
+        long ret;
 
-        if (!pginfo)
-                return;
+        psize = 1ul << porder;
+        npages = memslot->npages >> (porder - PAGE_SHIFT);
 
         /* VRMA can't be > 1TB */
-        if (npages > 1ul << (40 - kvm->arch.ram_porder))
-                npages = 1ul << (40 - kvm->arch.ram_porder);
+        if (npages > 1ul << (40 - porder))
+                npages = 1ul << (40 - porder);
         /* Can't use more than 1 HPTE per HPTEG */
         if (npages > HPT_NPTEG)
                 npages = HPT_NPTEG;
 
+        hp0 = HPTE_V_1TB_SEG | (VRMA_VSID << (40 - 16)) |
+                HPTE_V_BOLTED | hpte0_pgsize_encoding(psize);
+        hp1 = hpte1_pgsize_encoding(psize) |
+                HPTE_R_R | HPTE_R_C | HPTE_R_M | PP_RWXX;
+
         for (i = 0; i < npages; ++i) {
-                pfn = pginfo[i].pfn;
-                if (!pfn)
-                        break;
+                addr = i << porder;
                 /* can't use hpt_hash since va > 64 bits */
                 hash = (i ^ (VRMA_VSID ^ (VRMA_VSID << 25))) & HPT_HASH_MASK;
                 /*
@@ -113,15 +152,15 @@ void kvmppc_map_vrma(struct kvm *kvm, struct kvm_userspace_memory_region *mem)
                  * at most one HPTE per HPTEG, we just assume entry 7
                  * is available and use it.
                  */
-                hpte = (unsigned long *) (kvm->arch.hpt_virt + (hash << 7));
-                hpte += 7 * 2;
-                /* HPTE low word - RPN, protection, etc. */
-                hpte[1] = (pfn << PAGE_SHIFT) | HPTE_R_R | HPTE_R_C |
-                        HPTE_R_M | PP_RWXX;
-                wmb();
-                hpte[0] = HPTE_V_1TB_SEG | (VRMA_VSID << (40 - 16)) |
-                        (i << (VRMA_PAGE_ORDER - 16)) | HPTE_V_BOLTED |
-                        HPTE_V_LARGE | HPTE_V_VALID;
+                hash = (hash << 3) + 7;
+                hp_v = hp0 | ((addr >> 16) & ~0x7fUL);
+                hp_r = hp1 | addr;
+                ret = kvmppc_virtmode_h_enter(vcpu, H_EXACT, hash, hp_v, hp_r);
+                if (ret != H_SUCCESS) {
+                        pr_err("KVM: map_vrma at %lx failed, ret=%ld\n",
+                               addr, ret);
+                        break;
+                }
         }
 }
 
@@ -158,10 +197,814 @@ static void kvmppc_mmu_book3s_64_hv_reset_msr(struct kvm_vcpu *vcpu)
         kvmppc_set_msr(vcpu, MSR_SF | MSR_ME);
 }
 
+/*
+ * This is called to get a reference to a guest page if there isn't
+ * one already in the kvm->arch.slot_phys[][] arrays.
+ */
+static long kvmppc_get_guest_page(struct kvm *kvm, unsigned long gfn,
+                                  struct kvm_memory_slot *memslot,
+                                  unsigned long psize)
+{
+        unsigned long start;
+        long np, err;
+        struct page *page, *hpage, *pages[1];
+        unsigned long s, pgsize;
+        unsigned long *physp;
+        unsigned int is_io, got, pgorder;
+        struct vm_area_struct *vma;
+        unsigned long pfn, i, npages;
+
+        physp = kvm->arch.slot_phys[memslot->id];
+        if (!physp)
+                return -EINVAL;
+        if (physp[gfn - memslot->base_gfn])
+                return 0;
+
+        is_io = 0;
+        got = 0;
+        page = NULL;
+        pgsize = psize;
+        err = -EINVAL;
+        start = gfn_to_hva_memslot(memslot, gfn);
+
+        /* Instantiate and get the page we want access to */
+        np = get_user_pages_fast(start, 1, 1, pages);
+        if (np != 1) {
+                /* Look up the vma for the page */
+                down_read(&current->mm->mmap_sem);
+                vma = find_vma(current->mm, start);
+                if (!vma || vma->vm_start > start ||
+                    start + psize > vma->vm_end ||
+                    !(vma->vm_flags & VM_PFNMAP))
+                        goto up_err;
+                is_io = hpte_cache_bits(pgprot_val(vma->vm_page_prot));
+                pfn = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT);
+                /* check alignment of pfn vs. requested page size */
+                if (psize > PAGE_SIZE && (pfn & ((psize >> PAGE_SHIFT) - 1)))
+                        goto up_err;
+                up_read(&current->mm->mmap_sem);
+
+        } else {
+                page = pages[0];
+                got = KVMPPC_GOT_PAGE;
+
+                /* See if this is a large page */
+                s = PAGE_SIZE;
+                if (PageHuge(page)) {
+                        hpage = compound_head(page);
+                        s <<= compound_order(hpage);
+                        /* Get the whole large page if slot alignment is ok */
+                        if (s > psize && slot_is_aligned(memslot, s) &&
+                            !(memslot->userspace_addr & (s - 1))) {
+                                start &= ~(s - 1);
+                                pgsize = s;
+                                page = hpage;
+                        }
+                }
+                if (s < psize)
+                        goto out;
+                pfn = page_to_pfn(page);
+        }
+
+        npages = pgsize >> PAGE_SHIFT;
+        pgorder = __ilog2(npages);
+        physp += (gfn - memslot->base_gfn) & ~(npages - 1);
+        spin_lock(&kvm->arch.slot_phys_lock);
+        for (i = 0; i < npages; ++i) {
+                if (!physp[i]) {
+                        physp[i] = ((pfn + i) << PAGE_SHIFT) +
+                                got + is_io + pgorder;
+                        got = 0;
+                }
+        }
+        spin_unlock(&kvm->arch.slot_phys_lock);
+        err = 0;
+
+ out:
+        if (got) {
+                if (PageHuge(page))
+                        page = compound_head(page);
+                put_page(page);
+        }
+        return err;
+
+ up_err:
+        up_read(&current->mm->mmap_sem);
+        return err;
+}
+
+/*
+ * We come here on a H_ENTER call from the guest when we are not
+ * using mmu notifiers and we don't have the requested page pinned
+ * already.
+ */
+long kvmppc_virtmode_h_enter(struct kvm_vcpu *vcpu, unsigned long flags,
+                        long pte_index, unsigned long pteh, unsigned long ptel)
+{
+        struct kvm *kvm = vcpu->kvm;
+        unsigned long psize, gpa, gfn;
+        struct kvm_memory_slot *memslot;
+        long ret;
+
+        if (kvm->arch.using_mmu_notifiers)
+                goto do_insert;
+
+        psize = hpte_page_size(pteh, ptel);
+        if (!psize)
+                return H_PARAMETER;
+
+        pteh &= ~(HPTE_V_HVLOCK | HPTE_V_ABSENT | HPTE_V_VALID);
+
+        /* Find the memslot (if any) for this address */
+        gpa = (ptel & HPTE_R_RPN) & ~(psize - 1);
+        gfn = gpa >> PAGE_SHIFT;
+        memslot = gfn_to_memslot(kvm, gfn);
+        if (memslot && !(memslot->flags & KVM_MEMSLOT_INVALID)) {
+                if (!slot_is_aligned(memslot, psize))
+                        return H_PARAMETER;
+                if (kvmppc_get_guest_page(kvm, gfn, memslot, psize) < 0)
+                        return H_PARAMETER;
+        }
+
+ do_insert:
+        /* Protect linux PTE lookup from page table destruction */
+        rcu_read_lock_sched();  /* this disables preemption too */
+        vcpu->arch.pgdir = current->mm->pgd;
+        ret = kvmppc_h_enter(vcpu, flags, pte_index, pteh, ptel);
+        rcu_read_unlock_sched();
+        if (ret == H_TOO_HARD) {
+                /* this can't happen */
+                pr_err("KVM: Oops, kvmppc_h_enter returned too hard!\n");
+                ret = H_RESOURCE;       /* or something */
+        }
+        return ret;
+
+}
+
+static struct kvmppc_slb *kvmppc_mmu_book3s_hv_find_slbe(struct kvm_vcpu *vcpu,
+                                                         gva_t eaddr)
+{
+        u64 mask;
+        int i;
+
+        for (i = 0; i < vcpu->arch.slb_nr; i++) {
+                if (!(vcpu->arch.slb[i].orige & SLB_ESID_V))
+                        continue;
+
+                if (vcpu->arch.slb[i].origv & SLB_VSID_B_1T)
+                        mask = ESID_MASK_1T;
+                else
+                        mask = ESID_MASK;
+
+                if (((vcpu->arch.slb[i].orige ^ eaddr) & mask) == 0)
+                        return &vcpu->arch.slb[i];
+        }
+        return NULL;
+}
+
+static unsigned long kvmppc_mmu_get_real_addr(unsigned long v, unsigned long r,
+                        unsigned long ea)
+{
+        unsigned long ra_mask;
+
+        ra_mask = hpte_page_size(v, r) - 1;
+        return (r & HPTE_R_RPN & ~ra_mask) | (ea & ra_mask);
+}
+
 static int kvmppc_mmu_book3s_64_hv_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
-                                struct kvmppc_pte *gpte, bool data)
+                        struct kvmppc_pte *gpte, bool data)
+{
+        struct kvm *kvm = vcpu->kvm;
+        struct kvmppc_slb *slbe;
+        unsigned long slb_v;
+        unsigned long pp, key;
+        unsigned long v, gr;
+        unsigned long *hptep;
+        int index;
+        int virtmode = vcpu->arch.shregs.msr & (data ? MSR_DR : MSR_IR);
+
+        /* Get SLB entry */
+        if (virtmode) {
+                slbe = kvmppc_mmu_book3s_hv_find_slbe(vcpu, eaddr);
+                if (!slbe)
+                        return -EINVAL;
+                slb_v = slbe->origv;
+        } else {
+                /* real mode access */
+                slb_v = vcpu->kvm->arch.vrma_slb_v;
+        }
+
+        /* Find the HPTE in the hash table */
+        index = kvmppc_hv_find_lock_hpte(kvm, eaddr, slb_v,
+                                         HPTE_V_VALID | HPTE_V_ABSENT);
+        if (index < 0)
+                return -ENOENT;
+        hptep = (unsigned long *)(kvm->arch.hpt_virt + (index << 4));
+        v = hptep[0] & ~HPTE_V_HVLOCK;
+        gr = kvm->arch.revmap[index].guest_rpte;
+
+        /* Unlock the HPTE */
+        asm volatile("lwsync" : : : "memory");
+        hptep[0] = v;
+
+        gpte->eaddr = eaddr;
+        gpte->vpage = ((v & HPTE_V_AVPN) << 4) | ((eaddr >> 12) & 0xfff);
+
+        /* Get PP bits and key for permission check */
+        pp = gr & (HPTE_R_PP0 | HPTE_R_PP);
+        key = (vcpu->arch.shregs.msr & MSR_PR) ? SLB_VSID_KP : SLB_VSID_KS;
+        key &= slb_v;
+
+        /* Calculate permissions */
+        gpte->may_read = hpte_read_permission(pp, key);
+        gpte->may_write = hpte_write_permission(pp, key);
+        gpte->may_execute = gpte->may_read && !(gr & (HPTE_R_N | HPTE_R_G));
+
+        /* Storage key permission check for POWER7 */
+        if (data && virtmode && cpu_has_feature(CPU_FTR_ARCH_206)) {
+                int amrfield = hpte_get_skey_perm(gr, vcpu->arch.amr);
+                if (amrfield & 1)
+                        gpte->may_read = 0;
+                if (amrfield & 2)
+                        gpte->may_write = 0;
+        }
+
+        /* Get the guest physical address */
+        gpte->raddr = kvmppc_mmu_get_real_addr(v, gr, eaddr);
+        return 0;
+}
+
+/*
+ * Quick test for whether an instruction is a load or a store.
+ * If the instruction is a load or a store, then this will indicate
+ * which it is, at least on server processors.  (Embedded processors
+ * have some external PID instructions that don't follow the rule
+ * embodied here.)  If the instruction isn't a load or store, then
+ * this doesn't return anything useful.
+ */
+static int instruction_is_store(unsigned int instr)
+{
+        unsigned int mask;
+
+        mask = 0x10000000;
+        if ((instr & 0xfc000000) == 0x7c000000)
+                mask = 0x100;           /* major opcode 31 */
+        return (instr & mask) != 0;
+}
+
+static int kvmppc_hv_emulate_mmio(struct kvm_run *run, struct kvm_vcpu *vcpu,
+                                  unsigned long gpa, int is_store)
+{
+        int ret;
+        u32 last_inst;
+        unsigned long srr0 = kvmppc_get_pc(vcpu);
+
+        /* We try to load the last instruction.  We don't let
+         * emulate_instruction do it as it doesn't check what
+         * kvmppc_ld returns.
+         * If we fail, we just return to the guest and try executing it again.
+         */
+        if (vcpu->arch.last_inst == KVM_INST_FETCH_FAILED) {
+                ret = kvmppc_ld(vcpu, &srr0, sizeof(u32), &last_inst, false);
+                if (ret != EMULATE_DONE || last_inst == KVM_INST_FETCH_FAILED)
+                        return RESUME_GUEST;
+                vcpu->arch.last_inst = last_inst;
+        }
+
+        /*
+         * WARNING: We do not know for sure whether the instruction we just
+         * read from memory is the same that caused the fault in the first
+         * place.  If the instruction we read is neither an load or a store,
+         * then it can't access memory, so we don't need to worry about
+         * enforcing access permissions.  So, assuming it is a load or
+         * store, we just check that its direction (load or store) is
+         * consistent with the original fault, since that's what we
+         * checked the access permissions against.  If there is a mismatch
+         * we just return and retry the instruction.
+         */
+
+        if (instruction_is_store(vcpu->arch.last_inst) != !!is_store)
+                return RESUME_GUEST;
+
+        /*
+         * Emulated accesses are emulated by looking at the hash for
+         * translation once, then performing the access later. The
+         * translation could be invalidated in the meantime in which
+         * point performing the subsequent memory access on the old
+         * physical address could possibly be a security hole for the
+         * guest (but not the host).
+         *
+         * This is less of an issue for MMIO stores since they aren't
+         * globally visible. It could be an issue for MMIO loads to
+         * a certain extent but we'll ignore it for now.
+         */
+
+        vcpu->arch.paddr_accessed = gpa;
+        return kvmppc_emulate_mmio(run, vcpu);
+}
+
+int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
+                                unsigned long ea, unsigned long dsisr)
+{
+        struct kvm *kvm = vcpu->kvm;
+        unsigned long *hptep, hpte[3], r;
+        unsigned long mmu_seq, psize, pte_size;
+        unsigned long gfn, hva, pfn;
+        struct kvm_memory_slot *memslot;
+        unsigned long *rmap;
+        struct revmap_entry *rev;
+        struct page *page, *pages[1];
+        long index, ret, npages;
+        unsigned long is_io;
+        unsigned int writing, write_ok;
+        struct vm_area_struct *vma;
+        unsigned long rcbits;
+
+        /*
+         * Real-mode code has already searched the HPT and found the
+         * entry we're interested in.  Lock the entry and check that
+         * it hasn't changed.  If it has, just return and re-execute the
+         * instruction.
+         */
+        if (ea != vcpu->arch.pgfault_addr)
+                return RESUME_GUEST;
+        index = vcpu->arch.pgfault_index;
+        hptep = (unsigned long *)(kvm->arch.hpt_virt + (index << 4));
+        rev = &kvm->arch.revmap[index];
+        preempt_disable();
+        while (!try_lock_hpte(hptep, HPTE_V_HVLOCK))
+                cpu_relax();
+        hpte[0] = hptep[0] & ~HPTE_V_HVLOCK;
+        hpte[1] = hptep[1];
+        hpte[2] = r = rev->guest_rpte;
+        asm volatile("lwsync" : : : "memory");
+        hptep[0] = hpte[0];
+        preempt_enable();
+
+        if (hpte[0] != vcpu->arch.pgfault_hpte[0] ||
+            hpte[1] != vcpu->arch.pgfault_hpte[1])
+                return RESUME_GUEST;
+
+        /* Translate the logical address and get the page */
+        psize = hpte_page_size(hpte[0], r);
+        gfn = hpte_rpn(r, psize);
+        memslot = gfn_to_memslot(kvm, gfn);
+
+        /* No memslot means it's an emulated MMIO region */
+        if (!memslot || (memslot->flags & KVM_MEMSLOT_INVALID)) {
+                unsigned long gpa = (gfn << PAGE_SHIFT) | (ea & (psize - 1));
+                return kvmppc_hv_emulate_mmio(run, vcpu, gpa,
+                                              dsisr & DSISR_ISSTORE);
+        }
+
+        if (!kvm->arch.using_mmu_notifiers)
+                return -EFAULT;         /* should never get here */
+
+        /* used to check for invalidations in progress */
+        mmu_seq = kvm->mmu_notifier_seq;
+        smp_rmb();
+
+        is_io = 0;
+        pfn = 0;
+        page = NULL;
+        pte_size = PAGE_SIZE;
+        writing = (dsisr & DSISR_ISSTORE) != 0;
+        /* If writing != 0, then the HPTE must allow writing, if we get here */
+        write_ok = writing;
+        hva = gfn_to_hva_memslot(memslot, gfn);
+        npages = get_user_pages_fast(hva, 1, writing, pages);
+        if (npages < 1) {
+                /* Check if it's an I/O mapping */
+                down_read(&current->mm->mmap_sem);
+                vma = find_vma(current->mm, hva);
+                if (vma && vma->vm_start <= hva && hva + psize <= vma->vm_end &&
+                    (vma->vm_flags & VM_PFNMAP)) {
+                        pfn = vma->vm_pgoff +
+                                ((hva - vma->vm_start) >> PAGE_SHIFT);
+                        pte_size = psize;
+                        is_io = hpte_cache_bits(pgprot_val(vma->vm_page_prot));
+                        write_ok = vma->vm_flags & VM_WRITE;
+                }
+                up_read(&current->mm->mmap_sem);
+                if (!pfn)
+                        return -EFAULT;
+        } else {
+                page = pages[0];
+                if (PageHuge(page)) {
+                        page = compound_head(page);
+                        pte_size <<= compound_order(page);
+                }
+                /* if the guest wants write access, see if that is OK */
+                if (!writing && hpte_is_writable(r)) {
+                        pte_t *ptep, pte;
+
+                        /*
+                         * We need to protect against page table destruction
+                         * while looking up and updating the pte.
+                         */
+                        rcu_read_lock_sched();
+                        ptep = find_linux_pte_or_hugepte(current->mm->pgd,
+                                                         hva, NULL);
+                        if (ptep && pte_present(*ptep)) {
+                                pte = kvmppc_read_update_linux_pte(ptep, 1);
+                                if (pte_write(pte))
+                                        write_ok = 1;
+                        }
+                        rcu_read_unlock_sched();
+                }
+                pfn = page_to_pfn(page);
+        }
+
+        ret = -EFAULT;
+        if (psize > pte_size)
+                goto out_put;
+
+        /* Check WIMG vs. the actual page we're accessing */
+        if (!hpte_cache_flags_ok(r, is_io)) {
+                if (is_io)
+                        return -EFAULT;
+                /*
+                 * Allow guest to map emulated device memory as
+                 * uncacheable, but actually make it cacheable.
+                 */
+                r = (r & ~(HPTE_R_W|HPTE_R_I|HPTE_R_G)) | HPTE_R_M;
+        }
+
+        /* Set the HPTE to point to pfn */
+        r = (r & ~(HPTE_R_PP0 - pte_size)) | (pfn << PAGE_SHIFT);
+        if (hpte_is_writable(r) && !write_ok)
+                r = hpte_make_readonly(r);
+        ret = RESUME_GUEST;
+        preempt_disable();
+        while (!try_lock_hpte(hptep, HPTE_V_HVLOCK))
+                cpu_relax();
+        if ((hptep[0] & ~HPTE_V_HVLOCK) != hpte[0] || hptep[1] != hpte[1] ||
+            rev->guest_rpte != hpte[2])
+                /* HPTE has been changed under us; let the guest retry */
+                goto out_unlock;
+        hpte[0] = (hpte[0] & ~HPTE_V_ABSENT) | HPTE_V_VALID;
+
+        rmap = &memslot->rmap[gfn - memslot->base_gfn];
+        lock_rmap(rmap);
+
+        /* Check if we might have been invalidated; let the guest retry if so */
+        ret = RESUME_GUEST;
+        if (mmu_notifier_retry(vcpu, mmu_seq)) {
+                unlock_rmap(rmap);
+                goto out_unlock;
+        }
+
+        /* Only set R/C in real HPTE if set in both *rmap and guest_rpte */
+        rcbits = *rmap >> KVMPPC_RMAP_RC_SHIFT;
+        r &= rcbits | ~(HPTE_R_R | HPTE_R_C);
+
+        if (hptep[0] & HPTE_V_VALID) {
+                /* HPTE was previously valid, so we need to invalidate it */
+                unlock_rmap(rmap);
+                hptep[0] |= HPTE_V_ABSENT;
+                kvmppc_invalidate_hpte(kvm, hptep, index);
+                /* don't lose previous R and C bits */
+                r |= hptep[1] & (HPTE_R_R | HPTE_R_C);
+        } else {
+                kvmppc_add_revmap_chain(kvm, rev, rmap, index, 0);
+        }
+
+        hptep[1] = r;
+        eieio();
+        hptep[0] = hpte[0];
+        asm volatile("ptesync" : : : "memory");
+        preempt_enable();
+        if (page && hpte_is_writable(r))
+                SetPageDirty(page);
+
+ out_put:
+        if (page)
+                put_page(page);
+        return ret;
+
+ out_unlock:
+        hptep[0] &= ~HPTE_V_HVLOCK;
+        preempt_enable();
+        goto out_put;
+}
+
+static int kvm_handle_hva(struct kvm *kvm, unsigned long hva,
+                          int (*handler)(struct kvm *kvm, unsigned long *rmapp,
+                                         unsigned long gfn))
+{
+        int ret;
+        int retval = 0;
+        struct kvm_memslots *slots;
+        struct kvm_memory_slot *memslot;
+
+        slots = kvm_memslots(kvm);
+        kvm_for_each_memslot(memslot, slots) {
+                unsigned long start = memslot->userspace_addr;
+                unsigned long end;
+
+                end = start + (memslot->npages << PAGE_SHIFT);
+                if (hva >= start && hva < end) {
+                        gfn_t gfn_offset = (hva - start) >> PAGE_SHIFT;
+
+                        ret = handler(kvm, &memslot->rmap[gfn_offset],
+                                      memslot->base_gfn + gfn_offset);
+                        retval |= ret;
+                }
+        }
+
+        return retval;
+}
+
+static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp,
+                           unsigned long gfn)
+{
+        struct revmap_entry *rev = kvm->arch.revmap;
+        unsigned long h, i, j;
+        unsigned long *hptep;
+        unsigned long ptel, psize, rcbits;
+
+        for (;;) {
+                lock_rmap(rmapp);
+                if (!(*rmapp & KVMPPC_RMAP_PRESENT)) {
+                        unlock_rmap(rmapp);
+                        break;
+                }
+
+                /*
+                 * To avoid an ABBA deadlock with the HPTE lock bit,
+                 * we can't spin on the HPTE lock while holding the
+                 * rmap chain lock.
+                 */
+                i = *rmapp & KVMPPC_RMAP_INDEX;
+                hptep = (unsigned long *) (kvm->arch.hpt_virt + (i << 4));
+                if (!try_lock_hpte(hptep, HPTE_V_HVLOCK)) {
+                        /* unlock rmap before spinning on the HPTE lock */
+                        unlock_rmap(rmapp);
+                        while (hptep[0] & HPTE_V_HVLOCK)
+                                cpu_relax();
+                        continue;
+                }
+                j = rev[i].forw;
+                if (j == i) {
+                        /* chain is now empty */
+                        *rmapp &= ~(KVMPPC_RMAP_PRESENT | KVMPPC_RMAP_INDEX);
+                } else {
+                        /* remove i from chain */
+                        h = rev[i].back;
+                        rev[h].forw = j;
+                        rev[j].back = h;
+                        rev[i].forw = rev[i].back = i;
+                        *rmapp = (*rmapp & ~KVMPPC_RMAP_INDEX) | j;
+                }
+
+                /* Now check and modify the HPTE */
+                ptel = rev[i].guest_rpte;
+                psize = hpte_page_size(hptep[0], ptel);
+                if ((hptep[0] & HPTE_V_VALID) &&
+                    hpte_rpn(ptel, psize) == gfn) {
+                        hptep[0] |= HPTE_V_ABSENT;
+                        kvmppc_invalidate_hpte(kvm, hptep, i);
+                        /* Harvest R and C */
+                        rcbits = hptep[1] & (HPTE_R_R | HPTE_R_C);
+                        *rmapp |= rcbits << KVMPPC_RMAP_RC_SHIFT;
+                        rev[i].guest_rpte = ptel | rcbits;
+                }
+                unlock_rmap(rmapp);
+                hptep[0] &= ~HPTE_V_HVLOCK;
+        }
+        return 0;
+}
+
+int kvm_unmap_hva(struct kvm *kvm, unsigned long hva)
+{
+        if (kvm->arch.using_mmu_notifiers)
+                kvm_handle_hva(kvm, hva, kvm_unmap_rmapp);
+        return 0;
+}
+
+static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp,
+                         unsigned long gfn)
+{
+        struct revmap_entry *rev = kvm->arch.revmap;
+        unsigned long head, i, j;
+        unsigned long *hptep;
+        int ret = 0;
+
+ retry:
+        lock_rmap(rmapp);
+        if (*rmapp & KVMPPC_RMAP_REFERENCED) {
+                *rmapp &= ~KVMPPC_RMAP_REFERENCED;
+                ret = 1;
+        }
+        if (!(*rmapp & KVMPPC_RMAP_PRESENT)) {
+                unlock_rmap(rmapp);
+                return ret;
+        }
+
+        i = head = *rmapp & KVMPPC_RMAP_INDEX;
+        do {
+                hptep = (unsigned long *) (kvm->arch.hpt_virt + (i << 4));
+                j = rev[i].forw;
+
+                /* If this HPTE isn't referenced, ignore it */
+                if (!(hptep[1] & HPTE_R_R))
+                        continue;
+
+                if (!try_lock_hpte(hptep, HPTE_V_HVLOCK)) {
+                        /* unlock rmap before spinning on the HPTE lock */
+                        unlock_rmap(rmapp);
+                        while (hptep[0] & HPTE_V_HVLOCK)
+                                cpu_relax();
+                        goto retry;
+                }
+
+                /* Now check and modify the HPTE */
+                if ((hptep[0] & HPTE_V_VALID) && (hptep[1] & HPTE_R_R)) {
+                        kvmppc_clear_ref_hpte(kvm, hptep, i);
+                        rev[i].guest_rpte |= HPTE_R_R;
+                        ret = 1;
+                }
+                hptep[0] &= ~HPTE_V_HVLOCK;
+        } while ((i = j) != head);
+
+        unlock_rmap(rmapp);
+        return ret;
+}
+
+int kvm_age_hva(struct kvm *kvm, unsigned long hva)
+{
+        if (!kvm->arch.using_mmu_notifiers)
+                return 0;
+        return kvm_handle_hva(kvm, hva, kvm_age_rmapp);
+}
+
+static int kvm_test_age_rmapp(struct kvm *kvm, unsigned long *rmapp,
+                              unsigned long gfn)
+{
+        struct revmap_entry *rev = kvm->arch.revmap;
+        unsigned long head, i, j;
+        unsigned long *hp;
+        int ret = 1;
+
+        if (*rmapp & KVMPPC_RMAP_REFERENCED)
+                return 1;
+
+        lock_rmap(rmapp);
+        if (*rmapp & KVMPPC_RMAP_REFERENCED)
+                goto out;
+
+        if (*rmapp & KVMPPC_RMAP_PRESENT) {
+                i = head = *rmapp & KVMPPC_RMAP_INDEX;
+                do {
+                        hp = (unsigned long *)(kvm->arch.hpt_virt + (i << 4));
+                        j = rev[i].forw;
+                        if (hp[1] & HPTE_R_R)
+                                goto out;
+                } while ((i = j) != head);
+        }
+        ret = 0;
+
+ out:
+        unlock_rmap(rmapp);
+        return ret;
+}
+
+int kvm_test_age_hva(struct kvm *kvm, unsigned long hva)
+{
+        if (!kvm->arch.using_mmu_notifiers)
+                return 0;
+        return kvm_handle_hva(kvm, hva, kvm_test_age_rmapp);
+}
+
+void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte)
 {
-        return -ENOENT;
+        if (!kvm->arch.using_mmu_notifiers)
+                return;
+        kvm_handle_hva(kvm, hva, kvm_unmap_rmapp);
+}
+
+static int kvm_test_clear_dirty(struct kvm *kvm, unsigned long *rmapp)
+{
+        struct revmap_entry *rev = kvm->arch.revmap;
+        unsigned long head, i, j;
+        unsigned long *hptep;
+        int ret = 0;
+
+ retry:
+        lock_rmap(rmapp);
+        if (*rmapp & KVMPPC_RMAP_CHANGED) {
+                *rmapp &= ~KVMPPC_RMAP_CHANGED;
+                ret = 1;
+        }
+        if (!(*rmapp & KVMPPC_RMAP_PRESENT)) {
+                unlock_rmap(rmapp);
+                return ret;
+        }
+
+        i = head = *rmapp & KVMPPC_RMAP_INDEX;
+        do {
+                hptep = (unsigned long *) (kvm->arch.hpt_virt + (i << 4));
+                j = rev[i].forw;
+
+                if (!(hptep[1] & HPTE_R_C))
+                        continue;
+
+                if (!try_lock_hpte(hptep, HPTE_V_HVLOCK)) {
+                        /* unlock rmap before spinning on the HPTE lock */
+                        unlock_rmap(rmapp);
+                        while (hptep[0] & HPTE_V_HVLOCK)
+                                cpu_relax();
+                        goto retry;
+                }
+
+                /* Now check and modify the HPTE */
+                if ((hptep[0] & HPTE_V_VALID) && (hptep[1] & HPTE_R_C)) {
+                        /* need to make it temporarily absent to clear C */
+                        hptep[0] |= HPTE_V_ABSENT;
+                        kvmppc_invalidate_hpte(kvm, hptep, i);
+                        hptep[1] &= ~HPTE_R_C;
+                        eieio();
+                        hptep[0] = (hptep[0] & ~HPTE_V_ABSENT) | HPTE_V_VALID;
+                        rev[i].guest_rpte |= HPTE_R_C;
+                        ret = 1;
+                }
+                hptep[0] &= ~HPTE_V_HVLOCK;
+        } while ((i = j) != head);
+
+        unlock_rmap(rmapp);
+        return ret;
+}
+
+long kvmppc_hv_get_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot)
+{
+        unsigned long i;
+        unsigned long *rmapp, *map;
+
+        preempt_disable();
+        rmapp = memslot->rmap;
+        map = memslot->dirty_bitmap;
+        for (i = 0; i < memslot->npages; ++i) {
+                if (kvm_test_clear_dirty(kvm, rmapp))
+                        __set_bit_le(i, map);
+                ++rmapp;
+        }
+        preempt_enable();
+        return 0;
+}
+
+void *kvmppc_pin_guest_page(struct kvm *kvm, unsigned long gpa,
+                            unsigned long *nb_ret)
+{
+        struct kvm_memory_slot *memslot;
+        unsigned long gfn = gpa >> PAGE_SHIFT;
+        struct page *page, *pages[1];
+        int npages;
+        unsigned long hva, psize, offset;
+        unsigned long pa;
+        unsigned long *physp;
+
+        memslot = gfn_to_memslot(kvm, gfn);
+        if (!memslot || (memslot->flags & KVM_MEMSLOT_INVALID))
+                return NULL;
+        if (!kvm->arch.using_mmu_notifiers) {
+                physp = kvm->arch.slot_phys[memslot->id];
+                if (!physp)
+                        return NULL;
+                physp += gfn - memslot->base_gfn;
+                pa = *physp;
+                if (!pa) {
+                        if (kvmppc_get_guest_page(kvm, gfn, memslot,
+                                                  PAGE_SIZE) < 0)
+                                return NULL;
+                        pa = *physp;
+                }
+                page = pfn_to_page(pa >> PAGE_SHIFT);
+        } else {
+                hva = gfn_to_hva_memslot(memslot, gfn);
+                npages = get_user_pages_fast(hva, 1, 1, pages);
+                if (npages < 1)
+                        return NULL;
+                page = pages[0];
+        }
+        psize = PAGE_SIZE;
+        if (PageHuge(page)) {
+                page = compound_head(page);
+                psize <<= compound_order(page);
+        }
+        if (!kvm->arch.using_mmu_notifiers)
+                get_page(page);
+        offset = gpa & (psize - 1);
+        if (nb_ret)
+                *nb_ret = psize - offset;
+        return page_address(page) + offset;
+}
+
+void kvmppc_unpin_guest_page(struct kvm *kvm, void *va)
+{
+        struct page *page = virt_to_page(va);
+
+        page = compound_head(page);
+        put_page(page);
 }
 
 void kvmppc_mmu_book3s_hv_init(struct kvm_vcpu *vcpu)
diff --git a/arch/powerpc/kvm/book3s_emulate.c b/arch/powerpc/kvm/book3s_emulate.c
index 0c9dc62532d0..f1950d131827 100644
--- a/arch/powerpc/kvm/book3s_emulate.c
+++ b/arch/powerpc/kvm/book3s_emulate.c
@@ -230,9 +230,12 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
 
                         r = kvmppc_st(vcpu, &addr, 32, zeros, true);
                         if ((r == -ENOENT) || (r == -EPERM)) {
+                                struct kvmppc_book3s_shadow_vcpu *svcpu;
+
+                                svcpu = svcpu_get(vcpu);
                                 *advance = 0;
                                 vcpu->arch.shared->dar = vaddr;
-                                to_svcpu(vcpu)->fault_dar = vaddr;
+                                svcpu->fault_dar = vaddr;
 
                                 dsisr = DSISR_ISSTORE;
                                 if (r == -ENOENT)
@@ -241,7 +244,8 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
                                         dsisr |= DSISR_PROTFAULT;
 
                                 vcpu->arch.shared->dsisr = dsisr;
-                                to_svcpu(vcpu)->fault_dsisr = dsisr;
+                                svcpu->fault_dsisr = dsisr;
+                                svcpu_put(svcpu);
 
                                 kvmppc_book3s_queue_irqprio(vcpu,
                                         BOOK3S_INTERRUPT_DATA_STORAGE);
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 336983da9e72..d386b6198bc7 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -46,25 +46,16 @@
 #include <asm/page.h>
 #include <asm/hvcall.h>
 #include <linux/gfp.h>
-#include <linux/sched.h>
 #include <linux/vmalloc.h>
 #include <linux/highmem.h>
-
-/*
- * For now, limit memory to 64GB and require it to be large pages.
- * This value is chosen because it makes the ram_pginfo array be
- * 64kB in size, which is about as large as we want to be trying
- * to allocate with kmalloc.
- */
-#define MAX_MEM_ORDER           36
-
-#define LARGE_PAGE_ORDER        24      /* 16MB pages */
+#include <linux/hugetlb.h>
 
 /* #define EXIT_DEBUG */
 /* #define EXIT_DEBUG_SIMPLE */
 /* #define EXIT_DEBUG_INT */
 
 static void kvmppc_end_cede(struct kvm_vcpu *vcpu);
+static int kvmppc_hv_setup_rma(struct kvm_vcpu *vcpu);
 
 void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
@@ -147,10 +138,10 @@ static unsigned long do_h_register_vpa(struct kvm_vcpu *vcpu,
                                        unsigned long vcpuid, unsigned long vpa)
 {
         struct kvm *kvm = vcpu->kvm;
-        unsigned long pg_index, ra, len;
-        unsigned long pg_offset;
+        unsigned long len, nb;
         void *va;
         struct kvm_vcpu *tvcpu;
+        int err = H_PARAMETER;
 
         tvcpu = kvmppc_find_vcpu(kvm, vcpuid);
         if (!tvcpu)
@@ -163,45 +154,41 @@ static unsigned long do_h_register_vpa(struct kvm_vcpu *vcpu,
         if (flags < 4) {
                 if (vpa & 0x7f)
                         return H_PARAMETER;
+                if (flags >= 2 && !tvcpu->arch.vpa)
+                        return H_RESOURCE;
                 /* registering new area; convert logical addr to real */
-                pg_index = vpa >> kvm->arch.ram_porder;
-                pg_offset = vpa & (kvm->arch.ram_psize - 1);
-                if (pg_index >= kvm->arch.ram_npages)
-                        return H_PARAMETER;
-                if (kvm->arch.ram_pginfo[pg_index].pfn == 0)
+                va = kvmppc_pin_guest_page(kvm, vpa, &nb);
+                if (va == NULL)
                         return H_PARAMETER;
-                ra = kvm->arch.ram_pginfo[pg_index].pfn << PAGE_SHIFT;
-                ra |= pg_offset;
-                va = __va(ra);
                 if (flags <= 1)
                         len = *(unsigned short *)(va + 4);
                 else
                         len = *(unsigned int *)(va + 4);
-                if (pg_offset + len > kvm->arch.ram_psize)
-                        return H_PARAMETER;
+                if (len > nb)
+                        goto out_unpin;
                 switch (flags) {
                 case 1:         /* register VPA */
                         if (len < 640)
-                                return H_PARAMETER;
+                                goto out_unpin;
+                        if (tvcpu->arch.vpa)
+                                kvmppc_unpin_guest_page(kvm, vcpu->arch.vpa);
                         tvcpu->arch.vpa = va;
                         init_vpa(vcpu, va);
                         break;
                 case 2:         /* register DTL */
                         if (len < 48)
-                                return H_PARAMETER;
-                        if (!tvcpu->arch.vpa)
-                                return H_RESOURCE;
+                                goto out_unpin;
                         len -= len % 48;
+                        if (tvcpu->arch.dtl)
+                                kvmppc_unpin_guest_page(kvm, vcpu->arch.dtl);
                         tvcpu->arch.dtl = va;
                         tvcpu->arch.dtl_end = va + len;
                         break;
                 case 3:         /* register SLB shadow buffer */
-                        if (len < 8)
-                                return H_PARAMETER;
-                        if (!tvcpu->arch.vpa)
-                                return H_RESOURCE;
-                        tvcpu->arch.slb_shadow = va;
-                        len = (len - 16) / 16;
+                        if (len < 16)
+                                goto out_unpin;
+                        if (tvcpu->arch.slb_shadow)
+                                kvmppc_unpin_guest_page(kvm, vcpu->arch.slb_shadow);
                         tvcpu->arch.slb_shadow = va;
                         break;
                 }
@@ -210,17 +197,30 @@ static unsigned long do_h_register_vpa(struct kvm_vcpu *vcpu,
                 case 5:         /* unregister VPA */
                         if (tvcpu->arch.slb_shadow || tvcpu->arch.dtl)
                                 return H_RESOURCE;
+                        if (!tvcpu->arch.vpa)
+                                break;
+                        kvmppc_unpin_guest_page(kvm, tvcpu->arch.vpa);
                         tvcpu->arch.vpa = NULL;
                         break;
                 case 6:         /* unregister DTL */
+                        if (!tvcpu->arch.dtl)
+                                break;
+                        kvmppc_unpin_guest_page(kvm, tvcpu->arch.dtl);
                         tvcpu->arch.dtl = NULL;
                         break;
                 case 7:         /* unregister SLB shadow buffer */
+                        if (!tvcpu->arch.slb_shadow)
+                                break;
+                        kvmppc_unpin_guest_page(kvm, tvcpu->arch.slb_shadow);
                         tvcpu->arch.slb_shadow = NULL;
                         break;
                 }
         }
         return H_SUCCESS;
+
+ out_unpin:
+        kvmppc_unpin_guest_page(kvm, va);
+        return err;
 }
 
 int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
@@ -230,6 +230,12 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
         struct kvm_vcpu *tvcpu;
 
         switch (req) {
+        case H_ENTER:
+                ret = kvmppc_virtmode_h_enter(vcpu, kvmppc_get_gpr(vcpu, 4),
+                                              kvmppc_get_gpr(vcpu, 5),
+                                              kvmppc_get_gpr(vcpu, 6),
+                                              kvmppc_get_gpr(vcpu, 7));
+                break;
         case H_CEDE:
                 break;
         case H_PROD:
@@ -319,20 +325,19 @@ static int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
                 break;
         }
         /*
-         * We get these next two if the guest does a bad real-mode access,
-         * as we have enabled VRMA (virtualized real mode area) mode in the
-         * LPCR.  We just generate an appropriate DSI/ISI to the guest.
+         * We get these next two if the guest accesses a page which it thinks
+         * it has mapped but which is not actually present, either because
+         * it is for an emulated I/O device or because the corresonding
+         * host page has been paged out.  Any other HDSI/HISI interrupts
+         * have been handled already.
          */
         case BOOK3S_INTERRUPT_H_DATA_STORAGE:
-                vcpu->arch.shregs.dsisr = vcpu->arch.fault_dsisr;
-                vcpu->arch.shregs.dar = vcpu->arch.fault_dar;
-                kvmppc_inject_interrupt(vcpu, BOOK3S_INTERRUPT_DATA_STORAGE, 0);
-                r = RESUME_GUEST;
+                r = kvmppc_book3s_hv_page_fault(run, vcpu,
+                                vcpu->arch.fault_dar, vcpu->arch.fault_dsisr);
                 break;
         case BOOK3S_INTERRUPT_H_INST_STORAGE:
-                kvmppc_inject_interrupt(vcpu, BOOK3S_INTERRUPT_INST_STORAGE,
-                                        0x08000000);
-                r = RESUME_GUEST;
+                r = kvmppc_book3s_hv_page_fault(run, vcpu,
+                                kvmppc_get_pc(vcpu), 0);
                 break;
         /*
          * This occurs if the guest executes an illegal instruction.
@@ -392,6 +397,42 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
         return 0;
 }
 
+int kvm_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
+{
+        int r = -EINVAL;
+
+        switch (reg->id) {
+        case KVM_REG_PPC_HIOR:
+                r = put_user(0, (u64 __user *)reg->addr);
+                break;
+        default:
+                break;
+        }
+
+        return r;
+}
+
+int kvm_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
+{
+        int r = -EINVAL;
+
+        switch (reg->id) {
+        case KVM_REG_PPC_HIOR:
+        {
+                u64 hior;
+                /* Only allow this to be set to zero */
+                r = get_user(hior, (u64 __user *)reg->addr);
+                if (!r && (hior != 0))
+                        r = -EINVAL;
+                break;
+        }
+        default:
+                break;
+        }
+
+        return r;
+}
+
 int kvmppc_core_check_processor_compat(void)
 {
         if (cpu_has_feature(CPU_FTR_HVMODE))
@@ -411,7 +452,7 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
                 goto out;
 
         err = -ENOMEM;
-        vcpu = kzalloc(sizeof(struct kvm_vcpu), GFP_KERNEL);
+        vcpu = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL);
         if (!vcpu)
                 goto out;
 
@@ -463,15 +504,21 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
         return vcpu;
 
 free_vcpu:
-        kfree(vcpu);
+        kmem_cache_free(kvm_vcpu_cache, vcpu);
 out:
         return ERR_PTR(err);
 }
 
 void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu)
 {
+        if (vcpu->arch.dtl)
+                kvmppc_unpin_guest_page(vcpu->kvm, vcpu->arch.dtl);
+        if (vcpu->arch.slb_shadow)
+                kvmppc_unpin_guest_page(vcpu->kvm, vcpu->arch.slb_shadow);
+        if (vcpu->arch.vpa)
+                kvmppc_unpin_guest_page(vcpu->kvm, vcpu->arch.vpa);
         kvm_vcpu_uninit(vcpu);
-        kfree(vcpu);
+        kmem_cache_free(kvm_vcpu_cache, vcpu);
 }
 
 static void kvmppc_set_timer(struct kvm_vcpu *vcpu)
@@ -482,7 +529,7 @@ static void kvmppc_set_timer(struct kvm_vcpu *vcpu)
         if (now > vcpu->arch.dec_expires) {
                 /* decrementer has already gone negative */
                 kvmppc_core_queue_dec(vcpu);
-                kvmppc_core_deliver_interrupts(vcpu);
+                kvmppc_core_prepare_to_enter(vcpu);
                 return;
         }
         dec_nsec = (vcpu->arch.dec_expires - now) * NSEC_PER_SEC
@@ -797,7 +844,7 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 
                 list_for_each_entry_safe(v, vn, &vc->runnable_threads,
                                          arch.run_list) {
-                        kvmppc_core_deliver_interrupts(v);
+                        kvmppc_core_prepare_to_enter(v);
                         if (signal_pending(v->arch.run_task)) {
                                 kvmppc_remove_runnable(vc, v);
                                 v->stat.signal_exits++;
@@ -836,20 +883,26 @@ int kvmppc_vcpu_run(struct kvm_run *run, struct kvm_vcpu *vcpu)
                 return -EINVAL;
         }
 
+        kvmppc_core_prepare_to_enter(vcpu);
+
         /* 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;
+        /* On the first time here, set up VRMA or RMA */
+        if (!vcpu->kvm->arch.rma_setup_done) {
+                r = kvmppc_hv_setup_rma(vcpu);
+                if (r)
+                        return r;
+        }
 
         flush_fp_to_thread(current);
         flush_altivec_to_thread(current);
         flush_vsx_to_thread(current);
         vcpu->arch.wqp = &vcpu->arch.vcore->wq;
+        vcpu->arch.pgdir = current->mm->pgd;
 
         do {
                 r = kvmppc_run_vcpu(run, vcpu);
@@ -857,7 +910,7 @@ int kvmppc_vcpu_run(struct kvm_run *run, struct kvm_vcpu *vcpu)
                 if (run->exit_reason == KVM_EXIT_PAPR_HCALL &&
                     !(vcpu->arch.shregs.msr & MSR_PR)) {
                         r = kvmppc_pseries_do_hcall(vcpu);
-                        kvmppc_core_deliver_interrupts(vcpu);
+                        kvmppc_core_prepare_to_enter(vcpu);
                 }
         } while (r == RESUME_GUEST);
         return r;
@@ -1001,7 +1054,7 @@ static inline int lpcr_rmls(unsigned long rma_size)
 
 static int kvm_rma_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 {
-        struct kvmppc_rma_info *ri = vma->vm_file->private_data;
+        struct kvmppc_linear_info *ri = vma->vm_file->private_data;
         struct page *page;
 
         if (vmf->pgoff >= ri->npages)
@@ -1026,7 +1079,7 @@ static int kvm_rma_mmap(struct file *file, struct vm_area_struct *vma)
 
 static int kvm_rma_release(struct inode *inode, struct file *filp)
 {
-        struct kvmppc_rma_info *ri = filp->private_data;
+        struct kvmppc_linear_info *ri = filp->private_data;
 
         kvm_release_rma(ri);
         return 0;
@@ -1039,7 +1092,7 @@ static struct file_operations kvm_rma_fops = {
 
 long kvm_vm_ioctl_allocate_rma(struct kvm *kvm, struct kvm_allocate_rma *ret)
 {
-        struct kvmppc_rma_info *ri;
+        struct kvmppc_linear_info *ri;
         long fd;
 
         ri = kvm_alloc_rma();
@@ -1054,89 +1107,189 @@ long kvm_vm_ioctl_allocate_rma(struct kvm *kvm, struct kvm_allocate_rma *ret)
         return fd;
 }
 
-static struct page *hva_to_page(unsigned long addr)
+/*
+ * Get (and clear) the dirty memory log for a memory slot.
+ */
+int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log)
 {
-        struct page *page[1];
-        int npages;
+        struct kvm_memory_slot *memslot;
+        int r;
+        unsigned long n;
 
-        might_sleep();
+        mutex_lock(&kvm->slots_lock);
 
-        npages = get_user_pages_fast(addr, 1, 1, page);
+        r = -EINVAL;
+        if (log->slot >= KVM_MEMORY_SLOTS)
+                goto out;
 
-        if (unlikely(npages != 1))
-                return 0;
+        memslot = id_to_memslot(kvm->memslots, log->slot);
+        r = -ENOENT;
+        if (!memslot->dirty_bitmap)
+                goto out;
+
+        n = kvm_dirty_bitmap_bytes(memslot);
+        memset(memslot->dirty_bitmap, 0, n);
+
+        r = kvmppc_hv_get_dirty_log(kvm, memslot);
+        if (r)
+                goto out;
+
+        r = -EFAULT;
+        if (copy_to_user(log->dirty_bitmap, memslot->dirty_bitmap, n))
+                goto out;
+
+        r = 0;
+out:
+        mutex_unlock(&kvm->slots_lock);
+        return r;
+}
 
-        return page[0];
+static unsigned long slb_pgsize_encoding(unsigned long psize)
+{
+        unsigned long senc = 0;
+
+        if (psize > 0x1000) {
+                senc = SLB_VSID_L;
+                if (psize == 0x10000)
+                        senc |= SLB_VSID_LP_01;
+        }
+        return senc;
 }
 
 int kvmppc_core_prepare_memory_region(struct kvm *kvm,
                                 struct kvm_userspace_memory_region *mem)
 {
-        unsigned long psize, porder;
-        unsigned long i, npages, totalpages;
-        unsigned long pg_ix;
-        struct kvmppc_pginfo *pginfo;
-        unsigned long hva;
-        struct kvmppc_rma_info *ri = NULL;
+        unsigned long npages;
+        unsigned long *phys;
+
+        /* Allocate a slot_phys array */
+        phys = kvm->arch.slot_phys[mem->slot];
+        if (!kvm->arch.using_mmu_notifiers && !phys) {
+                npages = mem->memory_size >> PAGE_SHIFT;
+                phys = vzalloc(npages * sizeof(unsigned long));
+                if (!phys)
+                        return -ENOMEM;
+                kvm->arch.slot_phys[mem->slot] = phys;
+                kvm->arch.slot_npages[mem->slot] = npages;
+        }
+
+        return 0;
+}
+
+static void unpin_slot(struct kvm *kvm, int slot_id)
+{
+        unsigned long *physp;
+        unsigned long j, npages, pfn;
         struct page *page;
 
-        /* For now, only allow 16MB pages */
-        porder = LARGE_PAGE_ORDER;
-        psize = 1ul << porder;
-        if ((mem->memory_size & (psize - 1)) ||
-            (mem->guest_phys_addr & (psize - 1))) {
-                pr_err("bad memory_size=%llx @ %llx\n",
-                       mem->memory_size, mem->guest_phys_addr);
-                return -EINVAL;
+        physp = kvm->arch.slot_phys[slot_id];
+        npages = kvm->arch.slot_npages[slot_id];
+        if (physp) {
+                spin_lock(&kvm->arch.slot_phys_lock);
+                for (j = 0; j < npages; j++) {
+                        if (!(physp[j] & KVMPPC_GOT_PAGE))
+                                continue;
+                        pfn = physp[j] >> PAGE_SHIFT;
+                        page = pfn_to_page(pfn);
+                        if (PageHuge(page))
+                                page = compound_head(page);
+                        SetPageDirty(page);
+                        put_page(page);
+                }
+                kvm->arch.slot_phys[slot_id] = NULL;
+                spin_unlock(&kvm->arch.slot_phys_lock);
+                vfree(physp);
         }
+}
 
-        npages = mem->memory_size >> porder;
-        totalpages = (mem->guest_phys_addr + mem->memory_size) >> porder;
+void kvmppc_core_commit_memory_region(struct kvm *kvm,
+                                struct kvm_userspace_memory_region *mem)
+{
+}
 
-        /* More memory than we have space to track? */
-        if (totalpages > (1ul << (MAX_MEM_ORDER - LARGE_PAGE_ORDER)))
-                return -EINVAL;
+static int kvmppc_hv_setup_rma(struct kvm_vcpu *vcpu)
+{
+        int err = 0;
+        struct kvm *kvm = vcpu->kvm;
+        struct kvmppc_linear_info *ri = NULL;
+        unsigned long hva;
+        struct kvm_memory_slot *memslot;
+        struct vm_area_struct *vma;
+        unsigned long lpcr, senc;
+        unsigned long psize, porder;
+        unsigned long rma_size;
+        unsigned long rmls;
+        unsigned long *physp;
+        unsigned long i, npages;
 
-        /* Do we already have an RMA registered? */
-        if (mem->guest_phys_addr == 0 && kvm->arch.rma)
-                return -EINVAL;
+        mutex_lock(&kvm->lock);
+        if (kvm->arch.rma_setup_done)
+                goto out;       /* another vcpu beat us to it */
+
+        /* Look up the memslot for guest physical address 0 */
+        memslot = gfn_to_memslot(kvm, 0);
+
+        /* We must have some memory at 0 by now */
+        err = -EINVAL;
+        if (!memslot || (memslot->flags & KVM_MEMSLOT_INVALID))
+                goto out;
+
+        /* Look up the VMA for the start of this memory slot */
+        hva = memslot->userspace_addr;
+        down_read(&current->mm->mmap_sem);
+        vma = find_vma(current->mm, hva);
+        if (!vma || vma->vm_start > hva || (vma->vm_flags & VM_IO))
+                goto up_out;
 
-        if (totalpages > kvm->arch.ram_npages)
-                kvm->arch.ram_npages = totalpages;
+        psize = vma_kernel_pagesize(vma);
+        porder = __ilog2(psize);
 
         /* Is this one of our preallocated RMAs? */
-        if (mem->guest_phys_addr == 0) {
-                struct vm_area_struct *vma;
-
-                down_read(&current->mm->mmap_sem);
-                vma = find_vma(current->mm, mem->userspace_addr);
-                if (vma && vma->vm_file &&
-                    vma->vm_file->f_op == &kvm_rma_fops &&
-                    mem->userspace_addr == vma->vm_start)
-                        ri = vma->vm_file->private_data;
-                up_read(&current->mm->mmap_sem);
-                if (!ri && cpu_has_feature(CPU_FTR_ARCH_201)) {
-                        pr_err("CPU requires an RMO\n");
-                        return -EINVAL;
+        if (vma->vm_file && vma->vm_file->f_op == &kvm_rma_fops &&
+            hva == vma->vm_start)
+                ri = vma->vm_file->private_data;
+
+        up_read(&current->mm->mmap_sem);
+
+        if (!ri) {
+                /* On POWER7, use VRMA; on PPC970, give up */
+                err = -EPERM;
+                if (cpu_has_feature(CPU_FTR_ARCH_201)) {
+                        pr_err("KVM: CPU requires an RMO\n");
+                        goto out;
                 }
-        }
 
-        if (ri) {
-                unsigned long rma_size;
-                unsigned long lpcr;
-                long rmls;
+                /* We can handle 4k, 64k or 16M pages in the VRMA */
+                err = -EINVAL;
+                if (!(psize == 0x1000 || psize == 0x10000 ||
+                      psize == 0x1000000))
+                        goto out;
+
+                /* Update VRMASD field in the LPCR */
+                senc = slb_pgsize_encoding(psize);
+                kvm->arch.vrma_slb_v = senc | SLB_VSID_B_1T |
+                        (VRMA_VSID << SLB_VSID_SHIFT_1T);
+                lpcr = kvm->arch.lpcr & ~LPCR_VRMASD;
+                lpcr |= senc << (LPCR_VRMASD_SH - 4);
+                kvm->arch.lpcr = lpcr;
+
+                /* Create HPTEs in the hash page table for the VRMA */
+                kvmppc_map_vrma(vcpu, memslot, porder);
 
-                rma_size = ri->npages << PAGE_SHIFT;
-                if (rma_size > mem->memory_size)
-                        rma_size = mem->memory_size;
+        } else {
+                /* Set up to use an RMO region */
+                rma_size = ri->npages;
+                if (rma_size > memslot->npages)
+                        rma_size = memslot->npages;
+                rma_size <<= PAGE_SHIFT;
                 rmls = lpcr_rmls(rma_size);
+                err = -EINVAL;
                 if (rmls < 0) {
-                        pr_err("Can't use RMA of 0x%lx bytes\n", rma_size);
-                        return -EINVAL;
+                        pr_err("KVM: Can't use RMA of 0x%lx bytes\n", rma_size);
+                        goto out;
                 }
                 atomic_inc(&ri->use_count);
                 kvm->arch.rma = ri;
-                kvm->arch.n_rma_pages = rma_size >> porder;
 
                 /* Update LPCR and RMOR */
                 lpcr = kvm->arch.lpcr;
@@ -1156,53 +1309,35 @@ int kvmppc_core_prepare_memory_region(struct kvm *kvm,
                         kvm->arch.rmor = kvm->arch.rma->base_pfn << PAGE_SHIFT;
                 }
                 kvm->arch.lpcr = lpcr;
-                pr_info("Using RMO at %lx size %lx (LPCR = %lx)\n",
+                pr_info("KVM: Using RMO at %lx size %lx (LPCR = %lx)\n",
                         ri->base_pfn << PAGE_SHIFT, rma_size, lpcr);
-        }
 
-        pg_ix = mem->guest_phys_addr >> porder;
-        pginfo = kvm->arch.ram_pginfo + pg_ix;
-        for (i = 0; i < npages; ++i, ++pg_ix) {
-                if (ri && pg_ix < kvm->arch.n_rma_pages) {
-                        pginfo[i].pfn = ri->base_pfn +
-                                (pg_ix << (porder - PAGE_SHIFT));
-                        continue;
-                }
-                hva = mem->userspace_addr + (i << porder);
-                page = hva_to_page(hva);
-                if (!page) {
-                        pr_err("oops, no pfn for hva %lx\n", hva);
-                        goto err;
-                }
-                /* Check it's a 16MB page */
-                if (!PageHead(page) ||
-                    compound_order(page) != (LARGE_PAGE_ORDER - PAGE_SHIFT)) {
-                        pr_err("page at %lx isn't 16MB (o=%d)\n",
-                               hva, compound_order(page));
-                        goto err;
-                }
-                pginfo[i].pfn = page_to_pfn(page);
+                /* Initialize phys addrs of pages in RMO */
+                npages = ri->npages;
+                porder = __ilog2(npages);
+                physp = kvm->arch.slot_phys[memslot->id];
+                spin_lock(&kvm->arch.slot_phys_lock);
+                for (i = 0; i < npages; ++i)
+                        physp[i] = ((ri->base_pfn + i) << PAGE_SHIFT) + porder;
+                spin_unlock(&kvm->arch.slot_phys_lock);
         }
 
-        return 0;
-
- err:
-        return -EINVAL;
-}
+        /* Order updates to kvm->arch.lpcr etc. vs. rma_setup_done */
+        smp_wmb();
+        kvm->arch.rma_setup_done = 1;
+        err = 0;
+ out:
+        mutex_unlock(&kvm->lock);
+        return err;
 
-void kvmppc_core_commit_memory_region(struct kvm *kvm,
-                                struct kvm_userspace_memory_region *mem)
-{
-        if (mem->guest_phys_addr == 0 && mem->memory_size != 0 &&
-            !kvm->arch.rma)
-                kvmppc_map_vrma(kvm, mem);
+ up_out:
+        up_read(&current->mm->mmap_sem);
+        goto out;
 }
 
 int kvmppc_core_init_vm(struct kvm *kvm)
 {
         long r;
-        unsigned long npages = 1ul << (MAX_MEM_ORDER - LARGE_PAGE_ORDER);
-        long err = -ENOMEM;
         unsigned long lpcr;
 
         /* Allocate hashed page table */
@@ -1212,19 +1347,7 @@ int kvmppc_core_init_vm(struct kvm *kvm)
 
         INIT_LIST_HEAD(&kvm->arch.spapr_tce_tables);
 
-        kvm->arch.ram_pginfo = kzalloc(npages * sizeof(struct kvmppc_pginfo),
-                                       GFP_KERNEL);
-        if (!kvm->arch.ram_pginfo) {
-                pr_err("kvmppc_core_init_vm: couldn't alloc %lu bytes\n",
-                       npages * sizeof(struct kvmppc_pginfo));
-                goto out_free;
-        }
-
-        kvm->arch.ram_npages = 0;
-        kvm->arch.ram_psize = 1ul << LARGE_PAGE_ORDER;
-        kvm->arch.ram_porder = LARGE_PAGE_ORDER;
         kvm->arch.rma = NULL;
-        kvm->arch.n_rma_pages = 0;
 
         kvm->arch.host_sdr1 = mfspr(SPRN_SDR1);
 
@@ -1242,30 +1365,25 @@ int kvmppc_core_init_vm(struct kvm *kvm)
                 kvm->arch.host_lpcr = lpcr = mfspr(SPRN_LPCR);
                 lpcr &= LPCR_PECE | LPCR_LPES;
                 lpcr |= (4UL << LPCR_DPFD_SH) | LPCR_HDICE |
-                        LPCR_VPM0 | LPCR_VRMA_L;
+                        LPCR_VPM0 | LPCR_VPM1;
+                kvm->arch.vrma_slb_v = SLB_VSID_B_1T |
+                        (VRMA_VSID << SLB_VSID_SHIFT_1T);
         }
         kvm->arch.lpcr = lpcr;
 
+        kvm->arch.using_mmu_notifiers = !!cpu_has_feature(CPU_FTR_ARCH_206);
+        spin_lock_init(&kvm->arch.slot_phys_lock);
         return 0;
-
- out_free:
-        kvmppc_free_hpt(kvm);
-        return err;
 }
 
 void kvmppc_core_destroy_vm(struct kvm *kvm)
 {
-        struct kvmppc_pginfo *pginfo;
         unsigned long i;
 
-        if (kvm->arch.ram_pginfo) {
-                pginfo = kvm->arch.ram_pginfo;
-                kvm->arch.ram_pginfo = NULL;
-                for (i = kvm->arch.n_rma_pages; i < kvm->arch.ram_npages; ++i)
-                        if (pginfo[i].pfn)
-                                put_page(pfn_to_page(pginfo[i].pfn));
-                kfree(pginfo);
-        }
+        if (!kvm->arch.using_mmu_notifiers)
+                for (i = 0; i < KVM_MEM_SLOTS_NUM; i++)
+                        unpin_slot(kvm, i);
+
         if (kvm->arch.rma) {
                 kvm_release_rma(kvm->arch.rma);
                 kvm->arch.rma = NULL;
diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c
index a795a13f4a70..bed1279aa6a8 100644
--- a/arch/powerpc/kvm/book3s_hv_builtin.c
+++ b/arch/powerpc/kvm/book3s_hv_builtin.c
@@ -18,6 +18,15 @@
 #include <asm/kvm_ppc.h>
 #include <asm/kvm_book3s.h>
 
+#define KVM_LINEAR_RMA          0
+#define KVM_LINEAR_HPT          1
+
+static void __init kvm_linear_init_one(ulong size, int count, int type);
+static struct kvmppc_linear_info *kvm_alloc_linear(int type);
+static void kvm_release_linear(struct kvmppc_linear_info *ri);
+
+/*************** RMA *************/
+
 /*
  * This maintains a list of RMAs (real mode areas) for KVM guests to use.
  * Each RMA has to be physically contiguous and of a size that the
@@ -29,32 +38,6 @@
 static unsigned long kvm_rma_size = 64 << 20;   /* 64MB */
 static unsigned long kvm_rma_count;
 
-static int __init early_parse_rma_size(char *p)
-{
-        if (!p)
-                return 1;
-
-        kvm_rma_size = memparse(p, &p);
-
-        return 0;
-}
-early_param("kvm_rma_size", early_parse_rma_size);
-
-static int __init early_parse_rma_count(char *p)
-{
-        if (!p)
-                return 1;
-
-        kvm_rma_count = simple_strtoul(p, NULL, 0);
-
-        return 0;
-}
-early_param("kvm_rma_count", early_parse_rma_count);
-
-static struct kvmppc_rma_info *rma_info;
-static LIST_HEAD(free_rmas);
-static DEFINE_SPINLOCK(rma_lock);
-
 /* Work out RMLS (real mode limit selector) field value for a given RMA size.
    Assumes POWER7 or PPC970. */
 static inline int lpcr_rmls(unsigned long rma_size)
@@ -81,45 +64,106 @@ static inline int lpcr_rmls(unsigned long rma_size)
         }
 }
 
+static int __init early_parse_rma_size(char *p)
+{
+        if (!p)
+                return 1;
+
+        kvm_rma_size = memparse(p, &p);
+
+        return 0;
+}
+early_param("kvm_rma_size", early_parse_rma_size);
+
+static int __init early_parse_rma_count(char *p)
+{
+        if (!p)
+                return 1;
+
+        kvm_rma_count = simple_strtoul(p, NULL, 0);
+
+        return 0;
+}
+early_param("kvm_rma_count", early_parse_rma_count);
+
+struct kvmppc_linear_info *kvm_alloc_rma(void)
+{
+        return kvm_alloc_linear(KVM_LINEAR_RMA);
+}
+EXPORT_SYMBOL_GPL(kvm_alloc_rma);
+
+void kvm_release_rma(struct kvmppc_linear_info *ri)
+{
+        kvm_release_linear(ri);
+}
+EXPORT_SYMBOL_GPL(kvm_release_rma);
+
+/*************** HPT *************/
+
 /*
- * Called at boot time while the bootmem allocator is active,
- * to allocate contiguous physical memory for the real memory
- * areas for guests.
+ * This maintains a list of big linear HPT tables that contain the GVA->HPA
+ * memory mappings. If we don't reserve those early on, we might not be able
+ * to get a big (usually 16MB) linear memory region from the kernel anymore.
  */
-void __init kvm_rma_init(void)
+
+static unsigned long kvm_hpt_count;
+
+static int __init early_parse_hpt_count(char *p)
+{
+        if (!p)
+                return 1;
+
+        kvm_hpt_count = simple_strtoul(p, NULL, 0);
+
+        return 0;
+}
+early_param("kvm_hpt_count", early_parse_hpt_count);
+
+struct kvmppc_linear_info *kvm_alloc_hpt(void)
+{
+        return kvm_alloc_linear(KVM_LINEAR_HPT);
+}
+EXPORT_SYMBOL_GPL(kvm_alloc_hpt);
+
+void kvm_release_hpt(struct kvmppc_linear_info *li)
+{
+        kvm_release_linear(li);
+}
+EXPORT_SYMBOL_GPL(kvm_release_hpt);
+
+/*************** generic *************/
+
+static LIST_HEAD(free_linears);
+static DEFINE_SPINLOCK(linear_lock);
+
+static void __init kvm_linear_init_one(ulong size, int count, int type)
 {
         unsigned long i;
         unsigned long j, npages;
-        void *rma;
+        void *linear;
         struct page *pg;
+        const char *typestr;
+        struct kvmppc_linear_info *linear_info;
 
-        /* Only do this on PPC970 in HV mode */
-        if (!cpu_has_feature(CPU_FTR_HVMODE) ||
-            !cpu_has_feature(CPU_FTR_ARCH_201))
-                return;
-
-        if (!kvm_rma_size || !kvm_rma_count)
+        if (!count)
                 return;
 
-        /* Check that the requested size is one supported in hardware */
-        if (lpcr_rmls(kvm_rma_size) < 0) {
-                pr_err("RMA size of 0x%lx not supported\n", kvm_rma_size);
-                return;
-        }
-
-        npages = kvm_rma_size >> PAGE_SHIFT;
-        rma_info = alloc_bootmem(kvm_rma_count * sizeof(struct kvmppc_rma_info));
-        for (i = 0; i < kvm_rma_count; ++i) {
-                rma = alloc_bootmem_align(kvm_rma_size, kvm_rma_size);
-                pr_info("Allocated KVM RMA at %p (%ld MB)\n", rma,
-                        kvm_rma_size >> 20);
-                rma_info[i].base_virt = rma;
-                rma_info[i].base_pfn = __pa(rma) >> PAGE_SHIFT;
-                rma_info[i].npages = npages;
-                list_add_tail(&rma_info[i].list, &free_rmas);
-                atomic_set(&rma_info[i].use_count, 0);
-
-                pg = pfn_to_page(rma_info[i].base_pfn);
+        typestr = (type == KVM_LINEAR_RMA) ? "RMA" : "HPT";
+
+        npages = size >> PAGE_SHIFT;
+        linear_info = alloc_bootmem(count * sizeof(struct kvmppc_linear_info));
+        for (i = 0; i < count; ++i) {
+                linear = alloc_bootmem_align(size, size);
+                pr_info("Allocated KVM %s at %p (%ld MB)\n", typestr, linear,
+                        size >> 20);
+                linear_info[i].base_virt = linear;
+                linear_info[i].base_pfn = __pa(linear) >> PAGE_SHIFT;
+                linear_info[i].npages = npages;
+                linear_info[i].type = type;
+                list_add_tail(&linear_info[i].list, &free_linears);
+                atomic_set(&linear_info[i].use_count, 0);
+
+                pg = pfn_to_page(linear_info[i].base_pfn);
                 for (j = 0; j < npages; ++j) {
                         atomic_inc(&pg->_count);
                         ++pg;
@@ -127,30 +171,59 @@ void __init kvm_rma_init(void)
         }
 }
 
-struct kvmppc_rma_info *kvm_alloc_rma(void)
+static struct kvmppc_linear_info *kvm_alloc_linear(int type)
 {
-        struct kvmppc_rma_info *ri;
+        struct kvmppc_linear_info *ri;
 
         ri = NULL;
-        spin_lock(&rma_lock);
-        if (!list_empty(&free_rmas)) {
-                ri = list_first_entry(&free_rmas, struct kvmppc_rma_info, list);
+        spin_lock(&linear_lock);
+        list_for_each_entry(ri, &free_linears, list) {
+                if (ri->type != type)
+                        continue;
+
                 list_del(&ri->list);
                 atomic_inc(&ri->use_count);
+                break;
         }
-        spin_unlock(&rma_lock);
+        spin_unlock(&linear_lock);
+        memset(ri->base_virt, 0, ri->npages << PAGE_SHIFT);
         return ri;
 }
-EXPORT_SYMBOL_GPL(kvm_alloc_rma);
 
-void kvm_release_rma(struct kvmppc_rma_info *ri)
+static void kvm_release_linear(struct kvmppc_linear_info *ri)
 {
         if (atomic_dec_and_test(&ri->use_count)) {
-                spin_lock(&rma_lock);
-                list_add_tail(&ri->list, &free_rmas);
-                spin_unlock(&rma_lock);
+                spin_lock(&linear_lock);
+                list_add_tail(&ri->list, &free_linears);
+                spin_unlock(&linear_lock);
 
         }
 }
-EXPORT_SYMBOL_GPL(kvm_release_rma);
 
+/*
+ * Called at boot time while the bootmem allocator is active,
+ * to allocate contiguous physical memory for the hash page
+ * tables for guests.
+ */
+void __init kvm_linear_init(void)
+{
+        /* HPT */
+        kvm_linear_init_one(1 << HPT_ORDER, kvm_hpt_count, KVM_LINEAR_HPT);
+
+        /* RMA */
+        /* Only do this on PPC970 in HV mode */
+        if (!cpu_has_feature(CPU_FTR_HVMODE) ||
+            !cpu_has_feature(CPU_FTR_ARCH_201))
+                return;
+
+        if (!kvm_rma_size || !kvm_rma_count)
+                return;
+
+        /* Check that the requested size is one supported in hardware */
+        if (lpcr_rmls(kvm_rma_size) < 0) {
+                pr_err("RMA size of 0x%lx not supported\n", kvm_rma_size);
+                return;
+        }
+
+        kvm_linear_init_one(kvm_rma_size, kvm_rma_count, KVM_LINEAR_RMA);
+}
diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
index bacb0cfa3602..def880aea63a 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
@@ -11,6 +11,7 @@
 #include <linux/kvm.h>
 #include <linux/kvm_host.h>
 #include <linux/hugetlb.h>
+#include <linux/module.h>
 
 #include <asm/tlbflush.h>
 #include <asm/kvm_ppc.h>
@@ -20,95 +21,307 @@
 #include <asm/synch.h>
 #include <asm/ppc-opcode.h>
 
-/* For now use fixed-size 16MB page table */
-#define HPT_ORDER       24
-#define HPT_NPTEG       (1ul << (HPT_ORDER - 7))        /* 128B per pteg */
-#define HPT_HASH_MASK   (HPT_NPTEG - 1)
+/* Translate address of a vmalloc'd thing to a linear map address */
+static void *real_vmalloc_addr(void *x)
+{
+        unsigned long addr = (unsigned long) x;
+        pte_t *p;
 
-#define HPTE_V_HVLOCK   0x40UL
+        p = find_linux_pte(swapper_pg_dir, addr);
+        if (!p || !pte_present(*p))
+                return NULL;
+        /* assume we don't have huge pages in vmalloc space... */
+        addr = (pte_pfn(*p) << PAGE_SHIFT) | (addr & ~PAGE_MASK);
+        return __va(addr);
+}
 
-static inline long lock_hpte(unsigned long *hpte, unsigned long bits)
+/*
+ * Add this HPTE into the chain for the real page.
+ * Must be called with the chain locked; it unlocks the chain.
+ */
+void kvmppc_add_revmap_chain(struct kvm *kvm, struct revmap_entry *rev,
+                             unsigned long *rmap, long pte_index, int realmode)
 {
-        unsigned long tmp, old;
+        struct revmap_entry *head, *tail;
+        unsigned long i;
 
-        asm volatile("  ldarx   %0,0,%2\n"
-                     "  and.    %1,%0,%3\n"
-                     "  bne     2f\n"
-                     "  ori     %0,%0,%4\n"
-                     "  stdcx.  %0,0,%2\n"
-                     "  beq+    2f\n"
-                     "  li      %1,%3\n"
-                     "2:        isync"
-                     : "=&r" (tmp), "=&r" (old)
-                     : "r" (hpte), "r" (bits), "i" (HPTE_V_HVLOCK)
-                     : "cc", "memory");
-        return old == 0;
+        if (*rmap & KVMPPC_RMAP_PRESENT) {
+                i = *rmap & KVMPPC_RMAP_INDEX;
+                head = &kvm->arch.revmap[i];
+                if (realmode)
+                        head = real_vmalloc_addr(head);
+                tail = &kvm->arch.revmap[head->back];
+                if (realmode)
+                        tail = real_vmalloc_addr(tail);
+                rev->forw = i;
+                rev->back = head->back;
+                tail->forw = pte_index;
+                head->back = pte_index;
+        } else {
+                rev->forw = rev->back = pte_index;
+                i = pte_index;
+        }
+        smp_wmb();
+        *rmap = i | KVMPPC_RMAP_REFERENCED | KVMPPC_RMAP_PRESENT; /* unlock */
+}
+EXPORT_SYMBOL_GPL(kvmppc_add_revmap_chain);
+
+/* Remove this HPTE from the chain for a real page */
+static void remove_revmap_chain(struct kvm *kvm, long pte_index,
+                                struct revmap_entry *rev,
+                                unsigned long hpte_v, unsigned long hpte_r)
+{
+        struct revmap_entry *next, *prev;
+        unsigned long gfn, ptel, head;
+        struct kvm_memory_slot *memslot;
+        unsigned long *rmap;
+        unsigned long rcbits;
+
+        rcbits = hpte_r & (HPTE_R_R | HPTE_R_C);
+        ptel = rev->guest_rpte |= rcbits;
+        gfn = hpte_rpn(ptel, hpte_page_size(hpte_v, ptel));
+        memslot = __gfn_to_memslot(kvm_memslots(kvm), gfn);
+        if (!memslot || (memslot->flags & KVM_MEMSLOT_INVALID))
+                return;
+
+        rmap = real_vmalloc_addr(&memslot->rmap[gfn - memslot->base_gfn]);
+        lock_rmap(rmap);
+
+        head = *rmap & KVMPPC_RMAP_INDEX;
+        next = real_vmalloc_addr(&kvm->arch.revmap[rev->forw]);
+        prev = real_vmalloc_addr(&kvm->arch.revmap[rev->back]);
+        next->back = rev->back;
+        prev->forw = rev->forw;
+        if (head == pte_index) {
+                head = rev->forw;
+                if (head == pte_index)
+                        *rmap &= ~(KVMPPC_RMAP_PRESENT | KVMPPC_RMAP_INDEX);
+                else
+                        *rmap = (*rmap & ~KVMPPC_RMAP_INDEX) | head;
+        }
+        *rmap |= rcbits << KVMPPC_RMAP_RC_SHIFT;
+        unlock_rmap(rmap);
+}
+
+static pte_t lookup_linux_pte(struct kvm_vcpu *vcpu, unsigned long hva,
+                              int writing, unsigned long *pte_sizep)
+{
+        pte_t *ptep;
+        unsigned long ps = *pte_sizep;
+        unsigned int shift;
+
+        ptep = find_linux_pte_or_hugepte(vcpu->arch.pgdir, hva, &shift);
+        if (!ptep)
+                return __pte(0);
+        if (shift)
+                *pte_sizep = 1ul << shift;
+        else
+                *pte_sizep = PAGE_SIZE;
+        if (ps > *pte_sizep)
+                return __pte(0);
+        if (!pte_present(*ptep))
+                return __pte(0);
+        return kvmppc_read_update_linux_pte(ptep, writing);
+}
+
+static inline void unlock_hpte(unsigned long *hpte, unsigned long hpte_v)
+{
+        asm volatile(PPC_RELEASE_BARRIER "" : : : "memory");
+        hpte[0] = hpte_v;
 }
 
 long kvmppc_h_enter(struct kvm_vcpu *vcpu, unsigned long flags,
                     long pte_index, unsigned long pteh, unsigned long ptel)
 {
-        unsigned long porder;
         struct kvm *kvm = vcpu->kvm;
-        unsigned long i, lpn, pa;
+        unsigned long i, pa, gpa, gfn, psize;
+        unsigned long slot_fn, hva;
         unsigned long *hpte;
+        struct revmap_entry *rev;
+        unsigned long g_ptel = ptel;
+        struct kvm_memory_slot *memslot;
+        unsigned long *physp, pte_size;
+        unsigned long is_io;
+        unsigned long *rmap;
+        pte_t pte;
+        unsigned int writing;
+        unsigned long mmu_seq;
+        unsigned long rcbits;
+        bool realmode = vcpu->arch.vcore->vcore_state == VCORE_RUNNING;
 
-        /* only handle 4k, 64k and 16M pages for now */
-        porder = 12;
-        if (pteh & HPTE_V_LARGE) {
-                if (cpu_has_feature(CPU_FTR_ARCH_206) &&
-                    (ptel & 0xf000) == 0x1000) {
-                        /* 64k page */
-                        porder = 16;
-                } else if ((ptel & 0xff000) == 0) {
-                        /* 16M page */
-                        porder = 24;
-                        /* lowest AVA bit must be 0 for 16M pages */
-                        if (pteh & 0x80)
-                                return H_PARAMETER;
-                } else
+        psize = hpte_page_size(pteh, ptel);
+        if (!psize)
+                return H_PARAMETER;
+        writing = hpte_is_writable(ptel);
+        pteh &= ~(HPTE_V_HVLOCK | HPTE_V_ABSENT | HPTE_V_VALID);
+
+        /* used later to detect if we might have been invalidated */
+        mmu_seq = kvm->mmu_notifier_seq;
+        smp_rmb();
+
+        /* Find the memslot (if any) for this address */
+        gpa = (ptel & HPTE_R_RPN) & ~(psize - 1);
+        gfn = gpa >> PAGE_SHIFT;
+        memslot = __gfn_to_memslot(kvm_memslots(kvm), gfn);
+        pa = 0;
+        is_io = ~0ul;
+        rmap = NULL;
+        if (!(memslot && !(memslot->flags & KVM_MEMSLOT_INVALID))) {
+                /* PPC970 can't do emulated MMIO */
+                if (!cpu_has_feature(CPU_FTR_ARCH_206))
                         return H_PARAMETER;
+                /* Emulated MMIO - mark this with key=31 */
+                pteh |= HPTE_V_ABSENT;
+                ptel |= HPTE_R_KEY_HI | HPTE_R_KEY_LO;
+                goto do_insert;
         }
-        lpn = (ptel & HPTE_R_RPN) >> kvm->arch.ram_porder;
-        if (lpn >= kvm->arch.ram_npages || porder > kvm->arch.ram_porder)
-                return H_PARAMETER;
-        pa = kvm->arch.ram_pginfo[lpn].pfn << PAGE_SHIFT;
-        if (!pa)
+
+        /* Check if the requested page fits entirely in the memslot. */
+        if (!slot_is_aligned(memslot, psize))
                 return H_PARAMETER;
-        /* Check WIMG */
-        if ((ptel & HPTE_R_WIMG) != HPTE_R_M &&
-            (ptel & HPTE_R_WIMG) != (HPTE_R_W | HPTE_R_I | HPTE_R_M))
+        slot_fn = gfn - memslot->base_gfn;
+        rmap = &memslot->rmap[slot_fn];
+
+        if (!kvm->arch.using_mmu_notifiers) {
+                physp = kvm->arch.slot_phys[memslot->id];
+                if (!physp)
+                        return H_PARAMETER;
+                physp += slot_fn;
+                if (realmode)
+                        physp = real_vmalloc_addr(physp);
+                pa = *physp;
+                if (!pa)
+                        return H_TOO_HARD;
+                is_io = pa & (HPTE_R_I | HPTE_R_W);
+                pte_size = PAGE_SIZE << (pa & KVMPPC_PAGE_ORDER_MASK);
+                pa &= PAGE_MASK;
+        } else {
+                /* Translate to host virtual address */
+                hva = gfn_to_hva_memslot(memslot, gfn);
+
+                /* Look up the Linux PTE for the backing page */
+                pte_size = psize;
+                pte = lookup_linux_pte(vcpu, hva, writing, &pte_size);
+                if (pte_present(pte)) {
+                        if (writing && !pte_write(pte))
+                                /* make the actual HPTE be read-only */
+                                ptel = hpte_make_readonly(ptel);
+                        is_io = hpte_cache_bits(pte_val(pte));
+                        pa = pte_pfn(pte) << PAGE_SHIFT;
+                }
+        }
+        if (pte_size < psize)
                 return H_PARAMETER;
-        pteh &= ~0x60UL;
-        ptel &= ~(HPTE_R_PP0 - kvm->arch.ram_psize);
+        if (pa && pte_size > psize)
+                pa |= gpa & (pte_size - 1);
+
+        ptel &= ~(HPTE_R_PP0 - psize);
         ptel |= pa;
-        if (pte_index >= (HPT_NPTEG << 3))
+
+        if (pa)
+                pteh |= HPTE_V_VALID;
+        else
+                pteh |= HPTE_V_ABSENT;
+
+        /* Check WIMG */
+        if (is_io != ~0ul && !hpte_cache_flags_ok(ptel, is_io)) {
+                if (is_io)
+                        return H_PARAMETER;
+                /*
+                 * Allow guest to map emulated device memory as
+                 * uncacheable, but actually make it cacheable.
+                 */
+                ptel &= ~(HPTE_R_W|HPTE_R_I|HPTE_R_G);
+                ptel |= HPTE_R_M;
+        }
+
+        /* Find and lock the HPTEG slot to use */
+ do_insert:
+        if (pte_index >= HPT_NPTE)
                 return H_PARAMETER;
         if (likely((flags & H_EXACT) == 0)) {
                 pte_index &= ~7UL;
                 hpte = (unsigned long *)(kvm->arch.hpt_virt + (pte_index << 4));
-                for (i = 0; ; ++i) {
-                        if (i == 8)
-                                return H_PTEG_FULL;
+                for (i = 0; i < 8; ++i) {
                         if ((*hpte & HPTE_V_VALID) == 0 &&
-                            lock_hpte(hpte, HPTE_V_HVLOCK | HPTE_V_VALID))
+                            try_lock_hpte(hpte, HPTE_V_HVLOCK | HPTE_V_VALID |
+                                          HPTE_V_ABSENT))
                                 break;
                         hpte += 2;
                 }
+                if (i == 8) {
+                        /*
+                         * Since try_lock_hpte doesn't retry (not even stdcx.
+                         * failures), it could be that there is a free slot
+                         * but we transiently failed to lock it.  Try again,
+                         * actually locking each slot and checking it.
+                         */
+                        hpte -= 16;
+                        for (i = 0; i < 8; ++i) {
+                                while (!try_lock_hpte(hpte, HPTE_V_HVLOCK))
+                                        cpu_relax();
+                                if (!(*hpte & (HPTE_V_VALID | HPTE_V_ABSENT)))
+                                        break;
+                                *hpte &= ~HPTE_V_HVLOCK;
+                                hpte += 2;
+                        }
+                        if (i == 8)
+                                return H_PTEG_FULL;
+                }
+                pte_index += i;
         } else {
-                i = 0;
                 hpte = (unsigned long *)(kvm->arch.hpt_virt + (pte_index << 4));
-                if (!lock_hpte(hpte, HPTE_V_HVLOCK | HPTE_V_VALID))
-                        return H_PTEG_FULL;
+                if (!try_lock_hpte(hpte, HPTE_V_HVLOCK | HPTE_V_VALID |
+                                   HPTE_V_ABSENT)) {
+                        /* Lock the slot and check again */
+                        while (!try_lock_hpte(hpte, HPTE_V_HVLOCK))
+                                cpu_relax();
+                        if (*hpte & (HPTE_V_VALID | HPTE_V_ABSENT)) {
+                                *hpte &= ~HPTE_V_HVLOCK;
+                                return H_PTEG_FULL;
+                        }
+                }
         }
+
+        /* Save away the guest's idea of the second HPTE dword */
+        rev = &kvm->arch.revmap[pte_index];
+        if (realmode)
+                rev = real_vmalloc_addr(rev);
+        if (rev)
+                rev->guest_rpte = g_ptel;
+
+        /* Link HPTE into reverse-map chain */
+        if (pteh & HPTE_V_VALID) {
+                if (realmode)
+                        rmap = real_vmalloc_addr(rmap);
+                lock_rmap(rmap);
+                /* Check for pending invalidations under the rmap chain lock */
+                if (kvm->arch.using_mmu_notifiers &&
+                    mmu_notifier_retry(vcpu, mmu_seq)) {
+                        /* inval in progress, write a non-present HPTE */
+                        pteh |= HPTE_V_ABSENT;
+                        pteh &= ~HPTE_V_VALID;
+                        unlock_rmap(rmap);
+                } else {
+                        kvmppc_add_revmap_chain(kvm, rev, rmap, pte_index,
+                                                realmode);
+                        /* Only set R/C in real HPTE if already set in *rmap */
+                        rcbits = *rmap >> KVMPPC_RMAP_RC_SHIFT;
+                        ptel &= rcbits | ~(HPTE_R_R | HPTE_R_C);
+                }
+        }
+
         hpte[1] = ptel;
+
+        /* Write the first HPTE dword, unlocking the HPTE and making it valid */
         eieio();
         hpte[0] = pteh;
         asm volatile("ptesync" : : : "memory");
-        atomic_inc(&kvm->arch.ram_pginfo[lpn].refcnt);
-        vcpu->arch.gpr[4] = pte_index + i;
+
+        vcpu->arch.gpr[4] = pte_index;
         return H_SUCCESS;
 }
+EXPORT_SYMBOL_GPL(kvmppc_h_enter);
 
 #define LOCK_TOKEN      (*(u32 *)(&get_paca()->lock_token))
 
@@ -137,37 +350,46 @@ long kvmppc_h_remove(struct kvm_vcpu *vcpu, unsigned long flags,
         struct kvm *kvm = vcpu->kvm;
         unsigned long *hpte;
         unsigned long v, r, rb;
+        struct revmap_entry *rev;
 
-        if (pte_index >= (HPT_NPTEG << 3))
+        if (pte_index >= HPT_NPTE)
                 return H_PARAMETER;
         hpte = (unsigned long *)(kvm->arch.hpt_virt + (pte_index << 4));
-        while (!lock_hpte(hpte, HPTE_V_HVLOCK))
+        while (!try_lock_hpte(hpte, HPTE_V_HVLOCK))
                 cpu_relax();
-        if ((hpte[0] & HPTE_V_VALID) == 0 ||
+        if ((hpte[0] & (HPTE_V_ABSENT | HPTE_V_VALID)) == 0 ||
             ((flags & H_AVPN) && (hpte[0] & ~0x7fUL) != avpn) ||
             ((flags & H_ANDCOND) && (hpte[0] & avpn) != 0)) {
                 hpte[0] &= ~HPTE_V_HVLOCK;
                 return H_NOT_FOUND;
         }
-        if (atomic_read(&kvm->online_vcpus) == 1)
-                flags |= H_LOCAL;
-        vcpu->arch.gpr[4] = v = hpte[0] & ~HPTE_V_HVLOCK;
-        vcpu->arch.gpr[5] = r = hpte[1];
-        rb = compute_tlbie_rb(v, r, pte_index);
-        hpte[0] = 0;
-        if (!(flags & H_LOCAL)) {
-                while(!try_lock_tlbie(&kvm->arch.tlbie_lock))
-                        cpu_relax();
-                asm volatile("ptesync" : : : "memory");
-                asm volatile(PPC_TLBIE(%1,%0)"; eieio; tlbsync"
-                             : : "r" (rb), "r" (kvm->arch.lpid));
-                asm volatile("ptesync" : : : "memory");
-                kvm->arch.tlbie_lock = 0;
-        } else {
-                asm volatile("ptesync" : : : "memory");
-                asm volatile("tlbiel %0" : : "r" (rb));
-                asm volatile("ptesync" : : : "memory");
+
+        rev = real_vmalloc_addr(&kvm->arch.revmap[pte_index]);
+        v = hpte[0] & ~HPTE_V_HVLOCK;
+        if (v & HPTE_V_VALID) {
+                hpte[0] &= ~HPTE_V_VALID;
+                rb = compute_tlbie_rb(v, hpte[1], pte_index);
+                if (!(flags & H_LOCAL) && atomic_read(&kvm->online_vcpus) > 1) {
+                        while (!try_lock_tlbie(&kvm->arch.tlbie_lock))
+                                cpu_relax();
+                        asm volatile("ptesync" : : : "memory");
+                        asm volatile(PPC_TLBIE(%1,%0)"; eieio; tlbsync"
+                                     : : "r" (rb), "r" (kvm->arch.lpid));
+                        asm volatile("ptesync" : : : "memory");
+                        kvm->arch.tlbie_lock = 0;
+                } else {
+                        asm volatile("ptesync" : : : "memory");
+                        asm volatile("tlbiel %0" : : "r" (rb));
+                        asm volatile("ptesync" : : : "memory");
+                }
+                /* Read PTE low word after tlbie to get final R/C values */
+                remove_revmap_chain(kvm, pte_index, rev, v, hpte[1]);
         }
+        r = rev->guest_rpte;
+        unlock_hpte(hpte, 0);
+
+        vcpu->arch.gpr[4] = v;
+        vcpu->arch.gpr[5] = r;
         return H_SUCCESS;
 }
 
@@ -175,78 +397,117 @@ long kvmppc_h_bulk_remove(struct kvm_vcpu *vcpu)
 {
         struct kvm *kvm = vcpu->kvm;
         unsigned long *args = &vcpu->arch.gpr[4];
-        unsigned long *hp, tlbrb[4];
-        long int i, found;
-        long int n_inval = 0;
-        unsigned long flags, req, pte_index;
+        unsigned long *hp, *hptes[4], tlbrb[4];
+        long int i, j, k, n, found, indexes[4];
+        unsigned long flags, req, pte_index, rcbits;
         long int local = 0;
         long int ret = H_SUCCESS;
+        struct revmap_entry *rev, *revs[4];
 
         if (atomic_read(&kvm->online_vcpus) == 1)
                 local = 1;
-        for (i = 0; i < 4; ++i) {
-                pte_index = args[i * 2];
-                flags = pte_index >> 56;
-                pte_index &= ((1ul << 56) - 1);
-                req = flags >> 6;
-                flags &= 3;
-                if (req == 3)
-                        break;
-                if (req != 1 || flags == 3 ||
-                    pte_index >= (HPT_NPTEG << 3)) {
-                        /* parameter error */
-                        args[i * 2] = ((0xa0 | flags) << 56) + pte_index;
-                        ret = H_PARAMETER;
-                        break;
-                }
-                hp = (unsigned long *)(kvm->arch.hpt_virt + (pte_index << 4));
-                while (!lock_hpte(hp, HPTE_V_HVLOCK))
-                        cpu_relax();
-                found = 0;
-                if (hp[0] & HPTE_V_VALID) {
-                        switch (flags & 3) {
-                        case 0:         /* absolute */
-                                found = 1;
+        for (i = 0; i < 4 && ret == H_SUCCESS; ) {
+                n = 0;
+                for (; i < 4; ++i) {
+                        j = i * 2;
+                        pte_index = args[j];
+                        flags = pte_index >> 56;
+                        pte_index &= ((1ul << 56) - 1);
+                        req = flags >> 6;
+                        flags &= 3;
+                        if (req == 3) {         /* no more requests */
+                                i = 4;
                                 break;
-                        case 1:         /* andcond */
-                                if (!(hp[0] & args[i * 2 + 1]))
-                                        found = 1;
+                        }
+                        if (req != 1 || flags == 3 || pte_index >= HPT_NPTE) {
+                                /* parameter error */
+                                args[j] = ((0xa0 | flags) << 56) + pte_index;
+                                ret = H_PARAMETER;
                                 break;
-                        case 2:         /* AVPN */
-                                if ((hp[0] & ~0x7fUL) == args[i * 2 + 1])
+                        }
+                        hp = (unsigned long *)
+                                (kvm->arch.hpt_virt + (pte_index << 4));
+                        /* to avoid deadlock, don't spin except for first */
+                        if (!try_lock_hpte(hp, HPTE_V_HVLOCK)) {
+                                if (n)
+                                        break;
+                                while (!try_lock_hpte(hp, HPTE_V_HVLOCK))
+                                        cpu_relax();
+                        }
+                        found = 0;
+                        if (hp[0] & (HPTE_V_ABSENT | HPTE_V_VALID)) {
+                                switch (flags & 3) {
+                                case 0:         /* absolute */
                                         found = 1;
-                                break;
+                                        break;
+                                case 1:         /* andcond */
+                                        if (!(hp[0] & args[j + 1]))
+                                                found = 1;
+                                        break;
+                                case 2:         /* AVPN */
+                                        if ((hp[0] & ~0x7fUL) == args[j + 1])
+                                                found = 1;
+                                        break;
+                                }
+                        }
+                        if (!found) {
+                                hp[0] &= ~HPTE_V_HVLOCK;
+                                args[j] = ((0x90 | flags) << 56) + pte_index;
+                                continue;
                         }
+
+                        args[j] = ((0x80 | flags) << 56) + pte_index;
+                        rev = real_vmalloc_addr(&kvm->arch.revmap[pte_index]);
+
+                        if (!(hp[0] & HPTE_V_VALID)) {
+                                /* insert R and C bits from PTE */
+                                rcbits = rev->guest_rpte & (HPTE_R_R|HPTE_R_C);
+                                args[j] |= rcbits << (56 - 5);
+                                continue;
+                        }
+
+                        hp[0] &= ~HPTE_V_VALID;         /* leave it locked */
+                        tlbrb[n] = compute_tlbie_rb(hp[0], hp[1], pte_index);
+                        indexes[n] = j;
+                        hptes[n] = hp;
+                        revs[n] = rev;
+                        ++n;
+                }
+
+                if (!n)
+                        break;
+
+                /* Now that we've collected a batch, do the tlbies */
+                if (!local) {
+                        while(!try_lock_tlbie(&kvm->arch.tlbie_lock))
+                                cpu_relax();
+                        asm volatile("ptesync" : : : "memory");
+                        for (k = 0; k < n; ++k)
+                                asm volatile(PPC_TLBIE(%1,%0) : :
+                                             "r" (tlbrb[k]),
+                                             "r" (kvm->arch.lpid));
+                        asm volatile("eieio; tlbsync; ptesync" : : : "memory");
+                        kvm->arch.tlbie_lock = 0;
+                } else {
+                        asm volatile("ptesync" : : : "memory");
+                        for (k = 0; k < n; ++k)
+                                asm volatile("tlbiel %0" : : "r" (tlbrb[k]));
+                        asm volatile("ptesync" : : : "memory");
                 }
-                if (!found) {
-                        hp[0] &= ~HPTE_V_HVLOCK;
-                        args[i * 2] = ((0x90 | flags) << 56) + pte_index;
-                        continue;
+
+                /* Read PTE low words after tlbie to get final R/C values */
+                for (k = 0; k < n; ++k) {
+                        j = indexes[k];
+                        pte_index = args[j] & ((1ul << 56) - 1);
+                        hp = hptes[k];
+                        rev = revs[k];
+                        remove_revmap_chain(kvm, pte_index, rev, hp[0], hp[1]);
+                        rcbits = rev->guest_rpte & (HPTE_R_R|HPTE_R_C);
+                        args[j] |= rcbits << (56 - 5);
+                        hp[0] = 0;
                 }
-                /* insert R and C bits from PTE */
-                flags |= (hp[1] >> 5) & 0x0c;
-                args[i * 2] = ((0x80 | flags) << 56) + pte_index;
-                tlbrb[n_inval++] = compute_tlbie_rb(hp[0], hp[1], pte_index);
-                hp[0] = 0;
-        }
-        if (n_inval == 0)
-                return ret;
-
-        if (!local) {
-                while(!try_lock_tlbie(&kvm->arch.tlbie_lock))
-                        cpu_relax();
-                asm volatile("ptesync" : : : "memory");
-                for (i = 0; i < n_inval; ++i)
-                        asm volatile(PPC_TLBIE(%1,%0)
-                                     : : "r" (tlbrb[i]), "r" (kvm->arch.lpid));
-                asm volatile("eieio; tlbsync; ptesync" : : : "memory");
-                kvm->arch.tlbie_lock = 0;
-        } else {
-                asm volatile("ptesync" : : : "memory");
-                for (i = 0; i < n_inval; ++i)
-                        asm volatile("tlbiel %0" : : "r" (tlbrb[i]));
-                asm volatile("ptesync" : : : "memory");
         }
+
         return ret;
 }
 
@@ -256,40 +517,55 @@ long kvmppc_h_protect(struct kvm_vcpu *vcpu, unsigned long flags,
 {
         struct kvm *kvm = vcpu->kvm;
         unsigned long *hpte;
-        unsigned long v, r, rb;
+        struct revmap_entry *rev;
+        unsigned long v, r, rb, mask, bits;
 
-        if (pte_index >= (HPT_NPTEG << 3))
+        if (pte_index >= HPT_NPTE)
                 return H_PARAMETER;
+
         hpte = (unsigned long *)(kvm->arch.hpt_virt + (pte_index << 4));
-        while (!lock_hpte(hpte, HPTE_V_HVLOCK))
+        while (!try_lock_hpte(hpte, HPTE_V_HVLOCK))
                 cpu_relax();
-        if ((hpte[0] & HPTE_V_VALID) == 0 ||
+        if ((hpte[0] & (HPTE_V_ABSENT | HPTE_V_VALID)) == 0 ||
             ((flags & H_AVPN) && (hpte[0] & ~0x7fUL) != avpn)) {
                 hpte[0] &= ~HPTE_V_HVLOCK;
                 return H_NOT_FOUND;
         }
+
         if (atomic_read(&kvm->online_vcpus) == 1)
                 flags |= H_LOCAL;
         v = hpte[0];
-        r = hpte[1] & ~(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);
-        rb = compute_tlbie_rb(v, r, pte_index);
-        hpte[0] = v & ~HPTE_V_VALID;
-        if (!(flags & H_LOCAL)) {
-                while(!try_lock_tlbie(&kvm->arch.tlbie_lock))
-                        cpu_relax();
-                asm volatile("ptesync" : : : "memory");
-                asm volatile(PPC_TLBIE(%1,%0)"; eieio; tlbsync"
-                             : : "r" (rb), "r" (kvm->arch.lpid));
-                asm volatile("ptesync" : : : "memory");
-                kvm->arch.tlbie_lock = 0;
-        } else {
-                asm volatile("ptesync" : : : "memory");
-                asm volatile("tlbiel %0" : : "r" (rb));
-                asm volatile("ptesync" : : : "memory");
+        bits = (flags << 55) & HPTE_R_PP0;
+        bits |= (flags << 48) & HPTE_R_KEY_HI;
+        bits |= flags & (HPTE_R_PP | HPTE_R_N | HPTE_R_KEY_LO);
+
+        /* Update guest view of 2nd HPTE dword */
+        mask = HPTE_R_PP0 | HPTE_R_PP | HPTE_R_N |
+                HPTE_R_KEY_HI | HPTE_R_KEY_LO;
+        rev = real_vmalloc_addr(&kvm->arch.revmap[pte_index]);
+        if (rev) {
+                r = (rev->guest_rpte & ~mask) | bits;
+                rev->guest_rpte = r;
+        }
+        r = (hpte[1] & ~mask) | bits;
+
+        /* Update HPTE */
+        if (v & HPTE_V_VALID) {
+                rb = compute_tlbie_rb(v, r, pte_index);
+                hpte[0] = v & ~HPTE_V_VALID;
+                if (!(flags & H_LOCAL)) {
+                        while(!try_lock_tlbie(&kvm->arch.tlbie_lock))
+                                cpu_relax();
+                        asm volatile("ptesync" : : : "memory");
+                        asm volatile(PPC_TLBIE(%1,%0)"; eieio; tlbsync"
+                                     : : "r" (rb), "r" (kvm->arch.lpid));
+                        asm volatile("ptesync" : : : "memory");
+                        kvm->arch.tlbie_lock = 0;
+                } else {
+                        asm volatile("ptesync" : : : "memory");
+                        asm volatile("tlbiel %0" : : "r" (rb));
+                        asm volatile("ptesync" : : : "memory");
+                }
         }
         hpte[1] = r;
         eieio();
@@ -298,40 +574,243 @@ long kvmppc_h_protect(struct kvm_vcpu *vcpu, unsigned long flags,
         return H_SUCCESS;
 }
 
-static unsigned long reverse_xlate(struct kvm *kvm, unsigned long realaddr)
-{
-        long int i;
-        unsigned long offset, rpn;
-
-        offset = realaddr & (kvm->arch.ram_psize - 1);
-        rpn = (realaddr - offset) >> PAGE_SHIFT;
-        for (i = 0; i < kvm->arch.ram_npages; ++i)
-                if (rpn == kvm->arch.ram_pginfo[i].pfn)
-                        return (i << PAGE_SHIFT) + offset;
-        return HPTE_R_RPN;      /* all 1s in the RPN field */
-}
-
 long kvmppc_h_read(struct kvm_vcpu *vcpu, unsigned long flags,
                    unsigned long pte_index)
 {
         struct kvm *kvm = vcpu->kvm;
-        unsigned long *hpte, r;
+        unsigned long *hpte, v, r;
         int i, n = 1;
+        struct revmap_entry *rev = NULL;
 
-        if (pte_index >= (HPT_NPTEG << 3))
+        if (pte_index >= HPT_NPTE)
                 return H_PARAMETER;
         if (flags & H_READ_4) {
                 pte_index &= ~3;
                 n = 4;
         }
+        rev = real_vmalloc_addr(&kvm->arch.revmap[pte_index]);
         for (i = 0; i < n; ++i, ++pte_index) {
                 hpte = (unsigned long *)(kvm->arch.hpt_virt + (pte_index << 4));
+                v = hpte[0] & ~HPTE_V_HVLOCK;
                 r = hpte[1];
-                if ((flags & H_R_XLATE) && (hpte[0] & HPTE_V_VALID))
-                        r = reverse_xlate(kvm, r & HPTE_R_RPN) |
-                                (r & ~HPTE_R_RPN);
-                vcpu->arch.gpr[4 + i * 2] = hpte[0];
+                if (v & HPTE_V_ABSENT) {
+                        v &= ~HPTE_V_ABSENT;
+                        v |= HPTE_V_VALID;
+                }
+                if (v & HPTE_V_VALID)
+                        r = rev[i].guest_rpte | (r & (HPTE_R_R | HPTE_R_C));
+                vcpu->arch.gpr[4 + i * 2] = v;
                 vcpu->arch.gpr[5 + i * 2] = r;
         }
         return H_SUCCESS;
 }
+
+void kvmppc_invalidate_hpte(struct kvm *kvm, unsigned long *hptep,
+                        unsigned long pte_index)
+{
+        unsigned long rb;
+
+        hptep[0] &= ~HPTE_V_VALID;
+        rb = compute_tlbie_rb(hptep[0], hptep[1], pte_index);
+        while (!try_lock_tlbie(&kvm->arch.tlbie_lock))
+                cpu_relax();
+        asm volatile("ptesync" : : : "memory");
+        asm volatile(PPC_TLBIE(%1,%0)"; eieio; tlbsync"
+                     : : "r" (rb), "r" (kvm->arch.lpid));
+        asm volatile("ptesync" : : : "memory");
+        kvm->arch.tlbie_lock = 0;
+}
+EXPORT_SYMBOL_GPL(kvmppc_invalidate_hpte);
+
+void kvmppc_clear_ref_hpte(struct kvm *kvm, unsigned long *hptep,
+                           unsigned long pte_index)
+{
+        unsigned long rb;
+        unsigned char rbyte;
+
+        rb = compute_tlbie_rb(hptep[0], hptep[1], pte_index);
+        rbyte = (hptep[1] & ~HPTE_R_R) >> 8;
+        /* modify only the second-last byte, which contains the ref bit */
+        *((char *)hptep + 14) = rbyte;
+        while (!try_lock_tlbie(&kvm->arch.tlbie_lock))
+                cpu_relax();
+        asm volatile(PPC_TLBIE(%1,%0)"; eieio; tlbsync"
+                     : : "r" (rb), "r" (kvm->arch.lpid));
+        asm volatile("ptesync" : : : "memory");
+        kvm->arch.tlbie_lock = 0;
+}
+EXPORT_SYMBOL_GPL(kvmppc_clear_ref_hpte);
+
+static int slb_base_page_shift[4] = {
+        24,     /* 16M */
+        16,     /* 64k */
+        34,     /* 16G */
+        20,     /* 1M, unsupported */
+};
+
+long kvmppc_hv_find_lock_hpte(struct kvm *kvm, gva_t eaddr, unsigned long slb_v,
+                              unsigned long valid)
+{
+        unsigned int i;
+        unsigned int pshift;
+        unsigned long somask;
+        unsigned long vsid, hash;
+        unsigned long avpn;
+        unsigned long *hpte;
+        unsigned long mask, val;
+        unsigned long v, r;
+
+        /* Get page shift, work out hash and AVPN etc. */
+        mask = SLB_VSID_B | HPTE_V_AVPN | HPTE_V_SECONDARY;
+        val = 0;
+        pshift = 12;
+        if (slb_v & SLB_VSID_L) {
+                mask |= HPTE_V_LARGE;
+                val |= HPTE_V_LARGE;
+                pshift = slb_base_page_shift[(slb_v & SLB_VSID_LP) >> 4];
+        }
+        if (slb_v & SLB_VSID_B_1T) {
+                somask = (1UL << 40) - 1;
+                vsid = (slb_v & ~SLB_VSID_B) >> SLB_VSID_SHIFT_1T;
+                vsid ^= vsid << 25;
+        } else {
+                somask = (1UL << 28) - 1;
+                vsid = (slb_v & ~SLB_VSID_B) >> SLB_VSID_SHIFT;
+        }
+        hash = (vsid ^ ((eaddr & somask) >> pshift)) & HPT_HASH_MASK;
+        avpn = slb_v & ~(somask >> 16); /* also includes B */
+        avpn |= (eaddr & somask) >> 16;
+
+        if (pshift >= 24)
+                avpn &= ~((1UL << (pshift - 16)) - 1);
+        else
+                avpn &= ~0x7fUL;
+        val |= avpn;
+
+        for (;;) {
+                hpte = (unsigned long *)(kvm->arch.hpt_virt + (hash << 7));
+
+                for (i = 0; i < 16; i += 2) {
+                        /* Read the PTE racily */
+                        v = hpte[i] & ~HPTE_V_HVLOCK;
+
+                        /* Check valid/absent, hash, segment size and AVPN */
+                        if (!(v & valid) || (v & mask) != val)
+                                continue;
+
+                        /* Lock the PTE and read it under the lock */
+                        while (!try_lock_hpte(&hpte[i], HPTE_V_HVLOCK))
+                                cpu_relax();
+                        v = hpte[i] & ~HPTE_V_HVLOCK;
+                        r = hpte[i+1];
+
+                        /*
+                         * Check the HPTE again, including large page size
+                         * Since we don't currently allow any MPSS (mixed
+                         * page-size segment) page sizes, it is sufficient
+                         * to check against the actual page size.
+                         */
+                        if ((v & valid) && (v & mask) == val &&
+                            hpte_page_size(v, r) == (1ul << pshift))
+                                /* Return with the HPTE still locked */
+                                return (hash << 3) + (i >> 1);
+
+                        /* Unlock and move on */
+                        hpte[i] = v;
+                }
+
+                if (val & HPTE_V_SECONDARY)
+                        break;
+                val |= HPTE_V_SECONDARY;
+                hash = hash ^ HPT_HASH_MASK;
+        }
+        return -1;
+}
+EXPORT_SYMBOL(kvmppc_hv_find_lock_hpte);
+
+/*
+ * Called in real mode to check whether an HPTE not found fault
+ * is due to accessing a paged-out page or an emulated MMIO page,
+ * or if a protection fault is due to accessing a page that the
+ * guest wanted read/write access to but which we made read-only.
+ * Returns a possibly modified status (DSISR) value if not
+ * (i.e. pass the interrupt to the guest),
+ * -1 to pass the fault up to host kernel mode code, -2 to do that
+ * and also load the instruction word (for MMIO emulation),
+ * or 0 if we should make the guest retry the access.
+ */
+long kvmppc_hpte_hv_fault(struct kvm_vcpu *vcpu, unsigned long addr,
+                          unsigned long slb_v, unsigned int status, bool data)
+{
+        struct kvm *kvm = vcpu->kvm;
+        long int index;
+        unsigned long v, r, gr;
+        unsigned long *hpte;
+        unsigned long valid;
+        struct revmap_entry *rev;
+        unsigned long pp, key;
+
+        /* For protection fault, expect to find a valid HPTE */
+        valid = HPTE_V_VALID;
+        if (status & DSISR_NOHPTE)
+                valid |= HPTE_V_ABSENT;
+
+        index = kvmppc_hv_find_lock_hpte(kvm, addr, slb_v, valid);
+        if (index < 0) {
+                if (status & DSISR_NOHPTE)
+                        return status;  /* there really was no HPTE */
+                return 0;               /* for prot fault, HPTE disappeared */
+        }
+        hpte = (unsigned long *)(kvm->arch.hpt_virt + (index << 4));
+        v = hpte[0] & ~HPTE_V_HVLOCK;
+        r = hpte[1];
+        rev = real_vmalloc_addr(&kvm->arch.revmap[index]);
+        gr = rev->guest_rpte;
+
+        unlock_hpte(hpte, v);
+
+        /* For not found, if the HPTE is valid by now, retry the instruction */
+        if ((status & DSISR_NOHPTE) && (v & HPTE_V_VALID))
+                return 0;
+
+        /* Check access permissions to the page */
+        pp = gr & (HPTE_R_PP0 | HPTE_R_PP);
+        key = (vcpu->arch.shregs.msr & MSR_PR) ? SLB_VSID_KP : SLB_VSID_KS;
+        status &= ~DSISR_NOHPTE;        /* DSISR_NOHPTE == SRR1_ISI_NOPT */
+        if (!data) {
+                if (gr & (HPTE_R_N | HPTE_R_G))
+                        return status | SRR1_ISI_N_OR_G;
+                if (!hpte_read_permission(pp, slb_v & key))
+                        return status | SRR1_ISI_PROT;
+        } else if (status & DSISR_ISSTORE) {
+                /* check write permission */
+                if (!hpte_write_permission(pp, slb_v & key))
+                        return status | DSISR_PROTFAULT;
+        } else {
+                if (!hpte_read_permission(pp, slb_v & key))
+                        return status | DSISR_PROTFAULT;
+        }
+
+        /* Check storage key, if applicable */
+        if (data && (vcpu->arch.shregs.msr & MSR_DR)) {
+                unsigned int perm = hpte_get_skey_perm(gr, vcpu->arch.amr);
+                if (status & DSISR_ISSTORE)
+                        perm >>= 1;
+                if (perm & 1)
+                        return status | DSISR_KEYFAULT;
+        }
+
+        /* Save HPTE info for virtual-mode handler */
+        vcpu->arch.pgfault_addr = addr;
+        vcpu->arch.pgfault_index = index;
+        vcpu->arch.pgfault_hpte[0] = v;
+        vcpu->arch.pgfault_hpte[1] = r;
+
+        /* Check the storage key to see if it is possibly emulated MMIO */
+        if (data && (vcpu->arch.shregs.msr & MSR_IR) &&
+            (r & (HPTE_R_KEY_HI | HPTE_R_KEY_LO)) ==
+            (HPTE_R_KEY_HI | HPTE_R_KEY_LO))
+                return -2;      /* MMIO emulation - load instr word */
+
+        return -1;              /* send fault up to host kernel mode */
+}
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 5c8b26183f50..b70bf22a3ff3 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -601,6 +601,30 @@ kvmppc_interrupt:
 
         stw     r12,VCPU_TRAP(r9)
 
+        /* Save HEIR (HV emulation assist reg) in last_inst
+           if this is an HEI (HV emulation interrupt, e40) */
+        li      r3,KVM_INST_FETCH_FAILED
+BEGIN_FTR_SECTION
+        cmpwi   r12,BOOK3S_INTERRUPT_H_EMUL_ASSIST
+        bne     11f
+        mfspr   r3,SPRN_HEIR
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
+11:     stw     r3,VCPU_LAST_INST(r9)
+
+        /* these are volatile across C function calls */
+        mfctr   r3
+        mfxer   r4
+        std     r3, VCPU_CTR(r9)
+        stw     r4, VCPU_XER(r9)
+
+BEGIN_FTR_SECTION
+        /* If this is a page table miss then see if it's theirs or ours */
+        cmpwi   r12, BOOK3S_INTERRUPT_H_DATA_STORAGE
+        beq     kvmppc_hdsi
+        cmpwi   r12, BOOK3S_INTERRUPT_H_INST_STORAGE
+        beq     kvmppc_hisi
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
+
         /* See if this is a leftover HDEC interrupt */
         cmpwi   r12,BOOK3S_INTERRUPT_HV_DECREMENTER
         bne     2f
@@ -608,7 +632,7 @@ kvmppc_interrupt:
         cmpwi   r3,0
         bge     ignore_hdec
 2:
-        /* See if this is something we can handle in real mode */
+        /* See if this is an hcall we can handle in real mode */
         cmpwi   r12,BOOK3S_INTERRUPT_SYSCALL
         beq     hcall_try_real_mode
 
@@ -624,6 +648,7 @@ BEGIN_FTR_SECTION
 1:
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
 
+nohpte_cont:
 hcall_real_cont:                /* r9 = vcpu, r12 = trap, r13 = paca */
         /* Save DEC */
         mfspr   r5,SPRN_DEC
@@ -632,36 +657,21 @@ hcall_real_cont:		/* r9 = vcpu, r12 = trap, r13 = paca */
         add     r5,r5,r6
         std     r5,VCPU_DEC_EXPIRES(r9)
 
-        /* Save HEIR (HV emulation assist reg) in last_inst
-           if this is an HEI (HV emulation interrupt, e40) */
-        li      r3,-1
-BEGIN_FTR_SECTION
-        cmpwi   r12,BOOK3S_INTERRUPT_H_EMUL_ASSIST
-        bne     11f
-        mfspr   r3,SPRN_HEIR
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
-11:     stw     r3,VCPU_LAST_INST(r9)
-
         /* Save more register state  */
-        mfxer   r5
         mfdar   r6
         mfdsisr r7
-        mfctr   r8
-
-        stw     r5, VCPU_XER(r9)
         std     r6, VCPU_DAR(r9)
         stw     r7, VCPU_DSISR(r9)
-        std     r8, VCPU_CTR(r9)
-        /* grab HDAR & HDSISR if HV data storage interrupt (HDSI) */
 BEGIN_FTR_SECTION
+        /* don't overwrite fault_dar/fault_dsisr if HDSI */
         cmpwi   r12,BOOK3S_INTERRUPT_H_DATA_STORAGE
         beq     6f
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
-7:      std     r6, VCPU_FAULT_DAR(r9)
+        std     r6, VCPU_FAULT_DAR(r9)
         stw     r7, VCPU_FAULT_DSISR(r9)
 
         /* Save guest CTRL register, set runlatch to 1 */
-        mfspr   r6,SPRN_CTRLF
+6:      mfspr   r6,SPRN_CTRLF
         stw     r6,VCPU_CTRL(r9)
         andi.   r0,r6,1
         bne     4f
@@ -1094,9 +1104,131 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
         mtspr   SPRN_HSRR1, r7
         ba      0x500
 
-6:      mfspr   r6,SPRN_HDAR
-        mfspr   r7,SPRN_HDSISR
-        b       7b
+/*
+ * Check whether an HDSI is an HPTE not found fault or something else.
+ * If it is an HPTE not found fault that is due to the guest accessing
+ * a page that they have mapped but which we have paged out, then
+ * we continue on with the guest exit path.  In all other cases,
+ * reflect the HDSI to the guest as a DSI.
+ */
+kvmppc_hdsi:
+        mfspr   r4, SPRN_HDAR
+        mfspr   r6, SPRN_HDSISR
+        /* HPTE not found fault or protection fault? */
+        andis.  r0, r6, (DSISR_NOHPTE | DSISR_PROTFAULT)@h
+        beq     1f                      /* if not, send it to the guest */
+        andi.   r0, r11, MSR_DR         /* data relocation enabled? */
+        beq     3f
+        clrrdi  r0, r4, 28
+        PPC_SLBFEE_DOT(r5, r0)          /* if so, look up SLB */
+        bne     1f                      /* if no SLB entry found */
+4:      std     r4, VCPU_FAULT_DAR(r9)
+        stw     r6, VCPU_FAULT_DSISR(r9)
+
+        /* Search the hash table. */
+        mr      r3, r9                  /* vcpu pointer */
+        li      r7, 1                   /* data fault */
+        bl      .kvmppc_hpte_hv_fault
+        ld      r9, HSTATE_KVM_VCPU(r13)
+        ld      r10, VCPU_PC(r9)
+        ld      r11, VCPU_MSR(r9)
+        li      r12, BOOK3S_INTERRUPT_H_DATA_STORAGE
+        cmpdi   r3, 0                   /* retry the instruction */
+        beq     6f
+        cmpdi   r3, -1                  /* handle in kernel mode */
+        beq     nohpte_cont
+        cmpdi   r3, -2                  /* MMIO emulation; need instr word */
+        beq     2f
+
+        /* Synthesize a DSI for the guest */
+        ld      r4, VCPU_FAULT_DAR(r9)
+        mr      r6, r3
+1:      mtspr   SPRN_DAR, r4
+        mtspr   SPRN_DSISR, r6
+        mtspr   SPRN_SRR0, r10
+        mtspr   SPRN_SRR1, r11
+        li      r10, BOOK3S_INTERRUPT_DATA_STORAGE
+        li      r11, (MSR_ME << 1) | 1  /* synthesize MSR_SF | MSR_ME */
+        rotldi  r11, r11, 63
+6:      ld      r7, VCPU_CTR(r9)
+        lwz     r8, VCPU_XER(r9)
+        mtctr   r7
+        mtxer   r8
+        mr      r4, r9
+        b       fast_guest_return
+
+3:      ld      r5, VCPU_KVM(r9)        /* not relocated, use VRMA */
+        ld      r5, KVM_VRMA_SLB_V(r5)
+        b       4b
+
+        /* If this is for emulated MMIO, load the instruction word */
+2:      li      r8, KVM_INST_FETCH_FAILED       /* In case lwz faults */
+
+        /* Set guest mode to 'jump over instruction' so if lwz faults
+         * we'll just continue at the next IP. */
+        li      r0, KVM_GUEST_MODE_SKIP
+        stb     r0, HSTATE_IN_GUEST(r13)
+
+        /* Do the access with MSR:DR enabled */
+        mfmsr   r3
+        ori     r4, r3, MSR_DR          /* Enable paging for data */
+        mtmsrd  r4
+        lwz     r8, 0(r10)
+        mtmsrd  r3
+
+        /* Store the result */
+        stw     r8, VCPU_LAST_INST(r9)
+
+        /* Unset guest mode. */
+        li      r0, KVM_GUEST_MODE_NONE
+        stb     r0, HSTATE_IN_GUEST(r13)
+        b       nohpte_cont
+
+/*
+ * Similarly for an HISI, reflect it to the guest as an ISI unless
+ * it is an HPTE not found fault for a page that we have paged out.
+ */
+kvmppc_hisi:
+        andis.  r0, r11, SRR1_ISI_NOPT@h
+        beq     1f
+        andi.   r0, r11, MSR_IR         /* instruction relocation enabled? */
+        beq     3f
+        clrrdi  r0, r10, 28
+        PPC_SLBFEE_DOT(r5, r0)          /* if so, look up SLB */
+        bne     1f                      /* if no SLB entry found */
+4:
+        /* Search the hash table. */
+        mr      r3, r9                  /* vcpu pointer */
+        mr      r4, r10
+        mr      r6, r11
+        li      r7, 0                   /* instruction fault */
+        bl      .kvmppc_hpte_hv_fault
+        ld      r9, HSTATE_KVM_VCPU(r13)
+        ld      r10, VCPU_PC(r9)
+        ld      r11, VCPU_MSR(r9)
+        li      r12, BOOK3S_INTERRUPT_H_INST_STORAGE
+        cmpdi   r3, 0                   /* retry the instruction */
+        beq     6f
+        cmpdi   r3, -1                  /* handle in kernel mode */
+        beq     nohpte_cont
+
+        /* Synthesize an ISI for the guest */
+        mr      r11, r3
+1:      mtspr   SPRN_SRR0, r10
+        mtspr   SPRN_SRR1, r11
+        li      r10, BOOK3S_INTERRUPT_INST_STORAGE
+        li      r11, (MSR_ME << 1) | 1  /* synthesize MSR_SF | MSR_ME */
+        rotldi  r11, r11, 63
+6:      ld      r7, VCPU_CTR(r9)
+        lwz     r8, VCPU_XER(r9)
+        mtctr   r7
+        mtxer   r8
+        mr      r4, r9
+        b       fast_guest_return
+
+3:      ld      r6, VCPU_KVM(r9)        /* not relocated, use VRMA */
+        ld      r5, KVM_VRMA_SLB_V(r6)
+        b       4b
 
 /*
  * Try to handle an hcall in real mode.
diff --git a/arch/powerpc/kvm/book3s_paired_singles.c b/arch/powerpc/kvm/book3s_paired_singles.c
index 7b0ee96c1bed..e70ef2d86431 100644
--- a/arch/powerpc/kvm/book3s_paired_singles.c
+++ b/arch/powerpc/kvm/book3s_paired_singles.c
@@ -196,7 +196,8 @@ static int kvmppc_emulate_fpr_load(struct kvm_run *run, struct kvm_vcpu *vcpu,
                 kvmppc_inject_pf(vcpu, addr, false);
                 goto done_load;
         } else if (r == EMULATE_DO_MMIO) {
-                emulated = kvmppc_handle_load(run, vcpu, KVM_REG_FPR | rs, len, 1);
+                emulated = kvmppc_handle_load(run, vcpu, KVM_MMIO_REG_FPR | rs,
+                                              len, 1);
                 goto done_load;
         }
 
@@ -286,11 +287,13 @@ static int kvmppc_emulate_psq_load(struct kvm_run *run, struct kvm_vcpu *vcpu,
                 kvmppc_inject_pf(vcpu, addr, false);
                 goto done_load;
         } else if ((r == EMULATE_DO_MMIO) && w) {
-                emulated = kvmppc_handle_load(run, vcpu, KVM_REG_FPR | rs, 4, 1);
+                emulated = kvmppc_handle_load(run, vcpu, KVM_MMIO_REG_FPR | rs,
+                                              4, 1);
                 vcpu->arch.qpr[rs] = tmp[1];
                 goto done_load;
         } else if (r == EMULATE_DO_MMIO) {
-                emulated = kvmppc_handle_load(run, vcpu, KVM_REG_FQPR | rs, 8, 1);
+                emulated = kvmppc_handle_load(run, vcpu, KVM_MMIO_REG_FQPR | rs,
+                                              8, 1);
                 goto done_load;
         }
 
diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c
index e2cfb9e1e20e..7340e1090b77 100644
--- a/arch/powerpc/kvm/book3s_pr.c
+++ b/arch/powerpc/kvm/book3s_pr.c
@@ -51,15 +51,19 @@ static int kvmppc_handle_ext(struct kvm_vcpu *vcpu, unsigned int exit_nr,
 #define MSR_USER32 MSR_USER
 #define MSR_USER64 MSR_USER
 #define HW_PAGE_SIZE PAGE_SIZE
+#define __hard_irq_disable local_irq_disable
+#define __hard_irq_enable local_irq_enable
 #endif
 
 void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
 #ifdef CONFIG_PPC_BOOK3S_64
-        memcpy(to_svcpu(vcpu)->slb, to_book3s(vcpu)->slb_shadow, sizeof(to_svcpu(vcpu)->slb));
+        struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
+        memcpy(svcpu->slb, to_book3s(vcpu)->slb_shadow, sizeof(svcpu->slb));
         memcpy(&get_paca()->shadow_vcpu, to_book3s(vcpu)->shadow_vcpu,
                sizeof(get_paca()->shadow_vcpu));
-        to_svcpu(vcpu)->slb_max = to_book3s(vcpu)->slb_shadow_max;
+        svcpu->slb_max = to_book3s(vcpu)->slb_shadow_max;
+        svcpu_put(svcpu);
 #endif
 
 #ifdef CONFIG_PPC_BOOK3S_32
@@ -70,10 +74,12 @@ void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu)
 {
 #ifdef CONFIG_PPC_BOOK3S_64
-        memcpy(to_book3s(vcpu)->slb_shadow, to_svcpu(vcpu)->slb, sizeof(to_svcpu(vcpu)->slb));
+        struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
+        memcpy(to_book3s(vcpu)->slb_shadow, svcpu->slb, sizeof(svcpu->slb));
         memcpy(to_book3s(vcpu)->shadow_vcpu, &get_paca()->shadow_vcpu,
                sizeof(get_paca()->shadow_vcpu));
-        to_book3s(vcpu)->slb_shadow_max = to_svcpu(vcpu)->slb_max;
+        to_book3s(vcpu)->slb_shadow_max = svcpu->slb_max;
+        svcpu_put(svcpu);
 #endif
 
         kvmppc_giveup_ext(vcpu, MSR_FP);
@@ -151,14 +157,16 @@ 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_explicit)
+                        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_explicit)
+                        to_book3s(vcpu)->hior = 0;
                 to_book3s(vcpu)->msr_mask = 0xffffffffULL;
                 vcpu->arch.cpu_type = KVM_CPU_3S_32;
         }
@@ -227,14 +235,14 @@ static void kvmppc_patch_dcbz(struct kvm_vcpu *vcpu, struct kvmppc_pte *pte)
         hpage_offset /= 4;
 
         get_page(hpage);
-        page = kmap_atomic(hpage, KM_USER0);
+        page = kmap_atomic(hpage);
 
         /* patch dcbz into reserved instruction, so we trap */
         for (i=hpage_offset; i < hpage_offset + (HW_PAGE_SIZE / 4); i++)
                 if ((page[i] & 0xff0007ff) == INS_DCBZ)
                         page[i] &= 0xfffffff7;
 
-        kunmap_atomic(page, KM_USER0);
+        kunmap_atomic(page);
         put_page(hpage);
 }
 
@@ -308,19 +316,22 @@ int kvmppc_handle_pagefault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 
         if (page_found == -ENOENT) {
                 /* Page not found in guest PTE entries */
+                struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
                 vcpu->arch.shared->dar = kvmppc_get_fault_dar(vcpu);
-                vcpu->arch.shared->dsisr = to_svcpu(vcpu)->fault_dsisr;
+                vcpu->arch.shared->dsisr = svcpu->fault_dsisr;
                 vcpu->arch.shared->msr |=
-                        (to_svcpu(vcpu)->shadow_srr1 & 0x00000000f8000000ULL);
+                        (svcpu->shadow_srr1 & 0x00000000f8000000ULL);
+                svcpu_put(svcpu);
                 kvmppc_book3s_queue_irqprio(vcpu, vec);
         } else if (page_found == -EPERM) {
                 /* Storage protection */
+                struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
                 vcpu->arch.shared->dar = kvmppc_get_fault_dar(vcpu);
-                vcpu->arch.shared->dsisr =
-                        to_svcpu(vcpu)->fault_dsisr & ~DSISR_NOHPTE;
+                vcpu->arch.shared->dsisr = svcpu->fault_dsisr & ~DSISR_NOHPTE;
                 vcpu->arch.shared->dsisr |= DSISR_PROTFAULT;
                 vcpu->arch.shared->msr |=
-                        (to_svcpu(vcpu)->shadow_srr1 & 0x00000000f8000000ULL);
+                        svcpu->shadow_srr1 & 0x00000000f8000000ULL;
+                svcpu_put(svcpu);
                 kvmppc_book3s_queue_irqprio(vcpu, vec);
         } else if (page_found == -EINVAL) {
                 /* Page not found in guest SLB */
@@ -517,24 +528,29 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
         run->ready_for_interrupt_injection = 1;
 
         trace_kvm_book3s_exit(exit_nr, vcpu);
+        preempt_enable();
         kvm_resched(vcpu);
         switch (exit_nr) {
         case BOOK3S_INTERRUPT_INST_STORAGE:
+        {
+                struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
+                ulong shadow_srr1 = svcpu->shadow_srr1;
                 vcpu->stat.pf_instruc++;
 
 #ifdef CONFIG_PPC_BOOK3S_32
                 /* We set segments as unused segments when invalidating them. So
                  * treat the respective fault as segment fault. */
-                if (to_svcpu(vcpu)->sr[kvmppc_get_pc(vcpu) >> SID_SHIFT]
-                    == SR_INVALID) {
+                if (svcpu->sr[kvmppc_get_pc(vcpu) >> SID_SHIFT] == SR_INVALID) {
                         kvmppc_mmu_map_segment(vcpu, kvmppc_get_pc(vcpu));
                         r = RESUME_GUEST;
+                        svcpu_put(svcpu);
                         break;
                 }
 #endif
+                svcpu_put(svcpu);
 
                 /* only care about PTEG not found errors, but leave NX alone */
-                if (to_svcpu(vcpu)->shadow_srr1 & 0x40000000) {
+                if (shadow_srr1 & 0x40000000) {
                         r = kvmppc_handle_pagefault(run, vcpu, kvmppc_get_pc(vcpu), exit_nr);
                         vcpu->stat.sp_instruc++;
                 } else if (vcpu->arch.mmu.is_dcbz32(vcpu) &&
@@ -547,33 +563,37 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
                         kvmppc_mmu_pte_flush(vcpu, kvmppc_get_pc(vcpu), ~0xFFFUL);
                         r = RESUME_GUEST;
                 } else {
-                        vcpu->arch.shared->msr |=
-                                to_svcpu(vcpu)->shadow_srr1 & 0x58000000;
+                        vcpu->arch.shared->msr |= shadow_srr1 & 0x58000000;
                         kvmppc_book3s_queue_irqprio(vcpu, exit_nr);
                         r = RESUME_GUEST;
                 }
                 break;
+        }
         case BOOK3S_INTERRUPT_DATA_STORAGE:
         {
                 ulong dar = kvmppc_get_fault_dar(vcpu);
+                struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
+                u32 fault_dsisr = svcpu->fault_dsisr;
                 vcpu->stat.pf_storage++;
 
 #ifdef CONFIG_PPC_BOOK3S_32
                 /* We set segments as unused segments when invalidating them. So
                  * treat the respective fault as segment fault. */
-                if ((to_svcpu(vcpu)->sr[dar >> SID_SHIFT]) == SR_INVALID) {
+                if ((svcpu->sr[dar >> SID_SHIFT]) == SR_INVALID) {
                         kvmppc_mmu_map_segment(vcpu, dar);
                         r = RESUME_GUEST;
+                        svcpu_put(svcpu);
                         break;
                 }
 #endif
+                svcpu_put(svcpu);
 
                 /* The only case we need to handle is missing shadow PTEs */
-                if (to_svcpu(vcpu)->fault_dsisr & DSISR_NOHPTE) {
+                if (fault_dsisr & DSISR_NOHPTE) {
                         r = kvmppc_handle_pagefault(run, vcpu, dar, exit_nr);
                 } else {
                         vcpu->arch.shared->dar = dar;
-                        vcpu->arch.shared->dsisr = to_svcpu(vcpu)->fault_dsisr;
+                        vcpu->arch.shared->dsisr = fault_dsisr;
                         kvmppc_book3s_queue_irqprio(vcpu, exit_nr);
                         r = RESUME_GUEST;
                 }
@@ -609,10 +629,13 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
         case BOOK3S_INTERRUPT_PROGRAM:
         {
                 enum emulation_result er;
+                struct kvmppc_book3s_shadow_vcpu *svcpu;
                 ulong flags;
 
 program_interrupt:
-                flags = to_svcpu(vcpu)->shadow_srr1 & 0x1f0000ull;
+                svcpu = svcpu_get(vcpu);
+                flags = svcpu->shadow_srr1 & 0x1f0000ull;
+                svcpu_put(svcpu);
 
                 if (vcpu->arch.shared->msr & MSR_PR) {
 #ifdef EXIT_DEBUG
@@ -740,20 +763,33 @@ program_interrupt:
                 r = RESUME_GUEST;
                 break;
         default:
+        {
+                struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
+                ulong shadow_srr1 = svcpu->shadow_srr1;
+                svcpu_put(svcpu);
                 /* Ugh - bork here! What did we get? */
                 printk(KERN_EMERG "exit_nr=0x%x | pc=0x%lx | msr=0x%lx\n",
-                        exit_nr, kvmppc_get_pc(vcpu), to_svcpu(vcpu)->shadow_srr1);
+                        exit_nr, kvmppc_get_pc(vcpu), shadow_srr1);
                 r = RESUME_HOST;
                 BUG();
                 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. */
+
+                /*
+                 * Interrupts could be timers for the guest which we have to
+                 * inject again, so let's postpone them until we're in the guest
+                 * and if we really did time things so badly, then we just exit
+                 * again due to a host external interrupt.
+                 */
+                __hard_irq_disable();
                 if (signal_pending(current)) {
+                        __hard_irq_enable();
 #ifdef EXIT_DEBUG
                         printk(KERN_EMERG "KVM: Going back to host\n");
 #endif
@@ -761,10 +797,12 @@ program_interrupt:
                         run->exit_reason = KVM_EXIT_INTR;
                         r = -EINTR;
                 } else {
+                        preempt_disable();
+
                         /* In case an interrupt came in that was triggered
                          * from userspace (like DEC), we need to check what
                          * to inject now! */
-                        kvmppc_core_deliver_interrupts(vcpu);
+                        kvmppc_core_prepare_to_enter(vcpu);
                 }
         }
 
@@ -836,6 +874,38 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
         return 0;
 }
 
+int kvm_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
+{
+        int r = -EINVAL;
+
+        switch (reg->id) {
+        case KVM_REG_PPC_HIOR:
+                r = put_user(to_book3s(vcpu)->hior, (u64 __user *)reg->addr);
+                break;
+        default:
+                break;
+        }
+
+        return r;
+}
+
+int kvm_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
+{
+        int r = -EINVAL;
+
+        switch (reg->id) {
+        case KVM_REG_PPC_HIOR:
+                r = get_user(to_book3s(vcpu)->hior, (u64 __user *)reg->addr);
+                if (!r)
+                        to_book3s(vcpu)->hior_explicit = true;
+                break;
+        default:
+                break;
+        }
+
+        return r;
+}
+
 int kvmppc_core_check_processor_compat(void)
 {
         return 0;
@@ -923,16 +993,31 @@ int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 #endif
         ulong ext_msr;
 
+        preempt_disable();
+
         /* Check if we can run the vcpu at all */
         if (!vcpu->arch.sane) {
                 kvm_run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
-                return -EINVAL;
+                ret = -EINVAL;
+                goto out;
         }
 
+        kvmppc_core_prepare_to_enter(vcpu);
+
+        /*
+         * Interrupts could be timers for the guest which we have to inject
+         * again, so let's postpone them until we're in the guest and if we
+         * really did time things so badly, then we just exit again due to
+         * a host external interrupt.
+         */
+        __hard_irq_disable();
+
         /* No need to go into the guest when all we do is going out */
         if (signal_pending(current)) {
+                __hard_irq_enable();
                 kvm_run->exit_reason = KVM_EXIT_INTR;
-                return -EINTR;
+                ret = -EINTR;
+                goto out;
         }
 
         /* Save FPU state in stack */
@@ -974,8 +1059,6 @@ int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 
         kvm_guest_exit();
 
-        local_irq_disable();
-
         current->thread.regs->msr = ext_msr;
 
         /* Make sure we save the guest FPU/Altivec/VSX state */
@@ -1002,9 +1085,50 @@ int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
         current->thread.used_vsr = used_vsr;
 #endif
 
+out:
+        preempt_enable();
         return ret;
 }
 
+/*
+ * Get (and clear) the dirty memory log for a memory slot.
+ */
+int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
+                                      struct kvm_dirty_log *log)
+{
+        struct kvm_memory_slot *memslot;
+        struct kvm_vcpu *vcpu;
+        ulong ga, ga_end;
+        int is_dirty = 0;
+        int r;
+        unsigned long n;
+
+        mutex_lock(&kvm->slots_lock);
+
+        r = kvm_get_dirty_log(kvm, log, &is_dirty);
+        if (r)
+                goto out;
+
+        /* If nothing is dirty, don't bother messing with page tables. */
+        if (is_dirty) {
+                memslot = id_to_memslot(kvm->memslots, log->slot);
+
+                ga = memslot->base_gfn << PAGE_SHIFT;
+                ga_end = ga + (memslot->npages << PAGE_SHIFT);
+
+                kvm_for_each_vcpu(n, vcpu, kvm)
+                        kvmppc_mmu_pte_pflush(vcpu, ga, ga_end);
+
+                n = kvm_dirty_bitmap_bytes(memslot);
+                memset(memslot->dirty_bitmap, 0, n);
+        }
+
+        r = 0;
+out:
+        mutex_unlock(&kvm->slots_lock);
+        return r;
+}
+
 int kvmppc_core_prepare_memory_region(struct kvm *kvm,
                                       struct kvm_userspace_memory_region *mem)
 {
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index bb6c988f010a..ee9e1ee9c858 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -124,12 +124,6 @@ void kvmppc_set_msr(struct kvm_vcpu *vcpu, u32 new_msr)
         vcpu->arch.shared->msr = new_msr;
 
         kvmppc_mmu_msr_notify(vcpu, old_msr);
-
-        if (vcpu->arch.shared->msr & MSR_WE) {
-                kvm_vcpu_block(vcpu);
-                kvmppc_set_exit_type(vcpu, EMULATED_MTMSRWE_EXITS);
-        };
-
         kvmppc_vcpu_sync_spe(vcpu);
 }
 
@@ -258,9 +252,11 @@ static int kvmppc_booke_irqprio_deliver(struct kvm_vcpu *vcpu,
                 allowed = vcpu->arch.shared->msr & MSR_ME;
                 msr_mask = 0;
                 break;
-        case BOOKE_IRQPRIO_EXTERNAL:
         case BOOKE_IRQPRIO_DECREMENTER:
         case BOOKE_IRQPRIO_FIT:
+                keep_irq = true;
+                /* fall through */
+        case BOOKE_IRQPRIO_EXTERNAL:
                 allowed = vcpu->arch.shared->msr & MSR_EE;
                 allowed = allowed && !crit;
                 msr_mask = MSR_CE|MSR_ME|MSR_DE;
@@ -276,7 +272,7 @@ static int kvmppc_booke_irqprio_deliver(struct kvm_vcpu *vcpu,
                 vcpu->arch.shared->srr1 = vcpu->arch.shared->msr;
                 vcpu->arch.pc = vcpu->arch.ivpr | vcpu->arch.ivor[priority];
                 if (update_esr == true)
-                        vcpu->arch.esr = vcpu->arch.queued_esr;
+                        vcpu->arch.shared->esr = vcpu->arch.queued_esr;
                 if (update_dear == true)
                         vcpu->arch.shared->dar = vcpu->arch.queued_dear;
                 kvmppc_set_msr(vcpu, vcpu->arch.shared->msr & msr_mask);
@@ -288,13 +284,26 @@ static int kvmppc_booke_irqprio_deliver(struct kvm_vcpu *vcpu,
         return allowed;
 }
 
-/* Check pending exceptions and deliver one, if possible. */
-void kvmppc_core_deliver_interrupts(struct kvm_vcpu *vcpu)
+static void update_timer_ints(struct kvm_vcpu *vcpu)
+{
+        if ((vcpu->arch.tcr & TCR_DIE) && (vcpu->arch.tsr & TSR_DIS))
+                kvmppc_core_queue_dec(vcpu);
+        else
+                kvmppc_core_dequeue_dec(vcpu);
+}
+
+static void kvmppc_core_check_exceptions(struct kvm_vcpu *vcpu)
 {
         unsigned long *pending = &vcpu->arch.pending_exceptions;
-        unsigned long old_pending = vcpu->arch.pending_exceptions;
         unsigned int priority;
 
+        if (vcpu->requests) {
+                if (kvm_check_request(KVM_REQ_PENDING_TIMER, vcpu)) {
+                        smp_mb();
+                        update_timer_ints(vcpu);
+                }
+        }
+
         priority = __ffs(*pending);
         while (priority <= BOOKE_IRQPRIO_MAX) {
                 if (kvmppc_booke_irqprio_deliver(vcpu, priority))
@@ -306,10 +315,24 @@ void kvmppc_core_deliver_interrupts(struct kvm_vcpu *vcpu)
         }
 
         /* Tell the guest about our interrupt status */
-        if (*pending)
-                vcpu->arch.shared->int_pending = 1;
-        else if (old_pending)
-                vcpu->arch.shared->int_pending = 0;
+        vcpu->arch.shared->int_pending = !!*pending;
+}
+
+/* Check pending exceptions and deliver one, if possible. */
+void kvmppc_core_prepare_to_enter(struct kvm_vcpu *vcpu)
+{
+        WARN_ON_ONCE(!irqs_disabled());
+
+        kvmppc_core_check_exceptions(vcpu);
+
+        if (vcpu->arch.shared->msr & MSR_WE) {
+                local_irq_enable();
+                kvm_vcpu_block(vcpu);
+                local_irq_disable();
+
+                kvmppc_set_exit_type(vcpu, EMULATED_MTMSRWE_EXITS);
+                kvmppc_core_check_exceptions(vcpu);
+        };
 }
 
 int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
@@ -322,11 +345,21 @@ int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
         }
 
         local_irq_disable();
+
+        kvmppc_core_prepare_to_enter(vcpu);
+
+        if (signal_pending(current)) {
+                kvm_run->exit_reason = KVM_EXIT_INTR;
+                ret = -EINTR;
+                goto out;
+        }
+
         kvm_guest_enter();
         ret = __kvmppc_vcpu_run(kvm_run, vcpu);
         kvm_guest_exit();
-        local_irq_enable();
 
+out:
+        local_irq_enable();
         return ret;
 }
 
@@ -603,7 +636,7 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 
         local_irq_disable();
 
-        kvmppc_core_deliver_interrupts(vcpu);
+        kvmppc_core_prepare_to_enter(vcpu);
 
         if (!(r & RESUME_HOST)) {
                 /* To avoid clobbering exit_reason, only check for signals if
@@ -628,6 +661,7 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
         vcpu->arch.pc = 0;
         vcpu->arch.shared->msr = 0;
         vcpu->arch.shadow_msr = MSR_USER | MSR_DE | MSR_IS | MSR_DS;
+        vcpu->arch.shared->pir = vcpu->vcpu_id;
         kvmppc_set_gpr(vcpu, 1, (16<<20) - 8); /* -8 for the callee-save LR slot */
 
         vcpu->arch.shadow_pid = 1;
@@ -662,10 +696,10 @@ int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
         regs->sprg1 = vcpu->arch.shared->sprg1;
         regs->sprg2 = vcpu->arch.shared->sprg2;
         regs->sprg3 = vcpu->arch.shared->sprg3;
-        regs->sprg4 = vcpu->arch.sprg4;
-        regs->sprg5 = vcpu->arch.sprg5;
-        regs->sprg6 = vcpu->arch.sprg6;
-        regs->sprg7 = vcpu->arch.sprg7;
+        regs->sprg4 = vcpu->arch.shared->sprg4;
+        regs->sprg5 = vcpu->arch.shared->sprg5;
+        regs->sprg6 = vcpu->arch.shared->sprg6;
+        regs->sprg7 = vcpu->arch.shared->sprg7;
 
         for (i = 0; i < ARRAY_SIZE(regs->gpr); i++)
                 regs->gpr[i] = kvmppc_get_gpr(vcpu, i);
@@ -690,10 +724,10 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
         vcpu->arch.shared->sprg1 = regs->sprg1;
         vcpu->arch.shared->sprg2 = regs->sprg2;
         vcpu->arch.shared->sprg3 = regs->sprg3;
-        vcpu->arch.sprg4 = regs->sprg4;
-        vcpu->arch.sprg5 = regs->sprg5;
-        vcpu->arch.sprg6 = regs->sprg6;
-        vcpu->arch.sprg7 = regs->sprg7;
+        vcpu->arch.shared->sprg4 = regs->sprg4;
+        vcpu->arch.shared->sprg5 = regs->sprg5;
+        vcpu->arch.shared->sprg6 = regs->sprg6;
+        vcpu->arch.shared->sprg7 = regs->sprg7;
 
         for (i = 0; i < ARRAY_SIZE(regs->gpr); i++)
                 kvmppc_set_gpr(vcpu, i, regs->gpr[i]);
@@ -711,7 +745,7 @@ static void get_sregs_base(struct kvm_vcpu *vcpu,
         sregs->u.e.csrr0 = vcpu->arch.csrr0;
         sregs->u.e.csrr1 = vcpu->arch.csrr1;
         sregs->u.e.mcsr = vcpu->arch.mcsr;
-        sregs->u.e.esr = vcpu->arch.esr;
+        sregs->u.e.esr = vcpu->arch.shared->esr;
         sregs->u.e.dear = vcpu->arch.shared->dar;
         sregs->u.e.tsr = vcpu->arch.tsr;
         sregs->u.e.tcr = vcpu->arch.tcr;
@@ -729,28 +763,19 @@ static int set_sregs_base(struct kvm_vcpu *vcpu,
         vcpu->arch.csrr0 = sregs->u.e.csrr0;
         vcpu->arch.csrr1 = sregs->u.e.csrr1;
         vcpu->arch.mcsr = sregs->u.e.mcsr;
-        vcpu->arch.esr = sregs->u.e.esr;
+        vcpu->arch.shared->esr = sregs->u.e.esr;
         vcpu->arch.shared->dar = sregs->u.e.dear;
         vcpu->arch.vrsave = sregs->u.e.vrsave;
-        vcpu->arch.tcr = sregs->u.e.tcr;
+        kvmppc_set_tcr(vcpu, sregs->u.e.tcr);
 
-        if (sregs->u.e.update_special & KVM_SREGS_E_UPDATE_DEC)
+        if (sregs->u.e.update_special & KVM_SREGS_E_UPDATE_DEC) {
                 vcpu->arch.dec = sregs->u.e.dec;
-
-        kvmppc_emulate_dec(vcpu);
+                kvmppc_emulate_dec(vcpu);
+        }
 
         if (sregs->u.e.update_special & KVM_SREGS_E_UPDATE_TSR) {
-                /*
-                 * FIXME: existing KVM timer handling is incomplete.
-                 * TSR cannot be read by the guest, and its value in
-                 * vcpu->arch is always zero.  For now, just handle
-                 * the case where the caller is trying to inject a
-                 * decrementer interrupt.
-                 */
-
-                if ((sregs->u.e.tsr & TSR_DIS) &&
-                    (vcpu->arch.tcr & TCR_DIE))
-                        kvmppc_core_queue_dec(vcpu);
+                vcpu->arch.tsr = sregs->u.e.tsr;
+                update_timer_ints(vcpu);
         }
 
         return 0;
@@ -761,7 +786,7 @@ static void get_sregs_arch206(struct kvm_vcpu *vcpu,
 {
         sregs->u.e.features |= KVM_SREGS_E_ARCH206;
 
-        sregs->u.e.pir = 0;
+        sregs->u.e.pir = vcpu->vcpu_id;
         sregs->u.e.mcsrr0 = vcpu->arch.mcsrr0;
         sregs->u.e.mcsrr1 = vcpu->arch.mcsrr1;
         sregs->u.e.decar = vcpu->arch.decar;
@@ -774,7 +799,7 @@ static int set_sregs_arch206(struct kvm_vcpu *vcpu,
         if (!(sregs->u.e.features & KVM_SREGS_E_ARCH206))
                 return 0;
 
-        if (sregs->u.e.pir != 0)
+        if (sregs->u.e.pir != vcpu->vcpu_id)
                 return -EINVAL;
 
         vcpu->arch.mcsrr0 = sregs->u.e.mcsrr0;
@@ -862,6 +887,16 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
         return kvmppc_core_set_sregs(vcpu, sregs);
 }
 
+int kvm_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
+{
+        return -EINVAL;
+}
+
+int kvm_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
+{
+        return -EINVAL;
+}
+
 int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
 {
         return -ENOTSUPP;
@@ -906,6 +941,33 @@ void kvmppc_core_destroy_vm(struct kvm *kvm)
 {
 }
 
+void kvmppc_set_tcr(struct kvm_vcpu *vcpu, u32 new_tcr)
+{
+        vcpu->arch.tcr = new_tcr;
+        update_timer_ints(vcpu);
+}
+
+void kvmppc_set_tsr_bits(struct kvm_vcpu *vcpu, u32 tsr_bits)
+{
+        set_bits(tsr_bits, &vcpu->arch.tsr);
+        smp_wmb();
+        kvm_make_request(KVM_REQ_PENDING_TIMER, vcpu);
+        kvm_vcpu_kick(vcpu);
+}
+
+void kvmppc_clr_tsr_bits(struct kvm_vcpu *vcpu, u32 tsr_bits)
+{
+        clear_bits(tsr_bits, &vcpu->arch.tsr);
+        update_timer_ints(vcpu);
+}
+
+void kvmppc_decrementer_func(unsigned long data)
+{
+        struct kvm_vcpu *vcpu = (struct kvm_vcpu *)data;
+
+        kvmppc_set_tsr_bits(vcpu, TSR_DIS);
+}
+
 int __init kvmppc_booke_init(void)
 {
         unsigned long ivor[16];
diff --git a/arch/powerpc/kvm/booke.h b/arch/powerpc/kvm/booke.h
index 8e1fe33d64e5..2fe202705a3f 100644
--- a/arch/powerpc/kvm/booke.h
+++ b/arch/powerpc/kvm/booke.h
@@ -55,6 +55,10 @@ extern unsigned long kvmppc_booke_handlers;
 void kvmppc_set_msr(struct kvm_vcpu *vcpu, u32 new_msr);
 void kvmppc_mmu_msr_notify(struct kvm_vcpu *vcpu, u32 old_msr);
 
+void kvmppc_set_tcr(struct kvm_vcpu *vcpu, u32 new_tcr);
+void kvmppc_set_tsr_bits(struct kvm_vcpu *vcpu, u32 tsr_bits);
+void kvmppc_clr_tsr_bits(struct kvm_vcpu *vcpu, u32 tsr_bits);
+
 int kvmppc_booke_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
                             unsigned int inst, int *advance);
 int kvmppc_booke_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt);
diff --git a/arch/powerpc/kvm/booke_emulate.c b/arch/powerpc/kvm/booke_emulate.c
index 1260f5f24c0c..3e652da36534 100644
--- a/arch/powerpc/kvm/booke_emulate.c
+++ b/arch/powerpc/kvm/booke_emulate.c
@@ -13,6 +13,7 @@
  * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
  *
  * Copyright IBM Corp. 2008
+ * Copyright 2011 Freescale Semiconductor, Inc.
  *
  * Authors: Hollis Blanchard <hollisb@us.ibm.com>
  */
@@ -107,7 +108,7 @@ int kvmppc_booke_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs)
         case SPRN_DEAR:
                 vcpu->arch.shared->dar = spr_val; break;
         case SPRN_ESR:
-                vcpu->arch.esr = spr_val; break;
+                vcpu->arch.shared->esr = spr_val; break;
         case SPRN_DBCR0:
                 vcpu->arch.dbcr0 = spr_val; break;
         case SPRN_DBCR1:
@@ -115,23 +116,23 @@ int kvmppc_booke_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs)
         case SPRN_DBSR:
                 vcpu->arch.dbsr &= ~spr_val; break;
         case SPRN_TSR:
-                vcpu->arch.tsr &= ~spr_val; break;
+                kvmppc_clr_tsr_bits(vcpu, spr_val);
+                break;
         case SPRN_TCR:
-                vcpu->arch.tcr = spr_val;
-                kvmppc_emulate_dec(vcpu);
+                kvmppc_set_tcr(vcpu, spr_val);
                 break;
 
         /* Note: SPRG4-7 are user-readable. These values are
          * loaded into the real SPRGs when resuming the
          * guest. */
         case SPRN_SPRG4:
-                vcpu->arch.sprg4 = spr_val; break;
+                vcpu->arch.shared->sprg4 = spr_val; break;
         case SPRN_SPRG5:
-                vcpu->arch.sprg5 = spr_val; break;
+                vcpu->arch.shared->sprg5 = spr_val; break;
         case SPRN_SPRG6:
-                vcpu->arch.sprg6 = spr_val; break;
+                vcpu->arch.shared->sprg6 = spr_val; break;
         case SPRN_SPRG7:
-                vcpu->arch.sprg7 = spr_val; break;
+                vcpu->arch.shared->sprg7 = spr_val; break;
 
         case SPRN_IVPR:
                 vcpu->arch.ivpr = spr_val;
@@ -202,13 +203,17 @@ int kvmppc_booke_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt)
         case SPRN_DEAR:
                 kvmppc_set_gpr(vcpu, rt, vcpu->arch.shared->dar); break;
         case SPRN_ESR:
-                kvmppc_set_gpr(vcpu, rt, vcpu->arch.esr); break;
+                kvmppc_set_gpr(vcpu, rt, vcpu->arch.shared->esr); break;
         case SPRN_DBCR0:
                 kvmppc_set_gpr(vcpu, rt, vcpu->arch.dbcr0); break;
         case SPRN_DBCR1:
                 kvmppc_set_gpr(vcpu, rt, vcpu->arch.dbcr1); break;
         case SPRN_DBSR:
                 kvmppc_set_gpr(vcpu, rt, vcpu->arch.dbsr); break;
+        case SPRN_TSR:
+                kvmppc_set_gpr(vcpu, rt, vcpu->arch.tsr); break;
+        case SPRN_TCR:
+                kvmppc_set_gpr(vcpu, rt, vcpu->arch.tcr); break;
 
         case SPRN_IVOR0:
                 kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_CRITICAL]);
diff --git a/arch/powerpc/kvm/booke_interrupts.S b/arch/powerpc/kvm/booke_interrupts.S
index 42f2fb1f66e9..10d8ef602e5c 100644
--- a/arch/powerpc/kvm/booke_interrupts.S
+++ b/arch/powerpc/kvm/booke_interrupts.S
@@ -402,19 +402,25 @@ lightweight_exit:
         /* Save vcpu pointer for the exception handlers. */
         mtspr   SPRN_SPRG_WVCPU, r4
 
+        lwz     r5, VCPU_SHARED(r4)
+
         /* Can't switch the stack pointer until after IVPR is switched,
          * because host interrupt handlers would get confused. */
         lwz     r1, VCPU_GPR(r1)(r4)
 
-        /* Host interrupt handlers may have clobbered these guest-readable
-         * SPRGs, so we need to reload them here with the guest's values. */
-        lwz     r3, VCPU_SPRG4(r4)
+        /*
+         * Host interrupt handlers may have clobbered these
+         * guest-readable SPRGs, or the guest kernel may have
+         * written directly to the shared area, so we
+         * need to reload them here with the guest's values.
+         */
+        lwz     r3, VCPU_SHARED_SPRG4(r5)
         mtspr   SPRN_SPRG4W, r3
-        lwz     r3, VCPU_SPRG5(r4)
+        lwz     r3, VCPU_SHARED_SPRG5(r5)
         mtspr   SPRN_SPRG5W, r3
-        lwz     r3, VCPU_SPRG6(r4)
+        lwz     r3, VCPU_SHARED_SPRG6(r5)
         mtspr   SPRN_SPRG6W, r3
-        lwz     r3, VCPU_SPRG7(r4)
+        lwz     r3, VCPU_SHARED_SPRG7(r5)
         mtspr   SPRN_SPRG7W, r3
 
 #ifdef CONFIG_KVM_EXIT_TIMING
diff --git a/arch/powerpc/kvm/e500.c b/arch/powerpc/kvm/e500.c
index 8c0d45a6faf7..ddcd896fa2ff 100644
--- a/arch/powerpc/kvm/e500.c
+++ b/arch/powerpc/kvm/e500.c
@@ -71,9 +71,6 @@ int kvmppc_core_vcpu_setup(struct kvm_vcpu *vcpu)
         vcpu->arch.pvr = mfspr(SPRN_PVR);
         vcpu_e500->svr = mfspr(SPRN_SVR);
 
-        /* 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;
@@ -118,12 +115,12 @@ void kvmppc_core_get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
         sregs->u.e.impl.fsl.hid0 = vcpu_e500->hid0;
         sregs->u.e.impl.fsl.mcar = vcpu_e500->mcar;
 
-        sregs->u.e.mas0 = vcpu_e500->mas0;
-        sregs->u.e.mas1 = vcpu_e500->mas1;
-        sregs->u.e.mas2 = vcpu_e500->mas2;
-        sregs->u.e.mas7_3 = ((u64)vcpu_e500->mas7 << 32) | vcpu_e500->mas3;
-        sregs->u.e.mas4 = vcpu_e500->mas4;
-        sregs->u.e.mas6 = vcpu_e500->mas6;
+        sregs->u.e.mas0 = vcpu->arch.shared->mas0;
+        sregs->u.e.mas1 = vcpu->arch.shared->mas1;
+        sregs->u.e.mas2 = vcpu->arch.shared->mas2;
+        sregs->u.e.mas7_3 = vcpu->arch.shared->mas7_3;
+        sregs->u.e.mas4 = vcpu->arch.shared->mas4;
+        sregs->u.e.mas6 = vcpu->arch.shared->mas6;
 
         sregs->u.e.mmucfg = mfspr(SPRN_MMUCFG);
         sregs->u.e.tlbcfg[0] = vcpu_e500->tlb0cfg;
@@ -151,13 +148,12 @@ int kvmppc_core_set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
         }
 
         if (sregs->u.e.features & KVM_SREGS_E_ARCH206_MMU) {
-                vcpu_e500->mas0 = sregs->u.e.mas0;
-                vcpu_e500->mas1 = sregs->u.e.mas1;
-                vcpu_e500->mas2 = sregs->u.e.mas2;
-                vcpu_e500->mas7 = sregs->u.e.mas7_3 >> 32;
-                vcpu_e500->mas3 = (u32)sregs->u.e.mas7_3;
-                vcpu_e500->mas4 = sregs->u.e.mas4;
-                vcpu_e500->mas6 = sregs->u.e.mas6;
+                vcpu->arch.shared->mas0 = sregs->u.e.mas0;
+                vcpu->arch.shared->mas1 = sregs->u.e.mas1;
+                vcpu->arch.shared->mas2 = sregs->u.e.mas2;
+                vcpu->arch.shared->mas7_3 = sregs->u.e.mas7_3;
+                vcpu->arch.shared->mas4 = sregs->u.e.mas4;
+                vcpu->arch.shared->mas6 = sregs->u.e.mas6;
         }
 
         if (!(sregs->u.e.features & KVM_SREGS_E_IVOR))
@@ -233,6 +229,10 @@ static int __init kvmppc_e500_init(void)
         unsigned long ivor[3];
         unsigned long max_ivor = 0;
 
+        r = kvmppc_core_check_processor_compat();
+        if (r)
+                return r;
+
         r = kvmppc_booke_init();
         if (r)
                 return r;
diff --git a/arch/powerpc/kvm/e500_emulate.c b/arch/powerpc/kvm/e500_emulate.c
index d48ae396f41e..6d0b2bd54fb0 100644
--- a/arch/powerpc/kvm/e500_emulate.c
+++ b/arch/powerpc/kvm/e500_emulate.c
@@ -89,19 +89,23 @@ int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs)
                         return EMULATE_FAIL;
                 vcpu_e500->pid[2] = spr_val; break;
         case SPRN_MAS0:
-                vcpu_e500->mas0 = spr_val; break;
+                vcpu->arch.shared->mas0 = spr_val; break;
         case SPRN_MAS1:
-                vcpu_e500->mas1 = spr_val; break;
+                vcpu->arch.shared->mas1 = spr_val; break;
         case SPRN_MAS2:
-                vcpu_e500->mas2 = spr_val; break;
+                vcpu->arch.shared->mas2 = spr_val; break;
         case SPRN_MAS3:
-                vcpu_e500->mas3 = spr_val; break;
+                vcpu->arch.shared->mas7_3 &= ~(u64)0xffffffff;
+                vcpu->arch.shared->mas7_3 |= spr_val;
+                break;
         case SPRN_MAS4:
-                vcpu_e500->mas4 = spr_val; break;
+                vcpu->arch.shared->mas4 = spr_val; break;
         case SPRN_MAS6:
-                vcpu_e500->mas6 = spr_val; break;
+                vcpu->arch.shared->mas6 = spr_val; break;
         case SPRN_MAS7:
-                vcpu_e500->mas7 = spr_val; break;
+                vcpu->arch.shared->mas7_3 &= (u64)0xffffffff;
+                vcpu->arch.shared->mas7_3 |= (u64)spr_val << 32;
+                break;
         case SPRN_L1CSR0:
                 vcpu_e500->l1csr0 = spr_val;
                 vcpu_e500->l1csr0 &= ~(L1CSR0_DCFI | L1CSR0_CLFC);
@@ -143,6 +147,7 @@ int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt)
 {
         struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
         int emulated = EMULATE_DONE;
+        unsigned long val;
 
         switch (sprn) {
         case SPRN_PID:
@@ -152,20 +157,23 @@ int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt)
         case SPRN_PID2:
                 kvmppc_set_gpr(vcpu, rt, vcpu_e500->pid[2]); break;
         case SPRN_MAS0:
-                kvmppc_set_gpr(vcpu, rt, vcpu_e500->mas0); break;
+                kvmppc_set_gpr(vcpu, rt, vcpu->arch.shared->mas0); break;
         case SPRN_MAS1:
-                kvmppc_set_gpr(vcpu, rt, vcpu_e500->mas1); break;
+                kvmppc_set_gpr(vcpu, rt, vcpu->arch.shared->mas1); break;
         case SPRN_MAS2:
-                kvmppc_set_gpr(vcpu, rt, vcpu_e500->mas2); break;
+                kvmppc_set_gpr(vcpu, rt, vcpu->arch.shared->mas2); break;
         case SPRN_MAS3:
-                kvmppc_set_gpr(vcpu, rt, vcpu_e500->mas3); break;
+                val = (u32)vcpu->arch.shared->mas7_3;
+                kvmppc_set_gpr(vcpu, rt, val);
+                break;
         case SPRN_MAS4:
-                kvmppc_set_gpr(vcpu, rt, vcpu_e500->mas4); break;
+                kvmppc_set_gpr(vcpu, rt, vcpu->arch.shared->mas4); break;
         case SPRN_MAS6:
-                kvmppc_set_gpr(vcpu, rt, vcpu_e500->mas6); break;
+                kvmppc_set_gpr(vcpu, rt, vcpu->arch.shared->mas6); break;
         case SPRN_MAS7:
-                kvmppc_set_gpr(vcpu, rt, vcpu_e500->mas7); break;
-
+                val = vcpu->arch.shared->mas7_3 >> 32;
+                kvmppc_set_gpr(vcpu, rt, val);
+                break;
         case SPRN_TLB0CFG:
                 kvmppc_set_gpr(vcpu, rt, vcpu_e500->tlb0cfg); break;
         case SPRN_TLB1CFG:
diff --git a/arch/powerpc/kvm/e500_tlb.c b/arch/powerpc/kvm/e500_tlb.c
index 13c432ea2fa8..6e53e4164de1 100644
--- a/arch/powerpc/kvm/e500_tlb.c
+++ b/arch/powerpc/kvm/e500_tlb.c
@@ -12,12 +12,19 @@
  * published by the Free Software Foundation.
  */
 
+#include <linux/kernel.h>
 #include <linux/types.h>
 #include <linux/slab.h>
 #include <linux/string.h>
 #include <linux/kvm.h>
 #include <linux/kvm_host.h>
 #include <linux/highmem.h>
+#include <linux/log2.h>
+#include <linux/uaccess.h>
+#include <linux/sched.h>
+#include <linux/rwsem.h>
+#include <linux/vmalloc.h>
+#include <linux/hugetlb.h>
 #include <asm/kvm_ppc.h>
 #include <asm/kvm_e500.h>
 
@@ -26,7 +33,7 @@
 #include "trace.h"
 #include "timing.h"
 
-#define to_htlb1_esel(esel) (tlb1_entry_num - (esel) - 1)
+#define to_htlb1_esel(esel) (host_tlb_params[1].entries - (esel) - 1)
 
 struct id {
         unsigned long val;
@@ -63,7 +70,14 @@ static DEFINE_PER_CPU(struct pcpu_id_table, pcpu_sids);
  * The valid range of shadow ID is [1..255] */
 static DEFINE_PER_CPU(unsigned long, pcpu_last_used_sid);
 
-static unsigned int tlb1_entry_num;
+static struct kvmppc_e500_tlb_params host_tlb_params[E500_TLB_NUM];
+
+static struct kvm_book3e_206_tlb_entry *get_entry(
+        struct kvmppc_vcpu_e500 *vcpu_e500, int tlbsel, int entry)
+{
+        int offset = vcpu_e500->gtlb_offset[tlbsel];
+        return &vcpu_e500->gtlb_arch[offset + entry];
+}
 
 /*
  * Allocate a free shadow id and setup a valid sid mapping in given entry.
@@ -116,13 +130,11 @@ static inline int local_sid_lookup(struct id *entry)
         return -1;
 }
 
-/* Invalidate all id mappings on local core */
+/* Invalidate all id mappings on local core -- call with preempt disabled */
 static inline void local_sid_destroy_all(void)
 {
-        preempt_disable();
         __get_cpu_var(pcpu_last_used_sid) = 0;
         memset(&__get_cpu_var(pcpu_sids), 0, sizeof(__get_cpu_var(pcpu_sids)));
-        preempt_enable();
 }
 
 static void *kvmppc_e500_id_table_alloc(struct kvmppc_vcpu_e500 *vcpu_e500)
@@ -218,34 +230,13 @@ void kvmppc_e500_recalc_shadow_pid(struct kvmppc_vcpu_e500 *vcpu_e500)
         preempt_enable();
 }
 
-void kvmppc_dump_tlbs(struct kvm_vcpu *vcpu)
-{
-        struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
-        struct tlbe *tlbe;
-        int i, tlbsel;
-
-        printk("| %8s | %8s | %8s | %8s | %8s |\n",
-                        "nr", "mas1", "mas2", "mas3", "mas7");
-
-        for (tlbsel = 0; tlbsel < 2; tlbsel++) {
-                printk("Guest TLB%d:\n", tlbsel);
-                for (i = 0; i < vcpu_e500->gtlb_size[tlbsel]; i++) {
-                        tlbe = &vcpu_e500->gtlb_arch[tlbsel][i];
-                        if (tlbe->mas1 & MAS1_VALID)
-                                printk(" G[%d][%3d] |  %08X | %08X | %08X | %08X |\n",
-                                        tlbsel, i, tlbe->mas1, tlbe->mas2,
-                                        tlbe->mas3, tlbe->mas7);
-                }
-        }
-}
-
-static inline unsigned int tlb0_get_next_victim(
+static inline unsigned int gtlb0_get_next_victim(
                 struct kvmppc_vcpu_e500 *vcpu_e500)
 {
         unsigned int victim;
 
         victim = vcpu_e500->gtlb_nv[0]++;
-        if (unlikely(vcpu_e500->gtlb_nv[0] >= KVM_E500_TLB0_WAY_NUM))
+        if (unlikely(vcpu_e500->gtlb_nv[0] >= vcpu_e500->gtlb_params[0].ways))
                 vcpu_e500->gtlb_nv[0] = 0;
 
         return victim;
@@ -254,12 +245,12 @@ static inline unsigned int tlb0_get_next_victim(
 static inline unsigned int tlb1_max_shadow_size(void)
 {
         /* reserve one entry for magic page */
-        return tlb1_entry_num - tlbcam_index - 1;
+        return host_tlb_params[1].entries - tlbcam_index - 1;
 }
 
-static inline int tlbe_is_writable(struct tlbe *tlbe)
+static inline int tlbe_is_writable(struct kvm_book3e_206_tlb_entry *tlbe)
 {
-        return tlbe->mas3 & (MAS3_SW|MAS3_UW);
+        return tlbe->mas7_3 & (MAS3_SW|MAS3_UW);
 }
 
 static inline u32 e500_shadow_mas3_attrib(u32 mas3, int usermode)
@@ -290,40 +281,66 @@ static inline u32 e500_shadow_mas2_attrib(u32 mas2, int usermode)
 /*
  * writing shadow tlb entry to host TLB
  */
-static inline void __write_host_tlbe(struct tlbe *stlbe, uint32_t mas0)
+static inline void __write_host_tlbe(struct kvm_book3e_206_tlb_entry *stlbe,
+                                     uint32_t mas0)
 {
         unsigned long flags;
 
         local_irq_save(flags);
         mtspr(SPRN_MAS0, mas0);
         mtspr(SPRN_MAS1, stlbe->mas1);
-        mtspr(SPRN_MAS2, stlbe->mas2);
-        mtspr(SPRN_MAS3, stlbe->mas3);
-        mtspr(SPRN_MAS7, stlbe->mas7);
+        mtspr(SPRN_MAS2, (unsigned long)stlbe->mas2);
+        mtspr(SPRN_MAS3, (u32)stlbe->mas7_3);
+        mtspr(SPRN_MAS7, (u32)(stlbe->mas7_3 >> 32));
         asm volatile("isync; tlbwe" : : : "memory");
         local_irq_restore(flags);
+
+        trace_kvm_booke206_stlb_write(mas0, stlbe->mas8, stlbe->mas1,
+                                      stlbe->mas2, stlbe->mas7_3);
+}
+
+/*
+ * Acquire a mas0 with victim hint, as if we just took a TLB miss.
+ *
+ * We don't care about the address we're searching for, other than that it's
+ * in the right set and is not present in the TLB.  Using a zero PID and a
+ * userspace address means we don't have to set and then restore MAS5, or
+ * calculate a proper MAS6 value.
+ */
+static u32 get_host_mas0(unsigned long eaddr)
+{
+        unsigned long flags;
+        u32 mas0;
+
+        local_irq_save(flags);
+        mtspr(SPRN_MAS6, 0);
+        asm volatile("tlbsx 0, %0" : : "b" (eaddr & ~CONFIG_PAGE_OFFSET));
+        mas0 = mfspr(SPRN_MAS0);
+        local_irq_restore(flags);
+
+        return mas0;
 }
 
+/* sesel is for tlb1 only */
 static inline void write_host_tlbe(struct kvmppc_vcpu_e500 *vcpu_e500,
-                int tlbsel, int esel, struct tlbe *stlbe)
+                int tlbsel, int sesel, struct kvm_book3e_206_tlb_entry *stlbe)
 {
+        u32 mas0;
+
         if (tlbsel == 0) {
-                __write_host_tlbe(stlbe,
-                                  MAS0_TLBSEL(0) |
-                                  MAS0_ESEL(esel & (KVM_E500_TLB0_WAY_NUM - 1)));
+                mas0 = get_host_mas0(stlbe->mas2);
+                __write_host_tlbe(stlbe, mas0);
         } else {
                 __write_host_tlbe(stlbe,
                                   MAS0_TLBSEL(1) |
-                                  MAS0_ESEL(to_htlb1_esel(esel)));
+                                  MAS0_ESEL(to_htlb1_esel(sesel)));
         }
-        trace_kvm_stlb_write(index_of(tlbsel, esel), stlbe->mas1, stlbe->mas2,
-                             stlbe->mas3, stlbe->mas7);
 }
 
 void kvmppc_map_magic(struct kvm_vcpu *vcpu)
 {
         struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
-        struct tlbe magic;
+        struct kvm_book3e_206_tlb_entry magic;
         ulong shared_page = ((ulong)vcpu->arch.shared) & PAGE_MASK;
         unsigned int stid;
         pfn_t pfn;
@@ -337,9 +354,9 @@ void kvmppc_map_magic(struct kvm_vcpu *vcpu)
         magic.mas1 = MAS1_VALID | MAS1_TS | MAS1_TID(stid) |
                      MAS1_TSIZE(BOOK3E_PAGESZ_4K);
         magic.mas2 = vcpu->arch.magic_page_ea | MAS2_M;
-        magic.mas3 = (pfn << PAGE_SHIFT) |
-                     MAS3_SW | MAS3_SR | MAS3_UW | MAS3_UR;
-        magic.mas7 = pfn >> (32 - PAGE_SHIFT);
+        magic.mas7_3 = ((u64)pfn << PAGE_SHIFT) |
+                       MAS3_SW | MAS3_SR | MAS3_UW | MAS3_UR;
+        magic.mas8 = 0;
 
         __write_host_tlbe(&magic, MAS0_TLBSEL(1) | MAS0_ESEL(tlbcam_index));
         preempt_enable();
@@ -357,10 +374,11 @@ void kvmppc_e500_tlb_put(struct kvm_vcpu *vcpu)
 {
 }
 
-static void kvmppc_e500_stlbe_invalidate(struct kvmppc_vcpu_e500 *vcpu_e500,
-                                         int tlbsel, int esel)
+static void inval_gtlbe_on_host(struct kvmppc_vcpu_e500 *vcpu_e500,
+                                int tlbsel, int esel)
 {
-        struct tlbe *gtlbe = &vcpu_e500->gtlb_arch[tlbsel][esel];
+        struct kvm_book3e_206_tlb_entry *gtlbe =
+                get_entry(vcpu_e500, tlbsel, esel);
         struct vcpu_id_table *idt = vcpu_e500->idt;
         unsigned int pr, tid, ts, pid;
         u32 val, eaddr;
@@ -414,25 +432,57 @@ static void kvmppc_e500_stlbe_invalidate(struct kvmppc_vcpu_e500 *vcpu_e500,
         preempt_enable();
 }
 
+static int tlb0_set_base(gva_t addr, int sets, int ways)
+{
+        int set_base;
+
+        set_base = (addr >> PAGE_SHIFT) & (sets - 1);
+        set_base *= ways;
+
+        return set_base;
+}
+
+static int gtlb0_set_base(struct kvmppc_vcpu_e500 *vcpu_e500, gva_t addr)
+{
+        return tlb0_set_base(addr, vcpu_e500->gtlb_params[0].sets,
+                             vcpu_e500->gtlb_params[0].ways);
+}
+
+static unsigned int get_tlb_esel(struct kvm_vcpu *vcpu, int tlbsel)
+{
+        struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
+        int esel = get_tlb_esel_bit(vcpu);
+
+        if (tlbsel == 0) {
+                esel &= vcpu_e500->gtlb_params[0].ways - 1;
+                esel += gtlb0_set_base(vcpu_e500, vcpu->arch.shared->mas2);
+        } else {
+                esel &= vcpu_e500->gtlb_params[tlbsel].entries - 1;
+        }
+
+        return esel;
+}
+
 /* Search the guest TLB for a matching entry. */
 static int kvmppc_e500_tlb_index(struct kvmppc_vcpu_e500 *vcpu_e500,
                 gva_t eaddr, int tlbsel, unsigned int pid, int as)
 {
-        int size = vcpu_e500->gtlb_size[tlbsel];
-        int set_base;
+        int size = vcpu_e500->gtlb_params[tlbsel].entries;
+        unsigned int set_base, offset;
         int i;
 
         if (tlbsel == 0) {
-                int mask = size / KVM_E500_TLB0_WAY_NUM - 1;
-                set_base = (eaddr >> PAGE_SHIFT) & mask;
-                set_base *= KVM_E500_TLB0_WAY_NUM;
-                size = KVM_E500_TLB0_WAY_NUM;
+                set_base = gtlb0_set_base(vcpu_e500, eaddr);
+                size = vcpu_e500->gtlb_params[0].ways;
         } else {
                 set_base = 0;
         }
 
+        offset = vcpu_e500->gtlb_offset[tlbsel];
+
         for (i = 0; i < size; i++) {
-                struct tlbe *tlbe = &vcpu_e500->gtlb_arch[tlbsel][set_base + i];
+                struct kvm_book3e_206_tlb_entry *tlbe =
+                        &vcpu_e500->gtlb_arch[offset + set_base + i];
                 unsigned int tid;
 
                 if (eaddr < get_tlb_eaddr(tlbe))
@@ -457,27 +507,55 @@ static int kvmppc_e500_tlb_index(struct kvmppc_vcpu_e500 *vcpu_e500,
         return -1;
 }
 
-static inline void kvmppc_e500_priv_setup(struct tlbe_priv *priv,
-                                          struct tlbe *gtlbe,
-                                          pfn_t pfn)
+static inline void kvmppc_e500_ref_setup(struct tlbe_ref *ref,
+                                         struct kvm_book3e_206_tlb_entry *gtlbe,
+                                         pfn_t pfn)
 {
-        priv->pfn = pfn;
-        priv->flags = E500_TLB_VALID;
+        ref->pfn = pfn;
+        ref->flags = E500_TLB_VALID;
 
         if (tlbe_is_writable(gtlbe))
-                priv->flags |= E500_TLB_DIRTY;
+                ref->flags |= E500_TLB_DIRTY;
 }
 
-static inline void kvmppc_e500_priv_release(struct tlbe_priv *priv)
+static inline void kvmppc_e500_ref_release(struct tlbe_ref *ref)
 {
-        if (priv->flags & E500_TLB_VALID) {
-                if (priv->flags & E500_TLB_DIRTY)
-                        kvm_release_pfn_dirty(priv->pfn);
+        if (ref->flags & E500_TLB_VALID) {
+                if (ref->flags & E500_TLB_DIRTY)
+                        kvm_release_pfn_dirty(ref->pfn);
                 else
-                        kvm_release_pfn_clean(priv->pfn);
+                        kvm_release_pfn_clean(ref->pfn);
+
+                ref->flags = 0;
+        }
+}
+
+static void clear_tlb_privs(struct kvmppc_vcpu_e500 *vcpu_e500)
+{
+        int tlbsel = 0;
+        int i;
+
+        for (i = 0; i < vcpu_e500->gtlb_params[tlbsel].entries; i++) {
+                struct tlbe_ref *ref =
+                        &vcpu_e500->gtlb_priv[tlbsel][i].ref;
+                kvmppc_e500_ref_release(ref);
+        }
+}
+
+static void clear_tlb_refs(struct kvmppc_vcpu_e500 *vcpu_e500)
+{
+        int stlbsel = 1;
+        int i;
+
+        kvmppc_e500_id_table_reset_all(vcpu_e500);
 
-                priv->flags = 0;
+        for (i = 0; i < host_tlb_params[stlbsel].entries; i++) {
+                struct tlbe_ref *ref =
+                        &vcpu_e500->tlb_refs[stlbsel][i];
+                kvmppc_e500_ref_release(ref);
         }
+
+        clear_tlb_privs(vcpu_e500);
 }
 
 static inline void kvmppc_e500_deliver_tlb_miss(struct kvm_vcpu *vcpu,
@@ -488,59 +566,54 @@ static inline void kvmppc_e500_deliver_tlb_miss(struct kvm_vcpu *vcpu,
         int tlbsel;
 
         /* since we only have two TLBs, only lower bit is used. */
-        tlbsel = (vcpu_e500->mas4 >> 28) & 0x1;
-        victim = (tlbsel == 0) ? tlb0_get_next_victim(vcpu_e500) : 0;
-        pidsel = (vcpu_e500->mas4 >> 16) & 0xf;
-        tsized = (vcpu_e500->mas4 >> 7) & 0x1f;
+        tlbsel = (vcpu->arch.shared->mas4 >> 28) & 0x1;
+        victim = (tlbsel == 0) ? gtlb0_get_next_victim(vcpu_e500) : 0;
+        pidsel = (vcpu->arch.shared->mas4 >> 16) & 0xf;
+        tsized = (vcpu->arch.shared->mas4 >> 7) & 0x1f;
 
-        vcpu_e500->mas0 = MAS0_TLBSEL(tlbsel) | MAS0_ESEL(victim)
+        vcpu->arch.shared->mas0 = MAS0_TLBSEL(tlbsel) | MAS0_ESEL(victim)
                 | MAS0_NV(vcpu_e500->gtlb_nv[tlbsel]);
-        vcpu_e500->mas1 = MAS1_VALID | (as ? MAS1_TS : 0)
+        vcpu->arch.shared->mas1 = MAS1_VALID | (as ? MAS1_TS : 0)
                 | MAS1_TID(vcpu_e500->pid[pidsel])
                 | MAS1_TSIZE(tsized);
-        vcpu_e500->mas2 = (eaddr & MAS2_EPN)
-                | (vcpu_e500->mas4 & MAS2_ATTRIB_MASK);
-        vcpu_e500->mas3 &= MAS3_U0 | MAS3_U1 | MAS3_U2 | MAS3_U3;
-        vcpu_e500->mas6 = (vcpu_e500->mas6 & MAS6_SPID1)
+        vcpu->arch.shared->mas2 = (eaddr & MAS2_EPN)
+                | (vcpu->arch.shared->mas4 & MAS2_ATTRIB_MASK);
+        vcpu->arch.shared->mas7_3 &= MAS3_U0 | MAS3_U1 | MAS3_U2 | MAS3_U3;
+        vcpu->arch.shared->mas6 = (vcpu->arch.shared->mas6 & MAS6_SPID1)
                 | (get_cur_pid(vcpu) << 16)
                 | (as ? MAS6_SAS : 0);
-        vcpu_e500->mas7 = 0;
 }
 
-static inline void kvmppc_e500_setup_stlbe(struct kvmppc_vcpu_e500 *vcpu_e500,
-                                           struct tlbe *gtlbe, int tsize,
-                                           struct tlbe_priv *priv,
-                                           u64 gvaddr, struct tlbe *stlbe)
+/* TID must be supplied by the caller */
+static inline void kvmppc_e500_setup_stlbe(
+        struct kvmppc_vcpu_e500 *vcpu_e500,
+        struct kvm_book3e_206_tlb_entry *gtlbe,
+        int tsize, struct tlbe_ref *ref, u64 gvaddr,
+        struct kvm_book3e_206_tlb_entry *stlbe)
 {
-        pfn_t pfn = priv->pfn;
-        unsigned int stid;
+        pfn_t pfn = ref->pfn;
 
-        stid = kvmppc_e500_get_sid(vcpu_e500, get_tlb_ts(gtlbe),
-                                   get_tlb_tid(gtlbe),
-                                   get_cur_pr(&vcpu_e500->vcpu), 0);
+        BUG_ON(!(ref->flags & E500_TLB_VALID));
 
         /* Force TS=1 IPROT=0 for all guest mappings. */
-        stlbe->mas1 = MAS1_TSIZE(tsize)
-                | MAS1_TID(stid) | MAS1_TS | MAS1_VALID;
+        stlbe->mas1 = MAS1_TSIZE(tsize) | MAS1_TS | MAS1_VALID;
         stlbe->mas2 = (gvaddr & MAS2_EPN)
                 | e500_shadow_mas2_attrib(gtlbe->mas2,
                                 vcpu_e500->vcpu.arch.shared->msr & MSR_PR);
-        stlbe->mas3 = ((pfn << PAGE_SHIFT) & MAS3_RPN)
-                | e500_shadow_mas3_attrib(gtlbe->mas3,
+        stlbe->mas7_3 = ((u64)pfn << PAGE_SHIFT)
+                | e500_shadow_mas3_attrib(gtlbe->mas7_3,
                                 vcpu_e500->vcpu.arch.shared->msr & MSR_PR);
-        stlbe->mas7 = (pfn >> (32 - PAGE_SHIFT)) & MAS7_RPN;
 }
 
-
 static inline void kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
-        u64 gvaddr, gfn_t gfn, struct tlbe *gtlbe, int tlbsel, int esel,
-        struct tlbe *stlbe)
+        u64 gvaddr, gfn_t gfn, struct kvm_book3e_206_tlb_entry *gtlbe,
+        int tlbsel, struct kvm_book3e_206_tlb_entry *stlbe,
+        struct tlbe_ref *ref)
 {
         struct kvm_memory_slot *slot;
         unsigned long pfn, hva;
         int pfnmap = 0;
         int tsize = BOOK3E_PAGESZ_4K;
-        struct tlbe_priv *priv;
 
         /*
          * Translate guest physical to true physical, acquiring
@@ -621,12 +694,31 @@ static inline void kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
                                 pfn &= ~(tsize_pages - 1);
                                 break;
                         }
+                } else if (vma && hva >= vma->vm_start &&
+                           (vma->vm_flags & VM_HUGETLB)) {
+                        unsigned long psize = vma_kernel_pagesize(vma);
+
+                        tsize = (gtlbe->mas1 & MAS1_TSIZE_MASK) >>
+                                MAS1_TSIZE_SHIFT;
+
+                        /*
+                         * Take the largest page size that satisfies both host
+                         * and guest mapping
+                         */
+                        tsize = min(__ilog2(psize) - 10, tsize);
+
+                        /*
+                         * e500 doesn't implement the lowest tsize bit,
+                         * or 1K pages.
+                         */
+                        tsize = max(BOOK3E_PAGESZ_4K, tsize & ~1);
                 }
 
                 up_read(&current->mm->mmap_sem);
         }
 
         if (likely(!pfnmap)) {
+                unsigned long tsize_pages = 1 << (tsize + 10 - PAGE_SHIFT);
                 pfn = gfn_to_pfn_memslot(vcpu_e500->vcpu.kvm, slot, gfn);
                 if (is_error_pfn(pfn)) {
                         printk(KERN_ERR "Couldn't get real page for gfn %lx!\n",
@@ -634,45 +726,52 @@ static inline void kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
                         kvm_release_pfn_clean(pfn);
                         return;
                 }
+
+                /* Align guest and physical address to page map boundaries */
+                pfn &= ~(tsize_pages - 1);
+                gvaddr &= ~((tsize_pages << PAGE_SHIFT) - 1);
         }
 
-        /* Drop old priv and setup new one. */
-        priv = &vcpu_e500->gtlb_priv[tlbsel][esel];
-        kvmppc_e500_priv_release(priv);
-        kvmppc_e500_priv_setup(priv, gtlbe, pfn);
+        /* Drop old ref and setup new one. */
+        kvmppc_e500_ref_release(ref);
+        kvmppc_e500_ref_setup(ref, gtlbe, pfn);
 
-        kvmppc_e500_setup_stlbe(vcpu_e500, gtlbe, tsize, priv, gvaddr, stlbe);
+        kvmppc_e500_setup_stlbe(vcpu_e500, gtlbe, tsize, ref, gvaddr, stlbe);
 }
 
 /* XXX only map the one-one case, for now use TLB0 */
-static int kvmppc_e500_tlb0_map(struct kvmppc_vcpu_e500 *vcpu_e500,
-                                int esel, struct tlbe *stlbe)
+static void kvmppc_e500_tlb0_map(struct kvmppc_vcpu_e500 *vcpu_e500,
+                                 int esel,
+                                 struct kvm_book3e_206_tlb_entry *stlbe)
 {
-        struct tlbe *gtlbe;
+        struct kvm_book3e_206_tlb_entry *gtlbe;
+        struct tlbe_ref *ref;
 
-        gtlbe = &vcpu_e500->gtlb_arch[0][esel];
+        gtlbe = get_entry(vcpu_e500, 0, esel);
+        ref = &vcpu_e500->gtlb_priv[0][esel].ref;
 
         kvmppc_e500_shadow_map(vcpu_e500, get_tlb_eaddr(gtlbe),
                         get_tlb_raddr(gtlbe) >> PAGE_SHIFT,
-                        gtlbe, 0, esel, stlbe);
-
-        return esel;
+                        gtlbe, 0, stlbe, ref);
 }
 
 /* Caller must ensure that the specified guest TLB entry is safe to insert into
  * the shadow TLB. */
 /* XXX for both one-one and one-to-many , for now use TLB1 */
 static int kvmppc_e500_tlb1_map(struct kvmppc_vcpu_e500 *vcpu_e500,
-                u64 gvaddr, gfn_t gfn, struct tlbe *gtlbe, struct tlbe *stlbe)
+                u64 gvaddr, gfn_t gfn, struct kvm_book3e_206_tlb_entry *gtlbe,
+                struct kvm_book3e_206_tlb_entry *stlbe)
 {
+        struct tlbe_ref *ref;
         unsigned int victim;
 
-        victim = vcpu_e500->gtlb_nv[1]++;
+        victim = vcpu_e500->host_tlb1_nv++;
 
-        if (unlikely(vcpu_e500->gtlb_nv[1] >= tlb1_max_shadow_size()))
-                vcpu_e500->gtlb_nv[1] = 0;
+        if (unlikely(vcpu_e500->host_tlb1_nv >= tlb1_max_shadow_size()))
+                vcpu_e500->host_tlb1_nv = 0;
 
-        kvmppc_e500_shadow_map(vcpu_e500, gvaddr, gfn, gtlbe, 1, victim, stlbe);
+        ref = &vcpu_e500->tlb_refs[1][victim];
+        kvmppc_e500_shadow_map(vcpu_e500, gvaddr, gfn, gtlbe, 1, stlbe, ref);
 
         return victim;
 }
@@ -689,7 +788,8 @@ static inline int kvmppc_e500_gtlbe_invalidate(
                                 struct kvmppc_vcpu_e500 *vcpu_e500,
                                 int tlbsel, int esel)
 {
-        struct tlbe *gtlbe = &vcpu_e500->gtlb_arch[tlbsel][esel];
+        struct kvm_book3e_206_tlb_entry *gtlbe =
+                get_entry(vcpu_e500, tlbsel, esel);
 
         if (unlikely(get_tlb_iprot(gtlbe)))
                 return -1;
@@ -704,10 +804,10 @@ int kvmppc_e500_emul_mt_mmucsr0(struct kvmppc_vcpu_e500 *vcpu_e500, ulong value)
         int esel;
 
         if (value & MMUCSR0_TLB0FI)
-                for (esel = 0; esel < vcpu_e500->gtlb_size[0]; esel++)
+                for (esel = 0; esel < vcpu_e500->gtlb_params[0].entries; esel++)
                         kvmppc_e500_gtlbe_invalidate(vcpu_e500, 0, esel);
         if (value & MMUCSR0_TLB1FI)
-                for (esel = 0; esel < vcpu_e500->gtlb_size[1]; esel++)
+                for (esel = 0; esel < vcpu_e500->gtlb_params[1].entries; esel++)
                         kvmppc_e500_gtlbe_invalidate(vcpu_e500, 1, esel);
 
         /* Invalidate all vcpu id mappings */
@@ -732,7 +832,8 @@ int kvmppc_e500_emul_tlbivax(struct kvm_vcpu *vcpu, int ra, int rb)
 
         if (ia) {
                 /* invalidate all entries */
-                for (esel = 0; esel < vcpu_e500->gtlb_size[tlbsel]; esel++)
+                for (esel = 0; esel < vcpu_e500->gtlb_params[tlbsel].entries;
+                     esel++)
                         kvmppc_e500_gtlbe_invalidate(vcpu_e500, tlbsel, esel);
         } else {
                 ea &= 0xfffff000;
@@ -752,18 +853,17 @@ int kvmppc_e500_emul_tlbre(struct kvm_vcpu *vcpu)
 {
         struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
         int tlbsel, esel;
-        struct tlbe *gtlbe;
+        struct kvm_book3e_206_tlb_entry *gtlbe;
 
-        tlbsel = get_tlb_tlbsel(vcpu_e500);
-        esel = get_tlb_esel(vcpu_e500, tlbsel);
+        tlbsel = get_tlb_tlbsel(vcpu);
+        esel = get_tlb_esel(vcpu, tlbsel);
 
-        gtlbe = &vcpu_e500->gtlb_arch[tlbsel][esel];
-        vcpu_e500->mas0 &= ~MAS0_NV(~0);
-        vcpu_e500->mas0 |= MAS0_NV(vcpu_e500->gtlb_nv[tlbsel]);
-        vcpu_e500->mas1 = gtlbe->mas1;
-        vcpu_e500->mas2 = gtlbe->mas2;
-        vcpu_e500->mas3 = gtlbe->mas3;
-        vcpu_e500->mas7 = gtlbe->mas7;
+        gtlbe = get_entry(vcpu_e500, tlbsel, esel);
+        vcpu->arch.shared->mas0 &= ~MAS0_NV(~0);
+        vcpu->arch.shared->mas0 |= MAS0_NV(vcpu_e500->gtlb_nv[tlbsel]);
+        vcpu->arch.shared->mas1 = gtlbe->mas1;
+        vcpu->arch.shared->mas2 = gtlbe->mas2;
+        vcpu->arch.shared->mas7_3 = gtlbe->mas7_3;
 
         return EMULATE_DONE;
 }
@@ -771,10 +871,10 @@ int kvmppc_e500_emul_tlbre(struct kvm_vcpu *vcpu)
 int kvmppc_e500_emul_tlbsx(struct kvm_vcpu *vcpu, int rb)
 {
         struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
-        int as = !!get_cur_sas(vcpu_e500);
-        unsigned int pid = get_cur_spid(vcpu_e500);
+        int as = !!get_cur_sas(vcpu);
+        unsigned int pid = get_cur_spid(vcpu);
         int esel, tlbsel;
-        struct tlbe *gtlbe = NULL;
+        struct kvm_book3e_206_tlb_entry *gtlbe = NULL;
         gva_t ea;
 
         ea = kvmppc_get_gpr(vcpu, rb);
@@ -782,70 +882,90 @@ int kvmppc_e500_emul_tlbsx(struct kvm_vcpu *vcpu, int rb)
         for (tlbsel = 0; tlbsel < 2; tlbsel++) {
                 esel = kvmppc_e500_tlb_index(vcpu_e500, ea, tlbsel, pid, as);
                 if (esel >= 0) {
-                        gtlbe = &vcpu_e500->gtlb_arch[tlbsel][esel];
+                        gtlbe = get_entry(vcpu_e500, tlbsel, esel);
                         break;
                 }
         }
 
         if (gtlbe) {
-                vcpu_e500->mas0 = MAS0_TLBSEL(tlbsel) | MAS0_ESEL(esel)
+                esel &= vcpu_e500->gtlb_params[tlbsel].ways - 1;
+
+                vcpu->arch.shared->mas0 = MAS0_TLBSEL(tlbsel) | MAS0_ESEL(esel)
                         | MAS0_NV(vcpu_e500->gtlb_nv[tlbsel]);
-                vcpu_e500->mas1 = gtlbe->mas1;
-                vcpu_e500->mas2 = gtlbe->mas2;
-                vcpu_e500->mas3 = gtlbe->mas3;
-                vcpu_e500->mas7 = gtlbe->mas7;
+                vcpu->arch.shared->mas1 = gtlbe->mas1;
+                vcpu->arch.shared->mas2 = gtlbe->mas2;
+                vcpu->arch.shared->mas7_3 = gtlbe->mas7_3;
         } else {
                 int victim;
 
                 /* since we only have two TLBs, only lower bit is used. */
-                tlbsel = vcpu_e500->mas4 >> 28 & 0x1;
-                victim = (tlbsel == 0) ? tlb0_get_next_victim(vcpu_e500) : 0;
+                tlbsel = vcpu->arch.shared->mas4 >> 28 & 0x1;
+                victim = (tlbsel == 0) ? gtlb0_get_next_victim(vcpu_e500) : 0;
 
-                vcpu_e500->mas0 = MAS0_TLBSEL(tlbsel) | MAS0_ESEL(victim)
+                vcpu->arch.shared->mas0 = MAS0_TLBSEL(tlbsel)
+                        | MAS0_ESEL(victim)
                         | MAS0_NV(vcpu_e500->gtlb_nv[tlbsel]);
-                vcpu_e500->mas1 = (vcpu_e500->mas6 & MAS6_SPID0)
-                        | (vcpu_e500->mas6 & (MAS6_SAS ? MAS1_TS : 0))
-                        | (vcpu_e500->mas4 & MAS4_TSIZED(~0));
-                vcpu_e500->mas2 &= MAS2_EPN;
-                vcpu_e500->mas2 |= vcpu_e500->mas4 & MAS2_ATTRIB_MASK;
-                vcpu_e500->mas3 &= MAS3_U0 | MAS3_U1 | MAS3_U2 | MAS3_U3;
-                vcpu_e500->mas7 = 0;
+                vcpu->arch.shared->mas1 =
+                          (vcpu->arch.shared->mas6 & MAS6_SPID0)
+                        | (vcpu->arch.shared->mas6 & (MAS6_SAS ? MAS1_TS : 0))
+                        | (vcpu->arch.shared->mas4 & MAS4_TSIZED(~0));
+                vcpu->arch.shared->mas2 &= MAS2_EPN;
+                vcpu->arch.shared->mas2 |= vcpu->arch.shared->mas4 &
+                                           MAS2_ATTRIB_MASK;
+                vcpu->arch.shared->mas7_3 &= MAS3_U0 | MAS3_U1 |
+                                             MAS3_U2 | MAS3_U3;
         }
 
         kvmppc_set_exit_type(vcpu, EMULATED_TLBSX_EXITS);
         return EMULATE_DONE;
 }
 
+/* sesel is for tlb1 only */
+static void write_stlbe(struct kvmppc_vcpu_e500 *vcpu_e500,
+                        struct kvm_book3e_206_tlb_entry *gtlbe,
+                        struct kvm_book3e_206_tlb_entry *stlbe,
+                        int stlbsel, int sesel)
+{
+        int stid;
+
+        preempt_disable();
+        stid = kvmppc_e500_get_sid(vcpu_e500, get_tlb_ts(gtlbe),
+                                   get_tlb_tid(gtlbe),
+                                   get_cur_pr(&vcpu_e500->vcpu), 0);
+
+        stlbe->mas1 |= MAS1_TID(stid);
+        write_host_tlbe(vcpu_e500, stlbsel, sesel, stlbe);
+        preempt_enable();
+}
+
 int kvmppc_e500_emul_tlbwe(struct kvm_vcpu *vcpu)
 {
         struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
-        struct tlbe *gtlbe;
+        struct kvm_book3e_206_tlb_entry *gtlbe;
         int tlbsel, esel;
 
-        tlbsel = get_tlb_tlbsel(vcpu_e500);
-        esel = get_tlb_esel(vcpu_e500, tlbsel);
+        tlbsel = get_tlb_tlbsel(vcpu);
+        esel = get_tlb_esel(vcpu, tlbsel);
 
-        gtlbe = &vcpu_e500->gtlb_arch[tlbsel][esel];
+        gtlbe = get_entry(vcpu_e500, tlbsel, esel);
 
         if (get_tlb_v(gtlbe))
-                kvmppc_e500_stlbe_invalidate(vcpu_e500, tlbsel, esel);
+                inval_gtlbe_on_host(vcpu_e500, tlbsel, esel);
 
-        gtlbe->mas1 = vcpu_e500->mas1;
-        gtlbe->mas2 = vcpu_e500->mas2;
-        gtlbe->mas3 = vcpu_e500->mas3;
-        gtlbe->mas7 = vcpu_e500->mas7;
+        gtlbe->mas1 = vcpu->arch.shared->mas1;
+        gtlbe->mas2 = vcpu->arch.shared->mas2;
+        gtlbe->mas7_3 = vcpu->arch.shared->mas7_3;
 
-        trace_kvm_gtlb_write(vcpu_e500->mas0, gtlbe->mas1, gtlbe->mas2,
-                             gtlbe->mas3, gtlbe->mas7);
+        trace_kvm_booke206_gtlb_write(vcpu->arch.shared->mas0, gtlbe->mas1,
+                                      gtlbe->mas2, gtlbe->mas7_3);
 
         /* Invalidate shadow mappings for the about-to-be-clobbered TLBE. */
         if (tlbe_is_host_safe(vcpu, gtlbe)) {
-                struct tlbe stlbe;
+                struct kvm_book3e_206_tlb_entry stlbe;
                 int stlbsel, sesel;
                 u64 eaddr;
                 u64 raddr;
 
-                preempt_disable();
                 switch (tlbsel) {
                 case 0:
                         /* TLB0 */
@@ -853,7 +973,8 @@ int kvmppc_e500_emul_tlbwe(struct kvm_vcpu *vcpu)
                         gtlbe->mas1 |= MAS1_TSIZE(BOOK3E_PAGESZ_4K);
 
                         stlbsel = 0;
-                        sesel = kvmppc_e500_tlb0_map(vcpu_e500, esel, &stlbe);
+                        kvmppc_e500_tlb0_map(vcpu_e500, esel, &stlbe);
+                        sesel = 0; /* unused */
 
                         break;
 
@@ -874,8 +995,8 @@ int kvmppc_e500_emul_tlbwe(struct kvm_vcpu *vcpu)
                 default:
                         BUG();
                 }
-                write_host_tlbe(vcpu_e500, stlbsel, sesel, &stlbe);
-                preempt_enable();
+
+                write_stlbe(vcpu_e500, gtlbe, &stlbe, stlbsel, sesel);
         }
 
         kvmppc_set_exit_type(vcpu, EMULATED_TLBWE_EXITS);
@@ -914,9 +1035,11 @@ gpa_t kvmppc_mmu_xlate(struct kvm_vcpu *vcpu, unsigned int index,
                         gva_t eaddr)
 {
         struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
-        struct tlbe *gtlbe =
-                &vcpu_e500->gtlb_arch[tlbsel_of(index)][esel_of(index)];
-        u64 pgmask = get_tlb_bytes(gtlbe) - 1;
+        struct kvm_book3e_206_tlb_entry *gtlbe;
+        u64 pgmask;
+
+        gtlbe = get_entry(vcpu_e500, tlbsel_of(index), esel_of(index));
+        pgmask = get_tlb_bytes(gtlbe) - 1;
 
         return get_tlb_raddr(gtlbe) | (eaddr & pgmask);
 }
@@ -930,22 +1053,21 @@ void kvmppc_mmu_map(struct kvm_vcpu *vcpu, u64 eaddr, gpa_t gpaddr,
 {
         struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
         struct tlbe_priv *priv;
-        struct tlbe *gtlbe, stlbe;
+        struct kvm_book3e_206_tlb_entry *gtlbe, stlbe;
         int tlbsel = tlbsel_of(index);
         int esel = esel_of(index);
         int stlbsel, sesel;
 
-        gtlbe = &vcpu_e500->gtlb_arch[tlbsel][esel];
+        gtlbe = get_entry(vcpu_e500, tlbsel, esel);
 
-        preempt_disable();
         switch (tlbsel) {
         case 0:
                 stlbsel = 0;
-                sesel = esel;
-                priv = &vcpu_e500->gtlb_priv[stlbsel][sesel];
+                sesel = 0; /* unused */
+                priv = &vcpu_e500->gtlb_priv[tlbsel][esel];
 
                 kvmppc_e500_setup_stlbe(vcpu_e500, gtlbe, BOOK3E_PAGESZ_4K,
-                                        priv, eaddr, &stlbe);
+                                        &priv->ref, eaddr, &stlbe);
                 break;
 
         case 1: {
@@ -962,8 +1084,7 @@ void kvmppc_mmu_map(struct kvm_vcpu *vcpu, u64 eaddr, gpa_t gpaddr,
                 break;
         }
 
-        write_host_tlbe(vcpu_e500, stlbsel, sesel, &stlbe);
-        preempt_enable();
+        write_stlbe(vcpu_e500, gtlbe, &stlbe, stlbsel, sesel);
 }
 
 int kvmppc_e500_tlb_search(struct kvm_vcpu *vcpu,
@@ -993,85 +1114,279 @@ void kvmppc_set_pid(struct kvm_vcpu *vcpu, u32 pid)
 
 void kvmppc_e500_tlb_setup(struct kvmppc_vcpu_e500 *vcpu_e500)
 {
-        struct tlbe *tlbe;
+        struct kvm_book3e_206_tlb_entry *tlbe;
 
         /* Insert large initial mapping for guest. */
-        tlbe = &vcpu_e500->gtlb_arch[1][0];
+        tlbe = get_entry(vcpu_e500, 1, 0);
         tlbe->mas1 = MAS1_VALID | MAS1_TSIZE(BOOK3E_PAGESZ_256M);
         tlbe->mas2 = 0;
-        tlbe->mas3 = E500_TLB_SUPER_PERM_MASK;
-        tlbe->mas7 = 0;
+        tlbe->mas7_3 = E500_TLB_SUPER_PERM_MASK;
 
         /* 4K map for serial output. Used by kernel wrapper. */
-        tlbe = &vcpu_e500->gtlb_arch[1][1];
+        tlbe = get_entry(vcpu_e500, 1, 1);
         tlbe->mas1 = MAS1_VALID | MAS1_TSIZE(BOOK3E_PAGESZ_4K);
         tlbe->mas2 = (0xe0004500 & 0xFFFFF000) | MAS2_I | MAS2_G;
-        tlbe->mas3 = (0xe0004500 & 0xFFFFF000) | E500_TLB_SUPER_PERM_MASK;
-        tlbe->mas7 = 0;
+        tlbe->mas7_3 = (0xe0004500 & 0xFFFFF000) | E500_TLB_SUPER_PERM_MASK;
+}
+
+static void free_gtlb(struct kvmppc_vcpu_e500 *vcpu_e500)
+{
+        int i;
+
+        clear_tlb_refs(vcpu_e500);
+        kfree(vcpu_e500->gtlb_priv[0]);
+        kfree(vcpu_e500->gtlb_priv[1]);
+
+        if (vcpu_e500->shared_tlb_pages) {
+                vfree((void *)(round_down((uintptr_t)vcpu_e500->gtlb_arch,
+                                          PAGE_SIZE)));
+
+                for (i = 0; i < vcpu_e500->num_shared_tlb_pages; i++) {
+                        set_page_dirty_lock(vcpu_e500->shared_tlb_pages[i]);
+                        put_page(vcpu_e500->shared_tlb_pages[i]);
+                }
+
+                vcpu_e500->num_shared_tlb_pages = 0;
+                vcpu_e500->shared_tlb_pages = NULL;
+        } else {
+                kfree(vcpu_e500->gtlb_arch);
+        }
+
+        vcpu_e500->gtlb_arch = NULL;
+}
+
+int kvm_vcpu_ioctl_config_tlb(struct kvm_vcpu *vcpu,
+                              struct kvm_config_tlb *cfg)
+{
+        struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
+        struct kvm_book3e_206_tlb_params params;
+        char *virt;
+        struct page **pages;
+        struct tlbe_priv *privs[2] = {};
+        size_t array_len;
+        u32 sets;
+        int num_pages, ret, i;
+
+        if (cfg->mmu_type != KVM_MMU_FSL_BOOKE_NOHV)
+                return -EINVAL;
+
+        if (copy_from_user(&params, (void __user *)(uintptr_t)cfg->params,
+                           sizeof(params)))
+                return -EFAULT;
+
+        if (params.tlb_sizes[1] > 64)
+                return -EINVAL;
+        if (params.tlb_ways[1] != params.tlb_sizes[1])
+                return -EINVAL;
+        if (params.tlb_sizes[2] != 0 || params.tlb_sizes[3] != 0)
+                return -EINVAL;
+        if (params.tlb_ways[2] != 0 || params.tlb_ways[3] != 0)
+                return -EINVAL;
+
+        if (!is_power_of_2(params.tlb_ways[0]))
+                return -EINVAL;
+
+        sets = params.tlb_sizes[0] >> ilog2(params.tlb_ways[0]);
+        if (!is_power_of_2(sets))
+                return -EINVAL;
+
+        array_len = params.tlb_sizes[0] + params.tlb_sizes[1];
+        array_len *= sizeof(struct kvm_book3e_206_tlb_entry);
+
+        if (cfg->array_len < array_len)
+                return -EINVAL;
+
+        num_pages = DIV_ROUND_UP(cfg->array + array_len - 1, PAGE_SIZE) -
+                    cfg->array / PAGE_SIZE;
+        pages = kmalloc(sizeof(struct page *) * num_pages, GFP_KERNEL);
+        if (!pages)
+                return -ENOMEM;
+
+        ret = get_user_pages_fast(cfg->array, num_pages, 1, pages);
+        if (ret < 0)
+                goto err_pages;
+
+        if (ret != num_pages) {
+                num_pages = ret;
+                ret = -EFAULT;
+                goto err_put_page;
+        }
+
+        virt = vmap(pages, num_pages, VM_MAP, PAGE_KERNEL);
+        if (!virt)
+                goto err_put_page;
+
+        privs[0] = kzalloc(sizeof(struct tlbe_priv) * params.tlb_sizes[0],
+                           GFP_KERNEL);
+        privs[1] = kzalloc(sizeof(struct tlbe_priv) * params.tlb_sizes[1],
+                           GFP_KERNEL);
+
+        if (!privs[0] || !privs[1])
+                goto err_put_page;
+
+        free_gtlb(vcpu_e500);
+
+        vcpu_e500->gtlb_priv[0] = privs[0];
+        vcpu_e500->gtlb_priv[1] = privs[1];
+
+        vcpu_e500->gtlb_arch = (struct kvm_book3e_206_tlb_entry *)
+                (virt + (cfg->array & (PAGE_SIZE - 1)));
+
+        vcpu_e500->gtlb_params[0].entries = params.tlb_sizes[0];
+        vcpu_e500->gtlb_params[1].entries = params.tlb_sizes[1];
+
+        vcpu_e500->gtlb_offset[0] = 0;
+        vcpu_e500->gtlb_offset[1] = params.tlb_sizes[0];
+
+        vcpu_e500->tlb0cfg &= ~(TLBnCFG_N_ENTRY | TLBnCFG_ASSOC);
+        if (params.tlb_sizes[0] <= 2048)
+                vcpu_e500->tlb0cfg |= params.tlb_sizes[0];
+        vcpu_e500->tlb0cfg |= params.tlb_ways[0] << TLBnCFG_ASSOC_SHIFT;
+
+        vcpu_e500->tlb1cfg &= ~(TLBnCFG_N_ENTRY | TLBnCFG_ASSOC);
+        vcpu_e500->tlb1cfg |= params.tlb_sizes[1];
+        vcpu_e500->tlb1cfg |= params.tlb_ways[1] << TLBnCFG_ASSOC_SHIFT;
+
+        vcpu_e500->shared_tlb_pages = pages;
+        vcpu_e500->num_shared_tlb_pages = num_pages;
+
+        vcpu_e500->gtlb_params[0].ways = params.tlb_ways[0];
+        vcpu_e500->gtlb_params[0].sets = sets;
+
+        vcpu_e500->gtlb_params[1].ways = params.tlb_sizes[1];
+        vcpu_e500->gtlb_params[1].sets = 1;
+
+        return 0;
+
+err_put_page:
+        kfree(privs[0]);
+        kfree(privs[1]);
+
+        for (i = 0; i < num_pages; i++)
+                put_page(pages[i]);
+
+err_pages:
+        kfree(pages);
+        return ret;
+}
+
+int kvm_vcpu_ioctl_dirty_tlb(struct kvm_vcpu *vcpu,
+                             struct kvm_dirty_tlb *dirty)
+{
+        struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
+
+        clear_tlb_refs(vcpu_e500);
+        return 0;
 }
 
 int kvmppc_e500_tlb_init(struct kvmppc_vcpu_e500 *vcpu_e500)
 {
-        tlb1_entry_num = mfspr(SPRN_TLB1CFG) & 0xFFF;
-
-        vcpu_e500->gtlb_size[0] = KVM_E500_TLB0_SIZE;
-        vcpu_e500->gtlb_arch[0] =
-                kzalloc(sizeof(struct tlbe) * KVM_E500_TLB0_SIZE, GFP_KERNEL);
-        if (vcpu_e500->gtlb_arch[0] == NULL)
-                goto err_out;
-
-        vcpu_e500->gtlb_size[1] = KVM_E500_TLB1_SIZE;
-        vcpu_e500->gtlb_arch[1] =
-                kzalloc(sizeof(struct tlbe) * KVM_E500_TLB1_SIZE, GFP_KERNEL);
-        if (vcpu_e500->gtlb_arch[1] == NULL)
-                goto err_out_guest0;
-
-        vcpu_e500->gtlb_priv[0] = (struct tlbe_priv *)
-                kzalloc(sizeof(struct tlbe_priv) * KVM_E500_TLB0_SIZE, GFP_KERNEL);
-        if (vcpu_e500->gtlb_priv[0] == NULL)
-                goto err_out_guest1;
-        vcpu_e500->gtlb_priv[1] = (struct tlbe_priv *)
-                kzalloc(sizeof(struct tlbe_priv) * KVM_E500_TLB1_SIZE, GFP_KERNEL);
-
-        if (vcpu_e500->gtlb_priv[1] == NULL)
-                goto err_out_priv0;
+        int entry_size = sizeof(struct kvm_book3e_206_tlb_entry);
+        int entries = KVM_E500_TLB0_SIZE + KVM_E500_TLB1_SIZE;
+
+        host_tlb_params[0].entries = mfspr(SPRN_TLB0CFG) & TLBnCFG_N_ENTRY;
+        host_tlb_params[1].entries = mfspr(SPRN_TLB1CFG) & TLBnCFG_N_ENTRY;
+
+        /*
+         * This should never happen on real e500 hardware, but is
+         * architecturally possible -- e.g. in some weird nested
+         * virtualization case.
+         */
+        if (host_tlb_params[0].entries == 0 ||
+            host_tlb_params[1].entries == 0) {
+                pr_err("%s: need to know host tlb size\n", __func__);
+                return -ENODEV;
+        }
+
+        host_tlb_params[0].ways = (mfspr(SPRN_TLB0CFG) & TLBnCFG_ASSOC) >>
+                                  TLBnCFG_ASSOC_SHIFT;
+        host_tlb_params[1].ways = host_tlb_params[1].entries;
+
+        if (!is_power_of_2(host_tlb_params[0].entries) ||
+            !is_power_of_2(host_tlb_params[0].ways) ||
+            host_tlb_params[0].entries < host_tlb_params[0].ways ||
+            host_tlb_params[0].ways == 0) {
+                pr_err("%s: bad tlb0 host config: %u entries %u ways\n",
+                       __func__, host_tlb_params[0].entries,
+                       host_tlb_params[0].ways);
+                return -ENODEV;
+        }
+
+        host_tlb_params[0].sets =
+                host_tlb_params[0].entries / host_tlb_params[0].ways;
+        host_tlb_params[1].sets = 1;
+
+        vcpu_e500->gtlb_params[0].entries = KVM_E500_TLB0_SIZE;
+        vcpu_e500->gtlb_params[1].entries = KVM_E500_TLB1_SIZE;
+
+        vcpu_e500->gtlb_params[0].ways = KVM_E500_TLB0_WAY_NUM;
+        vcpu_e500->gtlb_params[0].sets =
+                KVM_E500_TLB0_SIZE / KVM_E500_TLB0_WAY_NUM;
+
+        vcpu_e500->gtlb_params[1].ways = KVM_E500_TLB1_SIZE;
+        vcpu_e500->gtlb_params[1].sets = 1;
+
+        vcpu_e500->gtlb_arch = kmalloc(entries * entry_size, GFP_KERNEL);
+        if (!vcpu_e500->gtlb_arch)
+                return -ENOMEM;
+
+        vcpu_e500->gtlb_offset[0] = 0;
+        vcpu_e500->gtlb_offset[1] = KVM_E500_TLB0_SIZE;
+
+        vcpu_e500->tlb_refs[0] =
+                kzalloc(sizeof(struct tlbe_ref) * host_tlb_params[0].entries,
+                        GFP_KERNEL);
+        if (!vcpu_e500->tlb_refs[0])
+                goto err;
+
+        vcpu_e500->tlb_refs[1] =
+                kzalloc(sizeof(struct tlbe_ref) * host_tlb_params[1].entries,
+                        GFP_KERNEL);
+        if (!vcpu_e500->tlb_refs[1])
+                goto err;
+
+        vcpu_e500->gtlb_priv[0] = kzalloc(sizeof(struct tlbe_ref) *
+                                          vcpu_e500->gtlb_params[0].entries,
+                                          GFP_KERNEL);
+        if (!vcpu_e500->gtlb_priv[0])
+                goto err;
+
+        vcpu_e500->gtlb_priv[1] = kzalloc(sizeof(struct tlbe_ref) *
+                                          vcpu_e500->gtlb_params[1].entries,
+                                          GFP_KERNEL);
+        if (!vcpu_e500->gtlb_priv[1])
+                goto err;
 
         if (kvmppc_e500_id_table_alloc(vcpu_e500) == NULL)
-                goto err_out_priv1;
+                goto err;
 
         /* Init TLB configuration register */
-        vcpu_e500->tlb0cfg = mfspr(SPRN_TLB0CFG) & ~0xfffUL;
-        vcpu_e500->tlb0cfg |= vcpu_e500->gtlb_size[0];
-        vcpu_e500->tlb1cfg = mfspr(SPRN_TLB1CFG) & ~0xfffUL;
-        vcpu_e500->tlb1cfg |= vcpu_e500->gtlb_size[1];
+        vcpu_e500->tlb0cfg = mfspr(SPRN_TLB0CFG) &
+                             ~(TLBnCFG_N_ENTRY | TLBnCFG_ASSOC);
+        vcpu_e500->tlb0cfg |= vcpu_e500->gtlb_params[0].entries;
+        vcpu_e500->tlb0cfg |=
+                vcpu_e500->gtlb_params[0].ways << TLBnCFG_ASSOC_SHIFT;
+
+        vcpu_e500->tlb1cfg = mfspr(SPRN_TLB1CFG) &
+                             ~(TLBnCFG_N_ENTRY | TLBnCFG_ASSOC);
+        vcpu_e500->tlb0cfg |= vcpu_e500->gtlb_params[1].entries;
+        vcpu_e500->tlb0cfg |=
+                vcpu_e500->gtlb_params[1].ways << TLBnCFG_ASSOC_SHIFT;
 
         return 0;
 
-err_out_priv1:
-        kfree(vcpu_e500->gtlb_priv[1]);
-err_out_priv0:
-        kfree(vcpu_e500->gtlb_priv[0]);
-err_out_guest1:
-        kfree(vcpu_e500->gtlb_arch[1]);
-err_out_guest0:
-        kfree(vcpu_e500->gtlb_arch[0]);
-err_out:
+err:
+        free_gtlb(vcpu_e500);
+        kfree(vcpu_e500->tlb_refs[0]);
+        kfree(vcpu_e500->tlb_refs[1]);
         return -1;
 }
 
 void kvmppc_e500_tlb_uninit(struct kvmppc_vcpu_e500 *vcpu_e500)
 {
-        int stlbsel, i;
-
-        /* release all privs */
-        for (stlbsel = 0; stlbsel < 2; stlbsel++)
-                for (i = 0; i < vcpu_e500->gtlb_size[stlbsel]; i++) {
-                        struct tlbe_priv *priv =
-                                &vcpu_e500->gtlb_priv[stlbsel][i];
-                        kvmppc_e500_priv_release(priv);
-                }
-
+        free_gtlb(vcpu_e500);
         kvmppc_e500_id_table_free(vcpu_e500);
-        kfree(vcpu_e500->gtlb_arch[1]);
-        kfree(vcpu_e500->gtlb_arch[0]);
+
+        kfree(vcpu_e500->tlb_refs[0]);
+        kfree(vcpu_e500->tlb_refs[1]);
 }
diff --git a/arch/powerpc/kvm/e500_tlb.h b/arch/powerpc/kvm/e500_tlb.h
index 59b88e99a235..5c6d2d7bf058 100644
--- a/arch/powerpc/kvm/e500_tlb.h
+++ b/arch/powerpc/kvm/e500_tlb.h
@@ -20,13 +20,9 @@
 #include <asm/tlb.h>
 #include <asm/kvm_e500.h>
 
-#define KVM_E500_TLB0_WAY_SIZE_BIT      7       /* Fixed */
-#define KVM_E500_TLB0_WAY_SIZE          (1UL << KVM_E500_TLB0_WAY_SIZE_BIT)
-#define KVM_E500_TLB0_WAY_SIZE_MASK     (KVM_E500_TLB0_WAY_SIZE - 1)
-
-#define KVM_E500_TLB0_WAY_NUM_BIT       1       /* No greater than 7 */
-#define KVM_E500_TLB0_WAY_NUM           (1UL << KVM_E500_TLB0_WAY_NUM_BIT)
-#define KVM_E500_TLB0_WAY_NUM_MASK      (KVM_E500_TLB0_WAY_NUM - 1)
+/* This geometry is the legacy default -- can be overridden by userspace */
+#define KVM_E500_TLB0_WAY_SIZE          128
+#define KVM_E500_TLB0_WAY_NUM           2
 
 #define KVM_E500_TLB0_SIZE  (KVM_E500_TLB0_WAY_SIZE * KVM_E500_TLB0_WAY_NUM)
 #define KVM_E500_TLB1_SIZE  16
@@ -58,50 +54,54 @@ extern void kvmppc_e500_tlb_setup(struct kvmppc_vcpu_e500 *);
 extern void kvmppc_e500_recalc_shadow_pid(struct kvmppc_vcpu_e500 *);
 
 /* TLB helper functions */
-static inline unsigned int get_tlb_size(const struct tlbe *tlbe)
+static inline unsigned int
+get_tlb_size(const struct kvm_book3e_206_tlb_entry *tlbe)
 {
         return (tlbe->mas1 >> 7) & 0x1f;
 }
 
-static inline gva_t get_tlb_eaddr(const struct tlbe *tlbe)
+static inline gva_t get_tlb_eaddr(const struct kvm_book3e_206_tlb_entry *tlbe)
 {
         return tlbe->mas2 & 0xfffff000;
 }
 
-static inline u64 get_tlb_bytes(const struct tlbe *tlbe)
+static inline u64 get_tlb_bytes(const struct kvm_book3e_206_tlb_entry *tlbe)
 {
         unsigned int pgsize = get_tlb_size(tlbe);
         return 1ULL << 10 << pgsize;
 }
 
-static inline gva_t get_tlb_end(const struct tlbe *tlbe)
+static inline gva_t get_tlb_end(const struct kvm_book3e_206_tlb_entry *tlbe)
 {
         u64 bytes = get_tlb_bytes(tlbe);
         return get_tlb_eaddr(tlbe) + bytes - 1;
 }
 
-static inline u64 get_tlb_raddr(const struct tlbe *tlbe)
+static inline u64 get_tlb_raddr(const struct kvm_book3e_206_tlb_entry *tlbe)
 {
-        u64 rpn = tlbe->mas7;
-        return (rpn << 32) | (tlbe->mas3 & 0xfffff000);
+        return tlbe->mas7_3 & ~0xfffULL;
 }
 
-static inline unsigned int get_tlb_tid(const struct tlbe *tlbe)
+static inline unsigned int
+get_tlb_tid(const struct kvm_book3e_206_tlb_entry *tlbe)
 {
         return (tlbe->mas1 >> 16) & 0xff;
 }
 
-static inline unsigned int get_tlb_ts(const struct tlbe *tlbe)
+static inline unsigned int
+get_tlb_ts(const struct kvm_book3e_206_tlb_entry *tlbe)
 {
         return (tlbe->mas1 >> 12) & 0x1;
 }
 
-static inline unsigned int get_tlb_v(const struct tlbe *tlbe)
+static inline unsigned int
+get_tlb_v(const struct kvm_book3e_206_tlb_entry *tlbe)
 {
         return (tlbe->mas1 >> 31) & 0x1;
 }
 
-static inline unsigned int get_tlb_iprot(const struct tlbe *tlbe)
+static inline unsigned int
+get_tlb_iprot(const struct kvm_book3e_206_tlb_entry *tlbe)
 {
         return (tlbe->mas1 >> 30) & 0x1;
 }
@@ -121,59 +121,37 @@ static inline unsigned int get_cur_pr(struct kvm_vcpu *vcpu)
         return !!(vcpu->arch.shared->msr & MSR_PR);
 }
 
-static inline unsigned int get_cur_spid(
-                const struct kvmppc_vcpu_e500 *vcpu_e500)
+static inline unsigned int get_cur_spid(const struct kvm_vcpu *vcpu)
 {
-        return (vcpu_e500->mas6 >> 16) & 0xff;
+        return (vcpu->arch.shared->mas6 >> 16) & 0xff;
 }
 
-static inline unsigned int get_cur_sas(
-                const struct kvmppc_vcpu_e500 *vcpu_e500)
+static inline unsigned int get_cur_sas(const struct kvm_vcpu *vcpu)
 {
-        return vcpu_e500->mas6 & 0x1;
+        return vcpu->arch.shared->mas6 & 0x1;
 }
 
-static inline unsigned int get_tlb_tlbsel(
-                const struct kvmppc_vcpu_e500 *vcpu_e500)
+static inline unsigned int get_tlb_tlbsel(const struct kvm_vcpu *vcpu)
 {
         /*
          * Manual says that tlbsel has 2 bits wide.
          * Since we only have two TLBs, only lower bit is used.
          */
-        return (vcpu_e500->mas0 >> 28) & 0x1;
-}
-
-static inline unsigned int get_tlb_nv_bit(
-                const struct kvmppc_vcpu_e500 *vcpu_e500)
-{
-        return vcpu_e500->mas0 & 0xfff;
+        return (vcpu->arch.shared->mas0 >> 28) & 0x1;
 }
 
-static inline unsigned int get_tlb_esel_bit(
-                const struct kvmppc_vcpu_e500 *vcpu_e500)
+static inline unsigned int get_tlb_nv_bit(const struct kvm_vcpu *vcpu)
 {
-        return (vcpu_e500->mas0 >> 16) & 0xfff;
+        return vcpu->arch.shared->mas0 & 0xfff;
 }
 
-static inline unsigned int get_tlb_esel(
-                const struct kvmppc_vcpu_e500 *vcpu_e500,
-                int tlbsel)
+static inline unsigned int get_tlb_esel_bit(const struct kvm_vcpu *vcpu)
 {
-        unsigned int esel = get_tlb_esel_bit(vcpu_e500);
-
-        if (tlbsel == 0) {
-                esel &= KVM_E500_TLB0_WAY_NUM_MASK;
-                esel |= ((vcpu_e500->mas2 >> 12) & KVM_E500_TLB0_WAY_SIZE_MASK)
-                                << KVM_E500_TLB0_WAY_NUM_BIT;
-        } else {
-                esel &= KVM_E500_TLB1_SIZE - 1;
-        }
-
-        return esel;
+        return (vcpu->arch.shared->mas0 >> 16) & 0xfff;
 }
 
 static inline int tlbe_is_host_safe(const struct kvm_vcpu *vcpu,
-                        const struct tlbe *tlbe)
+                        const struct kvm_book3e_206_tlb_entry *tlbe)
 {
         gpa_t gpa;
 
diff --git a/arch/powerpc/kvm/emulate.c b/arch/powerpc/kvm/emulate.c
index 141dce3c6810..968f40101883 100644
--- a/arch/powerpc/kvm/emulate.c
+++ b/arch/powerpc/kvm/emulate.c
@@ -13,6 +13,7 @@
  * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
  *
  * Copyright IBM Corp. 2007
+ * Copyright 2011 Freescale Semiconductor, Inc.
  *
  * Authors: Hollis Blanchard <hollisb@us.ibm.com>
  */
@@ -69,54 +70,55 @@
 #define OP_STH  44
 #define OP_STHU 45
 
-#ifdef CONFIG_PPC_BOOK3S
-static int kvmppc_dec_enabled(struct kvm_vcpu *vcpu)
-{
-        return 1;
-}
-#else
-static int kvmppc_dec_enabled(struct kvm_vcpu *vcpu)
-{
-        return vcpu->arch.tcr & TCR_DIE;
-}
-#endif
-
 void kvmppc_emulate_dec(struct kvm_vcpu *vcpu)
 {
         unsigned long dec_nsec;
+        unsigned long long dec_time;
 
         pr_debug("mtDEC: %x\n", vcpu->arch.dec);
+        hrtimer_try_to_cancel(&vcpu->arch.dec_timer);
+
 #ifdef CONFIG_PPC_BOOK3S
         /* mtdec lowers the interrupt line when positive. */
         kvmppc_core_dequeue_dec(vcpu);
 
         /* POWER4+ triggers a dec interrupt if the value is < 0 */
         if (vcpu->arch.dec & 0x80000000) {
-                hrtimer_try_to_cancel(&vcpu->arch.dec_timer);
                 kvmppc_core_queue_dec(vcpu);
                 return;
         }
 #endif
-        if (kvmppc_dec_enabled(vcpu)) {
-                /* The decrementer ticks at the same rate as the timebase, so
-                 * that's how we convert the guest DEC value to the number of
-                 * host ticks. */
-
-                hrtimer_try_to_cancel(&vcpu->arch.dec_timer);
-                dec_nsec = vcpu->arch.dec;
-                dec_nsec *= 1000;
-                dec_nsec /= tb_ticks_per_usec;
-                hrtimer_start(&vcpu->arch.dec_timer, ktime_set(0, dec_nsec),
-                              HRTIMER_MODE_REL);
-                vcpu->arch.dec_jiffies = get_tb();
-        } else {
-                hrtimer_try_to_cancel(&vcpu->arch.dec_timer);
-        }
+
+#ifdef CONFIG_BOOKE
+        /* On BOOKE, DEC = 0 is as good as decrementer not enabled */
+        if (vcpu->arch.dec == 0)
+                return;
+#endif
+
+        /*
+         * The decrementer ticks at the same rate as the timebase, so
+         * that's how we convert the guest DEC value to the number of
+         * host ticks.
+         */
+
+        dec_time = vcpu->arch.dec;
+        dec_time *= 1000;
+        do_div(dec_time, tb_ticks_per_usec);
+        dec_nsec = do_div(dec_time, NSEC_PER_SEC);
+        hrtimer_start(&vcpu->arch.dec_timer,
+                ktime_set(dec_time, dec_nsec), HRTIMER_MODE_REL);
+        vcpu->arch.dec_jiffies = get_tb();
 }
 
 u32 kvmppc_get_dec(struct kvm_vcpu *vcpu, u64 tb)
 {
         u64 jd = tb - vcpu->arch.dec_jiffies;
+
+#ifdef CONFIG_BOOKE
+        if (vcpu->arch.dec < jd)
+                return 0;
+#endif
+
         return vcpu->arch.dec - jd;
 }
 
@@ -159,7 +161,8 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
         case OP_TRAP_64:
                 kvmppc_core_queue_program(vcpu, SRR1_PROGTRAP);
 #else
-                kvmppc_core_queue_program(vcpu, vcpu->arch.esr | ESR_PTR);
+                kvmppc_core_queue_program(vcpu,
+                                          vcpu->arch.shared->esr | ESR_PTR);
 #endif
                 advance = 0;
                 break;
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 607fbdf24b84..00d7e345b3fe 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -39,7 +39,8 @@
 int kvm_arch_vcpu_runnable(struct kvm_vcpu *v)
 {
         return !(v->arch.shared->msr & MSR_WE) ||
-               !!(v->arch.pending_exceptions);
+               !!(v->arch.pending_exceptions) ||
+               v->requests;
 }
 
 int kvmppc_kvm_pv(struct kvm_vcpu *vcpu)
@@ -66,7 +67,7 @@ int kvmppc_kvm_pv(struct kvm_vcpu *vcpu)
                 vcpu->arch.magic_page_pa = param1;
                 vcpu->arch.magic_page_ea = param2;
 
-                r2 = KVM_MAGIC_FEAT_SR;
+                r2 = KVM_MAGIC_FEAT_SR | KVM_MAGIC_FEAT_MAS0_TO_SPRG7;
 
                 r = HC_EV_SUCCESS;
                 break;
@@ -171,8 +172,11 @@ void kvm_arch_check_processor_compat(void *rtn)
         *(int *)rtn = kvmppc_core_check_processor_compat();
 }
 
-int kvm_arch_init_vm(struct kvm *kvm)
+int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 {
+        if (type)
+                return -EINVAL;
+
         return kvmppc_core_init_vm(kvm);
 }
 
@@ -208,17 +212,22 @@ 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:
         case KVM_CAP_ENABLE_CAP:
+        case KVM_CAP_ONE_REG:
                 r = 1;
                 break;
 #ifndef CONFIG_KVM_BOOK3S_64_HV
         case KVM_CAP_PPC_PAIRED_SINGLES:
         case KVM_CAP_PPC_OSI:
         case KVM_CAP_PPC_GET_PVINFO:
+#ifdef CONFIG_KVM_E500
+        case KVM_CAP_SW_TLB:
+#endif
                 r = 1;
                 break;
         case KVM_CAP_COALESCED_MMIO:
@@ -238,7 +247,26 @@ int kvm_dev_ioctl_check_extension(long ext)
                 if (cpu_has_feature(CPU_FTR_ARCH_201))
                         r = 2;
                 break;
+        case KVM_CAP_SYNC_MMU:
+                r = cpu_has_feature(CPU_FTR_ARCH_206) ? 1 : 0;
+                break;
 #endif
+        case KVM_CAP_NR_VCPUS:
+                /*
+                 * Recommending a number of CPUs is somewhat arbitrary; we
+                 * return the number of present CPUs for -HV (since a host
+                 * will have secondary threads "offline"), and for other KVM
+                 * implementations just count online CPUs.
+                 */
+#ifdef CONFIG_KVM_BOOK3S_64_HV
+                r = num_present_cpus();
+#else
+                r = num_online_cpus();
+#endif
+                break;
+        case KVM_CAP_MAX_VCPUS:
+                r = KVM_MAX_VCPUS;
+                break;
         default:
                 r = 0;
                 break;
@@ -253,6 +281,16 @@ long kvm_arch_dev_ioctl(struct file *filp,
         return -EINVAL;
 }
 
+void kvm_arch_free_memslot(struct kvm_memory_slot *free,
+                           struct kvm_memory_slot *dont)
+{
+}
+
+int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages)
+{
+        return 0;
+}
+
 int kvm_arch_prepare_memory_region(struct kvm *kvm,
                                    struct kvm_memory_slot *memslot,
                                    struct kvm_memory_slot old,
@@ -279,9 +317,10 @@ 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))
+        if (!IS_ERR(vcpu)) {
+                vcpu->arch.wqp = &vcpu->wq;
                 kvmppc_create_vcpu_debugfs(vcpu, id);
+        }
         return vcpu;
 }
 
@@ -305,18 +344,6 @@ int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
         return kvmppc_core_pending_dec(vcpu);
 }
 
-static void kvmppc_decrementer_func(unsigned long data)
-{
-        struct kvm_vcpu *vcpu = (struct kvm_vcpu *)data;
-
-        kvmppc_core_queue_dec(vcpu);
-
-        if (waitqueue_active(vcpu->arch.wqp)) {
-                wake_up_interruptible(vcpu->arch.wqp);
-                vcpu->stat.halt_wakeup++;
-        }
-}
-
 /*
  * low level hrtimer wake routine. Because this runs in hardirq context
  * we schedule a tasklet to do the real work.
@@ -431,20 +458,20 @@ static void kvmppc_complete_mmio_load(struct kvm_vcpu *vcpu,
 
         kvmppc_set_gpr(vcpu, vcpu->arch.io_gpr, gpr);
 
-        switch (vcpu->arch.io_gpr & KVM_REG_EXT_MASK) {
-        case KVM_REG_GPR:
+        switch (vcpu->arch.io_gpr & KVM_MMIO_REG_EXT_MASK) {
+        case KVM_MMIO_REG_GPR:
                 kvmppc_set_gpr(vcpu, vcpu->arch.io_gpr, gpr);
                 break;
-        case KVM_REG_FPR:
-                vcpu->arch.fpr[vcpu->arch.io_gpr & KVM_REG_MASK] = gpr;
+        case KVM_MMIO_REG_FPR:
+                vcpu->arch.fpr[vcpu->arch.io_gpr & KVM_MMIO_REG_MASK] = gpr;
                 break;
 #ifdef CONFIG_PPC_BOOK3S
-        case KVM_REG_QPR:
-                vcpu->arch.qpr[vcpu->arch.io_gpr & KVM_REG_MASK] = gpr;
+        case KVM_MMIO_REG_QPR:
+                vcpu->arch.qpr[vcpu->arch.io_gpr & KVM_MMIO_REG_MASK] = gpr;
                 break;
-        case KVM_REG_FQPR:
-                vcpu->arch.fpr[vcpu->arch.io_gpr & KVM_REG_MASK] = gpr;
-                vcpu->arch.qpr[vcpu->arch.io_gpr & KVM_REG_MASK] = gpr;
+        case KVM_MMIO_REG_FQPR:
+                vcpu->arch.fpr[vcpu->arch.io_gpr & KVM_MMIO_REG_MASK] = gpr;
+                vcpu->arch.qpr[vcpu->arch.io_gpr & KVM_MMIO_REG_MASK] = gpr;
                 break;
 #endif
         default:
@@ -553,8 +580,6 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
                 vcpu->arch.hcall_needed = 0;
         }
 
-        kvmppc_core_deliver_interrupts(vcpu);
-
         r = kvmppc_vcpu_run(run, vcpu);
 
         if (vcpu->sigset_active)
@@ -563,6 +588,21 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
         return r;
 }
 
+void kvm_vcpu_kick(struct kvm_vcpu *vcpu)
+{
+        int me;
+        int cpu = vcpu->cpu;
+
+        me = get_cpu();
+        if (waitqueue_active(vcpu->arch.wqp)) {
+                wake_up_interruptible(vcpu->arch.wqp);
+                vcpu->stat.halt_wakeup++;
+        } else if (cpu != me && cpu != -1) {
+                smp_send_reschedule(vcpu->cpu);
+        }
+        put_cpu();
+}
+
 int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu, struct kvm_interrupt *irq)
 {
         if (irq->irq == KVM_INTERRUPT_UNSET) {
@@ -571,13 +611,7 @@ int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu, struct kvm_interrupt *irq)
         }
 
         kvmppc_core_queue_external(vcpu, irq);
-
-        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);
-        }
+        kvm_vcpu_kick(vcpu);
 
         return 0;
 }
@@ -599,6 +633,19 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
                 r = 0;
                 vcpu->arch.papr_enabled = true;
                 break;
+#ifdef CONFIG_KVM_E500
+        case KVM_CAP_SW_TLB: {
+                struct kvm_config_tlb cfg;
+                void __user *user_ptr = (void __user *)(uintptr_t)cap->args[0];
+
+                r = -EFAULT;
+                if (copy_from_user(&cfg, user_ptr, sizeof(cfg)))
+                        break;
+
+                r = kvm_vcpu_ioctl_config_tlb(vcpu, &cfg);
+                break;
+        }
+#endif
         default:
                 r = -EINVAL;
                 break;
@@ -648,6 +695,32 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
                 r = kvm_vcpu_ioctl_enable_cap(vcpu, &cap);
                 break;
         }
+
+        case KVM_SET_ONE_REG:
+        case KVM_GET_ONE_REG:
+        {
+                struct kvm_one_reg reg;
+                r = -EFAULT;
+                if (copy_from_user(&reg, argp, sizeof(reg)))
+                        goto out;
+                if (ioctl == KVM_SET_ONE_REG)
+                        r = kvm_vcpu_ioctl_set_one_reg(vcpu, &reg);
+                else
+                        r = kvm_vcpu_ioctl_get_one_reg(vcpu, &reg);
+                break;
+        }
+
+#ifdef CONFIG_KVM_E500
+        case KVM_DIRTY_TLB: {
+                struct kvm_dirty_tlb dirty;
+                r = -EFAULT;
+                if (copy_from_user(&dirty, argp, sizeof(dirty)))
+                        goto out;
+                r = kvm_vcpu_ioctl_dirty_tlb(vcpu, &dirty);
+                break;
+        }
+#endif
+
         default:
                 r = -EINVAL;
         }
@@ -656,6 +729,11 @@ out:
         return r;
 }
 
+int kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf)
+{
+        return VM_FAULT_SIGBUS;
+}
+
 static int kvm_vm_ioctl_get_pvinfo(struct kvm_ppc_pvinfo *pvinfo)
 {
         u32 inst_lis = 0x3c000000;
diff --git a/arch/powerpc/kvm/trace.h b/arch/powerpc/kvm/trace.h
index b135d3d397db..877186b7b1c3 100644
--- a/arch/powerpc/kvm/trace.h
+++ b/arch/powerpc/kvm/trace.h
@@ -118,11 +118,14 @@ TRACE_EVENT(kvm_book3s_exit,
         ),
 
         TP_fast_assign(
+                struct kvmppc_book3s_shadow_vcpu *svcpu;
                 __entry->exit_nr        = exit_nr;
                 __entry->pc             = kvmppc_get_pc(vcpu);
                 __entry->dar            = kvmppc_get_fault_dar(vcpu);
                 __entry->msr            = vcpu->arch.shared->msr;
-                __entry->srr1           = to_svcpu(vcpu)->shadow_srr1;
+                svcpu = svcpu_get(vcpu);
+                __entry->srr1           = svcpu->shadow_srr1;
+                svcpu_put(svcpu);
         ),
 
         TP_printk("exit=0x%x | pc=0x%lx | msr=0x%lx | dar=0x%lx | srr1=0x%lx",
@@ -337,6 +340,63 @@ TRACE_EVENT(kvm_book3s_slbmte,
 
 #endif /* CONFIG_PPC_BOOK3S */
 
+
+/*************************************************************************
+ *                         Book3E trace points                           *
+ *************************************************************************/
+
+#ifdef CONFIG_BOOKE
+
+TRACE_EVENT(kvm_booke206_stlb_write,
+        TP_PROTO(__u32 mas0, __u32 mas8, __u32 mas1, __u64 mas2, __u64 mas7_3),
+        TP_ARGS(mas0, mas8, mas1, mas2, mas7_3),
+
+        TP_STRUCT__entry(
+                __field(        __u32,  mas0            )
+                __field(        __u32,  mas8            )
+                __field(        __u32,  mas1            )
+                __field(        __u64,  mas2            )
+                __field(        __u64,  mas7_3          )
+        ),
+
+        TP_fast_assign(
+                __entry->mas0           = mas0;
+                __entry->mas8           = mas8;
+                __entry->mas1           = mas1;
+                __entry->mas2           = mas2;
+                __entry->mas7_3         = mas7_3;
+        ),
+
+        TP_printk("mas0=%x mas8=%x mas1=%x mas2=%llx mas7_3=%llx",
+                __entry->mas0, __entry->mas8, __entry->mas1,
+                __entry->mas2, __entry->mas7_3)
+);
+
+TRACE_EVENT(kvm_booke206_gtlb_write,
+        TP_PROTO(__u32 mas0, __u32 mas1, __u64 mas2, __u64 mas7_3),
+        TP_ARGS(mas0, mas1, mas2, mas7_3),
+
+        TP_STRUCT__entry(
+                __field(        __u32,  mas0            )
+                __field(        __u32,  mas1            )
+                __field(        __u64,  mas2            )
+                __field(        __u64,  mas7_3          )
+        ),
+
+        TP_fast_assign(
+                __entry->mas0           = mas0;
+                __entry->mas1           = mas1;
+                __entry->mas2           = mas2;
+                __entry->mas7_3         = mas7_3;
+        ),
+
+        TP_printk("mas0=%x mas1=%x mas2=%llx mas7_3=%llx",
+                __entry->mas0, __entry->mas1,
+                __entry->mas2, __entry->mas7_3)
+);
+
+#endif
+
 #endif /* _TRACE_KVM_H */
 
 /* This part must be outside protection */
diff --git a/arch/powerpc/lib/locks.c b/arch/powerpc/lib/locks.c
index a6ebba56fdd4..bb7cfecf2788 100644
--- a/arch/powerpc/lib/locks.c
+++ b/arch/powerpc/lib/locks.c
@@ -19,11 +19,9 @@
 #include <linux/smp.h>
 
 /* waiting for a spinlock... */
-#if defined(CONFIG_PPC_SPLPAR) || defined(CONFIG_PPC_ISERIES)
+#if defined(CONFIG_PPC_SPLPAR)
 #include <asm/hvcall.h>
-#include <asm/iseries/hv_call.h>
 #include <asm/smp.h>
-#include <asm/firmware.h>
 
 void __spin_yield(arch_spinlock_t *lock)
 {
@@ -40,14 +38,8 @@ void __spin_yield(arch_spinlock_t *lock)
         rmb();
         if (lock->slock != lock_value)
                 return;         /* something has changed */
-        if (firmware_has_feature(FW_FEATURE_ISERIES))
-                HvCall2(HvCallBaseYieldProcessor, HvCall_YieldToProc,
-                        ((u64)holder_cpu << 32) | yield_count);
-#ifdef CONFIG_PPC_SPLPAR
-        else
-                plpar_hcall_norets(H_CONFER,
-                        get_hard_smp_processor_id(holder_cpu), yield_count);
-#endif
+        plpar_hcall_norets(H_CONFER,
+                get_hard_smp_processor_id(holder_cpu), yield_count);
 }
 
 /*
@@ -71,14 +63,8 @@ void __rw_yield(arch_rwlock_t *rw)
         rmb();
         if (rw->lock != lock_value)
                 return;         /* something has changed */
-        if (firmware_has_feature(FW_FEATURE_ISERIES))
-                HvCall2(HvCallBaseYieldProcessor, HvCall_YieldToProc,
-                        ((u64)holder_cpu << 32) | yield_count);
-#ifdef CONFIG_PPC_SPLPAR
-        else
-                plpar_hcall_norets(H_CONFER,
-                        get_hard_smp_processor_id(holder_cpu), yield_count);
-#endif
+        plpar_hcall_norets(H_CONFER,
+                get_hard_smp_processor_id(holder_cpu), yield_count);
 }
 #endif
 
diff --git a/arch/powerpc/mm/dma-noncoherent.c b/arch/powerpc/mm/dma-noncoherent.c
index 329be36c0a8d..6747eece84af 100644
--- a/arch/powerpc/mm/dma-noncoherent.c
+++ b/arch/powerpc/mm/dma-noncoherent.c
@@ -365,12 +365,11 @@ static inline void __dma_sync_page_highmem(struct page *page,
         local_irq_save(flags);
 
         do {
-                start = (unsigned long)kmap_atomic(page + seg_nr,
-                                KM_PPC_SYNC_PAGE) + seg_offset;
+                start = (unsigned long)kmap_atomic(page + seg_nr) + seg_offset;
 
                 /* Sync this buffer segment */
                 __dma_sync((void *)start, seg_size, direction);
-                kunmap_atomic((void *)start, KM_PPC_SYNC_PAGE);
+                kunmap_atomic((void *)start);
                 seg_nr++;
 
                 /* Calculate next buffer segment size */
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index 2f0d1b032a89..19f2f9498b27 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -105,6 +105,82 @@ static int store_updates_sp(struct pt_regs *regs)
         }
         return 0;
 }
+/*
+ * do_page_fault error handling helpers
+ */
+
+#define MM_FAULT_RETURN         0
+#define MM_FAULT_CONTINUE       -1
+#define MM_FAULT_ERR(sig)       (sig)
+
+static int out_of_memory(struct pt_regs *regs)
+{
+        /*
+         * We ran out of memory, or some other thing happened to us that made
+         * us unable to handle the page fault gracefully.
+         */
+        up_read(&current->mm->mmap_sem);
+        if (!user_mode(regs))
+                return MM_FAULT_ERR(SIGKILL);
+        pagefault_out_of_memory();
+        return MM_FAULT_RETURN;
+}
+
+static int do_sigbus(struct pt_regs *regs, unsigned long address)
+{
+        siginfo_t info;
+
+        up_read(&current->mm->mmap_sem);
+
+        if (user_mode(regs)) {
+                info.si_signo = SIGBUS;
+                info.si_errno = 0;
+                info.si_code = BUS_ADRERR;
+                info.si_addr = (void __user *)address;
+                force_sig_info(SIGBUS, &info, current);
+                return MM_FAULT_RETURN;
+        }
+        return MM_FAULT_ERR(SIGBUS);
+}
+
+static int mm_fault_error(struct pt_regs *regs, unsigned long addr, int fault)
+{
+        /*
+         * Pagefault was interrupted by SIGKILL. We have no reason to
+         * continue the pagefault.
+         */
+        if (fatal_signal_pending(current)) {
+                /*
+                 * If we have retry set, the mmap semaphore will have
+                 * alrady been released in __lock_page_or_retry(). Else
+                 * we release it now.
+                 */
+                if (!(fault & VM_FAULT_RETRY))
+                        up_read(&current->mm->mmap_sem);
+                /* Coming from kernel, we need to deal with uaccess fixups */
+                if (user_mode(regs))
+                        return MM_FAULT_RETURN;
+                return MM_FAULT_ERR(SIGKILL);
+        }
+
+        /* No fault: be happy */
+        if (!(fault & VM_FAULT_ERROR))
+                return MM_FAULT_CONTINUE;
+
+        /* Out of memory */
+        if (fault & VM_FAULT_OOM)
+                return out_of_memory(regs);
+
+        /* Bus error. x86 handles HWPOISON here, we'll add this if/when
+         * we support the feature in HW
+         */
+        if (fault & VM_FAULT_SIGBUS)
+                return do_sigbus(regs, addr);
+
+        /* We don't understand the fault code, this is fatal */
+        BUG();
+        return MM_FAULT_CONTINUE;
+}
 
 /*
  * For 600- and 800-family processors, the error_code parameter is DSISR
@@ -124,11 +200,12 @@ int __kprobes do_page_fault(struct pt_regs *regs, unsigned long address,
 {
         struct vm_area_struct * vma;
         struct mm_struct *mm = current->mm;
-        siginfo_t info;
+        unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
         int code = SEGV_MAPERR;
-        int is_write = 0, ret;
+        int is_write = 0;
         int trap = TRAP(regs);
         int is_exec = trap == 0x400;
+        int fault;
 
 #if !(defined(CONFIG_4xx) || defined(CONFIG_BOOKE))
         /*
@@ -145,6 +222,9 @@ int __kprobes do_page_fault(struct pt_regs *regs, unsigned long address,
         is_write = error_code & ESR_DST;
 #endif /* CONFIG_4xx || CONFIG_BOOKE */
 
+        if (is_write)
+                flags |= FAULT_FLAG_WRITE;
+
 #ifdef CONFIG_PPC_ICSWX
         /*
          * we need to do this early because this "data storage
@@ -152,13 +232,11 @@ int __kprobes do_page_fault(struct pt_regs *regs, unsigned long address,
          * look at it
          */
         if (error_code & ICSWX_DSI_UCT) {
-                int ret;
-
-                ret = acop_handle_fault(regs, address, error_code);
-                if (ret)
-                        return ret;
+                int rc = acop_handle_fault(regs, address, error_code);
+                if (rc)
+                        return rc;
         }
-#endif
+#endif /* CONFIG_PPC_ICSWX */
 
         if (notify_page_fault(regs))
                 return 0;
@@ -179,6 +257,10 @@ int __kprobes do_page_fault(struct pt_regs *regs, unsigned long address,
         }
 #endif
 
+        /* We restore the interrupt state now */
+        if (!arch_irq_disabled_regs(regs))
+                local_irq_enable();
+
         if (in_atomic() || mm == NULL) {
                 if (!user_mode(regs))
                         return SIGSEGV;
@@ -212,7 +294,15 @@ int __kprobes do_page_fault(struct pt_regs *regs, unsigned long address,
                 if (!user_mode(regs) && !search_exception_tables(regs->nip))
                         goto bad_area_nosemaphore;
 
+retry:
                 down_read(&mm->mmap_sem);
+        } else {
+                /*
+                 * The above down_read_trylock() might have succeeded in
+                 * which case we'll have missed the might_sleep() from
+                 * down_read():
+                 */
+                might_sleep();
         }
 
         vma = find_vma(mm, address);
@@ -327,30 +417,43 @@ good_area:
          * make sure we exit gracefully rather than endlessly redo
          * the fault.
          */
-        ret = handle_mm_fault(mm, vma, address, is_write ? FAULT_FLAG_WRITE : 0);
-        if (unlikely(ret & VM_FAULT_ERROR)) {
-                if (ret & VM_FAULT_OOM)
-                        goto out_of_memory;
-                else if (ret & VM_FAULT_SIGBUS)
-                        goto do_sigbus;
-                BUG();
+        fault = handle_mm_fault(mm, vma, address, flags);
+        if (unlikely(fault & (VM_FAULT_RETRY|VM_FAULT_ERROR))) {
+                int rc = mm_fault_error(regs, address, fault);
+                if (rc >= MM_FAULT_RETURN)
+                        return rc;
         }
-        if (ret & VM_FAULT_MAJOR) {
-                current->maj_flt++;
-                perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1,
-                                     regs, address);
+
+        /*
+         * Major/minor page fault accounting is only done on the
+         * initial attempt. If we go through a retry, it is extremely
+         * likely that the page will be found in page cache at that point.
+         */
+        if (flags & FAULT_FLAG_ALLOW_RETRY) {
+                if (fault & VM_FAULT_MAJOR) {
+                        current->maj_flt++;
+                        perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1,
+                                      regs, address);
 #ifdef CONFIG_PPC_SMLPAR
-                if (firmware_has_feature(FW_FEATURE_CMO)) {
-                        preempt_disable();
-                        get_lppaca()->page_ins += (1 << PAGE_FACTOR);
-                        preempt_enable();
+                        if (firmware_has_feature(FW_FEATURE_CMO)) {
+                                preempt_disable();
+                                get_lppaca()->page_ins += (1 << PAGE_FACTOR);
+                                preempt_enable();
+                        }
+#endif /* CONFIG_PPC_SMLPAR */
+                } else {
+                        current->min_flt++;
+                        perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1,
+                                      regs, address);
+                }
+                if (fault & VM_FAULT_RETRY) {
+                        /* Clear FAULT_FLAG_ALLOW_RETRY to avoid any risk
+                         * of starvation. */
+                        flags &= ~FAULT_FLAG_ALLOW_RETRY;
+                        goto retry;
                 }
-#endif
-        } else {
-                current->min_flt++;
-                perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1,
-                                     regs, address);
         }
+
         up_read(&mm->mmap_sem);
         return 0;
 
@@ -371,28 +474,6 @@ bad_area_nosemaphore:
 
         return SIGSEGV;
 
-/*
- * We ran out of memory, or some other thing happened to us that made
- * us unable to handle the page fault gracefully.
- */
-out_of_memory:
-        up_read(&mm->mmap_sem);
-        if (!user_mode(regs))
-                return SIGKILL;
-        pagefault_out_of_memory();
-        return 0;
-
-do_sigbus:
-        up_read(&mm->mmap_sem);
-        if (user_mode(regs)) {
-                info.si_signo = SIGBUS;
-                info.si_errno = 0;
-                info.si_code = BUS_ADRERR;
-                info.si_addr = (void __user *)address;
-                force_sig_info(SIGBUS, &info, current);
-                return 0;
-        }
-        return SIGBUS;
 }
 
 /*
diff --git a/arch/powerpc/mm/fsl_booke_mmu.c b/arch/powerpc/mm/fsl_booke_mmu.c
index 66a6fd38e9cd..07ba45b0f07c 100644
--- a/arch/powerpc/mm/fsl_booke_mmu.c
+++ b/arch/powerpc/mm/fsl_booke_mmu.c
@@ -149,12 +149,19 @@ static void settlbcam(int index, unsigned long virt, phys_addr_t phys,
 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;
+        unsigned int camsize = __ilog2(ram);
+        unsigned int align = __ffs(virt | phys);
+        unsigned long max_cam;
+
+        if ((mfspr(SPRN_MMUCFG) & MMUCFG_MAVN) == MMUCFG_MAVN_V1) {
+                /* Convert (4^max) kB to (2^max) bytes */
+                max_cam = ((mfspr(SPRN_TLB1CFG) >> 16) & 0xf) * 2 + 10;
+                camsize &= ~1U;
+                align &= ~1U;
+        } else {
+                /* Convert (2^max) kB to (2^max) bytes */
+                max_cam = __ilog2(mfspr(SPRN_TLB1PS)) + 10;
+        }
 
         if (camsize > align)
                 camsize = align;
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index 2d282186cb45..3e8c37a4e395 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -55,6 +55,8 @@
 #include <asm/spu.h>
 #include <asm/udbg.h>
 #include <asm/code-patching.h>
+#include <asm/fadump.h>
+#include <asm/firmware.h>
 
 #ifdef DEBUG
 #define DBG(fmt...) udbg_printf(fmt)
@@ -625,6 +627,16 @@ static void __init htab_initialize(void)
                 /* Using a hypervisor which owns the htab */
                 htab_address = NULL;
                 _SDR1 = 0; 
+#ifdef CONFIG_FA_DUMP
+                /*
+                 * If firmware assisted dump is active firmware preserves
+                 * the contents of htab along with entire partition memory.
+                 * Clear the htab if firmware assisted dump is active so
+                 * that we dont end up using old mappings.
+                 */
+                if (is_fadump_active() && ppc_md.hpte_clear_all)
+                        ppc_md.hpte_clear_all();
+#endif
         } else {
                 /* Find storage for the HPT.  Must be contiguous in
                  * the absolute address space. On cell we want it to be
@@ -745,12 +757,9 @@ void __init early_init_mmu(void)
          */
         htab_initialize();
 
-        /* Initialize stab / SLB management except on iSeries
-         */
+        /* Initialize stab / SLB management */
         if (mmu_has_feature(MMU_FTR_SLB))
                 slb_initialize();
-        else if (!firmware_has_feature(FW_FEATURE_ISERIES))
-                stab_initialize(get_paca()->stab_real);
 }
 
 #ifdef CONFIG_SMP
@@ -761,8 +770,7 @@ void __cpuinit early_init_mmu_secondary(void)
                 mtspr(SPRN_SDR1, _SDR1);
 
         /* Initialize STAB/SLB. We use a virtual address as it works
-         * in real mode on pSeries and we want a virtual address on
-         * iSeries anyway
+         * in real mode on pSeries.
          */
         if (mmu_has_feature(MMU_FTR_SLB))
                 slb_initialize();
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index a8b3cc7d90fe..fb05b123218f 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -12,6 +12,7 @@
 #include <linux/io.h>
 #include <linux/slab.h>
 #include <linux/hugetlb.h>
+#include <linux/export.h>
 #include <linux/of_fdt.h>
 #include <linux/memblock.h>
 #include <linux/bootmem.h>
@@ -103,6 +104,7 @@ pte_t *find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea, unsigned *shift
                 *shift = hugepd_shift(*hpdp);
         return hugepte_offset(hpdp, ea, pdshift);
 }
+EXPORT_SYMBOL_GPL(find_linux_pte_or_hugepte);
 
 pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
 {
@@ -310,7 +312,8 @@ void __init reserve_hugetlb_gpages(void)
         int i;
 
         strlcpy(cmdline, boot_command_line, COMMAND_LINE_SIZE);
-        parse_args("hugetlb gpages", cmdline, NULL, 0, &do_gpage_early_setup);
+        parse_args("hugetlb gpages", cmdline, NULL, 0, 0, 0,
+                        &do_gpage_early_setup);
 
         /*
          * Walk gpage list in reverse, allocating larger page sizes first.
@@ -910,9 +913,9 @@ void flush_dcache_icache_hugepage(struct page *page)
                 if (!PageHighMem(page)) {
                         __flush_dcache_icache(page_address(page+i));
                 } else {
-                        start = kmap_atomic(page+i, KM_PPC_SYNC_ICACHE);
+                        start = kmap_atomic(page+i);
                         __flush_dcache_icache(start);
-                        kunmap_atomic(start, KM_PPC_SYNC_ICACHE);
+                        kunmap_atomic(start);
                 }
         }
 }
diff --git a/arch/powerpc/mm/icswx.c b/arch/powerpc/mm/icswx.c
index 5d9a59eaad93..8cdbd8634a58 100644
--- a/arch/powerpc/mm/icswx.c
+++ b/arch/powerpc/mm/icswx.c
@@ -163,7 +163,7 @@ EXPORT_SYMBOL_GPL(drop_cop);
 
 static int acop_use_cop(int ct)
 {
-        /* todo */
+        /* There is no alternate policy, yet */
         return -1;
 }
 
@@ -227,11 +227,30 @@ int acop_handle_fault(struct pt_regs *regs, unsigned long address,
                 ct = (ccw >> 16) & 0x3f;
         }
 
+        /*
+         * We could be here because another thread has enabled acop
+         * but the ACOP register has yet to be updated.
+         *
+         * This should have been taken care of by the IPI to sync all
+         * the threads (see smp_call_function(sync_cop, mm, 1)), but
+         * that could take forever if there are a significant amount
+         * of threads.
+         *
+         * Given the number of threads on some of these systems,
+         * perhaps this is the best way to sync ACOP rather than whack
+         * every thread with an IPI.
+         */
+        if ((acop_copro_type_bit(ct) & current->active_mm->context.acop) != 0) {
+                sync_cop(current->active_mm);
+                return 0;
+        }
+
+        /* check for alternate policy */
         if (!acop_use_cop(ct))
                 return 0;
 
         /* at this point the CT is unknown to the system */
-        pr_warn("%s[%d]: Coprocessor %d is unavailable",
+        pr_warn("%s[%d]: Coprocessor %d is unavailable\n",
                 current->comm, current->pid, ct);
 
         /* get inst if we don't already have it */
diff --git a/arch/powerpc/mm/icswx.h b/arch/powerpc/mm/icswx.h
index 42176bd0884c..6dedc08e62c8 100644
--- a/arch/powerpc/mm/icswx.h
+++ b/arch/powerpc/mm/icswx.h
@@ -59,4 +59,10 @@ extern void free_cop_pid(int free_pid);
 
 extern int acop_handle_fault(struct pt_regs *regs, unsigned long address,
                              unsigned long error_code);
+
+static inline u64 acop_copro_type_bit(unsigned int type)
+{
+        return 1ULL << (63 - type);
+}
+
 #endif /* !_ARCH_POWERPC_MM_ICSWX_H_ */
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index d974b79a3068..baaafde7d135 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -458,9 +458,9 @@ void flush_dcache_icache_page(struct page *page)
 #endif
 #ifdef CONFIG_BOOKE
         {
-                void *start = kmap_atomic(page, KM_PPC_SYNC_ICACHE);
+                void *start = kmap_atomic(page);
                 __flush_dcache_icache(start);
-                kunmap_atomic(start, KM_PPC_SYNC_ICACHE);
+                kunmap_atomic(start);
         }
 #elif defined(CONFIG_8xx) || defined(CONFIG_PPC64)
         /* On 8xx there is no need to kmap since highmem is not supported */
diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c
index 51f87956f8f8..0907f92ce309 100644
--- a/arch/powerpc/mm/pgtable_32.c
+++ b/arch/powerpc/mm/pgtable_32.c
@@ -207,7 +207,7 @@ __ioremap_caller(phys_addr_t addr, unsigned long size, unsigned long flags,
          */
         if (mem_init_done && (p < virt_to_phys(high_memory)) &&
             !(__allow_ioremap_reserved && memblock_is_region_reserved(p, size))) {
-                printk("__ioremap(): phys addr 0x%llx is RAM lr %p\n",
+                printk("__ioremap(): phys addr 0x%llx is RAM lr %pf\n",
                        (unsigned long long)p, __builtin_return_address(0));
                 return NULL;
         }
diff --git a/arch/powerpc/mm/slb.c b/arch/powerpc/mm/slb.c
index e22276cb67a4..a538c80db2df 100644
--- a/arch/powerpc/mm/slb.c
+++ b/arch/powerpc/mm/slb.c
@@ -21,7 +21,6 @@
 #include <asm/cputable.h>
 #include <asm/cacheflush.h>
 #include <asm/smp.h>
-#include <asm/firmware.h>
 #include <linux/compiler.h>
 #include <asm/udbg.h>
 #include <asm/code-patching.h>
@@ -307,11 +306,6 @@ void slb_initialize(void)
 
         get_paca()->stab_rr = SLB_NUM_BOLTED;
 
-        /* On iSeries the bolted entries have already been set up by
-         * the hypervisor from the lparMap data in head.S */
-        if (firmware_has_feature(FW_FEATURE_ISERIES))
-                return;
-
         lflags = SLB_VSID_KERNEL | linear_llp;
         vflags = SLB_VSID_KERNEL | vmalloc_llp;
 
diff --git a/arch/powerpc/mm/slb_low.S b/arch/powerpc/mm/slb_low.S
index ef653dc95b65..b9ee79ce2200 100644
--- a/arch/powerpc/mm/slb_low.S
+++ b/arch/powerpc/mm/slb_low.S
@@ -217,21 +217,6 @@ slb_finish_load:
          * free slot first but that took too long. Unfortunately we
          * dont have any LRU information to help us choose a slot.
          */
-#ifdef CONFIG_PPC_ISERIES
-BEGIN_FW_FTR_SECTION
-        /*
-         * On iSeries, the "bolted" stack segment can be cast out on
-         * shared processor switch so we need to check for a miss on
-         * it and restore it to the right slot.
-         */
-        ld      r9,PACAKSAVE(r13)
-        clrrdi  r9,r9,28
-        clrrdi  r3,r3,28
-        li      r10,SLB_NUM_BOLTED-1    /* Stack goes in last bolted slot */
-        cmpld   r9,r3
-        beq     3f
-END_FW_FTR_SECTION_IFSET(FW_FEATURE_ISERIES)
-#endif /* CONFIG_PPC_ISERIES */
 
 7:      ld      r10,PACASTABRR(r13)
         addi    r10,r10,1
@@ -282,7 +267,6 @@ _GLOBAL(slb_compare_rr_to_size)
 
 /*
  * Finish loading of a 1T SLB entry (for the kernel linear mapping) and return.
- * We assume legacy iSeries will never have 1T segments.
  *
  * r3 = EA, r10 = proto-VSID, r11 = flags, clobbers r9
  */
diff --git a/arch/powerpc/mm/stab.c b/arch/powerpc/mm/stab.c
index 41e31642a86a..9106ebb118f5 100644
--- a/arch/powerpc/mm/stab.c
+++ b/arch/powerpc/mm/stab.c
@@ -21,8 +21,6 @@
 #include <asm/cputable.h>
 #include <asm/prom.h>
 #include <asm/abs_addr.h>
-#include <asm/firmware.h>
-#include <asm/iseries/hv_call.h>
 
 struct stab_entry {
         unsigned long esid_data;
@@ -285,12 +283,5 @@ void stab_initialize(unsigned long stab)
         /* Set ASR */
         stabreal = get_paca()->stab_real | 0x1ul;
 
-#ifdef CONFIG_PPC_ISERIES
-        if (firmware_has_feature(FW_FEATURE_ISERIES)) {
-                HvCall1(HvCallBaseSetASR, stabreal);
-                return;
-        }
-#endif /* CONFIG_PPC_ISERIES */
-
         mtspr(SPRN_ASR, stabreal);
 }
diff --git a/arch/powerpc/oprofile/common.c b/arch/powerpc/oprofile/common.c
index d65e68f3cb25..6f01624f317f 100644
--- a/arch/powerpc/oprofile/common.c
+++ b/arch/powerpc/oprofile/common.c
@@ -195,9 +195,6 @@ int __init oprofile_arch_init(struct oprofile_operations *ops)
         if (!cur_cpu_spec->oprofile_cpu_type)
                 return -ENODEV;
 
-        if (firmware_has_feature(FW_FEATURE_ISERIES))
-                return -ENODEV;
-
         switch (cur_cpu_spec->oprofile_type) {
 #ifdef CONFIG_PPC_BOOK3S_64
 #ifdef CONFIG_OPROFILE_CELL
diff --git a/arch/powerpc/perf/Makefile b/arch/powerpc/perf/Makefile
new file mode 100644
index 000000000000..af3fac23768c
--- /dev/null
+++ b/arch/powerpc/perf/Makefile
@@ -0,0 +1,14 @@
+subdir-ccflags-$(CONFIG_PPC_WERROR) := -Werror
+
+obj-$(CONFIG_PERF_EVENTS)       += callchain.o
+
+obj-$(CONFIG_PPC_PERF_CTRS)     += core-book3s.o
+obj64-$(CONFIG_PPC_PERF_CTRS)   += power4-pmu.o ppc970-pmu.o power5-pmu.o \
+                                   power5+-pmu.o power6-pmu.o power7-pmu.o
+obj32-$(CONFIG_PPC_PERF_CTRS)   += mpc7450-pmu.o
+
+obj-$(CONFIG_FSL_EMB_PERF_EVENT) += core-fsl-emb.o
+obj-$(CONFIG_FSL_EMB_PERF_EVENT_E500) += e500-pmu.o
+
+obj-$(CONFIG_PPC64)             += $(obj64-y)
+obj-$(CONFIG_PPC32)             += $(obj32-y)
diff --git a/arch/powerpc/kernel/perf_callchain.c b/arch/powerpc/perf/callchain.c
index 564c1d8bdb5c..e8a18d1cc7c9 100644
--- a/arch/powerpc/kernel/perf_callchain.c
+++ b/arch/powerpc/perf/callchain.c
@@ -20,7 +20,7 @@
 #include <asm/ucontext.h>
 #include <asm/vdso.h>
 #ifdef CONFIG_PPC64
-#include "ppc32.h"
+#include "../kernel/ppc32.h"
 #endif
 
 
diff --git a/arch/powerpc/kernel/perf_event.c b/arch/powerpc/perf/core-book3s.c
index 10a140f82cb8..02aee03e713c 100644
--- a/arch/powerpc/kernel/perf_event.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -116,14 +116,45 @@ static inline void perf_get_data_addr(struct pt_regs *regs, u64 *addrp)
                 *addrp = mfspr(SPRN_SDAR);
 }
 
+static inline u32 perf_flags_from_msr(struct pt_regs *regs)
+{
+        if (regs->msr & MSR_PR)
+                return PERF_RECORD_MISC_USER;
+        if ((regs->msr & MSR_HV) && freeze_events_kernel != MMCR0_FCHV)
+                return PERF_RECORD_MISC_HYPERVISOR;
+        return PERF_RECORD_MISC_KERNEL;
+}
+
 static inline u32 perf_get_misc_flags(struct pt_regs *regs)
 {
         unsigned long mmcra = regs->dsisr;
         unsigned long sihv = MMCRA_SIHV;
         unsigned long sipr = MMCRA_SIPR;
 
+        /* Not a PMU interrupt: Make up flags from regs->msr */
         if (TRAP(regs) != 0xf00)
-                return 0;       /* not a PMU interrupt */
+                return perf_flags_from_msr(regs);
+
+        /*
+         * If we don't support continuous sampling and this
+         * is not a marked event, same deal
+         */
+        if ((ppmu->flags & PPMU_NO_CONT_SAMPLING) &&
+            !(mmcra & MMCRA_SAMPLE_ENABLE))
+                return perf_flags_from_msr(regs);
+
+        /*
+         * If we don't have flags in MMCRA, rather than using
+         * the MSR, we intuit the flags from the address in
+         * SIAR which should give slightly more reliable
+         * results
+         */
+        if (ppmu->flags & PPMU_NO_SIPR) {
+                unsigned long siar = mfspr(SPRN_SIAR);
+                if (siar >= PAGE_OFFSET)
+                        return PERF_RECORD_MISC_KERNEL;
+                return PERF_RECORD_MISC_USER;
+        }
 
         if (ppmu->flags & PPMU_ALT_SIPR) {
                 sihv = POWER6_MMCRA_SIHV;
@@ -865,6 +896,7 @@ static void power_pmu_start(struct perf_event *event, int ef_flags)
 {
         unsigned long flags;
         s64 left;
+        unsigned long val;
 
         if (!event->hw.idx || !event->hw.sample_period)
                 return;
@@ -880,7 +912,12 @@ static void power_pmu_start(struct perf_event *event, int ef_flags)
 
         event->hw.state = 0;
         left = local64_read(&event->hw.period_left);
-        write_pmc(event->hw.idx, left);
+
+        val = 0;
+        if (left < 0x80000000L)
+                val = 0x80000000L - left;
+
+        write_pmc(event->hw.idx, val);
 
         perf_event_update_userpage(event);
         perf_pmu_enable(event->pmu);
@@ -1078,6 +1115,10 @@ static int power_pmu_event_init(struct perf_event *event)
         if (!ppmu)
                 return -ENOENT;
 
+        /* does not support taken branch sampling */
+        if (has_branch_stack(event))
+                return -EOPNOTSUPP;
+
         switch (event->attr.type) {
         case PERF_TYPE_HARDWARE:
                 ev = event->attr.config;
@@ -1187,6 +1228,11 @@ static int power_pmu_event_init(struct perf_event *event)
         return err;
 }
 
+static int power_pmu_event_idx(struct perf_event *event)
+{
+        return event->hw.idx;
+}
+
 struct pmu power_pmu = {
         .pmu_enable     = power_pmu_enable,
         .pmu_disable    = power_pmu_disable,
@@ -1199,6 +1245,7 @@ struct pmu power_pmu = {
         .start_txn      = power_pmu_start_txn,
         .cancel_txn     = power_pmu_cancel_txn,
         .commit_txn     = power_pmu_commit_txn,
+        .event_idx      = power_pmu_event_idx,
 };
 
 /*
@@ -1283,13 +1330,18 @@ unsigned long perf_misc_flags(struct pt_regs *regs)
  */
 unsigned long perf_instruction_pointer(struct pt_regs *regs)
 {
-        unsigned long ip;
+        unsigned long mmcra = regs->dsisr;
 
+        /* Not a PMU interrupt */
         if (TRAP(regs) != 0xf00)
-                return regs->nip;       /* not a PMU interrupt */
+                return regs->nip;
+
+        /* Processor doesn't support sampling non marked events */
+        if ((ppmu->flags & PPMU_NO_CONT_SAMPLING) &&
+            !(mmcra & MMCRA_SAMPLE_ENABLE))
+                return regs->nip;
 
-        ip = mfspr(SPRN_SIAR) + perf_ip_adjust(regs);
-        return ip;
+        return mfspr(SPRN_SIAR) + perf_ip_adjust(regs);
 }
 
 static bool pmc_overflow(unsigned long val)
diff --git a/arch/powerpc/kernel/perf_event_fsl_emb.c b/arch/powerpc/perf/core-fsl-emb.c
index 0a6d2a9d569c..0a6d2a9d569c 100644
--- a/arch/powerpc/kernel/perf_event_fsl_emb.c
+++ b/arch/powerpc/perf/core-fsl-emb.c
diff --git a/arch/powerpc/kernel/e500-pmu.c b/arch/powerpc/perf/e500-pmu.c
index cb2e2949c8d1..cb2e2949c8d1 100644
--- a/arch/powerpc/kernel/e500-pmu.c
+++ b/arch/powerpc/perf/e500-pmu.c
diff --git a/arch/powerpc/kernel/mpc7450-pmu.c b/arch/powerpc/perf/mpc7450-pmu.c
index fe21b515ca44..fe21b515ca44 100644
--- a/arch/powerpc/kernel/mpc7450-pmu.c
+++ b/arch/powerpc/perf/mpc7450-pmu.c
diff --git a/arch/powerpc/kernel/power4-pmu.c b/arch/powerpc/perf/power4-pmu.c
index b4f1dda4d089..9103a1de864d 100644
--- a/arch/powerpc/kernel/power4-pmu.c
+++ b/arch/powerpc/perf/power4-pmu.c
@@ -607,6 +607,7 @@ static struct power_pmu power4_pmu = {
         .n_generic              = ARRAY_SIZE(p4_generic_events),
         .generic_events         = p4_generic_events,
         .cache_events           = &power4_cache_events,
+        .flags                  = PPMU_NO_SIPR | PPMU_NO_CONT_SAMPLING,
 };
 
 static int __init init_power4_pmu(void)
diff --git a/arch/powerpc/kernel/power5+-pmu.c b/arch/powerpc/perf/power5+-pmu.c
index a8757baa28f3..a8757baa28f3 100644
--- a/arch/powerpc/kernel/power5+-pmu.c
+++ b/arch/powerpc/perf/power5+-pmu.c
diff --git a/arch/powerpc/kernel/power5-pmu.c b/arch/powerpc/perf/power5-pmu.c
index e7f06eb7a861..e7f06eb7a861 100644
--- a/arch/powerpc/kernel/power5-pmu.c
+++ b/arch/powerpc/perf/power5-pmu.c
diff --git a/arch/powerpc/kernel/power6-pmu.c b/arch/powerpc/perf/power6-pmu.c
index 0bbc901e7efc..31128e086fed 100644
--- a/arch/powerpc/kernel/power6-pmu.c
+++ b/arch/powerpc/perf/power6-pmu.c
@@ -131,7 +131,7 @@ static u32 marked_bus_events[16] = {
         0x00000022,     /* BFP set 2: byte 0 bits 1, 5 */
         0, 0
 };
-        
+
 /*
  * Returns 1 if event counts things relating to marked instructions
  * and thus needs the MMCRA_SAMPLE_ENABLE bit set, or 0 if not.
diff --git a/arch/powerpc/kernel/power7-pmu.c b/arch/powerpc/perf/power7-pmu.c
index 1251e4d7e262..1251e4d7e262 100644
--- a/arch/powerpc/kernel/power7-pmu.c
+++ b/arch/powerpc/perf/power7-pmu.c
diff --git a/arch/powerpc/kernel/ppc970-pmu.c b/arch/powerpc/perf/ppc970-pmu.c
index 8c2190206964..20139ceeacf6 100644
--- a/arch/powerpc/kernel/ppc970-pmu.c
+++ b/arch/powerpc/perf/ppc970-pmu.c
@@ -252,7 +252,7 @@ static int p970_get_alternatives(u64 event, unsigned int flags, u64 alt[])
                 alt[1] = event ^ 0x1000;
                 return 2;
         }
-                
+
         return 1;
 }
 
@@ -487,6 +487,7 @@ static struct power_pmu ppc970_pmu = {
         .n_generic              = ARRAY_SIZE(ppc970_generic_events),
         .generic_events         = ppc970_generic_events,
         .cache_events           = &ppc970_cache_events,
+        .flags                  = PPMU_NO_SIPR | PPMU_NO_CONT_SAMPLING,
 };
 
 static int __init init_ppc970_pmu(void)
diff --git a/arch/powerpc/platforms/44x/Kconfig b/arch/powerpc/platforms/44x/Kconfig
index fcf6bf2ceee9..2e4e64abfab4 100644
--- a/arch/powerpc/platforms/44x/Kconfig
+++ b/arch/powerpc/platforms/44x/Kconfig
@@ -23,6 +23,7 @@ config BLUESTONE
         default n
         select PPC44x_SIMPLE
         select APM821xx
+        select PPC4xx_PCI_EXPRESS
         select IBM_EMAC_RGMII
         help
           This option enables support for the APM APM821xx Evaluation board.
diff --git a/arch/powerpc/platforms/44x/currituck.c b/arch/powerpc/platforms/44x/currituck.c
index 3f6229b5dee0..583e67fee37e 100644
--- a/arch/powerpc/platforms/44x/currituck.c
+++ b/arch/powerpc/platforms/44x/currituck.c
@@ -83,7 +83,7 @@ static void __init ppc47x_init_irq(void)
                  * device-tree, just pass 0 to all arguments
                  */
                 struct mpic *mpic =
-                        mpic_alloc(np, 0, 0, 0, 0, " MPIC     ");
+                        mpic_alloc(np, 0, MPIC_NO_RESET, 0, 0, " MPIC     ");
                 BUG_ON(mpic == NULL);
                 mpic_init(mpic);
                 ppc_md.get_irq = mpic_get_irq;
diff --git a/arch/powerpc/platforms/44x/iss4xx.c b/arch/powerpc/platforms/44x/iss4xx.c
index 5b8cdbb82f80..a28a8629727e 100644
--- a/arch/powerpc/platforms/44x/iss4xx.c
+++ b/arch/powerpc/platforms/44x/iss4xx.c
@@ -71,8 +71,7 @@ static void __init iss4xx_init_irq(void)
                 /* The MPIC driver will get everything it needs from the
                  * device-tree, just pass 0 to all arguments
                  */
-                struct mpic *mpic = mpic_alloc(np, 0, 0, 0, 0,
-                                               " MPIC     ");
+                struct mpic *mpic = mpic_alloc(np, 0, MPIC_NO_RESET, 0, 0, " MPIC     ");
                 BUG_ON(mpic == NULL);
                 mpic_init(mpic);
                 ppc_md.get_irq = mpic_get_irq;
diff --git a/arch/powerpc/platforms/44x/ppc44x_simple.c b/arch/powerpc/platforms/44x/ppc44x_simple.c
index 8d2202763415..3ffb915446e3 100644
--- a/arch/powerpc/platforms/44x/ppc44x_simple.c
+++ b/arch/powerpc/platforms/44x/ppc44x_simple.c
@@ -52,7 +52,7 @@ machine_device_initcall(ppc44x_simple, ppc44x_device_probe);
 static char *board[] __initdata = {
         "amcc,arches",
         "amcc,bamboo",
-        "amcc,bluestone",
+        "apm,bluestone",
         "amcc,glacier",
         "ibm,ebony",
         "amcc,eiger",
diff --git a/arch/powerpc/platforms/512x/mpc5121_ads_cpld.c b/arch/powerpc/platforms/512x/mpc5121_ads_cpld.c
index 9f09319352c0..ca3a062ed1b9 100644
--- a/arch/powerpc/platforms/512x/mpc5121_ads_cpld.c
+++ b/arch/powerpc/platforms/512x/mpc5121_ads_cpld.c
@@ -21,7 +21,7 @@
 #include <asm/prom.h>
 
 static struct device_node *cpld_pic_node;
-static struct irq_host *cpld_pic_host;
+static struct irq_domain *cpld_pic_host;
 
 /*
  * Bits to ignore in the misc_status register
@@ -123,13 +123,13 @@ cpld_pic_cascade(unsigned int irq, struct irq_desc *desc)
 }
 
 static int
-cpld_pic_host_match(struct irq_host *h, struct device_node *node)
+cpld_pic_host_match(struct irq_domain *h, struct device_node *node)
 {
         return cpld_pic_node == node;
 }
 
 static int
-cpld_pic_host_map(struct irq_host *h, unsigned int virq,
+cpld_pic_host_map(struct irq_domain *h, unsigned int virq,
                              irq_hw_number_t hw)
 {
         irq_set_status_flags(virq, IRQ_LEVEL);
@@ -137,8 +137,7 @@ cpld_pic_host_map(struct irq_host *h, unsigned int virq,
         return 0;
 }
 
-static struct
-irq_host_ops cpld_pic_host_ops = {
+static const struct irq_domain_ops cpld_pic_host_ops = {
         .match = cpld_pic_host_match,
         .map = cpld_pic_host_map,
 };
@@ -191,8 +190,7 @@ mpc5121_ads_cpld_pic_init(void)
 
         cpld_pic_node = of_node_get(np);
 
-        cpld_pic_host =
-            irq_alloc_host(np, IRQ_HOST_MAP_LINEAR, 16, &cpld_pic_host_ops, 16);
+        cpld_pic_host = irq_domain_add_linear(np, 16, &cpld_pic_host_ops, NULL);
         if (!cpld_pic_host) {
                 printk(KERN_ERR "CPLD PIC: failed to allocate irq host!\n");
                 goto end;
diff --git a/arch/powerpc/platforms/52xx/media5200.c b/arch/powerpc/platforms/52xx/media5200.c
index 96f85e5e0cd3..17d91b7da315 100644
--- a/arch/powerpc/platforms/52xx/media5200.c
+++ b/arch/powerpc/platforms/52xx/media5200.c
@@ -45,7 +45,7 @@ static struct of_device_id mpc5200_gpio_ids[] __initdata = {
 struct media5200_irq {
         void __iomem *regs;
         spinlock_t lock;
-        struct irq_host *irqhost;
+        struct irq_domain *irqhost;
 };
 struct media5200_irq media5200_irq;
 
@@ -112,7 +112,7 @@ void media5200_irq_cascade(unsigned int virq, struct irq_desc *desc)
         raw_spin_unlock(&desc->lock);
 }
 
-static int media5200_irq_map(struct irq_host *h, unsigned int virq,
+static int media5200_irq_map(struct irq_domain *h, unsigned int virq,
                              irq_hw_number_t hw)
 {
         pr_debug("%s: h=%p, virq=%i, hwirq=%i\n", __func__, h, virq, (int)hw);
@@ -122,7 +122,7 @@ static int media5200_irq_map(struct irq_host *h, unsigned int virq,
         return 0;
 }
 
-static int media5200_irq_xlate(struct irq_host *h, struct device_node *ct,
+static int media5200_irq_xlate(struct irq_domain *h, struct device_node *ct,
                                  const u32 *intspec, unsigned int intsize,
                                  irq_hw_number_t *out_hwirq,
                                  unsigned int *out_flags)
@@ -136,7 +136,7 @@ static int media5200_irq_xlate(struct irq_host *h, struct device_node *ct,
         return 0;
 }
 
-static struct irq_host_ops media5200_irq_ops = {
+static const struct irq_domain_ops media5200_irq_ops = {
         .map = media5200_irq_map,
         .xlate = media5200_irq_xlate,
 };
@@ -173,15 +173,12 @@ static void __init media5200_init_irq(void)
 
         spin_lock_init(&media5200_irq.lock);
 
-        media5200_irq.irqhost = irq_alloc_host(fpga_np, IRQ_HOST_MAP_LINEAR,
-                                               MEDIA5200_NUM_IRQS,
-                                               &media5200_irq_ops, -1);
+        media5200_irq.irqhost = irq_domain_add_linear(fpga_np,
+                        MEDIA5200_NUM_IRQS, &media5200_irq_ops, &media5200_irq);
         if (!media5200_irq.irqhost)
                 goto out;
         pr_debug("%s: allocated irqhost\n", __func__);
 
-        media5200_irq.irqhost->host_data = &media5200_irq;
-
         irq_set_handler_data(cascade_virq, &media5200_irq);
         irq_set_chained_handler(cascade_virq, media5200_irq_cascade);
 
diff --git a/arch/powerpc/platforms/52xx/mpc5200_simple.c b/arch/powerpc/platforms/52xx/mpc5200_simple.c
index 846b789fb195..c0aa04068d69 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 = {
+        "anonymous,a4m072",
         "anon,charon",
         "intercontrol,digsy-mtc",
         "manroland,mucmc52",
diff --git a/arch/powerpc/platforms/52xx/mpc52xx_common.c b/arch/powerpc/platforms/52xx/mpc52xx_common.c
index 369fd5457a3f..d7e94f49532a 100644
--- a/arch/powerpc/platforms/52xx/mpc52xx_common.c
+++ b/arch/powerpc/platforms/52xx/mpc52xx_common.c
@@ -98,13 +98,11 @@ struct mpc52xx_gpio_wkup __iomem *wkup_gpio;
  *                                      of the localplus bus to the of_platform
  *                                      bus.
  */
-void __init
-mpc52xx_declare_of_platform_devices(void)
+void __init mpc52xx_declare_of_platform_devices(void)
 {
-        /* Find every child of the SOC node and add it to of_platform */
-        if (of_platform_bus_probe(NULL, mpc52xx_bus_ids, NULL))
-                printk(KERN_ERR __FILE__ ": "
-                        "Error while probing of_platform bus\n");
+        /* Find all the 'platform' devices and register them. */
+        if (of_platform_populate(NULL, mpc52xx_bus_ids, NULL, NULL))
+                pr_err(__FILE__ ": Error while populating devices from DT\n");
 }
 
 /*
diff --git a/arch/powerpc/platforms/52xx/mpc52xx_gpt.c b/arch/powerpc/platforms/52xx/mpc52xx_gpt.c
index f94f06e52762..028470b95886 100644
--- a/arch/powerpc/platforms/52xx/mpc52xx_gpt.c
+++ b/arch/powerpc/platforms/52xx/mpc52xx_gpt.c
@@ -81,7 +81,7 @@ MODULE_LICENSE("GPL");
  * @regs: virtual address of GPT registers
  * @lock: spinlock to coordinate between different functions.
  * @gc: gpio_chip instance structure; used when GPIO is enabled
- * @irqhost: Pointer to irq_host instance; used when IRQ mode is supported
+ * @irqhost: Pointer to irq_domain instance; used when IRQ mode is supported
  * @wdt_mode: only relevant for gpt0: bit 0 (MPC52xx_GPT_CAN_WDT) indicates
  *   if the gpt may be used as wdt, bit 1 (MPC52xx_GPT_IS_WDT) indicates
  *   if the timer is actively used as wdt which blocks gpt functions
@@ -91,7 +91,7 @@ struct mpc52xx_gpt_priv {
         struct device *dev;
         struct mpc52xx_gpt __iomem *regs;
         spinlock_t lock;
-        struct irq_host *irqhost;
+        struct irq_domain *irqhost;
         u32 ipb_freq;
         u8 wdt_mode;
 
@@ -204,7 +204,7 @@ void mpc52xx_gpt_irq_cascade(unsigned int virq, struct irq_desc *desc)
         }
 }
 
-static int mpc52xx_gpt_irq_map(struct irq_host *h, unsigned int virq,
+static int mpc52xx_gpt_irq_map(struct irq_domain *h, unsigned int virq,
                                irq_hw_number_t hw)
 {
         struct mpc52xx_gpt_priv *gpt = h->host_data;
@@ -216,7 +216,7 @@ static int mpc52xx_gpt_irq_map(struct irq_host *h, unsigned int virq,
         return 0;
 }
 
-static int mpc52xx_gpt_irq_xlate(struct irq_host *h, struct device_node *ct,
+static int mpc52xx_gpt_irq_xlate(struct irq_domain *h, struct device_node *ct,
                                  const u32 *intspec, unsigned int intsize,
                                  irq_hw_number_t *out_hwirq,
                                  unsigned int *out_flags)
@@ -236,7 +236,7 @@ static int mpc52xx_gpt_irq_xlate(struct irq_host *h, struct device_node *ct,
         return 0;
 }
 
-static struct irq_host_ops mpc52xx_gpt_irq_ops = {
+static const struct irq_domain_ops mpc52xx_gpt_irq_ops = {
         .map = mpc52xx_gpt_irq_map,
         .xlate = mpc52xx_gpt_irq_xlate,
 };
@@ -252,14 +252,12 @@ mpc52xx_gpt_irq_setup(struct mpc52xx_gpt_priv *gpt, struct device_node *node)
         if (!cascade_virq)
                 return;
 
-        gpt->irqhost = irq_alloc_host(node, IRQ_HOST_MAP_LINEAR, 1,
-                                      &mpc52xx_gpt_irq_ops, -1);
+        gpt->irqhost = irq_domain_add_linear(node, 1, &mpc52xx_gpt_irq_ops, gpt);
         if (!gpt->irqhost) {
-                dev_err(gpt->dev, "irq_alloc_host() failed\n");
+                dev_err(gpt->dev, "irq_domain_add_linear() failed\n");
                 return;
         }
 
-        gpt->irqhost->host_data = gpt;
         irq_set_handler_data(cascade_virq, gpt);
         irq_set_chained_handler(cascade_virq, mpc52xx_gpt_irq_cascade);
 
diff --git a/arch/powerpc/platforms/52xx/mpc52xx_pic.c b/arch/powerpc/platforms/52xx/mpc52xx_pic.c
index 1a9a49570579..8520b58a5e9a 100644
--- a/arch/powerpc/platforms/52xx/mpc52xx_pic.c
+++ b/arch/powerpc/platforms/52xx/mpc52xx_pic.c
@@ -132,7 +132,7 @@ static struct of_device_id mpc52xx_sdma_ids[] __initdata = {
 
 static struct mpc52xx_intr __iomem *intr;
 static struct mpc52xx_sdma __iomem *sdma;
-static struct irq_host *mpc52xx_irqhost = NULL;
+static struct irq_domain *mpc52xx_irqhost = NULL;
 
 static unsigned char mpc52xx_map_senses[4] = {
         IRQ_TYPE_LEVEL_HIGH,
@@ -301,7 +301,7 @@ static int mpc52xx_is_extirq(int l1, int l2)
 /**
  * mpc52xx_irqhost_xlate - translate virq# from device tree interrupts property
  */
-static int mpc52xx_irqhost_xlate(struct irq_host *h, struct device_node *ct,
+static int mpc52xx_irqhost_xlate(struct irq_domain *h, struct device_node *ct,
                                  const u32 *intspec, unsigned int intsize,
                                  irq_hw_number_t *out_hwirq,
                                  unsigned int *out_flags)
@@ -335,7 +335,7 @@ static int mpc52xx_irqhost_xlate(struct irq_host *h, struct device_node *ct,
 /**
  * mpc52xx_irqhost_map - Hook to map from virq to an irq_chip structure
  */
-static int mpc52xx_irqhost_map(struct irq_host *h, unsigned int virq,
+static int mpc52xx_irqhost_map(struct irq_domain *h, unsigned int virq,
                                irq_hw_number_t irq)
 {
         int l1irq;
@@ -384,7 +384,7 @@ static int mpc52xx_irqhost_map(struct irq_host *h, unsigned int virq,
         return 0;
 }
 
-static struct irq_host_ops mpc52xx_irqhost_ops = {
+static const struct irq_domain_ops mpc52xx_irqhost_ops = {
         .xlate = mpc52xx_irqhost_xlate,
         .map = mpc52xx_irqhost_map,
 };
@@ -444,9 +444,9 @@ void __init mpc52xx_init_irq(void)
          * As last step, add an irq host to translate the real
          * hw irq information provided by the ofw to linux virq
          */
-        mpc52xx_irqhost = irq_alloc_host(picnode, IRQ_HOST_MAP_LINEAR,
+        mpc52xx_irqhost = irq_domain_add_linear(picnode,
                                          MPC52xx_IRQ_HIGHTESTHWIRQ,
-                                         &mpc52xx_irqhost_ops, -1);
+                                         &mpc52xx_irqhost_ops, NULL);
 
         if (!mpc52xx_irqhost)
                 panic(__FILE__ ": Cannot allocate the IRQ host\n");
diff --git a/arch/powerpc/platforms/82xx/pq2ads-pci-pic.c b/arch/powerpc/platforms/82xx/pq2ads-pci-pic.c
index 8ccf9ed62fe2..328d221fd1c0 100644
--- a/arch/powerpc/platforms/82xx/pq2ads-pci-pic.c
+++ b/arch/powerpc/platforms/82xx/pq2ads-pci-pic.c
@@ -29,7 +29,7 @@ static DEFINE_RAW_SPINLOCK(pci_pic_lock);
 
 struct pq2ads_pci_pic {
         struct device_node *node;
-        struct irq_host *host;
+        struct irq_domain *host;
 
         struct {
                 u32 stat;
@@ -103,7 +103,7 @@ static void pq2ads_pci_irq_demux(unsigned int irq, struct irq_desc *desc)
         }
 }
 
-static int pci_pic_host_map(struct irq_host *h, unsigned int virq,
+static int pci_pic_host_map(struct irq_domain *h, unsigned int virq,
                             irq_hw_number_t hw)
 {
         irq_set_status_flags(virq, IRQ_LEVEL);
@@ -112,14 +112,14 @@ static int pci_pic_host_map(struct irq_host *h, unsigned int virq,
         return 0;
 }
 
-static struct irq_host_ops pci_pic_host_ops = {
+static const struct irq_domain_ops pci_pic_host_ops = {
         .map = pci_pic_host_map,
 };
 
 int __init pq2ads_pci_init_irq(void)
 {
         struct pq2ads_pci_pic *priv;
-        struct irq_host *host;
+        struct irq_domain *host;
         struct device_node *np;
         int ret = -ENODEV;
         int irq;
@@ -156,17 +156,13 @@ int __init pq2ads_pci_init_irq(void)
         out_be32(&priv->regs->mask, ~0);
         mb();
 
-        host = irq_alloc_host(np, IRQ_HOST_MAP_LINEAR, NUM_IRQS,
-                              &pci_pic_host_ops, NUM_IRQS);
+        host = irq_domain_add_linear(np, NUM_IRQS, &pci_pic_host_ops, priv);
         if (!host) {
                 ret = -ENOMEM;
                 goto out_unmap_regs;
         }
 
-        host->host_data = priv;
-
         priv->host = host;
-        host->host_data = priv;
         irq_set_handler_data(irq, priv);
         irq_set_chained_handler(irq, pq2ads_pci_irq_demux);
 
diff --git a/arch/powerpc/platforms/85xx/Kconfig b/arch/powerpc/platforms/85xx/Kconfig
index d7946be298b6..f000d81c4e31 100644
--- a/arch/powerpc/platforms/85xx/Kconfig
+++ b/arch/powerpc/platforms/85xx/Kconfig
@@ -6,6 +6,7 @@ menuconfig FSL_SOC_BOOKE
         select MPIC
         select PPC_PCI_CHOICE
         select FSL_PCI if PCI
+        select SERIAL_8250_EXTENDED if SERIAL_8250
         select SERIAL_8250_SHARE_IRQ if SERIAL_8250
         default y
 
@@ -13,6 +14,15 @@ if FSL_SOC_BOOKE
 
 if PPC32
 
+config FSL_85XX_CACHE_SRAM
+        bool
+        select PPC_LIB_RHEAP
+        help
+          When selected, this option enables cache-sram support
+          for memory allocation on P1/P2 QorIQ platforms.
+          cache-sram-size and cache-sram-offset kernel boot
+          parameters should be passed when this option is enabled.
+
 config MPC8540_ADS
         bool "Freescale MPC8540 ADS"
         select DEFAULT_UIMAGE
@@ -30,6 +40,7 @@ config MPC85xx_CDS
         bool "Freescale MPC85xx CDS"
         select DEFAULT_UIMAGE
         select PPC_I8259
+        select HAS_RAPIDIO
         help
           This option enables support for the MPC85xx CDS board
 
@@ -80,7 +91,6 @@ config P1010_RDB
 config P1022_DS
         bool "Freescale P1022 DS"
         select DEFAULT_UIMAGE
-        select PHYS_64BIT       # The DTS has 36-bit addresses
         select SWIOTLB
         help
           This option enables support for the Freescale P1022DS reference board.
@@ -171,6 +181,21 @@ config SBC8560
         help
           This option enables support for the Wind River SBC8560 board
 
+config GE_IMP3A
+        bool "GE Intelligent Platforms IMP3A"
+        select DEFAULT_UIMAGE
+        select SWIOTLB
+        select MMIO_NVRAM
+        select GENERIC_GPIO
+        select ARCH_REQUIRE_GPIOLIB
+        select GE_FPGA
+        help
+          This option enables support for the GE Intelligent Platforms IMP3A
+          board.
+
+          This board is a 3U CompactPCI Single Board Computer with a Freescale
+          P2020 processor.
+
 config P2041_RDB
         bool "Freescale P2041 RDB"
         select DEFAULT_UIMAGE
diff --git a/arch/powerpc/platforms/85xx/Makefile b/arch/powerpc/platforms/85xx/Makefile
index 9cb2d4320dcc..2125d4ca068a 100644
--- a/arch/powerpc/platforms/85xx/Makefile
+++ b/arch/powerpc/platforms/85xx/Makefile
@@ -27,3 +27,4 @@ obj-$(CONFIG_SBC8548)     += sbc8548.o
 obj-$(CONFIG_SOCRATES)    += socrates.o socrates_fpga_pic.o
 obj-$(CONFIG_KSI8560)     += ksi8560.o
 obj-$(CONFIG_XES_MPC85xx) += xes_mpc85xx.o
+obj-$(CONFIG_GE_IMP3A)    += ge_imp3a.o
diff --git a/arch/powerpc/platforms/85xx/corenet_ds.c b/arch/powerpc/platforms/85xx/corenet_ds.c
index 07e3e6c47371..df69e99e511c 100644
--- a/arch/powerpc/platforms/85xx/corenet_ds.c
+++ b/arch/powerpc/platforms/85xx/corenet_ds.c
@@ -36,8 +36,8 @@
 void __init corenet_ds_pic_init(void)
 {
         struct mpic *mpic;
-        unsigned int flags = MPIC_BIG_ENDIAN |
-                                MPIC_BROKEN_FRR_NIRQS | MPIC_SINGLE_DEST_CPU;
+        unsigned int flags = MPIC_BIG_ENDIAN | MPIC_SINGLE_DEST_CPU |
+                MPIC_NO_RESET;
 
         if (ppc_md.get_irq == mpic_get_coreint_irq)
                 flags |= MPIC_ENABLE_COREINT;
diff --git a/arch/powerpc/platforms/85xx/ge_imp3a.c b/arch/powerpc/platforms/85xx/ge_imp3a.c
new file mode 100644
index 000000000000..d50056f424f6
--- /dev/null
+++ b/arch/powerpc/platforms/85xx/ge_imp3a.c
@@ -0,0 +1,246 @@
+/*
+ * GE IMP3A Board Setup
+ *
+ * Author Martyn Welch <martyn.welch@ge.com>
+ *
+ * Copyright 2010 GE Intelligent Platforms Embedded Systems, 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.
+ *
+ * Based on: mpc85xx_ds.c (MPC85xx DS Board Setup)
+ * Copyright 2007 Freescale Semiconductor Inc.
+ */
+
+#include <linux/stddef.h>
+#include <linux/kernel.h>
+#include <linux/pci.h>
+#include <linux/kdev_t.h>
+#include <linux/delay.h>
+#include <linux/seq_file.h>
+#include <linux/interrupt.h>
+#include <linux/of_platform.h>
+#include <linux/memblock.h>
+
+#include <asm/system.h>
+#include <asm/time.h>
+#include <asm/machdep.h>
+#include <asm/pci-bridge.h>
+#include <mm/mmu_decl.h>
+#include <asm/prom.h>
+#include <asm/udbg.h>
+#include <asm/mpic.h>
+#include <asm/swiotlb.h>
+#include <asm/nvram.h>
+
+#include <sysdev/fsl_soc.h>
+#include <sysdev/fsl_pci.h>
+#include "smp.h"
+
+#include "mpc85xx.h"
+#include <sysdev/ge/ge_pic.h>
+
+void __iomem *imp3a_regs;
+
+void __init ge_imp3a_pic_init(void)
+{
+        struct mpic *mpic;
+        struct device_node *np;
+        struct device_node *cascade_node = NULL;
+        unsigned long root = of_get_flat_dt_root();
+
+        if (of_flat_dt_is_compatible(root, "fsl,MPC8572DS-CAMP")) {
+                mpic = mpic_alloc(NULL, 0,
+                        MPIC_NO_RESET |
+                        MPIC_BIG_ENDIAN |
+                        MPIC_SINGLE_DEST_CPU,
+                        0, 256, " OpenPIC  ");
+        } else {
+                mpic = mpic_alloc(NULL, 0,
+                          MPIC_BIG_ENDIAN |
+                          MPIC_SINGLE_DEST_CPU,
+                        0, 256, " OpenPIC  ");
+        }
+
+        BUG_ON(mpic == NULL);
+        mpic_init(mpic);
+        /*
+         * There is a simple interrupt handler in the main FPGA, this needs
+         * to be cascaded into the MPIC
+         */
+        for_each_node_by_type(np, "interrupt-controller")
+                if (of_device_is_compatible(np, "gef,fpga-pic-1.00")) {
+                        cascade_node = np;
+                        break;
+                }
+
+        if (cascade_node == NULL) {
+                printk(KERN_WARNING "IMP3A: No FPGA PIC\n");
+                return;
+        }
+
+        gef_pic_init(cascade_node);
+        of_node_put(cascade_node);
+}
+
+#ifdef CONFIG_PCI
+static int primary_phb_addr;
+#endif  /* CONFIG_PCI */
+
+/*
+ * Setup the architecture
+ */
+static void __init ge_imp3a_setup_arch(void)
+{
+        struct device_node *regs;
+#ifdef CONFIG_PCI
+        struct device_node *np;
+        struct pci_controller *hose;
+#endif
+        dma_addr_t max = 0xffffffff;
+
+        if (ppc_md.progress)
+                ppc_md.progress("ge_imp3a_setup_arch()", 0);
+
+#ifdef CONFIG_PCI
+        for_each_node_by_type(np, "pci") {
+                if (of_device_is_compatible(np, "fsl,mpc8540-pci") ||
+                    of_device_is_compatible(np, "fsl,mpc8548-pcie") ||
+                    of_device_is_compatible(np, "fsl,p2020-pcie")) {
+                        struct resource rsrc;
+                        of_address_to_resource(np, 0, &rsrc);
+                        if ((rsrc.start & 0xfffff) == primary_phb_addr)
+                                fsl_add_bridge(np, 1);
+                        else
+                                fsl_add_bridge(np, 0);
+
+                        hose = pci_find_hose_for_OF_device(np);
+                        max = min(max, hose->dma_window_base_cur +
+                                        hose->dma_window_size);
+                }
+        }
+#endif
+
+        mpc85xx_smp_init();
+
+#ifdef CONFIG_SWIOTLB
+        if (memblock_end_of_DRAM() > max) {
+                ppc_swiotlb_enable = 1;
+                set_pci_dma_ops(&swiotlb_dma_ops);
+                ppc_md.pci_dma_dev_setup = pci_dma_dev_setup_swiotlb;
+        }
+#endif
+
+        /* Remap basic board registers */
+        regs = of_find_compatible_node(NULL, NULL, "ge,imp3a-fpga-regs");
+        if (regs) {
+                imp3a_regs = of_iomap(regs, 0);
+                if (imp3a_regs == NULL)
+                        printk(KERN_WARNING "Unable to map board registers\n");
+                of_node_put(regs);
+        }
+
+#if defined(CONFIG_MMIO_NVRAM)
+        mmio_nvram_init();
+#endif
+
+        printk(KERN_INFO "GE Intelligent Platforms IMP3A 3U cPCI SBC\n");
+}
+
+/* Return the PCB revision */
+static unsigned int ge_imp3a_get_pcb_rev(void)
+{
+        unsigned int reg;
+
+        reg = ioread16(imp3a_regs);
+        return (reg >> 8) & 0xff;
+}
+
+/* Return the board (software) revision */
+static unsigned int ge_imp3a_get_board_rev(void)
+{
+        unsigned int reg;
+
+        reg = ioread16(imp3a_regs + 0x2);
+        return reg & 0xff;
+}
+
+/* Return the FPGA revision */
+static unsigned int ge_imp3a_get_fpga_rev(void)
+{
+        unsigned int reg;
+
+        reg = ioread16(imp3a_regs + 0x2);
+        return (reg >> 8) & 0xff;
+}
+
+/* Return compactPCI Geographical Address */
+static unsigned int ge_imp3a_get_cpci_geo_addr(void)
+{
+        unsigned int reg;
+
+        reg = ioread16(imp3a_regs + 0x6);
+        return (reg & 0x0f00) >> 8;
+}
+
+/* Return compactPCI System Controller Status */
+static unsigned int ge_imp3a_get_cpci_is_syscon(void)
+{
+        unsigned int reg;
+
+        reg = ioread16(imp3a_regs + 0x6);
+        return reg & (1 << 12);
+}
+
+static void ge_imp3a_show_cpuinfo(struct seq_file *m)
+{
+        seq_printf(m, "Vendor\t\t: GE Intelligent Platforms\n");
+
+        seq_printf(m, "Revision\t: %u%c\n", ge_imp3a_get_pcb_rev(),
+                ('A' + ge_imp3a_get_board_rev() - 1));
+
+        seq_printf(m, "FPGA Revision\t: %u\n", ge_imp3a_get_fpga_rev());
+
+        seq_printf(m, "cPCI geo. addr\t: %u\n", ge_imp3a_get_cpci_geo_addr());
+
+        seq_printf(m, "cPCI syscon\t: %s\n",
+                ge_imp3a_get_cpci_is_syscon() ? "yes" : "no");
+}
+
+/*
+ * Called very early, device-tree isn't unflattened
+ */
+static int __init ge_imp3a_probe(void)
+{
+        unsigned long root = of_get_flat_dt_root();
+
+        if (of_flat_dt_is_compatible(root, "ge,IMP3A")) {
+#ifdef CONFIG_PCI
+                primary_phb_addr = 0x9000;
+#endif
+                return 1;
+        }
+
+        return 0;
+}
+
+machine_device_initcall(ge_imp3a, mpc85xx_common_publish_devices);
+
+machine_arch_initcall(ge_imp3a, swiotlb_setup_bus_notifier);
+
+define_machine(ge_imp3a) {
+        .name                   = "GE_IMP3A",
+        .probe                  = ge_imp3a_probe,
+        .setup_arch             = ge_imp3a_setup_arch,
+        .init_IRQ               = ge_imp3a_pic_init,
+        .show_cpuinfo           = ge_imp3a_show_cpuinfo,
+#ifdef CONFIG_PCI
+        .pcibios_fixup_bus      = fsl_pcibios_fixup_bus,
+#endif
+        .get_irq                = mpic_get_irq,
+        .restart                = fsl_rstcr_restart,
+        .calibrate_decr         = generic_calibrate_decr,
+        .progress               = udbg_progress,
+};
diff --git a/arch/powerpc/platforms/85xx/ksi8560.c b/arch/powerpc/platforms/85xx/ksi8560.c
index 20f75d7819c6..60120e55da41 100644
--- a/arch/powerpc/platforms/85xx/ksi8560.c
+++ b/arch/powerpc/platforms/85xx/ksi8560.c
@@ -57,8 +57,7 @@ static void machine_restart(char *cmd)
 
 static void __init ksi8560_pic_init(void)
 {
-        struct mpic *mpic = mpic_alloc(NULL, 0,
-                        MPIC_WANTS_RESET | MPIC_BIG_ENDIAN,
+        struct mpic *mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN,
                         0, 256, " OpenPIC  ");
         BUG_ON(mpic == NULL);
         mpic_init(mpic);
diff --git a/arch/powerpc/platforms/85xx/mpc8536_ds.c b/arch/powerpc/platforms/85xx/mpc8536_ds.c
index cf266826682e..f58872688d8f 100644
--- a/arch/powerpc/platforms/85xx/mpc8536_ds.c
+++ b/arch/powerpc/platforms/85xx/mpc8536_ds.c
@@ -36,9 +36,7 @@
 
 void __init mpc8536_ds_pic_init(void)
 {
-        struct mpic *mpic = mpic_alloc(NULL, 0,
-                          MPIC_WANTS_RESET |
-                          MPIC_BIG_ENDIAN | MPIC_BROKEN_FRR_NIRQS,
+        struct mpic *mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN,
                         0, 256, " OpenPIC  ");
         BUG_ON(mpic == NULL);
         mpic_init(mpic);
diff --git a/arch/powerpc/platforms/85xx/mpc85xx_ads.c b/arch/powerpc/platforms/85xx/mpc85xx_ads.c
index 3bebb5173bfc..d19f675cb369 100644
--- a/arch/powerpc/platforms/85xx/mpc85xx_ads.c
+++ b/arch/powerpc/platforms/85xx/mpc85xx_ads.c
@@ -50,8 +50,7 @@ static int mpc85xx_exclude_device(struct pci_controller *hose,
 
 static void __init mpc85xx_ads_pic_init(void)
 {
-        struct mpic *mpic = mpic_alloc(NULL, 0,
-                        MPIC_WANTS_RESET | MPIC_BIG_ENDIAN,
+        struct mpic *mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN,
                         0, 256, " OpenPIC  ");
         BUG_ON(mpic == NULL);
         mpic_init(mpic);
diff --git a/arch/powerpc/platforms/85xx/mpc85xx_cds.c b/arch/powerpc/platforms/85xx/mpc85xx_cds.c
index 40f03da616a9..ab5f0bf19454 100644
--- a/arch/powerpc/platforms/85xx/mpc85xx_cds.c
+++ b/arch/powerpc/platforms/85xx/mpc85xx_cds.c
@@ -3,7 +3,7 @@
  *
  * Maintained by Kumar Gala (see MAINTAINERS for contact information)
  *
- * Copyright 2005 Freescale Semiconductor Inc.
+ * Copyright 2005, 2011-2012 Freescale Semiconductor Inc.
  *
  * This program is free software; you can redistribute  it and/or modify it
  * under  the terms of  the GNU General  Public License as published by the
@@ -48,17 +48,24 @@
 
 #include "mpc85xx.h"
 
-/* CADMUS info */
-/* xxx - galak, move into device tree */
-#define CADMUS_BASE (0xf8004000)
-#define CADMUS_SIZE (256)
-#define CM_VER  (0)
-#define CM_CSR  (1)
-#define CM_RST  (2)
-
+/*
+ * The CDS board contains an FPGA/CPLD called "Cadmus", which collects
+ * various logic and performs system control functions.
+ * Here is the FPGA/CPLD register map.
+ */
+struct cadmus_reg {
+        u8 cm_ver;              /* Board version */
+        u8 cm_csr;              /* General control/status */
+        u8 cm_rst;              /* Reset control */
+        u8 cm_hsclk;    /* High speed clock */
+        u8 cm_hsxclk;   /* High speed clock extended */
+        u8 cm_led;              /* LED data */
+        u8 cm_pci;              /* PCI control/status */
+        u8 cm_dma;              /* DMA control */
+        u8 res[248];    /* Total 256 bytes */
+};
 
-static int cds_pci_slot = 2;
-static volatile u8 *cadmus;
+static struct cadmus_reg *cadmus;
 
 #ifdef CONFIG_PCI
 
@@ -158,6 +165,33 @@ DECLARE_PCI_FIXUP_EARLY(0x1957, 0x3fff, skip_fake_bridge);
 DECLARE_PCI_FIXUP_EARLY(0x3fff, 0x1957, skip_fake_bridge);
 DECLARE_PCI_FIXUP_EARLY(0xff3f, 0x5719, skip_fake_bridge);
 
+#define PCI_DEVICE_ID_IDT_TSI310        0x01a7
+
+/*
+ * Fix Tsi310 PCI-X bridge resource.
+ * Force the bridge to open a window from 0x0000-0x1fff in PCI I/O space.
+ * This allows legacy I/O(i8259, etc) on the VIA southbridge to be accessed.
+ */
+void mpc85xx_cds_fixup_bus(struct pci_bus *bus)
+{
+        struct pci_dev *dev = bus->self;
+        struct resource *res = bus->resource[0];
+
+        if (dev != NULL &&
+            dev->vendor == PCI_VENDOR_ID_IBM &&
+            dev->device == PCI_DEVICE_ID_IDT_TSI310) {
+                if (res) {
+                        res->start = 0;
+                        res->end   = 0x1fff;
+                        res->flags = IORESOURCE_IO;
+                        pr_info("mpc85xx_cds: PCI bridge resource fixup applied\n");
+                        pr_info("mpc85xx_cds: %pR\n", res);
+                }
+        }
+
+        fsl_pcibios_fixup_bus(bus);
+}
+
 #ifdef CONFIG_PPC_I8259
 static void mpc85xx_8259_cascade_handler(unsigned int irq,
                                          struct irq_desc *desc)
@@ -188,8 +222,7 @@ static struct irqaction mpc85xxcds_8259_irqaction = {
 static void __init mpc85xx_cds_pic_init(void)
 {
         struct mpic *mpic;
-        mpic = mpic_alloc(NULL, 0,
-                        MPIC_WANTS_RESET | MPIC_BIG_ENDIAN,
+        mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN,
                         0, 256, " OpenPIC  ");
         BUG_ON(mpic == NULL);
         mpic_init(mpic);
@@ -249,20 +282,30 @@ machine_device_initcall(mpc85xx_cds, mpc85xx_cds_8259_attach);
  */
 static void __init mpc85xx_cds_setup_arch(void)
 {
-#ifdef CONFIG_PCI
         struct device_node *np;
-#endif
+        int cds_pci_slot;
 
         if (ppc_md.progress)
                 ppc_md.progress("mpc85xx_cds_setup_arch()", 0);
 
-        cadmus = ioremap(CADMUS_BASE, CADMUS_SIZE);
-        cds_pci_slot = ((cadmus[CM_CSR] >> 6) & 0x3) + 1;
+        np = of_find_compatible_node(NULL, NULL, "fsl,mpc8548cds-fpga");
+        if (!np) {
+                pr_err("Could not find FPGA node.\n");
+                return;
+        }
+
+        cadmus = of_iomap(np, 0);
+        of_node_put(np);
+        if (!cadmus) {
+                pr_err("Fail to map FPGA area.\n");
+                return;
+        }
 
         if (ppc_md.progress) {
                 char buf[40];
+                cds_pci_slot = ((in_8(&cadmus->cm_csr) >> 6) & 0x3) + 1;
                 snprintf(buf, 40, "CDS Version = 0x%x in slot %d\n",
-                                cadmus[CM_VER], cds_pci_slot);
+                                in_8(&cadmus->cm_ver), cds_pci_slot);
                 ppc_md.progress(buf, 0);
         }
 
@@ -292,7 +335,8 @@ static void mpc85xx_cds_show_cpuinfo(struct seq_file *m)
         svid = mfspr(SPRN_SVR);
 
         seq_printf(m, "Vendor\t\t: Freescale Semiconductor\n");
-        seq_printf(m, "Machine\t\t: MPC85xx CDS (0x%x)\n", cadmus[CM_VER]);
+        seq_printf(m, "Machine\t\t: MPC85xx CDS (0x%x)\n",
+                        in_8(&cadmus->cm_ver));
         seq_printf(m, "PVR\t\t: 0x%x\n", pvid);
         seq_printf(m, "SVR\t\t: 0x%x\n", svid);
 
@@ -323,7 +367,7 @@ define_machine(mpc85xx_cds) {
         .get_irq        = mpic_get_irq,
 #ifdef CONFIG_PCI
         .restart        = mpc85xx_cds_restart,
-        .pcibios_fixup_bus      = fsl_pcibios_fixup_bus,
+        .pcibios_fixup_bus      = mpc85xx_cds_fixup_bus,
 #else
         .restart        = fsl_rstcr_restart,
 #endif
diff --git a/arch/powerpc/platforms/85xx/mpc85xx_ds.c b/arch/powerpc/platforms/85xx/mpc85xx_ds.c
index eefbb91e1d61..6e23e3e34bd9 100644
--- a/arch/powerpc/platforms/85xx/mpc85xx_ds.c
+++ b/arch/powerpc/platforms/85xx/mpc85xx_ds.c
@@ -72,13 +72,13 @@ void __init mpc85xx_ds_pic_init(void)
 
         if (of_flat_dt_is_compatible(root, "fsl,MPC8572DS-CAMP")) {
                 mpic = mpic_alloc(NULL, 0,
-                        MPIC_BIG_ENDIAN | MPIC_BROKEN_FRR_NIRQS |
+                        MPIC_NO_RESET |
+                        MPIC_BIG_ENDIAN |
                         MPIC_SINGLE_DEST_CPU,
                         0, 256, " OpenPIC  ");
         } else {
                 mpic = mpic_alloc(NULL, 0,
-                          MPIC_WANTS_RESET |
-                          MPIC_BIG_ENDIAN | MPIC_BROKEN_FRR_NIRQS |
+                          MPIC_BIG_ENDIAN |
                           MPIC_SINGLE_DEST_CPU,
                         0, 256, " OpenPIC  ");
         }
diff --git a/arch/powerpc/platforms/85xx/mpc85xx_mds.c b/arch/powerpc/platforms/85xx/mpc85xx_mds.c
index 1d15a0cd2c82..f33662b46b8d 100644
--- a/arch/powerpc/platforms/85xx/mpc85xx_mds.c
+++ b/arch/powerpc/platforms/85xx/mpc85xx_mds.c
@@ -1,5 +1,6 @@
 /*
- * Copyright (C) Freescale Semicondutor, Inc. 2006-2010. All rights reserved.
+ * Copyright (C) 2006-2010, 2012 Freescale Semicondutor, Inc.
+ * All rights reserved.
  *
  * Author: Andy Fleming <afleming@freescale.com>
  *
@@ -51,6 +52,7 @@
 #include <asm/qe_ic.h>
 #include <asm/mpic.h>
 #include <asm/swiotlb.h>
+#include <asm/fsl_guts.h>
 #include "smp.h"
 
 #include "mpc85xx.h"
@@ -268,34 +270,27 @@ static void __init mpc85xx_mds_qe_init(void)
         mpc85xx_mds_reset_ucc_phys();
 
         if (machine_is(p1021_mds)) {
-#define MPC85xx_PMUXCR_OFFSET           0x60
-#define MPC85xx_PMUXCR_QE0              0x00008000
-#define MPC85xx_PMUXCR_QE3              0x00001000
-#define MPC85xx_PMUXCR_QE9              0x00000040
-#define MPC85xx_PMUXCR_QE12             0x00000008
-                static __be32 __iomem *pmuxcr;
 
-                np = of_find_node_by_name(NULL, "global-utilities");
+                struct ccsr_guts_85xx __iomem *guts;
 
+                np = of_find_node_by_name(NULL, "global-utilities");
                 if (np) {
-                        pmuxcr = of_iomap(np, 0) + MPC85xx_PMUXCR_OFFSET;
-
-                        if (!pmuxcr)
-                                printk(KERN_EMERG "Error: Alternate function"
-                                        " signal multiplex control register not"
-                                        " mapped!\n");
-                        else
+                        guts = of_iomap(np, 0);
+                        if (!guts)
+                                pr_err("mpc85xx-rdb: could not map global utilities register\n");
+                        else{
                         /* P1021 has pins muxed for QE and other functions. To
                          * enable QE UEC mode, we need to set bit QE0 for UCC1
                          * in Eth mode, QE0 and QE3 for UCC5 in Eth mode, QE9
                          * and QE12 for QE MII management signals in PMUXCR
                          * register.
                          */
-                                setbits32(pmuxcr, MPC85xx_PMUXCR_QE0 |
-                                                  MPC85xx_PMUXCR_QE3 |
-                                                  MPC85xx_PMUXCR_QE9 |
-                                                  MPC85xx_PMUXCR_QE12);
-
+                                setbits32(&guts->pmuxcr, MPC85xx_PMUXCR_QE(0) |
+                                                  MPC85xx_PMUXCR_QE(3) |
+                                                  MPC85xx_PMUXCR_QE(9) |
+                                                  MPC85xx_PMUXCR_QE(12));
+                                iounmap(guts);
+                        }
                         of_node_put(np);
                 }
 
@@ -434,9 +429,8 @@ machine_arch_initcall(p1021_mds, swiotlb_setup_bus_notifier);
 
 static void __init mpc85xx_mds_pic_init(void)
 {
-        struct mpic *mpic = mpic_alloc(NULL, 0,
-                        MPIC_WANTS_RESET | MPIC_BIG_ENDIAN |
-                        MPIC_BROKEN_FRR_NIRQS | MPIC_SINGLE_DEST_CPU,
+        struct mpic *mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN |
+                        MPIC_SINGLE_DEST_CPU,
                         0, 256, " OpenPIC  ");
         BUG_ON(mpic == NULL);
 
diff --git a/arch/powerpc/platforms/85xx/mpc85xx_rdb.c b/arch/powerpc/platforms/85xx/mpc85xx_rdb.c
index ccf520e890be..db214cd4c822 100644
--- a/arch/powerpc/platforms/85xx/mpc85xx_rdb.c
+++ b/arch/powerpc/platforms/85xx/mpc85xx_rdb.c
@@ -1,7 +1,7 @@
 /*
  * MPC85xx RDB Board Setup
  *
- * Copyright 2009 Freescale Semiconductor Inc.
+ * Copyright 2009,2012 Freescale Semiconductor Inc.
  *
  * This program is free software; you can redistribute  it and/or modify it
  * under  the terms of  the GNU General  Public License as published by the
@@ -26,6 +26,9 @@
 #include <asm/prom.h>
 #include <asm/udbg.h>
 #include <asm/mpic.h>
+#include <asm/qe.h>
+#include <asm/qe_ic.h>
+#include <asm/fsl_guts.h>
 
 #include <sysdev/fsl_soc.h>
 #include <sysdev/fsl_pci.h>
@@ -47,21 +50,36 @@ void __init mpc85xx_rdb_pic_init(void)
         struct mpic *mpic;
         unsigned long root = of_get_flat_dt_root();
 
+#ifdef CONFIG_QUICC_ENGINE
+        struct device_node *np;
+#endif
+
         if (of_flat_dt_is_compatible(root, "fsl,MPC85XXRDB-CAMP")) {
-                mpic = mpic_alloc(NULL, 0,
-                        MPIC_BIG_ENDIAN | MPIC_BROKEN_FRR_NIRQS |
+                mpic = mpic_alloc(NULL, 0, MPIC_NO_RESET |
+                        MPIC_BIG_ENDIAN |
                         MPIC_SINGLE_DEST_CPU,
                         0, 256, " OpenPIC  ");
         } else {
                 mpic = mpic_alloc(NULL, 0,
-                  MPIC_WANTS_RESET |
-                  MPIC_BIG_ENDIAN | MPIC_BROKEN_FRR_NIRQS |
+                  MPIC_BIG_ENDIAN |
                   MPIC_SINGLE_DEST_CPU,
                   0, 256, " OpenPIC  ");
         }
 
         BUG_ON(mpic == NULL);
         mpic_init(mpic);
+
+#ifdef CONFIG_QUICC_ENGINE
+        np = of_find_compatible_node(NULL, NULL, "fsl,qe-ic");
+        if (np) {
+                qe_ic_init(np, 0, qe_ic_cascade_low_mpic,
+                                qe_ic_cascade_high_mpic);
+                of_node_put(np);
+
+        } else
+                pr_err("%s: Could not find qe-ic node\n", __func__);
+#endif
+
 }
 
 /*
@@ -69,7 +87,7 @@ void __init mpc85xx_rdb_pic_init(void)
  */
 static void __init mpc85xx_rdb_setup_arch(void)
 {
-#ifdef CONFIG_PCI
+#if defined(CONFIG_PCI) || defined(CONFIG_QUICC_ENGINE)
         struct device_node *np;
 #endif
 
@@ -85,11 +103,73 @@ static void __init mpc85xx_rdb_setup_arch(void)
 #endif
 
         mpc85xx_smp_init();
+
+#ifdef CONFIG_QUICC_ENGINE
+        np = of_find_compatible_node(NULL, NULL, "fsl,qe");
+        if (!np) {
+                pr_err("%s: Could not find Quicc Engine node\n", __func__);
+                goto qe_fail;
+        }
+
+        qe_reset();
+        of_node_put(np);
+
+        np = of_find_node_by_name(NULL, "par_io");
+        if (np) {
+                struct device_node *ucc;
+
+                par_io_init(np);
+                of_node_put(np);
+
+                for_each_node_by_name(ucc, "ucc")
+                        par_io_of_config(ucc);
+
+        }
+#if defined(CONFIG_UCC_GETH) || defined(CONFIG_SERIAL_QE)
+        if (machine_is(p1025_rdb)) {
+
+                struct ccsr_guts_85xx __iomem *guts;
+
+                np = of_find_node_by_name(NULL, "global-utilities");
+                if (np) {
+                        guts = of_iomap(np, 0);
+                        if (!guts) {
+
+                                pr_err("mpc85xx-rdb: could not map global utilities register\n");
+
+                        } else {
+                        /* P1025 has pins muxed for QE and other functions. To
+                        * enable QE UEC mode, we need to set bit QE0 for UCC1
+                        * in Eth mode, QE0 and QE3 for UCC5 in Eth mode, QE9
+                        * and QE12 for QE MII management singals in PMUXCR
+                        * register.
+                        */
+                                setbits32(&guts->pmuxcr, MPC85xx_PMUXCR_QE(0) |
+                                                MPC85xx_PMUXCR_QE(3) |
+                                                MPC85xx_PMUXCR_QE(9) |
+                                                MPC85xx_PMUXCR_QE(12));
+                                iounmap(guts);
+                        }
+                        of_node_put(np);
+                }
+
+        }
+#endif
+
+qe_fail:
+#endif  /* CONFIG_QUICC_ENGINE */
+
         printk(KERN_INFO "MPC85xx RDB board from Freescale Semiconductor\n");
 }
 
 machine_device_initcall(p2020_rdb, mpc85xx_common_publish_devices);
+machine_device_initcall(p2020_rdb_pc, mpc85xx_common_publish_devices);
+machine_device_initcall(p1020_mbg_pc, mpc85xx_common_publish_devices);
 machine_device_initcall(p1020_rdb, mpc85xx_common_publish_devices);
+machine_device_initcall(p1020_rdb_pc, mpc85xx_common_publish_devices);
+machine_device_initcall(p1020_utm_pc, mpc85xx_common_publish_devices);
+machine_device_initcall(p1021_rdb_pc, mpc85xx_common_publish_devices);
+machine_device_initcall(p1025_rdb, mpc85xx_common_publish_devices);
 
 /*
  * Called very early, device-tree isn't unflattened
@@ -112,6 +192,52 @@ static int __init p1020_rdb_probe(void)
         return 0;
 }
 
+static int __init p1020_rdb_pc_probe(void)
+{
+        unsigned long root = of_get_flat_dt_root();
+
+        return of_flat_dt_is_compatible(root, "fsl,P1020RDB-PC");
+}
+
+static int __init p1021_rdb_pc_probe(void)
+{
+        unsigned long root = of_get_flat_dt_root();
+
+        if (of_flat_dt_is_compatible(root, "fsl,P1021RDB-PC"))
+                return 1;
+        return 0;
+}
+
+static int __init p2020_rdb_pc_probe(void)
+{
+        unsigned long root = of_get_flat_dt_root();
+
+        if (of_flat_dt_is_compatible(root, "fsl,P2020RDB-PC"))
+                return 1;
+        return 0;
+}
+
+static int __init p1025_rdb_probe(void)
+{
+        unsigned long root = of_get_flat_dt_root();
+
+        return of_flat_dt_is_compatible(root, "fsl,P1025RDB");
+}
+
+static int __init p1020_mbg_pc_probe(void)
+{
+        unsigned long root = of_get_flat_dt_root();
+
+        return of_flat_dt_is_compatible(root, "fsl,P1020MBG-PC");
+}
+
+static int __init p1020_utm_pc_probe(void)
+{
+        unsigned long root = of_get_flat_dt_root();
+
+        return of_flat_dt_is_compatible(root, "fsl,P1020UTM-PC");
+}
+
 define_machine(p2020_rdb) {
         .name                   = "P2020 RDB",
         .probe                  = p2020_rdb_probe,
@@ -139,3 +265,87 @@ define_machine(p1020_rdb) {
         .calibrate_decr         = generic_calibrate_decr,
         .progress               = udbg_progress,
 };
+
+define_machine(p1021_rdb_pc) {
+        .name                   = "P1021 RDB-PC",
+        .probe                  = p1021_rdb_pc_probe,
+        .setup_arch             = mpc85xx_rdb_setup_arch,
+        .init_IRQ               = mpc85xx_rdb_pic_init,
+#ifdef CONFIG_PCI
+        .pcibios_fixup_bus      = fsl_pcibios_fixup_bus,
+#endif
+        .get_irq                = mpic_get_irq,
+        .restart                = fsl_rstcr_restart,
+        .calibrate_decr         = generic_calibrate_decr,
+        .progress               = udbg_progress,
+};
+
+define_machine(p2020_rdb_pc) {
+        .name                   = "P2020RDB-PC",
+        .probe                  = p2020_rdb_pc_probe,
+        .setup_arch             = mpc85xx_rdb_setup_arch,
+        .init_IRQ               = mpc85xx_rdb_pic_init,
+#ifdef CONFIG_PCI
+        .pcibios_fixup_bus      = fsl_pcibios_fixup_bus,
+#endif
+        .get_irq                = mpic_get_irq,
+        .restart                = fsl_rstcr_restart,
+        .calibrate_decr         = generic_calibrate_decr,
+        .progress               = udbg_progress,
+};
+
+define_machine(p1025_rdb) {
+        .name                   = "P1025 RDB",
+        .probe                  = p1025_rdb_probe,
+        .setup_arch             = mpc85xx_rdb_setup_arch,
+        .init_IRQ               = mpc85xx_rdb_pic_init,
+#ifdef CONFIG_PCI
+        .pcibios_fixup_bus      = fsl_pcibios_fixup_bus,
+#endif
+        .get_irq                = mpic_get_irq,
+        .restart                = fsl_rstcr_restart,
+        .calibrate_decr         = generic_calibrate_decr,
+        .progress               = udbg_progress,
+};
+
+define_machine(p1020_mbg_pc) {
+        .name                   = "P1020 MBG-PC",
+        .probe                  = p1020_mbg_pc_probe,
+        .setup_arch             = mpc85xx_rdb_setup_arch,
+        .init_IRQ               = mpc85xx_rdb_pic_init,
+#ifdef CONFIG_PCI
+        .pcibios_fixup_bus      = fsl_pcibios_fixup_bus,
+#endif
+        .get_irq                = mpic_get_irq,
+        .restart                = fsl_rstcr_restart,
+        .calibrate_decr         = generic_calibrate_decr,
+        .progress               = udbg_progress,
+};
+
+define_machine(p1020_utm_pc) {
+        .name                   = "P1020 UTM-PC",
+        .probe                  = p1020_utm_pc_probe,
+        .setup_arch             = mpc85xx_rdb_setup_arch,
+        .init_IRQ               = mpc85xx_rdb_pic_init,
+#ifdef CONFIG_PCI
+        .pcibios_fixup_bus      = fsl_pcibios_fixup_bus,
+#endif
+        .get_irq                = mpic_get_irq,
+        .restart                = fsl_rstcr_restart,
+        .calibrate_decr         = generic_calibrate_decr,
+        .progress               = udbg_progress,
+};
+
+define_machine(p1020_rdb_pc) {
+        .name                   = "P1020RDB-PC",
+        .probe                  = p1020_rdb_pc_probe,
+        .setup_arch             = mpc85xx_rdb_setup_arch,
+        .init_IRQ               = mpc85xx_rdb_pic_init,
+#ifdef CONFIG_PCI
+        .pcibios_fixup_bus      = fsl_pcibios_fixup_bus,
+#endif
+        .get_irq                = mpic_get_irq,
+        .restart                = fsl_rstcr_restart,
+        .calibrate_decr         = generic_calibrate_decr,
+        .progress               = udbg_progress,
+};
diff --git a/arch/powerpc/platforms/85xx/p1010rdb.c b/arch/powerpc/platforms/85xx/p1010rdb.c
index 538bc3f57e9d..d8bd6563d9ca 100644
--- a/arch/powerpc/platforms/85xx/p1010rdb.c
+++ b/arch/powerpc/platforms/85xx/p1010rdb.c
@@ -32,9 +32,8 @@
 
 void __init p1010_rdb_pic_init(void)
 {
-        struct mpic *mpic = mpic_alloc(NULL, 0,
-          MPIC_WANTS_RESET | MPIC_BIG_ENDIAN |
-          MPIC_BROKEN_FRR_NIRQS | MPIC_SINGLE_DEST_CPU,
+        struct mpic *mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN |
+          MPIC_SINGLE_DEST_CPU,
           0, 256, " OpenPIC  ");
 
         BUG_ON(mpic == NULL);
diff --git a/arch/powerpc/platforms/85xx/p1022_ds.c b/arch/powerpc/platforms/85xx/p1022_ds.c
index bb3d84f4046f..0fe88e39945e 100644
--- a/arch/powerpc/platforms/85xx/p1022_ds.c
+++ b/arch/powerpc/platforms/85xx/p1022_ds.c
@@ -25,6 +25,7 @@
 
 #include <sysdev/fsl_soc.h>
 #include <sysdev/fsl_pci.h>
+#include <asm/udbg.h>
 #include <asm/fsl_guts.h>
 #include "smp.h"
 
@@ -32,6 +33,10 @@
 
 #if defined(CONFIG_FB_FSL_DIU) || defined(CONFIG_FB_FSL_DIU_MODULE)
 
+#define PMUXCR_ELBCDIU_MASK     0xc0000000
+#define PMUXCR_ELBCDIU_NOR16    0x80000000
+#define PMUXCR_ELBCDIU_DIU      0x40000000
+
 /*
  * Board-specific initialization of the DIU.  This code should probably be
  * executed when the DIU is opened, rather than in arch code, but the DIU
@@ -49,11 +54,22 @@
 #define CLKDVDR_PXCLK_MASK      0x00FF0000
 
 /* Some ngPIXIS register definitions */
+#define PX_CTL          3
+#define PX_BRDCFG0      8
+#define PX_BRDCFG1      9
+
+#define PX_BRDCFG0_ELBC_SPI_MASK        0xc0
+#define PX_BRDCFG0_ELBC_SPI_ELBC        0x00
+#define PX_BRDCFG0_ELBC_SPI_NULL        0xc0
+#define PX_BRDCFG0_ELBC_DIU             0x02
+
 #define PX_BRDCFG1_DVIEN        0x80
 #define PX_BRDCFG1_DFPEN        0x40
 #define PX_BRDCFG1_BACKLIGHT    0x20
 #define PX_BRDCFG1_DDCEN        0x10
 
+#define PX_CTL_ALTACC           0x80
+
 /*
  * DIU Area Descriptor
  *
@@ -132,44 +148,117 @@ static void p1022ds_set_gamma_table(enum fsl_diu_monitor_port port,
  */
 static void p1022ds_set_monitor_port(enum fsl_diu_monitor_port port)
 {
-        struct device_node *np;
-        void __iomem *pixis;
-        u8 __iomem *brdcfg1;
-
-        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");
+        struct device_node *guts_node;
+        struct device_node *indirect_node = NULL;
+        struct ccsr_guts_85xx __iomem *guts;
+        u8 __iomem *lbc_lcs0_ba = NULL;
+        u8 __iomem *lbc_lcs1_ba = NULL;
+        u8 b;
+
+        /* Map the global utilities registers. */
+        guts_node = of_find_compatible_node(NULL, NULL, "fsl,p1022-guts");
+        if (!guts_node) {
+                pr_err("p1022ds: missing global utilties device node\n");
                 return;
         }
 
-        pixis = of_iomap(np, 0);
-        if (!pixis) {
-                pr_err("p1022ds: could not map ngPIXIS registers\n");
-                return;
+        guts = of_iomap(guts_node, 0);
+        if (!guts) {
+                pr_err("p1022ds: could not map global utilties device\n");
+                goto exit;
         }
-        brdcfg1 = pixis + 9;    /* BRDCFG1 is at offset 9 in the ngPIXIS */
+
+        indirect_node = of_find_compatible_node(NULL, NULL,
+                                             "fsl,p1022ds-indirect-pixis");
+        if (!indirect_node) {
+                pr_err("p1022ds: missing pixis indirect mode node\n");
+                goto exit;
+        }
+
+        lbc_lcs0_ba = of_iomap(indirect_node, 0);
+        if (!lbc_lcs0_ba) {
+                pr_err("p1022ds: could not map localbus chip select 0\n");
+                goto exit;
+        }
+
+        lbc_lcs1_ba = of_iomap(indirect_node, 1);
+        if (!lbc_lcs1_ba) {
+                pr_err("p1022ds: could not map localbus chip select 1\n");
+                goto exit;
+        }
+
+        /* Make sure we're in indirect mode first. */
+        if ((in_be32(&guts->pmuxcr) & PMUXCR_ELBCDIU_MASK) !=
+            PMUXCR_ELBCDIU_DIU) {
+                struct device_node *pixis_node;
+                void __iomem *pixis;
+
+                pixis_node =
+                        of_find_compatible_node(NULL, NULL, "fsl,p1022ds-fpga");
+                if (!pixis_node) {
+                        pr_err("p1022ds: missing pixis node\n");
+                        goto exit;
+                }
+
+                pixis = of_iomap(pixis_node, 0);
+                of_node_put(pixis_node);
+                if (!pixis) {
+                        pr_err("p1022ds: could not map pixis registers\n");
+                        goto exit;
+                }
+
+                /* Enable indirect PIXIS mode.  */
+                setbits8(pixis + PX_CTL, PX_CTL_ALTACC);
+                iounmap(pixis);
+
+                /* Switch the board mux to the DIU */
+                out_8(lbc_lcs0_ba, PX_BRDCFG0); /* BRDCFG0 */
+                b = in_8(lbc_lcs1_ba);
+                b |= PX_BRDCFG0_ELBC_DIU;
+                out_8(lbc_lcs1_ba, b);
+
+                /* Set the chip mux to DIU mode. */
+                clrsetbits_be32(&guts->pmuxcr, PMUXCR_ELBCDIU_MASK,
+                                PMUXCR_ELBCDIU_DIU);
+                in_be32(&guts->pmuxcr);
+        }
+
 
         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);
+                out_8(lbc_lcs0_ba, PX_BRDCFG1);
+                b = in_8(lbc_lcs1_ba);
+                b &= ~(PX_BRDCFG1_DFPEN | PX_BRDCFG1_BACKLIGHT);
+                b |= PX_BRDCFG1_DVIEN;
+                out_8(lbc_lcs1_ba, b);
                 break;
         case FSL_DIU_PORT_LVDS:
-                printk(KERN_INFO "%s:%u\n", __func__, __LINE__);
+                /*
+                 * LVDS also needs backlight enabled, otherwise the display
+                 * will be blank.
+                 */
                 /* Enable the DFP port, disable the DVI and the backlight */
-                clrsetbits_8(brdcfg1, PX_BRDCFG1_DVIEN | PX_BRDCFG1_BACKLIGHT,
-                             PX_BRDCFG1_DFPEN);
+                out_8(lbc_lcs0_ba, PX_BRDCFG1);
+                b = in_8(lbc_lcs1_ba);
+                b &= ~PX_BRDCFG1_DVIEN;
+                b |= PX_BRDCFG1_DFPEN | PX_BRDCFG1_BACKLIGHT;
+                out_8(lbc_lcs1_ba, b);
                 break;
         default:
                 pr_err("p1022ds: unsupported monitor port %i\n", port);
         }
 
-        iounmap(pixis);
+exit:
+        if (lbc_lcs1_ba)
+                iounmap(lbc_lcs1_ba);
+        if (lbc_lcs0_ba)
+                iounmap(lbc_lcs0_ba);
+        if (guts)
+                iounmap(guts);
+
+        of_node_put(indirect_node);
+        of_node_put(guts_node);
 }
 
 /**
@@ -241,15 +330,56 @@ p1022ds_valid_monitor_port(enum fsl_diu_monitor_port port)
 
 void __init p1022_ds_pic_init(void)
 {
-        struct mpic *mpic = mpic_alloc(NULL, 0,
-                MPIC_WANTS_RESET |
-                MPIC_BIG_ENDIAN | MPIC_BROKEN_FRR_NIRQS |
+        struct mpic *mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN |
                 MPIC_SINGLE_DEST_CPU,
                 0, 256, " OpenPIC  ");
         BUG_ON(mpic == NULL);
         mpic_init(mpic);
 }
 
+#if defined(CONFIG_FB_FSL_DIU) || defined(CONFIG_FB_FSL_DIU_MODULE)
+
+/*
+ * Disables a node in the device tree.
+ *
+ * This function is called before kmalloc() is available, so the 'new' object
+ * should be allocated in the global area.  The easiest way is to do that is
+ * to allocate one static local variable for each call to this function.
+ */
+static void __init disable_one_node(struct device_node *np, struct property *new)
+{
+        struct property *old;
+
+        old = of_find_property(np, new->name, NULL);
+        if (old)
+                prom_update_property(np, new, old);
+        else
+                prom_add_property(np, new);
+}
+
+/* TRUE if there is a "video=fslfb" command-line parameter. */
+static bool fslfb;
+
+/*
+ * Search for a "video=fslfb" command-line parameter, and set 'fslfb' to
+ * true if we find it.
+ *
+ * We need to use early_param() instead of __setup() because the normal
+ * __setup() gets called to late.  However, early_param() gets called very
+ * early, before the device tree is unflattened, so all we can do now is set a
+ * global variable.  Later on, p1022_ds_setup_arch() will use that variable
+ * to determine if we need to update the device tree.
+ */
+static int __init early_video_setup(char *options)
+{
+        fslfb = (strncmp(options, "fslfb:", 6) == 0);
+
+        return 0;
+}
+early_param("video", early_video_setup);
+
+#endif
+
 /*
  * Setup the architecture
  */
@@ -287,6 +417,34 @@ static void __init p1022_ds_setup_arch(void)
         diu_ops.set_monitor_port        = p1022ds_set_monitor_port;
         diu_ops.set_pixel_clock         = p1022ds_set_pixel_clock;
         diu_ops.valid_monitor_port      = p1022ds_valid_monitor_port;
+
+        /*
+         * Disable the NOR flash node if there is video=fslfb... command-line
+         * parameter.  When the DIU is active, NOR flash is unavailable, so we
+         * have to disable the node before the MTD driver loads.
+         */
+        if (fslfb) {
+                struct device_node *np =
+                        of_find_compatible_node(NULL, NULL, "fsl,p1022-elbc");
+
+                if (np) {
+                        np = of_find_compatible_node(np, NULL, "cfi-flash");
+                        if (np) {
+                                static struct property nor_status = {
+                                        .name = "status",
+                                        .value = "disabled",
+                                        .length = sizeof("disabled"),
+                                };
+
+                                pr_info("p1022ds: disabling %s node",
+                                        np->full_name);
+                                disable_one_node(np, &nor_status);
+                                of_node_put(np);
+                        }
+                }
+
+        }
+
 #endif
 
         mpc85xx_smp_init();
diff --git a/arch/powerpc/platforms/85xx/p1023_rds.c b/arch/powerpc/platforms/85xx/p1023_rds.c
index d951e7027bb6..6b07398e4369 100644
--- a/arch/powerpc/platforms/85xx/p1023_rds.c
+++ b/arch/powerpc/platforms/85xx/p1023_rds.c
@@ -93,9 +93,8 @@ machine_device_initcall(p1023_rds, mpc85xx_common_publish_devices);
 
 static void __init mpc85xx_rds_pic_init(void)
 {
-        struct mpic *mpic = mpic_alloc(NULL, 0,
-                MPIC_WANTS_RESET | MPIC_BIG_ENDIAN |
-                MPIC_BROKEN_FRR_NIRQS | MPIC_SINGLE_DEST_CPU,
+        struct mpic *mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN |
+                MPIC_SINGLE_DEST_CPU,
                 0, 256, " OpenPIC  ");
 
         BUG_ON(mpic == NULL);
diff --git a/arch/powerpc/platforms/85xx/sbc8548.c b/arch/powerpc/platforms/85xx/sbc8548.c
index 184a50784617..1677b8a22677 100644
--- a/arch/powerpc/platforms/85xx/sbc8548.c
+++ b/arch/powerpc/platforms/85xx/sbc8548.c
@@ -54,8 +54,7 @@ static int sbc_rev;
 
 static void __init sbc8548_pic_init(void)
 {
-        struct mpic *mpic = mpic_alloc(NULL, 0,
-                        MPIC_WANTS_RESET | MPIC_BIG_ENDIAN,
+        struct mpic *mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN,
                         0, 256, " OpenPIC  ");
         BUG_ON(mpic == NULL);
         mpic_init(mpic);
diff --git a/arch/powerpc/platforms/85xx/sbc8560.c b/arch/powerpc/platforms/85xx/sbc8560.c
index 940752e93051..3c3bbcc27566 100644
--- a/arch/powerpc/platforms/85xx/sbc8560.c
+++ b/arch/powerpc/platforms/85xx/sbc8560.c
@@ -41,8 +41,7 @@
 
 static void __init sbc8560_pic_init(void)
 {
-        struct mpic *mpic = mpic_alloc(NULL, 0,
-                        MPIC_WANTS_RESET | MPIC_BIG_ENDIAN,
+        struct mpic *mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN,
                         0, 256, " OpenPIC  ");
         BUG_ON(mpic == NULL);
         mpic_init(mpic);
diff --git a/arch/powerpc/platforms/85xx/socrates.c b/arch/powerpc/platforms/85xx/socrates.c
index 18f635906b27..b71919217756 100644
--- a/arch/powerpc/platforms/85xx/socrates.c
+++ b/arch/powerpc/platforms/85xx/socrates.c
@@ -48,8 +48,7 @@ static void __init socrates_pic_init(void)
 {
         struct device_node *np;
 
-        struct mpic *mpic = mpic_alloc(NULL, 0,
-                        MPIC_WANTS_RESET | MPIC_BIG_ENDIAN,
+        struct mpic *mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN,
                         0, 256, " OpenPIC  ");
         BUG_ON(mpic == NULL);
         mpic_init(mpic);
diff --git a/arch/powerpc/platforms/85xx/socrates_fpga_pic.c b/arch/powerpc/platforms/85xx/socrates_fpga_pic.c
index 12cb9bb2cc68..3bbbf7489487 100644
--- a/arch/powerpc/platforms/85xx/socrates_fpga_pic.c
+++ b/arch/powerpc/platforms/85xx/socrates_fpga_pic.c
@@ -51,7 +51,7 @@ static struct socrates_fpga_irq_info fpga_irqs[SOCRATES_FPGA_NUM_IRQS] = {
 static DEFINE_RAW_SPINLOCK(socrates_fpga_pic_lock);
 
 static void __iomem *socrates_fpga_pic_iobase;
-static struct irq_host *socrates_fpga_pic_irq_host;
+static struct irq_domain *socrates_fpga_pic_irq_host;
 static unsigned int socrates_fpga_irqs[3];
 
 static inline uint32_t socrates_fpga_pic_read(int reg)
@@ -227,7 +227,7 @@ static struct irq_chip socrates_fpga_pic_chip = {
         .irq_set_type   = socrates_fpga_pic_set_type,
 };
 
-static int socrates_fpga_pic_host_map(struct irq_host *h, unsigned int virq,
+static int socrates_fpga_pic_host_map(struct irq_domain *h, unsigned int virq,
                 irq_hw_number_t hwirq)
 {
         /* All interrupts are LEVEL sensitive */
@@ -238,7 +238,7 @@ static int socrates_fpga_pic_host_map(struct irq_host *h, unsigned int virq,
         return 0;
 }
 
-static int socrates_fpga_pic_host_xlate(struct irq_host *h,
+static int socrates_fpga_pic_host_xlate(struct irq_domain *h,
                 struct device_node *ct, const u32 *intspec, unsigned int intsize,
                 irq_hw_number_t *out_hwirq, unsigned int *out_flags)
 {
@@ -269,7 +269,7 @@ static int socrates_fpga_pic_host_xlate(struct irq_host *h,
         return 0;
 }
 
-static struct irq_host_ops socrates_fpga_pic_host_ops = {
+static const struct irq_domain_ops socrates_fpga_pic_host_ops = {
         .map    = socrates_fpga_pic_host_map,
         .xlate  = socrates_fpga_pic_host_xlate,
 };
@@ -279,10 +279,9 @@ void socrates_fpga_pic_init(struct device_node *pic)
         unsigned long flags;
         int i;
 
-        /* Setup an irq_host structure */
-        socrates_fpga_pic_irq_host = irq_alloc_host(pic, IRQ_HOST_MAP_LINEAR,
-                        SOCRATES_FPGA_NUM_IRQS, &socrates_fpga_pic_host_ops,
-                        SOCRATES_FPGA_NUM_IRQS);
+        /* Setup an irq_domain structure */
+        socrates_fpga_pic_irq_host = irq_domain_add_linear(pic,
+                    SOCRATES_FPGA_NUM_IRQS, &socrates_fpga_pic_host_ops, NULL);
         if (socrates_fpga_pic_irq_host == NULL) {
                 pr_err("FPGA PIC: Unable to allocate host\n");
                 return;
diff --git a/arch/powerpc/platforms/85xx/stx_gp3.c b/arch/powerpc/platforms/85xx/stx_gp3.c
index e9e5234b4e76..27ca3a7b04ab 100644
--- a/arch/powerpc/platforms/85xx/stx_gp3.c
+++ b/arch/powerpc/platforms/85xx/stx_gp3.c
@@ -48,8 +48,7 @@
 
 static void __init stx_gp3_pic_init(void)
 {
-        struct mpic *mpic = mpic_alloc(NULL, 0,
-                        MPIC_WANTS_RESET | MPIC_BIG_ENDIAN,
+        struct mpic *mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN,
                         0, 256, " OpenPIC  ");
         BUG_ON(mpic == NULL);
         mpic_init(mpic);
diff --git a/arch/powerpc/platforms/85xx/tqm85xx.c b/arch/powerpc/platforms/85xx/tqm85xx.c
index bf7c89fb75bb..d7504cefe016 100644
--- a/arch/powerpc/platforms/85xx/tqm85xx.c
+++ b/arch/powerpc/platforms/85xx/tqm85xx.c
@@ -47,7 +47,7 @@
 static void __init tqm85xx_pic_init(void)
 {
         struct mpic *mpic = mpic_alloc(NULL, 0,
-                        MPIC_WANTS_RESET | MPIC_BIG_ENDIAN,
+                        MPIC_BIG_ENDIAN,
                         0, 256, " OpenPIC  ");
         BUG_ON(mpic == NULL);
         mpic_init(mpic);
diff --git a/arch/powerpc/platforms/85xx/xes_mpc85xx.c b/arch/powerpc/platforms/85xx/xes_mpc85xx.c
index 3a69f8b77de6..503c21596c63 100644
--- a/arch/powerpc/platforms/85xx/xes_mpc85xx.c
+++ b/arch/powerpc/platforms/85xx/xes_mpc85xx.c
@@ -43,9 +43,7 @@
 
 void __init xes_mpc85xx_pic_init(void)
 {
-        struct mpic *mpic = mpic_alloc(NULL, 0,
-                          MPIC_WANTS_RESET |
-                          MPIC_BIG_ENDIAN | MPIC_BROKEN_FRR_NIRQS,
+        struct mpic *mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN,
                         0, 256, " OpenPIC  ");
         BUG_ON(mpic == NULL);
         mpic_init(mpic);
diff --git a/arch/powerpc/platforms/86xx/Kconfig b/arch/powerpc/platforms/86xx/Kconfig
index 8d6599d54ea6..7a6279e38213 100644
--- a/arch/powerpc/platforms/86xx/Kconfig
+++ b/arch/powerpc/platforms/86xx/Kconfig
@@ -39,6 +39,7 @@ config GEF_PPC9A
         select MMIO_NVRAM
         select GENERIC_GPIO
         select ARCH_REQUIRE_GPIOLIB
+        select GE_FPGA
         help
           This option enables support for the GE PPC9A.
 
@@ -48,6 +49,7 @@ config GEF_SBC310
         select MMIO_NVRAM
         select GENERIC_GPIO
         select ARCH_REQUIRE_GPIOLIB
+        select GE_FPGA
         help
           This option enables support for the GE SBC310.
 
@@ -57,6 +59,7 @@ config GEF_SBC610
         select MMIO_NVRAM
         select GENERIC_GPIO
         select ARCH_REQUIRE_GPIOLIB
+        select GE_FPGA
         select HAS_RAPIDIO
         help
           This option enables support for the GE SBC610.
diff --git a/arch/powerpc/platforms/86xx/Makefile b/arch/powerpc/platforms/86xx/Makefile
index 4b0d7b1aa005..ede815d6489d 100644
--- a/arch/powerpc/platforms/86xx/Makefile
+++ b/arch/powerpc/platforms/86xx/Makefile
@@ -7,7 +7,6 @@ obj-$(CONFIG_SMP)		+= mpc86xx_smp.o
 obj-$(CONFIG_MPC8641_HPCN)      += mpc86xx_hpcn.o
 obj-$(CONFIG_SBC8641D)          += sbc8641d.o
 obj-$(CONFIG_MPC8610_HPCD)      += mpc8610_hpcd.o
-gef-gpio-$(CONFIG_GPIOLIB)      += gef_gpio.o
-obj-$(CONFIG_GEF_SBC610)        += gef_sbc610.o gef_pic.o $(gef-gpio-y)
-obj-$(CONFIG_GEF_SBC310)        += gef_sbc310.o gef_pic.o $(gef-gpio-y)
-obj-$(CONFIG_GEF_PPC9A)         += gef_ppc9a.o gef_pic.o $(gef-gpio-y)
+obj-$(CONFIG_GEF_SBC610)        += gef_sbc610.o
+obj-$(CONFIG_GEF_SBC310)        += gef_sbc310.o
+obj-$(CONFIG_GEF_PPC9A)         += gef_ppc9a.o
diff --git a/arch/powerpc/platforms/86xx/gef_gpio.c b/arch/powerpc/platforms/86xx/gef_gpio.c
deleted file mode 100644
index 2a703365e664..000000000000
--- a/arch/powerpc/platforms/86xx/gef_gpio.c
+++ /dev/null
@@ -1,171 +0,0 @@
-/*
- * Driver for GE FPGA based GPIO
- *
- * Author: Martyn Welch <martyn.welch@ge.com>
- *
- * 2008 (c) GE Intelligent Platforms Embedded Systems, 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.
- */
-
-/* TODO
- *
- * Configuration of output modes (totem-pole/open-drain)
- * Interrupt configuration - interrupts are always generated the FPGA relies on
- *      the I/O interrupt controllers mask to stop them propergating
- */
-
-#include <linux/kernel.h>
-#include <linux/compiler.h>
-#include <linux/init.h>
-#include <linux/io.h>
-#include <linux/of.h>
-#include <linux/of_device.h>
-#include <linux/of_platform.h>
-#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
-#define GEF_GPIO_OUT            0x08
-#define GEF_GPIO_TRIG           0x0C
-#define GEF_GPIO_POLAR_A        0x10
-#define GEF_GPIO_POLAR_B        0x14
-#define GEF_GPIO_INT_STAT       0x18
-#define GEF_GPIO_OVERRUN        0x1C
-#define GEF_GPIO_MODE           0x20
-
-static void _gef_gpio_set(void __iomem *reg, unsigned int offset, int value)
-{
-        unsigned int data;
-
-        data = ioread32be(reg);
-        /* value: 0=low; 1=high */
-        if (value & 0x1)
-                data = data | (0x1 << offset);
-        else
-                data = data & ~(0x1 << offset);
-
-        iowrite32be(data, reg);
-}
-
-
-static int gef_gpio_dir_in(struct gpio_chip *chip, unsigned offset)
-{
-        unsigned int data;
-        struct of_mm_gpio_chip *mmchip = to_of_mm_gpio_chip(chip);
-
-        data = ioread32be(mmchip->regs + GEF_GPIO_DIRECT);
-        data = data | (0x1 << offset);
-        iowrite32be(data, mmchip->regs + GEF_GPIO_DIRECT);
-
-        return 0;
-}
-
-static int gef_gpio_dir_out(struct gpio_chip *chip, unsigned offset, int value)
-{
-        unsigned int data;
-        struct of_mm_gpio_chip *mmchip = to_of_mm_gpio_chip(chip);
-
-        /* Set direction before switching to input */
-        _gef_gpio_set(mmchip->regs + GEF_GPIO_OUT, offset, value);
-
-        data = ioread32be(mmchip->regs + GEF_GPIO_DIRECT);
-        data = data & ~(0x1 << offset);
-        iowrite32be(data, mmchip->regs + GEF_GPIO_DIRECT);
-
-        return 0;
-}
-
-static int gef_gpio_get(struct gpio_chip *chip, unsigned offset)
-{
-        unsigned int data;
-        int state = 0;
-        struct of_mm_gpio_chip *mmchip = to_of_mm_gpio_chip(chip);
-
-        data = ioread32be(mmchip->regs + GEF_GPIO_IN);
-        state = (int)((data >> offset) & 0x1);
-
-        return state;
-}
-
-static void gef_gpio_set(struct gpio_chip *chip, unsigned offset, int value)
-{
-        struct of_mm_gpio_chip *mmchip = to_of_mm_gpio_chip(chip);
-
-        _gef_gpio_set(mmchip->regs + GEF_GPIO_OUT, offset, value);
-}
-
-static int __init gef_gpio_init(void)
-{
-        struct device_node *np;
-        int retval;
-        struct of_mm_gpio_chip *gef_gpio_chip;
-
-        for_each_compatible_node(np, NULL, "gef,sbc610-gpio") {
-
-                pr_debug("%s: Initialising GEF GPIO\n", np->full_name);
-
-                /* Allocate chip structure */
-                gef_gpio_chip = kzalloc(sizeof(*gef_gpio_chip), GFP_KERNEL);
-                if (!gef_gpio_chip) {
-                        pr_err("%s: Unable to allocate structure\n",
-                                np->full_name);
-                        continue;
-                }
-
-                /* Setup pointers to chip functions */
-                gef_gpio_chip->gc.of_gpio_n_cells = 2;
-                gef_gpio_chip->gc.ngpio = 19;
-                gef_gpio_chip->gc.direction_input = gef_gpio_dir_in;
-                gef_gpio_chip->gc.direction_output = gef_gpio_dir_out;
-                gef_gpio_chip->gc.get = gef_gpio_get;
-                gef_gpio_chip->gc.set = gef_gpio_set;
-
-                /* This function adds a memory mapped GPIO chip */
-                retval = of_mm_gpiochip_add(np, gef_gpio_chip);
-                if (retval) {
-                        kfree(gef_gpio_chip);
-                        pr_err("%s: Unable to add GPIO\n", np->full_name);
-                }
-        }
-
-        for_each_compatible_node(np, NULL, "gef,sbc310-gpio") {
-
-                pr_debug("%s: Initialising GEF GPIO\n", np->full_name);
-
-                /* Allocate chip structure */
-                gef_gpio_chip = kzalloc(sizeof(*gef_gpio_chip), GFP_KERNEL);
-                if (!gef_gpio_chip) {
-                        pr_err("%s: Unable to allocate structure\n",
-                                np->full_name);
-                        continue;
-                }
-
-                /* Setup pointers to chip functions */
-                gef_gpio_chip->gc.of_gpio_n_cells = 2;
-                gef_gpio_chip->gc.ngpio = 6;
-                gef_gpio_chip->gc.direction_input = gef_gpio_dir_in;
-                gef_gpio_chip->gc.direction_output = gef_gpio_dir_out;
-                gef_gpio_chip->gc.get = gef_gpio_get;
-                gef_gpio_chip->gc.set = gef_gpio_set;
-
-                /* This function adds a memory mapped GPIO chip */
-                retval = of_mm_gpiochip_add(np, gef_gpio_chip);
-                if (retval) {
-                        kfree(gef_gpio_chip);
-                        pr_err("%s: Unable to add GPIO\n", np->full_name);
-                }
-        }
-
-        return 0;
-};
-arch_initcall(gef_gpio_init);
-
-MODULE_DESCRIPTION("GE I/O FPGA GPIO driver");
-MODULE_AUTHOR("Martyn Welch <martyn.welch@ge.com");
-MODULE_LICENSE("GPL");
diff --git a/arch/powerpc/platforms/86xx/gef_ppc9a.c b/arch/powerpc/platforms/86xx/gef_ppc9a.c
index 60ce07e39100..ed58b6cfd60c 100644
--- a/arch/powerpc/platforms/86xx/gef_ppc9a.c
+++ b/arch/powerpc/platforms/86xx/gef_ppc9a.c
@@ -37,9 +37,9 @@
 
 #include <sysdev/fsl_pci.h>
 #include <sysdev/fsl_soc.h>
+#include <sysdev/ge/ge_pic.h>
 
 #include "mpc86xx.h"
-#include "gef_pic.h"
 
 #undef DEBUG
 
diff --git a/arch/powerpc/platforms/86xx/gef_sbc310.c b/arch/powerpc/platforms/86xx/gef_sbc310.c
index 3ecee25bf3ed..710db69bd523 100644
--- a/arch/powerpc/platforms/86xx/gef_sbc310.c
+++ b/arch/powerpc/platforms/86xx/gef_sbc310.c
@@ -37,9 +37,9 @@
 
 #include <sysdev/fsl_pci.h>
 #include <sysdev/fsl_soc.h>
+#include <sysdev/ge/ge_pic.h>
 
 #include "mpc86xx.h"
-#include "gef_pic.h"
 
 #undef DEBUG
 
diff --git a/arch/powerpc/platforms/86xx/gef_sbc610.c b/arch/powerpc/platforms/86xx/gef_sbc610.c
index 5090d608d9ee..4a13d2f4ac20 100644
--- a/arch/powerpc/platforms/86xx/gef_sbc610.c
+++ b/arch/powerpc/platforms/86xx/gef_sbc610.c
@@ -37,9 +37,9 @@
 
 #include <sysdev/fsl_pci.h>
 #include <sysdev/fsl_soc.h>
+#include <sysdev/ge/ge_pic.h>
 
 #include "mpc86xx.h"
-#include "gef_pic.h"
 
 #undef DEBUG
 
diff --git a/arch/powerpc/platforms/86xx/pic.c b/arch/powerpc/platforms/86xx/pic.c
index 52bbfa031531..22cc3571ae19 100644
--- a/arch/powerpc/platforms/86xx/pic.c
+++ b/arch/powerpc/platforms/86xx/pic.c
@@ -37,9 +37,8 @@ void __init mpc86xx_init_irq(void)
         int cascade_irq;
 #endif
 
-        struct mpic *mpic = mpic_alloc(NULL, 0,
-                        MPIC_WANTS_RESET | MPIC_BIG_ENDIAN |
-                        MPIC_BROKEN_FRR_NIRQS | MPIC_SINGLE_DEST_CPU,
+        struct mpic *mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN |
+                        MPIC_SINGLE_DEST_CPU,
                         0, 256, " MPIC     ");
         BUG_ON(mpic == NULL);
 
diff --git a/arch/powerpc/platforms/8xx/Kconfig b/arch/powerpc/platforms/8xx/Kconfig
index ee56a9ea6a79..1fb0b3cddeb3 100644
--- a/arch/powerpc/platforms/8xx/Kconfig
+++ b/arch/powerpc/platforms/8xx/Kconfig
@@ -26,6 +26,7 @@ config MPC86XADS
 config MPC885ADS
         bool "MPC885ADS"
         select CPM1
+        select OF_DYNAMIC
         help
           Freescale Semiconductor MPC885 Application Development System (ADS).
           Also known as DUET.
diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig
index 0cfb46d54b8c..a35ca44ade66 100644
--- a/arch/powerpc/platforms/Kconfig
+++ b/arch/powerpc/platforms/Kconfig
@@ -2,7 +2,6 @@ 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"
 source "arch/powerpc/platforms/512x/Kconfig"
 source "arch/powerpc/platforms/52xx/Kconfig"
@@ -87,6 +86,14 @@ config MPIC_WEIRD
         bool
         default n
 
+config MPIC_MSGR
+        bool "MPIC message register support"
+        depends on MPIC
+        default n
+        help
+          Enables support for the MPIC message registers.  These
+          registers are used for inter-processor communication.
+
 config PPC_I8259
         bool
         default n
@@ -138,7 +145,7 @@ config MPIC_BROKEN_REGREAD
           of the register contents in software.
 
 config IBMVIO
-        depends on PPC_PSERIES || PPC_ISERIES
+        depends on PPC_PSERIES
         bool
         default y
 
diff --git a/arch/powerpc/platforms/Makefile b/arch/powerpc/platforms/Makefile
index 2635a22bade2..879b4a448498 100644
--- a/arch/powerpc/platforms/Makefile
+++ b/arch/powerpc/platforms/Makefile
@@ -16,7 +16,6 @@ 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/
 obj-$(CONFIG_PPC_PASEMI)        += pasemi/
 obj-$(CONFIG_PPC_CELL)          += cell/
diff --git a/arch/powerpc/platforms/cell/axon_msi.c b/arch/powerpc/platforms/cell/axon_msi.c
index 40a6e34793b4..db360fc4cf0e 100644
--- a/arch/powerpc/platforms/cell/axon_msi.c
+++ b/arch/powerpc/platforms/cell/axon_msi.c
@@ -67,7 +67,7 @@
 
 
 struct axon_msic {
-        struct irq_host *irq_host;
+        struct irq_domain *irq_domain;
         __le32 *fifo_virt;
         dma_addr_t fifo_phys;
         dcr_host_t dcr_host;
@@ -152,7 +152,7 @@ static void axon_msi_cascade(unsigned int irq, struct irq_desc *desc)
 
 static struct axon_msic *find_msi_translator(struct pci_dev *dev)
 {
-        struct irq_host *irq_host;
+        struct irq_domain *irq_domain;
         struct device_node *dn, *tmp;
         const phandle *ph;
         struct axon_msic *msic = NULL;
@@ -184,14 +184,14 @@ static struct axon_msic *find_msi_translator(struct pci_dev *dev)
                 goto out_error;
         }
 
-        irq_host = irq_find_host(dn);
-        if (!irq_host) {
-                dev_dbg(&dev->dev, "axon_msi: no irq_host found for node %s\n",
+        irq_domain = irq_find_host(dn);
+        if (!irq_domain) {
+                dev_dbg(&dev->dev, "axon_msi: no irq_domain found for node %s\n",
                         dn->full_name);
                 goto out_error;
         }
 
-        msic = irq_host->host_data;
+        msic = irq_domain->host_data;
 
 out_error:
         of_node_put(dn);
@@ -280,7 +280,7 @@ static int axon_msi_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
         BUILD_BUG_ON(NR_IRQS > 65536);
 
         list_for_each_entry(entry, &dev->msi_list, list) {
-                virq = irq_create_direct_mapping(msic->irq_host);
+                virq = irq_create_direct_mapping(msic->irq_domain);
                 if (virq == NO_IRQ) {
                         dev_warn(&dev->dev,
                                  "axon_msi: virq allocation failed!\n");
@@ -318,7 +318,7 @@ static struct irq_chip msic_irq_chip = {
         .name           = "AXON-MSI",
 };
 
-static int msic_host_map(struct irq_host *h, unsigned int virq,
+static int msic_host_map(struct irq_domain *h, unsigned int virq,
                          irq_hw_number_t hw)
 {
         irq_set_chip_data(virq, h->host_data);
@@ -327,7 +327,7 @@ static int msic_host_map(struct irq_host *h, unsigned int virq,
         return 0;
 }
 
-static struct irq_host_ops msic_host_ops = {
+static const struct irq_domain_ops msic_host_ops = {
         .map    = msic_host_map,
 };
 
@@ -337,7 +337,7 @@ static void axon_msi_shutdown(struct platform_device *device)
         u32 tmp;
 
         pr_devel("axon_msi: disabling %s\n",
-                  msic->irq_host->of_node->full_name);
+                  msic->irq_domain->of_node->full_name);
         tmp  = dcr_read(msic->dcr_host, MSIC_CTRL_REG);
         tmp &= ~MSIC_CTRL_ENABLE & ~MSIC_CTRL_IRQ_ENABLE;
         msic_dcr_write(msic, MSIC_CTRL_REG, tmp);
@@ -392,16 +392,13 @@ static int axon_msi_probe(struct platform_device *device)
         }
         memset(msic->fifo_virt, 0xff, MSIC_FIFO_SIZE_BYTES);
 
-        msic->irq_host = irq_alloc_host(dn, IRQ_HOST_MAP_NOMAP,
-                                        NR_IRQS, &msic_host_ops, 0);
-        if (!msic->irq_host) {
-                printk(KERN_ERR "axon_msi: couldn't allocate irq_host for %s\n",
+        msic->irq_domain = irq_domain_add_nomap(dn, &msic_host_ops, msic);
+        if (!msic->irq_domain) {
+                printk(KERN_ERR "axon_msi: couldn't allocate irq_domain for %s\n",
                        dn->full_name);
                 goto out_free_fifo;
         }
 
-        msic->irq_host->host_data = msic;
-
         irq_set_handler_data(virq, msic);
         irq_set_chained_handler(virq, axon_msi_cascade);
         pr_devel("axon_msi: irq 0x%x setup for axon_msi\n", virq);
diff --git a/arch/powerpc/platforms/cell/beat_htab.c b/arch/powerpc/platforms/cell/beat_htab.c
index 2516c1cf8467..943c9d39aa16 100644
--- a/arch/powerpc/platforms/cell/beat_htab.c
+++ b/arch/powerpc/platforms/cell/beat_htab.c
@@ -95,7 +95,6 @@ static long beat_lpar_hpte_insert(unsigned long hpte_group,
         unsigned long lpar_rc;
         u64 hpte_v, hpte_r, slot;
 
-        /* same as iseries */
         if (vflags & HPTE_V_SECONDARY)
                 return -1;
 
@@ -319,7 +318,6 @@ static long beat_lpar_hpte_insert_v3(unsigned long hpte_group,
         unsigned long lpar_rc;
         u64 hpte_v, hpte_r, slot;
 
-        /* same as iseries */
         if (vflags & HPTE_V_SECONDARY)
                 return -1;
 
diff --git a/arch/powerpc/platforms/cell/beat_interrupt.c b/arch/powerpc/platforms/cell/beat_interrupt.c
index 55015e1f6939..e5c3a2c6090d 100644
--- a/arch/powerpc/platforms/cell/beat_interrupt.c
+++ b/arch/powerpc/platforms/cell/beat_interrupt.c
@@ -34,7 +34,7 @@ static DEFINE_RAW_SPINLOCK(beatic_irq_mask_lock);
 static uint64_t beatic_irq_mask_enable[(MAX_IRQS+255)/64];
 static uint64_t beatic_irq_mask_ack[(MAX_IRQS+255)/64];
 
-static struct irq_host *beatic_host;
+static struct irq_domain *beatic_host;
 
 /*
  * In this implementation, "virq" == "IRQ plug number",
@@ -122,7 +122,7 @@ static struct irq_chip beatic_pic = {
  *
  * Note that the number (virq) is already assigned at upper layer.
  */
-static void beatic_pic_host_unmap(struct irq_host *h, unsigned int virq)
+static void beatic_pic_host_unmap(struct irq_domain *h, unsigned int virq)
 {
         beat_destruct_irq_plug(virq);
 }
@@ -133,7 +133,7 @@ static void beatic_pic_host_unmap(struct irq_host *h, unsigned int virq)
  *
  * Note that the number (virq) is already assigned at upper layer.
  */
-static int beatic_pic_host_map(struct irq_host *h, unsigned int virq,
+static int beatic_pic_host_map(struct irq_domain *h, unsigned int virq,
                                irq_hw_number_t hw)
 {
         int64_t err;
@@ -154,7 +154,7 @@ static int beatic_pic_host_map(struct irq_host *h, unsigned int virq,
  * Called from irq_create_of_mapping() only.
  * Note: We have only 1 entry to translate.
  */
-static int beatic_pic_host_xlate(struct irq_host *h, struct device_node *ct,
+static int beatic_pic_host_xlate(struct irq_domain *h, struct device_node *ct,
                                  const u32 *intspec, unsigned int intsize,
                                  irq_hw_number_t *out_hwirq,
                                  unsigned int *out_flags)
@@ -166,13 +166,13 @@ static int beatic_pic_host_xlate(struct irq_host *h, struct device_node *ct,
         return 0;
 }
 
-static int beatic_pic_host_match(struct irq_host *h, struct device_node *np)
+static int beatic_pic_host_match(struct irq_domain *h, struct device_node *np)
 {
         /* Match all */
         return 1;
 }
 
-static struct irq_host_ops beatic_pic_host_ops = {
+static const struct irq_domain_ops beatic_pic_host_ops = {
         .map = beatic_pic_host_map,
         .unmap = beatic_pic_host_unmap,
         .xlate = beatic_pic_host_xlate,
@@ -239,9 +239,7 @@ void __init beatic_init_IRQ(void)
         ppc_md.get_irq = beatic_get_irq;
 
         /* Allocate an irq host */
-        beatic_host = irq_alloc_host(NULL, IRQ_HOST_MAP_NOMAP, 0,
-                                     &beatic_pic_host_ops,
-                                         0);
+        beatic_host = irq_domain_add_nomap(NULL, &beatic_pic_host_ops, NULL);
         BUG_ON(beatic_host == NULL);
         irq_set_default_host(beatic_host);
 }
diff --git a/arch/powerpc/platforms/cell/interrupt.c b/arch/powerpc/platforms/cell/interrupt.c
index 96a433dd2d64..2d42f3bb66d6 100644
--- a/arch/powerpc/platforms/cell/interrupt.c
+++ b/arch/powerpc/platforms/cell/interrupt.c
@@ -56,7 +56,7 @@ struct iic {
 
 static DEFINE_PER_CPU(struct iic, cpu_iic);
 #define IIC_NODE_COUNT  2
-static struct irq_host *iic_host;
+static struct irq_domain *iic_host;
 
 /* Convert between "pending" bits and hw irq number */
 static irq_hw_number_t iic_pending_to_hwnum(struct cbe_iic_pending_bits bits)
@@ -186,7 +186,7 @@ void iic_message_pass(int cpu, int msg)
         out_be64(&per_cpu(cpu_iic, cpu).regs->generate, (0xf - msg) << 4);
 }
 
-struct irq_host *iic_get_irq_host(int node)
+struct irq_domain *iic_get_irq_host(int node)
 {
         return iic_host;
 }
@@ -222,13 +222,13 @@ void iic_request_IPIs(void)
 #endif /* CONFIG_SMP */
 
 
-static int iic_host_match(struct irq_host *h, struct device_node *node)
+static int iic_host_match(struct irq_domain *h, struct device_node *node)
 {
         return of_device_is_compatible(node,
                                     "IBM,CBEA-Internal-Interrupt-Controller");
 }
 
-static int iic_host_map(struct irq_host *h, unsigned int virq,
+static int iic_host_map(struct irq_domain *h, unsigned int virq,
                         irq_hw_number_t hw)
 {
         switch (hw & IIC_IRQ_TYPE_MASK) {
@@ -245,7 +245,7 @@ static int iic_host_map(struct irq_host *h, unsigned int virq,
         return 0;
 }
 
-static int iic_host_xlate(struct irq_host *h, struct device_node *ct,
+static int iic_host_xlate(struct irq_domain *h, struct device_node *ct,
                            const u32 *intspec, unsigned int intsize,
                            irq_hw_number_t *out_hwirq, unsigned int *out_flags)
 
@@ -285,7 +285,7 @@ static int iic_host_xlate(struct irq_host *h, struct device_node *ct,
         return 0;
 }
 
-static struct irq_host_ops iic_host_ops = {
+static const struct irq_domain_ops iic_host_ops = {
         .match = iic_host_match,
         .map = iic_host_map,
         .xlate = iic_host_xlate,
@@ -378,8 +378,8 @@ static int __init setup_iic(void)
 void __init iic_init_IRQ(void)
 {
         /* Setup an irq host data structure */
-        iic_host = irq_alloc_host(NULL, IRQ_HOST_MAP_LINEAR, IIC_SOURCE_COUNT,
-                                  &iic_host_ops, IIC_IRQ_INVALID);
+        iic_host = irq_domain_add_linear(NULL, IIC_SOURCE_COUNT, &iic_host_ops,
+                                         NULL);
         BUG_ON(iic_host == NULL);
         irq_set_default_host(iic_host);
 
diff --git a/arch/powerpc/platforms/cell/setup.c b/arch/powerpc/platforms/cell/setup.c
index 62002a7edfed..fa3e294fd343 100644
--- a/arch/powerpc/platforms/cell/setup.c
+++ b/arch/powerpc/platforms/cell/setup.c
@@ -197,7 +197,8 @@ static void __init mpic_init_IRQ(void)
                 /* The MPIC driver will get everything it needs from the
                  * device-tree, just pass 0 to all arguments
                  */
-                mpic = mpic_alloc(dn, 0, MPIC_SECONDARY, 0, 0, " MPIC     ");
+                mpic = mpic_alloc(dn, 0, MPIC_SECONDARY | MPIC_NO_RESET,
+                                0, 0, " MPIC     ");
                 if (mpic == NULL)
                         continue;
                 mpic_init(mpic);
diff --git a/arch/powerpc/platforms/cell/spider-pic.c b/arch/powerpc/platforms/cell/spider-pic.c
index 442c28c00f88..d8b7cc8a66ca 100644
--- a/arch/powerpc/platforms/cell/spider-pic.c
+++ b/arch/powerpc/platforms/cell/spider-pic.c
@@ -62,7 +62,7 @@ enum {
 #define SPIDER_IRQ_INVALID      63
 
 struct spider_pic {
-        struct irq_host         *host;
+        struct irq_domain               *host;
         void __iomem            *regs;
         unsigned int            node_id;
 };
@@ -168,7 +168,7 @@ static struct irq_chip spider_pic = {
         .irq_set_type = spider_set_irq_type,
 };
 
-static int spider_host_map(struct irq_host *h, unsigned int virq,
+static int spider_host_map(struct irq_domain *h, unsigned int virq,
                         irq_hw_number_t hw)
 {
         irq_set_chip_data(virq, h->host_data);
@@ -180,7 +180,7 @@ static int spider_host_map(struct irq_host *h, unsigned int virq,
         return 0;
 }
 
-static int spider_host_xlate(struct irq_host *h, struct device_node *ct,
+static int spider_host_xlate(struct irq_domain *h, struct device_node *ct,
                            const u32 *intspec, unsigned int intsize,
                            irq_hw_number_t *out_hwirq, unsigned int *out_flags)
 
@@ -194,7 +194,7 @@ static int spider_host_xlate(struct irq_host *h, struct device_node *ct,
         return 0;
 }
 
-static struct irq_host_ops spider_host_ops = {
+static const struct irq_domain_ops spider_host_ops = {
         .map = spider_host_map,
         .xlate = spider_host_xlate,
 };
@@ -299,12 +299,10 @@ static void __init spider_init_one(struct device_node *of_node, int chip,
                 panic("spider_pic: can't map registers !");
 
         /* Allocate a host */
-        pic->host = irq_alloc_host(of_node, IRQ_HOST_MAP_LINEAR,
-                                   SPIDER_SRC_COUNT, &spider_host_ops,
-                                   SPIDER_IRQ_INVALID);
+        pic->host = irq_domain_add_linear(of_node, SPIDER_SRC_COUNT,
+                                          &spider_host_ops, pic);
         if (pic->host == NULL)
                 panic("spider_pic: can't allocate irq host !");
-        pic->host->host_data = pic;
 
         /* Go through all sources and disable them */
         for (i = 0; i < SPIDER_SRC_COUNT; i++) {
diff --git a/arch/powerpc/platforms/cell/spufs/inode.c b/arch/powerpc/platforms/cell/spufs/inode.c
index d4a094ca96f3..1d75c92ea8fb 100644
--- a/arch/powerpc/platforms/cell/spufs/inode.c
+++ b/arch/powerpc/platforms/cell/spufs/inode.c
@@ -646,6 +646,7 @@ long spufs_create(struct path *path, struct dentry *dentry,
 
 out:
         mutex_unlock(&path->dentry->d_inode->i_mutex);
+        dput(dentry);
         return ret;
 }
 
@@ -757,9 +758,9 @@ spufs_create_root(struct super_block *sb, void *data)
                 goto out_iput;
 
         ret = -ENOMEM;
-        sb->s_root = d_alloc_root(inode);
+        sb->s_root = d_make_root(inode);
         if (!sb->s_root)
-                goto out_iput;
+                goto out;
 
         return 0;
 out_iput:
@@ -828,19 +829,19 @@ static int __init spufs_init(void)
         ret = spu_sched_init();
         if (ret)
                 goto out_cache;
-        ret = register_filesystem(&spufs_type);
+        ret = register_spu_syscalls(&spufs_calls);
         if (ret)
                 goto out_sched;
-        ret = register_spu_syscalls(&spufs_calls);
+        ret = register_filesystem(&spufs_type);
         if (ret)
-                goto out_fs;
+                goto out_syscalls;
 
         spufs_init_isolated_loader();
 
         return 0;
 
-out_fs:
-        unregister_filesystem(&spufs_type);
+out_syscalls:
+        unregister_spu_syscalls(&spufs_calls);
 out_sched:
         spu_sched_exit();
 out_cache:
diff --git a/arch/powerpc/platforms/cell/spufs/syscalls.c b/arch/powerpc/platforms/cell/spufs/syscalls.c
index 8591bb62d7fc..5665dcc382c7 100644
--- a/arch/powerpc/platforms/cell/spufs/syscalls.c
+++ b/arch/powerpc/platforms/cell/spufs/syscalls.c
@@ -70,8 +70,6 @@ static long do_spu_create(const char __user *pathname, unsigned int flags,
         ret = PTR_ERR(dentry);
         if (!IS_ERR(dentry)) {
                 ret = spufs_create(&path, dentry, flags, mode, neighbor);
-                mutex_unlock(&path.dentry->d_inode->i_mutex);
-                dput(dentry);
                 path_put(&path);
         }
 
diff --git a/arch/powerpc/platforms/chrp/setup.c b/arch/powerpc/platforms/chrp/setup.c
index f1f17bb2c33c..c665d7de6c99 100644
--- a/arch/powerpc/platforms/chrp/setup.c
+++ b/arch/powerpc/platforms/chrp/setup.c
@@ -435,7 +435,8 @@ static void __init chrp_find_openpic(void)
         if (len > 1)
                 isu_size = iranges[3];
 
-        chrp_mpic = mpic_alloc(np, opaddr, 0, isu_size, 0, " MPIC    ");
+        chrp_mpic = mpic_alloc(np, opaddr, MPIC_NO_RESET,
+                        isu_size, 0, " MPIC    ");
         if (chrp_mpic == NULL) {
                 printk(KERN_ERR "Failed to allocate MPIC structure\n");
                 goto bail;
diff --git a/arch/powerpc/platforms/embedded6xx/flipper-pic.c b/arch/powerpc/platforms/embedded6xx/flipper-pic.c
index f61a2dd96b99..53d6eee01963 100644
--- a/arch/powerpc/platforms/embedded6xx/flipper-pic.c
+++ b/arch/powerpc/platforms/embedded6xx/flipper-pic.c
@@ -96,9 +96,9 @@ static struct irq_chip flipper_pic = {
  *
  */
 
-static struct irq_host *flipper_irq_host;
+static struct irq_domain *flipper_irq_host;
 
-static int flipper_pic_map(struct irq_host *h, unsigned int virq,
+static int flipper_pic_map(struct irq_domain *h, unsigned int virq,
                            irq_hw_number_t hwirq)
 {
         irq_set_chip_data(virq, h->host_data);
@@ -107,13 +107,13 @@ static int flipper_pic_map(struct irq_host *h, unsigned int virq,
         return 0;
 }
 
-static int flipper_pic_match(struct irq_host *h, struct device_node *np)
+static int flipper_pic_match(struct irq_domain *h, struct device_node *np)
 {
         return 1;
 }
 
 
-static struct irq_host_ops flipper_irq_host_ops = {
+static const struct irq_domain_ops flipper_irq_domain_ops = {
         .map = flipper_pic_map,
         .match = flipper_pic_match,
 };
@@ -130,10 +130,10 @@ static void __flipper_quiesce(void __iomem *io_base)
         out_be32(io_base + FLIPPER_ICR, 0xffffffff);
 }
 
-struct irq_host * __init flipper_pic_init(struct device_node *np)
+struct irq_domain * __init flipper_pic_init(struct device_node *np)
 {
         struct device_node *pi;
-        struct irq_host *irq_host = NULL;
+        struct irq_domain *irq_domain = NULL;
         struct resource res;
         void __iomem *io_base;
         int retval;
@@ -159,17 +159,15 @@ struct irq_host * __init flipper_pic_init(struct device_node *np)
 
         __flipper_quiesce(io_base);
 
-        irq_host = irq_alloc_host(np, IRQ_HOST_MAP_LINEAR, FLIPPER_NR_IRQS,
-                                  &flipper_irq_host_ops, -1);
-        if (!irq_host) {
-                pr_err("failed to allocate irq_host\n");
+        irq_domain = irq_domain_add_linear(np, FLIPPER_NR_IRQS,
+                                  &flipper_irq_domain_ops, io_base);
+        if (!irq_domain) {
+                pr_err("failed to allocate irq_domain\n");
                 return NULL;
         }
 
-        irq_host->host_data = io_base;
-
 out:
-        return irq_host;
+        return irq_domain;
 }
 
 unsigned int flipper_pic_get_irq(void)
diff --git a/arch/powerpc/platforms/embedded6xx/hlwd-pic.c b/arch/powerpc/platforms/embedded6xx/hlwd-pic.c
index e4919170c6bc..3006b5117ec6 100644
--- a/arch/powerpc/platforms/embedded6xx/hlwd-pic.c
+++ b/arch/powerpc/platforms/embedded6xx/hlwd-pic.c
@@ -89,9 +89,9 @@ static struct irq_chip hlwd_pic = {
  *
  */
 
-static struct irq_host *hlwd_irq_host;
+static struct irq_domain *hlwd_irq_host;
 
-static int hlwd_pic_map(struct irq_host *h, unsigned int virq,
+static int hlwd_pic_map(struct irq_domain *h, unsigned int virq,
                            irq_hw_number_t hwirq)
 {
         irq_set_chip_data(virq, h->host_data);
@@ -100,11 +100,11 @@ static int hlwd_pic_map(struct irq_host *h, unsigned int virq,
         return 0;
 }
 
-static struct irq_host_ops hlwd_irq_host_ops = {
+static const struct irq_domain_ops hlwd_irq_domain_ops = {
         .map = hlwd_pic_map,
 };
 
-static unsigned int __hlwd_pic_get_irq(struct irq_host *h)
+static unsigned int __hlwd_pic_get_irq(struct irq_domain *h)
 {
         void __iomem *io_base = h->host_data;
         int irq;
@@ -123,14 +123,14 @@ static void hlwd_pic_irq_cascade(unsigned int cascade_virq,
                                       struct irq_desc *desc)
 {
         struct irq_chip *chip = irq_desc_get_chip(desc);
-        struct irq_host *irq_host = irq_get_handler_data(cascade_virq);
+        struct irq_domain *irq_domain = irq_get_handler_data(cascade_virq);
         unsigned int virq;
 
         raw_spin_lock(&desc->lock);
         chip->irq_mask(&desc->irq_data); /* IRQ_LEVEL */
         raw_spin_unlock(&desc->lock);
 
-        virq = __hlwd_pic_get_irq(irq_host);
+        virq = __hlwd_pic_get_irq(irq_domain);
         if (virq != NO_IRQ)
                 generic_handle_irq(virq);
         else
@@ -155,9 +155,9 @@ static void __hlwd_quiesce(void __iomem *io_base)
         out_be32(io_base + HW_BROADWAY_ICR, 0xffffffff);
 }
 
-struct irq_host *hlwd_pic_init(struct device_node *np)
+struct irq_domain *hlwd_pic_init(struct device_node *np)
 {
-        struct irq_host *irq_host;
+        struct irq_domain *irq_domain;
         struct resource res;
         void __iomem *io_base;
         int retval;
@@ -177,15 +177,14 @@ struct irq_host *hlwd_pic_init(struct device_node *np)
 
         __hlwd_quiesce(io_base);
 
-        irq_host = irq_alloc_host(np, IRQ_HOST_MAP_LINEAR, HLWD_NR_IRQS,
-                                  &hlwd_irq_host_ops, -1);
-        if (!irq_host) {
-                pr_err("failed to allocate irq_host\n");
+        irq_domain = irq_domain_add_linear(np, HLWD_NR_IRQS,
+                                           &hlwd_irq_domain_ops, io_base);
+        if (!irq_domain) {
+                pr_err("failed to allocate irq_domain\n");
                 return NULL;
         }
-        irq_host->host_data = io_base;
 
-        return irq_host;
+        return irq_domain;
 }
 
 unsigned int hlwd_pic_get_irq(void)
@@ -200,7 +199,7 @@ unsigned int hlwd_pic_get_irq(void)
 
 void hlwd_pic_probe(void)
 {
-        struct irq_host *host;
+        struct irq_domain *host;
         struct device_node *np;
         const u32 *interrupts;
         int cascade_virq;
diff --git a/arch/powerpc/platforms/embedded6xx/holly.c b/arch/powerpc/platforms/embedded6xx/holly.c
index 9cfcf20c0560..ab51b21b4bd7 100644
--- a/arch/powerpc/platforms/embedded6xx/holly.c
+++ b/arch/powerpc/platforms/embedded6xx/holly.c
@@ -154,11 +154,9 @@ static void __init holly_init_IRQ(void)
         struct device_node *cascade_node = NULL;
 #endif
 
-        mpic = mpic_alloc(NULL, 0,
-                        MPIC_BIG_ENDIAN | MPIC_WANTS_RESET |
+        mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN |
                         MPIC_SPV_EOI | MPIC_NO_PTHROU_DIS | MPIC_REGSET_TSI108,
-                        24,
-                        NR_IRQS-4, /* num_sources used */
+                        24, 0,
                         "Tsi108_PIC");
 
         BUG_ON(mpic == NULL);
diff --git a/arch/powerpc/platforms/embedded6xx/linkstation.c b/arch/powerpc/platforms/embedded6xx/linkstation.c
index bcfad92c9cec..455e7c087422 100644
--- a/arch/powerpc/platforms/embedded6xx/linkstation.c
+++ b/arch/powerpc/platforms/embedded6xx/linkstation.c
@@ -82,8 +82,7 @@ static void __init linkstation_init_IRQ(void)
 {
         struct mpic *mpic;
 
-        mpic = mpic_alloc(NULL, 0, MPIC_WANTS_RESET,
-                        4, 32, " EPIC     ");
+        mpic = mpic_alloc(NULL, 0, 0, 4, 0, " EPIC     ");
         BUG_ON(mpic == NULL);
 
         /* PCI IRQs */
diff --git a/arch/powerpc/platforms/embedded6xx/mpc7448_hpc2.c b/arch/powerpc/platforms/embedded6xx/mpc7448_hpc2.c
index f3350d786f5b..74ccce36baed 100644
--- a/arch/powerpc/platforms/embedded6xx/mpc7448_hpc2.c
+++ b/arch/powerpc/platforms/embedded6xx/mpc7448_hpc2.c
@@ -108,11 +108,9 @@ static void __init mpc7448_hpc2_init_IRQ(void)
         struct device_node *cascade_node = NULL;
 #endif
 
-        mpic = mpic_alloc(NULL, 0,
-                        MPIC_BIG_ENDIAN | MPIC_WANTS_RESET |
+        mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN |
                         MPIC_SPV_EOI | MPIC_NO_PTHROU_DIS | MPIC_REGSET_TSI108,
-                        24,
-                        NR_IRQS-4, /* num_sources used */
+                        24, 0,
                         "Tsi108_PIC");
 
         BUG_ON(mpic == NULL);
diff --git a/arch/powerpc/platforms/embedded6xx/storcenter.c b/arch/powerpc/platforms/embedded6xx/storcenter.c
index afa638834965..e0ed3c71d69b 100644
--- a/arch/powerpc/platforms/embedded6xx/storcenter.c
+++ b/arch/powerpc/platforms/embedded6xx/storcenter.c
@@ -84,8 +84,7 @@ static void __init storcenter_init_IRQ(void)
 {
         struct mpic *mpic;
 
-        mpic = mpic_alloc(NULL, 0, MPIC_WANTS_RESET,
-                        16, 32, " OpenPIC  ");
+        mpic = mpic_alloc(NULL, 0, 0, 16, 0, " OpenPIC  ");
         BUG_ON(mpic == NULL);
 
         /*
diff --git a/arch/powerpc/platforms/iseries/Kconfig b/arch/powerpc/platforms/iseries/Kconfig
deleted file mode 100644
index b57cda3a0817..000000000000
--- a/arch/powerpc/platforms/iseries/Kconfig
+++ /dev/null
@@ -1,38 +0,0 @@
-config PPC_ISERIES
-        bool "IBM Legacy iSeries"
-        depends on PPC64 && PPC_BOOK3S
-        select PPC_SMP_MUXED_IPI
-        select PPC_INDIRECT_PIO
-        select PPC_INDIRECT_MMIO
-        select PPC_PCI_CHOICE if EXPERT
-
-menu "iSeries device drivers"
-        depends on PPC_ISERIES
-
-config VIODASD
-        tristate "iSeries Virtual I/O disk support"
-        depends on BLOCK
-        select VIOPATH
-        help
-          If you are running on an iSeries system and you want to use
-          virtual disks created and managed by OS/400, say Y.
-
-config VIOCD
-        tristate "iSeries Virtual I/O CD support"
-        depends on BLOCK
-        select VIOPATH
-        help
-          If you are running Linux on an IBM iSeries system and you want to
-          read a CD drive owned by OS/400, say Y here.
-
-config VIOTAPE
-        tristate "iSeries Virtual Tape Support"
-        select VIOPATH
-        help
-          If you are running Linux on an iSeries system and you want Linux
-          to read and/or write a tape drive owned by OS/400, say Y here.
-
-endmenu
-
-config VIOPATH
-        bool
diff --git a/arch/powerpc/platforms/iseries/Makefile b/arch/powerpc/platforms/iseries/Makefile
deleted file mode 100644
index a7602b11ed9d..000000000000
--- a/arch/powerpc/platforms/iseries/Makefile
+++ /dev/null
@@ -1,9 +0,0 @@
-ccflags-y       := -mno-minimal-toc
-
-obj-y += exception.o
-obj-y += hvlog.o hvlpconfig.o lpardata.o setup.o dt.o mf.o lpevents.o \
-        hvcall.o proc.o htab.o iommu.o misc.o irq.o
-obj-$(CONFIG_PCI) += pci.o
-obj-$(CONFIG_SMP) += smp.o
-obj-$(CONFIG_VIOPATH) += viopath.o vio.o
-obj-$(CONFIG_MODULES) += ksyms.o
diff --git a/arch/powerpc/platforms/iseries/call_hpt.h b/arch/powerpc/platforms/iseries/call_hpt.h
deleted file mode 100644
index 8d95fe4b554e..000000000000
--- a/arch/powerpc/platforms/iseries/call_hpt.h
+++ /dev/null
@@ -1,102 +0,0 @@
-/*
- * Copyright (C) 2001  Mike Corrigan 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.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
- */
-#ifndef _PLATFORMS_ISERIES_CALL_HPT_H
-#define _PLATFORMS_ISERIES_CALL_HPT_H
-
-/*
- * This file contains the "hypervisor call" interface which is used to
- * drive the hypervisor from the OS.
- */
-
-#include <asm/iseries/hv_call_sc.h>
-#include <asm/iseries/hv_types.h>
-#include <asm/mmu.h>
-
-#define HvCallHptGetHptAddress          HvCallHpt +  0
-#define HvCallHptGetHptPages            HvCallHpt +  1
-#define HvCallHptSetPp                  HvCallHpt +  5
-#define HvCallHptSetSwBits              HvCallHpt +  6
-#define HvCallHptUpdate                 HvCallHpt +  7
-#define HvCallHptInvalidateNoSyncICache HvCallHpt +  8
-#define HvCallHptGet                    HvCallHpt + 11
-#define HvCallHptFindNextValid          HvCallHpt + 12
-#define HvCallHptFindValid              HvCallHpt + 13
-#define HvCallHptAddValidate            HvCallHpt + 16
-#define HvCallHptInvalidateSetSwBitsGet HvCallHpt + 18
-
-
-static inline u64 HvCallHpt_getHptAddress(void)
-{
-        return HvCall0(HvCallHptGetHptAddress);
-}
-
-static inline u64 HvCallHpt_getHptPages(void)
-{
-        return HvCall0(HvCallHptGetHptPages);
-}
-
-static inline void HvCallHpt_setPp(u32 hpteIndex, u8 value)
-{
-        HvCall2(HvCallHptSetPp, hpteIndex, value);
-}
-
-static inline void HvCallHpt_setSwBits(u32 hpteIndex, u8 bitson, u8 bitsoff)
-{
-        HvCall3(HvCallHptSetSwBits, hpteIndex, bitson, bitsoff);
-}
-
-static inline void HvCallHpt_invalidateNoSyncICache(u32 hpteIndex)
-{
-        HvCall1(HvCallHptInvalidateNoSyncICache, hpteIndex);
-}
-
-static inline u64 HvCallHpt_invalidateSetSwBitsGet(u32 hpteIndex, u8 bitson,
-                u8 bitsoff)
-{
-        u64 compressedStatus;
-
-        compressedStatus = HvCall4(HvCallHptInvalidateSetSwBitsGet,
-                        hpteIndex, bitson, bitsoff, 1);
-        HvCall1(HvCallHptInvalidateNoSyncICache, hpteIndex);
-        return compressedStatus;
-}
-
-static inline u64 HvCallHpt_findValid(struct hash_pte *hpte, u64 vpn)
-{
-        return HvCall3Ret16(HvCallHptFindValid, hpte, vpn, 0, 0);
-}
-
-static inline u64 HvCallHpt_findNextValid(struct hash_pte *hpte, u32 hpteIndex,
-                u8 bitson, u8 bitsoff)
-{
-        return HvCall3Ret16(HvCallHptFindNextValid, hpte, hpteIndex,
-                        bitson, bitsoff);
-}
-
-static inline void HvCallHpt_get(struct hash_pte *hpte, u32 hpteIndex)
-{
-        HvCall2Ret16(HvCallHptGet, hpte, hpteIndex, 0);
-}
-
-static inline void HvCallHpt_addValidate(u32 hpteIndex, u32 hBit,
-                                         struct hash_pte *hpte)
-{
-        HvCall4(HvCallHptAddValidate, hpteIndex, hBit, hpte->v, hpte->r);
-}
-
-#endif /* _PLATFORMS_ISERIES_CALL_HPT_H */
diff --git a/arch/powerpc/platforms/iseries/call_pci.h b/arch/powerpc/platforms/iseries/call_pci.h
deleted file mode 100644
index dbdf69850ed9..000000000000
--- a/arch/powerpc/platforms/iseries/call_pci.h
+++ /dev/null
@@ -1,309 +0,0 @@
-/*
- * Provides the Hypervisor PCI calls for iSeries Linux Parition.
- * Copyright (C) 2001  <Wayne G Holm> <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.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the:
- * Free Software Foundation, Inc.,
- * 59 Temple Place, Suite 330,
- * Boston, MA  02111-1307  USA
- *
- * Change Activity:
- *   Created, Jan 9, 2001
- */
-
-#ifndef _PLATFORMS_ISERIES_CALL_PCI_H
-#define _PLATFORMS_ISERIES_CALL_PCI_H
-
-#include <asm/iseries/hv_call_sc.h>
-#include <asm/iseries/hv_types.h>
-
-/*
- * DSA == Direct Select Address
- * this struct must be 64 bits in total
- */
-struct HvCallPci_DsaAddr {
-        u16             busNumber;              /* PHB index? */
-        u8              subBusNumber;           /* PCI bus number? */
-        u8              deviceId;               /* device and function? */
-        u8              barNumber;
-        u8              reserved[3];
-};
-
-union HvDsaMap {
-        u64     DsaAddr;
-        struct HvCallPci_DsaAddr Dsa;
-};
-
-struct HvCallPci_LoadReturn {
-        u64             rc;
-        u64             value;
-};
-
-enum HvCallPci_DeviceType {
-        HvCallPci_NodeDevice    = 1,
-        HvCallPci_SpDevice      = 2,
-        HvCallPci_IopDevice     = 3,
-        HvCallPci_BridgeDevice  = 4,
-        HvCallPci_MultiFunctionDevice = 5,
-        HvCallPci_IoaDevice     = 6
-};
-
-
-struct HvCallPci_DeviceInfo {
-        u32     deviceType;             /* See DeviceType enum for values */
-};
-
-struct HvCallPci_BusUnitInfo {
-        u32     sizeReturned;           /* length of data returned */
-        u32     deviceType;             /* see DeviceType enum for values */
-};
-
-struct HvCallPci_BridgeInfo {
-        struct HvCallPci_BusUnitInfo busUnitInfo;  /* Generic bus unit info */
-        u8              subBusNumber;   /* Bus number of secondary bus */
-        u8              maxAgents;      /* Max idsels on secondary bus */
-        u8              maxSubBusNumber; /* Max Sub Bus */
-        u8              logicalSlotNumber; /* Logical Slot Number for IOA */
-};
-
-
-/*
- * Maximum BusUnitInfo buffer size.  Provided for clients so
- * they can allocate a buffer big enough for any type of bus
- * unit.  Increase as needed.
- */
-enum {HvCallPci_MaxBusUnitInfoSize = 128};
-
-struct HvCallPci_BarParms {
-        u64             vaddr;
-        u64             raddr;
-        u64             size;
-        u64             protectStart;
-        u64             protectEnd;
-        u64             relocationOffset;
-        u64             pciAddress;
-        u64             reserved[3];
-};
-
-enum HvCallPci_VpdType {
-        HvCallPci_BusVpd        = 1,
-        HvCallPci_BusAdapterVpd = 2
-};
-
-#define HvCallPciConfigLoad8            HvCallPci + 0
-#define HvCallPciConfigLoad16           HvCallPci + 1
-#define HvCallPciConfigLoad32           HvCallPci + 2
-#define HvCallPciConfigStore8           HvCallPci + 3
-#define HvCallPciConfigStore16          HvCallPci + 4
-#define HvCallPciConfigStore32          HvCallPci + 5
-#define HvCallPciEoi                    HvCallPci + 16
-#define HvCallPciGetBarParms            HvCallPci + 18
-#define HvCallPciMaskFisr               HvCallPci + 20
-#define HvCallPciUnmaskFisr             HvCallPci + 21
-#define HvCallPciSetSlotReset           HvCallPci + 25
-#define HvCallPciGetDeviceInfo          HvCallPci + 27
-#define HvCallPciGetCardVpd             HvCallPci + 28
-#define HvCallPciBarLoad8               HvCallPci + 40
-#define HvCallPciBarLoad16              HvCallPci + 41
-#define HvCallPciBarLoad32              HvCallPci + 42
-#define HvCallPciBarLoad64              HvCallPci + 43
-#define HvCallPciBarStore8              HvCallPci + 44
-#define HvCallPciBarStore16             HvCallPci + 45
-#define HvCallPciBarStore32             HvCallPci + 46
-#define HvCallPciBarStore64             HvCallPci + 47
-#define HvCallPciMaskInterrupts         HvCallPci + 48
-#define HvCallPciUnmaskInterrupts       HvCallPci + 49
-#define HvCallPciGetBusUnitInfo         HvCallPci + 50
-
-static inline u64 HvCallPci_configLoad16(u16 busNumber, u8 subBusNumber,
-                u8 deviceId, u32 offset, u16 *value)
-{
-        struct HvCallPci_DsaAddr dsa;
-        struct HvCallPci_LoadReturn retVal;
-
-        *((u64*)&dsa) = 0;
-
-        dsa.busNumber = busNumber;
-        dsa.subBusNumber = subBusNumber;
-        dsa.deviceId = deviceId;
-
-        HvCall3Ret16(HvCallPciConfigLoad16, &retVal, *(u64 *)&dsa, offset, 0);
-
-        *value = retVal.value;
-
-        return retVal.rc;
-}
-
-static inline u64 HvCallPci_configLoad32(u16 busNumber, u8 subBusNumber,
-                u8 deviceId, u32 offset, u32 *value)
-{
-        struct HvCallPci_DsaAddr dsa;
-        struct HvCallPci_LoadReturn retVal;
-
-        *((u64*)&dsa) = 0;
-
-        dsa.busNumber = busNumber;
-        dsa.subBusNumber = subBusNumber;
-        dsa.deviceId = deviceId;
-
-        HvCall3Ret16(HvCallPciConfigLoad32, &retVal, *(u64 *)&dsa, offset, 0);
-
-        *value = retVal.value;
-
-        return retVal.rc;
-}
-
-static inline u64 HvCallPci_configStore8(u16 busNumber, u8 subBusNumber,
-                u8 deviceId, u32 offset, u8 value)
-{
-        struct HvCallPci_DsaAddr dsa;
-
-        *((u64*)&dsa) = 0;
-
-        dsa.busNumber = busNumber;
-        dsa.subBusNumber = subBusNumber;
-        dsa.deviceId = deviceId;
-
-        return HvCall4(HvCallPciConfigStore8, *(u64 *)&dsa, offset, value, 0);
-}
-
-static inline u64 HvCallPci_eoi(u16 busNumberParm, u8 subBusParm,
-                u8 deviceIdParm)
-{
-        struct HvCallPci_DsaAddr dsa;
-        struct HvCallPci_LoadReturn retVal;
-
-        *((u64*)&dsa) = 0;
-
-        dsa.busNumber = busNumberParm;
-        dsa.subBusNumber = subBusParm;
-        dsa.deviceId = deviceIdParm;
-
-        HvCall1Ret16(HvCallPciEoi, &retVal, *(u64*)&dsa);
-
-        return retVal.rc;
-}
-
-static inline u64 HvCallPci_getBarParms(u16 busNumberParm, u8 subBusParm,
-                u8 deviceIdParm, u8 barNumberParm, u64 parms, u32 sizeofParms)
-{
-        struct HvCallPci_DsaAddr dsa;
-
-        *((u64*)&dsa) = 0;
-
-        dsa.busNumber = busNumberParm;
-        dsa.subBusNumber = subBusParm;
-        dsa.deviceId = deviceIdParm;
-        dsa.barNumber = barNumberParm;
-
-        return HvCall3(HvCallPciGetBarParms, *(u64*)&dsa, parms, sizeofParms);
-}
-
-static inline u64 HvCallPci_maskFisr(u16 busNumberParm, u8 subBusParm,
-                u8 deviceIdParm, u64 fisrMask)
-{
-        struct HvCallPci_DsaAddr dsa;
-
-        *((u64*)&dsa) = 0;
-
-        dsa.busNumber = busNumberParm;
-        dsa.subBusNumber = subBusParm;
-        dsa.deviceId = deviceIdParm;
-
-        return HvCall2(HvCallPciMaskFisr, *(u64*)&dsa, fisrMask);
-}
-
-static inline u64 HvCallPci_unmaskFisr(u16 busNumberParm, u8 subBusParm,
-                u8 deviceIdParm, u64 fisrMask)
-{
-        struct HvCallPci_DsaAddr dsa;
-
-        *((u64*)&dsa) = 0;
-
-        dsa.busNumber = busNumberParm;
-        dsa.subBusNumber = subBusParm;
-        dsa.deviceId = deviceIdParm;
-
-        return HvCall2(HvCallPciUnmaskFisr, *(u64*)&dsa, fisrMask);
-}
-
-static inline u64 HvCallPci_getDeviceInfo(u16 busNumberParm, u8 subBusParm,
-                u8 deviceNumberParm, u64 parms, u32 sizeofParms)
-{
-        struct HvCallPci_DsaAddr dsa;
-
-        *((u64*)&dsa) = 0;
-
-        dsa.busNumber = busNumberParm;
-        dsa.subBusNumber = subBusParm;
-        dsa.deviceId = deviceNumberParm << 4;
-
-        return HvCall3(HvCallPciGetDeviceInfo, *(u64*)&dsa, parms, sizeofParms);
-}
-
-static inline u64 HvCallPci_maskInterrupts(u16 busNumberParm, u8 subBusParm,
-                u8 deviceIdParm, u64 interruptMask)
-{
-        struct HvCallPci_DsaAddr dsa;
-
-        *((u64*)&dsa) = 0;
-
-        dsa.busNumber = busNumberParm;
-        dsa.subBusNumber = subBusParm;
-        dsa.deviceId = deviceIdParm;
-
-        return HvCall2(HvCallPciMaskInterrupts, *(u64*)&dsa, interruptMask);
-}
-
-static inline u64 HvCallPci_unmaskInterrupts(u16 busNumberParm, u8 subBusParm,
-                u8 deviceIdParm, u64 interruptMask)
-{
-        struct HvCallPci_DsaAddr dsa;
-
-        *((u64*)&dsa) = 0;
-
-        dsa.busNumber = busNumberParm;
-        dsa.subBusNumber = subBusParm;
-        dsa.deviceId = deviceIdParm;
-
-        return HvCall2(HvCallPciUnmaskInterrupts, *(u64*)&dsa, interruptMask);
-}
-
-static inline u64 HvCallPci_getBusUnitInfo(u16 busNumberParm, u8 subBusParm,
-                u8 deviceIdParm, u64 parms, u32 sizeofParms)
-{
-        struct HvCallPci_DsaAddr dsa;
-
-        *((u64*)&dsa) = 0;
-
-        dsa.busNumber = busNumberParm;
-        dsa.subBusNumber = subBusParm;
-        dsa.deviceId = deviceIdParm;
-
-        return HvCall3(HvCallPciGetBusUnitInfo, *(u64*)&dsa, parms,
-                        sizeofParms);
-}
-
-static inline int HvCallPci_getBusVpd(u16 busNumParm, u64 destParm,
-                u16 sizeParm)
-{
-        u64 xRc = HvCall4(HvCallPciGetCardVpd, busNumParm, destParm,
-                        sizeParm, HvCallPci_BusVpd);
-        if (xRc == -1)
-                return -1;
-        else
-                return xRc & 0xFFFF;
-}
-
-#endif /* _PLATFORMS_ISERIES_CALL_PCI_H */
diff --git a/arch/powerpc/platforms/iseries/call_sm.h b/arch/powerpc/platforms/iseries/call_sm.h
deleted file mode 100644
index c7e251619f48..000000000000
--- a/arch/powerpc/platforms/iseries/call_sm.h
+++ /dev/null
@@ -1,37 +0,0 @@
-/*
- * Copyright (C) 2001  Mike Corrigan 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.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
- */
-#ifndef _ISERIES_CALL_SM_H
-#define _ISERIES_CALL_SM_H
-
-/*
- * This file contains the "hypervisor call" interface which is used to
- * drive the hypervisor from the OS.
- */
-
-#include <asm/iseries/hv_call_sc.h>
-#include <asm/iseries/hv_types.h>
-
-#define HvCallSmGet64BitsOfAccessMap    HvCallSm  + 11
-
-static inline u64 HvCallSm_get64BitsOfAccessMap(HvLpIndex lpIndex,
-                u64 indexIntoBitMap)
-{
-        return HvCall2(HvCallSmGet64BitsOfAccessMap, lpIndex, indexIntoBitMap);
-}
-
-#endif /* _ISERIES_CALL_SM_H */
diff --git a/arch/powerpc/platforms/iseries/dt.c b/arch/powerpc/platforms/iseries/dt.c
deleted file mode 100644
index f0491cc28900..000000000000
--- a/arch/powerpc/platforms/iseries/dt.c
+++ /dev/null
@@ -1,643 +0,0 @@
-/*
- *    Copyright (C) 2005-2006 Michael Ellerman, IBM Corporation
- *    Copyright (C) 2000-2004, IBM Corporation
- *
- *    Description:
- *      This file contains all the routines to build a flattened device
- *      tree for a legacy iSeries machine.
- *
- *      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/init.h>
-#include <linux/pci.h>
-#include <linux/pci_regs.h>
-#include <linux/pci_ids.h>
-#include <linux/threads.h>
-#include <linux/bitops.h>
-#include <linux/string.h>
-#include <linux/kernel.h>
-#include <linux/if_ether.h>     /* ETH_ALEN */
-
-#include <asm/machdep.h>
-#include <asm/prom.h>
-#include <asm/lppaca.h>
-#include <asm/cputable.h>
-#include <asm/abs_addr.h>
-#include <asm/system.h>
-#include <asm/iseries/hv_types.h>
-#include <asm/iseries/hv_lp_config.h>
-#include <asm/iseries/hv_call_xm.h>
-#include <asm/udbg.h>
-
-#include "processor_vpd.h"
-#include "call_hpt.h"
-#include "call_pci.h"
-#include "pci.h"
-#include "it_exp_vpd_panel.h"
-#include "naca.h"
-
-#ifdef DEBUG
-#define DBG(fmt...) udbg_printf(fmt)
-#else
-#define DBG(fmt...)
-#endif
-
-/*
- * These are created by the linker script at the start and end
- * of the section containing all the strings marked with the DS macro.
- */
-extern char __dt_strings_start[];
-extern char __dt_strings_end[];
-
-#define DS(s)   ({      \
-        static const char __s[] __attribute__((section(".dt_strings"))) = s; \
-        __s;            \
-})
-
-struct iseries_flat_dt {
-        struct boot_param_header header;
-        u64 reserve_map[2];
-};
-
-static void * __initdata dt_data;
-
-/*
- * Putting these strings here keeps them out of the .dt_strings section
- * that we capture for the strings blob of the flattened device tree.
- */
-static char __initdata device_type_cpu[] = "cpu";
-static char __initdata device_type_memory[] = "memory";
-static char __initdata device_type_serial[] = "serial";
-static char __initdata device_type_network[] = "network";
-static char __initdata device_type_pci[] = "pci";
-static char __initdata device_type_vdevice[] = "vdevice";
-static char __initdata device_type_vscsi[] = "vscsi";
-
-
-/* EBCDIC to ASCII conversion routines */
-
-static unsigned char __init e2a(unsigned char x)
-{
-        switch (x) {
-        case 0x81 ... 0x89:
-                return x - 0x81 + 'a';
-        case 0x91 ... 0x99:
-                return x - 0x91 + 'j';
-        case 0xA2 ... 0xA9:
-                return x - 0xA2 + 's';
-        case 0xC1 ... 0xC9:
-                return x - 0xC1 + 'A';
-        case 0xD1 ... 0xD9:
-                return x - 0xD1 + 'J';
-        case 0xE2 ... 0xE9:
-                return x - 0xE2 + 'S';
-        case 0xF0 ... 0xF9:
-                return x - 0xF0 + '0';
-        }
-        return ' ';
-}
-
-static unsigned char * __init strne2a(unsigned char *dest,
-                const unsigned char *src, size_t n)
-{
-        int i;
-
-        n = strnlen(src, n);
-
-        for (i = 0; i < n; i++)
-                dest[i] = e2a(src[i]);
-
-        return dest;
-}
-
-static struct iseries_flat_dt * __init dt_init(void)
-{
-        struct iseries_flat_dt *dt;
-        unsigned long str_len;
-
-        str_len = __dt_strings_end - __dt_strings_start;
-        dt = (struct iseries_flat_dt *)ALIGN(klimit, 8);
-        dt->header.off_mem_rsvmap =
-                offsetof(struct iseries_flat_dt, reserve_map);
-        dt->header.off_dt_strings = ALIGN(sizeof(*dt), 8);
-        dt->header.off_dt_struct = dt->header.off_dt_strings
-                + ALIGN(str_len, 8);
-        dt_data = (void *)((unsigned long)dt + dt->header.off_dt_struct);
-        dt->header.dt_strings_size = str_len;
-
-        /* There is no notion of hardware cpu id on iSeries */
-        dt->header.boot_cpuid_phys = smp_processor_id();
-
-        memcpy((char *)dt + dt->header.off_dt_strings, __dt_strings_start,
-                        str_len);
-
-        dt->header.magic = OF_DT_HEADER;
-        dt->header.version = 0x10;
-        dt->header.last_comp_version = 0x10;
-
-        dt->reserve_map[0] = 0;
-        dt->reserve_map[1] = 0;
-
-        return dt;
-}
-
-static void __init dt_push_u32(struct iseries_flat_dt *dt, u32 value)
-{
-        *((u32 *)dt_data) = value;
-        dt_data += sizeof(u32);
-}
-
-#ifdef notyet
-static void __init dt_push_u64(struct iseries_flat_dt *dt, u64 value)
-{
-        *((u64 *)dt_data) = value;
-        dt_data += sizeof(u64);
-}
-#endif
-
-static void __init dt_push_bytes(struct iseries_flat_dt *dt, const char *data,
-                int len)
-{
-        memcpy(dt_data, data, len);
-        dt_data += ALIGN(len, 4);
-}
-
-static void __init dt_start_node(struct iseries_flat_dt *dt, const char *name)
-{
-        dt_push_u32(dt, OF_DT_BEGIN_NODE);
-        dt_push_bytes(dt, name, strlen(name) + 1);
-}
-
-#define dt_end_node(dt) dt_push_u32(dt, OF_DT_END_NODE)
-
-static void __init __dt_prop(struct iseries_flat_dt *dt, const char *name,
-                const void *data, int len)
-{
-        unsigned long offset;
-
-        dt_push_u32(dt, OF_DT_PROP);
-
-        /* Length of the data */
-        dt_push_u32(dt, len);
-
-        offset = name - __dt_strings_start;
-
-        /* The offset of the properties name in the string blob. */
-        dt_push_u32(dt, (u32)offset);
-
-        /* The actual data. */
-        dt_push_bytes(dt, data, len);
-}
-#define dt_prop(dt, name, data, len)    __dt_prop((dt), DS(name), (data), (len))
-
-#define dt_prop_str(dt, name, data)     \
-        dt_prop((dt), name, (data), strlen((data)) + 1); /* + 1 for NULL */
-
-static void __init __dt_prop_u32(struct iseries_flat_dt *dt, const char *name,
-                u32 data)
-{
-        __dt_prop(dt, name, &data, sizeof(u32));
-}
-#define dt_prop_u32(dt, name, data)     __dt_prop_u32((dt), DS(name), (data))
-
-static void __init __maybe_unused __dt_prop_u64(struct iseries_flat_dt *dt,
-                const char *name, u64 data)
-{
-        __dt_prop(dt, name, &data, sizeof(u64));
-}
-#define dt_prop_u64(dt, name, data)     __dt_prop_u64((dt), DS(name), (data))
-
-#define dt_prop_u64_list(dt, name, data, n)     \
-        dt_prop((dt), name, (data), sizeof(u64) * (n))
-
-#define dt_prop_u32_list(dt, name, data, n)     \
-        dt_prop((dt), name, (data), sizeof(u32) * (n))
-
-#define dt_prop_empty(dt, name)         dt_prop((dt), name, NULL, 0)
-
-static void __init dt_cpus(struct iseries_flat_dt *dt)
-{
-        unsigned char buf[32];
-        unsigned char *p;
-        unsigned int i, index;
-        struct IoHriProcessorVpd *d;
-        u32 pft_size[2];
-
-        /* yuck */
-        snprintf(buf, 32, "PowerPC,%s", cur_cpu_spec->cpu_name);
-        p = strchr(buf, ' ');
-        if (!p) p = buf + strlen(buf);
-
-        dt_start_node(dt, "cpus");
-        dt_prop_u32(dt, "#address-cells", 1);
-        dt_prop_u32(dt, "#size-cells", 0);
-
-        pft_size[0] = 0; /* NUMA CEC cookie, 0 for non NUMA  */
-        pft_size[1] = __ilog2(HvCallHpt_getHptPages() * HW_PAGE_SIZE);
-
-        for (i = 0; i < NR_LPPACAS; i++) {
-                if (lppaca[i].dyn_proc_status >= 2)
-                        continue;
-
-                snprintf(p, 32 - (p - buf), "@%d", i);
-                dt_start_node(dt, buf);
-
-                dt_prop_str(dt, "device_type", device_type_cpu);
-
-                index = lppaca[i].dyn_hv_phys_proc_index;
-                d = &xIoHriProcessorVpd[index];
-
-                dt_prop_u32(dt, "i-cache-size", d->xInstCacheSize * 1024);
-                dt_prop_u32(dt, "i-cache-line-size", d->xInstCacheOperandSize);
-
-                dt_prop_u32(dt, "d-cache-size", d->xDataL1CacheSizeKB * 1024);
-                dt_prop_u32(dt, "d-cache-line-size", d->xDataCacheOperandSize);
-
-                /* magic conversions to Hz copied from old code */
-                dt_prop_u32(dt, "clock-frequency",
-                        ((1UL << 34) * 1000000) / d->xProcFreq);
-                dt_prop_u32(dt, "timebase-frequency",
-                        ((1UL << 32) * 1000000) / d->xTimeBaseFreq);
-
-                dt_prop_u32(dt, "reg", i);
-
-                dt_prop_u32_list(dt, "ibm,pft-size", pft_size, 2);
-
-                dt_end_node(dt);
-        }
-
-        dt_end_node(dt);
-}
-
-static void __init dt_model(struct iseries_flat_dt *dt)
-{
-        char buf[16] = "IBM,";
-
-        /* N.B. lparcfg.c knows about the "IBM," prefixes ... */
-        /* "IBM," + mfgId[2:3] + systemSerial[1:5] */
-        strne2a(buf + 4, xItExtVpdPanel.mfgID + 2, 2);
-        strne2a(buf + 6, xItExtVpdPanel.systemSerial + 1, 5);
-        buf[11] = '\0';
-        dt_prop_str(dt, "system-id", buf);
-
-        /* "IBM," + machineType[0:4] */
-        strne2a(buf + 4, xItExtVpdPanel.machineType, 4);
-        buf[8] = '\0';
-        dt_prop_str(dt, "model", buf);
-
-        dt_prop_str(dt, "compatible", "IBM,iSeries");
-        dt_prop_u32(dt, "ibm,partition-no", HvLpConfig_getLpIndex());
-}
-
-static void __init dt_initrd(struct iseries_flat_dt *dt)
-{
-#ifdef CONFIG_BLK_DEV_INITRD
-        if (naca.xRamDisk) {
-                dt_prop_u64(dt, "linux,initrd-start", (u64)naca.xRamDisk);
-                dt_prop_u64(dt, "linux,initrd-end",
-                        (u64)naca.xRamDisk + naca.xRamDiskSize * HW_PAGE_SIZE);
-        }
-#endif
-}
-
-static void __init dt_do_vdevice(struct iseries_flat_dt *dt,
-                const char *name, u32 reg, int unit,
-                const char *type, const char *compat, int end)
-{
-        char buf[32];
-
-        snprintf(buf, 32, "%s@%08x", name, reg + ((unit >= 0) ? unit : 0));
-        dt_start_node(dt, buf);
-        dt_prop_str(dt, "device_type", type);
-        if (compat)
-                dt_prop_str(dt, "compatible", compat);
-        dt_prop_u32(dt, "reg", reg + ((unit >= 0) ? unit : 0));
-        if (unit >= 0)
-                dt_prop_u32(dt, "linux,unit_address", unit);
-        if (end)
-                dt_end_node(dt);
-}
-
-static void __init dt_vdevices(struct iseries_flat_dt *dt)
-{
-        u32 reg = 0;
-        HvLpIndexMap vlan_map;
-        int i;
-
-        dt_start_node(dt, "vdevice");
-        dt_prop_str(dt, "device_type", device_type_vdevice);
-        dt_prop_str(dt, "compatible", "IBM,iSeries-vdevice");
-        dt_prop_u32(dt, "#address-cells", 1);
-        dt_prop_u32(dt, "#size-cells", 0);
-
-        dt_do_vdevice(dt, "vty", reg, -1, device_type_serial,
-                        "IBM,iSeries-vty", 1);
-        reg++;
-
-        dt_do_vdevice(dt, "v-scsi", reg, -1, device_type_vscsi,
-                        "IBM,v-scsi", 1);
-        reg++;
-
-        vlan_map = HvLpConfig_getVirtualLanIndexMap();
-        for (i = 0; i < HVMAXARCHITECTEDVIRTUALLANS; i++) {
-                unsigned char mac_addr[ETH_ALEN];
-
-                if ((vlan_map & (0x8000 >> i)) == 0)
-                        continue;
-                dt_do_vdevice(dt, "l-lan", reg, i, device_type_network,
-                                "IBM,iSeries-l-lan", 0);
-                mac_addr[0] = 0x02;
-                mac_addr[1] = 0x01;
-                mac_addr[2] = 0xff;
-                mac_addr[3] = i;
-                mac_addr[4] = 0xff;
-                mac_addr[5] = HvLpConfig_getLpIndex_outline();
-                dt_prop(dt, "local-mac-address", (char *)mac_addr, ETH_ALEN);
-                dt_prop(dt, "mac-address", (char *)mac_addr, ETH_ALEN);
-                dt_prop_u32(dt, "max-frame-size", 9000);
-                dt_prop_u32(dt, "address-bits", 48);
-
-                dt_end_node(dt);
-        }
-
-        dt_end_node(dt);
-}
-
-struct pci_class_name {
-        u16 code;
-        const char *name;
-        const char *type;
-};
-
-static struct pci_class_name __initdata pci_class_name[] = {
-        { PCI_CLASS_NETWORK_ETHERNET, "ethernet", device_type_network },
-};
-
-static struct pci_class_name * __init dt_find_pci_class_name(u16 class_code)
-{
-        struct pci_class_name *cp;
-
-        for (cp = pci_class_name;
-                        cp < &pci_class_name[ARRAY_SIZE(pci_class_name)]; cp++)
-                if (cp->code == class_code)
-                        return cp;
-        return NULL;
-}
-
-/*
- * This assumes that the node slot is always on the primary bus!
- */
-static void __init scan_bridge_slot(struct iseries_flat_dt *dt,
-                HvBusNumber bus, struct HvCallPci_BridgeInfo *bridge_info)
-{
-        HvSubBusNumber sub_bus = bridge_info->subBusNumber;
-        u16 vendor_id;
-        u16 device_id;
-        u32 class_id;
-        int err;
-        char buf[32];
-        u32 reg[5];
-        int id_sel = ISERIES_GET_DEVICE_FROM_SUBBUS(sub_bus);
-        int function = ISERIES_GET_FUNCTION_FROM_SUBBUS(sub_bus);
-        HvAgentId eads_id_sel = ISERIES_PCI_AGENTID(id_sel, function);
-        u8 devfn;
-        struct pci_class_name *cp;
-
-        /*
-         * Connect all functions of any device found.
-         */
-        for (id_sel = 1; id_sel <= bridge_info->maxAgents; id_sel++) {
-                for (function = 0; function < 8; function++) {
-                        HvAgentId agent_id = ISERIES_PCI_AGENTID(id_sel,
-                                        function);
-                        err = HvCallXm_connectBusUnit(bus, sub_bus,
-                                        agent_id, 0);
-                        if (err) {
-                                if (err != 0x302)
-                                        DBG("connectBusUnit(%x, %x, %x) %x\n",
-                                                bus, sub_bus, agent_id, err);
-                                continue;
-                        }
-
-                        err = HvCallPci_configLoad16(bus, sub_bus, agent_id,
-                                        PCI_VENDOR_ID, &vendor_id);
-                        if (err) {
-                                DBG("ReadVendor(%x, %x, %x) %x\n",
-                                        bus, sub_bus, agent_id, err);
-                                continue;
-                        }
-                        err = HvCallPci_configLoad16(bus, sub_bus, agent_id,
-                                        PCI_DEVICE_ID, &device_id);
-                        if (err) {
-                                DBG("ReadDevice(%x, %x, %x) %x\n",
-                                        bus, sub_bus, agent_id, err);
-                                continue;
-                        }
-                        err = HvCallPci_configLoad32(bus, sub_bus, agent_id,
-                                        PCI_CLASS_REVISION , &class_id);
-                        if (err) {
-                                DBG("ReadClass(%x, %x, %x) %x\n",
-                                        bus, sub_bus, agent_id, err);
-                                continue;
-                        }
-
-                        devfn = PCI_DEVFN(ISERIES_ENCODE_DEVICE(eads_id_sel),
-                                        function);
-                        cp = dt_find_pci_class_name(class_id >> 16);
-                        if (cp && cp->name)
-                                strncpy(buf, cp->name, sizeof(buf) - 1);
-                        else
-                                snprintf(buf, sizeof(buf), "pci%x,%x",
-                                                vendor_id, device_id);
-                        buf[sizeof(buf) - 1] = '\0';
-                        snprintf(buf + strlen(buf), sizeof(buf) - strlen(buf),
-                                        "@%x", PCI_SLOT(devfn));
-                        buf[sizeof(buf) - 1] = '\0';
-                        if (function != 0)
-                                snprintf(buf + strlen(buf),
-                                        sizeof(buf) - strlen(buf),
-                                        ",%x", function);
-                        dt_start_node(dt, buf);
-                        reg[0] = (bus << 16) | (devfn << 8);
-                        reg[1] = 0;
-                        reg[2] = 0;
-                        reg[3] = 0;
-                        reg[4] = 0;
-                        dt_prop_u32_list(dt, "reg", reg, 5);
-                        if (cp && (cp->type || cp->name))
-                                dt_prop_str(dt, "device_type",
-                                        cp->type ? cp->type : cp->name);
-                        dt_prop_u32(dt, "vendor-id", vendor_id);
-                        dt_prop_u32(dt, "device-id", device_id);
-                        dt_prop_u32(dt, "class-code", class_id >> 8);
-                        dt_prop_u32(dt, "revision-id", class_id & 0xff);
-                        dt_prop_u32(dt, "linux,subbus", sub_bus);
-                        dt_prop_u32(dt, "linux,agent-id", agent_id);
-                        dt_prop_u32(dt, "linux,logical-slot-number",
-                                        bridge_info->logicalSlotNumber);
-                        dt_end_node(dt);
-
-                }
-        }
-}
-
-static void __init scan_bridge(struct iseries_flat_dt *dt, HvBusNumber bus,
-                HvSubBusNumber sub_bus, int id_sel)
-{
-        struct HvCallPci_BridgeInfo bridge_info;
-        HvAgentId agent_id;
-        int function;
-        int ret;
-
-        /* Note: hvSubBus and irq is always be 0 at this level! */
-        for (function = 0; function < 8; ++function) {
-                agent_id = ISERIES_PCI_AGENTID(id_sel, function);
-                ret = HvCallXm_connectBusUnit(bus, sub_bus, agent_id, 0);
-                if (ret != 0) {
-                        if (ret != 0xb)
-                                DBG("connectBusUnit(%x, %x, %x) %x\n",
-                                                bus, sub_bus, agent_id, ret);
-                        continue;
-                }
-                DBG("found device at bus %d idsel %d func %d (AgentId %x)\n",
-                                bus, id_sel, function, agent_id);
-                ret = HvCallPci_getBusUnitInfo(bus, sub_bus, agent_id,
-                                iseries_hv_addr(&bridge_info),
-                                sizeof(struct HvCallPci_BridgeInfo));
-                if (ret != 0)
-                        continue;
-                DBG("bridge info: type %x subbus %x "
-                        "maxAgents %x maxsubbus %x logslot %x\n",
-                        bridge_info.busUnitInfo.deviceType,
-                        bridge_info.subBusNumber,
-                        bridge_info.maxAgents,
-                        bridge_info.maxSubBusNumber,
-                        bridge_info.logicalSlotNumber);
-                if (bridge_info.busUnitInfo.deviceType ==
-                                HvCallPci_BridgeDevice)
-                        scan_bridge_slot(dt, bus, &bridge_info);
-                else
-                        DBG("PCI: Invalid Bridge Configuration(0x%02X)",
-                                bridge_info.busUnitInfo.deviceType);
-        }
-}
-
-static void __init scan_phb(struct iseries_flat_dt *dt, HvBusNumber bus)
-{
-        struct HvCallPci_DeviceInfo dev_info;
-        const HvSubBusNumber sub_bus = 0;       /* EADs is always 0. */
-        int err;
-        int id_sel;
-        const int max_agents = 8;
-
-        /*
-         * Probe for EADs Bridges
-         */
-        for (id_sel = 1; id_sel < max_agents; ++id_sel) {
-                err = HvCallPci_getDeviceInfo(bus, sub_bus, id_sel,
-                                iseries_hv_addr(&dev_info),
-                                sizeof(struct HvCallPci_DeviceInfo));
-                if (err) {
-                        if (err != 0x302)
-                                DBG("getDeviceInfo(%x, %x, %x) %x\n",
-                                                bus, sub_bus, id_sel, err);
-                        continue;
-                }
-                if (dev_info.deviceType != HvCallPci_NodeDevice) {
-                        DBG("PCI: Invalid System Configuration"
-                                        "(0x%02X) for bus 0x%02x id 0x%02x.\n",
-                                        dev_info.deviceType, bus, id_sel);
-                        continue;
-                }
-                scan_bridge(dt, bus, sub_bus, id_sel);
-        }
-}
-
-static void __init dt_pci_devices(struct iseries_flat_dt *dt)
-{
-        HvBusNumber bus;
-        char buf[32];
-        u32 buses[2];
-        int phb_num = 0;
-
-        /* Check all possible buses. */
-        for (bus = 0; bus < 256; bus++) {
-                int err = HvCallXm_testBus(bus);
-
-                if (err) {
-                        /*
-                         * Check for Unexpected Return code, a clue that
-                         * something has gone wrong.
-                         */
-                        if (err != 0x0301)
-                                DBG("Unexpected Return on Probe(0x%02X) "
-                                                "0x%04X\n", bus, err);
-                        continue;
-                }
-                DBG("bus %d appears to exist\n", bus);
-                snprintf(buf, 32, "pci@%d", phb_num);
-                dt_start_node(dt, buf);
-                dt_prop_str(dt, "device_type", device_type_pci);
-                dt_prop_str(dt, "compatible", "IBM,iSeries-Logical-PHB");
-                dt_prop_u32(dt, "#address-cells", 3);
-                dt_prop_u32(dt, "#size-cells", 2);
-                buses[0] = buses[1] = bus;
-                dt_prop_u32_list(dt, "bus-range", buses, 2);
-                scan_phb(dt, bus);
-                dt_end_node(dt);
-                phb_num++;
-        }
-}
-
-static void dt_finish(struct iseries_flat_dt *dt)
-{
-        dt_push_u32(dt, OF_DT_END);
-        dt->header.totalsize = (unsigned long)dt_data - (unsigned long)dt;
-        klimit = ALIGN((unsigned long)dt_data, 8);
-}
-
-void * __init build_flat_dt(unsigned long phys_mem_size)
-{
-        struct iseries_flat_dt *iseries_dt;
-        u64 tmp[2];
-
-        iseries_dt = dt_init();
-
-        dt_start_node(iseries_dt, "");
-
-        dt_prop_u32(iseries_dt, "#address-cells", 2);
-        dt_prop_u32(iseries_dt, "#size-cells", 2);
-        dt_model(iseries_dt);
-
-        /* /memory */
-        dt_start_node(iseries_dt, "memory@0");
-        dt_prop_str(iseries_dt, "device_type", device_type_memory);
-        tmp[0] = 0;
-        tmp[1] = phys_mem_size;
-        dt_prop_u64_list(iseries_dt, "reg", tmp, 2);
-        dt_end_node(iseries_dt);
-
-        /* /chosen */
-        dt_start_node(iseries_dt, "chosen");
-        dt_prop_str(iseries_dt, "bootargs", cmd_line);
-        dt_initrd(iseries_dt);
-        dt_end_node(iseries_dt);
-
-        dt_cpus(iseries_dt);
-
-        dt_vdevices(iseries_dt);
-        dt_pci_devices(iseries_dt);
-
-        dt_end_node(iseries_dt);
-
-        dt_finish(iseries_dt);
-
-        return iseries_dt;
-}
diff --git a/arch/powerpc/platforms/iseries/exception.S b/arch/powerpc/platforms/iseries/exception.S
deleted file mode 100644
index f519ee17ff7d..000000000000
--- a/arch/powerpc/platforms/iseries/exception.S
+++ /dev/null
@@ -1,311 +0,0 @@
-/*
- *  Low level routines for legacy iSeries support.
- *
- *  Extracted from head_64.S
- *
- *  PowerPC version
- *    Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
- *
- *  Rewritten by Cort Dougan (cort@cs.nmt.edu) for PReP
- *    Copyright (C) 1996 Cort Dougan <cort@cs.nmt.edu>
- *  Adapted for Power Macintosh by Paul Mackerras.
- *  Low-level exception handlers and MMU support
- *  rewritten by Paul Mackerras.
- *    Copyright (C) 1996 Paul Mackerras.
- *
- *  Adapted for 64bit PowerPC by Dave Engebretsen, Peter Bergner, and
- *    Mike Corrigan {engebret|bergner|mikejc}@us.ibm.com
- *
- *  This file contains the low-level support and setup for the
- *  PowerPC-64 platform, including trap and interrupt dispatch.
- *
- *  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/reg.h>
-#include <asm/ppc_asm.h>
-#include <asm/asm-offsets.h>
-#include <asm/thread_info.h>
-#include <asm/ptrace.h>
-#include <asm/cputable.h>
-#include <asm/mmu.h>
-
-#include "exception.h"
-
-        .text
-
-        .globl system_reset_iSeries
-system_reset_iSeries:
-        bl      .relative_toc
-        mfspr   r13,SPRN_SPRG3          /* Get alpaca address */
-        LOAD_REG_ADDR(r23, alpaca)
-        li      r0,ALPACA_SIZE
-        sub     r23,r13,r23
-        divdu   r24,r23,r0              /* r24 has cpu number */
-        cmpwi   0,r24,0                 /* Are we processor 0? */
-        bne     1f
-        LOAD_REG_ADDR(r13, boot_paca)
-        mtspr   SPRN_SPRG_PACA,r13      /* Save it away for the future */
-        mfmsr   r23
-        ori     r23,r23,MSR_RI
-        mtmsrd  r23                     /* RI on */
-        b       .__start_initialization_iSeries /* Start up the first processor */
-1:      mfspr   r4,SPRN_CTRLF
-        li      r5,CTRL_RUNLATCH        /* Turn off the run light */
-        andc    r4,r4,r5
-        mtspr   SPRN_CTRLT,r4
-
-/* Spin on __secondary_hold_spinloop until it is updated by the boot cpu. */
-/* In the UP case we'll yield() later, and we will not access the paca anyway */
-#ifdef CONFIG_SMP
-iSeries_secondary_wait_paca:
-        HMT_LOW
-        LOAD_REG_ADDR(r23, __secondary_hold_spinloop)
-        ld      r23,0(r23)
-
-        cmpdi   0,r23,0
-        bne     2f                      /* go on when the master is ready */
-
-        /* Keep poking the Hypervisor until we're released */
-        /* 8002 is a call to HvCallCfg::getLps, a harmless Hypervisor function */
-        lis     r3,0x8002
-        rldicr  r3,r3,32,15             /* r0 = (r3 << 32) & 0xffff000000000000 */
-        li      r0,-1                   /* r0=-1 indicates a Hypervisor call */
-        sc                              /* Invoke the hypervisor via a system call */
-        b       iSeries_secondary_wait_paca
-
-2:
-        HMT_MEDIUM
-        sync
-
-        LOAD_REG_ADDR(r3, nr_cpu_ids)   /* get number of pacas allocated */
-        lwz     r3,0(r3)                /* nr_cpus= or NR_CPUS can limit */
-        cmpld   0,r24,r3                /* is our cpu number allocated? */
-        bge     iSeries_secondary_yield /* no, yield forever */
-
-        /* Load our paca now that it's been allocated */
-        LOAD_REG_ADDR(r13, paca)
-        ld      r13,0(r13)
-        mulli   r0,r24,PACA_SIZE
-        add     r13,r13,r0
-        mtspr   SPRN_SPRG_PACA,r13      /* Save it away for the future */
-        mfmsr   r23
-        ori     r23,r23,MSR_RI
-        mtmsrd  r23                     /* RI on */
-
-iSeries_secondary_smp_loop:
-        lbz     r23,PACAPROCSTART(r13)  /* Test if this processor
-                                         * should start */
-        cmpwi   0,r23,0
-        bne     3f                      /* go on when we are told */
-
-        HMT_LOW
-        /* Let the Hypervisor know we are alive */
-        /* 8002 is a call to HvCallCfg::getLps, a harmless Hypervisor function */
-        lis     r3,0x8002
-        rldicr  r3,r3,32,15             /* r0 = (r3 << 32) & 0xffff000000000000 */
-        li      r0,-1                   /* r0=-1 indicates a Hypervisor call */
-        sc                              /* Invoke the hypervisor via a system call */
-        mfspr   r13,SPRN_SPRG_PACA      /* Put r13 back ???? */
-        b       iSeries_secondary_smp_loop /* wait for signal to start */
-
-3:
-        HMT_MEDIUM
-        sync
-        LOAD_REG_ADDR(r3,current_set)
-        sldi    r28,r24,3               /* get current_set[cpu#] */
-        ldx     r3,r3,r28
-        addi    r1,r3,THREAD_SIZE
-        subi    r1,r1,STACK_FRAME_OVERHEAD
-
-        b       __secondary_start               /* Loop until told to go */
-#endif /* CONFIG_SMP */
-
-iSeries_secondary_yield:
-        /* Yield the processor.  This is required for non-SMP kernels
-                which are running on multi-threaded machines. */
-        HMT_LOW
-        lis     r3,0x8000
-        rldicr  r3,r3,32,15             /* r3 = (r3 << 32) & 0xffff000000000000 */
-        addi    r3,r3,18                /* r3 = 0x8000000000000012 which is "yield" */
-        li      r4,0                    /* "yield timed" */
-        li      r5,-1                   /* "yield forever" */
-        li      r0,-1                   /* r0=-1 indicates a Hypervisor call */
-        sc                              /* Invoke the hypervisor via a system call */
-        mfspr   r13,SPRN_SPRG_PACA      /* Put r13 back ???? */
-        b       iSeries_secondary_yield /* If SMP not configured, secondaries
-                                         * loop forever */
-
-/***  ISeries-LPAR interrupt handlers ***/
-
-        STD_EXCEPTION_ISERIES(machine_check, PACA_EXMC)
-
-        .globl data_access_iSeries
-data_access_iSeries:
-        mtspr   SPRN_SPRG_SCRATCH0,r13
-BEGIN_FTR_SECTION
-        mfspr   r13,SPRN_SPRG_PACA
-        std     r9,PACA_EXSLB+EX_R9(r13)
-        std     r10,PACA_EXSLB+EX_R10(r13)
-        mfspr   r10,SPRN_DAR
-        mfspr   r9,SPRN_DSISR
-        srdi    r10,r10,60
-        rlwimi  r10,r9,16,0x20
-        mfcr    r9
-        cmpwi   r10,0x2c
-        beq     .do_stab_bolted_iSeries
-        ld      r10,PACA_EXSLB+EX_R10(r13)
-        std     r11,PACA_EXGEN+EX_R11(r13)
-        ld      r11,PACA_EXSLB+EX_R9(r13)
-        std     r12,PACA_EXGEN+EX_R12(r13)
-        mfspr   r12,SPRN_SPRG_SCRATCH0
-        std     r10,PACA_EXGEN+EX_R10(r13)
-        std     r11,PACA_EXGEN+EX_R9(r13)
-        std     r12,PACA_EXGEN+EX_R13(r13)
-        EXCEPTION_PROLOG_ISERIES_1
-FTR_SECTION_ELSE
-        EXCEPTION_PROLOG_1(PACA_EXGEN, NOTEST, 0)
-        EXCEPTION_PROLOG_ISERIES_1
-ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_SLB)
-        b       data_access_common
-
-.do_stab_bolted_iSeries:
-        std     r11,PACA_EXSLB+EX_R11(r13)
-        std     r12,PACA_EXSLB+EX_R12(r13)
-        mfspr   r10,SPRN_SPRG_SCRATCH0
-        std     r10,PACA_EXSLB+EX_R13(r13)
-        EXCEPTION_PROLOG_ISERIES_1
-        b       .do_stab_bolted
-
-        .globl  data_access_slb_iSeries
-data_access_slb_iSeries:
-        mtspr   SPRN_SPRG_SCRATCH0,r13  /* save r13 */
-        mfspr   r13,SPRN_SPRG_PACA      /* get paca address into r13 */
-        std     r3,PACA_EXSLB+EX_R3(r13)
-        mfspr   r3,SPRN_DAR
-        std     r9,PACA_EXSLB+EX_R9(r13)
-        mfcr    r9
-#ifdef __DISABLED__
-        cmpdi   r3,0
-        bge     slb_miss_user_iseries
-#endif
-        std     r10,PACA_EXSLB+EX_R10(r13)
-        std     r11,PACA_EXSLB+EX_R11(r13)
-        std     r12,PACA_EXSLB+EX_R12(r13)
-        mfspr   r10,SPRN_SPRG_SCRATCH0
-        std     r10,PACA_EXSLB+EX_R13(r13)
-        ld      r12,PACALPPACAPTR(r13)
-        ld      r12,LPPACASRR1(r12)
-        b       .slb_miss_realmode
-
-        STD_EXCEPTION_ISERIES(instruction_access, PACA_EXGEN)
-
-        .globl  instruction_access_slb_iSeries
-instruction_access_slb_iSeries:
-        mtspr   SPRN_SPRG_SCRATCH0,r13  /* save r13 */
-        mfspr   r13,SPRN_SPRG_PACA      /* get paca address into r13 */
-        std     r3,PACA_EXSLB+EX_R3(r13)
-        ld      r3,PACALPPACAPTR(r13)
-        ld      r3,LPPACASRR0(r3)       /* get SRR0 value */
-        std     r9,PACA_EXSLB+EX_R9(r13)
-        mfcr    r9
-#ifdef __DISABLED__
-        cmpdi   r3,0
-        bge     slb_miss_user_iseries
-#endif
-        std     r10,PACA_EXSLB+EX_R10(r13)
-        std     r11,PACA_EXSLB+EX_R11(r13)
-        std     r12,PACA_EXSLB+EX_R12(r13)
-        mfspr   r10,SPRN_SPRG_SCRATCH0
-        std     r10,PACA_EXSLB+EX_R13(r13)
-        ld      r12,PACALPPACAPTR(r13)
-        ld      r12,LPPACASRR1(r12)
-        b       .slb_miss_realmode
-
-#ifdef __DISABLED__
-slb_miss_user_iseries:
-        std     r10,PACA_EXGEN+EX_R10(r13)
-        std     r11,PACA_EXGEN+EX_R11(r13)
-        std     r12,PACA_EXGEN+EX_R12(r13)
-        mfspr   r10,SPRG_SCRATCH0
-        ld      r11,PACA_EXSLB+EX_R9(r13)
-        ld      r12,PACA_EXSLB+EX_R3(r13)
-        std     r10,PACA_EXGEN+EX_R13(r13)
-        std     r11,PACA_EXGEN+EX_R9(r13)
-        std     r12,PACA_EXGEN+EX_R3(r13)
-        EXCEPTION_PROLOG_ISERIES_1
-        b       slb_miss_user_common
-#endif
-
-        MASKABLE_EXCEPTION_ISERIES(hardware_interrupt)
-        STD_EXCEPTION_ISERIES(alignment, PACA_EXGEN)
-        STD_EXCEPTION_ISERIES(program_check, PACA_EXGEN)
-        STD_EXCEPTION_ISERIES(fp_unavailable, PACA_EXGEN)
-        MASKABLE_EXCEPTION_ISERIES(decrementer)
-        STD_EXCEPTION_ISERIES(trap_0a, PACA_EXGEN)
-        STD_EXCEPTION_ISERIES(trap_0b, PACA_EXGEN)
-
-        .globl  system_call_iSeries
-system_call_iSeries:
-        mr      r9,r13
-        mfspr   r13,SPRN_SPRG_PACA
-        EXCEPTION_PROLOG_ISERIES_1
-        b       system_call_common
-
-        STD_EXCEPTION_ISERIES(single_step, PACA_EXGEN)
-        STD_EXCEPTION_ISERIES(trap_0e, PACA_EXGEN)
-        STD_EXCEPTION_ISERIES(performance_monitor, PACA_EXGEN)
-
-decrementer_iSeries_masked:
-        /* We may not have a valid TOC pointer in here. */
-        li      r11,1
-        ld      r12,PACALPPACAPTR(r13)
-        stb     r11,LPPACADECRINT(r12)
-        li      r12,-1
-        clrldi  r12,r12,33      /* set DEC to 0x7fffffff */
-        mtspr   SPRN_DEC,r12
-        /* fall through */
-
-hardware_interrupt_iSeries_masked:
-        mtcrf   0x80,r9         /* Restore regs */
-        ld      r12,PACALPPACAPTR(r13)
-        ld      r11,LPPACASRR0(r12)
-        ld      r12,LPPACASRR1(r12)
-        mtspr   SPRN_SRR0,r11
-        mtspr   SPRN_SRR1,r12
-        ld      r9,PACA_EXGEN+EX_R9(r13)
-        ld      r10,PACA_EXGEN+EX_R10(r13)
-        ld      r11,PACA_EXGEN+EX_R11(r13)
-        ld      r12,PACA_EXGEN+EX_R12(r13)
-        ld      r13,PACA_EXGEN+EX_R13(r13)
-        rfid
-        b       .       /* prevent speculative execution */
-
-_INIT_STATIC(__start_initialization_iSeries)
-        /* Clear out the BSS */
-        LOAD_REG_ADDR(r11,__bss_stop)
-        LOAD_REG_ADDR(r8,__bss_start)
-        sub     r11,r11,r8              /* bss size                     */
-        addi    r11,r11,7               /* round up to an even double word */
-        rldicl. r11,r11,61,3            /* shift right by 3             */
-        beq     4f
-        addi    r8,r8,-8
-        li      r0,0
-        mtctr   r11                     /* zero this many doublewords   */
-3:      stdu    r0,8(r8)
-        bdnz    3b
-4:
-        LOAD_REG_ADDR(r1,init_thread_union)
-        addi    r1,r1,THREAD_SIZE
-        li      r0,0
-        stdu    r0,-STACK_FRAME_OVERHEAD(r1)
-
-        bl      .iSeries_early_setup
-        bl      .early_setup
-
-        /* relocation is on at this point */
-
-        b       .start_here_common
diff --git a/arch/powerpc/platforms/iseries/exception.h b/arch/powerpc/platforms/iseries/exception.h
deleted file mode 100644
index 50271b550a99..000000000000
--- a/arch/powerpc/platforms/iseries/exception.h
+++ /dev/null
@@ -1,58 +0,0 @@
-#ifndef _ASM_POWERPC_ISERIES_EXCEPTION_H
-#define _ASM_POWERPC_ISERIES_EXCEPTION_H
-/*
- * Extracted from head_64.S
- *
- *  PowerPC version
- *    Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
- *
- *  Rewritten by Cort Dougan (cort@cs.nmt.edu) for PReP
- *    Copyright (C) 1996 Cort Dougan <cort@cs.nmt.edu>
- *  Adapted for Power Macintosh by Paul Mackerras.
- *  Low-level exception handlers and MMU support
- *  rewritten by Paul Mackerras.
- *    Copyright (C) 1996 Paul Mackerras.
- *
- *  Adapted for 64bit PowerPC by Dave Engebretsen, Peter Bergner, and
- *    Mike Corrigan {engebret|bergner|mikejc}@us.ibm.com
- *
- *  This file contains the low-level support and setup for the
- *  PowerPC-64 platform, including trap and interrupt dispatch.
- *
- *  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/exception-64s.h>
-
-#define EXCEPTION_PROLOG_ISERIES_1                                      \
-        mfmsr   r10;                                                    \
-        ld      r12,PACALPPACAPTR(r13);                                 \
-        ld      r11,LPPACASRR0(r12);                                    \
-        ld      r12,LPPACASRR1(r12);                                    \
-        ori     r10,r10,MSR_RI;                                         \
-        mtmsrd  r10,1
-
-#define STD_EXCEPTION_ISERIES(label, area)                              \
-        .globl label##_iSeries;                                         \
-label##_iSeries:                                                        \
-        HMT_MEDIUM;                                                     \
-        mtspr   SPRN_SPRG_SCRATCH0,r13; /* save r13 */                  \
-        EXCEPTION_PROLOG_1(area, NOTEST, 0);                            \
-        EXCEPTION_PROLOG_ISERIES_1;                                     \
-        b       label##_common
-
-#define MASKABLE_EXCEPTION_ISERIES(label)                               \
-        .globl label##_iSeries;                                         \
-label##_iSeries:                                                        \
-        HMT_MEDIUM;                                                     \
-        mtspr   SPRN_SPRG_SCRATCH0,r13; /* save r13 */                  \
-        EXCEPTION_PROLOG_1(PACA_EXGEN, NOTEST, 0);                      \
-        lbz     r10,PACASOFTIRQEN(r13);                                 \
-        cmpwi   0,r10,0;                                                \
-        beq-    label##_iSeries_masked;                                 \
-        EXCEPTION_PROLOG_ISERIES_1;                                     \
-        b       label##_common;                                         \
-
-#endif  /* _ASM_POWERPC_ISERIES_EXCEPTION_H */
diff --git a/arch/powerpc/platforms/iseries/htab.c b/arch/powerpc/platforms/iseries/htab.c
deleted file mode 100644
index 3ae66ab9d5e7..000000000000
--- a/arch/powerpc/platforms/iseries/htab.c
+++ /dev/null
@@ -1,257 +0,0 @@
-/*
- * iSeries hashtable management.
- *      Derived from pSeries_htab.c
- *
- * SMP scalability work:
- *    Copyright (C) 2001 Anton Blanchard <anton@au.ibm.com>, IBM
- *
- * 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/machdep.h>
-#include <asm/pgtable.h>
-#include <asm/mmu.h>
-#include <asm/mmu_context.h>
-#include <asm/abs_addr.h>
-#include <linux/spinlock.h>
-
-#include "call_hpt.h"
-
-static spinlock_t iSeries_hlocks[64] __cacheline_aligned_in_smp;
-
-/*
- * Very primitive algorithm for picking up a lock
- */
-static inline void iSeries_hlock(unsigned long slot)
-{
-        if (slot & 0x8)
-                slot = ~slot;
-        spin_lock(&iSeries_hlocks[(slot >> 4) & 0x3f]);
-}
-
-static inline void iSeries_hunlock(unsigned long slot)
-{
-        if (slot & 0x8)
-                slot = ~slot;
-        spin_unlock(&iSeries_hlocks[(slot >> 4) & 0x3f]);
-}
-
-static long iSeries_hpte_insert(unsigned long hpte_group, unsigned long va,
-                         unsigned long pa, unsigned long rflags,
-                         unsigned long vflags, int psize, int ssize)
-{
-        long slot;
-        struct hash_pte lhpte;
-        int secondary = 0;
-
-        BUG_ON(psize != MMU_PAGE_4K);
-
-        /*
-         * The hypervisor tries both primary and secondary.
-         * If we are being called to insert in the secondary,
-         * it means we have already tried both primary and secondary,
-         * so we return failure immediately.
-         */
-        if (vflags & HPTE_V_SECONDARY)
-                return -1;
-
-        iSeries_hlock(hpte_group);
-
-        slot = HvCallHpt_findValid(&lhpte, va >> HW_PAGE_SHIFT);
-        if (unlikely(lhpte.v & HPTE_V_VALID)) {
-                if (vflags & HPTE_V_BOLTED) {
-                        HvCallHpt_setSwBits(slot, 0x10, 0);
-                        HvCallHpt_setPp(slot, PP_RWXX);
-                        iSeries_hunlock(hpte_group);
-                        if (slot < 0)
-                                return 0x8 | (slot & 7);
-                        else
-                                return slot & 7;
-                }
-                BUG();
-        }
-
-        if (slot == -1) { /* No available entry found in either group */
-                iSeries_hunlock(hpte_group);
-                return -1;
-        }
-
-        if (slot < 0) {         /* MSB set means secondary group */
-                vflags |= HPTE_V_SECONDARY;
-                secondary = 1;
-                slot &= 0x7fffffffffffffff;
-        }
-
-
-        lhpte.v = hpte_encode_v(va, MMU_PAGE_4K, MMU_SEGSIZE_256M) |
-                vflags | HPTE_V_VALID;
-        lhpte.r = hpte_encode_r(phys_to_abs(pa), MMU_PAGE_4K) | rflags;
-
-        /* Now fill in the actual HPTE */
-        HvCallHpt_addValidate(slot, secondary, &lhpte);
-
-        iSeries_hunlock(hpte_group);
-
-        return (secondary << 3) | (slot & 7);
-}
-
-static unsigned long iSeries_hpte_getword0(unsigned long slot)
-{
-        struct hash_pte hpte;
-
-        HvCallHpt_get(&hpte, slot);
-        return hpte.v;
-}
-
-static long iSeries_hpte_remove(unsigned long hpte_group)
-{
-        unsigned long slot_offset;
-        int i;
-        unsigned long hpte_v;
-
-        /* Pick a random slot to start at */
-        slot_offset = mftb() & 0x7;
-
-        iSeries_hlock(hpte_group);
-
-        for (i = 0; i < HPTES_PER_GROUP; i++) {
-                hpte_v = iSeries_hpte_getword0(hpte_group + slot_offset);
-
-                if (! (hpte_v & HPTE_V_BOLTED)) {
-                        HvCallHpt_invalidateSetSwBitsGet(hpte_group +
-                                                         slot_offset, 0, 0);
-                        iSeries_hunlock(hpte_group);
-                        return i;
-                }
-
-                slot_offset++;
-                slot_offset &= 0x7;
-        }
-
-        iSeries_hunlock(hpte_group);
-
-        return -1;
-}
-
-/*
- * The HyperVisor expects the "flags" argument in this form:
- *      bits  0..59 : reserved
- *      bit      60 : N
- *      bits 61..63 : PP2,PP1,PP0
- */
-static long iSeries_hpte_updatepp(unsigned long slot, unsigned long newpp,
-                        unsigned long va, int psize, int ssize, int local)
-{
-        struct hash_pte hpte;
-        unsigned long want_v;
-
-        iSeries_hlock(slot);
-
-        HvCallHpt_get(&hpte, slot);
-        want_v = hpte_encode_v(va, MMU_PAGE_4K, MMU_SEGSIZE_256M);
-
-        if (HPTE_V_COMPARE(hpte.v, want_v) && (hpte.v & HPTE_V_VALID)) {
-                /*
-                 * Hypervisor expects bits as NPPP, which is
-                 * different from how they are mapped in our PP.
-                 */
-                HvCallHpt_setPp(slot, (newpp & 0x3) | ((newpp & 0x4) << 1));
-                iSeries_hunlock(slot);
-                return 0;
-        }
-        iSeries_hunlock(slot);
-
-        return -1;
-}
-
-/*
- * Functions used to find the PTE for a particular virtual address.
- * Only used during boot when bolting pages.
- *
- * Input : vpn      : virtual page number
- * Output: PTE index within the page table of the entry
- *         -1 on failure
- */
-static long iSeries_hpte_find(unsigned long vpn)
-{
-        struct hash_pte hpte;
-        long slot;
-
-        /*
-         * The HvCallHpt_findValid interface is as follows:
-         * 0xffffffffffffffff : No entry found.
-         * 0x00000000xxxxxxxx : Entry found in primary group, slot x
-         * 0x80000000xxxxxxxx : Entry found in secondary group, slot x
-         */
-        slot = HvCallHpt_findValid(&hpte, vpn);
-        if (hpte.v & HPTE_V_VALID) {
-                if (slot < 0) {
-                        slot &= 0x7fffffffffffffff;
-                        slot = -slot;
-                }
-        } else
-                slot = -1;
-        return slot;
-}
-
-/*
- * Update the page protection bits. Intended to be used to create
- * guard pages for kernel data structures on pages which are bolted
- * in the HPT. Assumes pages being operated on will not be stolen.
- * Does not work on large pages.
- *
- * No need to lock here because we should be the only user.
- */
-static void iSeries_hpte_updateboltedpp(unsigned long newpp, unsigned long ea,
-                                        int psize, int ssize)
-{
-        unsigned long vsid,va,vpn;
-        long slot;
-
-        BUG_ON(psize != MMU_PAGE_4K);
-
-        vsid = get_kernel_vsid(ea, MMU_SEGSIZE_256M);
-        va = (vsid << 28) | (ea & 0x0fffffff);
-        vpn = va >> HW_PAGE_SHIFT;
-        slot = iSeries_hpte_find(vpn);
-        if (slot == -1)
-                panic("updateboltedpp: Could not find page to bolt\n");
-        HvCallHpt_setPp(slot, newpp);
-}
-
-static void iSeries_hpte_invalidate(unsigned long slot, unsigned long va,
-                                    int psize, int ssize, int local)
-{
-        unsigned long hpte_v;
-        unsigned long avpn = va >> 23;
-        unsigned long flags;
-
-        local_irq_save(flags);
-
-        iSeries_hlock(slot);
-
-        hpte_v = iSeries_hpte_getword0(slot);
-
-        if ((HPTE_V_AVPN_VAL(hpte_v) == avpn) && (hpte_v & HPTE_V_VALID))
-                HvCallHpt_invalidateSetSwBitsGet(slot, 0, 0);
-
-        iSeries_hunlock(slot);
-
-        local_irq_restore(flags);
-}
-
-void __init hpte_init_iSeries(void)
-{
-        int i;
-
-        for (i = 0; i < ARRAY_SIZE(iSeries_hlocks); i++)
-                spin_lock_init(&iSeries_hlocks[i]);
-
-        ppc_md.hpte_invalidate  = iSeries_hpte_invalidate;
-        ppc_md.hpte_updatepp    = iSeries_hpte_updatepp;
-        ppc_md.hpte_updateboltedpp = iSeries_hpte_updateboltedpp;
-        ppc_md.hpte_insert      = iSeries_hpte_insert;
-        ppc_md.hpte_remove      = iSeries_hpte_remove;
-}
diff --git a/arch/powerpc/platforms/iseries/hvcall.S b/arch/powerpc/platforms/iseries/hvcall.S
deleted file mode 100644
index 07ae6ad5f49f..000000000000
--- a/arch/powerpc/platforms/iseries/hvcall.S
+++ /dev/null
@@ -1,94 +0,0 @@
-/*
- * This file contains the code to perform calls to the
- * iSeries LPAR hypervisor
- *
- * 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/processor.h>
-#include <asm/ptrace.h>         /* XXX for STACK_FRAME_OVERHEAD */
-
-        .text
-
-/*
- * Hypervisor call
- *
- * Invoke the iSeries hypervisor via the System Call instruction
- * Parameters are passed to this routine in registers r3 - r10
- *
- * r3 contains the HV function to be called
- * r4-r10 contain the operands to the hypervisor function
- *
- */
-
-_GLOBAL(HvCall)
-_GLOBAL(HvCall0)
-_GLOBAL(HvCall1)
-_GLOBAL(HvCall2)
-_GLOBAL(HvCall3)
-_GLOBAL(HvCall4)
-_GLOBAL(HvCall5)
-_GLOBAL(HvCall6)
-_GLOBAL(HvCall7)
-
-
-        mfcr    r0
-        std     r0,-8(r1)
-        stdu    r1,-(STACK_FRAME_OVERHEAD+16)(r1)
-
-        /* r0 = 0xffffffffffffffff indicates a hypervisor call */
-
-        li      r0,-1
-
-        /* Invoke the hypervisor */
-
-        sc
-
-        ld      r1,0(r1)
-        ld      r0,-8(r1)
-        mtcrf   0xff,r0
-
-        /*  return to caller, return value in r3 */
-
-        blr
-
-_GLOBAL(HvCall0Ret16)
-_GLOBAL(HvCall1Ret16)
-_GLOBAL(HvCall2Ret16)
-_GLOBAL(HvCall3Ret16)
-_GLOBAL(HvCall4Ret16)
-_GLOBAL(HvCall5Ret16)
-_GLOBAL(HvCall6Ret16)
-_GLOBAL(HvCall7Ret16)
-
-        mfcr    r0
-        std     r0,-8(r1)
-        std     r31,-16(r1)
-        stdu    r1,-(STACK_FRAME_OVERHEAD+32)(r1)
-
-        mr      r31,r4
-        li      r0,-1
-        mr      r4,r5
-        mr      r5,r6
-        mr      r6,r7
-        mr      r7,r8
-        mr      r8,r9
-        mr      r9,r10
-
-        sc
-
-        std     r3,0(r31)
-        std     r4,8(r31)
-
-        mr      r3,r5
-
-        ld      r1,0(r1)
-        ld      r0,-8(r1)
-        mtcrf   0xff,r0
-        ld      r31,-16(r1)
-
-        blr
diff --git a/arch/powerpc/platforms/iseries/hvlog.c b/arch/powerpc/platforms/iseries/hvlog.c
deleted file mode 100644
index f476d71194fa..000000000000
--- a/arch/powerpc/platforms/iseries/hvlog.c
+++ /dev/null
@@ -1,35 +0,0 @@
-/*
- * Copyright (C) 2001  Mike Corrigan 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.
- */
-
-#include <asm/page.h>
-#include <asm/abs_addr.h>
-#include <asm/iseries/hv_call.h>
-#include <asm/iseries/hv_call_sc.h>
-#include <asm/iseries/hv_types.h>
-
-
-void HvCall_writeLogBuffer(const void *buffer, u64 len)
-{
-        struct HvLpBufferList hv_buf;
-        u64 left_this_page;
-        u64 cur = virt_to_abs(buffer);
-
-        while (len) {
-                hv_buf.addr = cur;
-                left_this_page = ((cur & HW_PAGE_MASK) + HW_PAGE_SIZE) - cur;
-                if (left_this_page > len)
-                        left_this_page = len;
-                hv_buf.len = left_this_page;
-                len -= left_this_page;
-                HvCall2(HvCallBaseWriteLogBuffer,
-                                virt_to_abs(&hv_buf),
-                                left_this_page);
-                cur = (cur & HW_PAGE_MASK) + HW_PAGE_SIZE;
-        }
-}
diff --git a/arch/powerpc/platforms/iseries/hvlpconfig.c b/arch/powerpc/platforms/iseries/hvlpconfig.c
deleted file mode 100644
index f62a0c5fa670..000000000000
--- a/arch/powerpc/platforms/iseries/hvlpconfig.c
+++ /dev/null
@@ -1,39 +0,0 @@
-/*
- * Copyright (C) 2001  Kyle A. Lucke, 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.
- * 
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- * 
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
- */
-
-#include <linux/export.h>
-#include <asm/iseries/hv_lp_config.h>
-#include "it_lp_naca.h"
-
-HvLpIndex HvLpConfig_getLpIndex_outline(void)
-{
-        return HvLpConfig_getLpIndex();
-}
-EXPORT_SYMBOL(HvLpConfig_getLpIndex_outline);
-
-HvLpIndex HvLpConfig_getLpIndex(void)
-{
-        return itLpNaca.xLpIndex;
-}
-EXPORT_SYMBOL(HvLpConfig_getLpIndex);
-
-HvLpIndex HvLpConfig_getPrimaryLpIndex(void)
-{
-        return itLpNaca.xPrimaryLpIndex;
-}
-EXPORT_SYMBOL_GPL(HvLpConfig_getPrimaryLpIndex);
diff --git a/arch/powerpc/platforms/iseries/iommu.c b/arch/powerpc/platforms/iseries/iommu.c
deleted file mode 100644
index 2f3d9110248c..000000000000
--- a/arch/powerpc/platforms/iseries/iommu.c
+++ /dev/null
@@ -1,260 +0,0 @@
-/*
- * Copyright (C) 2001 Mike Corrigan & Dave Engebretsen, IBM Corporation
- *
- * Rewrite, cleanup:
- *
- * Copyright (C) 2004 Olof Johansson <olof@lixom.net>, IBM Corporation
- * Copyright (C) 2006 Olof Johansson <olof@lixom.net>
- *
- * Dynamic DMA mapping support, iSeries-specific parts.
- *
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
- */
-
-#include <linux/types.h>
-#include <linux/dma-mapping.h>
-#include <linux/list.h>
-#include <linux/pci.h>
-#include <linux/export.h>
-#include <linux/slab.h>
-
-#include <asm/iommu.h>
-#include <asm/vio.h>
-#include <asm/tce.h>
-#include <asm/machdep.h>
-#include <asm/abs_addr.h>
-#include <asm/prom.h>
-#include <asm/pci-bridge.h>
-#include <asm/iseries/hv_call_xm.h>
-#include <asm/iseries/hv_call_event.h>
-#include <asm/iseries/iommu.h>
-
-static int tce_build_iSeries(struct iommu_table *tbl, long index, long npages,
-                unsigned long uaddr, enum dma_data_direction direction,
-                struct dma_attrs *attrs)
-{
-        u64 rc;
-        u64 tce, rpn;
-
-        while (npages--) {
-                rpn = virt_to_abs(uaddr) >> TCE_SHIFT;
-                tce = (rpn & TCE_RPN_MASK) << TCE_RPN_SHIFT;
-
-                if (tbl->it_type == TCE_VB) {
-                        /* Virtual Bus */
-                        tce |= TCE_VALID|TCE_ALLIO;
-                        if (direction != DMA_TO_DEVICE)
-                                tce |= TCE_VB_WRITE;
-                } else {
-                        /* PCI Bus */
-                        tce |= TCE_PCI_READ; /* Read allowed */
-                        if (direction != DMA_TO_DEVICE)
-                                tce |= TCE_PCI_WRITE;
-                }
-
-                rc = HvCallXm_setTce((u64)tbl->it_index, (u64)index, tce);
-                if (rc)
-                        panic("PCI_DMA: HvCallXm_setTce failed, Rc: 0x%llx\n",
-                                        rc);
-                index++;
-                uaddr += TCE_PAGE_SIZE;
-        }
-        return 0;
-}
-
-static void tce_free_iSeries(struct iommu_table *tbl, long index, long npages)
-{
-        u64 rc;
-
-        while (npages--) {
-                rc = HvCallXm_setTce((u64)tbl->it_index, (u64)index, 0);
-                if (rc)
-                        panic("PCI_DMA: HvCallXm_setTce failed, Rc: 0x%llx\n",
-                                        rc);
-                index++;
-        }
-}
-
-/*
- * Structure passed to HvCallXm_getTceTableParms
- */
-struct iommu_table_cb {
-        unsigned long   itc_busno;      /* Bus number for this tce table */
-        unsigned long   itc_start;      /* Will be NULL for secondary */
-        unsigned long   itc_totalsize;  /* Size (in pages) of whole table */
-        unsigned long   itc_offset;     /* Index into real tce table of the
-                                           start of our section */
-        unsigned long   itc_size;       /* Size (in pages) of our section */
-        unsigned long   itc_index;      /* Index of this tce table */
-        unsigned short  itc_maxtables;  /* Max num of tables for partition */
-        unsigned char   itc_virtbus;    /* Flag to indicate virtual bus */
-        unsigned char   itc_slotno;     /* IOA Tce Slot Index */
-        unsigned char   itc_rsvd[4];
-};
-
-/*
- * Call Hv with the architected data structure to get TCE table info.
- * info. Put the returned data into the Linux representation of the
- * TCE table data.
- * The Hardware Tce table comes in three flavors.
- * 1. TCE table shared between Buses.
- * 2. TCE table per Bus.
- * 3. TCE Table per IOA.
- */
-void iommu_table_getparms_iSeries(unsigned long busno,
-                                  unsigned char slotno,
-                                  unsigned char virtbus,
-                                  struct iommu_table* tbl)
-{
-        struct iommu_table_cb *parms;
-
-        parms = kzalloc(sizeof(*parms), GFP_KERNEL);
-        if (parms == NULL)
-                panic("PCI_DMA: TCE Table Allocation failed.");
-
-        parms->itc_busno = busno;
-        parms->itc_slotno = slotno;
-        parms->itc_virtbus = virtbus;
-
-        HvCallXm_getTceTableParms(iseries_hv_addr(parms));
-
-        if (parms->itc_size == 0)
-                panic("PCI_DMA: parms->size is zero, parms is 0x%p", parms);
-
-        /* itc_size is in pages worth of table, it_size is in # of entries */
-        tbl->it_size = (parms->itc_size * TCE_PAGE_SIZE) / TCE_ENTRY_SIZE;
-        tbl->it_busno = parms->itc_busno;
-        tbl->it_offset = parms->itc_offset;
-        tbl->it_index = parms->itc_index;
-        tbl->it_blocksize = 1;
-        tbl->it_type = virtbus ? TCE_VB : TCE_PCI;
-
-        kfree(parms);
-}
-
-
-#ifdef CONFIG_PCI
-/*
- * This function compares the known tables to find an iommu_table
- * that has already been built for hardware TCEs.
- */
-static struct iommu_table *iommu_table_find(struct iommu_table * tbl)
-{
-        struct device_node *node;
-
-        for (node = NULL; (node = of_find_all_nodes(node)); ) {
-                struct pci_dn *pdn = PCI_DN(node);
-                struct iommu_table *it;
-
-                if (pdn == NULL)
-                        continue;
-                it = pdn->iommu_table;
-                if ((it != NULL) &&
-                    (it->it_type == TCE_PCI) &&
-                    (it->it_offset == tbl->it_offset) &&
-                    (it->it_index == tbl->it_index) &&
-                    (it->it_size == tbl->it_size)) {
-                        of_node_put(node);
-                        return it;
-                }
-        }
-        return NULL;
-}
-
-
-static void pci_dma_dev_setup_iseries(struct pci_dev *pdev)
-{
-        struct iommu_table *tbl;
-        struct device_node *dn = pci_device_to_OF_node(pdev);
-        struct pci_dn *pdn = PCI_DN(dn);
-        const u32 *lsn = of_get_property(dn, "linux,logical-slot-number", NULL);
-
-        BUG_ON(lsn == NULL);
-
-        tbl = kzalloc(sizeof(struct iommu_table), GFP_KERNEL);
-
-        iommu_table_getparms_iSeries(pdn->busno, *lsn, 0, tbl);
-
-        /* Look for existing tce table */
-        pdn->iommu_table = iommu_table_find(tbl);
-        if (pdn->iommu_table == NULL)
-                pdn->iommu_table = iommu_init_table(tbl, -1);
-        else
-                kfree(tbl);
-        set_iommu_table_base(&pdev->dev, pdn->iommu_table);
-}
-#else
-#define pci_dma_dev_setup_iseries       NULL
-#endif
-
-static struct iommu_table veth_iommu_table;
-static struct iommu_table vio_iommu_table;
-
-void *iseries_hv_alloc(size_t size, dma_addr_t *dma_handle, gfp_t flag)
-{
-        return iommu_alloc_coherent(NULL, &vio_iommu_table, size, dma_handle,
-                                DMA_BIT_MASK(32), flag, -1);
-}
-EXPORT_SYMBOL_GPL(iseries_hv_alloc);
-
-void iseries_hv_free(size_t size, void *vaddr, dma_addr_t dma_handle)
-{
-        iommu_free_coherent(&vio_iommu_table, size, vaddr, dma_handle);
-}
-EXPORT_SYMBOL_GPL(iseries_hv_free);
-
-dma_addr_t iseries_hv_map(void *vaddr, size_t size,
-                        enum dma_data_direction direction)
-{
-        return iommu_map_page(NULL, &vio_iommu_table, virt_to_page(vaddr),
-                              (unsigned long)vaddr % PAGE_SIZE, size,
-                              DMA_BIT_MASK(32), direction, NULL);
-}
-
-void iseries_hv_unmap(dma_addr_t dma_handle, size_t size,
-                        enum dma_data_direction direction)
-{
-        iommu_unmap_page(&vio_iommu_table, dma_handle, size, direction, NULL);
-}
-
-void __init iommu_vio_init(void)
-{
-        iommu_table_getparms_iSeries(255, 0, 0xff, &veth_iommu_table);
-        veth_iommu_table.it_size /= 2;
-        vio_iommu_table = veth_iommu_table;
-        vio_iommu_table.it_offset += veth_iommu_table.it_size;
-
-        if (!iommu_init_table(&veth_iommu_table, -1))
-                printk("Virtual Bus VETH TCE table failed.\n");
-        if (!iommu_init_table(&vio_iommu_table, -1))
-                printk("Virtual Bus VIO TCE table failed.\n");
-}
-
-struct iommu_table *vio_build_iommu_table_iseries(struct vio_dev *dev)
-{
-        if (strcmp(dev->type, "network") == 0)
-                return &veth_iommu_table;
-        return &vio_iommu_table;
-}
-
-void iommu_init_early_iSeries(void)
-{
-        ppc_md.tce_build = tce_build_iSeries;
-        ppc_md.tce_free  = tce_free_iSeries;
-
-        ppc_md.pci_dma_dev_setup = pci_dma_dev_setup_iseries;
-        set_pci_dma_ops(&dma_iommu_ops);
-}
diff --git a/arch/powerpc/platforms/iseries/ipl_parms.h b/arch/powerpc/platforms/iseries/ipl_parms.h
deleted file mode 100644
index 83e4ca42fc57..000000000000
--- a/arch/powerpc/platforms/iseries/ipl_parms.h
+++ /dev/null
@@ -1,68 +0,0 @@
-/*
- * Copyright (C) 2001  Mike Corrigan 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.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
- */
-#ifndef _ISERIES_IPL_PARMS_H
-#define _ISERIES_IPL_PARMS_H
-
-/*
- *      This struct maps the IPL Parameters DMA'd from the SP.
- *
- * Warning:
- *      This data must map in exactly 64 bytes and match the architecture for
- *      the IPL parms
- */
-
-#include <asm/types.h>
-
-struct ItIplParmsReal {
-        u8      xFormat;                // Defines format of IplParms   x00-x00
-        u8      xRsvd01:6;              // Reserved                     x01-x01
-        u8      xAlternateSearch:1;     // Alternate search indicator   ...
-        u8      xUaSupplied:1;          // UA Supplied on programmed IPL...
-        u8      xLsUaFormat;            // Format byte for UA           x02-x02
-        u8      xRsvd02;                // Reserved                     x03-x03
-        u32     xLsUa;                  // LS UA                        x04-x07
-        u32     xUnusedLsLid;           // First OS LID to load         x08-x0B
-        u16     xLsBusNumber;           // LS Bus Number                x0C-x0D
-        u8      xLsCardAdr;             // LS Card Address              x0E-x0E
-        u8      xLsBoardAdr;            // LS Board Address             x0F-x0F
-        u32     xRsvd03;                // Reserved                     x10-x13
-        u8      xSpcnPresent:1;         // SPCN present                 x14-x14
-        u8      xCpmPresent:1;          // CPM present                  ...
-        u8      xRsvd04:6;              // Reserved                     ...
-        u8      xRsvd05:4;              // Reserved                     x15-x15
-        u8      xKeyLock:4;             // Keylock setting              ...
-        u8      xRsvd06:6;              // Reserved                     x16-x16
-        u8      xIplMode:2;             // Ipl mode (A|B|C|D)           ...
-        u8      xHwIplType;             // Fast v slow v slow EC HW IPL x17-x17
-        u16     xCpmEnabledIpl:1;       // CPM in effect when IPL initiatedx18-x19
-        u16     xPowerOnResetIpl:1;     // Indicate POR condition       ...
-        u16     xMainStorePreserved:1;  // Main Storage is preserved    ...
-        u16     xRsvd07:13;             // Reserved                     ...
-        u16     xIplSource:16;          // Ipl source                   x1A-x1B
-        u8      xIplReason:8;           // Reason for this IPL          x1C-x1C
-        u8      xRsvd08;                // Reserved                     x1D-x1D
-        u16     xRsvd09;                // Reserved                     x1E-x1F
-        u16     xSysBoxType;            // System Box Type              x20-x21
-        u16     xSysProcType;           // System Processor Type        x22-x23
-        u32     xRsvd10;                // Reserved                     x24-x27
-        u64     xRsvd11;                // Reserved                     x28-x2F
-        u64     xRsvd12;                // Reserved                     x30-x37
-        u64     xRsvd13;                // Reserved                     x38-x3F
-};
-
-#endif /* _ISERIES_IPL_PARMS_H */
diff --git a/arch/powerpc/platforms/iseries/irq.c b/arch/powerpc/platforms/iseries/irq.c
deleted file mode 100644
index b2103453eb01..000000000000
--- a/arch/powerpc/platforms/iseries/irq.c
+++ /dev/null
@@ -1,400 +0,0 @@
-/*
- * This module supports the iSeries PCI bus interrupt handling
- * Copyright (C) 20yy  <Robert L Holtorf> <IBM Corp>
- * Copyright (C) 2004-2005 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.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the:
- * Free Software Foundation, Inc.,
- * 59 Temple Place, Suite 330,
- * Boston, MA  02111-1307  USA
- *
- * Change Activity:
- *   Created, December 13, 2000 by Wayne Holm
- * End Change Activity
- */
-#include <linux/pci.h>
-#include <linux/init.h>
-#include <linux/threads.h>
-#include <linux/smp.h>
-#include <linux/param.h>
-#include <linux/string.h>
-#include <linux/bootmem.h>
-#include <linux/irq.h>
-#include <linux/spinlock.h>
-
-#include <asm/paca.h>
-#include <asm/iseries/hv_types.h>
-#include <asm/iseries/hv_lp_event.h>
-#include <asm/iseries/hv_call_xm.h>
-#include <asm/iseries/it_lp_queue.h>
-
-#include "irq.h"
-#include "pci.h"
-#include "call_pci.h"
-
-#ifdef CONFIG_PCI
-
-enum pci_event_type {
-        pe_bus_created          = 0,    /* PHB has been created */
-        pe_bus_error            = 1,    /* PHB has failed */
-        pe_bus_failed           = 2,    /* Msg to Secondary, Primary failed bus */
-        pe_node_failed          = 4,    /* Multi-adapter bridge has failed */
-        pe_node_recovered       = 5,    /* Multi-adapter bridge has recovered */
-        pe_bus_recovered        = 12,   /* PHB has been recovered */
-        pe_unquiese_bus         = 18,   /* Secondary bus unqiescing */
-        pe_bridge_error         = 21,   /* Bridge Error */
-        pe_slot_interrupt       = 22    /* Slot interrupt */
-};
-
-struct pci_event {
-        struct HvLpEvent event;
-        union {
-                u64 __align;            /* Align on an 8-byte boundary */
-                struct {
-                        u32             fisr;
-                        HvBusNumber     bus_number;
-                        HvSubBusNumber  sub_bus_number;
-                        HvAgentId       dev_id;
-                } slot;
-                struct {
-                        HvBusNumber     bus_number;
-                        HvSubBusNumber  sub_bus_number;
-                } bus;
-                struct {
-                        HvBusNumber     bus_number;
-                        HvSubBusNumber  sub_bus_number;
-                        HvAgentId       dev_id;
-                } node;
-        } data;
-};
-
-static DEFINE_SPINLOCK(pending_irqs_lock);
-static int num_pending_irqs;
-static int pending_irqs[NR_IRQS];
-
-static void int_received(struct pci_event *event)
-{
-        int irq;
-
-        switch (event->event.xSubtype) {
-        case pe_slot_interrupt:
-                irq = event->event.xCorrelationToken;
-                if (irq < NR_IRQS) {
-                        spin_lock(&pending_irqs_lock);
-                        pending_irqs[irq]++;
-                        num_pending_irqs++;
-                        spin_unlock(&pending_irqs_lock);
-                } else {
-                        printk(KERN_WARNING "int_received: bad irq number %d\n",
-                                        irq);
-                        HvCallPci_eoi(event->data.slot.bus_number,
-                                        event->data.slot.sub_bus_number,
-                                        event->data.slot.dev_id);
-                }
-                break;
-                /* Ignore error recovery events for now */
-        case pe_bus_created:
-                printk(KERN_INFO "int_received: system bus %d created\n",
-                        event->data.bus.bus_number);
-                break;
-        case pe_bus_error:
-        case pe_bus_failed:
-                printk(KERN_INFO "int_received: system bus %d failed\n",
-                        event->data.bus.bus_number);
-                break;
-        case pe_bus_recovered:
-        case pe_unquiese_bus:
-                printk(KERN_INFO "int_received: system bus %d recovered\n",
-                        event->data.bus.bus_number);
-                break;
-        case pe_node_failed:
-        case pe_bridge_error:
-                printk(KERN_INFO
-                        "int_received: multi-adapter bridge %d/%d/%d failed\n",
-                        event->data.node.bus_number,
-                        event->data.node.sub_bus_number,
-                        event->data.node.dev_id);
-                break;
-        case pe_node_recovered:
-                printk(KERN_INFO
-                        "int_received: multi-adapter bridge %d/%d/%d recovered\n",
-                        event->data.node.bus_number,
-                        event->data.node.sub_bus_number,
-                        event->data.node.dev_id);
-                break;
-        default:
-                printk(KERN_ERR
-                        "int_received: unrecognized event subtype 0x%x\n",
-                        event->event.xSubtype);
-                break;
-        }
-}
-
-static void pci_event_handler(struct HvLpEvent *event)
-{
-        if (event && (event->xType == HvLpEvent_Type_PciIo)) {
-                if (hvlpevent_is_int(event))
-                        int_received((struct pci_event *)event);
-                else
-                        printk(KERN_ERR
-                                "pci_event_handler: unexpected ack received\n");
-        } else if (event)
-                printk(KERN_ERR
-                        "pci_event_handler: Unrecognized PCI event type 0x%x\n",
-                        (int)event->xType);
-        else
-                printk(KERN_ERR "pci_event_handler: NULL event received\n");
-}
-
-#define REAL_IRQ_TO_SUBBUS(irq) (((irq) >> 14) & 0xff)
-#define REAL_IRQ_TO_BUS(irq)    ((((irq) >> 6) & 0xff) + 1)
-#define REAL_IRQ_TO_IDSEL(irq)  ((((irq) >> 3) & 7) + 1)
-#define REAL_IRQ_TO_FUNC(irq)   ((irq) & 7)
-
-/*
- * This will be called by device drivers (via enable_IRQ)
- * to enable INTA in the bridge interrupt status register.
- */
-static void iseries_enable_IRQ(struct irq_data *d)
-{
-        u32 bus, dev_id, function, mask;
-        const u32 sub_bus = 0;
-        unsigned int rirq = (unsigned int)irqd_to_hwirq(d);
-
-        /* The IRQ has already been locked by the caller */
-        bus = REAL_IRQ_TO_BUS(rirq);
-        function = REAL_IRQ_TO_FUNC(rirq);
-        dev_id = (REAL_IRQ_TO_IDSEL(rirq) << 4) + function;
-
-        /* Unmask secondary INTA */
-        mask = 0x80000000;
-        HvCallPci_unmaskInterrupts(bus, sub_bus, dev_id, mask);
-}
-
-/* This is called by iseries_activate_IRQs */
-static unsigned int iseries_startup_IRQ(struct irq_data *d)
-{
-        u32 bus, dev_id, function, mask;
-        const u32 sub_bus = 0;
-        unsigned int rirq = (unsigned int)irqd_to_hwirq(d);
-
-        bus = REAL_IRQ_TO_BUS(rirq);
-        function = REAL_IRQ_TO_FUNC(rirq);
-        dev_id = (REAL_IRQ_TO_IDSEL(rirq) << 4) + function;
-
-        /* Link the IRQ number to the bridge */
-        HvCallXm_connectBusUnit(bus, sub_bus, dev_id, d->irq);
-
-        /* Unmask bridge interrupts in the FISR */
-        mask = 0x01010000 << function;
-        HvCallPci_unmaskFisr(bus, sub_bus, dev_id, mask);
-        iseries_enable_IRQ(d);
-        return 0;
-}
-
-/*
- * This is called out of iSeries_fixup to activate interrupt
- * generation for usable slots
- */
-void __init iSeries_activate_IRQs()
-{
-        int irq;
-        unsigned long flags;
-
-        for_each_irq (irq) {
-                struct irq_desc *desc = irq_to_desc(irq);
-                struct irq_chip *chip;
-
-                if (!desc)
-                        continue;
-
-                chip = irq_desc_get_chip(desc);
-                if (chip && chip->irq_startup) {
-                        raw_spin_lock_irqsave(&desc->lock, flags);
-                        chip->irq_startup(&desc->irq_data);
-                        raw_spin_unlock_irqrestore(&desc->lock, flags);
-                }
-        }
-}
-
-/*  this is not called anywhere currently */
-static void iseries_shutdown_IRQ(struct irq_data *d)
-{
-        u32 bus, dev_id, function, mask;
-        const u32 sub_bus = 0;
-        unsigned int rirq = (unsigned int)irqd_to_hwirq(d);
-
-        /* irq should be locked by the caller */
-        bus = REAL_IRQ_TO_BUS(rirq);
-        function = REAL_IRQ_TO_FUNC(rirq);
-        dev_id = (REAL_IRQ_TO_IDSEL(rirq) << 4) + function;
-
-        /* Invalidate the IRQ number in the bridge */
-        HvCallXm_connectBusUnit(bus, sub_bus, dev_id, 0);
-
-        /* Mask bridge interrupts in the FISR */
-        mask = 0x01010000 << function;
-        HvCallPci_maskFisr(bus, sub_bus, dev_id, mask);
-}
-
-/*
- * This will be called by device drivers (via disable_IRQ)
- * to disable INTA in the bridge interrupt status register.
- */
-static void iseries_disable_IRQ(struct irq_data *d)
-{
-        u32 bus, dev_id, function, mask;
-        const u32 sub_bus = 0;
-        unsigned int rirq = (unsigned int)irqd_to_hwirq(d);
-
-        /* The IRQ has already been locked by the caller */
-        bus = REAL_IRQ_TO_BUS(rirq);
-        function = REAL_IRQ_TO_FUNC(rirq);
-        dev_id = (REAL_IRQ_TO_IDSEL(rirq) << 4) + function;
-
-        /* Mask secondary INTA   */
-        mask = 0x80000000;
-        HvCallPci_maskInterrupts(bus, sub_bus, dev_id, mask);
-}
-
-static void iseries_end_IRQ(struct irq_data *d)
-{
-        unsigned int rirq = (unsigned int)irqd_to_hwirq(d);
-
-        HvCallPci_eoi(REAL_IRQ_TO_BUS(rirq), REAL_IRQ_TO_SUBBUS(rirq),
-                (REAL_IRQ_TO_IDSEL(rirq) << 4) + REAL_IRQ_TO_FUNC(rirq));
-}
-
-static struct irq_chip iseries_pic = {
-        .name           = "iSeries",
-        .irq_startup    = iseries_startup_IRQ,
-        .irq_shutdown   = iseries_shutdown_IRQ,
-        .irq_unmask     = iseries_enable_IRQ,
-        .irq_mask       = iseries_disable_IRQ,
-        .irq_eoi        = iseries_end_IRQ
-};
-
-/*
- * This is called out of iSeries_scan_slot to allocate an IRQ for an EADS slot
- * It calculates the irq value for the slot.
- * Note that sub_bus is always 0 (at the moment at least).
- */
-int __init iSeries_allocate_IRQ(HvBusNumber bus,
-                HvSubBusNumber sub_bus, u32 bsubbus)
-{
-        unsigned int realirq;
-        u8 idsel = ISERIES_GET_DEVICE_FROM_SUBBUS(bsubbus);
-        u8 function = ISERIES_GET_FUNCTION_FROM_SUBBUS(bsubbus);
-
-        realirq = (((((sub_bus << 8) + (bus - 1)) << 3) + (idsel - 1)) << 3)
-                + function;
-
-        return irq_create_mapping(NULL, realirq);
-}
-
-#endif /* CONFIG_PCI */
-
-/*
- * Get the next pending IRQ.
- */
-unsigned int iSeries_get_irq(void)
-{
-        int irq = NO_IRQ_IGNORE;
-
-#ifdef CONFIG_SMP
-        if (get_lppaca()->int_dword.fields.ipi_cnt) {
-                get_lppaca()->int_dword.fields.ipi_cnt = 0;
-                smp_ipi_demux();
-        }
-#endif /* CONFIG_SMP */
-        if (hvlpevent_is_pending())
-                process_hvlpevents();
-
-#ifdef CONFIG_PCI
-        if (num_pending_irqs) {
-                spin_lock(&pending_irqs_lock);
-                for (irq = 0; irq < NR_IRQS; irq++) {
-                        if (pending_irqs[irq]) {
-                                pending_irqs[irq]--;
-                                num_pending_irqs--;
-                                break;
-                        }
-                }
-                spin_unlock(&pending_irqs_lock);
-                if (irq >= NR_IRQS)
-                        irq = NO_IRQ_IGNORE;
-        }
-#endif
-
-        return irq;
-}
-
-#ifdef CONFIG_PCI
-
-static int iseries_irq_host_map(struct irq_host *h, unsigned int virq,
-                                irq_hw_number_t hw)
-{
-        irq_set_chip_and_handler(virq, &iseries_pic, handle_fasteoi_irq);
-
-        return 0;
-}
-
-static int iseries_irq_host_match(struct irq_host *h, struct device_node *np)
-{
-        /* Match all */
-        return 1;
-}
-
-static struct irq_host_ops iseries_irq_host_ops = {
-        .map = iseries_irq_host_map,
-        .match = iseries_irq_host_match,
-};
-
-/*
- * This is called by init_IRQ.  set in ppc_md.init_IRQ by iSeries_setup.c
- * It must be called before the bus walk.
- */
-void __init iSeries_init_IRQ(void)
-{
-        /* Register PCI event handler and open an event path */
-        struct irq_host *host;
-        int ret;
-
-        /*
-         * The Hypervisor only allows us up to 256 interrupt
-         * sources (the irq number is passed in a u8).
-         */
-        irq_set_virq_count(256);
-
-        /* Create irq host. No need for a revmap since HV will give us
-         * back our virtual irq number
-         */
-        host = irq_alloc_host(NULL, IRQ_HOST_MAP_NOMAP, 0,
-                              &iseries_irq_host_ops, 0);
-        BUG_ON(host == NULL);
-        irq_set_default_host(host);
-
-        ret = HvLpEvent_registerHandler(HvLpEvent_Type_PciIo,
-                        &pci_event_handler);
-        if (ret == 0) {
-                ret = HvLpEvent_openPath(HvLpEvent_Type_PciIo, 0);
-                if (ret != 0)
-                        printk(KERN_ERR "iseries_init_IRQ: open event path "
-                                        "failed with rc 0x%x\n", ret);
-        } else
-                printk(KERN_ERR "iseries_init_IRQ: register handler "
-                                "failed with rc 0x%x\n", ret);
-}
-
-#endif  /* CONFIG_PCI */
diff --git a/arch/powerpc/platforms/iseries/irq.h b/arch/powerpc/platforms/iseries/irq.h
deleted file mode 100644
index a1c236074034..000000000000
--- a/arch/powerpc/platforms/iseries/irq.h
+++ /dev/null
@@ -1,13 +0,0 @@
-#ifndef _ISERIES_IRQ_H
-#define _ISERIES_IRQ_H
-
-#ifdef CONFIG_PCI
-extern void iSeries_init_IRQ(void);
-extern int  iSeries_allocate_IRQ(HvBusNumber, HvSubBusNumber, u32);
-extern void iSeries_activate_IRQs(void);
-#else
-#define iSeries_init_IRQ        NULL
-#endif
-extern unsigned int iSeries_get_irq(void);
-
-#endif /* _ISERIES_IRQ_H */
diff --git a/arch/powerpc/platforms/iseries/it_exp_vpd_panel.h b/arch/powerpc/platforms/iseries/it_exp_vpd_panel.h
deleted file mode 100644
index 6de9097b7f57..000000000000
--- a/arch/powerpc/platforms/iseries/it_exp_vpd_panel.h
+++ /dev/null
@@ -1,51 +0,0 @@
-/*
- * Copyright (C) 2002  Dave Boutcher 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.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
- */
-#ifndef _PLATFORMS_ISERIES_IT_EXT_VPD_PANEL_H
-#define _PLATFORMS_ISERIES_IT_EXT_VPD_PANEL_H
-
-/*
- *      This struct maps the panel information
- *
- * Warning:
- *      This data must match the architecture for the panel information
- */
-
-#include <asm/types.h>
-
-struct ItExtVpdPanel {
-        /* Definition of the Extended Vpd On Panel Data Area */
-        char    systemSerial[8];
-        char    mfgID[4];
-        char    reserved1[24];
-        char    machineType[4];
-        char    systemID[6];
-        char    somUniqueCnt[4];
-        char    serialNumberCount;
-        char    reserved2[7];
-        u16     bbu3;
-        u16     bbu2;
-        u16     bbu1;
-        char    xLocationLabel[8];
-        u8      xRsvd1[6];
-        u16     xFrameId;
-        u8      xRsvd2[48];
-};
-
-extern struct ItExtVpdPanel     xItExtVpdPanel;
-
-#endif /* _PLATFORMS_ISERIES_IT_EXT_VPD_PANEL_H */
diff --git a/arch/powerpc/platforms/iseries/it_lp_naca.h b/arch/powerpc/platforms/iseries/it_lp_naca.h
deleted file mode 100644
index cf6dcf6ef07b..000000000000
--- a/arch/powerpc/platforms/iseries/it_lp_naca.h
+++ /dev/null
@@ -1,80 +0,0 @@
-/*
- * Copyright (C) 2001  Mike Corrigan 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.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
- */
-#ifndef _PLATFORMS_ISERIES_IT_LP_NACA_H
-#define _PLATFORMS_ISERIES_IT_LP_NACA_H
-
-#include <linux/types.h>
-
-/*
- *      This control block contains the data that is shared between the
- *      hypervisor (PLIC) and the OS.
- */
-
-struct ItLpNaca {
-// CACHE_LINE_1 0x0000 - 0x007F Contains read-only data
-        u32     xDesc;                  // Eye catcher                  x00-x03
-        u16     xSize;                  // Size of this class           x04-x05
-        u16     xIntHdlrOffset;         // Offset to IntHdlr array      x06-x07
-        u8      xMaxIntHdlrEntries;     // Number of entries in array   x08-x08
-        u8      xPrimaryLpIndex;        // LP Index of Primary          x09-x09
-        u8      xServiceLpIndex;        // LP Ind of Service Focal Pointx0A-x0A
-        u8      xLpIndex;               // LP Index                     x0B-x0B
-        u16     xMaxLpQueues;           // Number of allocated queues   x0C-x0D
-        u16     xLpQueueOffset;         // Offset to start of LP queues x0E-x0F
-        u8      xPirEnvironMode;        // Piranha or hardware          x10-x10
-        u8      xPirConsoleMode;        // Piranha console indicator    x11-x11
-        u8      xPirDasdMode;           // Piranha dasd indicator       x12-x12
-        u8      xRsvd1_0[5];            // Reserved for Piranha related x13-x17
-        u8      flags;                  // flags, see below             x18-x1F
-        u8      xSpVpdFormat;           // VPD areas are in CSP format  ...
-        u8      xIntProcRatio;          // Ratio of int procs to procs  ...
-        u8      xRsvd1_2[5];            // Reserved                     ...
-        u16     xRsvd1_3;               // Reserved                     x20-x21
-        u16     xPlicVrmIndex;          // VRM index of PLIC            x22-x23
-        u16     xMinSupportedSlicVrmInd;// Min supported OS VRM index   x24-x25
-        u16     xMinCompatableSlicVrmInd;// Min compatible OS VRM index x26-x27
-        u64     xLoadAreaAddr;          // ER address of load area      x28-x2F
-        u32     xLoadAreaChunks;        // Chunks for the load area     x30-x33
-        u32     xPaseSysCallCRMask;     // Mask used to test CR before  x34-x37
-                                        // doing an ASR switch on PASE
-                                        // system call.
-        u64     xSlicSegmentTablePtr;   // Pointer to Slic seg table.   x38-x3f
-        u8      xRsvd1_4[64];           //                              x40-x7F
-
-// CACHE_LINE_2 0x0080 - 0x00FF Contains local read-write data
-        u8      xRsvd2_0[128];          // Reserved                     x00-x7F
-
-// CACHE_LINE_3-6 0x0100 - 0x02FF Contains LP Queue indicators
-// NB: Padding required to keep xInterruptHdlr at x300 which is required
-// for v4r4 PLIC.
-        u8      xOldLpQueue[128];       // LP Queue needed for v4r4     100-17F
-        u8      xRsvd3_0[384];          // Reserved                     180-2FF
-
-// CACHE_LINE_7-8 0x0300 - 0x03FF Contains the address of the OS interrupt
-//  handlers
-        u64     xInterruptHdlr[32];     // Interrupt handlers           300-x3FF
-};
-
-extern struct ItLpNaca          itLpNaca;
-
-#define ITLPNACA_LPAR           0x80    /* Is LPAR installed on the system */
-#define ITLPNACA_PARTITIONED    0x40    /* Is the system partitioned */
-#define ITLPNACA_HWSYNCEDTBS    0x20    /* Hardware synced TBs */
-#define ITLPNACA_HMTINT         0x10    /* Utilize MHT for interrupts */
-
-#endif /* _PLATFORMS_ISERIES_IT_LP_NACA_H */
diff --git a/arch/powerpc/platforms/iseries/ksyms.c b/arch/powerpc/platforms/iseries/ksyms.c
deleted file mode 100644
index 997e234fb8b7..000000000000
--- a/arch/powerpc/platforms/iseries/ksyms.c
+++ /dev/null
@@ -1,21 +0,0 @@
-/*
- * (C) 2001-2005 PPC 64 Team, 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/export.h>
-
-#include <asm/hw_irq.h>
-#include <asm/iseries/hv_call_sc.h>
-
-EXPORT_SYMBOL(HvCall0);
-EXPORT_SYMBOL(HvCall1);
-EXPORT_SYMBOL(HvCall2);
-EXPORT_SYMBOL(HvCall3);
-EXPORT_SYMBOL(HvCall4);
-EXPORT_SYMBOL(HvCall5);
-EXPORT_SYMBOL(HvCall6);
-EXPORT_SYMBOL(HvCall7);
diff --git a/arch/powerpc/platforms/iseries/lpardata.c b/arch/powerpc/platforms/iseries/lpardata.c
deleted file mode 100644
index 00e0ec813a1c..000000000000
--- a/arch/powerpc/platforms/iseries/lpardata.c
+++ /dev/null
@@ -1,318 +0,0 @@
-/*
- * Copyright 2001 Mike Corrigan, 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/types.h>
-#include <linux/threads.h>
-#include <linux/bitops.h>
-#include <asm/processor.h>
-#include <asm/ptrace.h>
-#include <asm/abs_addr.h>
-#include <asm/lppaca.h>
-#include <asm/paca.h>
-#include <asm/iseries/lpar_map.h>
-#include <asm/iseries/it_lp_queue.h>
-#include <asm/iseries/alpaca.h>
-
-#include "naca.h"
-#include "vpd_areas.h"
-#include "spcomm_area.h"
-#include "ipl_parms.h"
-#include "processor_vpd.h"
-#include "release_data.h"
-#include "it_exp_vpd_panel.h"
-#include "it_lp_naca.h"
-
-/* The HvReleaseData is the root of the information shared between
- * the hypervisor and Linux.
- */
-const struct HvReleaseData hvReleaseData = {
-        .xDesc = 0xc8a5d9c4,    /* "HvRD" ebcdic */
-        .xSize = sizeof(struct HvReleaseData),
-        .xVpdAreasPtrOffset = offsetof(struct naca_struct, xItVpdAreas),
-        .xSlicNacaAddr = &naca,         /* 64-bit Naca address */
-        .xMsNucDataOffset = LPARMAP_PHYS,
-        .xFlags = HVREL_TAGSINACTIVE    /* tags inactive       */
-                                        /* 64 bit              */
-                                        /* shared processors   */
-                                        /* HMT allowed         */
-                  | 6,                  /* TEMP: This allows non-GA driver */
-        .xVrmIndex = 4,                 /* We are v5r2m0               */
-        .xMinSupportedPlicVrmIndex = 3,         /* v5r1m0 */
-        .xMinCompatablePlicVrmIndex = 3,        /* v5r1m0 */
-        .xVrmName = { 0xd3, 0x89, 0x95, 0xa4,   /* "Linux 2.4.64" ebcdic */
-                0xa7, 0x40, 0xf2, 0x4b,
-                0xf4, 0x4b, 0xf6, 0xf4 },
-};
-
-/*
- * The NACA.  The first dword of the naca is required by the iSeries
- * hypervisor to point to itVpdAreas.  The hypervisor finds the NACA
- * through the pointer in hvReleaseData.
- */
-struct naca_struct naca = {
-        .xItVpdAreas = &itVpdAreas,
-        .xRamDisk = 0,
-        .xRamDiskSize = 0,
-};
-
-struct ItLpRegSave {
-        u32     xDesc;          // Eye catcher  "LpRS" ebcdic   000-003
-        u16     xSize;          // Size of this class           004-005
-        u8      xInUse;         // Area is live                 006-007
-        u8      xRsvd1[9];      // Reserved                     007-00F
-
-        u8      xFixedRegSave[352]; // Fixed Register Save Area 010-16F
-        u32     xCTRL;          // Control Register             170-173
-        u32     xDEC;           // Decrementer                  174-177
-        u32     xFPSCR;         // FP Status and Control Reg    178-17B
-        u32     xPVR;           // Processor Version Number     17C-17F
-
-        u64     xMMCR0;         // Monitor Mode Control Reg 0   180-187
-        u32     xPMC1;          // Perf Monitor Counter 1       188-18B
-        u32     xPMC2;          // Perf Monitor Counter 2       18C-18F
-        u32     xPMC3;          // Perf Monitor Counter 3       190-193
-        u32     xPMC4;          // Perf Monitor Counter 4       194-197
-        u32     xPIR;           // Processor ID Reg             198-19B
-
-        u32     xMMCR1;         // Monitor Mode Control Reg 1   19C-19F
-        u32     xMMCRA;         // Monitor Mode Control Reg A   1A0-1A3
-        u32     xPMC5;          // Perf Monitor Counter 5       1A4-1A7
-        u32     xPMC6;          // Perf Monitor Counter 6       1A8-1AB
-        u32     xPMC7;          // Perf Monitor Counter 7       1AC-1AF
-        u32     xPMC8;          // Perf Monitor Counter 8       1B0-1B3
-        u32     xTSC;           // Thread Switch Control        1B4-1B7
-        u32     xTST;           // Thread Switch Timeout        1B8-1BB
-        u32     xRsvd;          // Reserved                     1BC-1BF
-
-        u64     xACCR;          // Address Compare Control Reg  1C0-1C7
-        u64     xIMR;           // Instruction Match Register   1C8-1CF
-        u64     xSDR1;          // Storage Description Reg 1    1D0-1D7
-        u64     xSPRG0;         // Special Purpose Reg General0 1D8-1DF
-        u64     xSPRG1;         // Special Purpose Reg General1 1E0-1E7
-        u64     xSPRG2;         // Special Purpose Reg General2 1E8-1EF
-        u64     xSPRG3;         // Special Purpose Reg General3 1F0-1F7
-        u64     xTB;            // Time Base Register           1F8-1FF
-
-        u64     xFPR[32];       // Floating Point Registers     200-2FF
-
-        u64     xMSR;           // Machine State Register       300-307
-        u64     xNIA;           // Next Instruction Address     308-30F
-
-        u64     xDABR;          // Data Address Breakpoint Reg  310-317
-        u64     xIABR;          // Inst Address Breakpoint Reg  318-31F
-
-        u64     xHID0;          // HW Implementation Dependent0 320-327
-
-        u64     xHID4;          // HW Implementation Dependent4 328-32F
-        u64     xSCOMd;         // SCON Data Reg (SPRG4)        330-337
-        u64     xSCOMc;         // SCON Command Reg (SPRG5)     338-33F
-        u64     xSDAR;          // Sample Data Address Register 340-347
-        u64     xSIAR;          // Sample Inst Address Register 348-34F
-
-        u8      xRsvd3[176];    // Reserved                     350-3FF
-};
-
-extern void system_reset_iSeries(void);
-extern void machine_check_iSeries(void);
-extern void data_access_iSeries(void);
-extern void instruction_access_iSeries(void);
-extern void hardware_interrupt_iSeries(void);
-extern void alignment_iSeries(void);
-extern void program_check_iSeries(void);
-extern void fp_unavailable_iSeries(void);
-extern void decrementer_iSeries(void);
-extern void trap_0a_iSeries(void);
-extern void trap_0b_iSeries(void);
-extern void system_call_iSeries(void);
-extern void single_step_iSeries(void);
-extern void trap_0e_iSeries(void);
-extern void performance_monitor_iSeries(void);
-extern void data_access_slb_iSeries(void);
-extern void instruction_access_slb_iSeries(void);
-
-struct ItLpNaca itLpNaca = {
-        .xDesc = 0xd397d581,            /* "LpNa" ebcdic */
-        .xSize = 0x0400,                /* size of ItLpNaca */
-        .xIntHdlrOffset = 0x0300,       /* offset to int array */
-        .xMaxIntHdlrEntries = 19,       /* # ents */
-        .xPrimaryLpIndex = 0,           /* Part # of primary */
-        .xServiceLpIndex = 0,           /* Part # of serv */
-        .xLpIndex = 0,                  /* Part # of me */
-        .xMaxLpQueues = 0,              /* # of LP queues */
-        .xLpQueueOffset = 0x100,        /* offset of start of LP queues */
-        .xPirEnvironMode = 0,           /* Piranha stuff */
-        .xPirConsoleMode = 0,
-        .xPirDasdMode = 0,
-        .flags = 0,
-        .xSpVpdFormat = 0,
-        .xIntProcRatio = 0,
-        .xPlicVrmIndex = 0,             /* VRM index of PLIC */
-        .xMinSupportedSlicVrmInd = 0,   /* min supported SLIC */
-        .xMinCompatableSlicVrmInd = 0,  /* min compat SLIC */
-        .xLoadAreaAddr = 0,             /* 64-bit addr of load area */
-        .xLoadAreaChunks = 0,           /* chunks for load area */
-        .xPaseSysCallCRMask = 0,        /* PASE mask */
-        .xSlicSegmentTablePtr = 0,      /* seg table */
-        .xOldLpQueue = { 0 },           /* Old LP Queue */
-        .xInterruptHdlr = {
-                (u64)system_reset_iSeries,      /* 0x100 System Reset */
-                (u64)machine_check_iSeries,     /* 0x200 Machine Check */
-                (u64)data_access_iSeries,       /* 0x300 Data Access */
-                (u64)instruction_access_iSeries, /* 0x400 Instruction Access */
-                (u64)hardware_interrupt_iSeries, /* 0x500 External */
-                (u64)alignment_iSeries,         /* 0x600 Alignment */
-                (u64)program_check_iSeries,     /* 0x700 Program Check */
-                (u64)fp_unavailable_iSeries,    /* 0x800 FP Unavailable */
-                (u64)decrementer_iSeries,       /* 0x900 Decrementer */
-                (u64)trap_0a_iSeries,           /* 0xa00 Trap 0A */
-                (u64)trap_0b_iSeries,           /* 0xb00 Trap 0B */
-                (u64)system_call_iSeries,       /* 0xc00 System Call */
-                (u64)single_step_iSeries,       /* 0xd00 Single Step */
-                (u64)trap_0e_iSeries,           /* 0xe00 Trap 0E */
-                (u64)performance_monitor_iSeries,/* 0xf00 Performance Monitor */
-                0,                              /* int 0x1000 */
-                0,                              /* int 0x1010 */
-                0,                              /* int 0x1020 CPU ctls */
-                (u64)hardware_interrupt_iSeries, /* SC Ret Hdlr */
-                (u64)data_access_slb_iSeries,   /* 0x380 D-SLB */
-                (u64)instruction_access_slb_iSeries /* 0x480 I-SLB */
-        }
-};
-
-/* May be filled in by the hypervisor so cannot end up in the BSS */
-static struct ItIplParmsReal xItIplParmsReal __attribute__((__section__(".data")));
-
-/* May be filled in by the hypervisor so cannot end up in the BSS */
-struct ItExtVpdPanel xItExtVpdPanel __attribute__((__section__(".data")));
-
-#define maxPhysicalProcessors 32
-
-struct IoHriProcessorVpd xIoHriProcessorVpd[maxPhysicalProcessors] = {
-        {
-                .xInstCacheOperandSize = 32,
-                .xDataCacheOperandSize = 32,
-                .xProcFreq     = 50000000,
-                .xTimeBaseFreq = 50000000,
-                .xPVR = 0x3600
-        }
-};
-
-/* Space for Main Store Vpd 27,200 bytes */
-/* May be filled in by the hypervisor so cannot end up in the BSS */
-u64    xMsVpd[3400] __attribute__((__section__(".data")));
-
-/* Space for Recovery Log Buffer */
-/* May be filled in by the hypervisor so cannot end up in the BSS */
-static u64    xRecoveryLogBuffer[32] __attribute__((__section__(".data")));
-
-static const struct SpCommArea xSpCommArea = {
-        .xDesc = 0xE2D7C3C2,
-        .xFormat = 1,
-};
-
-static const struct ItLpRegSave iseries_reg_save[] = {
-        [0 ... (NR_CPUS-1)] = {
-                .xDesc = 0xd397d9e2,    /* "LpRS" */
-                .xSize = sizeof(struct ItLpRegSave),
-        },
-};
-
-#define ALPACA_INIT(number)                                             \
-{                                                                       \
-        .lppaca_ptr = &lppaca[number],                                  \
-        .reg_save_ptr = &iseries_reg_save[number],                      \
-}
-
-const struct alpaca alpaca[] = {
-        ALPACA_INIT( 0),
-#if NR_CPUS > 1
-        ALPACA_INIT( 1), ALPACA_INIT( 2), ALPACA_INIT( 3),
-#if NR_CPUS > 4
-        ALPACA_INIT( 4), ALPACA_INIT( 5), ALPACA_INIT( 6), ALPACA_INIT( 7),
-#if NR_CPUS > 8
-        ALPACA_INIT( 8), ALPACA_INIT( 9), ALPACA_INIT(10), ALPACA_INIT(11),
-        ALPACA_INIT(12), ALPACA_INIT(13), ALPACA_INIT(14), ALPACA_INIT(15),
-        ALPACA_INIT(16), ALPACA_INIT(17), ALPACA_INIT(18), ALPACA_INIT(19),
-        ALPACA_INIT(20), ALPACA_INIT(21), ALPACA_INIT(22), ALPACA_INIT(23),
-        ALPACA_INIT(24), ALPACA_INIT(25), ALPACA_INIT(26), ALPACA_INIT(27),
-        ALPACA_INIT(28), ALPACA_INIT(29), ALPACA_INIT(30), ALPACA_INIT(31),
-#if NR_CPUS > 32
-        ALPACA_INIT(32), ALPACA_INIT(33), ALPACA_INIT(34), ALPACA_INIT(35),
-        ALPACA_INIT(36), ALPACA_INIT(37), ALPACA_INIT(38), ALPACA_INIT(39),
-        ALPACA_INIT(40), ALPACA_INIT(41), ALPACA_INIT(42), ALPACA_INIT(43),
-        ALPACA_INIT(44), ALPACA_INIT(45), ALPACA_INIT(46), ALPACA_INIT(47),
-        ALPACA_INIT(48), ALPACA_INIT(49), ALPACA_INIT(50), ALPACA_INIT(51),
-        ALPACA_INIT(52), ALPACA_INIT(53), ALPACA_INIT(54), ALPACA_INIT(55),
-        ALPACA_INIT(56), ALPACA_INIT(57), ALPACA_INIT(58), ALPACA_INIT(59),
-        ALPACA_INIT(60), ALPACA_INIT(61), ALPACA_INIT(62), ALPACA_INIT(63),
-#endif
-#endif
-#endif
-#endif
-};
-
-/* The LparMap data is now located at offset 0x6000 in head.S
- * It was put there so that the HvReleaseData could address it
- * with a 32-bit offset as required by the iSeries hypervisor
- *
- * The Naca has a pointer to the ItVpdAreas.  The hypervisor finds
- * the Naca via the HvReleaseData area.  The HvReleaseData has the
- * offset into the Naca of the pointer to the ItVpdAreas.
- */
-const struct ItVpdAreas itVpdAreas = {
-        .xSlicDesc = 0xc9a3e5c1,                /* "ItVA" */
-        .xSlicSize = sizeof(struct ItVpdAreas),
-        .xSlicVpdEntries = ItVpdMaxEntries,     /* # VPD array entries */
-        .xSlicDmaEntries = ItDmaMaxEntries,     /* # DMA array entries */
-        .xSlicMaxLogicalProcs = NR_CPUS * 2,    /* Max logical procs */
-        .xSlicMaxPhysicalProcs = maxPhysicalProcessors, /* Max physical procs */
-        .xSlicDmaToksOffset = offsetof(struct ItVpdAreas, xPlicDmaToks),
-        .xSlicVpdAdrsOffset = offsetof(struct ItVpdAreas, xSlicVpdAdrs),
-        .xSlicDmaLensOffset = offsetof(struct ItVpdAreas, xPlicDmaLens),
-        .xSlicVpdLensOffset = offsetof(struct ItVpdAreas, xSlicVpdLens),
-        .xSlicMaxSlotLabels = 0,                /* max slot labels */
-        .xSlicMaxLpQueues = 1,                  /* max LP queues */
-        .xPlicDmaLens = { 0 },                  /* DMA lengths */
-        .xPlicDmaToks = { 0 },                  /* DMA tokens */
-        .xSlicVpdLens = {                       /* VPD lengths */
-                0,0,0,                  /*  0 - 2 */
-                sizeof(xItExtVpdPanel), /*       3 Extended VPD   */
-                sizeof(struct alpaca),  /*       4 length of (fake) Paca  */
-                0,                      /*       5 */
-                sizeof(struct ItIplParmsReal),/* 6 length of IPL parms */
-                26992,                  /*       7 length of MS VPD */
-                0,                      /*       8 */
-                sizeof(struct ItLpNaca),/*       9 length of LP Naca */
-                0,                      /*      10 */
-                256,                    /*      11 length of Recovery Log Buf */
-                sizeof(struct SpCommArea), /*   12 length of SP Comm Area */
-                0,0,0,                  /* 13 - 15 */
-                sizeof(struct IoHriProcessorVpd),/* 16 length of Proc Vpd */
-                0,0,0,0,0,0,            /* 17 - 22  */
-                sizeof(struct hvlpevent_queue), /* 23 length of Lp Queue */
-                0,0                     /* 24 - 25 */
-                },
-        .xSlicVpdAdrs = {                       /* VPD addresses */
-                0,0,0,                  /*       0 -  2 */
-                &xItExtVpdPanel,        /*       3 Extended VPD */
-                &alpaca[0],             /*       4 first (fake) Paca */
-                0,                      /*       5 */
-                &xItIplParmsReal,       /*       6 IPL parms */
-                &xMsVpd,                /*       7 MS Vpd */
-                0,                      /*       8 */
-                &itLpNaca,              /*       9 LpNaca */
-                0,                      /*      10 */
-                &xRecoveryLogBuffer,    /*      11 Recovery Log Buffer */
-                &xSpCommArea,           /*      12 SP Comm Area */
-                0,0,0,                  /* 13 - 15 */
-                &xIoHriProcessorVpd,    /*      16 Proc Vpd */
-                0,0,0,0,0,0,            /* 17 - 22 */
-                &hvlpevent_queue,       /*      23 Lp Queue */
-                0,0
-        }
-};
diff --git a/arch/powerpc/platforms/iseries/lpevents.c b/arch/powerpc/platforms/iseries/lpevents.c
deleted file mode 100644
index 202e22798d30..000000000000
--- a/arch/powerpc/platforms/iseries/lpevents.c
+++ /dev/null
@@ -1,341 +0,0 @@
-/*
- * Copyright (C) 2001 Mike Corrigan  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.
- */
-
-#include <linux/stddef.h>
-#include <linux/kernel.h>
-#include <linux/sched.h>
-#include <linux/bootmem.h>
-#include <linux/seq_file.h>
-#include <linux/proc_fs.h>
-#include <linux/export.h>
-
-#include <asm/system.h>
-#include <asm/paca.h>
-#include <asm/firmware.h>
-#include <asm/iseries/it_lp_queue.h>
-#include <asm/iseries/hv_lp_event.h>
-#include <asm/iseries/hv_call_event.h>
-#include "it_lp_naca.h"
-
-/*
- * The LpQueue is used to pass event data from the hypervisor to
- * the partition.  This is where I/O interrupt events are communicated.
- *
- * It is written to by the hypervisor so cannot end up in the BSS.
- */
-struct hvlpevent_queue hvlpevent_queue __attribute__((__section__(".data")));
-
-DEFINE_PER_CPU(unsigned long[HvLpEvent_Type_NumTypes], hvlpevent_counts);
-
-static char *event_types[HvLpEvent_Type_NumTypes] = {
-        "Hypervisor",
-        "Machine Facilities",
-        "Session Manager",
-        "SPD I/O",
-        "Virtual Bus",
-        "PCI I/O",
-        "RIO I/O",
-        "Virtual Lan",
-        "Virtual I/O"
-};
-
-/* Array of LpEvent handler functions */
-static LpEventHandler lpEventHandler[HvLpEvent_Type_NumTypes];
-static unsigned lpEventHandlerPaths[HvLpEvent_Type_NumTypes];
-
-static struct HvLpEvent * get_next_hvlpevent(void)
-{
-        struct HvLpEvent * event;
-        event = (struct HvLpEvent *)hvlpevent_queue.hq_current_event;
-
-        if (hvlpevent_is_valid(event)) {
-                /* rmb() needed only for weakly consistent machines (regatta) */
-                rmb();
-                /* Set pointer to next potential event */
-                hvlpevent_queue.hq_current_event += ((event->xSizeMinus1 +
-                                IT_LP_EVENT_ALIGN) / IT_LP_EVENT_ALIGN) *
-                                        IT_LP_EVENT_ALIGN;
-
-                /* Wrap to beginning if no room at end */
-                if (hvlpevent_queue.hq_current_event >
-                                hvlpevent_queue.hq_last_event) {
-                        hvlpevent_queue.hq_current_event =
-                                hvlpevent_queue.hq_event_stack;
-                }
-        } else {
-                event = NULL;
-        }
-
-        return event;
-}
-
-static unsigned long spread_lpevents = NR_CPUS;
-
-int hvlpevent_is_pending(void)
-{
-        struct HvLpEvent *next_event;
-
-        if (smp_processor_id() >= spread_lpevents)
-                return 0;
-
-        next_event = (struct HvLpEvent *)hvlpevent_queue.hq_current_event;
-
-        return hvlpevent_is_valid(next_event) ||
-                hvlpevent_queue.hq_overflow_pending;
-}
-
-static void hvlpevent_clear_valid(struct HvLpEvent * event)
-{
-        /* Tell the Hypervisor that we're done with this event.
-         * Also clear bits within this event that might look like valid bits.
-         * ie. on 64-byte boundaries.
-         */
-        struct HvLpEvent *tmp;
-        unsigned extra = ((event->xSizeMinus1 + IT_LP_EVENT_ALIGN) /
-                                IT_LP_EVENT_ALIGN) - 1;
-
-        switch (extra) {
-        case 3:
-                tmp = (struct HvLpEvent*)((char*)event + 3 * IT_LP_EVENT_ALIGN);
-                hvlpevent_invalidate(tmp);
-        case 2:
-                tmp = (struct HvLpEvent*)((char*)event + 2 * IT_LP_EVENT_ALIGN);
-                hvlpevent_invalidate(tmp);
-        case 1:
-                tmp = (struct HvLpEvent*)((char*)event + 1 * IT_LP_EVENT_ALIGN);
-                hvlpevent_invalidate(tmp);
-        }
-
-        mb();
-
-        hvlpevent_invalidate(event);
-}
-
-void process_hvlpevents(void)
-{
-        struct HvLpEvent * event;
-
- restart:
-        /* If we have recursed, just return */
-        if (!spin_trylock(&hvlpevent_queue.hq_lock))
-                return;
-
-        for (;;) {
-                event = get_next_hvlpevent();
-                if (event) {
-                        /* Call appropriate handler here, passing
-                         * a pointer to the LpEvent.  The handler
-                         * must make a copy of the LpEvent if it
-                         * needs it in a bottom half. (perhaps for
-                         * an ACK)
-                         *
-                         *  Handlers are responsible for ACK processing
-                         *
-                         * The Hypervisor guarantees that LpEvents will
-                         * only be delivered with types that we have
-                         * registered for, so no type check is necessary
-                         * here!
-                         */
-                        if (event->xType < HvLpEvent_Type_NumTypes)
-                                __get_cpu_var(hvlpevent_counts)[event->xType]++;
-                        if (event->xType < HvLpEvent_Type_NumTypes &&
-                                        lpEventHandler[event->xType])
-                                lpEventHandler[event->xType](event);
-                        else {
-                                u8 type = event->xType;
-
-                                /*
-                                 * Don't printk in the spinlock as printk
-                                 * may require ack events form the HV to send
-                                 * any characters there.
-                                 */
-                                hvlpevent_clear_valid(event);
-                                spin_unlock(&hvlpevent_queue.hq_lock);
-                                printk(KERN_INFO
-                                        "Unexpected Lp Event type=%d\n", type);
-                                goto restart;
-                        }
-
-                        hvlpevent_clear_valid(event);
-                } else if (hvlpevent_queue.hq_overflow_pending)
-                        /*
-                         * No more valid events. If overflow events are
-                         * pending process them
-                         */
-                        HvCallEvent_getOverflowLpEvents(hvlpevent_queue.hq_index);
-                else
-                        break;
-        }
-
-        spin_unlock(&hvlpevent_queue.hq_lock);
-}
-
-static int set_spread_lpevents(char *str)
-{
-        unsigned long val = simple_strtoul(str, NULL, 0);
-
-        /*
-         * The parameter is the number of processors to share in processing
-         * lp events.
-         */
-        if (( val > 0) && (val <= NR_CPUS)) {
-                spread_lpevents = val;
-                printk("lpevent processing spread over %ld processors\n", val);
-        } else {
-                printk("invalid spread_lpevents %ld\n", val);
-        }
-
-        return 1;
-}
-__setup("spread_lpevents=", set_spread_lpevents);
-
-void __init setup_hvlpevent_queue(void)
-{
-        void *eventStack;
-
-        spin_lock_init(&hvlpevent_queue.hq_lock);
-
-        /* Allocate a page for the Event Stack. */
-        eventStack = alloc_bootmem_pages(IT_LP_EVENT_STACK_SIZE);
-        memset(eventStack, 0, IT_LP_EVENT_STACK_SIZE);
-
-        /* Invoke the hypervisor to initialize the event stack */
-        HvCallEvent_setLpEventStack(0, eventStack, IT_LP_EVENT_STACK_SIZE);
-
-        hvlpevent_queue.hq_event_stack = eventStack;
-        hvlpevent_queue.hq_current_event = eventStack;
-        hvlpevent_queue.hq_last_event = (char *)eventStack +
-                (IT_LP_EVENT_STACK_SIZE - IT_LP_EVENT_MAX_SIZE);
-        hvlpevent_queue.hq_index = 0;
-}
-
-/* Register a handler for an LpEvent type */
-int HvLpEvent_registerHandler(HvLpEvent_Type eventType, LpEventHandler handler)
-{
-        if (eventType < HvLpEvent_Type_NumTypes) {
-                lpEventHandler[eventType] = handler;
-                return 0;
-        }
-        return 1;
-}
-EXPORT_SYMBOL(HvLpEvent_registerHandler);
-
-int HvLpEvent_unregisterHandler(HvLpEvent_Type eventType)
-{
-        might_sleep();
-
-        if (eventType < HvLpEvent_Type_NumTypes) {
-                if (!lpEventHandlerPaths[eventType]) {
-                        lpEventHandler[eventType] = NULL;
-                        /*
-                         * We now sleep until all other CPUs have scheduled.
-                         * This ensures that the deletion is seen by all
-                         * other CPUs, and that the deleted handler isn't
-                         * still running on another CPU when we return.
-                         */
-                        synchronize_sched();
-                        return 0;
-                }
-        }
-        return 1;
-}
-EXPORT_SYMBOL(HvLpEvent_unregisterHandler);
-
-/*
- * lpIndex is the partition index of the target partition.
- * needed only for VirtualIo, VirtualLan and SessionMgr.  Zero
- * indicates to use our partition index - for the other types.
- */
-int HvLpEvent_openPath(HvLpEvent_Type eventType, HvLpIndex lpIndex)
-{
-        if ((eventType < HvLpEvent_Type_NumTypes) &&
-                        lpEventHandler[eventType]) {
-                if (lpIndex == 0)
-                        lpIndex = itLpNaca.xLpIndex;
-                HvCallEvent_openLpEventPath(lpIndex, eventType);
-                ++lpEventHandlerPaths[eventType];
-                return 0;
-        }
-        return 1;
-}
-
-int HvLpEvent_closePath(HvLpEvent_Type eventType, HvLpIndex lpIndex)
-{
-        if ((eventType < HvLpEvent_Type_NumTypes) &&
-                        lpEventHandler[eventType] &&
-                        lpEventHandlerPaths[eventType]) {
-                if (lpIndex == 0)
-                        lpIndex = itLpNaca.xLpIndex;
-                HvCallEvent_closeLpEventPath(lpIndex, eventType);
-                --lpEventHandlerPaths[eventType];
-                return 0;
-        }
-        return 1;
-}
-
-static int proc_lpevents_show(struct seq_file *m, void *v)
-{
-        int cpu, i;
-        unsigned long sum;
-        static unsigned long cpu_totals[NR_CPUS];
-
-        /* FIXME: do we care that there's no locking here? */
-        sum = 0;
-        for_each_online_cpu(cpu) {
-                cpu_totals[cpu] = 0;
-                for (i = 0; i < HvLpEvent_Type_NumTypes; i++) {
-                        cpu_totals[cpu] += per_cpu(hvlpevent_counts, cpu)[i];
-                }
-                sum += cpu_totals[cpu];
-        }
-
-        seq_printf(m, "LpEventQueue 0\n");
-        seq_printf(m, "  events processed:\t%lu\n", sum);
-
-        for (i = 0; i < HvLpEvent_Type_NumTypes; ++i) {
-                sum = 0;
-                for_each_online_cpu(cpu) {
-                        sum += per_cpu(hvlpevent_counts, cpu)[i];
-                }
-
-                seq_printf(m, "    %-20s %10lu\n", event_types[i], sum);
-        }
-
-        seq_printf(m, "\n  events processed by processor:\n");
-
-        for_each_online_cpu(cpu) {
-                seq_printf(m, "    CPU%02d  %10lu\n", cpu, cpu_totals[cpu]);
-        }
-
-        return 0;
-}
-
-static int proc_lpevents_open(struct inode *inode, struct file *file)
-{
-        return single_open(file, proc_lpevents_show, NULL);
-}
-
-static const struct file_operations proc_lpevents_operations = {
-        .open           = proc_lpevents_open,
-        .read           = seq_read,
-        .llseek         = seq_lseek,
-        .release        = single_release,
-};
-
-static int __init proc_lpevents_init(void)
-{
-        if (!firmware_has_feature(FW_FEATURE_ISERIES))
-                return 0;
-
-        proc_create("iSeries/lpevents", S_IFREG|S_IRUGO, NULL,
-                    &proc_lpevents_operations);
-        return 0;
-}
-__initcall(proc_lpevents_init);
-
diff --git a/arch/powerpc/platforms/iseries/main_store.h b/arch/powerpc/platforms/iseries/main_store.h
deleted file mode 100644
index 1a7a3f50e40b..000000000000
--- a/arch/powerpc/platforms/iseries/main_store.h
+++ /dev/null
@@ -1,165 +0,0 @@
-/*
- * Copyright (C) 2001  Mike Corrigan 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.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
- */
-
-#ifndef _ISERIES_MAIN_STORE_H
-#define _ISERIES_MAIN_STORE_H
-
-/* Main Store Vpd for Condor,iStar,sStar */
-struct IoHriMainStoreSegment4 {
-        u8      msArea0Exists:1;
-        u8      msArea1Exists:1;
-        u8      msArea2Exists:1;
-        u8      msArea3Exists:1;
-        u8      reserved1:4;
-        u8      reserved2;
-
-        u8      msArea0Functional:1;
-        u8      msArea1Functional:1;
-        u8      msArea2Functional:1;
-        u8      msArea3Functional:1;
-        u8      reserved3:4;
-        u8      reserved4;
-
-        u32     totalMainStore;
-
-        u64     msArea0Ptr;
-        u64     msArea1Ptr;
-        u64     msArea2Ptr;
-        u64     msArea3Ptr;
-
-        u32     cardProductionLevel;
-
-        u32     msAdrHole;
-
-        u8      msArea0HasRiserVpd:1;
-        u8      msArea1HasRiserVpd:1;
-        u8      msArea2HasRiserVpd:1;
-        u8      msArea3HasRiserVpd:1;
-        u8      reserved5:4;
-        u8      reserved6;
-        u16     reserved7;
-
-        u8      reserved8[28];
-
-        u64     nonInterleavedBlocksStartAdr;
-        u64     nonInterleavedBlocksEndAdr;
-};
-
-/* Main Store VPD for Power4 */
-struct __attribute((packed)) IoHriMainStoreChipInfo1 {
-        u32     chipMfgID;
-        char    chipECLevel[4];
-};
-
-struct IoHriMainStoreVpdIdData {
-        char    typeNumber[4];
-        char    modelNumber[4];
-        char    partNumber[12];
-        char    serialNumber[12];
-};
-
-struct  __attribute((packed)) IoHriMainStoreVpdFruData {
-        char    fruLabel[8];
-        u8      numberOfSlots;
-        u8      pluggingType;
-        u16     slotMapIndex;
-};
-
-struct  __attribute((packed)) IoHriMainStoreAdrRangeBlock {
-        void    *blockStart;
-        void    *blockEnd;
-        u32     blockProcChipId;
-};
-
-#define MaxAreaAdrRangeBlocks 4
-
-struct __attribute((packed)) IoHriMainStoreArea4 {
-        u32     msVpdFormat;
-        u8      containedVpdType;
-        u8      reserved1;
-        u16     reserved2;
-
-        u64     msExists;
-        u64     msFunctional;
-
-        u32     memorySize;
-        u32     procNodeId;
-
-        u32     numAdrRangeBlocks;
-        struct IoHriMainStoreAdrRangeBlock xAdrRangeBlock[MaxAreaAdrRangeBlocks];
-
-        struct IoHriMainStoreChipInfo1  chipInfo0;
-        struct IoHriMainStoreChipInfo1  chipInfo1;
-        struct IoHriMainStoreChipInfo1  chipInfo2;
-        struct IoHriMainStoreChipInfo1  chipInfo3;
-        struct IoHriMainStoreChipInfo1  chipInfo4;
-        struct IoHriMainStoreChipInfo1  chipInfo5;
-        struct IoHriMainStoreChipInfo1  chipInfo6;
-        struct IoHriMainStoreChipInfo1  chipInfo7;
-
-        void    *msRamAreaArray;
-        u32     msRamAreaArrayNumEntries;
-        u32     msRamAreaArrayEntrySize;
-
-        u32     numaDimmExists;
-        u32     numaDimmFunctional;
-        void    *numaDimmArray;
-        u32     numaDimmArrayNumEntries;
-        u32     numaDimmArrayEntrySize;
-
-        struct IoHriMainStoreVpdIdData idData;
-
-        u64     powerData;
-        u64     cardAssemblyPartNum;
-        u64     chipSerialNum;
-
-        u64     reserved3;
-        char    reserved4[16];
-
-        struct IoHriMainStoreVpdFruData fruData;
-
-        u8      vpdPortNum;
-        u8      reserved5;
-        u8      frameId;
-        u8      rackUnit;
-        char    asciiKeywordVpd[256];
-        u32     reserved6;
-};
-
-
-struct IoHriMainStoreSegment5 {
-        u16     reserved1;
-        u8      reserved2;
-        u8      msVpdFormat;
-
-        u32     totalMainStore;
-        u64     maxConfiguredMsAdr;
-
-        struct IoHriMainStoreArea4      *msAreaArray;
-        u32     msAreaArrayNumEntries;
-        u32     msAreaArrayEntrySize;
-
-        u32     msAreaExists;
-        u32     msAreaFunctional;
-
-        u64     reserved3;
-};
-
-extern u64      xMsVpd[];
-
-#endif  /* _ISERIES_MAIN_STORE_H */
diff --git a/arch/powerpc/platforms/iseries/mf.c b/arch/powerpc/platforms/iseries/mf.c
deleted file mode 100644
index 254c1fc3d8dd..000000000000
--- a/arch/powerpc/platforms/iseries/mf.c
+++ /dev/null
@@ -1,1275 +0,0 @@
-/*
- * Copyright (C) 2001 Troy D. Armstrong  IBM Corporation
- * Copyright (C) 2004-2005 Stephen Rothwell  IBM Corporation
- *
- * This modules exists as an interface between a Linux secondary partition
- * running on an iSeries and the primary partition's Virtual Service
- * Processor (VSP) object.  The VSP has final authority over powering on/off
- * all partitions in the iSeries.  It also provides miscellaneous low-level
- * machine facility type operations.
- *
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
- */
-
-#include <linux/types.h>
-#include <linux/errno.h>
-#include <linux/kernel.h>
-#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>
-#include <linux/rtc.h>
-#include <linux/slab.h>
-
-#include <asm/time.h>
-#include <asm/uaccess.h>
-#include <asm/paca.h>
-#include <asm/abs_addr.h>
-#include <asm/firmware.h>
-#include <asm/iseries/mf.h>
-#include <asm/iseries/hv_lp_config.h>
-#include <asm/iseries/hv_lp_event.h>
-#include <asm/iseries/it_lp_queue.h>
-
-#include "setup.h"
-
-static int mf_initialized;
-
-/*
- * This is the structure layout for the Machine Facilities LPAR event
- * flows.
- */
-struct vsp_cmd_data {
-        u64 token;
-        u16 cmd;
-        HvLpIndex lp_index;
-        u8 result_code;
-        u32 reserved;
-        union {
-                u64 state;      /* GetStateOut */
-                u64 ipl_type;   /* GetIplTypeOut, Function02SelectIplTypeIn */
-                u64 ipl_mode;   /* GetIplModeOut, Function02SelectIplModeIn */
-                u64 page[4];    /* GetSrcHistoryIn */
-                u64 flag;       /* GetAutoIplWhenPrimaryIplsOut,
-                                   SetAutoIplWhenPrimaryIplsIn,
-                                   WhiteButtonPowerOffIn,
-                                   Function08FastPowerOffIn,
-                                   IsSpcnRackPowerIncompleteOut */
-                struct {
-                        u64 token;
-                        u64 address_type;
-                        u64 side;
-                        u32 length;
-                        u32 offset;
-                } kern;         /* SetKernelImageIn, GetKernelImageIn,
-                                   SetKernelCmdLineIn, GetKernelCmdLineIn */
-                u32 length_out; /* GetKernelImageOut, GetKernelCmdLineOut */
-                u8 reserved[80];
-        } sub_data;
-};
-
-struct vsp_rsp_data {
-        struct completion com;
-        struct vsp_cmd_data *response;
-};
-
-struct alloc_data {
-        u16 size;
-        u16 type;
-        u32 count;
-        u16 reserved1;
-        u8 reserved2;
-        HvLpIndex target_lp;
-};
-
-struct ce_msg_data;
-
-typedef void (*ce_msg_comp_hdlr)(void *token, struct ce_msg_data *vsp_cmd_rsp);
-
-struct ce_msg_comp_data {
-        ce_msg_comp_hdlr handler;
-        void *token;
-};
-
-struct ce_msg_data {
-        u8 ce_msg[12];
-        char reserved[4];
-        struct ce_msg_comp_data *completion;
-};
-
-struct io_mf_lp_event {
-        struct HvLpEvent hp_lp_event;
-        u16 subtype_result_code;
-        u16 reserved1;
-        u32 reserved2;
-        union {
-                struct alloc_data alloc;
-                struct ce_msg_data ce_msg;
-                struct vsp_cmd_data vsp_cmd;
-        } data;
-};
-
-#define subtype_data(a, b, c, d)        \
-                (((a) << 24) + ((b) << 16) + ((c) << 8) + (d))
-
-/*
- * All outgoing event traffic is kept on a FIFO queue.  The first
- * pointer points to the one that is outstanding, and all new
- * requests get stuck on the end.  Also, we keep a certain number of
- * preallocated pending events so that we can operate very early in
- * the boot up sequence (before kmalloc is ready).
- */
-struct pending_event {
-        struct pending_event *next;
-        struct io_mf_lp_event event;
-        MFCompleteHandler hdlr;
-        char dma_data[72];
-        unsigned dma_data_length;
-        unsigned remote_address;
-};
-static spinlock_t pending_event_spinlock;
-static struct pending_event *pending_event_head;
-static struct pending_event *pending_event_tail;
-static struct pending_event *pending_event_avail;
-#define PENDING_EVENT_PREALLOC_LEN 16
-static struct pending_event pending_event_prealloc[PENDING_EVENT_PREALLOC_LEN];
-
-/*
- * Put a pending event onto the available queue, so it can get reused.
- * Attention! You must have the pending_event_spinlock before calling!
- */
-static void free_pending_event(struct pending_event *ev)
-{
-        if (ev != NULL) {
-                ev->next = pending_event_avail;
-                pending_event_avail = ev;
-        }
-}
-
-/*
- * Enqueue the outbound event onto the stack.  If the queue was
- * empty to begin with, we must also issue it via the Hypervisor
- * interface.  There is a section of code below that will touch
- * the first stack pointer without the protection of the pending_event_spinlock.
- * This is OK, because we know that nobody else will be modifying
- * the first pointer when we do this.
- */
-static int signal_event(struct pending_event *ev)
-{
-        int rc = 0;
-        unsigned long flags;
-        int go = 1;
-        struct pending_event *ev1;
-        HvLpEvent_Rc hv_rc;
-
-        /* enqueue the event */
-        if (ev != NULL) {
-                ev->next = NULL;
-                spin_lock_irqsave(&pending_event_spinlock, flags);
-                if (pending_event_head == NULL)
-                        pending_event_head = ev;
-                else {
-                        go = 0;
-                        pending_event_tail->next = ev;
-                }
-                pending_event_tail = ev;
-                spin_unlock_irqrestore(&pending_event_spinlock, flags);
-        }
-
-        /* send the event */
-        while (go) {
-                go = 0;
-
-                /* any DMA data to send beforehand? */
-                if (pending_event_head->dma_data_length > 0)
-                        HvCallEvent_dmaToSp(pending_event_head->dma_data,
-                                        pending_event_head->remote_address,
-                                        pending_event_head->dma_data_length,
-                                        HvLpDma_Direction_LocalToRemote);
-
-                hv_rc = HvCallEvent_signalLpEvent(
-                                &pending_event_head->event.hp_lp_event);
-                if (hv_rc != HvLpEvent_Rc_Good) {
-                        printk(KERN_ERR "mf.c: HvCallEvent_signalLpEvent() "
-                                        "failed with %d\n", (int)hv_rc);
-
-                        spin_lock_irqsave(&pending_event_spinlock, flags);
-                        ev1 = pending_event_head;
-                        pending_event_head = pending_event_head->next;
-                        if (pending_event_head != NULL)
-                                go = 1;
-                        spin_unlock_irqrestore(&pending_event_spinlock, flags);
-
-                        if (ev1 == ev)
-                                rc = -EIO;
-                        else if (ev1->hdlr != NULL)
-                                (*ev1->hdlr)((void *)ev1->event.hp_lp_event.xCorrelationToken, -EIO);
-
-                        spin_lock_irqsave(&pending_event_spinlock, flags);
-                        free_pending_event(ev1);
-                        spin_unlock_irqrestore(&pending_event_spinlock, flags);
-                }
-        }
-
-        return rc;
-}
-
-/*
- * Allocate a new pending_event structure, and initialize it.
- */
-static struct pending_event *new_pending_event(void)
-{
-        struct pending_event *ev = NULL;
-        HvLpIndex primary_lp = HvLpConfig_getPrimaryLpIndex();
-        unsigned long flags;
-        struct HvLpEvent *hev;
-
-        spin_lock_irqsave(&pending_event_spinlock, flags);
-        if (pending_event_avail != NULL) {
-                ev = pending_event_avail;
-                pending_event_avail = pending_event_avail->next;
-        }
-        spin_unlock_irqrestore(&pending_event_spinlock, flags);
-        if (ev == NULL) {
-                ev = kmalloc(sizeof(struct pending_event), GFP_ATOMIC);
-                if (ev == NULL) {
-                        printk(KERN_ERR "mf.c: unable to kmalloc %ld bytes\n",
-                                        sizeof(struct pending_event));
-                        return NULL;
-                }
-        }
-        memset(ev, 0, sizeof(struct pending_event));
-        hev = &ev->event.hp_lp_event;
-        hev->flags = HV_LP_EVENT_VALID | HV_LP_EVENT_DO_ACK | HV_LP_EVENT_INT;
-        hev->xType = HvLpEvent_Type_MachineFac;
-        hev->xSourceLp = HvLpConfig_getLpIndex();
-        hev->xTargetLp = primary_lp;
-        hev->xSizeMinus1 = sizeof(ev->event) - 1;
-        hev->xRc = HvLpEvent_Rc_Good;
-        hev->xSourceInstanceId = HvCallEvent_getSourceLpInstanceId(primary_lp,
-                        HvLpEvent_Type_MachineFac);
-        hev->xTargetInstanceId = HvCallEvent_getTargetLpInstanceId(primary_lp,
-                        HvLpEvent_Type_MachineFac);
-
-        return ev;
-}
-
-static int __maybe_unused
-signal_vsp_instruction(struct vsp_cmd_data *vsp_cmd)
-{
-        struct pending_event *ev = new_pending_event();
-        int rc;
-        struct vsp_rsp_data response;
-
-        if (ev == NULL)
-                return -ENOMEM;
-
-        init_completion(&response.com);
-        response.response = vsp_cmd;
-        ev->event.hp_lp_event.xSubtype = 6;
-        ev->event.hp_lp_event.x.xSubtypeData =
-                subtype_data('M', 'F',  'V',  'I');
-        ev->event.data.vsp_cmd.token = (u64)&response;
-        ev->event.data.vsp_cmd.cmd = vsp_cmd->cmd;
-        ev->event.data.vsp_cmd.lp_index = HvLpConfig_getLpIndex();
-        ev->event.data.vsp_cmd.result_code = 0xFF;
-        ev->event.data.vsp_cmd.reserved = 0;
-        memcpy(&(ev->event.data.vsp_cmd.sub_data),
-                        &(vsp_cmd->sub_data), sizeof(vsp_cmd->sub_data));
-        mb();
-
-        rc = signal_event(ev);
-        if (rc == 0)
-                wait_for_completion(&response.com);
-        return rc;
-}
-
-
-/*
- * Send a 12-byte CE message to the primary partition VSP object
- */
-static int signal_ce_msg(char *ce_msg, struct ce_msg_comp_data *completion)
-{
-        struct pending_event *ev = new_pending_event();
-
-        if (ev == NULL)
-                return -ENOMEM;
-
-        ev->event.hp_lp_event.xSubtype = 0;
-        ev->event.hp_lp_event.x.xSubtypeData =
-                subtype_data('M',  'F',  'C',  'E');
-        memcpy(ev->event.data.ce_msg.ce_msg, ce_msg, 12);
-        ev->event.data.ce_msg.completion = completion;
-        return signal_event(ev);
-}
-
-/*
- * Send a 12-byte CE message (with no data) to the primary partition VSP object
- */
-static int signal_ce_msg_simple(u8 ce_op, struct ce_msg_comp_data *completion)
-{
-        u8 ce_msg[12];
-
-        memset(ce_msg, 0, sizeof(ce_msg));
-        ce_msg[3] = ce_op;
-        return signal_ce_msg(ce_msg, completion);
-}
-
-/*
- * Send a 12-byte CE message and DMA data to the primary partition VSP object
- */
-static int dma_and_signal_ce_msg(char *ce_msg,
-                struct ce_msg_comp_data *completion, void *dma_data,
-                unsigned dma_data_length, unsigned remote_address)
-{
-        struct pending_event *ev = new_pending_event();
-
-        if (ev == NULL)
-                return -ENOMEM;
-
-        ev->event.hp_lp_event.xSubtype = 0;
-        ev->event.hp_lp_event.x.xSubtypeData =
-                subtype_data('M', 'F', 'C', 'E');
-        memcpy(ev->event.data.ce_msg.ce_msg, ce_msg, 12);
-        ev->event.data.ce_msg.completion = completion;
-        memcpy(ev->dma_data, dma_data, dma_data_length);
-        ev->dma_data_length = dma_data_length;
-        ev->remote_address = remote_address;
-        return signal_event(ev);
-}
-
-/*
- * Initiate a nice (hopefully) shutdown of Linux.  We simply are
- * going to try and send the init process a SIGINT signal.  If
- * this fails (why?), we'll simply force it off in a not-so-nice
- * manner.
- */
-static int shutdown(void)
-{
-        int rc = kill_cad_pid(SIGINT, 1);
-
-        if (rc) {
-                printk(KERN_ALERT "mf.c: SIGINT to init failed (%d), "
-                                "hard shutdown commencing\n", rc);
-                mf_power_off();
-        } else
-                printk(KERN_INFO "mf.c: init has been successfully notified "
-                                "to proceed with shutdown\n");
-        return rc;
-}
-
-/*
- * The primary partition VSP object is sending us a new
- * event flow.  Handle it...
- */
-static void handle_int(struct io_mf_lp_event *event)
-{
-        struct ce_msg_data *ce_msg_data;
-        struct ce_msg_data *pce_msg_data;
-        unsigned long flags;
-        struct pending_event *pev;
-
-        /* ack the interrupt */
-        event->hp_lp_event.xRc = HvLpEvent_Rc_Good;
-        HvCallEvent_ackLpEvent(&event->hp_lp_event);
-
-        /* process interrupt */
-        switch (event->hp_lp_event.xSubtype) {
-        case 0: /* CE message */
-                ce_msg_data = &event->data.ce_msg;
-                switch (ce_msg_data->ce_msg[3]) {
-                case 0x5B:      /* power control notification */
-                        if ((ce_msg_data->ce_msg[5] & 0x20) != 0) {
-                                printk(KERN_INFO "mf.c: Commencing partition shutdown\n");
-                                if (shutdown() == 0)
-                                        signal_ce_msg_simple(0xDB, NULL);
-                        }
-                        break;
-                case 0xC0:      /* get time */
-                        spin_lock_irqsave(&pending_event_spinlock, flags);
-                        pev = pending_event_head;
-                        if (pev != NULL)
-                                pending_event_head = pending_event_head->next;
-                        spin_unlock_irqrestore(&pending_event_spinlock, flags);
-                        if (pev == NULL)
-                                break;
-                        pce_msg_data = &pev->event.data.ce_msg;
-                        if (pce_msg_data->ce_msg[3] != 0x40)
-                                break;
-                        if (pce_msg_data->completion != NULL) {
-                                ce_msg_comp_hdlr handler =
-                                        pce_msg_data->completion->handler;
-                                void *token = pce_msg_data->completion->token;
-
-                                if (handler != NULL)
-                                        (*handler)(token, ce_msg_data);
-                        }
-                        spin_lock_irqsave(&pending_event_spinlock, flags);
-                        free_pending_event(pev);
-                        spin_unlock_irqrestore(&pending_event_spinlock, flags);
-                        /* send next waiting event */
-                        if (pending_event_head != NULL)
-                                signal_event(NULL);
-                        break;
-                }
-                break;
-        case 1: /* IT sys shutdown */
-                printk(KERN_INFO "mf.c: Commencing system shutdown\n");
-                shutdown();
-                break;
-        }
-}
-
-/*
- * The primary partition VSP object is acknowledging the receipt
- * of a flow we sent to them.  If there are other flows queued
- * up, we must send another one now...
- */
-static void handle_ack(struct io_mf_lp_event *event)
-{
-        unsigned long flags;
-        struct pending_event *two = NULL;
-        unsigned long free_it = 0;
-        struct ce_msg_data *ce_msg_data;
-        struct ce_msg_data *pce_msg_data;
-        struct vsp_rsp_data *rsp;
-
-        /* handle current event */
-        if (pending_event_head == NULL) {
-                printk(KERN_ERR "mf.c: stack empty for receiving ack\n");
-                return;
-        }
-
-        switch (event->hp_lp_event.xSubtype) {
-        case 0:     /* CE msg */
-                ce_msg_data = &event->data.ce_msg;
-                if (ce_msg_data->ce_msg[3] != 0x40) {
-                        free_it = 1;
-                        break;
-                }
-                if (ce_msg_data->ce_msg[2] == 0)
-                        break;
-                free_it = 1;
-                pce_msg_data = &pending_event_head->event.data.ce_msg;
-                if (pce_msg_data->completion != NULL) {
-                        ce_msg_comp_hdlr handler =
-                                pce_msg_data->completion->handler;
-                        void *token = pce_msg_data->completion->token;
-
-                        if (handler != NULL)
-                                (*handler)(token, ce_msg_data);
-                }
-                break;
-        case 4: /* allocate */
-        case 5: /* deallocate */
-                if (pending_event_head->hdlr != NULL)
-                        (*pending_event_head->hdlr)((void *)event->hp_lp_event.xCorrelationToken, event->data.alloc.count);
-                free_it = 1;
-                break;
-        case 6:
-                free_it = 1;
-                rsp = (struct vsp_rsp_data *)event->data.vsp_cmd.token;
-                if (rsp == NULL) {
-                        printk(KERN_ERR "mf.c: no rsp\n");
-                        break;
-                }
-                if (rsp->response != NULL)
-                        memcpy(rsp->response, &event->data.vsp_cmd,
-                                        sizeof(event->data.vsp_cmd));
-                complete(&rsp->com);
-                break;
-        }
-
-        /* remove from queue */
-        spin_lock_irqsave(&pending_event_spinlock, flags);
-        if ((pending_event_head != NULL) && (free_it == 1)) {
-                struct pending_event *oldHead = pending_event_head;
-
-                pending_event_head = pending_event_head->next;
-                two = pending_event_head;
-                free_pending_event(oldHead);
-        }
-        spin_unlock_irqrestore(&pending_event_spinlock, flags);
-
-        /* send next waiting event */
-        if (two != NULL)
-                signal_event(NULL);
-}
-
-/*
- * This is the generic event handler we are registering with
- * the Hypervisor.  Ensure the flows are for us, and then
- * parse it enough to know if it is an interrupt or an
- * acknowledge.
- */
-static void hv_handler(struct HvLpEvent *event)
-{
-        if ((event != NULL) && (event->xType == HvLpEvent_Type_MachineFac)) {
-                if (hvlpevent_is_ack(event))
-                        handle_ack((struct io_mf_lp_event *)event);
-                else
-                        handle_int((struct io_mf_lp_event *)event);
-        } else
-                printk(KERN_ERR "mf.c: alien event received\n");
-}
-
-/*
- * Global kernel interface to allocate and seed events into the
- * Hypervisor.
- */
-void mf_allocate_lp_events(HvLpIndex target_lp, HvLpEvent_Type type,
-                unsigned size, unsigned count, MFCompleteHandler hdlr,
-                void *user_token)
-{
-        struct pending_event *ev = new_pending_event();
-        int rc;
-
-        if (ev == NULL) {
-                rc = -ENOMEM;
-        } else {
-                ev->event.hp_lp_event.xSubtype = 4;
-                ev->event.hp_lp_event.xCorrelationToken = (u64)user_token;
-                ev->event.hp_lp_event.x.xSubtypeData =
-                        subtype_data('M', 'F', 'M', 'A');
-                ev->event.data.alloc.target_lp = target_lp;
-                ev->event.data.alloc.type = type;
-                ev->event.data.alloc.size = size;
-                ev->event.data.alloc.count = count;
-                ev->hdlr = hdlr;
-                rc = signal_event(ev);
-        }
-        if ((rc != 0) && (hdlr != NULL))
-                (*hdlr)(user_token, rc);
-}
-EXPORT_SYMBOL(mf_allocate_lp_events);
-
-/*
- * Global kernel interface to unseed and deallocate events already in
- * Hypervisor.
- */
-void mf_deallocate_lp_events(HvLpIndex target_lp, HvLpEvent_Type type,
-                unsigned count, MFCompleteHandler hdlr, void *user_token)
-{
-        struct pending_event *ev = new_pending_event();
-        int rc;
-
-        if (ev == NULL)
-                rc = -ENOMEM;
-        else {
-                ev->event.hp_lp_event.xSubtype = 5;
-                ev->event.hp_lp_event.xCorrelationToken = (u64)user_token;
-                ev->event.hp_lp_event.x.xSubtypeData =
-                        subtype_data('M', 'F', 'M', 'D');
-                ev->event.data.alloc.target_lp = target_lp;
-                ev->event.data.alloc.type = type;
-                ev->event.data.alloc.count = count;
-                ev->hdlr = hdlr;
-                rc = signal_event(ev);
-        }
-        if ((rc != 0) && (hdlr != NULL))
-                (*hdlr)(user_token, rc);
-}
-EXPORT_SYMBOL(mf_deallocate_lp_events);
-
-/*
- * Global kernel interface to tell the VSP object in the primary
- * partition to power this partition off.
- */
-void mf_power_off(void)
-{
-        printk(KERN_INFO "mf.c: Down it goes...\n");
-        signal_ce_msg_simple(0x4d, NULL);
-        for (;;)
-                ;
-}
-
-/*
- * Global kernel interface to tell the VSP object in the primary
- * partition to reboot this partition.
- */
-void mf_reboot(char *cmd)
-{
-        printk(KERN_INFO "mf.c: Preparing to bounce...\n");
-        signal_ce_msg_simple(0x4e, NULL);
-        for (;;)
-                ;
-}
-
-/*
- * Display a single word SRC onto the VSP control panel.
- */
-void mf_display_src(u32 word)
-{
-        u8 ce[12];
-
-        memset(ce, 0, sizeof(ce));
-        ce[3] = 0x4a;
-        ce[7] = 0x01;
-        ce[8] = word >> 24;
-        ce[9] = word >> 16;
-        ce[10] = word >> 8;
-        ce[11] = word;
-        signal_ce_msg(ce, NULL);
-}
-
-/*
- * Display a single word SRC of the form "PROGXXXX" on the VSP control panel.
- */
-static __init void mf_display_progress_src(u16 value)
-{
-        u8 ce[12];
-        u8 src[72];
-
-        memcpy(ce, "\x00\x00\x04\x4A\x00\x00\x00\x48\x00\x00\x00\x00", 12);
-        memcpy(src, "\x01\x00\x00\x01\x00\x00\x00\x00\x00\x00\x00\x00"
-                "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00"
-                "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00"
-                "\x00\x00\x00\x00PROGxxxx                        ",
-                72);
-        src[6] = value >> 8;
-        src[7] = value & 255;
-        src[44] = "0123456789ABCDEF"[(value >> 12) & 15];
-        src[45] = "0123456789ABCDEF"[(value >> 8) & 15];
-        src[46] = "0123456789ABCDEF"[(value >> 4) & 15];
-        src[47] = "0123456789ABCDEF"[value & 15];
-        dma_and_signal_ce_msg(ce, NULL, src, sizeof(src), 9 * 64 * 1024);
-}
-
-/*
- * Clear the VSP control panel.  Used to "erase" an SRC that was
- * previously displayed.
- */
-static void mf_clear_src(void)
-{
-        signal_ce_msg_simple(0x4b, NULL);
-}
-
-void __init mf_display_progress(u16 value)
-{
-        if (!mf_initialized)
-                return;
-
-        if (0xFFFF == value)
-                mf_clear_src();
-        else
-                mf_display_progress_src(value);
-}
-
-/*
- * Initialization code here.
- */
-void __init mf_init(void)
-{
-        int i;
-
-        spin_lock_init(&pending_event_spinlock);
-
-        for (i = 0; i < PENDING_EVENT_PREALLOC_LEN; i++)
-                free_pending_event(&pending_event_prealloc[i]);
-
-        HvLpEvent_registerHandler(HvLpEvent_Type_MachineFac, &hv_handler);
-
-        /* virtual continue ack */
-        signal_ce_msg_simple(0x57, NULL);
-
-        mf_initialized = 1;
-        mb();
-
-        printk(KERN_NOTICE "mf.c: iSeries Linux LPAR Machine Facilities "
-                        "initialized\n");
-}
-
-struct rtc_time_data {
-        struct completion com;
-        struct ce_msg_data ce_msg;
-        int rc;
-};
-
-static void get_rtc_time_complete(void *token, struct ce_msg_data *ce_msg)
-{
-        struct rtc_time_data *rtc = token;
-
-        memcpy(&rtc->ce_msg, ce_msg, sizeof(rtc->ce_msg));
-        rtc->rc = 0;
-        complete(&rtc->com);
-}
-
-static int mf_set_rtc(struct rtc_time *tm)
-{
-        char ce_time[12];
-        u8 day, mon, hour, min, sec, y1, y2;
-        unsigned year;
-
-        year = 1900 + tm->tm_year;
-        y1 = year / 100;
-        y2 = year % 100;
-
-        sec = tm->tm_sec;
-        min = tm->tm_min;
-        hour = tm->tm_hour;
-        day = tm->tm_mday;
-        mon = tm->tm_mon + 1;
-
-        sec = bin2bcd(sec);
-        min = bin2bcd(min);
-        hour = bin2bcd(hour);
-        mon = bin2bcd(mon);
-        day = bin2bcd(day);
-        y1 = bin2bcd(y1);
-        y2 = bin2bcd(y2);
-
-        memset(ce_time, 0, sizeof(ce_time));
-        ce_time[3] = 0x41;
-        ce_time[4] = y1;
-        ce_time[5] = y2;
-        ce_time[6] = sec;
-        ce_time[7] = min;
-        ce_time[8] = hour;
-        ce_time[10] = day;
-        ce_time[11] = mon;
-
-        return signal_ce_msg(ce_time, NULL);
-}
-
-static int rtc_set_tm(int rc, u8 *ce_msg, struct rtc_time *tm)
-{
-        tm->tm_wday = 0;
-        tm->tm_yday = 0;
-        tm->tm_isdst = 0;
-        if (rc) {
-                tm->tm_sec = 0;
-                tm->tm_min = 0;
-                tm->tm_hour = 0;
-                tm->tm_mday = 15;
-                tm->tm_mon = 5;
-                tm->tm_year = 52;
-                return rc;
-        }
-
-        if ((ce_msg[2] == 0xa9) ||
-            (ce_msg[2] == 0xaf)) {
-                /* TOD clock is not set */
-                tm->tm_sec = 1;
-                tm->tm_min = 1;
-                tm->tm_hour = 1;
-                tm->tm_mday = 10;
-                tm->tm_mon = 8;
-                tm->tm_year = 71;
-                mf_set_rtc(tm);
-        }
-        {
-                u8 year = ce_msg[5];
-                u8 sec = ce_msg[6];
-                u8 min = ce_msg[7];
-                u8 hour = ce_msg[8];
-                u8 day = ce_msg[10];
-                u8 mon = ce_msg[11];
-
-                sec = bcd2bin(sec);
-                min = bcd2bin(min);
-                hour = bcd2bin(hour);
-                day = bcd2bin(day);
-                mon = bcd2bin(mon);
-                year = bcd2bin(year);
-
-                if (year <= 69)
-                        year += 100;
-
-                tm->tm_sec = sec;
-                tm->tm_min = min;
-                tm->tm_hour = hour;
-                tm->tm_mday = day;
-                tm->tm_mon = mon;
-                tm->tm_year = year;
-        }
-
-        return 0;
-}
-
-static int mf_get_rtc(struct rtc_time *tm)
-{
-        struct ce_msg_comp_data ce_complete;
-        struct rtc_time_data rtc_data;
-        int rc;
-
-        memset(&ce_complete, 0, sizeof(ce_complete));
-        memset(&rtc_data, 0, sizeof(rtc_data));
-        init_completion(&rtc_data.com);
-        ce_complete.handler = &get_rtc_time_complete;
-        ce_complete.token = &rtc_data;
-        rc = signal_ce_msg_simple(0x40, &ce_complete);
-        if (rc)
-                return rc;
-        wait_for_completion(&rtc_data.com);
-        return rtc_set_tm(rtc_data.rc, rtc_data.ce_msg.ce_msg, tm);
-}
-
-struct boot_rtc_time_data {
-        int busy;
-        struct ce_msg_data ce_msg;
-        int rc;
-};
-
-static void get_boot_rtc_time_complete(void *token, struct ce_msg_data *ce_msg)
-{
-        struct boot_rtc_time_data *rtc = token;
-
-        memcpy(&rtc->ce_msg, ce_msg, sizeof(rtc->ce_msg));
-        rtc->rc = 0;
-        rtc->busy = 0;
-}
-
-static int mf_get_boot_rtc(struct rtc_time *tm)
-{
-        struct ce_msg_comp_data ce_complete;
-        struct boot_rtc_time_data rtc_data;
-        int rc;
-
-        memset(&ce_complete, 0, sizeof(ce_complete));
-        memset(&rtc_data, 0, sizeof(rtc_data));
-        rtc_data.busy = 1;
-        ce_complete.handler = &get_boot_rtc_time_complete;
-        ce_complete.token = &rtc_data;
-        rc = signal_ce_msg_simple(0x40, &ce_complete);
-        if (rc)
-                return rc;
-        /* We need to poll here as we are not yet taking interrupts */
-        while (rtc_data.busy) {
-                if (hvlpevent_is_pending())
-                        process_hvlpevents();
-        }
-        return rtc_set_tm(rtc_data.rc, rtc_data.ce_msg.ce_msg, tm);
-}
-
-#ifdef CONFIG_PROC_FS
-static int mf_cmdline_proc_show(struct seq_file *m, void *v)
-{
-        char *page, *p;
-        struct vsp_cmd_data vsp_cmd;
-        int rc;
-        dma_addr_t dma_addr;
-
-        /* The HV appears to return no more than 256 bytes of command line */
-        page = kmalloc(256, GFP_KERNEL);
-        if (!page)
-                return -ENOMEM;
-
-        dma_addr = iseries_hv_map(page, 256, DMA_FROM_DEVICE);
-        if (dma_addr == DMA_ERROR_CODE) {
-                kfree(page);
-                return -ENOMEM;
-        }
-        memset(page, 0, 256);
-        memset(&vsp_cmd, 0, sizeof(vsp_cmd));
-        vsp_cmd.cmd = 33;
-        vsp_cmd.sub_data.kern.token = dma_addr;
-        vsp_cmd.sub_data.kern.address_type = HvLpDma_AddressType_TceIndex;
-        vsp_cmd.sub_data.kern.side = (u64)m->private;
-        vsp_cmd.sub_data.kern.length = 256;
-        mb();
-        rc = signal_vsp_instruction(&vsp_cmd);
-        iseries_hv_unmap(dma_addr, 256, DMA_FROM_DEVICE);
-        if (rc) {
-                kfree(page);
-                return rc;
-        }
-        if (vsp_cmd.result_code != 0) {
-                kfree(page);
-                return -ENOMEM;
-        }
-        p = page;
-        while (p - page < 256) {
-                if (*p == '\0' || *p == '\n') {
-                        *p = '\n';
-                        break;
-                }
-                p++;
-
-        }
-        seq_write(m, page, p - page);
-        kfree(page);
-        return 0;
-}
-
-static int mf_cmdline_proc_open(struct inode *inode, struct file *file)
-{
-        return single_open(file, mf_cmdline_proc_show, PDE(inode)->data);
-}
-
-#if 0
-static int mf_getVmlinuxChunk(char *buffer, int *size, int offset, u64 side)
-{
-        struct vsp_cmd_data vsp_cmd;
-        int rc;
-        int len = *size;
-        dma_addr_t dma_addr;
-
-        dma_addr = iseries_hv_map(buffer, len, DMA_FROM_DEVICE);
-        memset(buffer, 0, len);
-        memset(&vsp_cmd, 0, sizeof(vsp_cmd));
-        vsp_cmd.cmd = 32;
-        vsp_cmd.sub_data.kern.token = dma_addr;
-        vsp_cmd.sub_data.kern.address_type = HvLpDma_AddressType_TceIndex;
-        vsp_cmd.sub_data.kern.side = side;
-        vsp_cmd.sub_data.kern.offset = offset;
-        vsp_cmd.sub_data.kern.length = len;
-        mb();
-        rc = signal_vsp_instruction(&vsp_cmd);
-        if (rc == 0) {
-                if (vsp_cmd.result_code == 0)
-                        *size = vsp_cmd.sub_data.length_out;
-                else
-                        rc = -ENOMEM;
-        }
-
-        iseries_hv_unmap(dma_addr, len, DMA_FROM_DEVICE);
-
-        return rc;
-}
-
-static int proc_mf_dump_vmlinux(char *page, char **start, off_t off,
-                int count, int *eof, void *data)
-{
-        int sizeToGet = count;
-
-        if (!capable(CAP_SYS_ADMIN))
-                return -EACCES;
-
-        if (mf_getVmlinuxChunk(page, &sizeToGet, off, (u64)data) == 0) {
-                if (sizeToGet != 0) {
-                        *start = page + off;
-                        return sizeToGet;
-                }
-                *eof = 1;
-                return 0;
-        }
-        *eof = 1;
-        return 0;
-}
-#endif
-
-static int mf_side_proc_show(struct seq_file *m, void *v)
-{
-        char mf_current_side = ' ';
-        struct vsp_cmd_data vsp_cmd;
-
-        memset(&vsp_cmd, 0, sizeof(vsp_cmd));
-        vsp_cmd.cmd = 2;
-        vsp_cmd.sub_data.ipl_type = 0;
-        mb();
-
-        if (signal_vsp_instruction(&vsp_cmd) == 0) {
-                if (vsp_cmd.result_code == 0) {
-                        switch (vsp_cmd.sub_data.ipl_type) {
-                        case 0: mf_current_side = 'A';
-                                break;
-                        case 1: mf_current_side = 'B';
-                                break;
-                        case 2: mf_current_side = 'C';
-                                break;
-                        default:        mf_current_side = 'D';
-                                break;
-                        }
-                }
-        }
-
-        seq_printf(m, "%c\n", mf_current_side);
-        return 0;
-}
-
-static int mf_side_proc_open(struct inode *inode, struct file *file)
-{
-        return single_open(file, mf_side_proc_show, NULL);
-}
-
-static ssize_t mf_side_proc_write(struct file *file, const char __user *buffer,
-                                  size_t count, loff_t *pos)
-{
-        char side;
-        u64 newSide;
-        struct vsp_cmd_data vsp_cmd;
-
-        if (!capable(CAP_SYS_ADMIN))
-                return -EACCES;
-
-        if (count == 0)
-                return 0;
-
-        if (get_user(side, buffer))
-                return -EFAULT;
-
-        switch (side) {
-        case 'A':       newSide = 0;
-                        break;
-        case 'B':       newSide = 1;
-                        break;
-        case 'C':       newSide = 2;
-                        break;
-        case 'D':       newSide = 3;
-                        break;
-        default:
-                printk(KERN_ERR "mf_proc.c: proc_mf_change_side: invalid side\n");
-                return -EINVAL;
-        }
-
-        memset(&vsp_cmd, 0, sizeof(vsp_cmd));
-        vsp_cmd.sub_data.ipl_type = newSide;
-        vsp_cmd.cmd = 10;
-
-        (void)signal_vsp_instruction(&vsp_cmd);
-
-        return count;
-}
-
-static const struct file_operations mf_side_proc_fops = {
-        .owner          = THIS_MODULE,
-        .open           = mf_side_proc_open,
-        .read           = seq_read,
-        .llseek         = seq_lseek,
-        .release        = single_release,
-        .write          = mf_side_proc_write,
-};
-
-static int mf_src_proc_show(struct seq_file *m, void *v)
-{
-        return 0;
-}
-
-static int mf_src_proc_open(struct inode *inode, struct file *file)
-{
-        return single_open(file, mf_src_proc_show, NULL);
-}
-
-static ssize_t mf_src_proc_write(struct file *file, const char __user *buffer,
-                                 size_t count, loff_t *pos)
-{
-        char stkbuf[10];
-
-        if (!capable(CAP_SYS_ADMIN))
-                return -EACCES;
-
-        if ((count < 4) && (count != 1)) {
-                printk(KERN_ERR "mf_proc: invalid src\n");
-                return -EINVAL;
-        }
-
-        if (count > (sizeof(stkbuf) - 1))
-                count = sizeof(stkbuf) - 1;
-        if (copy_from_user(stkbuf, buffer, count))
-                return -EFAULT;
-
-        if ((count == 1) && (*stkbuf == '\0'))
-                mf_clear_src();
-        else
-                mf_display_src(*(u32 *)stkbuf);
-
-        return count;
-}
-
-static const struct file_operations mf_src_proc_fops = {
-        .owner          = THIS_MODULE,
-        .open           = mf_src_proc_open,
-        .read           = seq_read,
-        .llseek         = seq_lseek,
-        .release        = single_release,
-        .write          = mf_src_proc_write,
-};
-
-static ssize_t mf_cmdline_proc_write(struct file *file, const char __user *buffer,
-                                     size_t count, loff_t *pos)
-{
-        void *data = PDE(file->f_path.dentry->d_inode)->data;
-        struct vsp_cmd_data vsp_cmd;
-        dma_addr_t dma_addr;
-        char *page;
-        int ret = -EACCES;
-
-        if (!capable(CAP_SYS_ADMIN))
-                goto out;
-
-        dma_addr = 0;
-        page = iseries_hv_alloc(count, &dma_addr, GFP_ATOMIC);
-        ret = -ENOMEM;
-        if (page == NULL)
-                goto out;
-
-        ret = -EFAULT;
-        if (copy_from_user(page, buffer, count))
-                goto out_free;
-
-        memset(&vsp_cmd, 0, sizeof(vsp_cmd));
-        vsp_cmd.cmd = 31;
-        vsp_cmd.sub_data.kern.token = dma_addr;
-        vsp_cmd.sub_data.kern.address_type = HvLpDma_AddressType_TceIndex;
-        vsp_cmd.sub_data.kern.side = (u64)data;
-        vsp_cmd.sub_data.kern.length = count;
-        mb();
-        (void)signal_vsp_instruction(&vsp_cmd);
-        ret = count;
-
-out_free:
-        iseries_hv_free(count, page, dma_addr);
-out:
-        return ret;
-}
-
-static const struct file_operations mf_cmdline_proc_fops = {
-        .owner          = THIS_MODULE,
-        .open           = mf_cmdline_proc_open,
-        .read           = seq_read,
-        .llseek         = seq_lseek,
-        .release        = single_release,
-        .write          = mf_cmdline_proc_write,
-};
-
-static ssize_t proc_mf_change_vmlinux(struct file *file,
-                                      const char __user *buf,
-                                      size_t count, loff_t *ppos)
-{
-        struct proc_dir_entry *dp = PDE(file->f_path.dentry->d_inode);
-        ssize_t rc;
-        dma_addr_t dma_addr;
-        char *page;
-        struct vsp_cmd_data vsp_cmd;
-
-        rc = -EACCES;
-        if (!capable(CAP_SYS_ADMIN))
-                goto out;
-
-        dma_addr = 0;
-        page = iseries_hv_alloc(count, &dma_addr, GFP_ATOMIC);
-        rc = -ENOMEM;
-        if (page == NULL) {
-                printk(KERN_ERR "mf.c: couldn't allocate memory to set vmlinux chunk\n");
-                goto out;
-        }
-        rc = -EFAULT;
-        if (copy_from_user(page, buf, count))
-                goto out_free;
-
-        memset(&vsp_cmd, 0, sizeof(vsp_cmd));
-        vsp_cmd.cmd = 30;
-        vsp_cmd.sub_data.kern.token = dma_addr;
-        vsp_cmd.sub_data.kern.address_type = HvLpDma_AddressType_TceIndex;
-        vsp_cmd.sub_data.kern.side = (u64)dp->data;
-        vsp_cmd.sub_data.kern.offset = *ppos;
-        vsp_cmd.sub_data.kern.length = count;
-        mb();
-        rc = signal_vsp_instruction(&vsp_cmd);
-        if (rc)
-                goto out_free;
-        rc = -ENOMEM;
-        if (vsp_cmd.result_code != 0)
-                goto out_free;
-
-        *ppos += count;
-        rc = count;
-out_free:
-        iseries_hv_free(count, page, dma_addr);
-out:
-        return rc;
-}
-
-static const struct file_operations proc_vmlinux_operations = {
-        .write          = proc_mf_change_vmlinux,
-        .llseek         = default_llseek,
-};
-
-static int __init mf_proc_init(void)
-{
-        struct proc_dir_entry *mf_proc_root;
-        struct proc_dir_entry *ent;
-        struct proc_dir_entry *mf;
-        char name[2];
-        int i;
-
-        if (!firmware_has_feature(FW_FEATURE_ISERIES))
-                return 0;
-
-        mf_proc_root = proc_mkdir("iSeries/mf", NULL);
-        if (!mf_proc_root)
-                return 1;
-
-        name[1] = '\0';
-        for (i = 0; i < 4; i++) {
-                name[0] = 'A' + i;
-                mf = proc_mkdir(name, mf_proc_root);
-                if (!mf)
-                        return 1;
-
-                ent = proc_create_data("cmdline", S_IRUSR|S_IWUSR, mf,
-                                       &mf_cmdline_proc_fops, (void *)(long)i);
-                if (!ent)
-                        return 1;
-
-                if (i == 3)     /* no vmlinux entry for 'D' */
-                        continue;
-
-                ent = proc_create_data("vmlinux", S_IFREG|S_IWUSR, mf,
-                                       &proc_vmlinux_operations,
-                                       (void *)(long)i);
-                if (!ent)
-                        return 1;
-        }
-
-        ent = proc_create("side", S_IFREG|S_IRUSR|S_IWUSR, mf_proc_root,
-                          &mf_side_proc_fops);
-        if (!ent)
-                return 1;
-
-        ent = proc_create("src", S_IFREG|S_IRUSR|S_IWUSR, mf_proc_root,
-                          &mf_src_proc_fops);
-        if (!ent)
-                return 1;
-
-        return 0;
-}
-
-__initcall(mf_proc_init);
-
-#endif /* CONFIG_PROC_FS */
-
-/*
- * Get the RTC from the virtual service processor
- * This requires flowing LpEvents to the primary partition
- */
-void iSeries_get_rtc_time(struct rtc_time *rtc_tm)
-{
-        mf_get_rtc(rtc_tm);
-        rtc_tm->tm_mon--;
-}
-
-/*
- * Set the RTC in the virtual service processor
- * This requires flowing LpEvents to the primary partition
- */
-int iSeries_set_rtc_time(struct rtc_time *tm)
-{
-        mf_set_rtc(tm);
-        return 0;
-}
-
-unsigned long iSeries_get_boot_time(void)
-{
-        struct rtc_time tm;
-
-        mf_get_boot_rtc(&tm);
-        return mktime(tm.tm_year + 1900, tm.tm_mon, tm.tm_mday,
-                      tm.tm_hour, tm.tm_min, tm.tm_sec);
-}
diff --git a/arch/powerpc/platforms/iseries/misc.S b/arch/powerpc/platforms/iseries/misc.S
deleted file mode 100644
index 2c6ff0fdac98..000000000000
--- a/arch/powerpc/platforms/iseries/misc.S
+++ /dev/null
@@ -1,26 +0,0 @@
-/*
- * This file contains miscellaneous low-level functions.
- *    Copyright (C) 1995-2005 IBM Corp
- *
- * Largely rewritten by Cort Dougan (cort@cs.nmt.edu)
- * and Paul Mackerras.
- * Adapted for iSeries by Mike Corrigan (mikejc@us.ibm.com)
- * PPC64 updates by Dave Engebretsen (engebret@us.ibm.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/processor.h>
-#include <asm/asm-offsets.h>
-#include <asm/ppc_asm.h>
-
-        .text
-
-/* Handle pending interrupts in interrupt context */
-_GLOBAL(iseries_handle_interrupts)
-        li      r0,0x5555
-        sc
-        blr
diff --git a/arch/powerpc/platforms/iseries/naca.h b/arch/powerpc/platforms/iseries/naca.h
deleted file mode 100644
index f01708e12862..000000000000
--- a/arch/powerpc/platforms/iseries/naca.h
+++ /dev/null
@@ -1,24 +0,0 @@
-#ifndef _PLATFORMS_ISERIES_NACA_H
-#define _PLATFORMS_ISERIES_NACA_H
-
-/*
- * c 2001 PPC 64 Team, 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/types.h>
-
-struct naca_struct {
-        /* Kernel only data - undefined for user space */
-        const void *xItVpdAreas;        /* VPD Data                  0x00 */
-        void *xRamDisk;                 /* iSeries ramdisk           0x08 */
-        u64   xRamDiskSize;             /* In pages                  0x10 */
-};
-
-extern struct naca_struct naca;
-
-#endif /* _PLATFORMS_ISERIES_NACA_H */
diff --git a/arch/powerpc/platforms/iseries/pci.c b/arch/powerpc/platforms/iseries/pci.c
deleted file mode 100644
index c75412884625..000000000000
--- a/arch/powerpc/platforms/iseries/pci.c
+++ /dev/null
@@ -1,919 +0,0 @@
-/*
- * Copyright (C) 2001 Allan Trautman, IBM Corporation
- * Copyright (C) 2005,2007  Stephen Rothwell, IBM Corp
- *
- * iSeries specific routines for PCI.
- *
- * Based on code from pci.c and iSeries_pci.c 32bit
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
- */
-
-#undef DEBUG
-
-#include <linux/jiffies.h>
-#include <linux/kernel.h>
-#include <linux/list.h>
-#include <linux/string.h>
-#include <linux/slab.h>
-#include <linux/init.h>
-#include <linux/pci.h>
-#include <linux/of.h>
-#include <linux/ratelimit.h>
-
-#include <asm/types.h>
-#include <asm/io.h>
-#include <asm/irq.h>
-#include <asm/prom.h>
-#include <asm/machdep.h>
-#include <asm/pci-bridge.h>
-#include <asm/iommu.h>
-#include <asm/abs_addr.h>
-#include <asm/firmware.h>
-
-#include <asm/iseries/hv_types.h>
-#include <asm/iseries/hv_call_xm.h>
-#include <asm/iseries/mf.h>
-#include <asm/iseries/iommu.h>
-
-#include <asm/ppc-pci.h>
-
-#include "irq.h"
-#include "pci.h"
-#include "call_pci.h"
-
-#define PCI_RETRY_MAX   3
-static int limit_pci_retries = 1;       /* Set Retry Error on. */
-
-/*
- * Table defines
- * Each Entry size is 4 MB * 1024 Entries = 4GB I/O address space.
- */
-#define IOMM_TABLE_MAX_ENTRIES  1024
-#define IOMM_TABLE_ENTRY_SIZE   0x0000000000400000UL
-#define BASE_IO_MEMORY          0xE000000000000000UL
-#define END_IO_MEMORY           0xEFFFFFFFFFFFFFFFUL
-
-static unsigned long max_io_memory = BASE_IO_MEMORY;
-static long current_iomm_table_entry;
-
-/*
- * Lookup Tables.
- */
-static struct device_node *iomm_table[IOMM_TABLE_MAX_ENTRIES];
-static u64 ds_addr_table[IOMM_TABLE_MAX_ENTRIES];
-
-static DEFINE_SPINLOCK(iomm_table_lock);
-
-/*
- * Generate a Direct Select Address for the Hypervisor
- */
-static inline u64 iseries_ds_addr(struct device_node *node)
-{
-        struct pci_dn *pdn = PCI_DN(node);
-        const u32 *sbp = of_get_property(node, "linux,subbus", NULL);
-
-        return ((u64)pdn->busno << 48) + ((u64)(sbp ? *sbp : 0) << 40)
-                        + ((u64)0x10 << 32);
-}
-
-/*
- * Size of Bus VPD data
- */
-#define BUS_VPDSIZE      1024
-
-/*
- * Bus Vpd Tags
- */
-#define VPD_END_OF_AREA         0x79
-#define VPD_ID_STRING           0x82
-#define VPD_VENDOR_AREA         0x84
-
-/*
- * Mfg Area Tags
- */
-#define VPD_FRU_FRAME_ID        0x4649  /* "FI" */
-#define VPD_SLOT_MAP_FORMAT     0x4D46  /* "MF" */
-#define VPD_SLOT_MAP            0x534D  /* "SM" */
-
-/*
- * Structures of the areas
- */
-struct mfg_vpd_area {
-        u16     tag;
-        u8      length;
-        u8      data1;
-        u8      data2;
-};
-#define MFG_ENTRY_SIZE   3
-
-struct slot_map {
-        u8      agent;
-        u8      secondary_agent;
-        u8      phb;
-        char    card_location[3];
-        char    parms[8];
-        char    reserved[2];
-};
-#define SLOT_ENTRY_SIZE   16
-
-/*
- * Parse the Slot Area
- */
-static void __init iseries_parse_slot_area(struct slot_map *map, int len,
-                HvAgentId agent, u8 *phb, char card[4])
-{
-        /*
-         * Parse Slot label until we find the one requested
-         */
-        while (len > 0) {
-                if (map->agent == agent) {
-                        /*
-                         * If Phb wasn't found, grab the entry first one found.
-                         */
-                        if (*phb == 0xff)
-                                *phb = map->phb;
-                        /* Found it, extract the data. */
-                        if (map->phb == *phb) {
-                                memcpy(card, &map->card_location, 3);
-                                card[3]  = 0;
-                                break;
-                        }
-                }
-                /* Point to the next Slot */
-                map = (struct slot_map *)((char *)map + SLOT_ENTRY_SIZE);
-                len -= SLOT_ENTRY_SIZE;
-        }
-}
-
-/*
- * Parse the Mfg Area
- */
-static void __init iseries_parse_mfg_area(struct mfg_vpd_area *area, int len,
-                HvAgentId agent, u8 *phb, u8 *frame, char card[4])
-{
-        u16 slot_map_fmt = 0;
-
-        /* Parse Mfg Data */
-        while (len > 0) {
-                int mfg_tag_len = area->length;
-                /* Frame ID         (FI 4649020310 ) */
-                if (area->tag == VPD_FRU_FRAME_ID)
-                        *frame = area->data1;
-                /* Slot Map Format  (MF 4D46020004 ) */
-                else if (area->tag == VPD_SLOT_MAP_FORMAT)
-                        slot_map_fmt = (area->data1 * 256)
-                                + area->data2;
-                /* Slot Map         (SM 534D90 */
-                else if (area->tag == VPD_SLOT_MAP) {
-                        struct slot_map *slot_map;
-
-                        if (slot_map_fmt == 0x1004)
-                                slot_map = (struct slot_map *)((char *)area
-                                                + MFG_ENTRY_SIZE + 1);
-                        else
-                                slot_map = (struct slot_map *)((char *)area
-                                                + MFG_ENTRY_SIZE);
-                        iseries_parse_slot_area(slot_map, mfg_tag_len,
-                                        agent, phb, card);
-                }
-                /*
-                 * Point to the next Mfg Area
-                 * Use defined size, sizeof give wrong answer
-                 */
-                area = (struct mfg_vpd_area *)((char *)area + mfg_tag_len
-                                + MFG_ENTRY_SIZE);
-                len -= (mfg_tag_len + MFG_ENTRY_SIZE);
-        }
-}
-
-/*
- * Look for "BUS".. Data is not Null terminated.
- * PHBID of 0xFF indicates PHB was not found in VPD Data.
- */
-static u8 __init iseries_parse_phbid(u8 *area, int len)
-{
-        while (len > 0) {
-                if ((*area == 'B') && (*(area + 1) == 'U')
-                                && (*(area + 2) == 'S')) {
-                        area += 3;
-                        while (*area == ' ')
-                                area++;
-                        return *area & 0x0F;
-                }
-                area++;
-                len--;
-        }
-        return 0xff;
-}
-
-/*
- * Parse out the VPD Areas
- */
-static void __init iseries_parse_vpd(u8 *data, int data_len,
-                HvAgentId agent, u8 *frame, char card[4])
-{
-        u8 phb = 0xff;
-
-        while (data_len > 0) {
-                int len;
-                u8 tag = *data;
-
-                if (tag == VPD_END_OF_AREA)
-                        break;
-                len = *(data + 1) + (*(data + 2) * 256);
-                data += 3;
-                data_len -= 3;
-                if (tag == VPD_ID_STRING)
-                        phb = iseries_parse_phbid(data, len);
-                else if (tag == VPD_VENDOR_AREA)
-                        iseries_parse_mfg_area((struct mfg_vpd_area *)data, len,
-                                        agent, &phb, frame, card);
-                /* Point to next Area. */
-                data += len;
-                data_len -= len;
-        }
-}
-
-static int __init iseries_get_location_code(u16 bus, HvAgentId agent,
-                u8 *frame, char card[4])
-{
-        int status = 0;
-        int bus_vpd_len = 0;
-        u8 *bus_vpd = kmalloc(BUS_VPDSIZE, GFP_KERNEL);
-
-        if (bus_vpd == NULL) {
-                printk("PCI: Bus VPD Buffer allocation failure.\n");
-                return 0;
-        }
-        bus_vpd_len = HvCallPci_getBusVpd(bus, iseries_hv_addr(bus_vpd),
-                                        BUS_VPDSIZE);
-        if (bus_vpd_len == 0) {
-                printk("PCI: Bus VPD Buffer zero length.\n");
-                goto out_free;
-        }
-        /* printk("PCI: bus_vpd: %p, %d\n",bus_vpd, bus_vpd_len); */
-        /* Make sure this is what I think it is */
-        if (*bus_vpd != VPD_ID_STRING) {
-                printk("PCI: Bus VPD Buffer missing starting tag.\n");
-                goto out_free;
-        }
-        iseries_parse_vpd(bus_vpd, bus_vpd_len, agent, frame, card);
-        status = 1;
-out_free:
-        kfree(bus_vpd);
-        return status;
-}
-
-/*
- * Prints the device information.
- * - Pass in pci_dev* pointer to the device.
- * - Pass in the device count
- *
- * Format:
- * PCI: Bus  0, Device 26, Vendor 0x12AE  Frame  1, Card  C10  Ethernet
- * controller
- */
-static void __init iseries_device_information(struct pci_dev *pdev,
-                                              u16 bus, HvSubBusNumber subbus)
-{
-        u8 frame = 0;
-        char card[4];
-        HvAgentId agent;
-
-        agent = ISERIES_PCI_AGENTID(ISERIES_GET_DEVICE_FROM_SUBBUS(subbus),
-                        ISERIES_GET_FUNCTION_FROM_SUBBUS(subbus));
-
-        if (iseries_get_location_code(bus, agent, &frame, card)) {
-                printk(KERN_INFO "PCI: %s, Vendor %04X Frame%3d, "
-                       "Card %4s  0x%04X\n", pci_name(pdev), pdev->vendor,
-                       frame, card, (int)(pdev->class >> 8));
-        }
-}
-
-/*
- * iomm_table_allocate_entry
- *
- * Adds pci_dev entry in address translation table
- *
- * - Allocates the number of entries required in table base on BAR
- *   size.
- * - Allocates starting at BASE_IO_MEMORY and increases.
- * - The size is round up to be a multiple of entry size.
- * - CurrentIndex is incremented to keep track of the last entry.
- * - Builds the resource entry for allocated BARs.
- */
-static void __init iomm_table_allocate_entry(struct pci_dev *dev, int bar_num)
-{
-        struct resource *bar_res = &dev->resource[bar_num];
-        long bar_size = pci_resource_len(dev, bar_num);
-        struct device_node *dn = pci_device_to_OF_node(dev);
-
-        /*
-         * No space to allocate, quick exit, skip Allocation.
-         */
-        if (bar_size == 0)
-                return;
-        /*
-         * Set Resource values.
-         */
-        spin_lock(&iomm_table_lock);
-        bar_res->start = BASE_IO_MEMORY +
-                IOMM_TABLE_ENTRY_SIZE * current_iomm_table_entry;
-        bar_res->end = bar_res->start + bar_size - 1;
-        /*
-         * Allocate the number of table entries needed for BAR.
-         */
-        while (bar_size > 0 ) {
-                iomm_table[current_iomm_table_entry] = dn;
-                ds_addr_table[current_iomm_table_entry] =
-                        iseries_ds_addr(dn) | (bar_num << 24);
-                bar_size -= IOMM_TABLE_ENTRY_SIZE;
-                ++current_iomm_table_entry;
-        }
-        max_io_memory = BASE_IO_MEMORY +
-                IOMM_TABLE_ENTRY_SIZE * current_iomm_table_entry;
-        spin_unlock(&iomm_table_lock);
-}
-
-/*
- * allocate_device_bars
- *
- * - Allocates ALL pci_dev BAR's and updates the resources with the
- *   BAR value.  BARS with zero length will have the resources
- *   The HvCallPci_getBarParms is used to get the size of the BAR
- *   space.  It calls iomm_table_allocate_entry to allocate
- *   each entry.
- * - Loops through The Bar resources(0 - 5) including the ROM
- *   is resource(6).
- */
-static void __init allocate_device_bars(struct pci_dev *dev)
-{
-        int bar_num;
-
-        for (bar_num = 0; bar_num <= PCI_ROM_RESOURCE; ++bar_num)
-                iomm_table_allocate_entry(dev, bar_num);
-}
-
-/*
- * Log error information to system console.
- * Filter out the device not there errors.
- * PCI: EADs Connect Failed 0x18.58.10 Rc: 0x00xx
- * PCI: Read Vendor Failed 0x18.58.10 Rc: 0x00xx
- * PCI: Connect Bus Unit Failed 0x18.58.10 Rc: 0x00xx
- */
-static void pci_log_error(char *error, int bus, int subbus,
-                int agent, int hv_res)
-{
-        if (hv_res == 0x0302)
-                return;
-        printk(KERN_ERR "PCI: %s Failed: 0x%02X.%02X.%02X Rc: 0x%04X",
-               error, bus, subbus, agent, hv_res);
-}
-
-/*
- * Look down the chain to find the matching Device Device
- */
-static struct device_node *find_device_node(int bus, int devfn)
-{
-        struct device_node *node;
-
-        for (node = NULL; (node = of_find_all_nodes(node)); ) {
-                struct pci_dn *pdn = PCI_DN(node);
-
-                if (pdn && (bus == pdn->busno) && (devfn == pdn->devfn))
-                        return node;
-        }
-        return NULL;
-}
-
-/*
- * iSeries_pcibios_fixup_resources
- *
- * Fixes up all resources for devices
- */
-void __init iSeries_pcibios_fixup_resources(struct pci_dev *pdev)
-{
-        const u32 *agent;
-        const u32 *sub_bus;
-        unsigned char bus = pdev->bus->number;
-        struct device_node *node;
-        int i;
-
-        node = pci_device_to_OF_node(pdev);
-        pr_debug("PCI: iSeries %s, pdev %p, node %p\n",
-                 pci_name(pdev), pdev, node);
-        if (!node) {
-                printk("PCI: %s disabled, device tree entry not found !\n",
-                       pci_name(pdev));
-                for (i = 0; i <= PCI_ROM_RESOURCE; i++)
-                        pdev->resource[i].flags = 0;
-                return;
-        }
-        sub_bus = of_get_property(node, "linux,subbus", NULL);
-        agent = of_get_property(node, "linux,agent-id", NULL);
-        if (agent && sub_bus) {
-                u8 irq = iSeries_allocate_IRQ(bus, 0, *sub_bus);
-                int err;
-
-                err = HvCallXm_connectBusUnit(bus, *sub_bus, *agent, irq);
-                if (err)
-                        pci_log_error("Connect Bus Unit",
-                                      bus, *sub_bus, *agent, err);
-                else {
-                        err = HvCallPci_configStore8(bus, *sub_bus,
-                                        *agent, PCI_INTERRUPT_LINE, irq);
-                        if (err)
-                                pci_log_error("PciCfgStore Irq Failed!",
-                                                bus, *sub_bus, *agent, err);
-                        else
-                                pdev->irq = irq;
-                }
-        }
-
-        allocate_device_bars(pdev);
-        if (likely(sub_bus))
-                iseries_device_information(pdev, bus, *sub_bus);
-        else
-                printk(KERN_ERR "PCI: Device node %s has missing or invalid "
-                                "linux,subbus property\n", node->full_name);
-}
-
-/*
- * iSeries_pci_final_fixup(void)
- */
-void __init iSeries_pci_final_fixup(void)
-{
-        /* Fix up at the device node and pci_dev relationship */
-        mf_display_src(0xC9000100);
-        iSeries_activate_IRQs();
-        mf_display_src(0xC9000200);
-}
-
-/*
- * Config space read and write functions.
- * For now at least, we look for the device node for the bus and devfn
- * that we are asked to access.  It may be possible to translate the devfn
- * to a subbus and deviceid more directly.
- */
-static u64 hv_cfg_read_func[4]  = {
-        HvCallPciConfigLoad8, HvCallPciConfigLoad16,
-        HvCallPciConfigLoad32, HvCallPciConfigLoad32
-};
-
-static u64 hv_cfg_write_func[4] = {
-        HvCallPciConfigStore8, HvCallPciConfigStore16,
-        HvCallPciConfigStore32, HvCallPciConfigStore32
-};
-
-/*
- * Read PCI config space
- */
-static int iSeries_pci_read_config(struct pci_bus *bus, unsigned int devfn,
-                int offset, int size, u32 *val)
-{
-        struct device_node *node = find_device_node(bus->number, devfn);
-        u64 fn;
-        struct HvCallPci_LoadReturn ret;
-
-        if (node == NULL)
-                return PCIBIOS_DEVICE_NOT_FOUND;
-        if (offset > 255) {
-                *val = ~0;
-                return PCIBIOS_BAD_REGISTER_NUMBER;
-        }
-
-        fn = hv_cfg_read_func[(size - 1) & 3];
-        HvCall3Ret16(fn, &ret, iseries_ds_addr(node), offset, 0);
-
-        if (ret.rc != 0) {
-                *val = ~0;
-                return PCIBIOS_DEVICE_NOT_FOUND;        /* or something */
-        }
-
-        *val = ret.value;
-        return 0;
-}
-
-/*
- * Write PCI config space
- */
-
-static int iSeries_pci_write_config(struct pci_bus *bus, unsigned int devfn,
-                int offset, int size, u32 val)
-{
-        struct device_node *node = find_device_node(bus->number, devfn);
-        u64 fn;
-        u64 ret;
-
-        if (node == NULL)
-                return PCIBIOS_DEVICE_NOT_FOUND;
-        if (offset > 255)
-                return PCIBIOS_BAD_REGISTER_NUMBER;
-
-        fn = hv_cfg_write_func[(size - 1) & 3];
-        ret = HvCall4(fn, iseries_ds_addr(node), offset, val, 0);
-
-        if (ret != 0)
-                return PCIBIOS_DEVICE_NOT_FOUND;
-
-        return 0;
-}
-
-static struct pci_ops iSeries_pci_ops = {
-        .read = iSeries_pci_read_config,
-        .write = iSeries_pci_write_config
-};
-
-/*
- * Check Return Code
- * -> On Failure, print and log information.
- *    Increment Retry Count, if exceeds max, panic partition.
- *
- * PCI: Device 23.90 ReadL I/O Error( 0): 0x1234
- * PCI: Device 23.90 ReadL Retry( 1)
- * PCI: Device 23.90 ReadL Retry Successful(1)
- */
-static int check_return_code(char *type, struct device_node *dn,
-                int *retry, u64 ret)
-{
-        if (ret != 0)  {
-                struct pci_dn *pdn = PCI_DN(dn);
-
-                (*retry)++;
-                printk("PCI: %s: Device 0x%04X:%02X  I/O Error(%2d): 0x%04X\n",
-                                type, pdn->busno, pdn->devfn,
-                                *retry, (int)ret);
-                /*
-                 * Bump the retry and check for retry count exceeded.
-                 * If, Exceeded, panic the system.
-                 */
-                if (((*retry) > PCI_RETRY_MAX) &&
-                                (limit_pci_retries > 0)) {
-                        mf_display_src(0xB6000103);
-                        panic_timeout = 0;
-                        panic("PCI: Hardware I/O Error, SRC B6000103, "
-                                        "Automatic Reboot Disabled.\n");
-                }
-                return -1;      /* Retry Try */
-        }
-        return 0;
-}
-
-/*
- * Translate the I/O Address into a device node, bar, and bar offset.
- * Note: Make sure the passed variable end up on the stack to avoid
- * the exposure of being device global.
- */
-static inline struct device_node *xlate_iomm_address(
-                const volatile void __iomem *addr,
-                u64 *dsaptr, u64 *bar_offset, const char *func)
-{
-        unsigned long orig_addr;
-        unsigned long base_addr;
-        unsigned long ind;
-        struct device_node *dn;
-
-        orig_addr = (unsigned long __force)addr;
-        if ((orig_addr < BASE_IO_MEMORY) || (orig_addr >= max_io_memory)) {
-                static DEFINE_RATELIMIT_STATE(ratelimit, 60 * HZ, 10);
-
-                if (__ratelimit(&ratelimit))
-                        printk(KERN_ERR
-                                "iSeries_%s: invalid access at IO address %p\n",
-                                func, addr);
-                return NULL;
-        }
-        base_addr = orig_addr - BASE_IO_MEMORY;
-        ind = base_addr / IOMM_TABLE_ENTRY_SIZE;
-        dn = iomm_table[ind];
-
-        if (dn != NULL) {
-                *dsaptr = ds_addr_table[ind];
-                *bar_offset = base_addr % IOMM_TABLE_ENTRY_SIZE;
-        } else
-                panic("PCI: Invalid PCI IO address detected!\n");
-        return dn;
-}
-
-/*
- * Read MM I/O Instructions for the iSeries
- * On MM I/O error, all ones are returned and iSeries_pci_IoError is cal
- * else, data is returned in Big Endian format.
- */
-static u8 iseries_readb(const volatile void __iomem *addr)
-{
-        u64 bar_offset;
-        u64 dsa;
-        int retry = 0;
-        struct HvCallPci_LoadReturn ret;
-        struct device_node *dn =
-                xlate_iomm_address(addr, &dsa, &bar_offset, "read_byte");
-
-        if (dn == NULL)
-                return 0xff;
-        do {
-                HvCall3Ret16(HvCallPciBarLoad8, &ret, dsa, bar_offset, 0);
-        } while (check_return_code("RDB", dn, &retry, ret.rc) != 0);
-
-        return ret.value;
-}
-
-static u16 iseries_readw_be(const volatile void __iomem *addr)
-{
-        u64 bar_offset;
-        u64 dsa;
-        int retry = 0;
-        struct HvCallPci_LoadReturn ret;
-        struct device_node *dn =
-                xlate_iomm_address(addr, &dsa, &bar_offset, "read_word");
-
-        if (dn == NULL)
-                return 0xffff;
-        do {
-                HvCall3Ret16(HvCallPciBarLoad16, &ret, dsa,
-                                bar_offset, 0);
-        } while (check_return_code("RDW", dn, &retry, ret.rc) != 0);
-
-        return ret.value;
-}
-
-static u32 iseries_readl_be(const volatile void __iomem *addr)
-{
-        u64 bar_offset;
-        u64 dsa;
-        int retry = 0;
-        struct HvCallPci_LoadReturn ret;
-        struct device_node *dn =
-                xlate_iomm_address(addr, &dsa, &bar_offset, "read_long");
-
-        if (dn == NULL)
-                return 0xffffffff;
-        do {
-                HvCall3Ret16(HvCallPciBarLoad32, &ret, dsa,
-                                bar_offset, 0);
-        } while (check_return_code("RDL", dn, &retry, ret.rc) != 0);
-
-        return ret.value;
-}
-
-/*
- * Write MM I/O Instructions for the iSeries
- *
- */
-static void iseries_writeb(u8 data, volatile void __iomem *addr)
-{
-        u64 bar_offset;
-        u64 dsa;
-        int retry = 0;
-        u64 rc;
-        struct device_node *dn =
-                xlate_iomm_address(addr, &dsa, &bar_offset, "write_byte");
-
-        if (dn == NULL)
-                return;
-        do {
-                rc = HvCall4(HvCallPciBarStore8, dsa, bar_offset, data, 0);
-        } while (check_return_code("WWB", dn, &retry, rc) != 0);
-}
-
-static void iseries_writew_be(u16 data, volatile void __iomem *addr)
-{
-        u64 bar_offset;
-        u64 dsa;
-        int retry = 0;
-        u64 rc;
-        struct device_node *dn =
-                xlate_iomm_address(addr, &dsa, &bar_offset, "write_word");
-
-        if (dn == NULL)
-                return;
-        do {
-                rc = HvCall4(HvCallPciBarStore16, dsa, bar_offset, data, 0);
-        } while (check_return_code("WWW", dn, &retry, rc) != 0);
-}
-
-static void iseries_writel_be(u32 data, volatile void __iomem *addr)
-{
-        u64 bar_offset;
-        u64 dsa;
-        int retry = 0;
-        u64 rc;
-        struct device_node *dn =
-                xlate_iomm_address(addr, &dsa, &bar_offset, "write_long");
-
-        if (dn == NULL)
-                return;
-        do {
-                rc = HvCall4(HvCallPciBarStore32, dsa, bar_offset, data, 0);
-        } while (check_return_code("WWL", dn, &retry, rc) != 0);
-}
-
-static u16 iseries_readw(const volatile void __iomem *addr)
-{
-        return le16_to_cpu(iseries_readw_be(addr));
-}
-
-static u32 iseries_readl(const volatile void __iomem *addr)
-{
-        return le32_to_cpu(iseries_readl_be(addr));
-}
-
-static void iseries_writew(u16 data, volatile void __iomem *addr)
-{
-        iseries_writew_be(cpu_to_le16(data), addr);
-}
-
-static void iseries_writel(u32 data, volatile void __iomem *addr)
-{
-        iseries_writel(cpu_to_le32(data), addr);
-}
-
-static void iseries_readsb(const volatile void __iomem *addr, void *buf,
-                           unsigned long count)
-{
-        u8 *dst = buf;
-        while(count-- > 0)
-                *(dst++) = iseries_readb(addr);
-}
-
-static void iseries_readsw(const volatile void __iomem *addr, void *buf,
-                           unsigned long count)
-{
-        u16 *dst = buf;
-        while(count-- > 0)
-                *(dst++) = iseries_readw_be(addr);
-}
-
-static void iseries_readsl(const volatile void __iomem *addr, void *buf,
-                           unsigned long count)
-{
-        u32 *dst = buf;
-        while(count-- > 0)
-                *(dst++) = iseries_readl_be(addr);
-}
-
-static void iseries_writesb(volatile void __iomem *addr, const void *buf,
-                            unsigned long count)
-{
-        const u8 *src = buf;
-        while(count-- > 0)
-                iseries_writeb(*(src++), addr);
-}
-
-static void iseries_writesw(volatile void __iomem *addr, const void *buf,
-                            unsigned long count)
-{
-        const u16 *src = buf;
-        while(count-- > 0)
-                iseries_writew_be(*(src++), addr);
-}
-
-static void iseries_writesl(volatile void __iomem *addr, const void *buf,
-                            unsigned long count)
-{
-        const u32 *src = buf;
-        while(count-- > 0)
-                iseries_writel_be(*(src++), addr);
-}
-
-static void iseries_memset_io(volatile void __iomem *addr, int c,
-                              unsigned long n)
-{
-        volatile char __iomem *d = addr;
-
-        while (n-- > 0)
-                iseries_writeb(c, d++);
-}
-
-static void iseries_memcpy_fromio(void *dest, const volatile void __iomem *src,
-                                  unsigned long n)
-{
-        char *d = dest;
-        const volatile char __iomem *s = src;
-
-        while (n-- > 0)
-                *d++ = iseries_readb(s++);
-}
-
-static void iseries_memcpy_toio(volatile void __iomem *dest, const void *src,
-                                unsigned long n)
-{
-        const char *s = src;
-        volatile char __iomem *d = dest;
-
-        while (n-- > 0)
-                iseries_writeb(*s++, d++);
-}
-
-/* We only set MMIO ops. The default PIO ops will be default
- * to the MMIO ops + pci_io_base which is 0 on iSeries as
- * expected so both should work.
- *
- * Note that we don't implement the readq/writeq versions as
- * I don't know of an HV call for doing so. Thus, the default
- * operation will be used instead, which will fault a the value
- * return by iSeries for MMIO addresses always hits a non mapped
- * area. This is as good as the BUG() we used to have there.
- */
-static struct ppc_pci_io __initdata iseries_pci_io = {
-        .readb = iseries_readb,
-        .readw = iseries_readw,
-        .readl = iseries_readl,
-        .readw_be = iseries_readw_be,
-        .readl_be = iseries_readl_be,
-        .writeb = iseries_writeb,
-        .writew = iseries_writew,
-        .writel = iseries_writel,
-        .writew_be = iseries_writew_be,
-        .writel_be = iseries_writel_be,
-        .readsb = iseries_readsb,
-        .readsw = iseries_readsw,
-        .readsl = iseries_readsl,
-        .writesb = iseries_writesb,
-        .writesw = iseries_writesw,
-        .writesl = iseries_writesl,
-        .memset_io = iseries_memset_io,
-        .memcpy_fromio = iseries_memcpy_fromio,
-        .memcpy_toio = iseries_memcpy_toio,
-};
-
-/*
- * iSeries_pcibios_init
- *
- * Description:
- *   This function checks for all possible system PCI host bridges that connect
- *   PCI buses.  The system hypervisor is queried as to the guest partition
- *   ownership status.  A pci_controller is built for any bus which is partially
- *   owned or fully owned by this guest partition.
- */
-void __init iSeries_pcibios_init(void)
-{
-        struct pci_controller *phb;
-        struct device_node *root = of_find_node_by_path("/");
-        struct device_node *node = NULL;
-
-        /* Install IO hooks */
-        ppc_pci_io = iseries_pci_io;
-
-        pci_probe_only = 1;
-
-        /* iSeries has no IO space in the common sense, it needs to set
-         * the IO base to 0
-         */
-        pci_io_base = 0;
-
-        if (root == NULL) {
-                printk(KERN_CRIT "iSeries_pcibios_init: can't find root "
-                                "of device tree\n");
-                return;
-        }
-        while ((node = of_get_next_child(root, node)) != NULL) {
-                HvBusNumber bus;
-                const u32 *busp;
-
-                if ((node->type == NULL) || (strcmp(node->type, "pci") != 0))
-                        continue;
-
-                busp = of_get_property(node, "bus-range", NULL);
-                if (busp == NULL)
-                        continue;
-                bus = *busp;
-                printk("bus %d appears to exist\n", bus);
-                phb = pcibios_alloc_controller(node);
-                if (phb == NULL)
-                        continue;
-                /* All legacy iSeries PHBs are in domain zero */
-                phb->global_number = 0;
-
-                phb->first_busno = bus;
-                phb->last_busno = bus;
-                phb->ops = &iSeries_pci_ops;
-                phb->io_base_virt = (void __iomem *)_IO_BASE;
-                phb->io_resource.flags = IORESOURCE_IO;
-                phb->io_resource.start = BASE_IO_MEMORY;
-                phb->io_resource.end = END_IO_MEMORY;
-                phb->io_resource.name = "iSeries PCI IO";
-                phb->mem_resources[0].flags = IORESOURCE_MEM;
-                phb->mem_resources[0].start = BASE_IO_MEMORY;
-                phb->mem_resources[0].end = END_IO_MEMORY;
-                phb->mem_resources[0].name = "Series PCI MEM";
-        }
-
-        of_node_put(root);
-
-        pci_devs_phb_init();
-}
-
diff --git a/arch/powerpc/platforms/iseries/pci.h b/arch/powerpc/platforms/iseries/pci.h
deleted file mode 100644
index d9cf974c2718..000000000000
--- a/arch/powerpc/platforms/iseries/pci.h
+++ /dev/null
@@ -1,58 +0,0 @@
-#ifndef _PLATFORMS_ISERIES_PCI_H
-#define _PLATFORMS_ISERIES_PCI_H
-
-/*
- * Created by Allan Trautman on Tue Feb 20, 2001.
- *
- * Define some useful macros for the iSeries pci routines.
- * Copyright (C) 2001  Allan H Trautman, 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.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the:
- * Free Software Foundation, Inc.,
- * 59 Temple Place, Suite 330,
- * Boston, MA  02111-1307  USA
- *
- * Change Activity:
- *   Created Feb 20, 2001
- *   Added device reset, March 22, 2001
- *   Ported to ppc64, May 25, 2001
- * End Change Activity
- */
-
-/*
- * Decodes Linux DevFn to iSeries DevFn, bridge device, or function.
- * For Linux, see PCI_SLOT and PCI_FUNC in include/linux/pci.h
- */
-
-#define ISERIES_PCI_AGENTID(idsel, func)        \
-        (((idsel & 0x0F) << 4) | (func & 0x07))
-#define ISERIES_ENCODE_DEVICE(agentid)          \
-        ((0x10) | ((agentid & 0x20) >> 2) | (agentid & 0x07))
-
-#define ISERIES_GET_DEVICE_FROM_SUBBUS(subbus)          ((subbus >> 5) & 0x7)
-#define ISERIES_GET_FUNCTION_FROM_SUBBUS(subbus)        ((subbus >> 2) & 0x7)
-
-struct pci_dev;
-
-#ifdef CONFIG_PCI
-extern void     iSeries_pcibios_init(void);
-extern void     iSeries_pci_final_fixup(void);
-extern void     iSeries_pcibios_fixup_resources(struct pci_dev *dev);
-#else
-static inline void      iSeries_pcibios_init(void) { }
-static inline void      iSeries_pci_final_fixup(void) { }
-static inline void      iSeries_pcibios_fixup_resources(struct pci_dev *dev) {}
-#endif
-
-#endif /* _PLATFORMS_ISERIES_PCI_H */
diff --git a/arch/powerpc/platforms/iseries/proc.c b/arch/powerpc/platforms/iseries/proc.c
deleted file mode 100644
index 06763682db47..000000000000
--- a/arch/powerpc/platforms/iseries/proc.c
+++ /dev/null
@@ -1,120 +0,0 @@
-/*
- * Copyright (C) 2001  Kyle A. Lucke IBM Corporation
- * Copyright (C) 2001 Mike Corrigan & Dave Engebretsen 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.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
- */
-#include <linux/init.h>
-#include <linux/proc_fs.h>
-#include <linux/seq_file.h>
-#include <linux/param.h>                /* for HZ */
-#include <asm/paca.h>
-#include <asm/processor.h>
-#include <asm/time.h>
-#include <asm/lppaca.h>
-#include <asm/firmware.h>
-#include <asm/iseries/hv_call_xm.h>
-
-#include "processor_vpd.h"
-#include "main_store.h"
-
-static int __init iseries_proc_create(void)
-{
-        struct proc_dir_entry *e;
-
-        if (!firmware_has_feature(FW_FEATURE_ISERIES))
-                return 0;
-
-        e = proc_mkdir("iSeries", 0);
-        if (!e)
-                return 1;
-
-        return 0;
-}
-core_initcall(iseries_proc_create);
-
-static unsigned long startTitan = 0;
-static unsigned long startTb = 0;
-
-static int proc_titantod_show(struct seq_file *m, void *v)
-{
-        unsigned long tb0, titan_tod;
-
-        tb0 = get_tb();
-        titan_tod = HvCallXm_loadTod();
-
-        seq_printf(m, "Titan\n" );
-        seq_printf(m, "  time base =          %016lx\n", tb0);
-        seq_printf(m, "  titan tod =          %016lx\n", titan_tod);
-        seq_printf(m, "  xProcFreq =          %016x\n",
-                   xIoHriProcessorVpd[0].xProcFreq);
-        seq_printf(m, "  xTimeBaseFreq =      %016x\n",
-                   xIoHriProcessorVpd[0].xTimeBaseFreq);
-        seq_printf(m, "  tb_ticks_per_jiffy = %lu\n", tb_ticks_per_jiffy);
-        seq_printf(m, "  tb_ticks_per_usec  = %lu\n", tb_ticks_per_usec);
-
-        if (!startTitan) {
-                startTitan = titan_tod;
-                startTb = tb0;
-        } else {
-                unsigned long titan_usec = (titan_tod - startTitan) >> 12;
-                unsigned long tb_ticks = (tb0 - startTb);
-                unsigned long titan_jiffies = titan_usec / (1000000/HZ);
-                unsigned long titan_jiff_usec = titan_jiffies * (1000000/HZ);
-                unsigned long titan_jiff_rem_usec =
-                        titan_usec - titan_jiff_usec;
-                unsigned long tb_jiffies = tb_ticks / tb_ticks_per_jiffy;
-                unsigned long tb_jiff_ticks = tb_jiffies * tb_ticks_per_jiffy;
-                unsigned long tb_jiff_rem_ticks = tb_ticks - tb_jiff_ticks;
-                unsigned long tb_jiff_rem_usec =
-                        tb_jiff_rem_ticks / tb_ticks_per_usec;
-                unsigned long new_tb_ticks_per_jiffy =
-                        (tb_ticks * (1000000/HZ))/titan_usec;
-
-                seq_printf(m, "  titan elapsed = %lu uSec\n", titan_usec);
-                seq_printf(m, "  tb elapsed    = %lu ticks\n", tb_ticks);
-                seq_printf(m, "  titan jiffies = %lu.%04lu\n", titan_jiffies,
-                           titan_jiff_rem_usec);
-                seq_printf(m, "  tb jiffies    = %lu.%04lu\n", tb_jiffies,
-                           tb_jiff_rem_usec);
-                seq_printf(m, "  new tb_ticks_per_jiffy = %lu\n",
-                           new_tb_ticks_per_jiffy);
-        }
-
-        return 0;
-}
-
-static int proc_titantod_open(struct inode *inode, struct file *file)
-{
-        return single_open(file, proc_titantod_show, NULL);
-}
-
-static const struct file_operations proc_titantod_operations = {
-        .open           = proc_titantod_open,
-        .read           = seq_read,
-        .llseek         = seq_lseek,
-        .release        = single_release,
-};
-
-static int __init iseries_proc_init(void)
-{
-        if (!firmware_has_feature(FW_FEATURE_ISERIES))
-                return 0;
-
-        proc_create("iSeries/titanTod", S_IFREG|S_IRUGO, NULL,
-                    &proc_titantod_operations);
-        return 0;
-}
-__initcall(iseries_proc_init);
diff --git a/arch/powerpc/platforms/iseries/processor_vpd.h b/arch/powerpc/platforms/iseries/processor_vpd.h
deleted file mode 100644
index 7ac5d0d0dbfa..000000000000
--- a/arch/powerpc/platforms/iseries/processor_vpd.h
+++ /dev/null
@@ -1,85 +0,0 @@
-/*
- * Copyright (C) 2001  Mike Corrigan 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.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
- */
-#ifndef _ISERIES_PROCESSOR_VPD_H
-#define _ISERIES_PROCESSOR_VPD_H
-
-#include <asm/types.h>
-
-/*
- * This struct maps Processor Vpd that is DMAd to SLIC by CSP
- */
-struct IoHriProcessorVpd {
-        u8      xFormat;                // VPD format indicator         x00-x00
-        u8      xProcStatus:8;          // Processor State              x01-x01
-        u8      xSecondaryThreadCount;  // Secondary thread cnt         x02-x02
-        u8      xSrcType:1;             // Src Type                     x03-x03
-        u8      xSrcSoft:1;             // Src stay soft                ...
-        u8      xSrcParable:1;          // Src parable                  ...
-        u8      xRsvd1:5;               // Reserved                     ...
-        u16     xHvPhysicalProcIndex;   // Hypervisor physical proc index04-x05
-        u16     xRsvd2;                 // Reserved                     x06-x07
-        u32     xHwNodeId;              // Hardware node id             x08-x0B
-        u32     xHwProcId;              // Hardware processor id        x0C-x0F
-
-        u32     xTypeNum;               // Card Type/CCIN number        x10-x13
-        u32     xModelNum;              // Model/Feature number         x14-x17
-        u64     xSerialNum;             // Serial number                x18-x1F
-        char    xPartNum[12];           // Book Part or FPU number      x20-x2B
-        char    xMfgID[4];              // Manufacturing ID             x2C-x2F
-
-        u32     xProcFreq;              // Processor Frequency          x30-x33
-        u32     xTimeBaseFreq;          // Time Base Frequency          x34-x37
-
-        u32     xChipEcLevel;           // Chip EC Levels               x38-x3B
-        u32     xProcIdReg;             // PIR SPR value                x3C-x3F
-        u32     xPVR;                   // PVR value                    x40-x43
-        u8      xRsvd3[12];             // Reserved                     x44-x4F
-
-        u32     xInstCacheSize;         // Instruction cache size in KB x50-x53
-        u32     xInstBlockSize;         // Instruction cache block size x54-x57
-        u32     xDataCacheOperandSize;  // Data cache operand size      x58-x5B
-        u32     xInstCacheOperandSize;  // Inst cache operand size      x5C-x5F
-
-        u32     xDataL1CacheSizeKB;     // L1 data cache size in KB     x60-x63
-        u32     xDataL1CacheLineSize;   // L1 data cache block size     x64-x67
-        u64     xRsvd4;                 // Reserved                     x68-x6F
-
-        u32     xDataL2CacheSizeKB;     // L2 data cache size in KB     x70-x73
-        u32     xDataL2CacheLineSize;   // L2 data cache block size     x74-x77
-        u64     xRsvd5;                 // Reserved                     x78-x7F
-
-        u32     xDataL3CacheSizeKB;     // L3 data cache size in KB     x80-x83
-        u32     xDataL3CacheLineSize;   // L3 data cache block size     x84-x87
-        u64     xRsvd6;                 // Reserved                     x88-x8F
-
-        u64     xFruLabel;              // Card Location Label          x90-x97
-        u8      xSlotsOnCard;           // Slots on card (0=no slots)   x98-x98
-        u8      xPartLocFlag;           // Location flag (0-pluggable 1-imbedded) x99-x99
-        u16     xSlotMapIndex;          // Index in slot map table      x9A-x9B
-        u8      xSmartCardPortNo;       // Smart card port number       x9C-x9C
-        u8      xRsvd7;                 // Reserved                     x9D-x9D
-        u16     xFrameIdAndRackUnit;    // Frame ID and rack unit adr   x9E-x9F
-
-        u8      xRsvd8[24];             // Reserved                     xA0-xB7
-
-        char    xProcSrc[72];           // CSP format SRC               xB8-xFF
-};
-
-extern struct IoHriProcessorVpd xIoHriProcessorVpd[];
-
-#endif /* _ISERIES_PROCESSOR_VPD_H */
diff --git a/arch/powerpc/platforms/iseries/release_data.h b/arch/powerpc/platforms/iseries/release_data.h
deleted file mode 100644
index 6ad7d843e8fc..000000000000
--- a/arch/powerpc/platforms/iseries/release_data.h
+++ /dev/null
@@ -1,63 +0,0 @@
-/*
- * Copyright (C) 2001  Mike Corrigan 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.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
- */
-#ifndef _ISERIES_RELEASE_DATA_H
-#define _ISERIES_RELEASE_DATA_H
-
-/*
- * This control block contains the critical information about the
- * release so that it can be changed in the future (ie, the virtual
- * address of the OS's NACA).
- */
-#include <asm/types.h>
-#include "naca.h"
-
-/*
- * When we IPL a secondary partition, we will check if if the
- * secondary xMinPlicVrmIndex > the primary xVrmIndex.
- * If it is then this tells PLIC that this secondary is not
- * supported running on this "old" of a level of PLIC.
- *
- * Likewise, we will compare the primary xMinSlicVrmIndex to
- * the secondary xVrmIndex.
- * If the primary xMinSlicVrmDelta > secondary xVrmDelta then we
- * know that this PLIC does not support running an OS "that old".
- */
-
-#define HVREL_TAGSINACTIVE      0x8000
-#define HVREL_32BIT             0x4000
-#define HVREL_NOSHAREDPROCS     0x2000
-#define HVREL_NOHMT             0x1000
-
-struct HvReleaseData {
-        u32     xDesc;          /* Descriptor "HvRD" ebcdic     x00-x03 */
-        u16     xSize;          /* Size of this control block   x04-x05 */
-        u16     xVpdAreasPtrOffset; /* Offset in NACA of ItVpdAreas x06-x07 */
-        struct  naca_struct     *xSlicNacaAddr; /* Virt addr of SLIC NACA x08-x0F */
-        u32     xMsNucDataOffset; /* Offset of Linux Mapping Data x10-x13 */
-        u32     xRsvd1;         /* Reserved                     x14-x17 */
-        u16     xFlags;
-        u16     xVrmIndex;      /* VRM Index of OS image        x1A-x1B */
-        u16     xMinSupportedPlicVrmIndex; /* Min PLIC level  (soft) x1C-x1D */
-        u16     xMinCompatablePlicVrmIndex; /* Min PLIC levelP (hard) x1E-x1F */
-        char    xVrmName[12];   /* Displayable name             x20-x2B */
-        char    xRsvd3[20];     /* Reserved                     x2C-x3F */
-};
-
-extern const struct HvReleaseData       hvReleaseData;
-
-#endif /* _ISERIES_RELEASE_DATA_H */
diff --git a/arch/powerpc/platforms/iseries/setup.c b/arch/powerpc/platforms/iseries/setup.c
deleted file mode 100644
index 8fc62586a973..000000000000
--- a/arch/powerpc/platforms/iseries/setup.c
+++ /dev/null
@@ -1,722 +0,0 @@
-/*
- *    Copyright (c) 2000 Mike Corrigan <mikejc@us.ibm.com>
- *    Copyright (c) 1999-2000 Grant Erickson <grant@lcse.umn.edu>
- *
- *    Description:
- *      Architecture- / platform-specific boot-time initialization code for
- *      the IBM iSeries LPAR.  Adapted from original code by Grant Erickson and
- *      code by Gary Thomas, Cort Dougan <cort@fsmlabs.com>, and Dan Malek
- *      <dan@net4x.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.
- */
-
-#undef DEBUG
-
-#include <linux/init.h>
-#include <linux/threads.h>
-#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>
-#include <linux/major.h>
-#include <linux/root_dev.h>
-#include <linux/kernel.h>
-#include <linux/hrtimer.h>
-#include <linux/tick.h>
-
-#include <asm/processor.h>
-#include <asm/machdep.h>
-#include <asm/page.h>
-#include <asm/mmu.h>
-#include <asm/pgtable.h>
-#include <asm/mmu_context.h>
-#include <asm/cputable.h>
-#include <asm/sections.h>
-#include <asm/iommu.h>
-#include <asm/firmware.h>
-#include <asm/system.h>
-#include <asm/time.h>
-#include <asm/paca.h>
-#include <asm/cache.h>
-#include <asm/abs_addr.h>
-#include <asm/iseries/hv_lp_config.h>
-#include <asm/iseries/hv_call_event.h>
-#include <asm/iseries/hv_call_xm.h>
-#include <asm/iseries/it_lp_queue.h>
-#include <asm/iseries/mf.h>
-#include <asm/iseries/hv_lp_event.h>
-#include <asm/iseries/lpar_map.h>
-#include <asm/udbg.h>
-#include <asm/irq.h>
-
-#include "naca.h"
-#include "setup.h"
-#include "irq.h"
-#include "vpd_areas.h"
-#include "processor_vpd.h"
-#include "it_lp_naca.h"
-#include "main_store.h"
-#include "call_sm.h"
-#include "call_hpt.h"
-#include "pci.h"
-
-#ifdef DEBUG
-#define DBG(fmt...) udbg_printf(fmt)
-#else
-#define DBG(fmt...)
-#endif
-
-/* Function Prototypes */
-static unsigned long build_iSeries_Memory_Map(void);
-static void iseries_shared_idle(void);
-static void iseries_dedicated_idle(void);
-
-
-struct MemoryBlock {
-        unsigned long absStart;
-        unsigned long absEnd;
-        unsigned long logicalStart;
-        unsigned long logicalEnd;
-};
-
-/*
- * Process the main store vpd to determine where the holes in memory are
- * and return the number of physical blocks and fill in the array of
- * block data.
- */
-static unsigned long iSeries_process_Condor_mainstore_vpd(
-                struct MemoryBlock *mb_array, unsigned long max_entries)
-{
-        unsigned long holeFirstChunk, holeSizeChunks;
-        unsigned long numMemoryBlocks = 1;
-        struct IoHriMainStoreSegment4 *msVpd =
-                (struct IoHriMainStoreSegment4 *)xMsVpd;
-        unsigned long holeStart = msVpd->nonInterleavedBlocksStartAdr;
-        unsigned long holeEnd = msVpd->nonInterleavedBlocksEndAdr;
-        unsigned long holeSize = holeEnd - holeStart;
-
-        printk("Mainstore_VPD: Condor\n");
-        /*
-         * Determine if absolute memory has any
-         * holes so that we can interpret the
-         * access map we get back from the hypervisor
-         * correctly.
-         */
-        mb_array[0].logicalStart = 0;
-        mb_array[0].logicalEnd = 0x100000000UL;
-        mb_array[0].absStart = 0;
-        mb_array[0].absEnd = 0x100000000UL;
-
-        if (holeSize) {
-                numMemoryBlocks = 2;
-                holeStart = holeStart & 0x000fffffffffffffUL;
-                holeStart = addr_to_chunk(holeStart);
-                holeFirstChunk = holeStart;
-                holeSize = addr_to_chunk(holeSize);
-                holeSizeChunks = holeSize;
-                printk( "Main store hole: start chunk = %0lx, size = %0lx chunks\n",
-                                holeFirstChunk, holeSizeChunks );
-                mb_array[0].logicalEnd = holeFirstChunk;
-                mb_array[0].absEnd = holeFirstChunk;
-                mb_array[1].logicalStart = holeFirstChunk;
-                mb_array[1].logicalEnd = 0x100000000UL - holeSizeChunks;
-                mb_array[1].absStart = holeFirstChunk + holeSizeChunks;
-                mb_array[1].absEnd = 0x100000000UL;
-        }
-        return numMemoryBlocks;
-}
-
-#define MaxSegmentAreas                 32
-#define MaxSegmentAdrRangeBlocks        128
-#define MaxAreaRangeBlocks              4
-
-static unsigned long iSeries_process_Regatta_mainstore_vpd(
-                struct MemoryBlock *mb_array, unsigned long max_entries)
-{
-        struct IoHriMainStoreSegment5 *msVpdP =
-                (struct IoHriMainStoreSegment5 *)xMsVpd;
-        unsigned long numSegmentBlocks = 0;
-        u32 existsBits = msVpdP->msAreaExists;
-        unsigned long area_num;
-
-        printk("Mainstore_VPD: Regatta\n");
-
-        for (area_num = 0; area_num < MaxSegmentAreas; ++area_num ) {
-                unsigned long numAreaBlocks;
-                struct IoHriMainStoreArea4 *currentArea;
-
-                if (existsBits & 0x80000000) {
-                        unsigned long block_num;
-
-                        currentArea = &msVpdP->msAreaArray[area_num];
-                        numAreaBlocks = currentArea->numAdrRangeBlocks;
-                        printk("ms_vpd: processing area %2ld  blocks=%ld",
-                                        area_num, numAreaBlocks);
-                        for (block_num = 0; block_num < numAreaBlocks;
-                                        ++block_num ) {
-                                /* Process an address range block */
-                                struct MemoryBlock tempBlock;
-                                unsigned long i;
-
-                                tempBlock.absStart =
-                                        (unsigned long)currentArea->xAdrRangeBlock[block_num].blockStart;
-                                tempBlock.absEnd =
-                                        (unsigned long)currentArea->xAdrRangeBlock[block_num].blockEnd;
-                                tempBlock.logicalStart = 0;
-                                tempBlock.logicalEnd   = 0;
-                                printk("\n          block %ld absStart=%016lx absEnd=%016lx",
-                                                block_num, tempBlock.absStart,
-                                                tempBlock.absEnd);
-
-                                for (i = 0; i < numSegmentBlocks; ++i) {
-                                        if (mb_array[i].absStart ==
-                                                        tempBlock.absStart)
-                                                break;
-                                }
-                                if (i == numSegmentBlocks) {
-                                        if (numSegmentBlocks == max_entries)
-                                                panic("iSeries_process_mainstore_vpd: too many memory blocks");
-                                        mb_array[numSegmentBlocks] = tempBlock;
-                                        ++numSegmentBlocks;
-                                } else
-                                        printk(" (duplicate)");
-                        }
-                        printk("\n");
-                }
-                existsBits <<= 1;
-        }
-        /* Now sort the blocks found into ascending sequence */
-        if (numSegmentBlocks > 1) {
-                unsigned long m, n;
-
-                for (m = 0; m < numSegmentBlocks - 1; ++m) {
-                        for (n = numSegmentBlocks - 1; m < n; --n) {
-                                if (mb_array[n].absStart <
-                                                mb_array[n-1].absStart) {
-                                        struct MemoryBlock tempBlock;
-
-                                        tempBlock = mb_array[n];
-                                        mb_array[n] = mb_array[n-1];
-                                        mb_array[n-1] = tempBlock;
-                                }
-                        }
-                }
-        }
-        /*
-         * Assign "logical" addresses to each block.  These
-         * addresses correspond to the hypervisor "bitmap" space.
-         * Convert all addresses into units of 256K chunks.
-         */
-        {
-        unsigned long i, nextBitmapAddress;
-
-        printk("ms_vpd: %ld sorted memory blocks\n", numSegmentBlocks);
-        nextBitmapAddress = 0;
-        for (i = 0; i < numSegmentBlocks; ++i) {
-                unsigned long length = mb_array[i].absEnd -
-                        mb_array[i].absStart;
-
-                mb_array[i].logicalStart = nextBitmapAddress;
-                mb_array[i].logicalEnd = nextBitmapAddress + length;
-                nextBitmapAddress += length;
-                printk("          Bitmap range: %016lx - %016lx\n"
-                                "        Absolute range: %016lx - %016lx\n",
-                                mb_array[i].logicalStart,
-                                mb_array[i].logicalEnd,
-                                mb_array[i].absStart, mb_array[i].absEnd);
-                mb_array[i].absStart = addr_to_chunk(mb_array[i].absStart &
-                                0x000fffffffffffffUL);
-                mb_array[i].absEnd = addr_to_chunk(mb_array[i].absEnd &
-                                0x000fffffffffffffUL);
-                mb_array[i].logicalStart =
-                        addr_to_chunk(mb_array[i].logicalStart);
-                mb_array[i].logicalEnd = addr_to_chunk(mb_array[i].logicalEnd);
-        }
-        }
-
-        return numSegmentBlocks;
-}
-
-static unsigned long iSeries_process_mainstore_vpd(struct MemoryBlock *mb_array,
-                unsigned long max_entries)
-{
-        unsigned long i;
-        unsigned long mem_blocks = 0;
-
-        if (mmu_has_feature(MMU_FTR_SLB))
-                mem_blocks = iSeries_process_Regatta_mainstore_vpd(mb_array,
-                                max_entries);
-        else
-                mem_blocks = iSeries_process_Condor_mainstore_vpd(mb_array,
-                                max_entries);
-
-        printk("Mainstore_VPD: numMemoryBlocks = %ld\n", mem_blocks);
-        for (i = 0; i < mem_blocks; ++i) {
-                printk("Mainstore_VPD: block %3ld logical chunks %016lx - %016lx\n"
-                       "                             abs chunks %016lx - %016lx\n",
-                        i, mb_array[i].logicalStart, mb_array[i].logicalEnd,
-                        mb_array[i].absStart, mb_array[i].absEnd);
-        }
-        return mem_blocks;
-}
-
-static void __init iSeries_get_cmdline(void)
-{
-        char *p, *q;
-
-        /* copy the command line parameter from the primary VSP  */
-        HvCallEvent_dmaToSp(cmd_line, 2 * 64* 1024, 256,
-                        HvLpDma_Direction_RemoteToLocal);
-
-        p = cmd_line;
-        q = cmd_line + 255;
-        while(p < q) {
-                if (!*p || *p == '\n')
-                        break;
-                ++p;
-        }
-        *p = 0;
-}
-
-static void __init iSeries_init_early(void)
-{
-        DBG(" -> iSeries_init_early()\n");
-
-        /* Snapshot the timebase, for use in later recalibration */
-        iSeries_time_init_early();
-
-        /*
-         * Initialize the DMA/TCE management
-         */
-        iommu_init_early_iSeries();
-
-        /* Initialize machine-dependency vectors */
-#ifdef CONFIG_SMP
-        smp_init_iSeries();
-#endif
-
-        /* Associate Lp Event Queue 0 with processor 0 */
-        HvCallEvent_setLpEventQueueInterruptProc(0, 0);
-
-        mf_init();
-
-        DBG(" <- iSeries_init_early()\n");
-}
-
-struct mschunks_map mschunks_map = {
-        /* XXX We don't use these, but Piranha might need them. */
-        .chunk_size  = MSCHUNKS_CHUNK_SIZE,
-        .chunk_shift = MSCHUNKS_CHUNK_SHIFT,
-        .chunk_mask  = MSCHUNKS_OFFSET_MASK,
-};
-EXPORT_SYMBOL(mschunks_map);
-
-static void mschunks_alloc(unsigned long num_chunks)
-{
-        klimit = _ALIGN(klimit, sizeof(u32));
-        mschunks_map.mapping = (u32 *)klimit;
-        klimit += num_chunks * sizeof(u32);
-        mschunks_map.num_chunks = num_chunks;
-}
-
-/*
- * The iSeries may have very large memories ( > 128 GB ) and a partition
- * may get memory in "chunks" that may be anywhere in the 2**52 real
- * address space.  The chunks are 256K in size.  To map this to the
- * memory model Linux expects, the AS/400 specific code builds a
- * translation table to translate what Linux thinks are "physical"
- * addresses to the actual real addresses.  This allows us to make
- * it appear to Linux that we have contiguous memory starting at
- * physical address zero while in fact this could be far from the truth.
- * To avoid confusion, I'll let the words physical and/or real address
- * apply to the Linux addresses while I'll use "absolute address" to
- * refer to the actual hardware real address.
- *
- * build_iSeries_Memory_Map gets information from the Hypervisor and
- * looks at the Main Store VPD to determine the absolute addresses
- * of the memory that has been assigned to our partition and builds
- * a table used to translate Linux's physical addresses to these
- * absolute addresses.  Absolute addresses are needed when
- * communicating with the hypervisor (e.g. to build HPT entries)
- *
- * Returns the physical memory size
- */
-
-static unsigned long __init build_iSeries_Memory_Map(void)
-{
-        u32 loadAreaFirstChunk, loadAreaLastChunk, loadAreaSize;
-        u32 nextPhysChunk;
-        u32 hptFirstChunk, hptLastChunk, hptSizeChunks, hptSizePages;
-        u32 totalChunks,moreChunks;
-        u32 currChunk, thisChunk, absChunk;
-        u32 currDword;
-        u32 chunkBit;
-        u64 map;
-        struct MemoryBlock mb[32];
-        unsigned long numMemoryBlocks, curBlock;
-
-        /* Chunk size on iSeries is 256K bytes */
-        totalChunks = (u32)HvLpConfig_getMsChunks();
-        mschunks_alloc(totalChunks);
-
-        /*
-         * Get absolute address of our load area
-         * and map it to physical address 0
-         * This guarantees that the loadarea ends up at physical 0
-         * otherwise, it might not be returned by PLIC as the first
-         * chunks
-         */
-
-        loadAreaFirstChunk = (u32)addr_to_chunk(itLpNaca.xLoadAreaAddr);
-        loadAreaSize =  itLpNaca.xLoadAreaChunks;
-
-        /*
-         * Only add the pages already mapped here.
-         * Otherwise we might add the hpt pages
-         * The rest of the pages of the load area
-         * aren't in the HPT yet and can still
-         * be assigned an arbitrary physical address
-         */
-        if ((loadAreaSize * 64) > HvPagesToMap)
-                loadAreaSize = HvPagesToMap / 64;
-
-        loadAreaLastChunk = loadAreaFirstChunk + loadAreaSize - 1;
-
-        /*
-         * TODO Do we need to do something if the HPT is in the 64MB load area?
-         * This would be required if the itLpNaca.xLoadAreaChunks includes
-         * the HPT size
-         */
-
-        printk("Mapping load area - physical addr = 0000000000000000\n"
-                "                    absolute addr = %016lx\n",
-                chunk_to_addr(loadAreaFirstChunk));
-        printk("Load area size %dK\n", loadAreaSize * 256);
-
-        for (nextPhysChunk = 0; nextPhysChunk < loadAreaSize; ++nextPhysChunk)
-                mschunks_map.mapping[nextPhysChunk] =
-                        loadAreaFirstChunk + nextPhysChunk;
-
-        /*
-         * Get absolute address of our HPT and remember it so
-         * we won't map it to any physical address
-         */
-        hptFirstChunk = (u32)addr_to_chunk(HvCallHpt_getHptAddress());
-        hptSizePages = (u32)HvCallHpt_getHptPages();
-        hptSizeChunks = hptSizePages >>
-                (MSCHUNKS_CHUNK_SHIFT - HW_PAGE_SHIFT);
-        hptLastChunk = hptFirstChunk + hptSizeChunks - 1;
-
-        printk("HPT absolute addr = %016lx, size = %dK\n",
-                        chunk_to_addr(hptFirstChunk), hptSizeChunks * 256);
-
-        /*
-         * Determine if absolute memory has any
-         * holes so that we can interpret the
-         * access map we get back from the hypervisor
-         * correctly.
-         */
-        numMemoryBlocks = iSeries_process_mainstore_vpd(mb, 32);
-
-        /*
-         * Process the main store access map from the hypervisor
-         * to build up our physical -> absolute translation table
-         */
-        curBlock = 0;
-        currChunk = 0;
-        currDword = 0;
-        moreChunks = totalChunks;
-
-        while (moreChunks) {
-                map = HvCallSm_get64BitsOfAccessMap(itLpNaca.xLpIndex,
-                                currDword);
-                thisChunk = currChunk;
-                while (map) {
-                        chunkBit = map >> 63;
-                        map <<= 1;
-                        if (chunkBit) {
-                                --moreChunks;
-                                while (thisChunk >= mb[curBlock].logicalEnd) {
-                                        ++curBlock;
-                                        if (curBlock >= numMemoryBlocks)
-                                                panic("out of memory blocks");
-                                }
-                                if (thisChunk < mb[curBlock].logicalStart)
-                                        panic("memory block error");
-
-                                absChunk = mb[curBlock].absStart +
-                                        (thisChunk - mb[curBlock].logicalStart);
-                                if (((absChunk < hptFirstChunk) ||
-                                     (absChunk > hptLastChunk)) &&
-                                    ((absChunk < loadAreaFirstChunk) ||
-                                     (absChunk > loadAreaLastChunk))) {
-                                        mschunks_map.mapping[nextPhysChunk] =
-                                                absChunk;
-                                        ++nextPhysChunk;
-                                }
-                        }
-                        ++thisChunk;
-                }
-                ++currDword;
-                currChunk += 64;
-        }
-
-        /*
-         * main store size (in chunks) is
-         *   totalChunks - hptSizeChunks
-         * which should be equal to
-         *   nextPhysChunk
-         */
-        return chunk_to_addr(nextPhysChunk);
-}
-
-/*
- * Document me.
- */
-static void __init iSeries_setup_arch(void)
-{
-        if (get_lppaca()->shared_proc) {
-                ppc_md.idle_loop = iseries_shared_idle;
-                printk(KERN_DEBUG "Using shared processor idle loop\n");
-        } else {
-                ppc_md.idle_loop = iseries_dedicated_idle;
-                printk(KERN_DEBUG "Using dedicated idle loop\n");
-        }
-
-        /* Setup the Lp Event Queue */
-        setup_hvlpevent_queue();
-
-        printk("Max  logical processors = %d\n",
-                        itVpdAreas.xSlicMaxLogicalProcs);
-        printk("Max physical processors = %d\n",
-                        itVpdAreas.xSlicMaxPhysicalProcs);
-
-        iSeries_pcibios_init();
-}
-
-static void iSeries_show_cpuinfo(struct seq_file *m)
-{
-        seq_printf(m, "machine\t\t: 64-bit iSeries Logical Partition\n");
-}
-
-static void __init iSeries_progress(char * st, unsigned short code)
-{
-        printk("Progress: [%04x] - %s\n", (unsigned)code, st);
-        mf_display_progress(code);
-}
-
-static void __init iSeries_fixup_klimit(void)
-{
-        /*
-         * Change klimit to take into account any ram disk
-         * that may be included
-         */
-        if (naca.xRamDisk)
-                klimit = KERNELBASE + (u64)naca.xRamDisk +
-                        (naca.xRamDiskSize * HW_PAGE_SIZE);
-}
-
-static int __init iSeries_src_init(void)
-{
-        /* clear the progress line */
-        if (firmware_has_feature(FW_FEATURE_ISERIES))
-                ppc_md.progress(" ", 0xffff);
-        return 0;
-}
-
-late_initcall(iSeries_src_init);
-
-static inline void process_iSeries_events(void)
-{
-        asm volatile ("li 0,0x5555; sc" : : : "r0", "r3");
-}
-
-static void yield_shared_processor(void)
-{
-        unsigned long tb;
-
-        HvCall_setEnabledInterrupts(HvCall_MaskIPI |
-                                    HvCall_MaskLpEvent |
-                                    HvCall_MaskLpProd |
-                                    HvCall_MaskTimeout);
-
-        tb = get_tb();
-        /* Compute future tb value when yield should expire */
-        HvCall_yieldProcessor(HvCall_YieldTimed, tb+tb_ticks_per_jiffy);
-
-        /*
-         * The decrementer stops during the yield.  Force a fake decrementer
-         * here and let the timer_interrupt code sort out the actual time.
-         */
-        get_lppaca()->int_dword.fields.decr_int = 1;
-        ppc64_runlatch_on();
-        process_iSeries_events();
-}
-
-static void iseries_shared_idle(void)
-{
-        while (1) {
-                tick_nohz_idle_enter();
-                rcu_idle_enter();
-                while (!need_resched() && !hvlpevent_is_pending()) {
-                        local_irq_disable();
-                        ppc64_runlatch_off();
-
-                        /* Recheck with irqs off */
-                        if (!need_resched() && !hvlpevent_is_pending())
-                                yield_shared_processor();
-
-                        HMT_medium();
-                        local_irq_enable();
-                }
-
-                ppc64_runlatch_on();
-                rcu_idle_exit();
-                tick_nohz_idle_exit();
-
-                if (hvlpevent_is_pending())
-                        process_iSeries_events();
-
-                preempt_enable_no_resched();
-                schedule();
-                preempt_disable();
-        }
-}
-
-static void iseries_dedicated_idle(void)
-{
-        set_thread_flag(TIF_POLLING_NRFLAG);
-
-        while (1) {
-                tick_nohz_idle_enter();
-                rcu_idle_enter();
-                if (!need_resched()) {
-                        while (!need_resched()) {
-                                ppc64_runlatch_off();
-                                HMT_low();
-
-                                if (hvlpevent_is_pending()) {
-                                        HMT_medium();
-                                        ppc64_runlatch_on();
-                                        process_iSeries_events();
-                                }
-                        }
-
-                        HMT_medium();
-                }
-
-                ppc64_runlatch_on();
-                rcu_idle_exit();
-                tick_nohz_idle_exit();
-                preempt_enable_no_resched();
-                schedule();
-                preempt_disable();
-        }
-}
-
-static void __iomem *iseries_ioremap(phys_addr_t address, unsigned long size,
-                                     unsigned long flags, void *caller)
-{
-        return (void __iomem *)address;
-}
-
-static void iseries_iounmap(volatile void __iomem *token)
-{
-}
-
-static int __init iseries_probe(void)
-{
-        unsigned long root = of_get_flat_dt_root();
-        if (!of_flat_dt_is_compatible(root, "IBM,iSeries"))
-                return 0;
-
-        hpte_init_iSeries();
-        /* iSeries does not support 16M pages */
-        cur_cpu_spec->mmu_features &= ~MMU_FTR_16M_PAGE;
-
-        return 1;
-}
-
-#ifdef CONFIG_KEXEC
-static int iseries_kexec_prepare(struct kimage *image)
-{
-        return -ENOSYS;
-}
-#endif
-
-define_machine(iseries) {
-        .name                   = "iSeries",
-        .setup_arch             = iSeries_setup_arch,
-        .show_cpuinfo           = iSeries_show_cpuinfo,
-        .init_IRQ               = iSeries_init_IRQ,
-        .get_irq                = iSeries_get_irq,
-        .init_early             = iSeries_init_early,
-        .pcibios_fixup          = iSeries_pci_final_fixup,
-        .pcibios_fixup_resources= iSeries_pcibios_fixup_resources,
-        .restart                = mf_reboot,
-        .power_off              = mf_power_off,
-        .halt                   = mf_power_off,
-        .get_boot_time          = iSeries_get_boot_time,
-        .set_rtc_time           = iSeries_set_rtc_time,
-        .get_rtc_time           = iSeries_get_rtc_time,
-        .calibrate_decr         = generic_calibrate_decr,
-        .progress               = iSeries_progress,
-        .probe                  = iseries_probe,
-        .ioremap                = iseries_ioremap,
-        .iounmap                = iseries_iounmap,
-#ifdef CONFIG_KEXEC
-        .machine_kexec_prepare  = iseries_kexec_prepare,
-#endif
-        /* XXX Implement enable_pmcs for iSeries */
-};
-
-void * __init iSeries_early_setup(void)
-{
-        unsigned long phys_mem_size;
-
-        /* Identify CPU type. This is done again by the common code later
-         * on but calling this function multiple times is fine.
-         */
-        identify_cpu(0, mfspr(SPRN_PVR));
-        initialise_paca(&boot_paca, 0);
-
-        powerpc_firmware_features |= FW_FEATURE_ISERIES;
-        powerpc_firmware_features |= FW_FEATURE_LPAR;
-
-#ifdef CONFIG_SMP
-        /* On iSeries we know we can never have more than 64 cpus */
-        nr_cpu_ids = max(nr_cpu_ids, 64);
-#endif
-
-        iSeries_fixup_klimit();
-
-        /*
-         * Initialize the table which translate Linux physical addresses to
-         * AS/400 absolute addresses
-         */
-        phys_mem_size = build_iSeries_Memory_Map();
-
-        iSeries_get_cmdline();
-
-        return (void *) __pa(build_flat_dt(phys_mem_size));
-}
-
-static void hvputc(char c)
-{
-        if (c == '\n')
-                hvputc('\r');
-
-        HvCall_writeLogBuffer(&c, 1);
-}
-
-void __init udbg_init_iseries(void)
-{
-        udbg_putc = hvputc;
-}
diff --git a/arch/powerpc/platforms/iseries/setup.h b/arch/powerpc/platforms/iseries/setup.h
deleted file mode 100644
index 729754bbb018..000000000000
--- a/arch/powerpc/platforms/iseries/setup.h
+++ /dev/null
@@ -1,27 +0,0 @@
-/*
- *    Copyright (c) 2000 Mike Corrigan <mikejc@us.ibm.com>
- *    Copyright (c) 1999-2000 Grant Erickson <grant@lcse.umn.edu>
- *
- *    Description:
- *      Architecture- / platform-specific boot-time initialization code for
- *      the IBM AS/400 LPAR. Adapted from original code by Grant Erickson and
- *      code by Gary Thomas, Cort Dougan <cort@cs.nmt.edu>, and Dan Malek
- *      <dan@netx4.com>.
- *
- *      This program is free software; you can redistribute it and/or
- *      modify it under the terms of the GNU General Public License
- *      as published by the Free Software Foundation; either version
- *      2 of the License, or (at your option) any later version.
- */
-
-#ifndef __ISERIES_SETUP_H__
-#define __ISERIES_SETUP_H__
-
-extern void *iSeries_early_setup(void);
-extern unsigned long iSeries_get_boot_time(void);
-extern int iSeries_set_rtc_time(struct rtc_time *tm);
-extern void iSeries_get_rtc_time(struct rtc_time *tm);
-
-extern void *build_flat_dt(unsigned long phys_mem_size);
-
-#endif /* __ISERIES_SETUP_H__ */
diff --git a/arch/powerpc/platforms/iseries/smp.c b/arch/powerpc/platforms/iseries/smp.c
deleted file mode 100644
index 02df49fb59f0..000000000000
--- a/arch/powerpc/platforms/iseries/smp.c
+++ /dev/null
@@ -1,88 +0,0 @@
-/*
- * SMP support for iSeries machines.
- *
- * Dave Engebretsen, Peter Bergner, and
- * Mike Corrigan {engebret|bergner|mikec}@us.ibm.com
- *
- * Plus various changes from other IBM teams...
- *
- *      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/kernel.h>
-#include <linux/sched.h>
-#include <linux/smp.h>
-#include <linux/interrupt.h>
-#include <linux/kernel_stat.h>
-#include <linux/delay.h>
-#include <linux/init.h>
-#include <linux/spinlock.h>
-#include <linux/cache.h>
-#include <linux/err.h>
-#include <linux/device.h>
-#include <linux/cpu.h>
-
-#include <asm/ptrace.h>
-#include <linux/atomic.h>
-#include <asm/irq.h>
-#include <asm/page.h>
-#include <asm/pgtable.h>
-#include <asm/io.h>
-#include <asm/smp.h>
-#include <asm/paca.h>
-#include <asm/iseries/hv_call.h>
-#include <asm/time.h>
-#include <asm/machdep.h>
-#include <asm/cputable.h>
-#include <asm/system.h>
-
-static void smp_iSeries_cause_ipi(int cpu, unsigned long data)
-{
-        HvCall_sendIPI(&(paca[cpu]));
-}
-
-static int smp_iSeries_probe(void)
-{
-        return cpumask_weight(cpu_possible_mask);
-}
-
-static int smp_iSeries_kick_cpu(int nr)
-{
-        BUG_ON((nr < 0) || (nr >= NR_CPUS));
-
-        /* Verify that our partition has a processor nr */
-        if (lppaca_of(nr).dyn_proc_status >= 2)
-                return -ENOENT;
-
-        /* The processor is currently spinning, waiting
-         * for the cpu_start field to become non-zero
-         * After we set cpu_start, the processor will
-         * continue on to secondary_start in iSeries_head.S
-         */
-        paca[nr].cpu_start = 1;
-
-        return 0;
-}
-
-static void __devinit smp_iSeries_setup_cpu(int nr)
-{
-}
-
-static struct smp_ops_t iSeries_smp_ops = {
-        .message_pass = NULL,   /* Use smp_muxed_ipi_message_pass */
-        .cause_ipi    = smp_iSeries_cause_ipi,
-        .probe        = smp_iSeries_probe,
-        .kick_cpu     = smp_iSeries_kick_cpu,
-        .setup_cpu    = smp_iSeries_setup_cpu,
-};
-
-/* This is called very early. */
-void __init smp_init_iSeries(void)
-{
-        smp_ops = &iSeries_smp_ops;
-}
diff --git a/arch/powerpc/platforms/iseries/spcomm_area.h b/arch/powerpc/platforms/iseries/spcomm_area.h
deleted file mode 100644
index 598b7c14573a..000000000000
--- a/arch/powerpc/platforms/iseries/spcomm_area.h
+++ /dev/null
@@ -1,34 +0,0 @@
-/*
- * Copyright (C) 2001  Mike Corrigan 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.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
- */
-
-#ifndef _ISERIES_SPCOMM_AREA_H
-#define _ISERIES_SPCOMM_AREA_H
-
-
-struct SpCommArea {
-        u32     xDesc;                  // Descriptor (only in new formats)     000-003
-        u8      xFormat;                // Format (only in new formats)         004-004
-        u8      xRsvd1[11];             // Reserved                             005-00F
-        u64     xRawTbAtIplStart;       // Raw HW TB value when IPL is started  010-017
-        u64     xRawTodAtIplStart;      // Raw HW TOD value when IPL is started 018-01F
-        u64     xBcdTimeAtIplStart;     // BCD time when IPL is started         020-027
-        u64     xBcdTimeAtOsStart;      // BCD time when OS passed control      028-02F
-        u8      xRsvd2[80];             // Reserved                             030-07F
-};
-
-#endif /* _ISERIES_SPCOMM_AREA_H */
diff --git a/arch/powerpc/platforms/iseries/vio.c b/arch/powerpc/platforms/iseries/vio.c
deleted file mode 100644
index 04be62d368a6..000000000000
--- a/arch/powerpc/platforms/iseries/vio.c
+++ /dev/null
@@ -1,556 +0,0 @@
-/*
- * Legacy iSeries specific vio initialisation
- * that needs to be built in (not a module).
- *
- * © Copyright 2007 IBM Corporation
- *      Author: Stephen Rothwell
- *      Some parts collected from various other files
- *
- * This program is free software;  you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation; either version 2 of the
- * License, or (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software Foundation,
- * Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
- */
-#include <linux/of.h>
-#include <linux/init.h>
-#include <linux/slab.h>
-#include <linux/completion.h>
-#include <linux/proc_fs.h>
-#include <linux/export.h>
-
-#include <asm/firmware.h>
-#include <asm/vio.h>
-#include <asm/iseries/vio.h>
-#include <asm/iseries/iommu.h>
-#include <asm/iseries/hv_types.h>
-#include <asm/iseries/hv_lp_event.h>
-
-#define FIRST_VTY       0
-#define NUM_VTYS        1
-#define FIRST_VSCSI     (FIRST_VTY + NUM_VTYS)
-#define NUM_VSCSIS      1
-#define FIRST_VLAN      (FIRST_VSCSI + NUM_VSCSIS)
-#define NUM_VLANS       HVMAXARCHITECTEDVIRTUALLANS
-#define FIRST_VIODASD   (FIRST_VLAN + NUM_VLANS)
-#define NUM_VIODASDS    HVMAXARCHITECTEDVIRTUALDISKS
-#define FIRST_VIOCD     (FIRST_VIODASD + NUM_VIODASDS)
-#define NUM_VIOCDS      HVMAXARCHITECTEDVIRTUALCDROMS
-#define FIRST_VIOTAPE   (FIRST_VIOCD + NUM_VIOCDS)
-#define NUM_VIOTAPES    HVMAXARCHITECTEDVIRTUALTAPES
-
-struct vio_waitevent {
-        struct completion       com;
-        int                     rc;
-        u16                     sub_result;
-};
-
-struct vio_resource {
-        char    rsrcname[10];
-        char    type[4];
-        char    model[3];
-};
-
-static struct property *new_property(const char *name, int length,
-                const void *value)
-{
-        struct property *np = kzalloc(sizeof(*np) + strlen(name) + 1 + length,
-                        GFP_KERNEL);
-
-        if (!np)
-                return NULL;
-        np->name = (char *)(np + 1);
-        np->value = np->name + strlen(name) + 1;
-        strcpy(np->name, name);
-        memcpy(np->value, value, length);
-        np->length = length;
-        return np;
-}
-
-static void free_property(struct property *np)
-{
-        kfree(np);
-}
-
-static struct device_node *new_node(const char *path,
-                struct device_node *parent)
-{
-        struct device_node *np = kzalloc(sizeof(*np), GFP_KERNEL);
-
-        if (!np)
-                return NULL;
-        np->full_name = kstrdup(path, GFP_KERNEL);
-        if (!np->full_name) {
-                kfree(np);
-                return NULL;
-        }
-        of_node_set_flag(np, OF_DYNAMIC);
-        kref_init(&np->kref);
-        np->parent = of_node_get(parent);
-        return np;
-}
-
-static void free_node(struct device_node *np)
-{
-        struct property *next;
-        struct property *prop;
-
-        next = np->properties;
-        while (next) {
-                prop = next;
-                next = prop->next;
-                free_property(prop);
-        }
-        of_node_put(np->parent);
-        kfree(np->full_name);
-        kfree(np);
-}
-
-static int add_string_property(struct device_node *np, const char *name,
-                const char *value)
-{
-        struct property *nprop = new_property(name, strlen(value) + 1, value);
-
-        if (!nprop)
-                return 0;
-        prom_add_property(np, nprop);
-        return 1;
-}
-
-static int add_raw_property(struct device_node *np, const char *name,
-                int length, const void *value)
-{
-        struct property *nprop = new_property(name, length, value);
-
-        if (!nprop)
-                return 0;
-        prom_add_property(np, nprop);
-        return 1;
-}
-
-static struct device_node *do_device_node(struct device_node *parent,
-                const char *name, u32 reg, u32 unit, const char *type,
-                const char *compat, struct vio_resource *res)
-{
-        struct device_node *np;
-        char path[32];
-
-        snprintf(path, sizeof(path), "/vdevice/%s@%08x", name, reg);
-        np = new_node(path, parent);
-        if (!np)
-                return NULL;
-        if (!add_string_property(np, "name", name) ||
-                !add_string_property(np, "device_type", type) ||
-                !add_string_property(np, "compatible", compat) ||
-                !add_raw_property(np, "reg", sizeof(reg), &reg) ||
-                !add_raw_property(np, "linux,unit_address",
-                        sizeof(unit), &unit)) {
-                goto node_free;
-        }
-        if (res) {
-                if (!add_raw_property(np, "linux,vio_rsrcname",
-                                sizeof(res->rsrcname), res->rsrcname) ||
-                        !add_raw_property(np, "linux,vio_type",
-                                sizeof(res->type), res->type) ||
-                        !add_raw_property(np, "linux,vio_model",
-                                sizeof(res->model), res->model))
-                        goto node_free;
-        }
-        np->name = of_get_property(np, "name", NULL);
-        np->type = of_get_property(np, "device_type", NULL);
-        of_attach_node(np);
-#ifdef CONFIG_PROC_DEVICETREE
-        if (parent->pde) {
-                struct proc_dir_entry *ent;
-
-                ent = proc_mkdir(strrchr(np->full_name, '/') + 1, parent->pde);
-                if (ent)
-                        proc_device_tree_add_node(np, ent);
-        }
-#endif
-        return np;
-
- node_free:
-        free_node(np);
-        return NULL;
-}
-
-/*
- * This is here so that we can dynamically add viodasd
- * devices without exposing all the above infrastructure.
- */
-struct vio_dev *vio_create_viodasd(u32 unit)
-{
-        struct device_node *vio_root;
-        struct device_node *np;
-        struct vio_dev *vdev = NULL;
-
-        vio_root = of_find_node_by_path("/vdevice");
-        if (!vio_root)
-                return NULL;
-        np = do_device_node(vio_root, "viodasd", FIRST_VIODASD + unit, unit,
-                        "block", "IBM,iSeries-viodasd", NULL);
-        of_node_put(vio_root);
-        if (np) {
-                vdev = vio_register_device_node(np);
-                if (!vdev)
-                        free_node(np);
-        }
-        return vdev;
-}
-EXPORT_SYMBOL_GPL(vio_create_viodasd);
-
-static void __init handle_block_event(struct HvLpEvent *event)
-{
-        struct vioblocklpevent *bevent = (struct vioblocklpevent *)event;
-        struct vio_waitevent *pwe;
-
-        if (event == NULL)
-                /* Notification that a partition went away! */
-                return;
-        /* First, we should NEVER get an int here...only acks */
-        if (hvlpevent_is_int(event)) {
-                printk(KERN_WARNING "handle_viod_request: "
-                       "Yikes! got an int in viodasd event handler!\n");
-                if (hvlpevent_need_ack(event)) {
-                        event->xRc = HvLpEvent_Rc_InvalidSubtype;
-                        HvCallEvent_ackLpEvent(event);
-                }
-                return;
-        }
-
-        switch (event->xSubtype & VIOMINOR_SUBTYPE_MASK) {
-        case vioblockopen:
-                /*
-                 * Handle a response to an open request.  We get all the
-                 * disk information in the response, so update it.  The
-                 * correlation token contains a pointer to a waitevent
-                 * structure that has a completion in it.  update the
-                 * return code in the waitevent structure and post the
-                 * completion to wake up the guy who sent the request
-                 */
-                pwe = (struct vio_waitevent *)event->xCorrelationToken;
-                pwe->rc = event->xRc;
-                pwe->sub_result = bevent->sub_result;
-                complete(&pwe->com);
-                break;
-        case vioblockclose:
-                break;
-        default:
-                printk(KERN_WARNING "handle_viod_request: unexpected subtype!");
-                if (hvlpevent_need_ack(event)) {
-                        event->xRc = HvLpEvent_Rc_InvalidSubtype;
-                        HvCallEvent_ackLpEvent(event);
-                }
-        }
-}
-
-static void __init probe_disk(struct device_node *vio_root, u32 unit)
-{
-        HvLpEvent_Rc hvrc;
-        struct vio_waitevent we;
-        u16 flags = 0;
-
-retry:
-        init_completion(&we.com);
-
-        /* Send the open event to OS/400 */
-        hvrc = HvCallEvent_signalLpEventFast(viopath_hostLp,
-                        HvLpEvent_Type_VirtualIo,
-                        viomajorsubtype_blockio | vioblockopen,
-                        HvLpEvent_AckInd_DoAck, HvLpEvent_AckType_ImmediateAck,
-                        viopath_sourceinst(viopath_hostLp),
-                        viopath_targetinst(viopath_hostLp),
-                        (u64)(unsigned long)&we, VIOVERSION << 16,
-                        ((u64)unit << 48) | ((u64)flags<< 32),
-                        0, 0, 0);
-        if (hvrc != 0) {
-                printk(KERN_WARNING "probe_disk: bad rc on HV open %d\n",
-                        (int)hvrc);
-                return;
-        }
-
-        wait_for_completion(&we.com);
-
-        if (we.rc != 0) {
-                if (flags != 0)
-                        return;
-                /* try again with read only flag set */
-                flags = vioblockflags_ro;
-                goto retry;
-        }
-
-        /* Send the close event to OS/400.  We DON'T expect a response */
-        hvrc = HvCallEvent_signalLpEventFast(viopath_hostLp,
-                        HvLpEvent_Type_VirtualIo,
-                        viomajorsubtype_blockio | vioblockclose,
-                        HvLpEvent_AckInd_NoAck, HvLpEvent_AckType_ImmediateAck,
-                        viopath_sourceinst(viopath_hostLp),
-                        viopath_targetinst(viopath_hostLp),
-                        0, VIOVERSION << 16,
-                        ((u64)unit << 48) | ((u64)flags << 32),
-                        0, 0, 0);
-        if (hvrc != 0) {
-                printk(KERN_WARNING "probe_disk: "
-                       "bad rc sending event to OS/400 %d\n", (int)hvrc);
-                return;
-        }
-
-        do_device_node(vio_root, "viodasd", FIRST_VIODASD + unit, unit,
-                        "block", "IBM,iSeries-viodasd", NULL);
-}
-
-static void __init get_viodasd_info(struct device_node *vio_root)
-{
-        int rc;
-        u32 unit;
-
-        rc = viopath_open(viopath_hostLp, viomajorsubtype_blockio, 2);
-        if (rc) {
-                printk(KERN_WARNING "get_viodasd_info: "
-                       "error opening path to host partition %d\n",
-                       viopath_hostLp);
-                return;
-        }
-
-        /* Initialize our request handler */
-        vio_setHandler(viomajorsubtype_blockio, handle_block_event);
-
-        for (unit = 0; unit < HVMAXARCHITECTEDVIRTUALDISKS; unit++)
-                probe_disk(vio_root, unit);
-
-        vio_clearHandler(viomajorsubtype_blockio);
-        viopath_close(viopath_hostLp, viomajorsubtype_blockio, 2);
-}
-
-static void __init handle_cd_event(struct HvLpEvent *event)
-{
-        struct viocdlpevent *bevent;
-        struct vio_waitevent *pwe;
-
-        if (!event)
-                /* Notification that a partition went away! */
-                return;
-
-        /* First, we should NEVER get an int here...only acks */
-        if (hvlpevent_is_int(event)) {
-                printk(KERN_WARNING "handle_cd_event: got an unexpected int\n");
-                if (hvlpevent_need_ack(event)) {
-                        event->xRc = HvLpEvent_Rc_InvalidSubtype;
-                        HvCallEvent_ackLpEvent(event);
-                }
-                return;
-        }
-
-        bevent = (struct viocdlpevent *)event;
-
-        switch (event->xSubtype & VIOMINOR_SUBTYPE_MASK) {
-        case viocdgetinfo:
-                pwe = (struct vio_waitevent *)event->xCorrelationToken;
-                pwe->rc = event->xRc;
-                pwe->sub_result = bevent->sub_result;
-                complete(&pwe->com);
-                break;
-
-        default:
-                printk(KERN_WARNING "handle_cd_event: "
-                        "message with unexpected subtype %0x04X!\n",
-                        event->xSubtype & VIOMINOR_SUBTYPE_MASK);
-                if (hvlpevent_need_ack(event)) {
-                        event->xRc = HvLpEvent_Rc_InvalidSubtype;
-                        HvCallEvent_ackLpEvent(event);
-                }
-        }
-}
-
-static void __init get_viocd_info(struct device_node *vio_root)
-{
-        HvLpEvent_Rc hvrc;
-        u32 unit;
-        struct vio_waitevent we;
-        struct vio_resource *unitinfo;
-        dma_addr_t unitinfo_dmaaddr;
-        int ret;
-
-        ret = viopath_open(viopath_hostLp, viomajorsubtype_cdio, 2);
-        if (ret) {
-                printk(KERN_WARNING
-                        "get_viocd_info: error opening path to host partition %d\n",
-                        viopath_hostLp);
-                return;
-        }
-
-        /* Initialize our request handler */
-        vio_setHandler(viomajorsubtype_cdio, handle_cd_event);
-
-        unitinfo = iseries_hv_alloc(
-                        sizeof(*unitinfo) * HVMAXARCHITECTEDVIRTUALCDROMS,
-                        &unitinfo_dmaaddr, GFP_ATOMIC);
-        if (!unitinfo) {
-                printk(KERN_WARNING
-                        "get_viocd_info: error allocating unitinfo\n");
-                goto clear_handler;
-        }
-
-        memset(unitinfo, 0, sizeof(*unitinfo) * HVMAXARCHITECTEDVIRTUALCDROMS);
-
-        init_completion(&we.com);
-
-        hvrc = HvCallEvent_signalLpEventFast(viopath_hostLp,
-                        HvLpEvent_Type_VirtualIo,
-                        viomajorsubtype_cdio | viocdgetinfo,
-                        HvLpEvent_AckInd_DoAck, HvLpEvent_AckType_ImmediateAck,
-                        viopath_sourceinst(viopath_hostLp),
-                        viopath_targetinst(viopath_hostLp),
-                        (u64)&we, VIOVERSION << 16, unitinfo_dmaaddr, 0,
-                        sizeof(*unitinfo) * HVMAXARCHITECTEDVIRTUALCDROMS, 0);
-        if (hvrc != HvLpEvent_Rc_Good) {
-                printk(KERN_WARNING
-                        "get_viocd_info: cdrom error sending event. rc %d\n",
-                        (int)hvrc);
-                goto hv_free;
-        }
-
-        wait_for_completion(&we.com);
-
-        if (we.rc) {
-                printk(KERN_WARNING "get_viocd_info: bad rc %d:0x%04X\n",
-                        we.rc, we.sub_result);
-                goto hv_free;
-        }
-
-        for (unit = 0; (unit < HVMAXARCHITECTEDVIRTUALCDROMS) &&
-                        unitinfo[unit].rsrcname[0]; unit++) {
-                if (!do_device_node(vio_root, "viocd", FIRST_VIOCD + unit, unit,
-                                "block", "IBM,iSeries-viocd", &unitinfo[unit]))
-                        break;
-        }
-
- hv_free:
-        iseries_hv_free(sizeof(*unitinfo) * HVMAXARCHITECTEDVIRTUALCDROMS,
-                        unitinfo, unitinfo_dmaaddr);
- clear_handler:
-        vio_clearHandler(viomajorsubtype_cdio);
-        viopath_close(viopath_hostLp, viomajorsubtype_cdio, 2);
-}
-
-/* Handle interrupt events for tape */
-static void __init handle_tape_event(struct HvLpEvent *event)
-{
-        struct vio_waitevent *we;
-        struct viotapelpevent *tevent = (struct viotapelpevent *)event;
-
-        if (event == NULL)
-                /* Notification that a partition went away! */
-                return;
-
-        we = (struct vio_waitevent *)event->xCorrelationToken;
-        switch (event->xSubtype & VIOMINOR_SUBTYPE_MASK) {
-        case viotapegetinfo:
-                we->rc = tevent->sub_type_result;
-                complete(&we->com);
-                break;
-        default:
-                printk(KERN_WARNING "handle_tape_event: weird ack\n");
-        }
-}
-
-static void __init get_viotape_info(struct device_node *vio_root)
-{
-        HvLpEvent_Rc hvrc;
-        u32 unit;
-        struct vio_resource *unitinfo;
-        dma_addr_t unitinfo_dmaaddr;
-        size_t len = sizeof(*unitinfo) * HVMAXARCHITECTEDVIRTUALTAPES;
-        struct vio_waitevent we;
-        int ret;
-
-        init_completion(&we.com);
-
-        ret = viopath_open(viopath_hostLp, viomajorsubtype_tape, 2);
-        if (ret) {
-                printk(KERN_WARNING "get_viotape_info: "
-                        "error on viopath_open to hostlp %d\n", ret);
-                return;
-        }
-
-        vio_setHandler(viomajorsubtype_tape, handle_tape_event);
-
-        unitinfo = iseries_hv_alloc(len, &unitinfo_dmaaddr, GFP_ATOMIC);
-        if (!unitinfo)
-                goto clear_handler;
-
-        memset(unitinfo, 0, len);
-
-        hvrc = HvCallEvent_signalLpEventFast(viopath_hostLp,
-                        HvLpEvent_Type_VirtualIo,
-                        viomajorsubtype_tape | viotapegetinfo,
-                        HvLpEvent_AckInd_DoAck, HvLpEvent_AckType_ImmediateAck,
-                        viopath_sourceinst(viopath_hostLp),
-                        viopath_targetinst(viopath_hostLp),
-                        (u64)(unsigned long)&we, VIOVERSION << 16,
-                        unitinfo_dmaaddr, len, 0, 0);
-        if (hvrc != HvLpEvent_Rc_Good) {
-                printk(KERN_WARNING "get_viotape_info: hv error on op %d\n",
-                                (int)hvrc);
-                goto hv_free;
-        }
-
-        wait_for_completion(&we.com);
-
-        for (unit = 0; (unit < HVMAXARCHITECTEDVIRTUALTAPES) &&
-                        unitinfo[unit].rsrcname[0]; unit++) {
-                if (!do_device_node(vio_root, "viotape", FIRST_VIOTAPE + unit,
-                                unit, "byte", "IBM,iSeries-viotape",
-                                &unitinfo[unit]))
-                        break;
-        }
-
- hv_free:
-        iseries_hv_free(len, unitinfo, unitinfo_dmaaddr);
- clear_handler:
-        vio_clearHandler(viomajorsubtype_tape);
-        viopath_close(viopath_hostLp, viomajorsubtype_tape, 2);
-}
-
-static int __init iseries_vio_init(void)
-{
-        struct device_node *vio_root;
-        int ret = -ENODEV;
-
-        if (!firmware_has_feature(FW_FEATURE_ISERIES))
-                goto out;
-
-        iommu_vio_init();
-
-        vio_root = of_find_node_by_path("/vdevice");
-        if (!vio_root)
-                goto out;
-
-        if (viopath_hostLp == HvLpIndexInvalid) {
-                vio_set_hostlp();
-                /* If we don't have a host, bail out */
-                if (viopath_hostLp == HvLpIndexInvalid)
-                        goto put_node;
-        }
-
-        get_viodasd_info(vio_root);
-        get_viocd_info(vio_root);
-        get_viotape_info(vio_root);
-
-        ret = 0;
-
- put_node:
-        of_node_put(vio_root);
- out:
-        return ret;
-}
-arch_initcall(iseries_vio_init);
diff --git a/arch/powerpc/platforms/iseries/viopath.c b/arch/powerpc/platforms/iseries/viopath.c
deleted file mode 100644
index 40dad0840eb3..000000000000
--- a/arch/powerpc/platforms/iseries/viopath.c
+++ /dev/null
@@ -1,677 +0,0 @@
-/* -*- linux-c -*-
- *
- *  iSeries Virtual I/O Message Path code
- *
- *  Authors: Dave Boutcher <boutcher@us.ibm.com>
- *           Ryan Arnold <ryanarn@us.ibm.com>
- *           Colin Devilbiss <devilbis@us.ibm.com>
- *
- * (C) Copyright 2000-2005 IBM Corporation
- *
- * This code is used by the iSeries virtual disk, cd,
- * tape, and console to communicate with OS/400 in another
- * partition.
- *
- * 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) anyu later version.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software Foundation,
- * Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
- *
- */
-#include <linux/export.h>
-#include <linux/kernel.h>
-#include <linux/slab.h>
-#include <linux/errno.h>
-#include <linux/vmalloc.h>
-#include <linux/string.h>
-#include <linux/proc_fs.h>
-#include <linux/dma-mapping.h>
-#include <linux/wait.h>
-#include <linux/seq_file.h>
-#include <linux/interrupt.h>
-#include <linux/completion.h>
-
-#include <asm/system.h>
-#include <asm/uaccess.h>
-#include <asm/prom.h>
-#include <asm/firmware.h>
-#include <asm/iseries/hv_types.h>
-#include <asm/iseries/hv_lp_event.h>
-#include <asm/iseries/hv_lp_config.h>
-#include <asm/iseries/mf.h>
-#include <asm/iseries/vio.h>
-
-/* Status of the path to each other partition in the system.
- * This is overkill, since we will only ever establish connections
- * to our hosting partition and the primary partition on the system.
- * But this allows for other support in the future.
- */
-static struct viopathStatus {
-        int isOpen;             /* Did we open the path?            */
-        int isActive;           /* Do we have a mon msg outstanding */
-        int users[VIO_MAX_SUBTYPES];
-        HvLpInstanceId mSourceInst;
-        HvLpInstanceId mTargetInst;
-        int numberAllocated;
-} viopathStatus[HVMAXARCHITECTEDLPS];
-
-static DEFINE_SPINLOCK(statuslock);
-
-/*
- * For each kind of event we allocate a buffer that is
- * guaranteed not to cross a page boundary
- */
-static unsigned char event_buffer[VIO_MAX_SUBTYPES * 256]
-        __attribute__((__aligned__(4096)));
-static atomic_t event_buffer_available[VIO_MAX_SUBTYPES];
-static int event_buffer_initialised;
-
-static void handleMonitorEvent(struct HvLpEvent *event);
-
-/*
- * We use this structure to handle asynchronous responses.  The caller
- * blocks on the semaphore and the handler posts the semaphore.  However,
- * if system_state is not SYSTEM_RUNNING, then wait_atomic is used ...
- */
-struct alloc_parms {
-        struct completion done;
-        int number;
-        atomic_t wait_atomic;
-        int used_wait_atomic;
-};
-
-/* Put a sequence number in each mon msg.  The value is not
- * important.  Start at something other than 0 just for
- * readability.  wrapping this is ok.
- */
-static u8 viomonseq = 22;
-
-/* Our hosting logical partition.  We get this at startup
- * time, and different modules access this variable directly.
- */
-HvLpIndex viopath_hostLp = HvLpIndexInvalid;
-EXPORT_SYMBOL(viopath_hostLp);
-HvLpIndex viopath_ourLp = HvLpIndexInvalid;
-EXPORT_SYMBOL(viopath_ourLp);
-
-/* For each kind of incoming event we set a pointer to a
- * routine to call.
- */
-static vio_event_handler_t *vio_handler[VIO_MAX_SUBTYPES];
-
-#define VIOPATH_KERN_WARN       KERN_WARNING "viopath: "
-#define VIOPATH_KERN_INFO       KERN_INFO "viopath: "
-
-static int proc_viopath_show(struct seq_file *m, void *v)
-{
-        char *buf;
-        u16 vlanMap;
-        dma_addr_t handle;
-        HvLpEvent_Rc hvrc;
-        DECLARE_COMPLETION_ONSTACK(done);
-        struct device_node *node;
-        const char *sysid;
-
-        buf = kzalloc(HW_PAGE_SIZE, GFP_KERNEL);
-        if (!buf)
-                return 0;
-
-        handle = iseries_hv_map(buf, HW_PAGE_SIZE, DMA_FROM_DEVICE);
-
-        hvrc = HvCallEvent_signalLpEventFast(viopath_hostLp,
-                        HvLpEvent_Type_VirtualIo,
-                        viomajorsubtype_config | vioconfigget,
-                        HvLpEvent_AckInd_DoAck, HvLpEvent_AckType_ImmediateAck,
-                        viopath_sourceinst(viopath_hostLp),
-                        viopath_targetinst(viopath_hostLp),
-                        (u64)(unsigned long)&done, VIOVERSION << 16,
-                        ((u64)handle) << 32, HW_PAGE_SIZE, 0, 0);
-
-        if (hvrc != HvLpEvent_Rc_Good)
-                printk(VIOPATH_KERN_WARN "hv error on op %d\n", (int)hvrc);
-
-        wait_for_completion(&done);
-
-        vlanMap = HvLpConfig_getVirtualLanIndexMap();
-
-        buf[HW_PAGE_SIZE-1] = '\0';
-        seq_printf(m, "%s", buf);
-
-        iseries_hv_unmap(handle, HW_PAGE_SIZE, DMA_FROM_DEVICE);
-        kfree(buf);
-
-        seq_printf(m, "AVAILABLE_VETH=%x\n", vlanMap);
-
-        node = of_find_node_by_path("/");
-        sysid = NULL;
-        if (node != NULL)
-                sysid = of_get_property(node, "system-id", NULL);
-
-        if (sysid == NULL)
-                seq_printf(m, "SRLNBR=<UNKNOWN>\n");
-        else
-                /* Skip "IBM," on front of serial number, see dt.c */
-                seq_printf(m, "SRLNBR=%s\n", sysid + 4);
-
-        of_node_put(node);
-
-        return 0;
-}
-
-static int proc_viopath_open(struct inode *inode, struct file *file)
-{
-        return single_open(file, proc_viopath_show, NULL);
-}
-
-static const struct file_operations proc_viopath_operations = {
-        .open           = proc_viopath_open,
-        .read           = seq_read,
-        .llseek         = seq_lseek,
-        .release        = single_release,
-};
-
-static int __init vio_proc_init(void)
-{
-        if (!firmware_has_feature(FW_FEATURE_ISERIES))
-                return 0;
-
-        proc_create("iSeries/config", 0, NULL, &proc_viopath_operations);
-        return 0;
-}
-__initcall(vio_proc_init);
-
-/* See if a given LP is active.  Allow for invalid lps to be passed in
- * and just return invalid
- */
-int viopath_isactive(HvLpIndex lp)
-{
-        if (lp == HvLpIndexInvalid)
-                return 0;
-        if (lp < HVMAXARCHITECTEDLPS)
-                return viopathStatus[lp].isActive;
-        else
-                return 0;
-}
-EXPORT_SYMBOL(viopath_isactive);
-
-/*
- * We cache the source and target instance ids for each
- * partition.
- */
-HvLpInstanceId viopath_sourceinst(HvLpIndex lp)
-{
-        return viopathStatus[lp].mSourceInst;
-}
-EXPORT_SYMBOL(viopath_sourceinst);
-
-HvLpInstanceId viopath_targetinst(HvLpIndex lp)
-{
-        return viopathStatus[lp].mTargetInst;
-}
-EXPORT_SYMBOL(viopath_targetinst);
-
-/*
- * Send a monitor message.  This is a message with the acknowledge
- * bit on that the other side will NOT explicitly acknowledge.  When
- * the other side goes down, the hypervisor will acknowledge any
- * outstanding messages....so we will know when the other side dies.
- */
-static void sendMonMsg(HvLpIndex remoteLp)
-{
-        HvLpEvent_Rc hvrc;
-
-        viopathStatus[remoteLp].mSourceInst =
-                HvCallEvent_getSourceLpInstanceId(remoteLp,
-                                HvLpEvent_Type_VirtualIo);
-        viopathStatus[remoteLp].mTargetInst =
-                HvCallEvent_getTargetLpInstanceId(remoteLp,
-                                HvLpEvent_Type_VirtualIo);
-
-        /*
-         * Deliberately ignore the return code here.  if we call this
-         * more than once, we don't care.
-         */
-        vio_setHandler(viomajorsubtype_monitor, handleMonitorEvent);
-
-        hvrc = HvCallEvent_signalLpEventFast(remoteLp, HvLpEvent_Type_VirtualIo,
-                        viomajorsubtype_monitor, HvLpEvent_AckInd_DoAck,
-                        HvLpEvent_AckType_DeferredAck,
-                        viopathStatus[remoteLp].mSourceInst,
-                        viopathStatus[remoteLp].mTargetInst,
-                        viomonseq++, 0, 0, 0, 0, 0);
-
-        if (hvrc == HvLpEvent_Rc_Good)
-                viopathStatus[remoteLp].isActive = 1;
-        else {
-                printk(VIOPATH_KERN_WARN "could not connect to partition %d\n",
-                                remoteLp);
-                viopathStatus[remoteLp].isActive = 0;
-        }
-}
-
-static void handleMonitorEvent(struct HvLpEvent *event)
-{
-        HvLpIndex remoteLp;
-        int i;
-
-        /*
-         * This handler is _also_ called as part of the loop
-         * at the end of this routine, so it must be able to
-         * ignore NULL events...
-         */
-        if (!event)
-                return;
-
-        /*
-         * First see if this is just a normal monitor message from the
-         * other partition
-         */
-        if (hvlpevent_is_int(event)) {
-                remoteLp = event->xSourceLp;
-                if (!viopathStatus[remoteLp].isActive)
-                        sendMonMsg(remoteLp);
-                return;
-        }
-
-        /*
-         * This path is for an acknowledgement; the other partition
-         * died
-         */
-        remoteLp = event->xTargetLp;
-        if ((event->xSourceInstanceId != viopathStatus[remoteLp].mSourceInst) ||
-            (event->xTargetInstanceId != viopathStatus[remoteLp].mTargetInst)) {
-                printk(VIOPATH_KERN_WARN "ignoring ack....mismatched instances\n");
-                return;
-        }
-
-        printk(VIOPATH_KERN_WARN "partition %d ended\n", remoteLp);
-
-        viopathStatus[remoteLp].isActive = 0;
-
-        /*
-         * For each active handler, pass them a NULL
-         * message to indicate that the other partition
-         * died
-         */
-        for (i = 0; i < VIO_MAX_SUBTYPES; i++) {
-                if (vio_handler[i] != NULL)
-                        (*vio_handler[i])(NULL);
-        }
-}
-
-int vio_setHandler(int subtype, vio_event_handler_t *beh)
-{
-        subtype = subtype >> VIOMAJOR_SUBTYPE_SHIFT;
-        if ((subtype < 0) || (subtype >= VIO_MAX_SUBTYPES))
-                return -EINVAL;
-        if (vio_handler[subtype] != NULL)
-                return -EBUSY;
-        vio_handler[subtype] = beh;
-        return 0;
-}
-EXPORT_SYMBOL(vio_setHandler);
-
-int vio_clearHandler(int subtype)
-{
-        subtype = subtype >> VIOMAJOR_SUBTYPE_SHIFT;
-        if ((subtype < 0) || (subtype >= VIO_MAX_SUBTYPES))
-                return -EINVAL;
-        if (vio_handler[subtype] == NULL)
-                return -EAGAIN;
-        vio_handler[subtype] = NULL;
-        return 0;
-}
-EXPORT_SYMBOL(vio_clearHandler);
-
-static void handleConfig(struct HvLpEvent *event)
-{
-        if (!event)
-                return;
-        if (hvlpevent_is_int(event)) {
-                printk(VIOPATH_KERN_WARN
-                       "unexpected config request from partition %d",
-                       event->xSourceLp);
-
-                if (hvlpevent_need_ack(event)) {
-                        event->xRc = HvLpEvent_Rc_InvalidSubtype;
-                        HvCallEvent_ackLpEvent(event);
-                }
-                return;
-        }
-
-        complete((struct completion *)event->xCorrelationToken);
-}
-
-/*
- * Initialization of the hosting partition
- */
-void vio_set_hostlp(void)
-{
-        /*
-         * If this has already been set then we DON'T want to either change
-         * it or re-register the proc file system
-         */
-        if (viopath_hostLp != HvLpIndexInvalid)
-                return;
-
-        /*
-         * Figure out our hosting partition.  This isn't allowed to change
-         * while we're active
-         */
-        viopath_ourLp = HvLpConfig_getLpIndex();
-        viopath_hostLp = HvLpConfig_getHostingLpIndex(viopath_ourLp);
-
-        if (viopath_hostLp != HvLpIndexInvalid)
-                vio_setHandler(viomajorsubtype_config, handleConfig);
-}
-EXPORT_SYMBOL(vio_set_hostlp);
-
-static void vio_handleEvent(struct HvLpEvent *event)
-{
-        HvLpIndex remoteLp;
-        int subtype = (event->xSubtype & VIOMAJOR_SUBTYPE_MASK)
-                >> VIOMAJOR_SUBTYPE_SHIFT;
-
-        if (hvlpevent_is_int(event)) {
-                remoteLp = event->xSourceLp;
-                /*
-                 * The isActive is checked because if the hosting partition
-                 * went down and came back up it would not be active but it
-                 * would have different source and target instances, in which
-                 * case we'd want to reset them.  This case really protects
-                 * against an unauthorized active partition sending interrupts
-                 * or acks to this linux partition.
-                 */
-                if (viopathStatus[remoteLp].isActive
-                    && (event->xSourceInstanceId !=
-                        viopathStatus[remoteLp].mTargetInst)) {
-                        printk(VIOPATH_KERN_WARN
-                               "message from invalid partition. "
-                               "int msg rcvd, source inst (%d) doesn't match (%d)\n",
-                               viopathStatus[remoteLp].mTargetInst,
-                               event->xSourceInstanceId);
-                        return;
-                }
-
-                if (viopathStatus[remoteLp].isActive
-                    && (event->xTargetInstanceId !=
-                        viopathStatus[remoteLp].mSourceInst)) {
-                        printk(VIOPATH_KERN_WARN
-                               "message from invalid partition. "
-                               "int msg rcvd, target inst (%d) doesn't match (%d)\n",
-                               viopathStatus[remoteLp].mSourceInst,
-                               event->xTargetInstanceId);
-                        return;
-                }
-        } else {
-                remoteLp = event->xTargetLp;
-                if (event->xSourceInstanceId !=
-                    viopathStatus[remoteLp].mSourceInst) {
-                        printk(VIOPATH_KERN_WARN
-                               "message from invalid partition. "
-                               "ack msg rcvd, source inst (%d) doesn't match (%d)\n",
-                               viopathStatus[remoteLp].mSourceInst,
-                               event->xSourceInstanceId);
-                        return;
-                }
-
-                if (event->xTargetInstanceId !=
-                    viopathStatus[remoteLp].mTargetInst) {
-                        printk(VIOPATH_KERN_WARN
-                               "message from invalid partition. "
-                               "viopath: ack msg rcvd, target inst (%d) doesn't match (%d)\n",
-                               viopathStatus[remoteLp].mTargetInst,
-                               event->xTargetInstanceId);
-                        return;
-                }
-        }
-
-        if (vio_handler[subtype] == NULL) {
-                printk(VIOPATH_KERN_WARN
-                       "unexpected virtual io event subtype %d from partition %d\n",
-                       event->xSubtype, remoteLp);
-                /* No handler.  Ack if necessary */
-                if (hvlpevent_is_int(event) && hvlpevent_need_ack(event)) {
-                        event->xRc = HvLpEvent_Rc_InvalidSubtype;
-                        HvCallEvent_ackLpEvent(event);
-                }
-                return;
-        }
-
-        /* This innocuous little line is where all the real work happens */
-        (*vio_handler[subtype])(event);
-}
-
-static void viopath_donealloc(void *parm, int number)
-{
-        struct alloc_parms *parmsp = parm;
-
-        parmsp->number = number;
-        if (parmsp->used_wait_atomic)
-                atomic_set(&parmsp->wait_atomic, 0);
-        else
-                complete(&parmsp->done);
-}
-
-static int allocateEvents(HvLpIndex remoteLp, int numEvents)
-{
-        struct alloc_parms parms;
-
-        if (system_state != SYSTEM_RUNNING) {
-                parms.used_wait_atomic = 1;
-                atomic_set(&parms.wait_atomic, 1);
-        } else {
-                parms.used_wait_atomic = 0;
-                init_completion(&parms.done);
-        }
-        mf_allocate_lp_events(remoteLp, HvLpEvent_Type_VirtualIo, 250,  /* It would be nice to put a real number here! */
-                            numEvents, &viopath_donealloc, &parms);
-        if (system_state != SYSTEM_RUNNING) {
-                while (atomic_read(&parms.wait_atomic))
-                        mb();
-        } else
-                wait_for_completion(&parms.done);
-        return parms.number;
-}
-
-int viopath_open(HvLpIndex remoteLp, int subtype, int numReq)
-{
-        int i;
-        unsigned long flags;
-        int tempNumAllocated;
-
-        if ((remoteLp >= HVMAXARCHITECTEDLPS) || (remoteLp == HvLpIndexInvalid))
-                return -EINVAL;
-
-        subtype = subtype >> VIOMAJOR_SUBTYPE_SHIFT;
-        if ((subtype < 0) || (subtype >= VIO_MAX_SUBTYPES))
-                return -EINVAL;
-
-        spin_lock_irqsave(&statuslock, flags);
-
-        if (!event_buffer_initialised) {
-                for (i = 0; i < VIO_MAX_SUBTYPES; i++)
-                        atomic_set(&event_buffer_available[i], 1);
-                event_buffer_initialised = 1;
-        }
-
-        viopathStatus[remoteLp].users[subtype]++;
-
-        if (!viopathStatus[remoteLp].isOpen) {
-                viopathStatus[remoteLp].isOpen = 1;
-                HvCallEvent_openLpEventPath(remoteLp, HvLpEvent_Type_VirtualIo);
-
-                /*
-                 * Don't hold the spinlock during an operation that
-                 * can sleep.
-                 */
-                spin_unlock_irqrestore(&statuslock, flags);
-                tempNumAllocated = allocateEvents(remoteLp, 1);
-                spin_lock_irqsave(&statuslock, flags);
-
-                viopathStatus[remoteLp].numberAllocated += tempNumAllocated;
-
-                if (viopathStatus[remoteLp].numberAllocated == 0) {
-                        HvCallEvent_closeLpEventPath(remoteLp,
-                                        HvLpEvent_Type_VirtualIo);
-
-                        spin_unlock_irqrestore(&statuslock, flags);
-                        return -ENOMEM;
-                }
-
-                viopathStatus[remoteLp].mSourceInst =
-                        HvCallEvent_getSourceLpInstanceId(remoteLp,
-                                        HvLpEvent_Type_VirtualIo);
-                viopathStatus[remoteLp].mTargetInst =
-                        HvCallEvent_getTargetLpInstanceId(remoteLp,
-                                        HvLpEvent_Type_VirtualIo);
-                HvLpEvent_registerHandler(HvLpEvent_Type_VirtualIo,
-                                          &vio_handleEvent);
-                sendMonMsg(remoteLp);
-                printk(VIOPATH_KERN_INFO "opening connection to partition %d, "
-                                "setting sinst %d, tinst %d\n",
-                                remoteLp, viopathStatus[remoteLp].mSourceInst,
-                                viopathStatus[remoteLp].mTargetInst);
-        }
-
-        spin_unlock_irqrestore(&statuslock, flags);
-        tempNumAllocated = allocateEvents(remoteLp, numReq);
-        spin_lock_irqsave(&statuslock, flags);
-        viopathStatus[remoteLp].numberAllocated += tempNumAllocated;
-        spin_unlock_irqrestore(&statuslock, flags);
-
-        return 0;
-}
-EXPORT_SYMBOL(viopath_open);
-
-int viopath_close(HvLpIndex remoteLp, int subtype, int numReq)
-{
-        unsigned long flags;
-        int i;
-        int numOpen;
-        struct alloc_parms parms;
-
-        if ((remoteLp >= HVMAXARCHITECTEDLPS) || (remoteLp == HvLpIndexInvalid))
-                return -EINVAL;
-
-        subtype = subtype >> VIOMAJOR_SUBTYPE_SHIFT;
-        if ((subtype < 0) || (subtype >= VIO_MAX_SUBTYPES))
-                return -EINVAL;
-
-        spin_lock_irqsave(&statuslock, flags);
-        /*
-         * If the viopath_close somehow gets called before a
-         * viopath_open it could decrement to -1 which is a non
-         * recoverable state so we'll prevent this from
-         * happening.
-         */
-        if (viopathStatus[remoteLp].users[subtype] > 0)
-                viopathStatus[remoteLp].users[subtype]--;
-
-        spin_unlock_irqrestore(&statuslock, flags);
-
-        parms.used_wait_atomic = 0;
-        init_completion(&parms.done);
-        mf_deallocate_lp_events(remoteLp, HvLpEvent_Type_VirtualIo,
-                              numReq, &viopath_donealloc, &parms);
-        wait_for_completion(&parms.done);
-
-        spin_lock_irqsave(&statuslock, flags);
-        for (i = 0, numOpen = 0; i < VIO_MAX_SUBTYPES; i++)
-                numOpen += viopathStatus[remoteLp].users[i];
-
-        if ((viopathStatus[remoteLp].isOpen) && (numOpen == 0)) {
-                printk(VIOPATH_KERN_INFO "closing connection to partition %d\n",
-                                remoteLp);
-
-                HvCallEvent_closeLpEventPath(remoteLp,
-                                             HvLpEvent_Type_VirtualIo);
-                viopathStatus[remoteLp].isOpen = 0;
-                viopathStatus[remoteLp].isActive = 0;
-
-                for (i = 0; i < VIO_MAX_SUBTYPES; i++)
-                        atomic_set(&event_buffer_available[i], 0);
-                event_buffer_initialised = 0;
-        }
-        spin_unlock_irqrestore(&statuslock, flags);
-        return 0;
-}
-EXPORT_SYMBOL(viopath_close);
-
-void *vio_get_event_buffer(int subtype)
-{
-        subtype = subtype >> VIOMAJOR_SUBTYPE_SHIFT;
-        if ((subtype < 0) || (subtype >= VIO_MAX_SUBTYPES))
-                return NULL;
-
-        if (atomic_dec_if_positive(&event_buffer_available[subtype]) == 0)
-                return &event_buffer[subtype * 256];
-        else
-                return NULL;
-}
-EXPORT_SYMBOL(vio_get_event_buffer);
-
-void vio_free_event_buffer(int subtype, void *buffer)
-{
-        subtype = subtype >> VIOMAJOR_SUBTYPE_SHIFT;
-        if ((subtype < 0) || (subtype >= VIO_MAX_SUBTYPES)) {
-                printk(VIOPATH_KERN_WARN
-                       "unexpected subtype %d freeing event buffer\n", subtype);
-                return;
-        }
-
-        if (atomic_read(&event_buffer_available[subtype]) != 0) {
-                printk(VIOPATH_KERN_WARN
-                       "freeing unallocated event buffer, subtype %d\n",
-                       subtype);
-                return;
-        }
-
-        if (buffer != &event_buffer[subtype * 256]) {
-                printk(VIOPATH_KERN_WARN
-                       "freeing invalid event buffer, subtype %d\n", subtype);
-        }
-
-        atomic_set(&event_buffer_available[subtype], 1);
-}
-EXPORT_SYMBOL(vio_free_event_buffer);
-
-static const struct vio_error_entry vio_no_error =
-    { 0, 0, "Non-VIO Error" };
-static const struct vio_error_entry vio_unknown_error =
-    { 0, EIO, "Unknown Error" };
-
-static const struct vio_error_entry vio_default_errors[] = {
-        {0x0001, EIO, "No Connection"},
-        {0x0002, EIO, "No Receiver"},
-        {0x0003, EIO, "No Buffer Available"},
-        {0x0004, EBADRQC, "Invalid Message Type"},
-        {0x0000, 0, NULL},
-};
-
-const struct vio_error_entry *vio_lookup_rc(
-                const struct vio_error_entry *local_table, u16 rc)
-{
-        const struct vio_error_entry *cur;
-
-        if (!rc)
-                return &vio_no_error;
-        if (local_table)
-                for (cur = local_table; cur->rc; ++cur)
-                        if (cur->rc == rc)
-                                return cur;
-        for (cur = vio_default_errors; cur->rc; ++cur)
-                if (cur->rc == rc)
-                        return cur;
-        return &vio_unknown_error;
-}
-EXPORT_SYMBOL(vio_lookup_rc);
diff --git a/arch/powerpc/platforms/iseries/vpd_areas.h b/arch/powerpc/platforms/iseries/vpd_areas.h
deleted file mode 100644
index feb001f3a5fe..000000000000
--- a/arch/powerpc/platforms/iseries/vpd_areas.h
+++ /dev/null
@@ -1,88 +0,0 @@
-/*
- * Copyright (C) 2001  Mike Corrigan 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.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
- */
-#ifndef _ISERIES_VPD_AREAS_H
-#define _ISERIES_VPD_AREAS_H
-
-/*
- * This file defines the address and length of all of the VPD area passed to
- * the OS from PLIC (most of which start from the SP).
- */
-
-#include <asm/types.h>
-
-/* VPD Entry index is carved in stone - cannot be changed (easily). */
-#define ItVpdCecVpd                             0
-#define ItVpdDynamicSpace                       1
-#define ItVpdExtVpd                             2
-#define ItVpdExtVpdOnPanel                      3
-#define ItVpdFirstPaca                          4
-#define ItVpdIoVpd                              5
-#define ItVpdIplParms                           6
-#define ItVpdMsVpd                              7
-#define ItVpdPanelVpd                           8
-#define ItVpdLpNaca                             9
-#define ItVpdBackplaneAndMaybeClockCardVpd      10
-#define ItVpdRecoveryLogBuffer                  11
-#define ItVpdSpCommArea                         12
-#define ItVpdSpLogBuffer                        13
-#define ItVpdSpLogBufferSave                    14
-#define ItVpdSpCardVpd                          15
-#define ItVpdFirstProcVpd                       16
-#define ItVpdApModelVpd                         17
-#define ItVpdClockCardVpd                       18
-#define ItVpdBusExtCardVpd                      19
-#define ItVpdProcCapacityVpd                    20
-#define ItVpdInteractiveCapacityVpd             21
-#define ItVpdFirstSlotLabel                     22
-#define ItVpdFirstLpQueue                       23
-#define ItVpdFirstL3CacheVpd                    24
-#define ItVpdFirstProcFruVpd                    25
-
-#define ItVpdMaxEntries                         26
-
-#define ItDmaMaxEntries                         10
-
-#define ItVpdAreasMaxSlotLabels                 192
-
-
-struct ItVpdAreas {
-        u32     xSlicDesc;              // Descriptor                   000-003
-        u16     xSlicSize;              // Size of this control block   004-005
-        u16     xPlicAdjustVpdLens:1;   // Flag to indicate new interface006-007
-        u16     xRsvd1:15;              // Reserved bits                ...
-        u16     xSlicVpdEntries;        // Number of VPD entries        008-009
-        u16     xSlicDmaEntries;        // Number of DMA entries        00A-00B
-        u16     xSlicMaxLogicalProcs;   // Maximum logical processors   00C-00D
-        u16     xSlicMaxPhysicalProcs;  // Maximum physical processors  00E-00F
-        u16     xSlicDmaToksOffset;     // Offset into this of array    010-011
-        u16     xSlicVpdAdrsOffset;     // Offset into this of array    012-013
-        u16     xSlicDmaLensOffset;     // Offset into this of array    014-015
-        u16     xSlicVpdLensOffset;     // Offset into this of array    016-017
-        u16     xSlicMaxSlotLabels;     // Maximum number of slot labels018-019
-        u16     xSlicMaxLpQueues;       // Maximum number of LP Queues  01A-01B
-        u8      xRsvd2[4];              // Reserved                     01C-01F
-        u64     xRsvd3[12];             // Reserved                     020-07F
-        u32     xPlicDmaLens[ItDmaMaxEntries];// Array of DMA lengths   080-0A7
-        u32     xPlicDmaToks[ItDmaMaxEntries];// Array of DMA tokens    0A8-0CF
-        u32     xSlicVpdLens[ItVpdMaxEntries];// Array of VPD lengths   0D0-12F
-        const void *xSlicVpdAdrs[ItVpdMaxEntries];// Array of VPD buffers 130-1EF
-};
-
-extern const struct ItVpdAreas  itVpdAreas;
-
-#endif /* _ISERIES_VPD_AREAS_H */
diff --git a/arch/powerpc/platforms/maple/pci.c b/arch/powerpc/platforms/maple/pci.c
index 401e3f3f74c8..465ee8f5c086 100644
--- a/arch/powerpc/platforms/maple/pci.c
+++ b/arch/powerpc/platforms/maple/pci.c
@@ -620,7 +620,7 @@ void __init maple_pci_init(void)
         }
 
         /* Tell pci.c to not change any resource allocations.  */
-        pci_probe_only = 1;
+        pci_add_flags(PCI_PROBE_ONLY);
 }
 
 int maple_pci_get_legacy_ide_irq(struct pci_dev *pdev, int channel)
diff --git a/arch/powerpc/platforms/maple/setup.c b/arch/powerpc/platforms/maple/setup.c
index 0bcbfe7b2c55..3b7545a51aa9 100644
--- a/arch/powerpc/platforms/maple/setup.c
+++ b/arch/powerpc/platforms/maple/setup.c
@@ -262,7 +262,7 @@ static void __init maple_init_IRQ(void)
                 flags |= MPIC_BIG_ENDIAN;
 
         /* XXX Maple specific bits */
-        flags |= MPIC_U3_HT_IRQS | MPIC_WANTS_RESET;
+        flags |= MPIC_U3_HT_IRQS;
         /* All U3/U4 are big-endian, older SLOF firmware doesn't encode this */
         flags |= MPIC_BIG_ENDIAN;
 
diff --git a/arch/powerpc/platforms/pasemi/pci.c b/arch/powerpc/platforms/pasemi/pci.c
index b6a0ec45c695..aa862713258c 100644
--- a/arch/powerpc/platforms/pasemi/pci.c
+++ b/arch/powerpc/platforms/pasemi/pci.c
@@ -229,9 +229,6 @@ void __init pas_pci_init(void)
 
         /* Setup the linkage between OF nodes and PHBs */
         pci_devs_phb_init();
-
-        /* Use the common resource allocation mechanism */
-        pci_probe_only = 1;
 }
 
 void __iomem *pasemi_pci_getcfgaddr(struct pci_dev *dev, int offset)
diff --git a/arch/powerpc/platforms/pasemi/setup.c b/arch/powerpc/platforms/pasemi/setup.c
index 98b7a7c13176..e777ad471a48 100644
--- a/arch/powerpc/platforms/pasemi/setup.c
+++ b/arch/powerpc/platforms/pasemi/setup.c
@@ -224,7 +224,7 @@ static __init void pas_init_IRQ(void)
         openpic_addr = of_read_number(opprop, naddr);
         printk(KERN_DEBUG "OpenPIC addr: %lx\n", openpic_addr);
 
-        mpic_flags = MPIC_LARGE_VECTORS | MPIC_NO_BIAS;
+        mpic_flags = MPIC_LARGE_VECTORS | MPIC_NO_BIAS | MPIC_NO_RESET;
 
         nmiprop = of_get_property(mpic_node, "nmi-source", NULL);
         if (nmiprop)
diff --git a/arch/powerpc/platforms/powermac/nvram.c b/arch/powerpc/platforms/powermac/nvram.c
index 54d227127c9f..da18b26dcc6f 100644
--- a/arch/powerpc/platforms/powermac/nvram.c
+++ b/arch/powerpc/platforms/powermac/nvram.c
@@ -279,7 +279,7 @@ static u32 core99_check(u8* datas)
 
 static int sm_erase_bank(int bank)
 {
-        int stat, i;
+        int stat;
         unsigned long timeout;
 
         u8 __iomem *base = (u8 __iomem *)nvram_data + core99_bank*NVRAM_SIZE;
@@ -301,11 +301,10 @@ static int sm_erase_bank(int bank)
         out_8(base, SM_FLASH_CMD_CLEAR_STATUS);
         out_8(base, SM_FLASH_CMD_RESET);
 
-        for (i=0; i<NVRAM_SIZE; i++)
-                if (base[i] != 0xff) {
-                        printk(KERN_ERR "nvram: Sharp/Micron flash erase failed !\n");
-                        return -ENXIO;
-                }
+        if (memchr_inv(base, 0xff, NVRAM_SIZE)) {
+                printk(KERN_ERR "nvram: Sharp/Micron flash erase failed !\n");
+                return -ENXIO;
+        }
         return 0;
 }
 
@@ -336,17 +335,16 @@ static int sm_write_bank(int bank, u8* datas)
         }
         out_8(base, SM_FLASH_CMD_CLEAR_STATUS);
         out_8(base, SM_FLASH_CMD_RESET);
-        for (i=0; i<NVRAM_SIZE; i++)
-                if (base[i] != datas[i]) {
-                        printk(KERN_ERR "nvram: Sharp/Micron flash write failed !\n");
-                        return -ENXIO;
-                }
+        if (memcmp(base, datas, NVRAM_SIZE)) {
+                printk(KERN_ERR "nvram: Sharp/Micron flash write failed !\n");
+                return -ENXIO;
+        }
         return 0;
 }
 
 static int amd_erase_bank(int bank)
 {
-        int i, stat = 0;
+        int stat = 0;
         unsigned long timeout;
 
         u8 __iomem *base = (u8 __iomem *)nvram_data + core99_bank*NVRAM_SIZE;
@@ -382,12 +380,11 @@ static int amd_erase_bank(int bank)
         /* Reset */
         out_8(base, 0xf0);
         udelay(1);
-        
-        for (i=0; i<NVRAM_SIZE; i++)
-                if (base[i] != 0xff) {
-                        printk(KERN_ERR "nvram: AMD flash erase failed !\n");
-                        return -ENXIO;
-                }
+
+        if (memchr_inv(base, 0xff, NVRAM_SIZE)) {
+                printk(KERN_ERR "nvram: AMD flash erase failed !\n");
+                return -ENXIO;
+        }
         return 0;
 }
 
@@ -429,11 +426,10 @@ static int amd_write_bank(int bank, u8* datas)
         out_8(base, 0xf0);
         udelay(1);
 
-        for (i=0; i<NVRAM_SIZE; i++)
-                if (base[i] != datas[i]) {
-                        printk(KERN_ERR "nvram: AMD flash write failed !\n");
-                        return -ENXIO;
-                }
+        if (memcmp(base, datas, NVRAM_SIZE)) {
+                printk(KERN_ERR "nvram: AMD flash write failed !\n");
+                return -ENXIO;
+        }
         return 0;
 }
 
diff --git a/arch/powerpc/platforms/powermac/pci.c b/arch/powerpc/platforms/powermac/pci.c
index 31a7d3a7ce25..43bbe1bda939 100644
--- a/arch/powerpc/platforms/powermac/pci.c
+++ b/arch/powerpc/platforms/powermac/pci.c
@@ -1059,9 +1059,6 @@ void __init pmac_pci_init(void)
         }
         /* pmac_check_ht_link(); */
 
-        /* We can allocate missing resources if any */
-        pci_probe_only = 0;
-
 #else /* CONFIG_PPC64 */
         init_p2pbridge();
         init_second_ohare();
diff --git a/arch/powerpc/platforms/powermac/pic.c b/arch/powerpc/platforms/powermac/pic.c
index 7761aabfc293..66ad93de1d55 100644
--- a/arch/powerpc/platforms/powermac/pic.c
+++ b/arch/powerpc/platforms/powermac/pic.c
@@ -61,7 +61,7 @@ static DEFINE_RAW_SPINLOCK(pmac_pic_lock);
 static unsigned long ppc_lost_interrupts[NR_MASK_WORDS];
 static unsigned long ppc_cached_irq_mask[NR_MASK_WORDS];
 static int pmac_irq_cascade = -1;
-static struct irq_host *pmac_pic_host;
+static struct irq_domain *pmac_pic_host;
 
 static void __pmac_retrigger(unsigned int irq_nr)
 {
@@ -268,13 +268,13 @@ static struct irqaction gatwick_cascade_action = {
         .name           = "cascade",
 };
 
-static int pmac_pic_host_match(struct irq_host *h, struct device_node *node)
+static int pmac_pic_host_match(struct irq_domain *h, struct device_node *node)
 {
         /* We match all, we don't always have a node anyway */
         return 1;
 }
 
-static int pmac_pic_host_map(struct irq_host *h, unsigned int virq,
+static int pmac_pic_host_map(struct irq_domain *h, unsigned int virq,
                              irq_hw_number_t hw)
 {
         if (hw >= max_irqs)
@@ -288,21 +288,10 @@ static int pmac_pic_host_map(struct irq_host *h, unsigned int virq,
         return 0;
 }
 
-static int pmac_pic_host_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)
-
-{
-        *out_flags = IRQ_TYPE_NONE;
-        *out_hwirq = *intspec;
-        return 0;
-}
-
-static struct irq_host_ops pmac_pic_host_ops = {
+static const struct irq_domain_ops pmac_pic_host_ops = {
         .match = pmac_pic_host_match,
         .map = pmac_pic_host_map,
-        .xlate = pmac_pic_host_xlate,
+        .xlate = irq_domain_xlate_onecell,
 };
 
 static void __init pmac_pic_probe_oldstyle(void)
@@ -352,9 +341,8 @@ static void __init pmac_pic_probe_oldstyle(void)
         /*
          * Allocate an irq host
          */
-        pmac_pic_host = irq_alloc_host(master, IRQ_HOST_MAP_LINEAR, max_irqs,
-                                       &pmac_pic_host_ops,
-                                       max_irqs);
+        pmac_pic_host = irq_domain_add_linear(master, max_irqs,
+                                              &pmac_pic_host_ops, NULL);
         BUG_ON(pmac_pic_host == NULL);
         irq_set_default_host(pmac_pic_host);
 
@@ -469,7 +457,6 @@ static struct mpic * __init pmac_setup_one_mpic(struct device_node *np,
 
         pmac_call_feature(PMAC_FTR_ENABLE_MPIC, np, 0, 0);
 
-        flags |= MPIC_WANTS_RESET;
         if (of_get_property(np, "big-endian", NULL))
                 flags |= MPIC_BIG_ENDIAN;
 
diff --git a/arch/powerpc/platforms/powermac/smp.c b/arch/powerpc/platforms/powermac/smp.c
index 44d769258ebf..a81e5a88fbdf 100644
--- a/arch/powerpc/platforms/powermac/smp.c
+++ b/arch/powerpc/platforms/powermac/smp.c
@@ -125,7 +125,7 @@ static volatile u32 __iomem *psurge_start;
 static int psurge_type = PSURGE_NONE;
 
 /* irq for secondary cpus to report */
-static struct irq_host *psurge_host;
+static struct irq_domain *psurge_host;
 int psurge_secondary_virq;
 
 /*
@@ -176,7 +176,7 @@ static void smp_psurge_cause_ipi(int cpu, unsigned long data)
         psurge_set_ipi(cpu);
 }
 
-static int psurge_host_map(struct irq_host *h, unsigned int virq,
+static int psurge_host_map(struct irq_domain *h, unsigned int virq,
                          irq_hw_number_t hw)
 {
         irq_set_chip_and_handler(virq, &dummy_irq_chip, handle_percpu_irq);
@@ -184,7 +184,7 @@ static int psurge_host_map(struct irq_host *h, unsigned int virq,
         return 0;
 }
 
-struct irq_host_ops psurge_host_ops = {
+static const struct irq_domain_ops psurge_host_ops = {
         .map    = psurge_host_map,
 };
 
@@ -192,8 +192,7 @@ static int psurge_secondary_ipi_init(void)
 {
         int rc = -ENOMEM;
 
-        psurge_host = irq_alloc_host(NULL, IRQ_HOST_MAP_NOMAP, 0,
-                &psurge_host_ops, 0);
+        psurge_host = irq_domain_add_nomap(NULL, &psurge_host_ops, NULL);
 
         if (psurge_host)
                 psurge_secondary_virq = irq_create_direct_mapping(psurge_host);
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index f31162cfdaa9..fbdd74dac3ac 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -204,11 +204,10 @@ static void __devinit pnv_ioda_offset_bus(struct pci_bus *bus,
         pr_devel("  -> OBR %s [%x] +%016llx\n",
                  bus->self ? pci_name(bus->self) : "root", flags, offset);
 
-        for (i = 0; i < 2; i++) {
-                r = bus->resource[i];
+        pci_bus_for_each_resource(bus, r, i) {
                 if (r && (r->flags & flags)) {
-                        bus->resource[i]->start += offset;
-                        bus->resource[i]->end += offset;
+                        r->start += offset;
+                        r->end += offset;
                 }
         }
         list_for_each_entry(dev, &bus->devices, bus_list)
@@ -288,12 +287,17 @@ static void __devinit pnv_ioda_calc_bus(struct pci_bus *bus, unsigned int flags,
          * assignment algorithm is going to be uber-trivial for now, we
          * can try to be smarter later at filling out holes.
          */
-        start = bus->self ? 0 : bus->resource[bres]->start;
-
-        /* Don't hand out IO 0 */
-        if ((flags & IORESOURCE_IO) && !bus->self)
-                start += 0x1000;
-
+        if (bus->self) {
+                /* No offset for downstream bridges */
+                start = 0;
+        } else {
+                /* Offset from the root */
+                if (flags & IORESOURCE_IO)
+                        /* Don't hand out IO 0 */
+                        start = hose->io_resource.start + 0x1000;
+                else
+                        start = hose->mem_resources[0].start;
+        }
         while(!list_empty(&head)) {
                 w = list_first_entry(&head, struct resource_wrap, link);
                 list_del(&w->link);
@@ -321,13 +325,20 @@ static void __devinit pnv_ioda_calc_bus(struct pci_bus *bus, unsigned int flags,
  empty:
         /* Only setup P2P's, not the PHB itself */
         if (bus->self) {
-                WARN_ON(bus->resource[bres] == NULL);
-                bus->resource[bres]->start = 0;
-                bus->resource[bres]->flags = (*size) ? flags : 0;
-                bus->resource[bres]->end = (*size) ? (*size - 1) : 0;
+                struct resource *res = bus->resource[bres];
+
+                if (WARN_ON(res == NULL))
+                        return;
 
-                /* Clear prefetch bus resources for now */
-                bus->resource[2]->flags = 0;
+                /*
+                 * FIXME: We should probably export and call
+                 * pci_bridge_check_ranges() to properly re-initialize
+                 * the PCI portion of the flags here, and to detect
+                 * what the bridge actually supports.
+                 */
+                res->start = 0;
+                res->flags = (*size) ? flags : 0;
+                res->end = (*size) ? (*size - 1) : 0;
         }
 
         pr_devel("<- CBR %s [%x] *size=%016llx *align=%016llx\n",
@@ -1288,15 +1299,14 @@ void __init pnv_pci_init_ioda1_phb(struct device_node *np)
         /* Setup MSI support */
         pnv_pci_init_ioda_msis(phb);
 
-        /* We set both probe_only and PCI_REASSIGN_ALL_RSRC. This is an
+        /* We set both PCI_PROBE_ONLY and PCI_REASSIGN_ALL_RSRC. This is an
          * odd combination which essentially means that we skip all resource
          * fixups and assignments in the generic code, and do it all
          * ourselves here
          */
-        pci_probe_only = 1;
         ppc_md.pcibios_fixup_phb = pnv_pci_ioda_fixup_phb;
         ppc_md.pcibios_enable_device_hook = pnv_pci_enable_device_hook;
-        pci_add_flags(PCI_REASSIGN_ALL_RSRC);
+        pci_add_flags(PCI_PROBE_ONLY | PCI_REASSIGN_ALL_RSRC);
 
         /* Reset IODA tables to a clean state */
         rc = opal_pci_reset(phb_id, OPAL_PCI_IODA_TABLE_RESET, OPAL_ASSERT_RESET);
diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c
index a70bc1e385eb..be3cfc5ceabb 100644
--- a/arch/powerpc/platforms/powernv/pci.c
+++ b/arch/powerpc/platforms/powernv/pci.c
@@ -31,6 +31,7 @@
 #include <asm/iommu.h>
 #include <asm/tce.h>
 #include <asm/abs_addr.h>
+#include <asm/firmware.h>
 
 #include "powernv.h"
 #include "pci.h"
@@ -52,32 +53,38 @@ static int pnv_msi_check_device(struct pci_dev* pdev, int nvec, int type)
 
 static unsigned int pnv_get_one_msi(struct pnv_phb *phb)
 {
-        unsigned int id;
+        unsigned long flags;
+        unsigned int id, rc;
+
+        spin_lock_irqsave(&phb->lock, flags);
 
-        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;
+                rc = 0;
+                goto out;
         }
         __set_bit(id, phb->msi_map);
-        spin_unlock(&phb->lock);
-        return id + phb->msi_base;
+        rc = id + phb->msi_base;
+out:
+        spin_unlock_irqrestore(&phb->lock, flags);
+        return rc;
 }
 
 static void pnv_put_msi(struct pnv_phb *phb, unsigned int hwirq)
 {
+        unsigned long flags;
         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);
+
+        spin_lock_irqsave(&phb->lock, flags);
         __clear_bit(id, phb->msi_map);
-        spin_unlock(&phb->lock);
+        spin_unlock_irqrestore(&phb->lock, flags);
 }
 
 static int pnv_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
@@ -555,10 +562,7 @@ 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;
+        pci_add_flags(PCI_CAN_SKIP_ISA_ALIGN);
 
         /* OPAL absent, try POPAL first then RTAS detection of PHBs */
         if (!firmware_has_feature(FW_FEATURE_OPAL)) {
diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c
index 467bd4ac6824..db1ad1c8f68f 100644
--- a/arch/powerpc/platforms/powernv/setup.c
+++ b/arch/powerpc/platforms/powernv/setup.c
@@ -31,7 +31,6 @@
 #include <asm/xics.h>
 #include <asm/rtas.h>
 #include <asm/opal.h>
-#include <asm/xics.h>
 
 #include "powernv.h"
 
diff --git a/arch/powerpc/platforms/ps3/interrupt.c b/arch/powerpc/platforms/ps3/interrupt.c
index 617efa12a3a5..2a4ff86cc21f 100644
--- a/arch/powerpc/platforms/ps3/interrupt.c
+++ b/arch/powerpc/platforms/ps3/interrupt.c
@@ -667,7 +667,7 @@ static void __maybe_unused _dump_mask(struct ps3_private *pd,
 static void dump_bmp(struct ps3_private* pd) {};
 #endif /* defined(DEBUG) */
 
-static int ps3_host_map(struct irq_host *h, unsigned int virq,
+static int ps3_host_map(struct irq_domain *h, unsigned int virq,
         irq_hw_number_t hwirq)
 {
         DBG("%s:%d: hwirq %lu, virq %u\n", __func__, __LINE__, hwirq,
@@ -678,13 +678,13 @@ static int ps3_host_map(struct irq_host *h, unsigned int virq,
         return 0;
 }
 
-static int ps3_host_match(struct irq_host *h, struct device_node *np)
+static int ps3_host_match(struct irq_domain *h, struct device_node *np)
 {
         /* Match all */
         return 1;
 }
 
-static struct irq_host_ops ps3_host_ops = {
+static const struct irq_domain_ops ps3_host_ops = {
         .map = ps3_host_map,
         .match = ps3_host_match,
 };
@@ -751,10 +751,9 @@ void __init ps3_init_IRQ(void)
 {
         int result;
         unsigned cpu;
-        struct irq_host *host;
+        struct irq_domain *host;
 
-        host = irq_alloc_host(NULL, IRQ_HOST_MAP_NOMAP, 0, &ps3_host_ops,
-                PS3_INVALID_OUTLET);
+        host = irq_domain_add_nomap(NULL, &ps3_host_ops, NULL);
         irq_set_default_host(host);
         irq_set_virq_count(PS3_PLUG_MAX + 1);
 
diff --git a/arch/powerpc/platforms/pseries/Kconfig b/arch/powerpc/platforms/pseries/Kconfig
index ae7b6d41fed3..aadbe4f6d537 100644
--- a/arch/powerpc/platforms/pseries/Kconfig
+++ b/arch/powerpc/platforms/pseries/Kconfig
@@ -3,6 +3,7 @@ config PPC_PSERIES
         bool "IBM pSeries & new (POWER5-based) iSeries"
         select HAVE_PCSPKR_PLATFORM
         select MPIC
+        select OF_DYNAMIC
         select PCI_MSI
         select PPC_XICS
         select PPC_ICP_NATIVE
@@ -72,7 +73,7 @@ config IO_EVENT_IRQ
 
 config LPARCFG
         bool "LPAR Configuration Data"
-        depends on PPC_PSERIES || PPC_ISERIES
+        depends on PPC_PSERIES
         help
         Provide system capacity information via human readable
         <key word>=<value> pairs through a /proc/ppc64/lparcfg interface.
@@ -122,7 +123,7 @@ config DTL
           Say N if you are unsure.
 
 config PSERIES_IDLE
-        tristate "Cpuidle driver for pSeries platforms"
+        bool "Cpuidle driver for pSeries platforms"
         depends on CPU_IDLE
         depends on PPC_PSERIES
         default y
diff --git a/arch/powerpc/platforms/pseries/Makefile b/arch/powerpc/platforms/pseries/Makefile
index 236db46b4078..c222189f5bb2 100644
--- a/arch/powerpc/platforms/pseries/Makefile
+++ b/arch/powerpc/platforms/pseries/Makefile
@@ -6,7 +6,8 @@ obj-y			:= lpar.o hvCall.o nvram.o reconfig.o \
                            firmware.o power.o dlpar.o mobility.o
 obj-$(CONFIG_SMP)       += smp.o
 obj-$(CONFIG_SCANLOG)   += scanlog.o
-obj-$(CONFIG_EEH)       += eeh.o eeh_cache.o eeh_driver.o eeh_event.o eeh_sysfs.o
+obj-$(CONFIG_EEH)       += eeh.o eeh_dev.o eeh_cache.o eeh_driver.o \
+                           eeh_event.o eeh_sysfs.o eeh_pseries.o
 obj-$(CONFIG_KEXEC)     += kexec.o
 obj-$(CONFIG_PCI)       += pci.o pci_dlpar.o
 obj-$(CONFIG_PSERIES_MSI)       += msi.o
@@ -18,7 +19,6 @@ obj-$(CONFIG_MEMORY_HOTPLUG)	+= hotplug-memory.o
 obj-$(CONFIG_HVC_CONSOLE)       += hvconsole.o
 obj-$(CONFIG_HVCS)              += hvcserver.o
 obj-$(CONFIG_HCALL_STATS)       += hvCall_inst.o
-obj-$(CONFIG_PHYP_DUMP)         += phyp_dump.o
 obj-$(CONFIG_CMM)               += cmm.o
 obj-$(CONFIG_DTL)               += dtl.o
 obj-$(CONFIG_IO_EVENT_IRQ)      += io_event_irq.o
diff --git a/arch/powerpc/platforms/pseries/eeh.c b/arch/powerpc/platforms/pseries/eeh.c
index 565869022e3d..309d38ef7322 100644
--- a/arch/powerpc/platforms/pseries/eeh.c
+++ b/arch/powerpc/platforms/pseries/eeh.c
@@ -1,8 +1,8 @@
 /*
- * eeh.c
  * Copyright IBM Corporation 2001, 2005, 2006
  * Copyright Dave Engebretsen & Todd Inglett 2001
  * Copyright Linas Vepstas 2005, 2006
+ * Copyright 2001-2012 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
@@ -22,7 +22,7 @@
  */
 
 #include <linux/delay.h>
-#include <linux/sched.h>        /* for init_mm */
+#include <linux/sched.h>
 #include <linux/init.h>
 #include <linux/list.h>
 #include <linux/pci.h>
@@ -86,16 +86,8 @@
 /* Time to wait for a PCI slot to report status, in milliseconds */
 #define PCI_BUS_RESET_WAIT_MSEC (60*1000)
 
-/* RTAS tokens */
-static int ibm_set_eeh_option;
-static int ibm_set_slot_reset;
-static int ibm_read_slot_reset_state;
-static int ibm_read_slot_reset_state2;
-static int ibm_slot_error_detail;
-static int ibm_get_config_addr_info;
-static int ibm_get_config_addr_info2;
-static int ibm_configure_bridge;
-static int ibm_configure_pe;
+/* Platform dependent EEH operations */
+struct eeh_ops *eeh_ops = NULL;
 
 int eeh_subsystem_enabled;
 EXPORT_SYMBOL(eeh_subsystem_enabled);
@@ -103,14 +95,6 @@ EXPORT_SYMBOL(eeh_subsystem_enabled);
 /* Lock to avoid races due to multiple reports of an error */
 static DEFINE_RAW_SPINLOCK(confirm_error_lock);
 
-/* Buffer for reporting slot-error-detail rtas calls. Its here
- * in BSS, and not dynamically alloced, so that it ends up in
- * RMO where RTAS can access it.
- */
-static unsigned char slot_errbuf[RTAS_ERROR_LOG_MAX];
-static DEFINE_SPINLOCK(slot_errbuf_lock);
-static int eeh_error_buf_size;
-
 /* Buffer for reporting pci register dumps. Its here in BSS, and
  * not dynamically alloced, so that it ends up in RMO where RTAS
  * can access it.
@@ -118,74 +102,50 @@ static int eeh_error_buf_size;
 #define EEH_PCI_REGS_LOG_LEN 4096
 static unsigned char pci_regs_buf[EEH_PCI_REGS_LOG_LEN];
 
-/* System monitoring statistics */
-static unsigned long no_device;
-static unsigned long no_dn;
-static unsigned long no_cfg_addr;
-static unsigned long ignored_check;
-static unsigned long total_mmio_ffs;
-static unsigned long false_positives;
-static unsigned long slot_resets;
-
-#define IS_BRIDGE(class_code) (((class_code)<<16) == PCI_BASE_CLASS_BRIDGE)
+/*
+ * The struct is used to maintain the EEH global statistic
+ * information. Besides, the EEH global statistics will be
+ * exported to user space through procfs
+ */
+struct eeh_stats {
+        u64 no_device;          /* PCI device not found         */
+        u64 no_dn;              /* OF node not found            */
+        u64 no_cfg_addr;        /* Config address not found     */
+        u64 ignored_check;      /* EEH check skipped            */
+        u64 total_mmio_ffs;     /* Total EEH checks             */
+        u64 false_positives;    /* Unnecessary EEH checks       */
+        u64 slot_resets;        /* PE reset                     */
+};
 
-/* --------------------------------------------------------------- */
-/* Below lies the EEH event infrastructure */
+static struct eeh_stats eeh_stats;
 
-static void rtas_slot_error_detail(struct pci_dn *pdn, int severity,
-                                   char *driver_log, size_t loglen)
-{
-        int config_addr;
-        unsigned long flags;
-        int rc;
-
-        /* Log the error with the rtas logger */
-        spin_lock_irqsave(&slot_errbuf_lock, flags);
-        memset(slot_errbuf, 0, eeh_error_buf_size);
-
-        /* Use PE configuration address, if present */
-        config_addr = pdn->eeh_config_addr;
-        if (pdn->eeh_pe_config_addr)
-                config_addr = pdn->eeh_pe_config_addr;
-
-        rc = rtas_call(ibm_slot_error_detail,
-                       8, 1, NULL, config_addr,
-                       BUID_HI(pdn->phb->buid),
-                       BUID_LO(pdn->phb->buid),
-                       virt_to_phys(driver_log), loglen,
-                       virt_to_phys(slot_errbuf),
-                       eeh_error_buf_size,
-                       severity);
-
-        if (rc == 0)
-                log_error(slot_errbuf, ERR_TYPE_RTAS_LOG, 0);
-        spin_unlock_irqrestore(&slot_errbuf_lock, flags);
-}
+#define IS_BRIDGE(class_code) (((class_code)<<16) == PCI_BASE_CLASS_BRIDGE)
 
 /**
- * gather_pci_data - copy assorted PCI config space registers to buff
- * @pdn: device to report data for
+ * eeh_gather_pci_data - Copy assorted PCI config space registers to buff
+ * @edev: device to report data for
  * @buf: point to buffer in which to log
  * @len: amount of room in buffer
  *
  * This routine captures assorted PCI configuration space data,
  * and puts them into a buffer for RTAS error logging.
  */
-static size_t gather_pci_data(struct pci_dn *pdn, char * buf, size_t len)
+static size_t eeh_gather_pci_data(struct eeh_dev *edev, char * buf, size_t len)
 {
-        struct pci_dev *dev = pdn->pcidev;
+        struct device_node *dn = eeh_dev_to_of_node(edev);
+        struct pci_dev *dev = eeh_dev_to_pci_dev(edev);
         u32 cfg;
         int cap, i;
         int n = 0;
 
-        n += scnprintf(buf+n, len-n, "%s\n", pdn->node->full_name);
-        printk(KERN_WARNING "EEH: of node=%s\n", pdn->node->full_name);
+        n += scnprintf(buf+n, len-n, "%s\n", dn->full_name);
+        printk(KERN_WARNING "EEH: of node=%s\n", dn->full_name);
 
-        rtas_read_config(pdn, PCI_VENDOR_ID, 4, &cfg);
+        eeh_ops->read_config(dn, PCI_VENDOR_ID, 4, &cfg);
         n += scnprintf(buf+n, len-n, "dev/vend:%08x\n", cfg);
         printk(KERN_WARNING "EEH: PCI device/vendor: %08x\n", cfg);
 
-        rtas_read_config(pdn, PCI_COMMAND, 4, &cfg);
+        eeh_ops->read_config(dn, PCI_COMMAND, 4, &cfg);
         n += scnprintf(buf+n, len-n, "cmd/stat:%x\n", cfg);
         printk(KERN_WARNING "EEH: PCI cmd/status register: %08x\n", cfg);
 
@@ -196,11 +156,11 @@ static size_t gather_pci_data(struct pci_dn *pdn, char * buf, size_t len)
 
         /* Gather bridge-specific registers */
         if (dev->class >> 16 == PCI_BASE_CLASS_BRIDGE) {
-                rtas_read_config(pdn, PCI_SEC_STATUS, 2, &cfg);
+                eeh_ops->read_config(dn, PCI_SEC_STATUS, 2, &cfg);
                 n += scnprintf(buf+n, len-n, "sec stat:%x\n", cfg);
                 printk(KERN_WARNING "EEH: Bridge secondary status: %04x\n", cfg);
 
-                rtas_read_config(pdn, PCI_BRIDGE_CONTROL, 2, &cfg);
+                eeh_ops->read_config(dn, PCI_BRIDGE_CONTROL, 2, &cfg);
                 n += scnprintf(buf+n, len-n, "brdg ctl:%x\n", cfg);
                 printk(KERN_WARNING "EEH: Bridge control: %04x\n", cfg);
         }
@@ -208,11 +168,11 @@ static size_t gather_pci_data(struct pci_dn *pdn, char * buf, size_t len)
         /* Dump out the PCI-X command and status regs */
         cap = pci_find_capability(dev, PCI_CAP_ID_PCIX);
         if (cap) {
-                rtas_read_config(pdn, cap, 4, &cfg);
+                eeh_ops->read_config(dn, cap, 4, &cfg);
                 n += scnprintf(buf+n, len-n, "pcix-cmd:%x\n", cfg);
                 printk(KERN_WARNING "EEH: PCI-X cmd: %08x\n", cfg);
 
-                rtas_read_config(pdn, cap+4, 4, &cfg);
+                eeh_ops->read_config(dn, cap+4, 4, &cfg);
                 n += scnprintf(buf+n, len-n, "pcix-stat:%x\n", cfg);
                 printk(KERN_WARNING "EEH: PCI-X status: %08x\n", cfg);
         }
@@ -225,7 +185,7 @@ static size_t gather_pci_data(struct pci_dn *pdn, char * buf, size_t len)
                        "EEH: PCI-E capabilities and status follow:\n");
 
                 for (i=0; i<=8; i++) {
-                        rtas_read_config(pdn, cap+4*i, 4, &cfg);
+                        eeh_ops->read_config(dn, cap+4*i, 4, &cfg);
                         n += scnprintf(buf+n, len-n, "%02x:%x\n", 4*i, cfg);
                         printk(KERN_WARNING "EEH: PCI-E %02x: %08x\n", i, cfg);
                 }
@@ -237,7 +197,7 @@ static size_t gather_pci_data(struct pci_dn *pdn, char * buf, size_t len)
                                "EEH: PCI-E AER capability register set follows:\n");
 
                         for (i=0; i<14; i++) {
-                                rtas_read_config(pdn, cap+4*i, 4, &cfg);
+                                eeh_ops->read_config(dn, cap+4*i, 4, &cfg);
                                 n += scnprintf(buf+n, len-n, "%02x:%x\n", 4*i, cfg);
                                 printk(KERN_WARNING "EEH: PCI-E AER %02x: %08x\n", i, cfg);
                         }
@@ -246,111 +206,46 @@ static size_t gather_pci_data(struct pci_dn *pdn, char * buf, size_t len)
 
         /* Gather status on devices under the bridge */
         if (dev->class >> 16 == PCI_BASE_CLASS_BRIDGE) {
-                struct device_node *dn;
+                struct device_node *child;
 
-                for_each_child_of_node(pdn->node, dn) {
-                        pdn = PCI_DN(dn);
-                        if (pdn)
-                                n += gather_pci_data(pdn, buf+n, len-n);
+                for_each_child_of_node(dn, child) {
+                        if (of_node_to_eeh_dev(child))
+                                n += eeh_gather_pci_data(of_node_to_eeh_dev(child), buf+n, len-n);
                 }
         }
 
         return n;
 }
 
-void eeh_slot_error_detail(struct pci_dn *pdn, int severity)
-{
-        size_t loglen = 0;
-        pci_regs_buf[0] = 0;
-
-        rtas_pci_enable(pdn, EEH_THAW_MMIO);
-        rtas_configure_bridge(pdn);
-        eeh_restore_bars(pdn);
-        loglen = gather_pci_data(pdn, pci_regs_buf, EEH_PCI_REGS_LOG_LEN);
-
-        rtas_slot_error_detail(pdn, severity, pci_regs_buf, loglen);
-}
-
-/**
- * read_slot_reset_state - Read the reset state of a device node's slot
- * @dn: device node to read
- * @rets: array to return results in
- */
-static int read_slot_reset_state(struct pci_dn *pdn, int rets[])
-{
-        int token, outputs;
-        int config_addr;
-
-        if (ibm_read_slot_reset_state2 != RTAS_UNKNOWN_SERVICE) {
-                token = ibm_read_slot_reset_state2;
-                outputs = 4;
-        } else {
-                token = ibm_read_slot_reset_state;
-                rets[2] = 0; /* fake PE Unavailable info */
-                outputs = 3;
-        }
-
-        /* Use PE configuration address, if present */
-        config_addr = pdn->eeh_config_addr;
-        if (pdn->eeh_pe_config_addr)
-                config_addr = pdn->eeh_pe_config_addr;
-
-        return rtas_call(token, 3, outputs, rets, config_addr,
-                         BUID_HI(pdn->phb->buid), BUID_LO(pdn->phb->buid));
-}
-
 /**
- * eeh_wait_for_slot_status - returns error status of slot
- * @pdn pci device node
- * @max_wait_msecs maximum number to millisecs to wait
+ * eeh_slot_error_detail - Generate combined log including driver log and error log
+ * @edev: device to report error log for
+ * @severity: temporary or permanent error log
  *
- * Return negative value if a permanent error, else return
- * Partition Endpoint (PE) status value.
- *
- * If @max_wait_msecs is positive, then this routine will
- * sleep until a valid status can be obtained, or until
- * the max allowed wait time is exceeded, in which case
- * a -2 is returned.
+ * This routine should be called to generate the combined log, which
+ * is comprised of driver log and error log. The driver log is figured
+ * out from the config space of the corresponding PCI device, while
+ * the error log is fetched through platform dependent function call.
  */
-int
-eeh_wait_for_slot_status(struct pci_dn *pdn, int max_wait_msecs)
+void eeh_slot_error_detail(struct eeh_dev *edev, int severity)
 {
-        int rc;
-        int rets[3];
-        int mwait;
-
-        while (1) {
-                rc = read_slot_reset_state(pdn, rets);
-                if (rc) return rc;
-                if (rets[1] == 0) return -1;  /* EEH is not supported */
-
-                if (rets[0] != 5) return rets[0]; /* return actual status */
-
-                if (rets[2] == 0) return -1; /* permanently unavailable */
+        size_t loglen = 0;
+        pci_regs_buf[0] = 0;
 
-                if (max_wait_msecs <= 0) break;
+        eeh_pci_enable(edev, EEH_OPT_THAW_MMIO);
+        eeh_ops->configure_bridge(eeh_dev_to_of_node(edev));
+        eeh_restore_bars(edev);
+        loglen = eeh_gather_pci_data(edev, pci_regs_buf, EEH_PCI_REGS_LOG_LEN);
 
-                mwait = rets[2];
-                if (mwait <= 0) {
-                        printk (KERN_WARNING
-                                "EEH: Firmware returned bad wait value=%d\n", mwait);
-                        mwait = 1000;
-                } else if (mwait > 300*1000) {
-                        printk (KERN_WARNING
-                                "EEH: Firmware is taking too long, time=%d\n", mwait);
-                        mwait = 300*1000;
-                }
-                max_wait_msecs -= mwait;
-                msleep (mwait);
-        }
-
-        printk(KERN_WARNING "EEH: Timed out waiting for slot status\n");
-        return -2;
+        eeh_ops->get_log(eeh_dev_to_of_node(edev), severity, pci_regs_buf, loglen);
 }
 
 /**
- * eeh_token_to_phys - convert EEH address token to phys address
- * @token i/o token, should be address in the form 0xA....
+ * eeh_token_to_phys - Convert EEH address token to phys address
+ * @token: I/O token, should be address in the form 0xA....
+ *
+ * This routine should be called to convert virtual I/O address
+ * to physical one.
  */
 static inline unsigned long eeh_token_to_phys(unsigned long token)
 {
@@ -365,36 +260,43 @@ static inline unsigned long eeh_token_to_phys(unsigned long token)
         return pa | (token & (PAGE_SIZE-1));
 }
 
-/** 
- * Return the "partitionable endpoint" (pe) under which this device lies
+/**
+ * eeh_find_device_pe - Retrieve the PE for the given device
+ * @dn: device node
+ *
+ * Return the PE under which this device lies
  */
-struct device_node * find_device_pe(struct device_node *dn)
+struct device_node *eeh_find_device_pe(struct device_node *dn)
 {
-        while ((dn->parent) && PCI_DN(dn->parent) &&
-              (PCI_DN(dn->parent)->eeh_mode & EEH_MODE_SUPPORTED)) {
+        while (dn->parent && of_node_to_eeh_dev(dn->parent) &&
+               (of_node_to_eeh_dev(dn->parent)->mode & EEH_MODE_SUPPORTED)) {
                 dn = dn->parent;
         }
         return dn;
 }
 
-/** Mark all devices that are children of this device as failed.
- *  Mark the device driver too, so that it can see the failure
- *  immediately; this is critical, since some drivers poll
- *  status registers in interrupts ... If a driver is polling,
- *  and the slot is frozen, then the driver can deadlock in
- *  an interrupt context, which is bad.
+/**
+ * __eeh_mark_slot - Mark all child devices as failed
+ * @parent: parent device
+ * @mode_flag: failure flag
+ *
+ * Mark all devices that are children of this device as failed.
+ * Mark the device driver too, so that it can see the failure
+ * immediately; this is critical, since some drivers poll
+ * status registers in interrupts ... If a driver is polling,
+ * and the slot is frozen, then the driver can deadlock in
+ * an interrupt context, which is bad.
  */
-
 static void __eeh_mark_slot(struct device_node *parent, int mode_flag)
 {
         struct device_node *dn;
 
         for_each_child_of_node(parent, dn) {
-                if (PCI_DN(dn)) {
+                if (of_node_to_eeh_dev(dn)) {
                         /* Mark the pci device driver too */
-                        struct pci_dev *dev = PCI_DN(dn)->pcidev;
+                        struct pci_dev *dev = of_node_to_eeh_dev(dn)->pdev;
 
-                        PCI_DN(dn)->eeh_mode |= mode_flag;
+                        of_node_to_eeh_dev(dn)->mode |= mode_flag;
 
                         if (dev && dev->driver)
                                 dev->error_state = pci_channel_io_frozen;
@@ -404,92 +306,81 @@ static void __eeh_mark_slot(struct device_node *parent, int mode_flag)
         }
 }
 
-void eeh_mark_slot (struct device_node *dn, int mode_flag)
+/**
+ * eeh_mark_slot - Mark the indicated device and its children as failed
+ * @dn: parent device
+ * @mode_flag: failure flag
+ *
+ * Mark the indicated device and its child devices as failed.
+ * The device drivers are marked as failed as well.
+ */
+void eeh_mark_slot(struct device_node *dn, int mode_flag)
 {
         struct pci_dev *dev;
-        dn = find_device_pe (dn);
+        dn = eeh_find_device_pe(dn);
 
         /* Back up one, since config addrs might be shared */
-        if (!pcibios_find_pci_bus(dn) && PCI_DN(dn->parent))
+        if (!pcibios_find_pci_bus(dn) && of_node_to_eeh_dev(dn->parent))
                 dn = dn->parent;
 
-        PCI_DN(dn)->eeh_mode |= mode_flag;
+        of_node_to_eeh_dev(dn)->mode |= mode_flag;
 
         /* Mark the pci device too */
-        dev = PCI_DN(dn)->pcidev;
+        dev = of_node_to_eeh_dev(dn)->pdev;
         if (dev)
                 dev->error_state = pci_channel_io_frozen;
 
         __eeh_mark_slot(dn, mode_flag);
 }
 
+/**
+ * __eeh_clear_slot - Clear failure flag for the child devices
+ * @parent: parent device
+ * @mode_flag: flag to be cleared
+ *
+ * Clear failure flag for the child devices.
+ */
 static void __eeh_clear_slot(struct device_node *parent, int mode_flag)
 {
         struct device_node *dn;
 
         for_each_child_of_node(parent, dn) {
-                if (PCI_DN(dn)) {
-                        PCI_DN(dn)->eeh_mode &= ~mode_flag;
-                        PCI_DN(dn)->eeh_check_count = 0;
+                if (of_node_to_eeh_dev(dn)) {
+                        of_node_to_eeh_dev(dn)->mode &= ~mode_flag;
+                        of_node_to_eeh_dev(dn)->check_count = 0;
                         __eeh_clear_slot(dn, mode_flag);
                 }
         }
 }
 
-void eeh_clear_slot (struct device_node *dn, int mode_flag)
+/**
+ * eeh_clear_slot - Clear failure flag for the indicated device and its children
+ * @dn: parent device
+ * @mode_flag: flag to be cleared
+ *
+ * Clear failure flag for the indicated device and its children.
+ */
+void eeh_clear_slot(struct device_node *dn, int mode_flag)
 {
         unsigned long flags;
         raw_spin_lock_irqsave(&confirm_error_lock, flags);
         
-        dn = find_device_pe (dn);
+        dn = eeh_find_device_pe(dn);
         
         /* Back up one, since config addrs might be shared */
-        if (!pcibios_find_pci_bus(dn) && PCI_DN(dn->parent))
+        if (!pcibios_find_pci_bus(dn) && of_node_to_eeh_dev(dn->parent))
                 dn = dn->parent;
 
-        PCI_DN(dn)->eeh_mode &= ~mode_flag;
-        PCI_DN(dn)->eeh_check_count = 0;
+        of_node_to_eeh_dev(dn)->mode &= ~mode_flag;
+        of_node_to_eeh_dev(dn)->check_count = 0;
         __eeh_clear_slot(dn, mode_flag);
         raw_spin_unlock_irqrestore(&confirm_error_lock, flags);
 }
 
-void __eeh_set_pe_freset(struct device_node *parent, unsigned int *freset)
-{
-        struct device_node *dn;
-
-        for_each_child_of_node(parent, dn) {
-                if (PCI_DN(dn)) {
-
-                        struct pci_dev *dev = PCI_DN(dn)->pcidev;
-
-                        if (dev && dev->driver)
-                                *freset |= dev->needs_freset;
-
-                        __eeh_set_pe_freset(dn, freset);
-                }
-        }
-}
-
-void eeh_set_pe_freset(struct device_node *dn, unsigned int *freset)
-{
-        struct pci_dev *dev;
-        dn = find_device_pe(dn);
-
-        /* Back up one, since config addrs might be shared */
-        if (!pcibios_find_pci_bus(dn) && PCI_DN(dn->parent))
-                dn = dn->parent;
-
-        dev = PCI_DN(dn)->pcidev;
-        if (dev)
-                *freset |= dev->needs_freset;
-
-        __eeh_set_pe_freset(dn, freset);
-}
-
 /**
- * eeh_dn_check_failure - check if all 1's data is due to EEH slot freeze
- * @dn device node
- * @dev pci device, if known
+ * eeh_dn_check_failure - Check if all 1's data is due to EEH slot freeze
+ * @dn: device node
+ * @dev: pci device, if known
  *
  * Check for an EEH failure for the given device node.  Call this
  * routine if the result of a read was all 0xff's and you want to
@@ -504,35 +395,34 @@ void eeh_set_pe_freset(struct device_node *dn, unsigned int *freset)
 int eeh_dn_check_failure(struct device_node *dn, struct pci_dev *dev)
 {
         int ret;
-        int rets[3];
         unsigned long flags;
-        struct pci_dn *pdn;
+        struct eeh_dev *edev;
         int rc = 0;
         const char *location;
 
-        total_mmio_ffs++;
+        eeh_stats.total_mmio_ffs++;
 
         if (!eeh_subsystem_enabled)
                 return 0;
 
         if (!dn) {
-                no_dn++;
+                eeh_stats.no_dn++;
                 return 0;
         }
-        dn = find_device_pe(dn);
-        pdn = PCI_DN(dn);
+        dn = eeh_find_device_pe(dn);
+        edev = of_node_to_eeh_dev(dn);
 
         /* Access to IO BARs might get this far and still not want checking. */
-        if (!(pdn->eeh_mode & EEH_MODE_SUPPORTED) ||
-            pdn->eeh_mode & EEH_MODE_NOCHECK) {
-                ignored_check++;
+        if (!(edev->mode & EEH_MODE_SUPPORTED) ||
+            edev->mode & EEH_MODE_NOCHECK) {
+                eeh_stats.ignored_check++;
                 pr_debug("EEH: Ignored check (%x) for %s %s\n",
-                         pdn->eeh_mode, eeh_pci_name(dev), dn->full_name);
+                        edev->mode, eeh_pci_name(dev), dn->full_name);
                 return 0;
         }
 
-        if (!pdn->eeh_config_addr && !pdn->eeh_pe_config_addr) {
-                no_cfg_addr++;
+        if (!edev->config_addr && !edev->pe_config_addr) {
+                eeh_stats.no_cfg_addr++;
                 return 0;
         }
 
@@ -544,16 +434,16 @@ int eeh_dn_check_failure(struct device_node *dn, struct pci_dev *dev)
          */
         raw_spin_lock_irqsave(&confirm_error_lock, flags);
         rc = 1;
-        if (pdn->eeh_mode & EEH_MODE_ISOLATED) {
-                pdn->eeh_check_count ++;
-                if (pdn->eeh_check_count % EEH_MAX_FAILS == 0) {
+        if (edev->mode & EEH_MODE_ISOLATED) {
+                edev->check_count++;
+                if (edev->check_count % EEH_MAX_FAILS == 0) {
                         location = of_get_property(dn, "ibm,loc-code", NULL);
-                        printk (KERN_ERR "EEH: %d reads ignored for recovering device at "
+                        printk(KERN_ERR "EEH: %d reads ignored for recovering device at "
                                 "location=%s driver=%s pci addr=%s\n",
-                                pdn->eeh_check_count, location,
-                                dev->driver->name, eeh_pci_name(dev));
-                        printk (KERN_ERR "EEH: Might be infinite loop in %s driver\n",
-                                dev->driver->name);
+                                edev->check_count, location,
+                                eeh_driver_name(dev), eeh_pci_name(dev));
+                        printk(KERN_ERR "EEH: Might be infinite loop in %s driver\n",
+                                eeh_driver_name(dev));
                         dump_stack();
                 }
                 goto dn_unlock;
@@ -566,58 +456,39 @@ int eeh_dn_check_failure(struct device_node *dn, struct pci_dev *dev)
          * function zero of a multi-function device.
          * In any case they must share a common PHB.
          */
-        ret = read_slot_reset_state(pdn, rets);
-
-        /* If the call to firmware failed, punt */
-        if (ret != 0) {
-                printk(KERN_WARNING "EEH: read_slot_reset_state() failed; rc=%d dn=%s\n",
-                       ret, dn->full_name);
-                false_positives++;
-                pdn->eeh_false_positives ++;
-                rc = 0;
-                goto dn_unlock;
-        }
+        ret = eeh_ops->get_state(dn, NULL);
 
         /* Note that config-io to empty slots may fail;
-         * they are empty when they don't have children. */
-        if ((rets[0] == 5) && (rets[2] == 0) && (dn->child == NULL)) {
-                false_positives++;
-                pdn->eeh_false_positives ++;
-                rc = 0;
-                goto dn_unlock;
-        }
-
-        /* If EEH is not supported on this device, punt. */
-        if (rets[1] != 1) {
-                printk(KERN_WARNING "EEH: event on unsupported device, rc=%d dn=%s\n",
-                       ret, dn->full_name);
-                false_positives++;
-                pdn->eeh_false_positives ++;
-                rc = 0;
-                goto dn_unlock;
-        }
-
-        /* If not the kind of error we know about, punt. */
-        if (rets[0] != 1 && rets[0] != 2 && rets[0] != 4 && rets[0] != 5) {
-                false_positives++;
-                pdn->eeh_false_positives ++;
+         * they are empty when they don't have children.
+         * We will punt with the following conditions: Failure to get
+         * PE's state, EEH not support and Permanently unavailable
+         * state, PE is in good state.
+         */
+        if ((ret < 0) ||
+            (ret == EEH_STATE_NOT_SUPPORT) ||
+            (ret & (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE)) ==
+            (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE)) {
+                eeh_stats.false_positives++;
+                edev->false_positives ++;
                 rc = 0;
                 goto dn_unlock;
         }
 
-        slot_resets++;
+        eeh_stats.slot_resets++;
  
         /* Avoid repeated reports of this failure, including problems
          * with other functions on this device, and functions under
-         * bridges. */
-        eeh_mark_slot (dn, EEH_MODE_ISOLATED);
+         * bridges.
+         */
+        eeh_mark_slot(dn, EEH_MODE_ISOLATED);
         raw_spin_unlock_irqrestore(&confirm_error_lock, flags);
 
-        eeh_send_failure_event (dn, dev);
+        eeh_send_failure_event(edev);
 
         /* Most EEH events are due to device driver bugs.  Having
          * a stack trace will help the device-driver authors figure
-         * out what happened.  So print that out. */
+         * out what happened.  So print that out.
+         */
         dump_stack();
         return 1;
 
@@ -629,9 +500,9 @@ dn_unlock:
 EXPORT_SYMBOL_GPL(eeh_dn_check_failure);
 
 /**
- * eeh_check_failure - check if all 1's data is due to EEH slot freeze
- * @token i/o token, should be address in the form 0xA....
- * @val value, should be all 1's (XXX why do we need this arg??)
+ * eeh_check_failure - Check if all 1's data is due to EEH slot freeze
+ * @token: I/O token, should be address in the form 0xA....
+ * @val: value, should be all 1's (XXX why do we need this arg??)
  *
  * Check for an EEH failure at the given token address.  Call this
  * routine if the result of a read was all 0xff's and you want to
@@ -648,14 +519,14 @@ unsigned long eeh_check_failure(const volatile void __iomem *token, unsigned lon
 
         /* Finding the phys addr + pci device; this is pretty quick. */
         addr = eeh_token_to_phys((unsigned long __force) token);
-        dev = pci_get_device_by_addr(addr);
+        dev = pci_addr_cache_get_device(addr);
         if (!dev) {
-                no_device++;
+                eeh_stats.no_device++;
                 return val;
         }
 
         dn = pci_device_to_OF_node(dev);
-        eeh_dn_check_failure (dn, dev);
+        eeh_dn_check_failure(dn, dev);
 
         pci_dev_put(dev);
         return val;
@@ -663,115 +534,54 @@ unsigned long eeh_check_failure(const volatile void __iomem *token, unsigned lon
 
 EXPORT_SYMBOL(eeh_check_failure);
 
-/* ------------------------------------------------------------- */
-/* The code below deals with error recovery */
 
 /**
- * rtas_pci_enable - enable MMIO or DMA transfers for this slot
- * @pdn pci device node
+ * eeh_pci_enable - Enable MMIO or DMA transfers for this slot
+ * @edev: pci device node
+ *
+ * This routine should be called to reenable frozen MMIO or DMA
+ * so that it would work correctly again. It's useful while doing
+ * recovery or log collection on the indicated device.
  */
-
-int
-rtas_pci_enable(struct pci_dn *pdn, int function)
+int eeh_pci_enable(struct eeh_dev *edev, int function)
 {
-        int config_addr;
         int rc;
+        struct device_node *dn = eeh_dev_to_of_node(edev);
 
-        /* Use PE configuration address, if present */
-        config_addr = pdn->eeh_config_addr;
-        if (pdn->eeh_pe_config_addr)
-                config_addr = pdn->eeh_pe_config_addr;
-
-        rc = rtas_call(ibm_set_eeh_option, 4, 1, NULL,
-                       config_addr,
-                       BUID_HI(pdn->phb->buid),
-                       BUID_LO(pdn->phb->buid),
-                            function);
-
+        rc = eeh_ops->set_option(dn, function);
         if (rc)
                 printk(KERN_WARNING "EEH: Unexpected state change %d, err=%d dn=%s\n",
-                        function, rc, pdn->node->full_name);
+                        function, rc, dn->full_name);
 
-        rc = eeh_wait_for_slot_status (pdn, PCI_BUS_RESET_WAIT_MSEC);
-        if ((rc == 4) && (function == EEH_THAW_MMIO))
+        rc = eeh_ops->wait_state(dn, PCI_BUS_RESET_WAIT_MSEC);
+        if (rc > 0 && (rc & EEH_STATE_MMIO_ENABLED) &&
+           (function == EEH_OPT_THAW_MMIO))
                 return 0;
 
         return rc;
 }
 
 /**
- * rtas_pci_slot_reset - raises/lowers the pci #RST line
- * @pdn pci device node
- * @state: 1/0 to raise/lower the #RST
- *
- * Clear the EEH-frozen condition on a slot.  This routine
- * asserts the PCI #RST line if the 'state' argument is '1',
- * and drops the #RST line if 'state is '0'.  This routine is
- * safe to call in an interrupt context.
- *
- */
-
-static void
-rtas_pci_slot_reset(struct pci_dn *pdn, int state)
-{
-        int config_addr;
-        int rc;
-
-        BUG_ON (pdn==NULL); 
-
-        if (!pdn->phb) {
-                printk (KERN_WARNING "EEH: in slot reset, device node %s has no phb\n",
-                        pdn->node->full_name);
-                return;
-        }
-
-        /* Use PE configuration address, if present */
-        config_addr = pdn->eeh_config_addr;
-        if (pdn->eeh_pe_config_addr)
-                config_addr = pdn->eeh_pe_config_addr;
-
-        rc = rtas_call(ibm_set_slot_reset, 4, 1, NULL,
-                       config_addr,
-                       BUID_HI(pdn->phb->buid),
-                       BUID_LO(pdn->phb->buid),
-                       state);
-
-        /* Fundamental-reset not supported on this PE, try hot-reset */
-        if (rc == -8 && state == 3) {
-                rc = rtas_call(ibm_set_slot_reset, 4, 1, NULL,
-                               config_addr,
-                               BUID_HI(pdn->phb->buid),
-                               BUID_LO(pdn->phb->buid), 1);
-                if (rc)
-                        printk(KERN_WARNING
-                                "EEH: Unable to reset the failed slot,"
-                                " #RST=%d dn=%s\n",
-                                rc, pdn->node->full_name);
-        }
-}
-
-/**
  * pcibios_set_pcie_slot_reset - Set PCI-E reset state
- * @dev:        pci device struct
- * @state:      reset state to enter
+ * @dev: pci device struct
+ * @state: reset state to enter
  *
  * Return value:
  *      0 if success
- **/
+ */
 int pcibios_set_pcie_reset_state(struct pci_dev *dev, enum pcie_reset_state state)
 {
         struct device_node *dn = pci_device_to_OF_node(dev);
-        struct pci_dn *pdn = PCI_DN(dn);
 
         switch (state) {
         case pcie_deassert_reset:
-                rtas_pci_slot_reset(pdn, 0);
+                eeh_ops->reset(dn, EEH_RESET_DEACTIVATE);
                 break;
         case pcie_hot_reset:
-                rtas_pci_slot_reset(pdn, 1);
+                eeh_ops->reset(dn, EEH_RESET_HOT);
                 break;
         case pcie_warm_reset:
-                rtas_pci_slot_reset(pdn, 3);
+                eeh_ops->reset(dn, EEH_RESET_FUNDAMENTAL);
                 break;
         default:
                 return -EINVAL;
@@ -781,13 +591,66 @@ int pcibios_set_pcie_reset_state(struct pci_dev *dev, enum pcie_reset_state stat
 }
 
 /**
- * rtas_set_slot_reset -- assert the pci #RST line for 1/4 second
- * @pdn: pci device node to be reset.
+ * __eeh_set_pe_freset - Check the required reset for child devices
+ * @parent: parent device
+ * @freset: return value
+ *
+ * Each device might have its preferred reset type: fundamental or
+ * hot reset. The routine is used to collect the information from
+ * the child devices so that they could be reset accordingly.
+ */
+void __eeh_set_pe_freset(struct device_node *parent, unsigned int *freset)
+{
+        struct device_node *dn;
+
+        for_each_child_of_node(parent, dn) {
+                if (of_node_to_eeh_dev(dn)) {
+                        struct pci_dev *dev = of_node_to_eeh_dev(dn)->pdev;
+
+                        if (dev && dev->driver)
+                                *freset |= dev->needs_freset;
+
+                        __eeh_set_pe_freset(dn, freset);
+                }
+        }
+}
+
+/**
+ * eeh_set_pe_freset - Check the required reset for the indicated device and its children
+ * @dn: parent device
+ * @freset: return value
+ *
+ * Each device might have its preferred reset type: fundamental or
+ * hot reset. The routine is used to collected the information for
+ * the indicated device and its children so that the bunch of the
+ * devices could be reset properly.
  */
+void eeh_set_pe_freset(struct device_node *dn, unsigned int *freset)
+{
+        struct pci_dev *dev;
+        dn = eeh_find_device_pe(dn);
 
-static void __rtas_set_slot_reset(struct pci_dn *pdn)
+        /* Back up one, since config addrs might be shared */
+        if (!pcibios_find_pci_bus(dn) && of_node_to_eeh_dev(dn->parent))
+                dn = dn->parent;
+
+        dev = of_node_to_eeh_dev(dn)->pdev;
+        if (dev)
+                *freset |= dev->needs_freset;
+
+        __eeh_set_pe_freset(dn, freset);
+}
+
+/**
+ * eeh_reset_pe_once - Assert the pci #RST line for 1/4 second
+ * @edev: pci device node to be reset.
+ *
+ * Assert the PCI #RST line for 1/4 second.
+ */
+static void eeh_reset_pe_once(struct eeh_dev *edev)
 {
         unsigned int freset = 0;
+        struct device_node *dn = eeh_dev_to_of_node(edev);
 
         /* Determine type of EEH reset required for
          * Partitionable Endpoint, a hot-reset (1)
@@ -795,58 +658,68 @@ static void __rtas_set_slot_reset(struct pci_dn *pdn)
          * A fundamental reset required by any device under
          * Partitionable Endpoint trumps hot-reset.
          */
-        eeh_set_pe_freset(pdn->node, &freset);
+        eeh_set_pe_freset(dn, &freset);
 
         if (freset)
-                rtas_pci_slot_reset(pdn, 3);
+                eeh_ops->reset(dn, EEH_RESET_FUNDAMENTAL);
         else
-                rtas_pci_slot_reset(pdn, 1);
+                eeh_ops->reset(dn, EEH_RESET_HOT);
 
         /* The PCI bus requires that the reset be held high for at least
-         * a 100 milliseconds. We wait a bit longer 'just in case'.  */
-
+         * a 100 milliseconds. We wait a bit longer 'just in case'.
+         */
 #define PCI_BUS_RST_HOLD_TIME_MSEC 250
-        msleep (PCI_BUS_RST_HOLD_TIME_MSEC);
+        msleep(PCI_BUS_RST_HOLD_TIME_MSEC);
         
         /* We might get hit with another EEH freeze as soon as the 
          * pci slot reset line is dropped. Make sure we don't miss
-         * these, and clear the flag now. */
-        eeh_clear_slot (pdn->node, EEH_MODE_ISOLATED);
+         * these, and clear the flag now.
+         */
+        eeh_clear_slot(dn, EEH_MODE_ISOLATED);
 
-        rtas_pci_slot_reset (pdn, 0);
+        eeh_ops->reset(dn, EEH_RESET_DEACTIVATE);
 
         /* After a PCI slot has been reset, the PCI Express spec requires
          * a 1.5 second idle time for the bus to stabilize, before starting
-         * up traffic. */
+         * up traffic.
+         */
 #define PCI_BUS_SETTLE_TIME_MSEC 1800
-        msleep (PCI_BUS_SETTLE_TIME_MSEC);
+        msleep(PCI_BUS_SETTLE_TIME_MSEC);
 }
 
-int rtas_set_slot_reset(struct pci_dn *pdn)
+/**
+ * eeh_reset_pe - Reset the indicated PE
+ * @edev: PCI device associated EEH device
+ *
+ * This routine should be called to reset indicated device, including
+ * PE. A PE might include multiple PCI devices and sometimes PCI bridges
+ * might be involved as well.
+ */
+int eeh_reset_pe(struct eeh_dev *edev)
 {
         int i, rc;
+        struct device_node *dn = eeh_dev_to_of_node(edev);
 
         /* Take three shots at resetting the bus */
         for (i=0; i<3; i++) {
-                __rtas_set_slot_reset(pdn);
+                eeh_reset_pe_once(edev);
 
-                rc = eeh_wait_for_slot_status(pdn, PCI_BUS_RESET_WAIT_MSEC);
-                if (rc == 0)
+                rc = eeh_ops->wait_state(dn, PCI_BUS_RESET_WAIT_MSEC);
+                if (rc == (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE))
                         return 0;
 
                 if (rc < 0) {
                         printk(KERN_ERR "EEH: unrecoverable slot failure %s\n",
-                               pdn->node->full_name);
+                               dn->full_name);
                         return -1;
                 }
                 printk(KERN_ERR "EEH: bus reset %d failed on slot %s, rc=%d\n",
-                       i+1, pdn->node->full_name, rc);
+                       i+1, dn->full_name, rc);
         }
 
         return -1;
 }
 
-/* ------------------------------------------------------- */
 /** Save and restore of PCI BARs
  *
  * Although firmware will set up BARs during boot, it doesn't
@@ -856,181 +729,122 @@ int rtas_set_slot_reset(struct pci_dn *pdn)
  */
 
 /**
- * __restore_bars - Restore the Base Address Registers
- * @pdn: pci device node
+ * eeh_restore_one_device_bars - Restore the Base Address Registers for one device
+ * @edev: PCI device associated EEH device
  *
  * Loads the PCI configuration space base address registers,
  * the expansion ROM base address, the latency timer, and etc.
  * from the saved values in the device node.
  */
-static inline void __restore_bars (struct pci_dn *pdn)
+static inline void eeh_restore_one_device_bars(struct eeh_dev *edev)
 {
         int i;
         u32 cmd;
+        struct device_node *dn = eeh_dev_to_of_node(edev);
+
+        if (!edev->phb)
+                return;
 
-        if (NULL==pdn->phb) return;
         for (i=4; i<10; i++) {
-                rtas_write_config(pdn, i*4, 4, pdn->config_space[i]);
+                eeh_ops->write_config(dn, i*4, 4, edev->config_space[i]);
         }
 
         /* 12 == Expansion ROM Address */
-        rtas_write_config(pdn, 12*4, 4, pdn->config_space[12]);
+        eeh_ops->write_config(dn, 12*4, 4, edev->config_space[12]);
 
 #define BYTE_SWAP(OFF) (8*((OFF)/4)+3-(OFF))
-#define SAVED_BYTE(OFF) (((u8 *)(pdn->config_space))[BYTE_SWAP(OFF)])
+#define SAVED_BYTE(OFF) (((u8 *)(edev->config_space))[BYTE_SWAP(OFF)])
 
-        rtas_write_config (pdn, PCI_CACHE_LINE_SIZE, 1,
+        eeh_ops->write_config(dn, PCI_CACHE_LINE_SIZE, 1,
                     SAVED_BYTE(PCI_CACHE_LINE_SIZE));
 
-        rtas_write_config (pdn, PCI_LATENCY_TIMER, 1,
+        eeh_ops->write_config(dn, PCI_LATENCY_TIMER, 1,
                     SAVED_BYTE(PCI_LATENCY_TIMER));
 
         /* max latency, min grant, interrupt pin and line */
-        rtas_write_config(pdn, 15*4, 4, pdn->config_space[15]);
+        eeh_ops->write_config(dn, 15*4, 4, edev->config_space[15]);
 
         /* Restore PERR & SERR bits, some devices require it,
-           don't touch the other command bits */
-        rtas_read_config(pdn, PCI_COMMAND, 4, &cmd);
-        if (pdn->config_space[1] & PCI_COMMAND_PARITY)
+         * don't touch the other command bits
+         */
+        eeh_ops->read_config(dn, PCI_COMMAND, 4, &cmd);
+        if (edev->config_space[1] & PCI_COMMAND_PARITY)
                 cmd |= PCI_COMMAND_PARITY;
         else
                 cmd &= ~PCI_COMMAND_PARITY;
-        if (pdn->config_space[1] & PCI_COMMAND_SERR)
+        if (edev->config_space[1] & PCI_COMMAND_SERR)
                 cmd |= PCI_COMMAND_SERR;
         else
                 cmd &= ~PCI_COMMAND_SERR;
-        rtas_write_config(pdn, PCI_COMMAND, 4, cmd);
+        eeh_ops->write_config(dn, PCI_COMMAND, 4, cmd);
 }
 
 /**
- * eeh_restore_bars - restore the PCI config space info
+ * eeh_restore_bars - Restore the PCI config space info
+ * @edev: EEH device
  *
  * This routine performs a recursive walk to the children
  * of this device as well.
  */
-void eeh_restore_bars(struct pci_dn *pdn)
+void eeh_restore_bars(struct eeh_dev *edev)
 {
         struct device_node *dn;
-        if (!pdn) 
+        if (!edev)
                 return;
         
-        if ((pdn->eeh_mode & EEH_MODE_SUPPORTED) && !IS_BRIDGE(pdn->class_code))
-                __restore_bars (pdn);
+        if ((edev->mode & EEH_MODE_SUPPORTED) && !IS_BRIDGE(edev->class_code))
+                eeh_restore_one_device_bars(edev);
 
-        for_each_child_of_node(pdn->node, dn)
-                eeh_restore_bars (PCI_DN(dn));
+        for_each_child_of_node(eeh_dev_to_of_node(edev), dn)
+                eeh_restore_bars(of_node_to_eeh_dev(dn));
 }
 
 /**
- * eeh_save_bars - save device bars
+ * eeh_save_bars - Save device bars
+ * @edev: PCI device associated EEH device
  *
  * Save the values of the device bars. Unlike the restore
  * routine, this routine is *not* recursive. This is because
  * PCI devices are added individually; but, for the restore,
  * an entire slot is reset at a time.
  */
-static void eeh_save_bars(struct pci_dn *pdn)
+static void eeh_save_bars(struct eeh_dev *edev)
 {
         int i;
+        struct device_node *dn;
 
-        if (!pdn )
+        if (!edev)
                 return;
+        dn = eeh_dev_to_of_node(edev);
         
         for (i = 0; i < 16; i++)
-                rtas_read_config(pdn, i * 4, 4, &pdn->config_space[i]);
-}
-
-void
-rtas_configure_bridge(struct pci_dn *pdn)
-{
-        int config_addr;
-        int rc;
-        int token;
-
-        /* Use PE configuration address, if present */
-        config_addr = pdn->eeh_config_addr;
-        if (pdn->eeh_pe_config_addr)
-                config_addr = pdn->eeh_pe_config_addr;
-
-        /* Use new configure-pe function, if supported */
-        if (ibm_configure_pe != RTAS_UNKNOWN_SERVICE)
-                token = ibm_configure_pe;
-        else
-                token = ibm_configure_bridge;
-
-        rc = rtas_call(token, 3, 1, NULL,
-                       config_addr,
-                       BUID_HI(pdn->phb->buid),
-                       BUID_LO(pdn->phb->buid));
-        if (rc) {
-                printk (KERN_WARNING "EEH: Unable to configure device bridge (%d) for %s\n",
-                        rc, pdn->node->full_name);
-        }
+                eeh_ops->read_config(dn, i * 4, 4, &edev->config_space[i]);
 }
 
-/* ------------------------------------------------------------- */
-/* The code below deals with enabling EEH for devices during  the
- * early boot sequence.  EEH must be enabled before any PCI probing
- * can be done.
+/**
+ * eeh_early_enable - Early enable EEH on the indicated device
+ * @dn: device node
+ * @data: BUID
+ *
+ * Enable EEH functionality on the specified PCI device. The function
+ * is expected to be called before real PCI probing is done. However,
+ * the PHBs have been initialized at this point.
  */
-
-#define EEH_ENABLE 1
-
-struct eeh_early_enable_info {
-        unsigned int buid_hi;
-        unsigned int buid_lo;
-};
-
-static int get_pe_addr (int config_addr,
-                        struct eeh_early_enable_info *info)
-{
-        unsigned int rets[3];
-        int ret;
-
-        /* Use latest config-addr token on power6 */
-        if (ibm_get_config_addr_info2 != RTAS_UNKNOWN_SERVICE) {
-                /* Make sure we have a PE in hand */
-                ret = rtas_call (ibm_get_config_addr_info2, 4, 2, rets,
-                        config_addr, info->buid_hi, info->buid_lo, 1);
-                if (ret || (rets[0]==0))
-                        return 0;
-
-                ret = rtas_call (ibm_get_config_addr_info2, 4, 2, rets,
-                        config_addr, info->buid_hi, info->buid_lo, 0);
-                if (ret)
-                        return 0;
-                return rets[0];
-        }
-
-        /* Use older config-addr token on power5 */
-        if (ibm_get_config_addr_info != RTAS_UNKNOWN_SERVICE) {
-                ret = rtas_call (ibm_get_config_addr_info, 4, 2, rets,
-                        config_addr, info->buid_hi, info->buid_lo, 0);
-                if (ret)
-                        return 0;
-                return rets[0];
-        }
-        return 0;
-}
-
-/* Enable eeh for the given device node. */
-static void *early_enable_eeh(struct device_node *dn, void *data)
+static void *eeh_early_enable(struct device_node *dn, void *data)
 {
-        unsigned int rets[3];
-        struct eeh_early_enable_info *info = data;
         int ret;
         const u32 *class_code = of_get_property(dn, "class-code", NULL);
         const u32 *vendor_id = of_get_property(dn, "vendor-id", NULL);
         const u32 *device_id = of_get_property(dn, "device-id", NULL);
         const u32 *regs;
         int enable;
-        struct pci_dn *pdn = PCI_DN(dn);
+        struct eeh_dev *edev = of_node_to_eeh_dev(dn);
 
-        pdn->class_code = 0;
-        pdn->eeh_mode = 0;
-        pdn->eeh_check_count = 0;
-        pdn->eeh_freeze_count = 0;
-        pdn->eeh_false_positives = 0;
+        edev->class_code = 0;
+        edev->mode = 0;
+        edev->check_count = 0;
+        edev->freeze_count = 0;
+        edev->false_positives = 0;
 
         if (!of_device_is_available(dn))
                 return NULL;
@@ -1041,54 +855,56 @@ static void *early_enable_eeh(struct device_node *dn, void *data)
 
         /* There is nothing to check on PCI to ISA bridges */
         if (dn->type && !strcmp(dn->type, "isa")) {
-                pdn->eeh_mode |= EEH_MODE_NOCHECK;
+                edev->mode |= EEH_MODE_NOCHECK;
                 return NULL;
         }
-        pdn->class_code = *class_code;
+        edev->class_code = *class_code;
 
         /* Ok... see if this device supports EEH.  Some do, some don't,
-         * and the only way to find out is to check each and every one. */
+         * and the only way to find out is to check each and every one.
+         */
         regs = of_get_property(dn, "reg", NULL);
         if (regs) {
                 /* First register entry is addr (00BBSS00)  */
                 /* Try to enable eeh */
-                ret = rtas_call(ibm_set_eeh_option, 4, 1, NULL,
-                                regs[0], info->buid_hi, info->buid_lo,
-                                EEH_ENABLE);
+                ret = eeh_ops->set_option(dn, EEH_OPT_ENABLE);
 
                 enable = 0;
                 if (ret == 0) {
-                        pdn->eeh_config_addr = regs[0];
+                        edev->config_addr = regs[0];
 
                         /* If the newer, better, ibm,get-config-addr-info is supported, 
-                         * then use that instead. */
-                        pdn->eeh_pe_config_addr = get_pe_addr(pdn->eeh_config_addr, info);
+                         * then use that instead.
+                         */
+                        edev->pe_config_addr = eeh_ops->get_pe_addr(dn);
 
                         /* Some older systems (Power4) allow the
                          * ibm,set-eeh-option call to succeed even on nodes
                          * where EEH is not supported. Verify support
-                         * explicitly. */
-                        ret = read_slot_reset_state(pdn, rets);
-                        if ((ret == 0) && (rets[1] == 1))
+                         * explicitly.
+                         */
+                        ret = eeh_ops->get_state(dn, NULL);
+                        if (ret > 0 && ret != EEH_STATE_NOT_SUPPORT)
                                 enable = 1;
                 }
 
                 if (enable) {
                         eeh_subsystem_enabled = 1;
-                        pdn->eeh_mode |= EEH_MODE_SUPPORTED;
+                        edev->mode |= EEH_MODE_SUPPORTED;
 
                         pr_debug("EEH: %s: eeh enabled, config=%x pe_config=%x\n",
-                                 dn->full_name, pdn->eeh_config_addr,
-                                 pdn->eeh_pe_config_addr);
+                                 dn->full_name, edev->config_addr,
+                                 edev->pe_config_addr);
                 } else {
 
                         /* This device doesn't support EEH, but it may have an
-                         * EEH parent, in which case we mark it as supported. */
-                        if (dn->parent && PCI_DN(dn->parent)
-                            && (PCI_DN(dn->parent)->eeh_mode & EEH_MODE_SUPPORTED)) {
+                         * EEH parent, in which case we mark it as supported.
+                         */
+                        if (dn->parent && of_node_to_eeh_dev(dn->parent) &&
+                            (of_node_to_eeh_dev(dn->parent)->mode & EEH_MODE_SUPPORTED)) {
                                 /* Parent supports EEH. */
-                                pdn->eeh_mode |= EEH_MODE_SUPPORTED;
-                                pdn->eeh_config_addr = PCI_DN(dn->parent)->eeh_config_addr;
+                                edev->mode |= EEH_MODE_SUPPORTED;
+                                edev->config_addr = of_node_to_eeh_dev(dn->parent)->config_addr;
                                 return NULL;
                         }
                 }
@@ -1097,11 +913,63 @@ static void *early_enable_eeh(struct device_node *dn, void *data)
                        dn->full_name);
         }
 
-        eeh_save_bars(pdn);
+        eeh_save_bars(edev);
         return NULL;
 }
 
-/*
+/**
+ * eeh_ops_register - Register platform dependent EEH operations
+ * @ops: platform dependent EEH operations
+ *
+ * Register the platform dependent EEH operation callback
+ * functions. The platform should call this function before
+ * any other EEH operations.
+ */
+int __init eeh_ops_register(struct eeh_ops *ops)
+{
+        if (!ops->name) {
+                pr_warning("%s: Invalid EEH ops name for %p\n",
+                        __func__, ops);
+                return -EINVAL;
+        }
+
+        if (eeh_ops && eeh_ops != ops) {
+                pr_warning("%s: EEH ops of platform %s already existing (%s)\n",
+                        __func__, eeh_ops->name, ops->name);
+                return -EEXIST;
+        }
+
+        eeh_ops = ops;
+
+        return 0;
+}
+
+/**
+ * eeh_ops_unregister - Unreigster platform dependent EEH operations
+ * @name: name of EEH platform operations
+ *
+ * Unregister the platform dependent EEH operation callback
+ * functions.
+ */
+int __exit eeh_ops_unregister(const char *name)
+{
+        if (!name || !strlen(name)) {
+                pr_warning("%s: Invalid EEH ops name\n",
+                        __func__);
+                return -EINVAL;
+        }
+
+        if (eeh_ops && !strcmp(eeh_ops->name, name)) {
+                eeh_ops = NULL;
+                return 0;
+        }
+
+        return -EEXIST;
+}
+
+/**
+ * eeh_init - EEH initialization
+ *
  * Initialize EEH by trying to enable it for all of the adapters in the system.
  * As a side effect we can determine here if eeh is supported at all.
  * Note that we leave EEH on so failed config cycles won't cause a machine
@@ -1116,51 +984,27 @@ static void *early_enable_eeh(struct device_node *dn, void *data)
  */
 void __init eeh_init(void)
 {
-        struct device_node *phb, *np;
-        struct eeh_early_enable_info info;
-
-        raw_spin_lock_init(&confirm_error_lock);
-        spin_lock_init(&slot_errbuf_lock);
+        struct pci_controller *hose, *tmp;
+        struct device_node *phb;
+        int ret;
 
-        np = of_find_node_by_path("/rtas");
-        if (np == NULL)
+        /* call platform initialization function */
+        if (!eeh_ops) {
+                pr_warning("%s: Platform EEH operation not found\n",
+                        __func__);
                 return;
-
-        ibm_set_eeh_option = rtas_token("ibm,set-eeh-option");
-        ibm_set_slot_reset = rtas_token("ibm,set-slot-reset");
-        ibm_read_slot_reset_state2 = rtas_token("ibm,read-slot-reset-state2");
-        ibm_read_slot_reset_state = rtas_token("ibm,read-slot-reset-state");
-        ibm_slot_error_detail = rtas_token("ibm,slot-error-detail");
-        ibm_get_config_addr_info = rtas_token("ibm,get-config-addr-info");
-        ibm_get_config_addr_info2 = rtas_token("ibm,get-config-addr-info2");
-        ibm_configure_bridge = rtas_token ("ibm,configure-bridge");
-        ibm_configure_pe = rtas_token("ibm,configure-pe");
-
-        if (ibm_set_eeh_option == RTAS_UNKNOWN_SERVICE)
+        } else if ((ret = eeh_ops->init())) {
+                pr_warning("%s: Failed to call platform init function (%d)\n",
+                        __func__, ret);
                 return;
-
-        eeh_error_buf_size = rtas_token("rtas-error-log-max");
-        if (eeh_error_buf_size == RTAS_UNKNOWN_SERVICE) {
-                eeh_error_buf_size = 1024;
-        }
-        if (eeh_error_buf_size > RTAS_ERROR_LOG_MAX) {
-                printk(KERN_WARNING "EEH: rtas-error-log-max is bigger than allocated "
-                      "buffer ! (%d vs %d)", eeh_error_buf_size, RTAS_ERROR_LOG_MAX);
-                eeh_error_buf_size = RTAS_ERROR_LOG_MAX;
         }
 
-        /* Enable EEH for all adapters.  Note that eeh requires buid's */
-        for (phb = of_find_node_by_name(NULL, "pci"); phb;
-             phb = of_find_node_by_name(phb, "pci")) {
-                unsigned long buid;
-
-                buid = get_phb_buid(phb);
-                if (buid == 0 || PCI_DN(phb) == NULL)
-                        continue;
+        raw_spin_lock_init(&confirm_error_lock);
 
-                info.buid_lo = BUID_LO(buid);
-                info.buid_hi = BUID_HI(buid);
-                traverse_pci_devices(phb, early_enable_eeh, &info);
+        /* Enable EEH for all adapters */
+        list_for_each_entry_safe(hose, tmp, &hose_list, list_node) {
+                phb = hose->dn;
+                traverse_pci_devices(phb, eeh_early_enable, NULL);
         }
 
         if (eeh_subsystem_enabled)
@@ -1170,7 +1014,7 @@ void __init eeh_init(void)
 }
 
 /**
- * eeh_add_device_early - enable EEH for the indicated device_node
+ * eeh_add_device_early - Enable EEH for the indicated device_node
  * @dn: device node for which to set up EEH
  *
  * This routine must be used to perform EEH initialization for PCI
@@ -1184,21 +1028,26 @@ void __init eeh_init(void)
 static void eeh_add_device_early(struct device_node *dn)
 {
         struct pci_controller *phb;
-        struct eeh_early_enable_info info;
 
-        if (!dn || !PCI_DN(dn))
+        if (!dn || !of_node_to_eeh_dev(dn))
                 return;
-        phb = PCI_DN(dn)->phb;
+        phb = of_node_to_eeh_dev(dn)->phb;
 
         /* USB Bus children of PCI devices will not have BUID's */
         if (NULL == phb || 0 == phb->buid)
                 return;
 
-        info.buid_hi = BUID_HI(phb->buid);
-        info.buid_lo = BUID_LO(phb->buid);
-        early_enable_eeh(dn, &info);
+        eeh_early_enable(dn, NULL);
 }
 
+/**
+ * eeh_add_device_tree_early - Enable EEH for the indicated device
+ * @dn: device node
+ *
+ * This routine must be used to perform EEH initialization for the
+ * indicated PCI device that was added after system boot (e.g.
+ * hotplug, dlpar).
+ */
 void eeh_add_device_tree_early(struct device_node *dn)
 {
         struct device_node *sib;
@@ -1210,7 +1059,7 @@ void eeh_add_device_tree_early(struct device_node *dn)
 EXPORT_SYMBOL_GPL(eeh_add_device_tree_early);
 
 /**
- * eeh_add_device_late - perform EEH initialization for the indicated pci device
+ * eeh_add_device_late - Perform EEH initialization for the indicated pci device
  * @dev: pci device for which to set up EEH
  *
  * This routine must be used to complete EEH initialization for PCI
@@ -1219,7 +1068,7 @@ EXPORT_SYMBOL_GPL(eeh_add_device_tree_early);
 static void eeh_add_device_late(struct pci_dev *dev)
 {
         struct device_node *dn;
-        struct pci_dn *pdn;
+        struct eeh_dev *edev;
 
         if (!dev || !eeh_subsystem_enabled)
                 return;
@@ -1227,20 +1076,29 @@ static void eeh_add_device_late(struct pci_dev *dev)
         pr_debug("EEH: Adding device %s\n", pci_name(dev));
 
         dn = pci_device_to_OF_node(dev);
-        pdn = PCI_DN(dn);
-        if (pdn->pcidev == dev) {
+        edev = pci_dev_to_eeh_dev(dev);
+        if (edev->pdev == dev) {
                 pr_debug("EEH: Already referenced !\n");
                 return;
         }
-        WARN_ON(pdn->pcidev);
+        WARN_ON(edev->pdev);
 
-        pci_dev_get (dev);
-        pdn->pcidev = dev;
+        pci_dev_get(dev);
+        edev->pdev = dev;
+        dev->dev.archdata.edev = edev;
 
         pci_addr_cache_insert_device(dev);
         eeh_sysfs_add_device(dev);
 }
 
+/**
+ * eeh_add_device_tree_late - Perform EEH initialization for the indicated PCI bus
+ * @bus: PCI bus
+ *
+ * This routine must be used to perform EEH initialization for PCI
+ * devices which are attached to the indicated PCI bus. The PCI bus
+ * is added after system boot through hotplug or dlpar.
+ */
 void eeh_add_device_tree_late(struct pci_bus *bus)
 {
         struct pci_dev *dev;
@@ -1257,7 +1115,7 @@ void eeh_add_device_tree_late(struct pci_bus *bus)
 EXPORT_SYMBOL_GPL(eeh_add_device_tree_late);
 
 /**
- * eeh_remove_device - undo EEH setup for the indicated pci device
+ * eeh_remove_device - Undo EEH setup for the indicated pci device
  * @dev: pci device to be removed
  *
  * This routine should be called when a device is removed from
@@ -1268,25 +1126,35 @@ EXPORT_SYMBOL_GPL(eeh_add_device_tree_late);
  */
 static void eeh_remove_device(struct pci_dev *dev)
 {
-        struct device_node *dn;
+        struct eeh_dev *edev;
+
         if (!dev || !eeh_subsystem_enabled)
                 return;
+        edev = pci_dev_to_eeh_dev(dev);
 
         /* Unregister the device with the EEH/PCI address search system */
         pr_debug("EEH: Removing device %s\n", pci_name(dev));
 
-        dn = pci_device_to_OF_node(dev);
-        if (PCI_DN(dn)->pcidev == NULL) {
+        if (!edev || !edev->pdev) {
                 pr_debug("EEH: Not referenced !\n");
                 return;
         }
-        PCI_DN(dn)->pcidev = NULL;
-        pci_dev_put (dev);
+        edev->pdev = NULL;
+        dev->dev.archdata.edev = NULL;
+        pci_dev_put(dev);
 
         pci_addr_cache_remove_device(dev);
         eeh_sysfs_remove_device(dev);
 }
 
+/**
+ * eeh_remove_bus_device - Undo EEH setup for the indicated PCI device
+ * @dev: PCI device
+ *
+ * This routine must be called when a device is removed from the
+ * running system through hotplug or dlpar. The corresponding
+ * PCI address cache will be removed.
+ */
 void eeh_remove_bus_device(struct pci_dev *dev)
 {
         struct pci_bus *bus = dev->subordinate;
@@ -1305,21 +1173,24 @@ static int proc_eeh_show(struct seq_file *m, void *v)
 {
         if (0 == eeh_subsystem_enabled) {
                 seq_printf(m, "EEH Subsystem is globally disabled\n");
-                seq_printf(m, "eeh_total_mmio_ffs=%ld\n", total_mmio_ffs);
+                seq_printf(m, "eeh_total_mmio_ffs=%llu\n", eeh_stats.total_mmio_ffs);
         } else {
                 seq_printf(m, "EEH Subsystem is enabled\n");
                 seq_printf(m,
-                                "no device=%ld\n"
-                                "no device node=%ld\n"
-                                "no config address=%ld\n"
-                                "check not wanted=%ld\n"
-                                "eeh_total_mmio_ffs=%ld\n"
-                                "eeh_false_positives=%ld\n"
-                                "eeh_slot_resets=%ld\n",
-                                no_device, no_dn, no_cfg_addr, 
-                                ignored_check, total_mmio_ffs, 
-                                false_positives,
-                                slot_resets);
+                                "no device=%llu\n"
+                                "no device node=%llu\n"
+                                "no config address=%llu\n"
+                                "check not wanted=%llu\n"
+                                "eeh_total_mmio_ffs=%llu\n"
+                                "eeh_false_positives=%llu\n"
+                                "eeh_slot_resets=%llu\n",
+                                eeh_stats.no_device,
+                                eeh_stats.no_dn,
+                                eeh_stats.no_cfg_addr,
+                                eeh_stats.ignored_check,
+                                eeh_stats.total_mmio_ffs,
+                                eeh_stats.false_positives,
+                                eeh_stats.slot_resets);
         }
 
         return 0;
diff --git a/arch/powerpc/platforms/pseries/eeh_cache.c b/arch/powerpc/platforms/pseries/eeh_cache.c
index fc5ae767989e..e5ae1c687c66 100644
--- a/arch/powerpc/platforms/pseries/eeh_cache.c
+++ b/arch/powerpc/platforms/pseries/eeh_cache.c
@@ -1,5 +1,4 @@
 /*
- * eeh_cache.c
  * PCI address cache; allows the lookup of PCI devices based on I/O address
  *
  * Copyright IBM Corporation 2004
@@ -47,8 +46,7 @@
  * than any hash algo I could think of for this problem, even
  * with the penalty of slow pointer chases for d-cache misses).
  */
-struct pci_io_addr_range
-{
+struct pci_io_addr_range {
         struct rb_node rb_node;
         unsigned long addr_lo;
         unsigned long addr_hi;
@@ -56,13 +54,12 @@ struct pci_io_addr_range
         unsigned int flags;
 };
 
-static struct pci_io_addr_cache
-{
+static struct pci_io_addr_cache {
         struct rb_root rb_root;
         spinlock_t piar_lock;
 } pci_io_addr_cache_root;
 
-static inline struct pci_dev *__pci_get_device_by_addr(unsigned long addr)
+static inline struct pci_dev *__pci_addr_cache_get_device(unsigned long addr)
 {
         struct rb_node *n = pci_io_addr_cache_root.rb_root.rb_node;
 
@@ -86,7 +83,7 @@ static inline struct pci_dev *__pci_get_device_by_addr(unsigned long addr)
 }
 
 /**
- * pci_get_device_by_addr - Get device, given only address
+ * pci_addr_cache_get_device - Get device, given only address
  * @addr: mmio (PIO) phys address or i/o port number
  *
  * Given an mmio phys address, or a port number, find a pci device
@@ -95,13 +92,13 @@ static inline struct pci_dev *__pci_get_device_by_addr(unsigned long addr)
  * from zero (that is, they do *not* have pci_io_addr added in).
  * It is safe to call this function within an interrupt.
  */
-struct pci_dev *pci_get_device_by_addr(unsigned long addr)
+struct pci_dev *pci_addr_cache_get_device(unsigned long addr)
 {
         struct pci_dev *dev;
         unsigned long flags;
 
         spin_lock_irqsave(&pci_io_addr_cache_root.piar_lock, flags);
-        dev = __pci_get_device_by_addr(addr);
+        dev = __pci_addr_cache_get_device(addr);
         spin_unlock_irqrestore(&pci_io_addr_cache_root.piar_lock, flags);
         return dev;
 }
@@ -166,7 +163,7 @@ pci_addr_cache_insert(struct pci_dev *dev, unsigned long alo,
 
 #ifdef DEBUG
         printk(KERN_DEBUG "PIAR: insert range=[%lx:%lx] dev=%s\n",
-                          alo, ahi, pci_name (dev));
+                          alo, ahi, pci_name(dev));
 #endif
 
         rb_link_node(&piar->rb_node, parent, p);
@@ -178,7 +175,7 @@ pci_addr_cache_insert(struct pci_dev *dev, unsigned long alo,
 static void __pci_addr_cache_insert_device(struct pci_dev *dev)
 {
         struct device_node *dn;
-        struct pci_dn *pdn;
+        struct eeh_dev *edev;
         int i;
 
         dn = pci_device_to_OF_node(dev);
@@ -187,13 +184,19 @@ static void __pci_addr_cache_insert_device(struct pci_dev *dev)
                 return;
         }
 
+        edev = of_node_to_eeh_dev(dn);
+        if (!edev) {
+                pr_warning("PCI: no EEH dev found for dn=%s\n",
+                        dn->full_name);
+                return;
+        }
+
         /* Skip any devices for which EEH is not enabled. */
-        pdn = PCI_DN(dn);
-        if (!(pdn->eeh_mode & EEH_MODE_SUPPORTED) ||
-            pdn->eeh_mode & EEH_MODE_NOCHECK) {
+        if (!(edev->mode & EEH_MODE_SUPPORTED) ||
+            edev->mode & EEH_MODE_NOCHECK) {
 #ifdef DEBUG
-                printk(KERN_INFO "PCI: skip building address cache for=%s - %s\n",
-                       pci_name(dev), pdn->node->full_name);
+                pr_info("PCI: skip building address cache for=%s - %s\n",
+                        pci_name(dev), dn->full_name);
 #endif
                 return;
         }
@@ -284,6 +287,7 @@ void pci_addr_cache_remove_device(struct pci_dev *dev)
 void __init pci_addr_cache_build(void)
 {
         struct device_node *dn;
+        struct eeh_dev *edev;
         struct pci_dev *dev = NULL;
 
         spin_lock_init(&pci_io_addr_cache_root.piar_lock);
@@ -294,8 +298,14 @@ void __init pci_addr_cache_build(void)
                 dn = pci_device_to_OF_node(dev);
                 if (!dn)
                         continue;
+
+                edev = of_node_to_eeh_dev(dn);
+                if (!edev)
+                        continue;
+
                 pci_dev_get(dev);  /* matching put is in eeh_remove_device() */
-                PCI_DN(dn)->pcidev = dev;
+                dev->dev.archdata.edev = edev;
+                edev->pdev = dev;
 
                 eeh_sysfs_add_device(dev);
         }
diff --git a/arch/powerpc/platforms/pseries/eeh_dev.c b/arch/powerpc/platforms/pseries/eeh_dev.c
new file mode 100644
index 000000000000..c4507d095900
--- /dev/null
+++ b/arch/powerpc/platforms/pseries/eeh_dev.c
@@ -0,0 +1,102 @@
+/*
+ * The file intends to implement dynamic creation of EEH device, which will
+ * be bound with OF node and PCI device simutaneously. The EEH devices would
+ * be foundamental information for EEH core components to work proerly. Besides,
+ * We have to support multiple situations where dynamic creation of EEH device
+ * is required:
+ *
+ * 1) Before PCI emunation starts, we need create EEH devices according to the
+ *    PCI sensitive OF nodes.
+ * 2) When PCI emunation is done, we need do the binding between PCI device and
+ *    the associated EEH device.
+ * 3) DR (Dynamic Reconfiguration) would create PCI sensitive OF node. EEH device
+ *    will be created while PCI sensitive OF node is detected from DR.
+ * 4) PCI hotplug needs redoing the binding between PCI device and EEH device. If
+ *    PHB is newly inserted, we also need create EEH devices accordingly.
+ *
+ * Copyright Benjamin Herrenschmidt & Gavin Shan, IBM Corporation 2012.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
+ */
+
+#include <linux/export.h>
+#include <linux/gfp.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/pci.h>
+#include <linux/string.h>
+
+#include <asm/pci-bridge.h>
+#include <asm/ppc-pci.h>
+
+/**
+ * eeh_dev_init - Create EEH device according to OF node
+ * @dn: device node
+ * @data: PHB
+ *
+ * It will create EEH device according to the given OF node. The function
+ * might be called by PCI emunation, DR, PHB hotplug.
+ */
+void * __devinit eeh_dev_init(struct device_node *dn, void *data)
+{
+        struct pci_controller *phb = data;
+        struct eeh_dev *edev;
+
+        /* Allocate EEH device */
+        edev = zalloc_maybe_bootmem(sizeof(*edev), GFP_KERNEL);
+        if (!edev) {
+                pr_warning("%s: out of memory\n", __func__);
+                return NULL;
+        }
+
+        /* Associate EEH device with OF node */
+        PCI_DN(dn)->edev = edev;
+        edev->dn  = dn;
+        edev->phb = phb;
+
+        return NULL;
+}
+
+/**
+ * eeh_dev_phb_init_dynamic - Create EEH devices for devices included in PHB
+ * @phb: PHB
+ *
+ * Scan the PHB OF node and its child association, then create the
+ * EEH devices accordingly
+ */
+void __devinit eeh_dev_phb_init_dynamic(struct pci_controller *phb)
+{
+        struct device_node *dn = phb->dn;
+
+        /* EEH device for PHB */
+        eeh_dev_init(dn, phb);
+
+        /* EEH devices for children OF nodes */
+        traverse_pci_devices(dn, eeh_dev_init, phb);
+}
+
+/**
+ * eeh_dev_phb_init - Create EEH devices for devices included in existing PHBs
+ *
+ * Scan all the existing PHBs and create EEH devices for their OF
+ * nodes and their children OF nodes
+ */
+void __init eeh_dev_phb_init(void)
+{
+        struct pci_controller *phb, *tmp;
+
+        list_for_each_entry_safe(phb, tmp, &hose_list, list_node)
+                eeh_dev_phb_init_dynamic(phb);
+}
diff --git a/arch/powerpc/platforms/pseries/eeh_driver.c b/arch/powerpc/platforms/pseries/eeh_driver.c
index 1b6cb10589e0..baf92cd9dfab 100644
--- a/arch/powerpc/platforms/pseries/eeh_driver.c
+++ b/arch/powerpc/platforms/pseries/eeh_driver.c
@@ -33,8 +33,14 @@
 #include <asm/prom.h>
 #include <asm/rtas.h>
 
-
-static inline const char * pcid_name (struct pci_dev *pdev)
+/**
+ * eeh_pcid_name - Retrieve name of PCI device driver
+ * @pdev: PCI device
+ *
+ * This routine is used to retrieve the name of PCI device driver
+ * if that's valid.
+ */
+static inline const char *eeh_pcid_name(struct pci_dev *pdev)
 {
         if (pdev && pdev->dev.driver)
                 return pdev->dev.driver->name;
@@ -64,48 +70,59 @@ static void print_device_node_tree(struct pci_dn *pdn, int dent)
 #endif
 
 /**
- * eeh_disable_irq - disable interrupt for the recovering device
+ * eeh_disable_irq - Disable interrupt for the recovering device
+ * @dev: PCI device
+ *
+ * This routine must be called when reporting temporary or permanent
+ * error to the particular PCI device to disable interrupt of that
+ * device. If the device has enabled MSI or MSI-X interrupt, we needn't
+ * do real work because EEH should freeze DMA transfers for those PCI
+ * devices encountering EEH errors, which includes MSI or MSI-X.
  */
 static void eeh_disable_irq(struct pci_dev *dev)
 {
-        struct device_node *dn = pci_device_to_OF_node(dev);
+        struct eeh_dev *edev = pci_dev_to_eeh_dev(dev);
 
         /* Don't disable MSI and MSI-X interrupts. They are
          * effectively disabled by the DMA Stopped state
          * when an EEH error occurs.
-        */
+         */
         if (dev->msi_enabled || dev->msix_enabled)
                 return;
 
         if (!irq_has_action(dev->irq))
                 return;
 
-        PCI_DN(dn)->eeh_mode |= EEH_MODE_IRQ_DISABLED;
+        edev->mode |= EEH_MODE_IRQ_DISABLED;
         disable_irq_nosync(dev->irq);
 }
 
 /**
- * eeh_enable_irq - enable interrupt for the recovering device
+ * eeh_enable_irq - Enable interrupt for the recovering device
+ * @dev: PCI device
+ *
+ * This routine must be called to enable interrupt while failed
+ * device could be resumed.
  */
 static void eeh_enable_irq(struct pci_dev *dev)
 {
-        struct device_node *dn = pci_device_to_OF_node(dev);
+        struct eeh_dev *edev = pci_dev_to_eeh_dev(dev);
 
-        if ((PCI_DN(dn)->eeh_mode) & EEH_MODE_IRQ_DISABLED) {
-                PCI_DN(dn)->eeh_mode &= ~EEH_MODE_IRQ_DISABLED;
+        if ((edev->mode) & EEH_MODE_IRQ_DISABLED) {
+                edev->mode &= ~EEH_MODE_IRQ_DISABLED;
                 enable_irq(dev->irq);
         }
 }
 
-/* ------------------------------------------------------- */
 /**
- * eeh_report_error - report pci error to each device driver
+ * eeh_report_error - Report pci error to each device driver
+ * @dev: PCI device
+ * @userdata: return value
  * 
  * Report an EEH error to each device driver, collect up and 
  * merge the device driver responses. Cumulative response 
  * passed back in "userdata".
  */
-
 static int eeh_report_error(struct pci_dev *dev, void *userdata)
 {
         enum pci_ers_result rc, *res = userdata;
@@ -122,7 +139,7 @@ static int eeh_report_error(struct pci_dev *dev, void *userdata)
             !driver->err_handler->error_detected)
                 return 0;
 
-        rc = driver->err_handler->error_detected (dev, pci_channel_io_frozen);
+        rc = driver->err_handler->error_detected(dev, pci_channel_io_frozen);
 
         /* A driver that needs a reset trumps all others */
         if (rc == PCI_ERS_RESULT_NEED_RESET) *res = rc;
@@ -132,13 +149,14 @@ static int eeh_report_error(struct pci_dev *dev, void *userdata)
 }
 
 /**
- * eeh_report_mmio_enabled - tell drivers that MMIO has been enabled
+ * eeh_report_mmio_enabled - Tell drivers that MMIO has been enabled
+ * @dev: PCI device
+ * @userdata: return value
  *
  * Tells each device driver that IO ports, MMIO and config space I/O
  * are now enabled. Collects up and merges the device driver responses.
  * Cumulative response passed back in "userdata".
  */
-
 static int eeh_report_mmio_enabled(struct pci_dev *dev, void *userdata)
 {
         enum pci_ers_result rc, *res = userdata;
@@ -149,7 +167,7 @@ static int eeh_report_mmio_enabled(struct pci_dev *dev, void *userdata)
             !driver->err_handler->mmio_enabled)
                 return 0;
 
-        rc = driver->err_handler->mmio_enabled (dev);
+        rc = driver->err_handler->mmio_enabled(dev);
 
         /* A driver that needs a reset trumps all others */
         if (rc == PCI_ERS_RESULT_NEED_RESET) *res = rc;
@@ -159,9 +177,15 @@ static int eeh_report_mmio_enabled(struct pci_dev *dev, void *userdata)
 }
 
 /**
- * eeh_report_reset - tell device that slot has been reset
+ * eeh_report_reset - Tell device that slot has been reset
+ * @dev: PCI device
+ * @userdata: return value
+ *
+ * This routine must be called while EEH tries to reset particular
+ * PCI device so that the associated PCI device driver could take
+ * some actions, usually to save data the driver needs so that the
+ * driver can work again while the device is recovered.
  */
-
 static int eeh_report_reset(struct pci_dev *dev, void *userdata)
 {
         enum pci_ers_result rc, *res = userdata;
@@ -188,9 +212,14 @@ static int eeh_report_reset(struct pci_dev *dev, void *userdata)
 }
 
 /**
- * eeh_report_resume - tell device to resume normal operations
+ * eeh_report_resume - Tell device to resume normal operations
+ * @dev: PCI device
+ * @userdata: return value
+ *
+ * This routine must be called to notify the device driver that it
+ * could resume so that the device driver can do some initialization
+ * to make the recovered device work again.
  */
-
 static int eeh_report_resume(struct pci_dev *dev, void *userdata)
 {
         struct pci_driver *driver = dev->driver;
@@ -212,12 +241,13 @@ static int eeh_report_resume(struct pci_dev *dev, void *userdata)
 }
 
 /**
- * eeh_report_failure - tell device driver that device is dead.
+ * eeh_report_failure - Tell device driver that device is dead.
+ * @dev: PCI device
+ * @userdata: return value
  *
  * This informs the device driver that the device is permanently
  * dead, and that no further recovery attempts will be made on it.
  */
-
 static int eeh_report_failure(struct pci_dev *dev, void *userdata)
 {
         struct pci_driver *driver = dev->driver;
@@ -238,65 +268,46 @@ static int eeh_report_failure(struct pci_dev *dev, void *userdata)
         return 0;
 }
 
-/* ------------------------------------------------------- */
 /**
- * handle_eeh_events -- reset a PCI device after hard lockup.
- *
- * pSeries systems will isolate a PCI slot if the PCI-Host
- * bridge detects address or data parity errors, DMA's
- * occurring to wild addresses (which usually happen due to
- * bugs in device drivers or in PCI adapter firmware).
- * Slot isolations also occur if #SERR, #PERR or other misc
- * PCI-related errors are detected.
+ * eeh_reset_device - Perform actual reset of a pci slot
+ * @edev: PE associated EEH device
+ * @bus: PCI bus corresponding to the isolcated slot
  *
- * Recovery process consists of unplugging the device driver
- * (which generated hotplug events to userspace), then issuing
- * a PCI #RST to the device, then reconfiguring the PCI config
- * space for all bridges & devices under this slot, and then
- * finally restarting the device drivers (which cause a second
- * set of hotplug events to go out to userspace).
+ * This routine must be called to do reset on the indicated PE.
+ * During the reset, udev might be invoked because those affected
+ * PCI devices will be removed and then added.
  */
-
-/**
- * eeh_reset_device() -- perform actual reset of a pci slot
- * @bus: pointer to the pci bus structure corresponding
- *            to the isolated slot. A non-null value will
- *            cause all devices under the bus to be removed
- *            and then re-added.
- * @pe_dn: pointer to a "Partionable Endpoint" device node.
- *            This is the top-level structure on which pci
- *            bus resets can be performed.
- */
-
-static int eeh_reset_device (struct pci_dn *pe_dn, struct pci_bus *bus)
+static int eeh_reset_device(struct eeh_dev *edev, struct pci_bus *bus)
 {
         struct device_node *dn;
         int cnt, rc;
 
         /* pcibios will clear the counter; save the value */
-        cnt = pe_dn->eeh_freeze_count;
+        cnt = edev->freeze_count;
 
         if (bus)
                 pcibios_remove_pci_devices(bus);
 
         /* Reset the pci controller. (Asserts RST#; resets config space).
          * Reconfigure bridges and devices. Don't try to bring the system
-         * up if the reset failed for some reason. */
-        rc = rtas_set_slot_reset(pe_dn);
+         * up if the reset failed for some reason.
+         */
+        rc = eeh_reset_pe(edev);
         if (rc)
                 return rc;
 
-        /* Walk over all functions on this device.  */
-        dn = pe_dn->node;
-        if (!pcibios_find_pci_bus(dn) && PCI_DN(dn->parent))
+        /* Walk over all functions on this device. */
+        dn = eeh_dev_to_of_node(edev);
+        if (!pcibios_find_pci_bus(dn) && of_node_to_eeh_dev(dn->parent))
                 dn = dn->parent->child;
 
         while (dn) {
-                struct pci_dn *ppe = PCI_DN(dn);
+                struct eeh_dev *pedev = of_node_to_eeh_dev(dn);
+
                 /* On Power4, always true because eeh_pe_config_addr=0 */
-                if (pe_dn->eeh_pe_config_addr == ppe->eeh_pe_config_addr) {
-                        rtas_configure_bridge(ppe);
-                        eeh_restore_bars(ppe);
+                if (edev->pe_config_addr == pedev->pe_config_addr) {
+                        eeh_ops->configure_bridge(dn);
+                        eeh_restore_bars(pedev);
                 }
                 dn = dn->sibling;
         }
@@ -308,10 +319,10 @@ static int eeh_reset_device (struct pci_dn *pe_dn, struct pci_bus *bus)
          * potentially weird things happen.
          */
         if (bus) {
-                ssleep (5);
+                ssleep(5);
                 pcibios_add_pci_devices(bus);
         }
-        pe_dn->eeh_freeze_count = cnt;
+        edev->freeze_count = cnt;
 
         return 0;
 }
@@ -321,23 +332,39 @@ static int eeh_reset_device (struct pci_dn *pe_dn, struct pci_bus *bus)
  */
 #define MAX_WAIT_FOR_RECOVERY 150
 
-struct pci_dn * handle_eeh_events (struct eeh_event *event)
+/**
+ * eeh_handle_event - Reset a PCI device after hard lockup.
+ * @event: EEH event
+ *
+ * While PHB detects address or data parity errors on particular PCI
+ * slot, the associated PE will be frozen. Besides, DMA's occurring
+ * to wild addresses (which usually happen due to bugs in device
+ * drivers or in PCI adapter firmware) can cause EEH error. #SERR,
+ * #PERR or other misc PCI-related errors also can trigger EEH errors.
+ *
+ * Recovery process consists of unplugging the device driver (which
+ * generated hotplug events to userspace), then issuing a PCI #RST to
+ * the device, then reconfiguring the PCI config space for all bridges
+ * & devices under this slot, and then finally restarting the device
+ * drivers (which cause a second set of hotplug events to go out to
+ * userspace).
+ */
+struct eeh_dev *handle_eeh_events(struct eeh_event *event)
 {
         struct device_node *frozen_dn;
-        struct pci_dn *frozen_pdn;
+        struct eeh_dev *frozen_edev;
         struct pci_bus *frozen_bus;
         int rc = 0;
         enum pci_ers_result result = PCI_ERS_RESULT_NONE;
         const char *location, *pci_str, *drv_str, *bus_pci_str, *bus_drv_str;
 
-        frozen_dn = find_device_pe(event->dn);
+        frozen_dn = eeh_find_device_pe(eeh_dev_to_of_node(event->edev));
         if (!frozen_dn) {
-
-                location = of_get_property(event->dn, "ibm,loc-code", NULL);
+                location = of_get_property(eeh_dev_to_of_node(event->edev), "ibm,loc-code", NULL);
                 location = location ? location : "unknown";
                 printk(KERN_ERR "EEH: Error: Cannot find partition endpoint "
                                 "for location=%s pci addr=%s\n",
-                        location, eeh_pci_name(event->dev));
+                        location, eeh_pci_name(eeh_dev_to_pci_dev(event->edev)));
                 return NULL;
         }
 
@@ -350,9 +377,10 @@ struct pci_dn * handle_eeh_events (struct eeh_event *event)
          * which was always an EADS pci bridge.  In the new style,
          * there might not be any EADS bridges, and even when there are,
          * the firmware marks them as "EEH incapable". So another
-         * two-step is needed to find the pci bus.. */
+         * two-step is needed to find the pci bus..
+         */
         if (!frozen_bus)
-                frozen_bus = pcibios_find_pci_bus (frozen_dn->parent);
+                frozen_bus = pcibios_find_pci_bus(frozen_dn->parent);
 
         if (!frozen_bus) {
                 printk(KERN_ERR "EEH: Cannot find PCI bus "
@@ -361,22 +389,21 @@ struct pci_dn * handle_eeh_events (struct eeh_event *event)
                 return NULL;
         }
 
-        frozen_pdn = PCI_DN(frozen_dn);
-        frozen_pdn->eeh_freeze_count++;
+        frozen_edev = of_node_to_eeh_dev(frozen_dn);
+        frozen_edev->freeze_count++;
+        pci_str = eeh_pci_name(eeh_dev_to_pci_dev(event->edev));
+        drv_str = eeh_pcid_name(eeh_dev_to_pci_dev(event->edev));
 
-        pci_str = eeh_pci_name(event->dev);
-        drv_str = pcid_name(event->dev);
-        
-        if (frozen_pdn->eeh_freeze_count > EEH_MAX_ALLOWED_FREEZES)
+        if (frozen_edev->freeze_count > EEH_MAX_ALLOWED_FREEZES)
                 goto excess_failures;
 
         printk(KERN_WARNING
            "EEH: This PCI device has failed %d times in the last hour:\n",
-                frozen_pdn->eeh_freeze_count);
+                frozen_edev->freeze_count);
 
-        if (frozen_pdn->pcidev) {
-                bus_pci_str = pci_name(frozen_pdn->pcidev);
-                bus_drv_str = pcid_name(frozen_pdn->pcidev);
+        if (frozen_edev->pdev) {
+                bus_pci_str = pci_name(frozen_edev->pdev);
+                bus_drv_str = eeh_pcid_name(frozen_edev->pdev);
                 printk(KERN_WARNING
                         "EEH: Bus location=%s driver=%s pci addr=%s\n",
                         location, bus_drv_str, bus_pci_str);
@@ -395,9 +422,10 @@ struct pci_dn * handle_eeh_events (struct eeh_event *event)
         pci_walk_bus(frozen_bus, eeh_report_error, &result);
 
         /* Get the current PCI slot state. This can take a long time,
-         * sometimes over 3 seconds for certain systems. */
-        rc = eeh_wait_for_slot_status (frozen_pdn, MAX_WAIT_FOR_RECOVERY*1000);
-        if (rc < 0) {
+         * sometimes over 3 seconds for certain systems.
+         */
+        rc = eeh_ops->wait_state(eeh_dev_to_of_node(frozen_edev), MAX_WAIT_FOR_RECOVERY*1000);
+        if (rc < 0 || rc == EEH_STATE_NOT_SUPPORT) {
                 printk(KERN_WARNING "EEH: Permanent failure\n");
                 goto hard_fail;
         }
@@ -406,14 +434,14 @@ struct pci_dn * handle_eeh_events (struct eeh_event *event)
          * don't post the error log until after all dev drivers
          * have been informed.
          */
-        eeh_slot_error_detail(frozen_pdn, EEH_LOG_TEMP_FAILURE);
+        eeh_slot_error_detail(frozen_edev, EEH_LOG_TEMP);
 
         /* If all device drivers were EEH-unaware, then shut
          * down all of the device drivers, and hope they
          * go down willingly, without panicing the system.
          */
         if (result == PCI_ERS_RESULT_NONE) {
-                rc = eeh_reset_device(frozen_pdn, frozen_bus);
+                rc = eeh_reset_device(frozen_edev, frozen_bus);
                 if (rc) {
                         printk(KERN_WARNING "EEH: Unable to reset, rc=%d\n", rc);
                         goto hard_fail;
@@ -422,7 +450,7 @@ struct pci_dn * handle_eeh_events (struct eeh_event *event)
 
         /* If all devices reported they can proceed, then re-enable MMIO */
         if (result == PCI_ERS_RESULT_CAN_RECOVER) {
-                rc = rtas_pci_enable(frozen_pdn, EEH_THAW_MMIO);
+                rc = eeh_pci_enable(frozen_edev, EEH_OPT_THAW_MMIO);
 
                 if (rc < 0)
                         goto hard_fail;
@@ -436,7 +464,7 @@ struct pci_dn * handle_eeh_events (struct eeh_event *event)
 
         /* If all devices reported they can proceed, then re-enable DMA */
         if (result == PCI_ERS_RESULT_CAN_RECOVER) {
-                rc = rtas_pci_enable(frozen_pdn, EEH_THAW_DMA);
+                rc = eeh_pci_enable(frozen_edev, EEH_OPT_THAW_DMA);
 
                 if (rc < 0)
                         goto hard_fail;
@@ -454,7 +482,7 @@ struct pci_dn * handle_eeh_events (struct eeh_event *event)
 
         /* If any device called out for a reset, then reset the slot */
         if (result == PCI_ERS_RESULT_NEED_RESET) {
-                rc = eeh_reset_device(frozen_pdn, NULL);
+                rc = eeh_reset_device(frozen_edev, NULL);
                 if (rc) {
                         printk(KERN_WARNING "EEH: Cannot reset, rc=%d\n", rc);
                         goto hard_fail;
@@ -473,7 +501,7 @@ struct pci_dn * handle_eeh_events (struct eeh_event *event)
         /* Tell all device drivers that they can resume operations */
         pci_walk_bus(frozen_bus, eeh_report_resume, NULL);
 
-        return frozen_pdn;
+        return frozen_edev;
         
 excess_failures:
         /*
@@ -486,7 +514,7 @@ excess_failures:
                 "has failed %d times in the last hour "
                 "and has been permanently disabled.\n"
                 "Please try reseating this device or replacing it.\n",
-                location, drv_str, pci_str, frozen_pdn->eeh_freeze_count);
+                location, drv_str, pci_str, frozen_edev->freeze_count);
         goto perm_error;
 
 hard_fail:
@@ -497,7 +525,7 @@ hard_fail:
                 location, drv_str, pci_str);
 
 perm_error:
-        eeh_slot_error_detail(frozen_pdn, EEH_LOG_PERM_FAILURE);
+        eeh_slot_error_detail(frozen_edev, EEH_LOG_PERM);
 
         /* Notify all devices that they're about to go down. */
         pci_walk_bus(frozen_bus, eeh_report_failure, NULL);
@@ -508,4 +536,3 @@ perm_error:
         return NULL;
 }
 
-/* ---------- end of file ---------- */
diff --git a/arch/powerpc/platforms/pseries/eeh_event.c b/arch/powerpc/platforms/pseries/eeh_event.c
index d2383cfb6dfd..4a4752565856 100644
--- a/arch/powerpc/platforms/pseries/eeh_event.c
+++ b/arch/powerpc/platforms/pseries/eeh_event.c
@@ -1,6 +1,4 @@
 /*
- * eeh_event.c
- *
  * 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
@@ -46,7 +44,7 @@ DECLARE_WORK(eeh_event_wq, eeh_thread_launcher);
 DEFINE_MUTEX(eeh_event_mutex);
 
 /**
- * eeh_event_handler - dispatch EEH events.
+ * eeh_event_handler - Dispatch EEH events.
  * @dummy - unused
  *
  * The detection of a frozen slot can occur inside an interrupt,
@@ -58,10 +56,10 @@ DEFINE_MUTEX(eeh_event_mutex);
 static int eeh_event_handler(void * dummy)
 {
         unsigned long flags;
-        struct eeh_event        *event;
-        struct pci_dn *pdn;
+        struct eeh_event *event;
+        struct eeh_dev *edev;
 
-        daemonize ("eehd");
+        daemonize("eehd");
         set_current_state(TASK_INTERRUPTIBLE);
 
         spin_lock_irqsave(&eeh_eventlist_lock, flags);
@@ -79,31 +77,37 @@ static int eeh_event_handler(void * dummy)
 
         /* Serialize processing of EEH events */
         mutex_lock(&eeh_event_mutex);
-        eeh_mark_slot(event->dn, EEH_MODE_RECOVERING);
+        edev = event->edev;
+        eeh_mark_slot(eeh_dev_to_of_node(edev), EEH_MODE_RECOVERING);
 
         printk(KERN_INFO "EEH: Detected PCI bus error on device %s\n",
-               eeh_pci_name(event->dev));
+               eeh_pci_name(edev->pdev));
+
+        edev = handle_eeh_events(event);
 
-        pdn = handle_eeh_events(event);
+        eeh_clear_slot(eeh_dev_to_of_node(edev), EEH_MODE_RECOVERING);
+        pci_dev_put(edev->pdev);
 
-        eeh_clear_slot(event->dn, EEH_MODE_RECOVERING);
-        pci_dev_put(event->dev);
         kfree(event);
         mutex_unlock(&eeh_event_mutex);
 
         /* If there are no new errors after an hour, clear the counter. */
-        if (pdn && pdn->eeh_freeze_count>0) {
-                msleep_interruptible (3600*1000);
-                if (pdn->eeh_freeze_count>0)
-                        pdn->eeh_freeze_count--;
+        if (edev && edev->freeze_count>0) {
+                msleep_interruptible(3600*1000);
+                if (edev->freeze_count>0)
+                        edev->freeze_count--;
+
         }
 
         return 0;
 }
 
 /**
- * eeh_thread_launcher
+ * eeh_thread_launcher - Start kernel thread to handle EEH events
  * @dummy - unused
+ *
+ * This routine is called to start the kernel thread for processing
+ * EEH event.
  */
 static void eeh_thread_launcher(struct work_struct *dummy)
 {
@@ -112,18 +116,18 @@ static void eeh_thread_launcher(struct work_struct *dummy)
 }
 
 /**
- * eeh_send_failure_event - generate a PCI error event
- * @dev pci device
+ * eeh_send_failure_event - Generate a PCI error event
+ * @edev: EEH device
  *
  * This routine can be called within an interrupt context;
  * the actual event will be delivered in a normal context
  * (from a workqueue).
  */
-int eeh_send_failure_event (struct device_node *dn,
-                            struct pci_dev *dev)
+int eeh_send_failure_event(struct eeh_dev *edev)
 {
         unsigned long flags;
         struct eeh_event *event;
+        struct device_node *dn = eeh_dev_to_of_node(edev);
         const char *location;
 
         if (!mem_init_done) {
@@ -135,15 +139,14 @@ int eeh_send_failure_event (struct device_node *dn,
         }
         event = kmalloc(sizeof(*event), GFP_ATOMIC);
         if (event == NULL) {
-                printk (KERN_ERR "EEH: out of memory, event not handled\n");
+                printk(KERN_ERR "EEH: out of memory, event not handled\n");
                 return 1;
         }
 
-        if (dev)
-                pci_dev_get(dev);
+        if (edev->pdev)
+                pci_dev_get(edev->pdev);
 
-        event->dn = dn;
-        event->dev = dev;
+        event->edev = edev;
 
         /* We may or may not be called in an interrupt context */
         spin_lock_irqsave(&eeh_eventlist_lock, flags);
@@ -154,5 +157,3 @@ int eeh_send_failure_event (struct device_node *dn,
 
         return 0;
 }
-
-/********************** END OF FILE ******************************/
diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c
new file mode 100644
index 000000000000..8752f79a6af8
--- /dev/null
+++ b/arch/powerpc/platforms/pseries/eeh_pseries.c
@@ -0,0 +1,565 @@
+/*
+ * The file intends to implement the platform dependent EEH operations on pseries.
+ * Actually, the pseries platform is built based on RTAS heavily. That means the
+ * pseries platform dependent EEH operations will be built on RTAS calls. The functions
+ * are devired from arch/powerpc/platforms/pseries/eeh.c and necessary cleanup has
+ * been done.
+ *
+ * Copyright Benjamin Herrenschmidt & Gavin Shan, IBM Corporation 2011.
+ * Copyright IBM Corporation 2001, 2005, 2006
+ * Copyright Dave Engebretsen & Todd Inglett 2001
+ * Copyright Linas Vepstas 2005, 2006
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
+ */
+
+#include <linux/atomic.h>
+#include <linux/delay.h>
+#include <linux/export.h>
+#include <linux/init.h>
+#include <linux/list.h>
+#include <linux/of.h>
+#include <linux/pci.h>
+#include <linux/proc_fs.h>
+#include <linux/rbtree.h>
+#include <linux/sched.h>
+#include <linux/seq_file.h>
+#include <linux/spinlock.h>
+
+#include <asm/eeh.h>
+#include <asm/eeh_event.h>
+#include <asm/io.h>
+#include <asm/machdep.h>
+#include <asm/ppc-pci.h>
+#include <asm/rtas.h>
+
+/* RTAS tokens */
+static int ibm_set_eeh_option;
+static int ibm_set_slot_reset;
+static int ibm_read_slot_reset_state;
+static int ibm_read_slot_reset_state2;
+static int ibm_slot_error_detail;
+static int ibm_get_config_addr_info;
+static int ibm_get_config_addr_info2;
+static int ibm_configure_bridge;
+static int ibm_configure_pe;
+
+/*
+ * Buffer for reporting slot-error-detail rtas calls. Its here
+ * in BSS, and not dynamically alloced, so that it ends up in
+ * RMO where RTAS can access it.
+ */
+static unsigned char slot_errbuf[RTAS_ERROR_LOG_MAX];
+static DEFINE_SPINLOCK(slot_errbuf_lock);
+static int eeh_error_buf_size;
+
+/**
+ * pseries_eeh_init - EEH platform dependent initialization
+ *
+ * EEH platform dependent initialization on pseries.
+ */
+static int pseries_eeh_init(void)
+{
+        /* figure out EEH RTAS function call tokens */
+        ibm_set_eeh_option              = rtas_token("ibm,set-eeh-option");
+        ibm_set_slot_reset              = rtas_token("ibm,set-slot-reset");
+        ibm_read_slot_reset_state2      = rtas_token("ibm,read-slot-reset-state2");
+        ibm_read_slot_reset_state       = rtas_token("ibm,read-slot-reset-state");
+        ibm_slot_error_detail           = rtas_token("ibm,slot-error-detail");
+        ibm_get_config_addr_info2       = rtas_token("ibm,get-config-addr-info2");
+        ibm_get_config_addr_info        = rtas_token("ibm,get-config-addr-info");
+        ibm_configure_pe                = rtas_token("ibm,configure-pe");
+        ibm_configure_bridge            = rtas_token ("ibm,configure-bridge");
+
+        /* necessary sanity check */
+        if (ibm_set_eeh_option == RTAS_UNKNOWN_SERVICE) {
+                pr_warning("%s: RTAS service <ibm,set-eeh-option> invalid\n",
+                        __func__);
+                return -EINVAL;
+        } else if (ibm_set_slot_reset == RTAS_UNKNOWN_SERVICE) {
+                pr_warning("%s: RTAS service <ibm, set-slot-reset> invalid\n",
+                        __func__);
+                return -EINVAL;
+        } else if (ibm_read_slot_reset_state2 == RTAS_UNKNOWN_SERVICE &&
+                   ibm_read_slot_reset_state == RTAS_UNKNOWN_SERVICE) {
+                pr_warning("%s: RTAS service <ibm,read-slot-reset-state2> and "
+                        "<ibm,read-slot-reset-state> invalid\n",
+                        __func__);
+                return -EINVAL;
+        } else if (ibm_slot_error_detail == RTAS_UNKNOWN_SERVICE) {
+                pr_warning("%s: RTAS service <ibm,slot-error-detail> invalid\n",
+                        __func__);
+                return -EINVAL;
+        } else if (ibm_get_config_addr_info2 == RTAS_UNKNOWN_SERVICE &&
+                   ibm_get_config_addr_info == RTAS_UNKNOWN_SERVICE) {
+                pr_warning("%s: RTAS service <ibm,get-config-addr-info2> and "
+                        "<ibm,get-config-addr-info> invalid\n",
+                        __func__);
+                return -EINVAL;
+        } else if (ibm_configure_pe == RTAS_UNKNOWN_SERVICE &&
+                   ibm_configure_bridge == RTAS_UNKNOWN_SERVICE) {
+                pr_warning("%s: RTAS service <ibm,configure-pe> and "
+                        "<ibm,configure-bridge> invalid\n",
+                        __func__);
+                return -EINVAL;
+        }
+
+        /* Initialize error log lock and size */
+        spin_lock_init(&slot_errbuf_lock);
+        eeh_error_buf_size = rtas_token("rtas-error-log-max");
+        if (eeh_error_buf_size == RTAS_UNKNOWN_SERVICE) {
+                pr_warning("%s: unknown EEH error log size\n",
+                        __func__);
+                eeh_error_buf_size = 1024;
+        } else if (eeh_error_buf_size > RTAS_ERROR_LOG_MAX) {
+                pr_warning("%s: EEH error log size %d exceeds the maximal %d\n",
+                        __func__, eeh_error_buf_size, RTAS_ERROR_LOG_MAX);
+                eeh_error_buf_size = RTAS_ERROR_LOG_MAX;
+        }
+
+        return 0;
+}
+
+/**
+ * pseries_eeh_set_option - Initialize EEH or MMIO/DMA reenable
+ * @dn: device node
+ * @option: operation to be issued
+ *
+ * The function is used to control the EEH functionality globally.
+ * Currently, following options are support according to PAPR:
+ * Enable EEH, Disable EEH, Enable MMIO and Enable DMA
+ */
+static int pseries_eeh_set_option(struct device_node *dn, int option)
+{
+        int ret = 0;
+        struct eeh_dev *edev;
+        const u32 *reg;
+        int config_addr;
+
+        edev = of_node_to_eeh_dev(dn);
+
+        /*
+         * When we're enabling or disabling EEH functioality on
+         * the particular PE, the PE config address is possibly
+         * unavailable. Therefore, we have to figure it out from
+         * the FDT node.
+         */
+        switch (option) {
+        case EEH_OPT_DISABLE:
+        case EEH_OPT_ENABLE:
+                reg = of_get_property(dn, "reg", NULL);
+                config_addr = reg[0];
+                break;
+
+        case EEH_OPT_THAW_MMIO:
+        case EEH_OPT_THAW_DMA:
+                config_addr = edev->config_addr;
+                if (edev->pe_config_addr)
+                        config_addr = edev->pe_config_addr;
+                break;
+
+        default:
+                pr_err("%s: Invalid option %d\n",
+                        __func__, option);
+                return -EINVAL;
+        }
+
+        ret = rtas_call(ibm_set_eeh_option, 4, 1, NULL,
+                        config_addr, BUID_HI(edev->phb->buid),
+                        BUID_LO(edev->phb->buid), option);
+
+        return ret;
+}
+
+/**
+ * pseries_eeh_get_pe_addr - Retrieve PE address
+ * @dn: device node
+ *
+ * Retrieve the assocated PE address. Actually, there're 2 RTAS
+ * function calls dedicated for the purpose. We need implement
+ * it through the new function and then the old one. Besides,
+ * you should make sure the config address is figured out from
+ * FDT node before calling the function.
+ *
+ * It's notable that zero'ed return value means invalid PE config
+ * address.
+ */
+static int pseries_eeh_get_pe_addr(struct device_node *dn)
+{
+        struct eeh_dev *edev;
+        int ret = 0;
+        int rets[3];
+
+        edev = of_node_to_eeh_dev(dn);
+
+        if (ibm_get_config_addr_info2 != RTAS_UNKNOWN_SERVICE) {
+                /*
+                 * First of all, we need to make sure there has one PE
+                 * associated with the device. Otherwise, PE address is
+                 * meaningless.
+                 */
+                ret = rtas_call(ibm_get_config_addr_info2, 4, 2, rets,
+                                edev->config_addr, BUID_HI(edev->phb->buid),
+                                BUID_LO(edev->phb->buid), 1);
+                if (ret || (rets[0] == 0))
+                        return 0;
+
+                /* Retrieve the associated PE config address */
+                ret = rtas_call(ibm_get_config_addr_info2, 4, 2, rets,
+                                edev->config_addr, BUID_HI(edev->phb->buid),
+                                BUID_LO(edev->phb->buid), 0);
+                if (ret) {
+                        pr_warning("%s: Failed to get PE address for %s\n",
+                                __func__, dn->full_name);
+                        return 0;
+                }
+
+                return rets[0];
+        }
+
+        if (ibm_get_config_addr_info != RTAS_UNKNOWN_SERVICE) {
+                ret = rtas_call(ibm_get_config_addr_info, 4, 2, rets,
+                                edev->config_addr, BUID_HI(edev->phb->buid),
+                                BUID_LO(edev->phb->buid), 0);
+                if (ret) {
+                        pr_warning("%s: Failed to get PE address for %s\n",
+                                __func__, dn->full_name);
+                        return 0;
+                }
+
+                return rets[0];
+        }
+
+        return ret;
+}
+
+/**
+ * pseries_eeh_get_state - Retrieve PE state
+ * @dn: PE associated device node
+ * @state: return value
+ *
+ * Retrieve the state of the specified PE. On RTAS compliant
+ * pseries platform, there already has one dedicated RTAS function
+ * for the purpose. It's notable that the associated PE config address
+ * might be ready when calling the function. Therefore, endeavour to
+ * use the PE config address if possible. Further more, there're 2
+ * RTAS calls for the purpose, we need to try the new one and back
+ * to the old one if the new one couldn't work properly.
+ */
+static int pseries_eeh_get_state(struct device_node *dn, int *state)
+{
+        struct eeh_dev *edev;
+        int config_addr;
+        int ret;
+        int rets[4];
+        int result;
+
+        /* Figure out PE config address if possible */
+        edev = of_node_to_eeh_dev(dn);
+        config_addr = edev->config_addr;
+        if (edev->pe_config_addr)
+                config_addr = edev->pe_config_addr;
+
+        if (ibm_read_slot_reset_state2 != RTAS_UNKNOWN_SERVICE) {
+                ret = rtas_call(ibm_read_slot_reset_state2, 3, 4, rets,
+                                config_addr, BUID_HI(edev->phb->buid),
+                                BUID_LO(edev->phb->buid));
+        } else if (ibm_read_slot_reset_state != RTAS_UNKNOWN_SERVICE) {
+                /* Fake PE unavailable info */
+                rets[2] = 0;
+                ret = rtas_call(ibm_read_slot_reset_state, 3, 3, rets,
+                                config_addr, BUID_HI(edev->phb->buid),
+                                BUID_LO(edev->phb->buid));
+        } else {
+                return EEH_STATE_NOT_SUPPORT;
+        }
+
+        if (ret)
+                return ret;
+
+        /* Parse the result out */
+        result = 0;
+        if (rets[1]) {
+                switch(rets[0]) {
+                case 0:
+                        result &= ~EEH_STATE_RESET_ACTIVE;
+                        result |= EEH_STATE_MMIO_ACTIVE;
+                        result |= EEH_STATE_DMA_ACTIVE;
+                        break;
+                case 1:
+                        result |= EEH_STATE_RESET_ACTIVE;
+                        result |= EEH_STATE_MMIO_ACTIVE;
+                        result |= EEH_STATE_DMA_ACTIVE;
+                        break;
+                case 2:
+                        result &= ~EEH_STATE_RESET_ACTIVE;
+                        result &= ~EEH_STATE_MMIO_ACTIVE;
+                        result &= ~EEH_STATE_DMA_ACTIVE;
+                        break;
+                case 4:
+                        result &= ~EEH_STATE_RESET_ACTIVE;
+                        result &= ~EEH_STATE_MMIO_ACTIVE;
+                        result &= ~EEH_STATE_DMA_ACTIVE;
+                        result |= EEH_STATE_MMIO_ENABLED;
+                        break;
+                case 5:
+                        if (rets[2]) {
+                                if (state) *state = rets[2];
+                                result = EEH_STATE_UNAVAILABLE;
+                        } else {
+                                result = EEH_STATE_NOT_SUPPORT;
+                        }
+                default:
+                        result = EEH_STATE_NOT_SUPPORT;
+                }
+        } else {
+                result = EEH_STATE_NOT_SUPPORT;
+        }
+
+        return result;
+}
+
+/**
+ * pseries_eeh_reset - Reset the specified PE
+ * @dn: PE associated device node
+ * @option: reset option
+ *
+ * Reset the specified PE
+ */
+static int pseries_eeh_reset(struct device_node *dn, int option)
+{
+        struct eeh_dev *edev;
+        int config_addr;
+        int ret;
+
+        /* Figure out PE address */
+        edev = of_node_to_eeh_dev(dn);
+        config_addr = edev->config_addr;
+        if (edev->pe_config_addr)
+                config_addr = edev->pe_config_addr;
+
+        /* Reset PE through RTAS call */
+        ret = rtas_call(ibm_set_slot_reset, 4, 1, NULL,
+                        config_addr, BUID_HI(edev->phb->buid),
+                        BUID_LO(edev->phb->buid), option);
+
+        /* If fundamental-reset not supported, try hot-reset */
+        if (option == EEH_RESET_FUNDAMENTAL &&
+            ret == -8) {
+                ret = rtas_call(ibm_set_slot_reset, 4, 1, NULL,
+                                config_addr, BUID_HI(edev->phb->buid),
+                                BUID_LO(edev->phb->buid), EEH_RESET_HOT);
+        }
+
+        return ret;
+}
+
+/**
+ * pseries_eeh_wait_state - Wait for PE state
+ * @dn: PE associated device node
+ * @max_wait: maximal period in microsecond
+ *
+ * Wait for the state of associated PE. It might take some time
+ * to retrieve the PE's state.
+ */
+static int pseries_eeh_wait_state(struct device_node *dn, int max_wait)
+{
+        int ret;
+        int mwait;
+
+        /*
+         * According to PAPR, the state of PE might be temporarily
+         * unavailable. Under the circumstance, we have to wait
+         * for indicated time determined by firmware. The maximal
+         * wait time is 5 minutes, which is acquired from the original
+         * EEH implementation. Also, the original implementation
+         * also defined the minimal wait time as 1 second.
+         */
+#define EEH_STATE_MIN_WAIT_TIME (1000)
+#define EEH_STATE_MAX_WAIT_TIME (300 * 1000)
+
+        while (1) {
+                ret = pseries_eeh_get_state(dn, &mwait);
+
+                /*
+                 * If the PE's state is temporarily unavailable,
+                 * we have to wait for the specified time. Otherwise,
+                 * the PE's state will be returned immediately.
+                 */
+                if (ret != EEH_STATE_UNAVAILABLE)
+                        return ret;
+
+                if (max_wait <= 0) {
+                        pr_warning("%s: Timeout when getting PE's state (%d)\n",
+                                __func__, max_wait);
+                        return EEH_STATE_NOT_SUPPORT;
+                }
+
+                if (mwait <= 0) {
+                        pr_warning("%s: Firmware returned bad wait value %d\n",
+                                __func__, mwait);
+                        mwait = EEH_STATE_MIN_WAIT_TIME;
+                } else if (mwait > EEH_STATE_MAX_WAIT_TIME) {
+                        pr_warning("%s: Firmware returned too long wait value %d\n",
+                                __func__, mwait);
+                        mwait = EEH_STATE_MAX_WAIT_TIME;
+                }
+
+                max_wait -= mwait;
+                msleep(mwait);
+        }
+
+        return EEH_STATE_NOT_SUPPORT;
+}
+
+/**
+ * pseries_eeh_get_log - Retrieve error log
+ * @dn: device node
+ * @severity: temporary or permanent error log
+ * @drv_log: driver log to be combined with retrieved error log
+ * @len: length of driver log
+ *
+ * Retrieve the temporary or permanent error from the PE.
+ * Actually, the error will be retrieved through the dedicated
+ * RTAS call.
+ */
+static int pseries_eeh_get_log(struct device_node *dn, int severity, char *drv_log, unsigned long len)
+{
+        struct eeh_dev *edev;
+        int config_addr;
+        unsigned long flags;
+        int ret;
+
+        edev = of_node_to_eeh_dev(dn);
+        spin_lock_irqsave(&slot_errbuf_lock, flags);
+        memset(slot_errbuf, 0, eeh_error_buf_size);
+
+        /* Figure out the PE address */
+        config_addr = edev->config_addr;
+        if (edev->pe_config_addr)
+                config_addr = edev->pe_config_addr;
+
+        ret = rtas_call(ibm_slot_error_detail, 8, 1, NULL, config_addr,
+                        BUID_HI(edev->phb->buid), BUID_LO(edev->phb->buid),
+                        virt_to_phys(drv_log), len,
+                        virt_to_phys(slot_errbuf), eeh_error_buf_size,
+                        severity);
+        if (!ret)
+                log_error(slot_errbuf, ERR_TYPE_RTAS_LOG, 0);
+        spin_unlock_irqrestore(&slot_errbuf_lock, flags);
+
+        return ret;
+}
+
+/**
+ * pseries_eeh_configure_bridge - Configure PCI bridges in the indicated PE
+ * @dn: PE associated device node
+ *
+ * The function will be called to reconfigure the bridges included
+ * in the specified PE so that the mulfunctional PE would be recovered
+ * again.
+ */
+static int pseries_eeh_configure_bridge(struct device_node *dn)
+{
+        struct eeh_dev *edev;
+        int config_addr;
+        int ret;
+
+        /* Figure out the PE address */
+        edev = of_node_to_eeh_dev(dn);
+        config_addr = edev->config_addr;
+        if (edev->pe_config_addr)
+                config_addr = edev->pe_config_addr;
+
+        /* Use new configure-pe function, if supported */
+        if (ibm_configure_pe != RTAS_UNKNOWN_SERVICE) {
+                ret = rtas_call(ibm_configure_pe, 3, 1, NULL,
+                                config_addr, BUID_HI(edev->phb->buid),
+                                BUID_LO(edev->phb->buid));
+        } else if (ibm_configure_bridge != RTAS_UNKNOWN_SERVICE) {
+                ret = rtas_call(ibm_configure_bridge, 3, 1, NULL,
+                                config_addr, BUID_HI(edev->phb->buid),
+                                BUID_LO(edev->phb->buid));
+        } else {
+                return -EFAULT;
+        }
+
+        if (ret)
+                pr_warning("%s: Unable to configure bridge %d for %s\n",
+                        __func__, ret, dn->full_name);
+
+        return ret;
+}
+
+/**
+ * pseries_eeh_read_config - Read PCI config space
+ * @dn: device node
+ * @where: PCI address
+ * @size: size to read
+ * @val: return value
+ *
+ * Read config space from the speicifed device
+ */
+static int pseries_eeh_read_config(struct device_node *dn, int where, int size, u32 *val)
+{
+        struct pci_dn *pdn;
+
+        pdn = PCI_DN(dn);
+
+        return rtas_read_config(pdn, where, size, val);
+}
+
+/**
+ * pseries_eeh_write_config - Write PCI config space
+ * @dn: device node
+ * @where: PCI address
+ * @size: size to write
+ * @val: value to be written
+ *
+ * Write config space to the specified device
+ */
+static int pseries_eeh_write_config(struct device_node *dn, int where, int size, u32 val)
+{
+        struct pci_dn *pdn;
+
+        pdn = PCI_DN(dn);
+
+        return rtas_write_config(pdn, where, size, val);
+}
+
+static struct eeh_ops pseries_eeh_ops = {
+        .name                   = "pseries",
+        .init                   = pseries_eeh_init,
+        .set_option             = pseries_eeh_set_option,
+        .get_pe_addr            = pseries_eeh_get_pe_addr,
+        .get_state              = pseries_eeh_get_state,
+        .reset                  = pseries_eeh_reset,
+        .wait_state             = pseries_eeh_wait_state,
+        .get_log                = pseries_eeh_get_log,
+        .configure_bridge       = pseries_eeh_configure_bridge,
+        .read_config            = pseries_eeh_read_config,
+        .write_config           = pseries_eeh_write_config
+};
+
+/**
+ * eeh_pseries_init - Register platform dependent EEH operations
+ *
+ * EEH initialization on pseries platform. This function should be
+ * called before any EEH related functions.
+ */
+int __init eeh_pseries_init(void)
+{
+        return eeh_ops_register(&pseries_eeh_ops);
+}
diff --git a/arch/powerpc/platforms/pseries/eeh_sysfs.c b/arch/powerpc/platforms/pseries/eeh_sysfs.c
index eb744ee234da..243b3510d70f 100644
--- a/arch/powerpc/platforms/pseries/eeh_sysfs.c
+++ b/arch/powerpc/platforms/pseries/eeh_sysfs.c
@@ -28,7 +28,7 @@
 #include <asm/pci-bridge.h>
 
 /**
- * EEH_SHOW_ATTR -- create sysfs entry for eeh statistic
+ * EEH_SHOW_ATTR -- Create sysfs entry for eeh statistic
  * @_name: name of file in sysfs directory
  * @_memb: name of member in struct pci_dn to access
  * @_format: printf format for display
@@ -41,24 +41,21 @@ static ssize_t eeh_show_##_name(struct device *dev,      \
                 struct device_attribute *attr, char *buf)          \
 {                                                        \
         struct pci_dev *pdev = to_pci_dev(dev);               \
-        struct device_node *dn = pci_device_to_OF_node(pdev); \
-        struct pci_dn *pdn;                                   \
+        struct eeh_dev *edev = pci_dev_to_eeh_dev(pdev);      \
                                                               \
-        if (!dn || PCI_DN(dn) == NULL)                        \
-                return 0;                                          \
+        if (!edev)                                            \
+                return 0;                                     \
                                                               \
-        pdn = PCI_DN(dn);                                     \
-        return sprintf(buf, _format "\n", pdn->_memb);        \
+        return sprintf(buf, _format "\n", edev->_memb);       \
 }                                                        \
 static DEVICE_ATTR(_name, S_IRUGO, eeh_show_##_name, NULL);
 
-
-EEH_SHOW_ATTR(eeh_mode, eeh_mode, "0x%x");
-EEH_SHOW_ATTR(eeh_config_addr, eeh_config_addr, "0x%x");
-EEH_SHOW_ATTR(eeh_pe_config_addr, eeh_pe_config_addr, "0x%x");
-EEH_SHOW_ATTR(eeh_check_count, eeh_check_count, "%d");
-EEH_SHOW_ATTR(eeh_freeze_count, eeh_freeze_count, "%d");
-EEH_SHOW_ATTR(eeh_false_positives, eeh_false_positives, "%d");
+EEH_SHOW_ATTR(eeh_mode,            mode,            "0x%x");
+EEH_SHOW_ATTR(eeh_config_addr,     config_addr,     "0x%x");
+EEH_SHOW_ATTR(eeh_pe_config_addr,  pe_config_addr,  "0x%x");
+EEH_SHOW_ATTR(eeh_check_count,     check_count,     "%d"  );
+EEH_SHOW_ATTR(eeh_freeze_count,    freeze_count,    "%d"  );
+EEH_SHOW_ATTR(eeh_false_positives, false_positives, "%d"  );
 
 void eeh_sysfs_add_device(struct pci_dev *pdev)
 {
diff --git a/arch/powerpc/platforms/pseries/io_event_irq.c b/arch/powerpc/platforms/pseries/io_event_irq.c
index 1a709bc48ce1..ef9d9d84c7d5 100644
--- a/arch/powerpc/platforms/pseries/io_event_irq.c
+++ b/arch/powerpc/platforms/pseries/io_event_irq.c
@@ -63,73 +63,9 @@ EXPORT_SYMBOL_GPL(pseries_ioei_notifier_list);
 
 static int ioei_check_exception_token;
 
-/* pSeries event log format */
-
-/* Two bytes ASCII section IDs */
-#define PSERIES_ELOG_SECT_ID_PRIV_HDR           (('P' << 8) | 'H')
-#define PSERIES_ELOG_SECT_ID_USER_HDR           (('U' << 8) | 'H')
-#define PSERIES_ELOG_SECT_ID_PRIMARY_SRC        (('P' << 8) | 'S')
-#define PSERIES_ELOG_SECT_ID_EXTENDED_UH        (('E' << 8) | 'H')
-#define PSERIES_ELOG_SECT_ID_FAILING_MTMS       (('M' << 8) | 'T')
-#define PSERIES_ELOG_SECT_ID_SECONDARY_SRC      (('S' << 8) | 'S')
-#define PSERIES_ELOG_SECT_ID_DUMP_LOCATOR       (('D' << 8) | 'H')
-#define PSERIES_ELOG_SECT_ID_FW_ERROR           (('S' << 8) | 'W')
-#define PSERIES_ELOG_SECT_ID_IMPACT_PART_ID     (('L' << 8) | 'P')
-#define PSERIES_ELOG_SECT_ID_LOGIC_RESOURCE_ID  (('L' << 8) | 'R')
-#define PSERIES_ELOG_SECT_ID_HMC_ID             (('H' << 8) | 'M')
-#define PSERIES_ELOG_SECT_ID_EPOW               (('E' << 8) | 'P')
-#define PSERIES_ELOG_SECT_ID_IO_EVENT           (('I' << 8) | 'E')
-#define PSERIES_ELOG_SECT_ID_MANUFACT_INFO      (('M' << 8) | 'I')
-#define PSERIES_ELOG_SECT_ID_CALL_HOME          (('C' << 8) | 'H')
-#define PSERIES_ELOG_SECT_ID_USER_DEF           (('U' << 8) | 'D')
-
-/* Vendor specific Platform Event Log Format, Version 6, section header */
-struct pseries_elog_section {
-        uint16_t id;                    /* 0x00 2-byte ASCII section ID */
-        uint16_t length;                /* 0x02 Section length in bytes */
-        uint8_t version;                /* 0x04 Section version         */
-        uint8_t subtype;                /* 0x05 Section subtype         */
-        uint16_t creator_component;     /* 0x06 Creator component ID    */
-        uint8_t data[];                 /* 0x08 Start of section data   */
-};
-
 static char ioei_rtas_buf[RTAS_DATA_BUF_SIZE] __cacheline_aligned;
 
 /**
- * Find data portion of a specific section in RTAS extended event log.
- * @elog: RTAS error/event log.
- * @sect_id: secsion ID.
- *
- * Return:
- *      pointer to the section data of the specified section
- *      NULL if not found
- */
-static struct pseries_elog_section *find_xelog_section(struct rtas_error_log *elog,
-                                                       uint16_t sect_id)
-{
-        struct rtas_ext_event_log_v6 *xelog =
-                (struct rtas_ext_event_log_v6 *) elog->buffer;
-        struct pseries_elog_section *sect;
-        unsigned char *p, *log_end;
-
-        /* Check that we understand the format */
-        if (elog->extended_log_length < sizeof(struct rtas_ext_event_log_v6) ||
-            xelog->log_format != RTAS_V6EXT_LOG_FORMAT_EVENT_LOG ||
-            xelog->company_id != RTAS_V6EXT_COMPANY_ID_IBM)
-                return NULL;
-
-        log_end = elog->buffer + elog->extended_log_length;
-        p = xelog->vendor_log;
-        while (p < log_end) {
-                sect = (struct pseries_elog_section *)p;
-                if (sect->id == sect_id)
-                        return sect;
-                p += sect->length;
-        }
-        return NULL;
-}
-
-/**
  * Find the data portion of an IO Event section from event log.
  * @elog: RTAS error/event log.
  *
@@ -138,7 +74,7 @@ static struct pseries_elog_section *find_xelog_section(struct rtas_error_log *el
  */
 static struct pseries_io_event * ioei_find_event(struct rtas_error_log *elog)
 {
-        struct pseries_elog_section *sect;
+        struct pseries_errorlog *sect;
 
         /* We should only ever get called for io-event interrupts, but if
          * we do get called for another type then something went wrong so
@@ -152,7 +88,7 @@ static struct pseries_io_event * ioei_find_event(struct rtas_error_log *elog)
                 return NULL;
         }
 
-        sect = find_xelog_section(elog, PSERIES_ELOG_SECT_ID_IO_EVENT);
+        sect = get_pseries_errorlog(elog, PSERIES_ELOG_SECT_ID_IO_EVENT);
         if (unlikely(!sect)) {
                 printk_once(KERN_WARNING "io_event_irq: RTAS extended event "
                             "log does not contain an IO Event section. "
diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index c442f2b1980f..0915b1ad66ce 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -809,8 +809,7 @@ machine_arch_initcall(pseries, find_existing_ddw_windows);
 static int query_ddw(struct pci_dev *dev, const u32 *ddw_avail,
                         struct ddw_query_response *query)
 {
-        struct device_node *dn;
-        struct pci_dn *pcidn;
+        struct eeh_dev *edev;
         u32 cfg_addr;
         u64 buid;
         int ret;
@@ -821,12 +820,12 @@ static int query_ddw(struct pci_dev *dev, const u32 *ddw_avail,
          * Retrieve them from the pci device, not the node with the
          * dma-window property
          */
-        dn = pci_device_to_OF_node(dev);
-        pcidn = PCI_DN(dn);
-        cfg_addr = pcidn->eeh_config_addr;
-        if (pcidn->eeh_pe_config_addr)
-                cfg_addr = pcidn->eeh_pe_config_addr;
-        buid = pcidn->phb->buid;
+        edev = pci_dev_to_eeh_dev(dev);
+        cfg_addr = edev->config_addr;
+        if (edev->pe_config_addr)
+                cfg_addr = edev->pe_config_addr;
+        buid = edev->phb->buid;
+
         ret = rtas_call(ddw_avail[0], 3, 5, (u32 *)query,
                   cfg_addr, BUID_HI(buid), BUID_LO(buid));
         dev_info(&dev->dev, "ibm,query-pe-dma-windows(%x) %x %x %x"
@@ -839,8 +838,7 @@ static int create_ddw(struct pci_dev *dev, const u32 *ddw_avail,
                         struct ddw_create_response *create, int page_shift,
                         int window_shift)
 {
-        struct device_node *dn;
-        struct pci_dn *pcidn;
+        struct eeh_dev *edev;
         u32 cfg_addr;
         u64 buid;
         int ret;
@@ -851,12 +849,11 @@ static int create_ddw(struct pci_dev *dev, const u32 *ddw_avail,
          * Retrieve them from the pci device, not the node with the
          * dma-window property
          */
-        dn = pci_device_to_OF_node(dev);
-        pcidn = PCI_DN(dn);
-        cfg_addr = pcidn->eeh_config_addr;
-        if (pcidn->eeh_pe_config_addr)
-                cfg_addr = pcidn->eeh_pe_config_addr;
-        buid = pcidn->phb->buid;
+        edev = pci_dev_to_eeh_dev(dev);
+        cfg_addr = edev->config_addr;
+        if (edev->pe_config_addr)
+                cfg_addr = edev->pe_config_addr;
+        buid = edev->phb->buid;
 
         do {
                 /* extra outputs are LIOBN and dma-addr (hi, lo) */
diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c
index 7bc73af6c7b9..5f3ef876ded2 100644
--- a/arch/powerpc/platforms/pseries/lpar.c
+++ b/arch/powerpc/platforms/pseries/lpar.c
@@ -41,6 +41,7 @@
 #include <asm/udbg.h>
 #include <asm/smp.h>
 #include <asm/trace.h>
+#include <asm/firmware.h>
 
 #include "plpar_wrappers.h"
 #include "pseries.h"
diff --git a/arch/powerpc/platforms/pseries/msi.c b/arch/powerpc/platforms/pseries/msi.c
index 38d24e7e7bb1..109fdb75578d 100644
--- a/arch/powerpc/platforms/pseries/msi.c
+++ b/arch/powerpc/platforms/pseries/msi.c
@@ -217,7 +217,7 @@ static struct device_node *find_pe_dn(struct pci_dev *dev, int *total)
         if (!dn)
                 return NULL;
 
-        dn = find_device_pe(dn);
+        dn = eeh_find_device_pe(dn);
         if (!dn)
                 return NULL;
 
diff --git a/arch/powerpc/platforms/pseries/pci_dlpar.c b/arch/powerpc/platforms/pseries/pci_dlpar.c
index 55d4ec1bd1ac..8b7bafa489c2 100644
--- a/arch/powerpc/platforms/pseries/pci_dlpar.c
+++ b/arch/powerpc/platforms/pseries/pci_dlpar.c
@@ -84,7 +84,7 @@ void pcibios_remove_pci_devices(struct pci_bus *bus)
         list_for_each_entry_safe(dev, tmp, &bus->devices, bus_list) {
                 pr_debug("     * Removing %s...\n", pci_name(dev));
                 eeh_remove_bus_device(dev);
-                pci_remove_bus_device(dev);
+                pci_stop_and_remove_bus_device(dev);
         }
 }
 EXPORT_SYMBOL_GPL(pcibios_remove_pci_devices);
@@ -147,6 +147,9 @@ struct pci_controller * __devinit init_phb_dynamic(struct device_node *dn)
 
         pci_devs_phb_init_dynamic(phb);
 
+        /* Create EEH devices for the PHB */
+        eeh_dev_phb_init_dynamic(phb);
+
         if (dn->child)
                 eeh_add_device_tree_early(dn);
 
diff --git a/arch/powerpc/platforms/pseries/phyp_dump.c b/arch/powerpc/platforms/pseries/phyp_dump.c
deleted file mode 100644
index 6e7742da0072..000000000000
--- a/arch/powerpc/platforms/pseries/phyp_dump.c
+++ /dev/null
@@ -1,513 +0,0 @@
-/*
- * Hypervisor-assisted dump
- *
- * Linas Vepstas, Manish Ahuja 2008
- * Copyright 2008 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/gfp.h>
-#include <linux/init.h>
-#include <linux/kobject.h>
-#include <linux/mm.h>
-#include <linux/of.h>
-#include <linux/pfn.h>
-#include <linux/swap.h>
-#include <linux/sysfs.h>
-
-#include <asm/page.h>
-#include <asm/phyp_dump.h>
-#include <asm/machdep.h>
-#include <asm/prom.h>
-#include <asm/rtas.h>
-
-/* Variables, used to communicate data between early boot and late boot */
-static struct phyp_dump phyp_dump_vars;
-struct phyp_dump *phyp_dump_info = &phyp_dump_vars;
-
-static int ibm_configure_kernel_dump;
-/* ------------------------------------------------- */
-/* RTAS interfaces to declare the dump regions */
-
-struct dump_section {
-        u32 dump_flags;
-        u16 source_type;
-        u16 error_flags;
-        u64 source_address;
-        u64 source_length;
-        u64 length_copied;
-        u64 destination_address;
-};
-
-struct phyp_dump_header {
-        u32 version;
-        u16 num_of_sections;
-        u16 status;
-
-        u32 first_offset_section;
-        u32 dump_disk_section;
-        u64 block_num_dd;
-        u64 num_of_blocks_dd;
-        u32 offset_dd;
-        u32 maxtime_to_auto;
-        /* No dump disk path string used */
-
-        struct dump_section cpu_data;
-        struct dump_section hpte_data;
-        struct dump_section kernel_data;
-};
-
-/* The dump header *must be* in low memory, so .bss it */
-static struct phyp_dump_header phdr;
-
-#define NUM_DUMP_SECTIONS       3
-#define DUMP_HEADER_VERSION     0x1
-#define DUMP_REQUEST_FLAG       0x1
-#define DUMP_SOURCE_CPU         0x0001
-#define DUMP_SOURCE_HPTE        0x0002
-#define DUMP_SOURCE_RMO         0x0011
-#define DUMP_ERROR_FLAG         0x2000
-#define DUMP_TRIGGERED          0x4000
-#define DUMP_PERFORMED          0x8000
-
-
-/**
- * init_dump_header() - initialize the header declaring a dump
- * Returns: length of dump save area.
- *
- * When the hypervisor saves crashed state, it needs to put
- * it somewhere. The dump header tells the hypervisor where
- * the data can be saved.
- */
-static unsigned long init_dump_header(struct phyp_dump_header *ph)
-{
-        unsigned long addr_offset = 0;
-
-        /* Set up the dump header */
-        ph->version = DUMP_HEADER_VERSION;
-        ph->num_of_sections = NUM_DUMP_SECTIONS;
-        ph->status = 0;
-
-        ph->first_offset_section =
-                (u32)offsetof(struct phyp_dump_header, cpu_data);
-        ph->dump_disk_section = 0;
-        ph->block_num_dd = 0;
-        ph->num_of_blocks_dd = 0;
-        ph->offset_dd = 0;
-
-        ph->maxtime_to_auto = 0; /* disabled */
-
-        /* The first two sections are mandatory */
-        ph->cpu_data.dump_flags = DUMP_REQUEST_FLAG;
-        ph->cpu_data.source_type = DUMP_SOURCE_CPU;
-        ph->cpu_data.source_address = 0;
-        ph->cpu_data.source_length = phyp_dump_info->cpu_state_size;
-        ph->cpu_data.destination_address = addr_offset;
-        addr_offset += phyp_dump_info->cpu_state_size;
-
-        ph->hpte_data.dump_flags = DUMP_REQUEST_FLAG;
-        ph->hpte_data.source_type = DUMP_SOURCE_HPTE;
-        ph->hpte_data.source_address = 0;
-        ph->hpte_data.source_length = phyp_dump_info->hpte_region_size;
-        ph->hpte_data.destination_address = addr_offset;
-        addr_offset += phyp_dump_info->hpte_region_size;
-
-        /* This section describes the low kernel region */
-        ph->kernel_data.dump_flags = DUMP_REQUEST_FLAG;
-        ph->kernel_data.source_type = DUMP_SOURCE_RMO;
-        ph->kernel_data.source_address = PHYP_DUMP_RMR_START;
-        ph->kernel_data.source_length = PHYP_DUMP_RMR_END;
-        ph->kernel_data.destination_address = addr_offset;
-        addr_offset += ph->kernel_data.source_length;
-
-        return addr_offset;
-}
-
-static void print_dump_header(const struct phyp_dump_header *ph)
-{
-#ifdef DEBUG
-        if (ph == NULL)
-                return;
-
-        printk(KERN_INFO "dump header:\n");
-        /* setup some ph->sections required */
-        printk(KERN_INFO "version = %d\n", ph->version);
-        printk(KERN_INFO "Sections = %d\n", ph->num_of_sections);
-        printk(KERN_INFO "Status = 0x%x\n", ph->status);
-
-        /* No ph->disk, so all should be set to 0 */
-        printk(KERN_INFO "Offset to first section 0x%x\n",
-                ph->first_offset_section);
-        printk(KERN_INFO "dump disk sections should be zero\n");
-        printk(KERN_INFO "dump disk section = %d\n", ph->dump_disk_section);
-        printk(KERN_INFO "block num = %lld\n", ph->block_num_dd);
-        printk(KERN_INFO "number of blocks = %lld\n", ph->num_of_blocks_dd);
-        printk(KERN_INFO "dump disk offset = %d\n", ph->offset_dd);
-        printk(KERN_INFO "Max auto time= %d\n", ph->maxtime_to_auto);
-
-        /*set cpu state and hpte states as well scratch pad area */
-        printk(KERN_INFO " CPU AREA\n");
-        printk(KERN_INFO "cpu dump_flags =%d\n", ph->cpu_data.dump_flags);
-        printk(KERN_INFO "cpu source_type =%d\n", ph->cpu_data.source_type);
-        printk(KERN_INFO "cpu error_flags =%d\n", ph->cpu_data.error_flags);
-        printk(KERN_INFO "cpu source_address =%llx\n",
-                ph->cpu_data.source_address);
-        printk(KERN_INFO "cpu source_length =%llx\n",
-                ph->cpu_data.source_length);
-        printk(KERN_INFO "cpu length_copied =%llx\n",
-                ph->cpu_data.length_copied);
-
-        printk(KERN_INFO " HPTE AREA\n");
-        printk(KERN_INFO "HPTE dump_flags =%d\n", ph->hpte_data.dump_flags);
-        printk(KERN_INFO "HPTE source_type =%d\n", ph->hpte_data.source_type);
-        printk(KERN_INFO "HPTE error_flags =%d\n", ph->hpte_data.error_flags);
-        printk(KERN_INFO "HPTE source_address =%llx\n",
-                ph->hpte_data.source_address);
-        printk(KERN_INFO "HPTE source_length =%llx\n",
-                ph->hpte_data.source_length);
-        printk(KERN_INFO "HPTE length_copied =%llx\n",
-                ph->hpte_data.length_copied);
-
-        printk(KERN_INFO " SRSD AREA\n");
-        printk(KERN_INFO "SRSD dump_flags =%d\n", ph->kernel_data.dump_flags);
-        printk(KERN_INFO "SRSD source_type =%d\n", ph->kernel_data.source_type);
-        printk(KERN_INFO "SRSD error_flags =%d\n", ph->kernel_data.error_flags);
-        printk(KERN_INFO "SRSD source_address =%llx\n",
-                ph->kernel_data.source_address);
-        printk(KERN_INFO "SRSD source_length =%llx\n",
-                ph->kernel_data.source_length);
-        printk(KERN_INFO "SRSD length_copied =%llx\n",
-                ph->kernel_data.length_copied);
-#endif
-}
-
-static ssize_t show_phyp_dump_active(struct kobject *kobj,
-                        struct kobj_attribute *attr, char *buf)
-{
-
-        /* create filesystem entry so kdump is phyp-dump aware */
-        return sprintf(buf, "%lx\n", phyp_dump_info->phyp_dump_at_boot);
-}
-
-static struct kobj_attribute pdl = __ATTR(phyp_dump_active, 0600,
-                                        show_phyp_dump_active,
-                                        NULL);
-
-static void register_dump_area(struct phyp_dump_header *ph, unsigned long addr)
-{
-        int rc;
-
-        /* Add addr value if not initialized before */
-        if (ph->cpu_data.destination_address == 0) {
-                ph->cpu_data.destination_address += addr;
-                ph->hpte_data.destination_address += addr;
-                ph->kernel_data.destination_address += addr;
-        }
-
-        /* ToDo Invalidate kdump and free memory range. */
-
-        do {
-                rc = rtas_call(ibm_configure_kernel_dump, 3, 1, NULL,
-                                1, ph, sizeof(struct phyp_dump_header));
-        } while (rtas_busy_delay(rc));
-
-        if (rc) {
-                printk(KERN_ERR "phyp-dump: unexpected error (%d) on "
-                                                "register\n", rc);
-                print_dump_header(ph);
-                return;
-        }
-
-        rc = sysfs_create_file(kernel_kobj, &pdl.attr);
-        if (rc)
-                printk(KERN_ERR "phyp-dump: unable to create sysfs"
-                                " file (%d)\n", rc);
-}
-
-static
-void invalidate_last_dump(struct phyp_dump_header *ph, unsigned long addr)
-{
-        int rc;
-
-        /* Add addr value if not initialized before */
-        if (ph->cpu_data.destination_address == 0) {
-                ph->cpu_data.destination_address += addr;
-                ph->hpte_data.destination_address += addr;
-                ph->kernel_data.destination_address += addr;
-        }
-
-        do {
-                rc = rtas_call(ibm_configure_kernel_dump, 3, 1, NULL,
-                                2, ph, sizeof(struct phyp_dump_header));
-        } while (rtas_busy_delay(rc));
-
-        if (rc) {
-                printk(KERN_ERR "phyp-dump: unexpected error (%d) "
-                                                "on invalidate\n", rc);
-                print_dump_header(ph);
-        }
-}
-
-/* ------------------------------------------------- */
-/**
- * release_memory_range -- release memory previously memblock_reserved
- * @start_pfn: starting physical frame number
- * @nr_pages: number of pages to free.
- *
- * This routine will release memory that had been previously
- * memblock_reserved in early boot. The released memory becomes
- * available for genreal use.
- */
-static void release_memory_range(unsigned long start_pfn,
-                        unsigned long nr_pages)
-{
-        struct page *rpage;
-        unsigned long end_pfn;
-        long i;
-
-        end_pfn = start_pfn + nr_pages;
-
-        for (i = start_pfn; i <= end_pfn; i++) {
-                rpage = pfn_to_page(i);
-                if (PageReserved(rpage)) {
-                        ClearPageReserved(rpage);
-                        init_page_count(rpage);
-                        __free_page(rpage);
-                        totalram_pages++;
-                }
-        }
-}
-
-/**
- * track_freed_range -- Counts the range being freed.
- * Once the counter goes to zero, it re-registers dump for
- * future use.
- */
-static void
-track_freed_range(unsigned long addr, unsigned long length)
-{
-        static unsigned long scratch_area_size, reserved_area_size;
-
-        if (addr < phyp_dump_info->init_reserve_start)
-                return;
-
-        if ((addr >= phyp_dump_info->init_reserve_start) &&
-            (addr <= phyp_dump_info->init_reserve_start +
-             phyp_dump_info->init_reserve_size))
-                reserved_area_size += length;
-
-        if ((addr >= phyp_dump_info->reserved_scratch_addr) &&
-            (addr <= phyp_dump_info->reserved_scratch_addr +
-             phyp_dump_info->reserved_scratch_size))
-                scratch_area_size += length;
-
-        if ((reserved_area_size == phyp_dump_info->init_reserve_size) &&
-            (scratch_area_size == phyp_dump_info->reserved_scratch_size)) {
-
-                invalidate_last_dump(&phdr,
-                                phyp_dump_info->reserved_scratch_addr);
-                register_dump_area(&phdr,
-                                phyp_dump_info->reserved_scratch_addr);
-        }
-}
-
-/* ------------------------------------------------- */
-/**
- * sysfs_release_region -- sysfs interface to release memory range.
- *
- * Usage:
- *   "echo <start addr> <length> > /sys/kernel/release_region"
- *
- * Example:
- *   "echo 0x40000000 0x10000000 > /sys/kernel/release_region"
- *
- * will release 256MB starting at 1GB.
- */
-static ssize_t store_release_region(struct kobject *kobj,
-                                struct kobj_attribute *attr,
-                                const char *buf, size_t count)
-{
-        unsigned long start_addr, length, end_addr;
-        unsigned long start_pfn, nr_pages;
-        ssize_t ret;
-
-        ret = sscanf(buf, "%lx %lx", &start_addr, &length);
-        if (ret != 2)
-                return -EINVAL;
-
-        track_freed_range(start_addr, length);
-
-        /* Range-check - don't free any reserved memory that
-         * wasn't reserved for phyp-dump */
-        if (start_addr < phyp_dump_info->init_reserve_start)
-                start_addr = phyp_dump_info->init_reserve_start;
-
-        end_addr = phyp_dump_info->init_reserve_start +
-                        phyp_dump_info->init_reserve_size;
-        if (start_addr+length > end_addr)
-                length = end_addr - start_addr;
-
-        /* Release the region of memory assed in by user */
-        start_pfn = PFN_DOWN(start_addr);
-        nr_pages = PFN_DOWN(length);
-        release_memory_range(start_pfn, nr_pages);
-
-        return count;
-}
-
-static ssize_t show_release_region(struct kobject *kobj,
-                        struct kobj_attribute *attr, char *buf)
-{
-        u64 second_addr_range;
-
-        /* total reserved size - start of scratch area */
-        second_addr_range = phyp_dump_info->init_reserve_size -
-                                phyp_dump_info->reserved_scratch_size;
-        return sprintf(buf, "CPU:0x%llx-0x%llx: HPTE:0x%llx-0x%llx:"
-                            " DUMP:0x%llx-0x%llx, 0x%lx-0x%llx:\n",
-                phdr.cpu_data.destination_address,
-                phdr.cpu_data.length_copied,
-                phdr.hpte_data.destination_address,
-                phdr.hpte_data.length_copied,
-                phdr.kernel_data.destination_address,
-                phdr.kernel_data.length_copied,
-                phyp_dump_info->init_reserve_start,
-                second_addr_range);
-}
-
-static struct kobj_attribute rr = __ATTR(release_region, 0600,
-                                        show_release_region,
-                                        store_release_region);
-
-static int __init phyp_dump_setup(void)
-{
-        struct device_node *rtas;
-        const struct phyp_dump_header *dump_header = NULL;
-        unsigned long dump_area_start;
-        unsigned long dump_area_length;
-        int header_len = 0;
-        int rc;
-
-        /* If no memory was reserved in early boot, there is nothing to do */
-        if (phyp_dump_info->init_reserve_size == 0)
-                return 0;
-
-        /* Return if phyp dump not supported */
-        if (!phyp_dump_info->phyp_dump_configured)
-                return -ENOSYS;
-
-        /* Is there dump data waiting for us? If there isn't,
-         * then register a new dump area, and release all of
-         * the rest of the reserved ram.
-         *
-         * The /rtas/ibm,kernel-dump rtas node is present only
-         * if there is dump data waiting for us.
-         */
-        rtas = of_find_node_by_path("/rtas");
-        if (rtas) {
-                dump_header = of_get_property(rtas, "ibm,kernel-dump",
-                                                &header_len);
-                of_node_put(rtas);
-        }
-
-        ibm_configure_kernel_dump = rtas_token("ibm,configure-kernel-dump");
-
-        print_dump_header(dump_header);
-        dump_area_length = init_dump_header(&phdr);
-        /* align down */
-        dump_area_start = phyp_dump_info->init_reserve_start & PAGE_MASK;
-
-        if (dump_header == NULL) {
-                register_dump_area(&phdr, dump_area_start);
-                return 0;
-        }
-
-        /* re-register the dump area, if old dump was invalid */
-        if ((dump_header) && (dump_header->status & DUMP_ERROR_FLAG)) {
-                invalidate_last_dump(&phdr, dump_area_start);
-                register_dump_area(&phdr, dump_area_start);
-                return 0;
-        }
-
-        if (dump_header) {
-                phyp_dump_info->reserved_scratch_addr =
-                                dump_header->cpu_data.destination_address;
-                phyp_dump_info->reserved_scratch_size =
-                                dump_header->cpu_data.source_length +
-                                dump_header->hpte_data.source_length +
-                                dump_header->kernel_data.source_length;
-        }
-
-        /* Should we create a dump_subsys, analogous to s390/ipl.c ? */
-        rc = sysfs_create_file(kernel_kobj, &rr.attr);
-        if (rc)
-                printk(KERN_ERR "phyp-dump: unable to create sysfs file (%d)\n",
-                                                                        rc);
-
-        /* ToDo: re-register the dump area, for next time. */
-        return 0;
-}
-machine_subsys_initcall(pseries, phyp_dump_setup);
-
-int __init early_init_dt_scan_phyp_dump(unsigned long node,
-                const char *uname, int depth, void *data)
-{
-        const unsigned int *sizes;
-
-        phyp_dump_info->phyp_dump_configured = 0;
-        phyp_dump_info->phyp_dump_is_active = 0;
-
-        if (depth != 1 || strcmp(uname, "rtas") != 0)
-                return 0;
-
-        if (of_get_flat_dt_prop(node, "ibm,configure-kernel-dump", NULL))
-                phyp_dump_info->phyp_dump_configured++;
-
-        if (of_get_flat_dt_prop(node, "ibm,dump-kernel", NULL))
-                phyp_dump_info->phyp_dump_is_active++;
-
-        sizes = of_get_flat_dt_prop(node, "ibm,configure-kernel-dump-sizes",
-                                    NULL);
-        if (!sizes)
-                return 0;
-
-        if (sizes[0] == 1)
-                phyp_dump_info->cpu_state_size = *((unsigned long *)&sizes[1]);
-
-        if (sizes[3] == 2)
-                phyp_dump_info->hpte_region_size =
-                                                *((unsigned long *)&sizes[4]);
-        return 1;
-}
-
-/* Look for phyp_dump= cmdline option */
-static int __init early_phyp_dump_enabled(char *p)
-{
-        phyp_dump_info->phyp_dump_at_boot = 1;
-
-        if (!p)
-                return 0;
-
-        if (strncmp(p, "1", 1) == 0)
-                phyp_dump_info->phyp_dump_at_boot = 1;
-        else if (strncmp(p, "0", 1) == 0)
-                phyp_dump_info->phyp_dump_at_boot = 0;
-
-        return 0;
-}
-early_param("phyp_dump", early_phyp_dump_enabled);
-
-/* Look for phyp_dump_reserve_size= cmdline option */
-static int __init early_phyp_dump_reserve_size(char *p)
-{
-        if (p)
-                phyp_dump_info->reserve_bootvar = memparse(p, &p);
-
-        return 0;
-}
-early_param("phyp_dump_reserve_size", early_phyp_dump_reserve_size);
diff --git a/arch/powerpc/platforms/pseries/processor_idle.c b/arch/powerpc/platforms/pseries/processor_idle.c
index 085fd3f45ad2..a12e95af6933 100644
--- a/arch/powerpc/platforms/pseries/processor_idle.c
+++ b/arch/powerpc/platforms/pseries/processor_idle.c
@@ -96,6 +96,20 @@ out:
         return index;
 }
 
+static void check_and_cede_processor(void)
+{
+        /*
+         * Interrupts are soft-disabled at this point,
+         * but not hard disabled. So an interrupt might have
+         * occurred before entering NAP, and would be potentially
+         * lost (edge events, decrementer events, etc...) unless
+         * we first hard disable then check.
+         */
+        hard_irq_disable();
+        if (get_paca()->irq_happened == 0)
+                cede_processor();
+}
+
 static int dedicated_cede_loop(struct cpuidle_device *dev,
                                 struct cpuidle_driver *drv,
                                 int index)
@@ -108,7 +122,7 @@ static int dedicated_cede_loop(struct cpuidle_device *dev,
 
         ppc64_runlatch_off();
         HMT_medium();
-        cede_processor();
+        check_and_cede_processor();
 
         get_lppaca()->donate_dedicated_cpu = 0;
         dev->last_residency =
@@ -132,7 +146,7 @@ static int shared_cede_loop(struct cpuidle_device *dev,
          * processor. When returning here, external interrupts
          * are enabled.
          */
-        cede_processor();
+        check_and_cede_processor();
 
         dev->last_residency =
                 (int)idle_loop_epilog(in_purr, kt_before);
diff --git a/arch/powerpc/platforms/pseries/ras.c b/arch/powerpc/platforms/pseries/ras.c
index 086d2ae4e06a..c4dfccd3a3d9 100644
--- a/arch/powerpc/platforms/pseries/ras.c
+++ b/arch/powerpc/platforms/pseries/ras.c
@@ -16,37 +16,15 @@
  * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
  */
 
-/* Change Activity:
- * 2001/09/21 : engebret : Created with minimal EPOW and HW exception support.
- * End Change Activity
- */
-
-#include <linux/errno.h>
-#include <linux/threads.h>
-#include <linux/kernel_stat.h>
-#include <linux/signal.h>
 #include <linux/sched.h>
-#include <linux/ioport.h>
 #include <linux/interrupt.h>
-#include <linux/timex.h>
-#include <linux/init.h>
-#include <linux/delay.h>
 #include <linux/irq.h>
-#include <linux/random.h>
-#include <linux/sysrq.h>
-#include <linux/bitops.h>
-
-#include <asm/uaccess.h>
-#include <asm/system.h>
-#include <asm/io.h>
-#include <asm/pgtable.h>
-#include <asm/irq.h>
-#include <asm/cache.h>
-#include <asm/prom.h>
-#include <asm/ptrace.h>
+#include <linux/of.h>
+#include <linux/fs.h>
+#include <linux/reboot.h>
+
 #include <asm/machdep.h>
 #include <asm/rtas.h>
-#include <asm/udbg.h>
 #include <asm/firmware.h>
 
 #include "pseries.h"
@@ -57,7 +35,6 @@ static DEFINE_SPINLOCK(ras_log_buf_lock);
 static char global_mce_data_buf[RTAS_ERROR_LOG_MAX];
 static DEFINE_PER_CPU(__u64, mce_data_buf);
 
-static int ras_get_sensor_state_token;
 static int ras_check_exception_token;
 
 #define EPOW_SENSOR_TOKEN       9
@@ -75,7 +52,6 @@ static int __init init_ras_IRQ(void)
 {
         struct device_node *np;
 
-        ras_get_sensor_state_token = rtas_token("get-sensor-state");
         ras_check_exception_token = rtas_token("check-exception");
 
         /* Internal Errors */
@@ -95,26 +71,126 @@ static int __init init_ras_IRQ(void)
 
         return 0;
 }
-__initcall(init_ras_IRQ);
+subsys_initcall(init_ras_IRQ);
 
-/*
- * Handle power subsystem events (EPOW).
- *
- * Presently we just log the event has occurred.  This should be fixed
- * to examine the type of power failure and take appropriate action where
- * the time horizon permits something useful to be done.
- */
+#define EPOW_SHUTDOWN_NORMAL                            1
+#define EPOW_SHUTDOWN_ON_UPS                            2
+#define EPOW_SHUTDOWN_LOSS_OF_CRITICAL_FUNCTIONS        3
+#define EPOW_SHUTDOWN_AMBIENT_TEMPERATURE_TOO_HIGH      4
+
+static void handle_system_shutdown(char event_modifier)
+{
+        switch (event_modifier) {
+        case EPOW_SHUTDOWN_NORMAL:
+                pr_emerg("Firmware initiated power off");
+                orderly_poweroff(1);
+                break;
+
+        case EPOW_SHUTDOWN_ON_UPS:
+                pr_emerg("Loss of power reported by firmware, system is "
+                        "running on UPS/battery");
+                break;
+
+        case EPOW_SHUTDOWN_LOSS_OF_CRITICAL_FUNCTIONS:
+                pr_emerg("Loss of system critical functions reported by "
+                        "firmware");
+                pr_emerg("Check RTAS error log for details");
+                orderly_poweroff(1);
+                break;
+
+        case EPOW_SHUTDOWN_AMBIENT_TEMPERATURE_TOO_HIGH:
+                pr_emerg("Ambient temperature too high reported by firmware");
+                pr_emerg("Check RTAS error log for details");
+                orderly_poweroff(1);
+                break;
+
+        default:
+                pr_err("Unknown power/cooling shutdown event (modifier %d)",
+                        event_modifier);
+        }
+}
+
+struct epow_errorlog {
+        unsigned char sensor_value;
+        unsigned char event_modifier;
+        unsigned char extended_modifier;
+        unsigned char reserved;
+        unsigned char platform_reason;
+};
+
+#define EPOW_RESET                      0
+#define EPOW_WARN_COOLING               1
+#define EPOW_WARN_POWER                 2
+#define EPOW_SYSTEM_SHUTDOWN            3
+#define EPOW_SYSTEM_HALT                4
+#define EPOW_MAIN_ENCLOSURE             5
+#define EPOW_POWER_OFF                  7
+
+void rtas_parse_epow_errlog(struct rtas_error_log *log)
+{
+        struct pseries_errorlog *pseries_log;
+        struct epow_errorlog *epow_log;
+        char action_code;
+        char modifier;
+
+        pseries_log = get_pseries_errorlog(log, PSERIES_ELOG_SECT_ID_EPOW);
+        if (pseries_log == NULL)
+                return;
+
+        epow_log = (struct epow_errorlog *)pseries_log->data;
+        action_code = epow_log->sensor_value & 0xF;     /* bottom 4 bits */
+        modifier = epow_log->event_modifier & 0xF;      /* bottom 4 bits */
+
+        switch (action_code) {
+        case EPOW_RESET:
+                pr_err("Non critical power or cooling issue cleared");
+                break;
+
+        case EPOW_WARN_COOLING:
+                pr_err("Non critical cooling issue reported by firmware");
+                pr_err("Check RTAS error log for details");
+                break;
+
+        case EPOW_WARN_POWER:
+                pr_err("Non critical power issue reported by firmware");
+                pr_err("Check RTAS error log for details");
+                break;
+
+        case EPOW_SYSTEM_SHUTDOWN:
+                handle_system_shutdown(epow_log->event_modifier);
+                break;
+
+        case EPOW_SYSTEM_HALT:
+                pr_emerg("Firmware initiated power off");
+                orderly_poweroff(1);
+                break;
+
+        case EPOW_MAIN_ENCLOSURE:
+        case EPOW_POWER_OFF:
+                pr_emerg("Critical power/cooling issue reported by firmware");
+                pr_emerg("Check RTAS error log for details");
+                pr_emerg("Immediate power off");
+                emergency_sync();
+                kernel_power_off();
+                break;
+
+        default:
+                pr_err("Unknown power/cooling event (action code %d)",
+                        action_code);
+        }
+}
+
+/* Handle environmental and power warning (EPOW) interrupts. */
 static irqreturn_t ras_epow_interrupt(int irq, void *dev_id)
 {
-        int status = 0xdeadbeef;
-        int state = 0;
+        int status;
+        int state;
         int critical;
 
-        status = rtas_call(ras_get_sensor_state_token, 2, 2, &state,
-                           EPOW_SENSOR_TOKEN, EPOW_SENSOR_INDEX);
+        status = rtas_get_sensor(EPOW_SENSOR_TOKEN, EPOW_SENSOR_INDEX, &state);
 
         if (state > 3)
-                critical = 1;  /* Time Critical */
+                critical = 1;           /* Time Critical */
         else
                 critical = 0;
 
@@ -123,18 +199,14 @@ static irqreturn_t ras_epow_interrupt(int irq, void *dev_id)
         status = rtas_call(ras_check_exception_token, 6, 1, NULL,
                            RTAS_VECTOR_EXTERNAL_INTERRUPT,
                            virq_to_hw(irq),
-                           RTAS_EPOW_WARNING | RTAS_POWERMGM_EVENTS,
+                           RTAS_EPOW_WARNING,
                            critical, __pa(&ras_log_buf),
                                 rtas_get_error_log_max());
 
-        udbg_printf("EPOW <0x%lx 0x%x 0x%x>\n",
-                    *((unsigned long *)&ras_log_buf), status, state);
-        printk(KERN_WARNING "EPOW <0x%lx 0x%x 0x%x>\n",
-               *((unsigned long *)&ras_log_buf), status, state);
-
-        /* format and print the extended information */
         log_error(ras_log_buf, ERR_TYPE_RTAS_LOG, 0);
 
+        rtas_parse_epow_errlog((struct rtas_error_log *)ras_log_buf);
+
         spin_unlock(&ras_log_buf_lock);
         return IRQ_HANDLED;
 }
@@ -150,7 +222,7 @@ static irqreturn_t ras_epow_interrupt(int irq, void *dev_id)
 static irqreturn_t ras_error_interrupt(int irq, void *dev_id)
 {
         struct rtas_error_log *rtas_elog;
-        int status = 0xdeadbeef;
+        int status;
         int fatal;
 
         spin_lock(&ras_log_buf_lock);
@@ -158,7 +230,7 @@ static irqreturn_t ras_error_interrupt(int irq, void *dev_id)
         status = rtas_call(ras_check_exception_token, 6, 1, NULL,
                            RTAS_VECTOR_EXTERNAL_INTERRUPT,
                            virq_to_hw(irq),
-                           RTAS_INTERNAL_ERROR, 1 /*Time Critical */,
+                           RTAS_INTERNAL_ERROR, 1 /* Time Critical */,
                            __pa(&ras_log_buf),
                                 rtas_get_error_log_max());
 
@@ -173,24 +245,13 @@ static irqreturn_t ras_error_interrupt(int irq, void *dev_id)
         log_error(ras_log_buf, ERR_TYPE_RTAS_LOG, fatal);
 
         if (fatal) {
-                udbg_printf("Fatal HW Error <0x%lx 0x%x>\n",
-                            *((unsigned long *)&ras_log_buf), status);
-                printk(KERN_EMERG "Error: Fatal hardware error <0x%lx 0x%x>\n",
-                       *((unsigned long *)&ras_log_buf), status);
-
-#ifndef DEBUG_RTAS_POWER_OFF
-                /* Don't actually power off when debugging so we can test
-                 * without actually failing while injecting errors.
-                 * Error data will not be logged to syslog.
-                 */
-                ppc_md.power_off();
-#endif
+                pr_emerg("Fatal hardware error reported by firmware");
+                pr_emerg("Check RTAS error log for details");
+                pr_emerg("Immediate power off");
+                emergency_sync();
+                kernel_power_off();
         } else {
-                udbg_printf("Recoverable HW Error <0x%lx 0x%x>\n",
-                            *((unsigned long *)&ras_log_buf), status);
-                printk(KERN_WARNING
-                       "Warning: Recoverable hardware error <0x%lx 0x%x>\n",
-                       *((unsigned long *)&ras_log_buf), status);
+                pr_err("Recoverable hardware error reported by firmware");
         }
 
         spin_unlock(&ras_log_buf_lock);
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index f79f1278dfca..51ecac920dd8 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -190,9 +190,8 @@ static void __init pseries_mpic_init_IRQ(void)
         BUG_ON(openpic_addr == 0);
 
         /* Setup the openpic driver */
-        mpic = mpic_alloc(pSeries_mpic_node, openpic_addr, 0,
-                          16, 250, /* isu size, irq count */
-                          " MPIC     ");
+        mpic = mpic_alloc(pSeries_mpic_node, openpic_addr,
+                        MPIC_NO_RESET, 16, 0, " MPIC     ");
         BUG_ON(mpic == NULL);
 
         /* Add ISUs */
@@ -261,8 +260,12 @@ static int pci_dn_reconfig_notifier(struct notifier_block *nb, unsigned long act
         switch (action) {
         case PSERIES_RECONFIG_ADD:
                 pci = np->parent->data;
-                if (pci)
+                if (pci) {
                         update_dn_pci_info(np, pci->phb);
+
+                        /* Create EEH device for the OF node */
+                        eeh_dev_init(np, pci->phb);
+                }
                 break;
         default:
                 err = NOTIFY_DONE;
@@ -380,8 +383,12 @@ static void __init pSeries_setup_arch(void)
 
         fwnmi_init();
 
+        /* By default, only probe PCI (can be overriden by rtas_pci) */
+        pci_add_flags(PCI_PROBE_ONLY);
+
         /* Find and initialize PCI host bridges */
         init_pci_config_tokens();
+        eeh_pseries_init();
         find_and_init_phbs();
         pSeries_reconfig_notifier_register(&pci_dn_reconfig_nb);
         eeh_init();
diff --git a/arch/powerpc/platforms/pseries/suspend.c b/arch/powerpc/platforms/pseries/suspend.c
index b84a8b2238dd..47226e04126d 100644
--- a/arch/powerpc/platforms/pseries/suspend.c
+++ b/arch/powerpc/platforms/pseries/suspend.c
@@ -24,6 +24,7 @@
 #include <asm/machdep.h>
 #include <asm/mmu.h>
 #include <asm/rtas.h>
+#include <asm/topology.h>
 
 static u64 stream_id;
 static struct device suspend_dev;
@@ -138,8 +139,11 @@ static ssize_t store_hibernate(struct device *dev,
                         ssleep(1);
         } while (rc == -EAGAIN);
 
-        if (!rc)
+        if (!rc) {
+                stop_topology_update();
                 rc = pm_suspend(PM_SUSPEND_MEM);
+                start_topology_update();
+        }
 
         stream_id = 0;
 
diff --git a/arch/powerpc/platforms/wsp/Kconfig b/arch/powerpc/platforms/wsp/Kconfig
index 57d22a2f4ba9..79d2225b7608 100644
--- a/arch/powerpc/platforms/wsp/Kconfig
+++ b/arch/powerpc/platforms/wsp/Kconfig
@@ -25,6 +25,7 @@ config PPC_CHROMA
         bool "PowerEN PCIe Chroma Card"
         select EPAPR_BOOT
         select PPC_WSP
+        select OF_DYNAMIC
         default y
 
 endmenu
diff --git a/arch/powerpc/platforms/wsp/ics.c b/arch/powerpc/platforms/wsp/ics.c
index 576874392543..97fe82ee8633 100644
--- a/arch/powerpc/platforms/wsp/ics.c
+++ b/arch/powerpc/platforms/wsp/ics.c
@@ -346,7 +346,7 @@ static int wsp_chip_set_affinity(struct irq_data *d,
          * For the moment only implement delivery to all cpus or one cpu.
          * Get current irq_server for the given irq
          */
-        ret = cache_hwirq_map(ics, d->irq, cpumask);
+        ret = cache_hwirq_map(ics, hw_irq, cpumask);
         if (ret == -1) {
                 char cpulist[128];
                 cpumask_scnprintf(cpulist, sizeof(cpulist), cpumask);
diff --git a/arch/powerpc/platforms/wsp/opb_pic.c b/arch/powerpc/platforms/wsp/opb_pic.c
index 19f353dfcd03..cb565bf93650 100644
--- a/arch/powerpc/platforms/wsp/opb_pic.c
+++ b/arch/powerpc/platforms/wsp/opb_pic.c
@@ -30,7 +30,7 @@
 static int opb_index = 0;
 
 struct opb_pic {
-        struct irq_host *host;
+        struct irq_domain *host;
         void *regs;
         int index;
         spinlock_t lock;
@@ -179,7 +179,7 @@ static struct irq_chip opb_irq_chip = {
         .irq_set_type   = opb_set_irq_type
 };
 
-static int opb_host_map(struct irq_host *host, unsigned int virq,
+static int opb_host_map(struct irq_domain *host, unsigned int virq,
                 irq_hw_number_t hwirq)
 {
         struct opb_pic *opb;
@@ -196,20 +196,9 @@ static int opb_host_map(struct irq_host *host, unsigned int virq,
         return 0;
 }
 
-static int opb_host_xlate(struct irq_host *host, struct device_node *dn,
-                const u32 *intspec, unsigned int intsize,
-                irq_hw_number_t *out_hwirq, unsigned int *out_type)
-{
-        /* Interrupt size must == 2 */
-        BUG_ON(intsize != 2);
-        *out_hwirq = intspec[0];
-        *out_type = intspec[1];
-        return 0;
-}
-
-static struct irq_host_ops opb_host_ops = {
+static const struct irq_domain_ops opb_host_ops = {
         .map = opb_host_map,
-        .xlate = opb_host_xlate,
+        .xlate = irq_domain_xlate_twocell,
 };
 
 irqreturn_t opb_irq_handler(int irq, void *private)
@@ -263,13 +252,11 @@ struct opb_pic *opb_pic_init_one(struct device_node *dn)
                 goto free_opb;
         }
 
-        /* Allocate an irq host so that Linux knows that despite only
+        /* Allocate an irq domain so that Linux knows that despite only
          * having one interrupt to issue, we're the controller for multiple
          * hardware IRQs, so later we can lookup their virtual IRQs. */
 
-        opb->host = irq_alloc_host(dn, IRQ_HOST_MAP_LINEAR,
-                        OPB_NR_IRQS, &opb_host_ops, -1);
-
+        opb->host = irq_domain_add_linear(dn, OPB_NR_IRQS, &opb_host_ops, opb);
         if (!opb->host) {
                 printk(KERN_ERR "opb: Failed to allocate IRQ host!\n");
                 goto free_regs;
@@ -277,7 +264,6 @@ struct opb_pic *opb_pic_init_one(struct device_node *dn)
 
         opb->index = opb_index++;
         spin_lock_init(&opb->lock);
-        opb->host->host_data = opb;
 
         /* Disable all interrupts by default */
         opb_out(opb, OPB_MLSASIER, 0);
diff --git a/arch/powerpc/platforms/wsp/smp.c b/arch/powerpc/platforms/wsp/smp.c
index 71bd105f3863..0ba103ae83a5 100644
--- a/arch/powerpc/platforms/wsp/smp.c
+++ b/arch/powerpc/platforms/wsp/smp.c
@@ -71,7 +71,7 @@ int __devinit smp_a2_kick_cpu(int nr)
 
 static int __init smp_a2_probe(void)
 {
-        return cpus_weight(cpu_possible_map);
+        return num_possible_cpus();
 }
 
 static struct smp_ops_t a2_smp_ops = {
diff --git a/arch/powerpc/platforms/wsp/wsp_pci.c b/arch/powerpc/platforms/wsp/wsp_pci.c
index e0262cd0e2d3..763014cd1e62 100644
--- a/arch/powerpc/platforms/wsp/wsp_pci.c
+++ b/arch/powerpc/platforms/wsp/wsp_pci.c
@@ -468,15 +468,15 @@ static void __init wsp_pcie_configure_hw(struct pci_controller *hose)
 #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 */
+        /*
+         * Some WSP variants  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 */
@@ -682,7 +682,6 @@ static int __init wsp_setup_one_phb(struct device_node *np)
         /* 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;
diff --git a/arch/powerpc/sysdev/Kconfig b/arch/powerpc/sysdev/Kconfig
index 7b4df37ac381..a84fecf63c4d 100644
--- a/arch/powerpc/sysdev/Kconfig
+++ b/arch/powerpc/sysdev/Kconfig
@@ -29,3 +29,7 @@ config SCOM_DEBUGFS
         bool "Expose SCOM controllers via debugfs"
         depends on PPC_SCOM
         default n
+
+config GE_FPGA
+        bool
+        default n
diff --git a/arch/powerpc/sysdev/Makefile b/arch/powerpc/sysdev/Makefile
index 5e37b4717864..1bd7ecb24620 100644
--- a/arch/powerpc/sysdev/Makefile
+++ b/arch/powerpc/sysdev/Makefile
@@ -4,6 +4,8 @@ ccflags-$(CONFIG_PPC64)		:= -mno-minimal-toc
 
 mpic-msi-obj-$(CONFIG_PCI_MSI)  += mpic_msi.o mpic_u3msi.o mpic_pasemi_msi.o
 obj-$(CONFIG_MPIC)              += mpic.o $(mpic-msi-obj-y)
+mpic-msgr-obj-$(CONFIG_MPIC_MSGR)       += mpic_msgr.o
+obj-$(CONFIG_MPIC)              += mpic.o $(mpic-msi-obj-y) $(mpic-msgr-obj-y)
 obj-$(CONFIG_PPC_EPAPR_HV_PIC)  += ehv_pic.o
 fsl-msi-obj-$(CONFIG_PCI_MSI)   += fsl_msi.o
 obj-$(CONFIG_PPC_MSI_BITMAP)    += msi_bitmap.o
@@ -65,3 +67,5 @@ obj-$(CONFIG_PPC_SCOM)		+= scom.o
 subdir-ccflags-$(CONFIG_PPC_WERROR) := -Werror
 
 obj-$(CONFIG_PPC_XICS)          += xics/
+
+obj-$(CONFIG_GE_FPGA)           += ge/
diff --git a/arch/powerpc/sysdev/cpm1.c b/arch/powerpc/sysdev/cpm1.c
index 5d7d59a43c4c..d4fa03f2b6ac 100644
--- a/arch/powerpc/sysdev/cpm1.c
+++ b/arch/powerpc/sysdev/cpm1.c
@@ -54,7 +54,7 @@ cpm8xx_t __iomem *cpmp;  /* Pointer to comm processor space */
 immap_t __iomem *mpc8xx_immr;
 static cpic8xx_t __iomem *cpic_reg;
 
-static struct irq_host *cpm_pic_host;
+static struct irq_domain *cpm_pic_host;
 
 static void cpm_mask_irq(struct irq_data *d)
 {
@@ -98,7 +98,7 @@ int cpm_get_irq(void)
         return irq_linear_revmap(cpm_pic_host, cpm_vec);
 }
 
-static int cpm_pic_host_map(struct irq_host *h, unsigned int virq,
+static int cpm_pic_host_map(struct irq_domain *h, unsigned int virq,
                           irq_hw_number_t hw)
 {
         pr_debug("cpm_pic_host_map(%d, 0x%lx)\n", virq, hw);
@@ -123,7 +123,7 @@ static struct irqaction cpm_error_irqaction = {
         .name = "error",
 };
 
-static struct irq_host_ops cpm_pic_host_ops = {
+static const struct irq_domain_ops cpm_pic_host_ops = {
         .map = cpm_pic_host_map,
 };
 
@@ -164,8 +164,7 @@ unsigned int cpm_pic_init(void)
 
         out_be32(&cpic_reg->cpic_cimr, 0);
 
-        cpm_pic_host = irq_alloc_host(np, IRQ_HOST_MAP_LINEAR,
-                                      64, &cpm_pic_host_ops, 64);
+        cpm_pic_host = irq_domain_add_linear(np, 64, &cpm_pic_host_ops, NULL);
         if (cpm_pic_host == NULL) {
                 printk(KERN_ERR "CPM2 PIC: failed to allocate irq host!\n");
                 sirq = NO_IRQ;
diff --git a/arch/powerpc/sysdev/cpm2_pic.c b/arch/powerpc/sysdev/cpm2_pic.c
index bcab50e2a9eb..d3be961e2ae7 100644
--- a/arch/powerpc/sysdev/cpm2_pic.c
+++ b/arch/powerpc/sysdev/cpm2_pic.c
@@ -50,7 +50,7 @@
 
 static intctl_cpm2_t __iomem *cpm2_intctl;
 
-static struct irq_host *cpm2_pic_host;
+static struct irq_domain *cpm2_pic_host;
 #define NR_MASK_WORDS   ((NR_IRQS + 31) / 32)
 static unsigned long ppc_cached_irq_mask[NR_MASK_WORDS];
 
@@ -214,7 +214,7 @@ unsigned int cpm2_get_irq(void)
         return irq_linear_revmap(cpm2_pic_host, irq);
 }
 
-static int cpm2_pic_host_map(struct irq_host *h, unsigned int virq,
+static int cpm2_pic_host_map(struct irq_domain *h, unsigned int virq,
                           irq_hw_number_t hw)
 {
         pr_debug("cpm2_pic_host_map(%d, 0x%lx)\n", virq, hw);
@@ -224,21 +224,9 @@ static int cpm2_pic_host_map(struct irq_host *h, unsigned int virq,
         return 0;
 }
 
-static int cpm2_pic_host_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)
-{
-        *out_hwirq = intspec[0];
-        if (intsize > 1)
-                *out_flags = intspec[1];
-        else
-                *out_flags = IRQ_TYPE_NONE;
-        return 0;
-}
-
-static struct irq_host_ops cpm2_pic_host_ops = {
+static const struct irq_domain_ops cpm2_pic_host_ops = {
         .map = cpm2_pic_host_map,
-        .xlate = cpm2_pic_host_xlate,
+        .xlate = irq_domain_xlate_onetwocell,
 };
 
 void cpm2_pic_init(struct device_node *node)
@@ -275,8 +263,7 @@ void cpm2_pic_init(struct device_node *node)
         out_be32(&cpm2_intctl->ic_scprrl, 0x05309770);
 
         /* create a legacy host */
-        cpm2_pic_host = irq_alloc_host(node, IRQ_HOST_MAP_LINEAR,
-                                       64, &cpm2_pic_host_ops, 64);
+        cpm2_pic_host = irq_domain_add_linear(node, 64, &cpm2_pic_host_ops, NULL);
         if (cpm2_pic_host == NULL) {
                 printk(KERN_ERR "CPM2 PIC: failed to allocate irq host!\n");
                 return;
diff --git a/arch/powerpc/sysdev/ehv_pic.c b/arch/powerpc/sysdev/ehv_pic.c
index b6731e4a6646..6e0e1005227f 100644
--- a/arch/powerpc/sysdev/ehv_pic.c
+++ b/arch/powerpc/sysdev/ehv_pic.c
@@ -182,13 +182,13 @@ unsigned int ehv_pic_get_irq(void)
         return irq_linear_revmap(global_ehv_pic->irqhost, irq);
 }
 
-static int ehv_pic_host_match(struct irq_host *h, struct device_node *node)
+static int ehv_pic_host_match(struct irq_domain *h, struct device_node *node)
 {
         /* Exact match, unless ehv_pic node is NULL */
         return h->of_node == NULL || h->of_node == node;
 }
 
-static int ehv_pic_host_map(struct irq_host *h, unsigned int virq,
+static int ehv_pic_host_map(struct irq_domain *h, unsigned int virq,
                          irq_hw_number_t hw)
 {
         struct ehv_pic *ehv_pic = h->host_data;
@@ -217,7 +217,7 @@ static int ehv_pic_host_map(struct irq_host *h, unsigned int virq,
         return 0;
 }
 
-static int ehv_pic_host_xlate(struct irq_host *h, struct device_node *ct,
+static int ehv_pic_host_xlate(struct irq_domain *h, struct device_node *ct,
                            const u32 *intspec, unsigned int intsize,
                            irq_hw_number_t *out_hwirq, unsigned int *out_flags)
 
@@ -248,7 +248,7 @@ static int ehv_pic_host_xlate(struct irq_host *h, struct device_node *ct,
         return 0;
 }
 
-static struct irq_host_ops ehv_pic_host_ops = {
+static const struct irq_domain_ops ehv_pic_host_ops = {
         .match = ehv_pic_host_match,
         .map = ehv_pic_host_map,
         .xlate = ehv_pic_host_xlate,
@@ -275,9 +275,8 @@ void __init ehv_pic_init(void)
                 return;
         }
 
-        ehv_pic->irqhost = irq_alloc_host(np, IRQ_HOST_MAP_LINEAR,
-                NR_EHV_PIC_INTS, &ehv_pic_host_ops, 0);
-
+        ehv_pic->irqhost = irq_domain_add_linear(np, NR_EHV_PIC_INTS,
+                                                 &ehv_pic_host_ops, ehv_pic);
         if (!ehv_pic->irqhost) {
                 of_node_put(np);
                 kfree(ehv_pic);
@@ -293,7 +292,6 @@ void __init ehv_pic_init(void)
                 of_node_put(np2);
         }
 
-        ehv_pic->irqhost->host_data = ehv_pic;
         ehv_pic->hc_irq = ehv_pic_irq_chip;
         ehv_pic->hc_irq.irq_set_affinity = ehv_pic_set_affinity;
         ehv_pic->coreint_flag = coreint_flag;
diff --git a/arch/powerpc/sysdev/fsl_85xx_cache_sram.c b/arch/powerpc/sysdev/fsl_85xx_cache_sram.c
index 116415899176..37a69097e022 100644
--- a/arch/powerpc/sysdev/fsl_85xx_cache_sram.c
+++ b/arch/powerpc/sysdev/fsl_85xx_cache_sram.c
@@ -24,6 +24,7 @@
  */
 
 #include <linux/kernel.h>
+#include <linux/export.h>
 #include <linux/slab.h>
 #include <linux/err.h>
 #include <linux/of_platform.h>
diff --git a/arch/powerpc/sysdev/fsl_85xx_l2ctlr.c b/arch/powerpc/sysdev/fsl_85xx_l2ctlr.c
index 5f88797dce73..cedabd0f4bfe 100644
--- a/arch/powerpc/sysdev/fsl_85xx_l2ctlr.c
+++ b/arch/powerpc/sysdev/fsl_85xx_l2ctlr.c
@@ -21,6 +21,7 @@
  */
 
 #include <linux/kernel.h>
+#include <linux/module.h>
 #include <linux/of_platform.h>
 #include <asm/io.h>
 
@@ -200,6 +201,9 @@ static struct of_device_id mpc85xx_l2ctlr_of_match[] = {
         {
                 .compatible = "fsl,p1022-l2-cache-controller",
         },
+        {
+                .compatible = "fsl,mpc8548-l2-cache-controller",
+        },
         {},
 };
 
diff --git a/arch/powerpc/sysdev/fsl_msi.c b/arch/powerpc/sysdev/fsl_msi.c
index ecb5c1946d22..6e097de00e09 100644
--- a/arch/powerpc/sysdev/fsl_msi.c
+++ b/arch/powerpc/sysdev/fsl_msi.c
@@ -60,7 +60,7 @@ static struct irq_chip fsl_msi_chip = {
         .name           = "FSL-MSI",
 };
 
-static int fsl_msi_host_map(struct irq_host *h, unsigned int virq,
+static int fsl_msi_host_map(struct irq_domain *h, unsigned int virq,
                                 irq_hw_number_t hw)
 {
         struct fsl_msi *msi_data = h->host_data;
@@ -74,7 +74,7 @@ static int fsl_msi_host_map(struct irq_host *h, unsigned int virq,
         return 0;
 }
 
-static struct irq_host_ops fsl_msi_host_ops = {
+static const struct irq_domain_ops fsl_msi_host_ops = {
         .map = fsl_msi_host_map,
 };
 
@@ -387,8 +387,8 @@ static int __devinit fsl_of_msi_probe(struct platform_device *dev)
         }
         platform_set_drvdata(dev, msi);
 
-        msi->irqhost = irq_alloc_host(dev->dev.of_node, IRQ_HOST_MAP_LINEAR,
-                                      NR_MSI_IRQS, &fsl_msi_host_ops, 0);
+        msi->irqhost = irq_domain_add_linear(dev->dev.of_node,
+                                      NR_MSI_IRQS, &fsl_msi_host_ops, msi);
 
         if (msi->irqhost == NULL) {
                 dev_err(&dev->dev, "No memory for MSI irqhost\n");
@@ -410,6 +410,7 @@ static int __devinit fsl_of_msi_probe(struct platform_device *dev)
 
                 msi->msi_regs = ioremap(res.start, resource_size(&res));
                 if (!msi->msi_regs) {
+                        err = -ENOMEM;
                         dev_err(&dev->dev, "could not map node %s\n",
                                 dev->dev.of_node->full_name);
                         goto error_out;
@@ -420,8 +421,6 @@ static int __devinit fsl_of_msi_probe(struct platform_device *dev)
 
         msi->feature = features->fsl_pic_ip;
 
-        msi->irqhost->host_data = msi;
-
         /*
          * Remember the phandle, so that we can match with any PCI nodes
          * that have an "fsl,msi" property.
diff --git a/arch/powerpc/sysdev/fsl_msi.h b/arch/powerpc/sysdev/fsl_msi.h
index f6c646a52541..8225f8653f78 100644
--- a/arch/powerpc/sysdev/fsl_msi.h
+++ b/arch/powerpc/sysdev/fsl_msi.h
@@ -26,7 +26,7 @@
 #define FSL_PIC_IP_VMPIC  0x00000003
 
 struct fsl_msi {
-        struct irq_host *irqhost;
+        struct irq_domain *irqhost;
 
         unsigned long cascade_irq;
 
diff --git a/arch/powerpc/sysdev/fsl_pci.c b/arch/powerpc/sysdev/fsl_pci.c
index 3b61e8cf3421..6073288fed29 100644
--- a/arch/powerpc/sysdev/fsl_pci.c
+++ b/arch/powerpc/sysdev/fsl_pci.c
@@ -205,12 +205,12 @@ static void __init setup_pci_atmu(struct pci_controller *hose,
 
         if (paddr_hi == paddr_lo) {
                 pr_err("%s: No outbound window space\n", name);
-                return ;
+                goto out;
         }
 
         if (paddr_lo == 0) {
                 pr_err("%s: No space for inbound window\n", name);
-                return ;
+                goto out;
         }
 
         /* setup PCSRBAR/PEXCSRBAR */
@@ -357,6 +357,7 @@ static void __init setup_pci_atmu(struct pci_controller *hose,
                         (u64)hose->dma_window_size);
         }
 
+out:
         iounmap(pci);
 }
 
@@ -384,26 +385,36 @@ static void __init setup_pci_cmd(struct pci_controller *hose)
 void fsl_pcibios_fixup_bus(struct pci_bus *bus)
 {
         struct pci_controller *hose = pci_bus_to_host(bus);
-        int i;
-
-        if ((bus->parent == hose->bus) &&
-            ((fsl_pcie_bus_fixup &&
-              early_find_capability(hose, 0, 0, PCI_CAP_ID_EXP)) ||
-             (hose->indirect_type & PPC_INDIRECT_TYPE_NO_PCIE_LINK)))
-        {
-                for (i = 0; i < 4; ++i) {
+        int i, is_pcie = 0, no_link;
+
+        /* The root complex bridge comes up with bogus resources,
+         * we copy the PHB ones in.
+         *
+         * With the current generic PCI code, the PHB bus no longer
+         * has bus->resource[0..4] set, so things are a bit more
+         * tricky.
+         */
+
+        if (fsl_pcie_bus_fixup)
+                is_pcie = early_find_capability(hose, 0, 0, PCI_CAP_ID_EXP);
+        no_link = !!(hose->indirect_type & PPC_INDIRECT_TYPE_NO_PCIE_LINK);
+
+        if (bus->parent == hose->bus && (is_pcie || no_link)) {
+                for (i = 0; i < PCI_BRIDGE_RESOURCE_NUM; ++i) {
                         struct resource *res = bus->resource[i];
-                        struct resource *par = bus->parent->resource[i];
-                        if (res) {
-                                res->start = 0;
-                                res->end   = 0;
-                                res->flags = 0;
-                        }
-                        if (res && par) {
-                                res->start = par->start;
-                                res->end   = par->end;
-                                res->flags = par->flags;
-                        }
+                        struct resource *par;
+
+                        if (!res)
+                                continue;
+                        if (i == 0)
+                                par = &hose->io_resource;
+                        else if (i < 4)
+                                par = &hose->mem_resources[i-1];
+                        else par = NULL;
+
+                        res->start = par ? par->start : 0;
+                        res->end   = par ? par->end   : 0;
+                        res->flags = par ? par->flags : 0;
                 }
         }
 }
diff --git a/arch/powerpc/sysdev/fsl_rio.c b/arch/powerpc/sysdev/fsl_rio.c
index a4c4f4a932d8..5b6f556094dd 100644
--- a/arch/powerpc/sysdev/fsl_rio.c
+++ b/arch/powerpc/sysdev/fsl_rio.c
@@ -66,8 +66,8 @@
                 "       li %0,%3\n"                     \
                 "       b 2b\n"                         \
                 ".section __ex_table,\"a\"\n"           \
-                "       .align 2\n"                     \
-                "       .long 1b,3b\n"                  \
+                        PPC_LONG_ALIGN "\n"             \
+                        PPC_LONG "1b,3b\n"              \
                 ".text"                                 \
                 : "=r" (err), "=r" (x)                  \
                 : "b" (addr), "i" (-EFAULT), "0" (err))
diff --git a/arch/powerpc/sysdev/fsl_rmu.c b/arch/powerpc/sysdev/fsl_rmu.c
index 15485789e9db..14bd5221f28a 100644
--- a/arch/powerpc/sysdev/fsl_rmu.c
+++ b/arch/powerpc/sysdev/fsl_rmu.c
@@ -100,14 +100,8 @@
 #define DOORBELL_DSR_TE         0x00000080
 #define DOORBELL_DSR_QFI        0x00000010
 #define DOORBELL_DSR_DIQI       0x00000001
-#define DOORBELL_TID_OFFSET     0x02
-#define DOORBELL_SID_OFFSET     0x04
-#define DOORBELL_INFO_OFFSET    0x06
 
 #define DOORBELL_MESSAGE_SIZE   0x08
-#define DBELL_SID(x)            (*(u16 *)(x + DOORBELL_SID_OFFSET))
-#define DBELL_TID(x)            (*(u16 *)(x + DOORBELL_TID_OFFSET))
-#define DBELL_INF(x)            (*(u16 *)(x + DOORBELL_INFO_OFFSET))
 
 struct rio_msg_regs {
         u32 omr;
@@ -193,6 +187,13 @@ struct fsl_rmu {
         int rxirq;
 };
 
+struct rio_dbell_msg {
+        u16 pad1;
+        u16 tid;
+        u16 sid;
+        u16 info;
+};
+
 /**
  * fsl_rio_tx_handler - MPC85xx outbound message interrupt handler
  * @irq: Linux interrupt number
@@ -311,8 +312,8 @@ fsl_rio_dbell_handler(int irq, void *dev_instance)
 
         /* XXX Need to check/dispatch until queue empty */
         if (dsr & DOORBELL_DSR_DIQI) {
-                u32 dmsg =
-                        (u32) fsl_dbell->dbell_ring.virt +
+                struct rio_dbell_msg *dmsg =
+                        fsl_dbell->dbell_ring.virt +
                         (in_be32(&fsl_dbell->dbell_regs->dqdpar) & 0xfff);
                 struct rio_dbell *dbell;
                 int found = 0;
@@ -320,25 +321,25 @@ fsl_rio_dbell_handler(int irq, void *dev_instance)
                 pr_debug
                         ("RIO: processing doorbell,"
                         " sid %2.2x tid %2.2x info %4.4x\n",
-                        DBELL_SID(dmsg), DBELL_TID(dmsg), DBELL_INF(dmsg));
+                        dmsg->sid, dmsg->tid, dmsg->info);
 
                 for (i = 0; i < MAX_PORT_NUM; i++) {
                         if (fsl_dbell->mport[i]) {
                                 list_for_each_entry(dbell,
                                         &fsl_dbell->mport[i]->dbells, node) {
                                         if ((dbell->res->start
-                                                <= DBELL_INF(dmsg))
+                                                <= dmsg->info)
                                                 && (dbell->res->end
-                                                >= DBELL_INF(dmsg))) {
+                                                >= dmsg->info)) {
                                                 found = 1;
                                                 break;
                                         }
                                 }
                                 if (found && dbell->dinb) {
                                         dbell->dinb(fsl_dbell->mport[i],
-                                                dbell->dev_id, DBELL_SID(dmsg),
-                                                DBELL_TID(dmsg),
-                                                DBELL_INF(dmsg));
+                                                dbell->dev_id, dmsg->sid,
+                                                dmsg->tid,
+                                                dmsg->info);
                                         break;
                                 }
                         }
@@ -348,8 +349,8 @@ fsl_rio_dbell_handler(int irq, void *dev_instance)
                         pr_debug
                                 ("RIO: spurious doorbell,"
                                 " sid %2.2x tid %2.2x info %4.4x\n",
-                                DBELL_SID(dmsg), DBELL_TID(dmsg),
-                                DBELL_INF(dmsg));
+                                dmsg->sid, dmsg->tid,
+                                dmsg->info);
                 }
                 setbits32(&fsl_dbell->dbell_regs->dmr, DOORBELL_DMR_DI);
                 out_be32(&fsl_dbell->dbell_regs->dsr, DOORBELL_DSR_DIQI);
@@ -657,7 +658,7 @@ fsl_add_outb_message(struct rio_mport *mport, struct rio_dev *rdev, int mbox,
         int ret = 0;
 
         pr_debug("RIO: fsl_add_outb_message(): destid %4.4x mbox %d buffer " \
-                 "%8.8x len %8.8x\n", rdev->destid, mbox, (int)buffer, len);
+                 "%p len %8.8zx\n", rdev->destid, mbox, buffer, len);
         if ((len < 8) || (len > RIO_MAX_MSG_SIZE)) {
                 ret = -EINVAL;
                 goto out;
@@ -972,7 +973,8 @@ out:
 void *fsl_get_inb_message(struct rio_mport *mport, int mbox)
 {
         struct fsl_rmu *rmu = GET_RMM_HANDLE(mport);
-        u32 phys_buf, virt_buf;
+        u32 phys_buf;
+        void *virt_buf;
         void *buf = NULL;
         int buf_idx;
 
@@ -982,7 +984,7 @@ void *fsl_get_inb_message(struct rio_mport *mport, int mbox)
         if (phys_buf == in_be32(&rmu->msg_regs->ifqepar))
                 goto out2;
 
-        virt_buf = (u32) rmu->msg_rx_ring.virt + (phys_buf
+        virt_buf = rmu->msg_rx_ring.virt + (phys_buf
                                                 - rmu->msg_rx_ring.phys);
         buf_idx = (phys_buf - rmu->msg_rx_ring.phys) / RIO_MAX_MSG_SIZE;
         buf = rmu->msg_rx_ring.virt_buffer[buf_idx];
@@ -994,7 +996,7 @@ void *fsl_get_inb_message(struct rio_mport *mport, int mbox)
         }
 
         /* Copy max message size, caller is expected to allocate that big */
-        memcpy(buf, (void *)virt_buf, RIO_MAX_MSG_SIZE);
+        memcpy(buf, virt_buf, RIO_MAX_MSG_SIZE);
 
         /* Clear the available buffer */
         rmu->msg_rx_ring.virt_buffer[buf_idx] = NULL;
diff --git a/arch/powerpc/sysdev/ge/Makefile b/arch/powerpc/sysdev/ge/Makefile
new file mode 100644
index 000000000000..8731ffcb79b9
--- /dev/null
+++ b/arch/powerpc/sysdev/ge/Makefile
@@ -0,0 +1 @@
+obj-$(CONFIG_GE_FPGA)           += ge_pic.o
diff --git a/arch/powerpc/platforms/86xx/gef_pic.c b/arch/powerpc/sysdev/ge/ge_pic.c
index 94594e58594c..2bcb78bb3a15 100644
--- a/arch/powerpc/platforms/86xx/gef_pic.c
+++ b/arch/powerpc/sysdev/ge/ge_pic.c
@@ -22,7 +22,7 @@
 #include <asm/prom.h>
 #include <asm/irq.h>
 
-#include "gef_pic.h"
+#include "ge_pic.h"
 
 #define DEBUG
 #undef DEBUG
@@ -50,7 +50,7 @@
 static DEFINE_RAW_SPINLOCK(gef_pic_lock);
 
 static void __iomem *gef_pic_irq_reg_base;
-static struct irq_host *gef_pic_irq_host;
+static struct irq_domain *gef_pic_irq_host;
 static int gef_pic_cascade_irq;
 
 /*
@@ -153,7 +153,7 @@ static struct irq_chip gef_pic_chip = {
 /* When an interrupt is being configured, this call allows some flexibilty
  * in deciding which irq_chip structure is used
  */
-static int gef_pic_host_map(struct irq_host *h, unsigned int virq,
+static int gef_pic_host_map(struct irq_domain *h, unsigned int virq,
                           irq_hw_number_t hwirq)
 {
         /* All interrupts are LEVEL sensitive */
@@ -163,7 +163,7 @@ static int gef_pic_host_map(struct irq_host *h, unsigned int virq,
         return 0;
 }
 
-static int gef_pic_host_xlate(struct irq_host *h, struct device_node *ct,
+static int gef_pic_host_xlate(struct irq_domain *h, struct device_node *ct,
                             const u32 *intspec, unsigned int intsize,
                             irq_hw_number_t *out_hwirq, unsigned int *out_flags)
 {
@@ -177,7 +177,7 @@ static int gef_pic_host_xlate(struct irq_host *h, struct device_node *ct,
         return 0;
 }
 
-static struct irq_host_ops gef_pic_host_ops = {
+static const struct irq_domain_ops gef_pic_host_ops = {
         .map    = gef_pic_host_map,
         .xlate  = gef_pic_host_xlate,
 };
@@ -211,10 +211,9 @@ void __init gef_pic_init(struct device_node *np)
                 return;
         }
 
-        /* Setup an irq_host structure */
-        gef_pic_irq_host = irq_alloc_host(np, IRQ_HOST_MAP_LINEAR,
-                                          GEF_PIC_NUM_IRQS,
-                                          &gef_pic_host_ops, NO_IRQ);
+        /* Setup an irq_domain structure */
+        gef_pic_irq_host = irq_domain_add_linear(np, GEF_PIC_NUM_IRQS,
+                                          &gef_pic_host_ops, NULL);
         if (gef_pic_irq_host == NULL)
                 return;
 
diff --git a/arch/powerpc/platforms/86xx/gef_pic.h b/arch/powerpc/sysdev/ge/ge_pic.h
index 6149916da3f4..6149916da3f4 100644
--- a/arch/powerpc/platforms/86xx/gef_pic.h
+++ b/arch/powerpc/sysdev/ge/ge_pic.h
diff --git a/arch/powerpc/sysdev/i8259.c b/arch/powerpc/sysdev/i8259.c
index d18bb27e4df9..997df6a7ab5d 100644
--- a/arch/powerpc/sysdev/i8259.c
+++ b/arch/powerpc/sysdev/i8259.c
@@ -25,7 +25,7 @@ static unsigned char cached_8259[2] = { 0xff, 0xff };
 
 static DEFINE_RAW_SPINLOCK(i8259_lock);
 
-static struct irq_host *i8259_host;
+static struct irq_domain *i8259_host;
 
 /*
  * Acknowledge the IRQ using either the PCI host bridge's interrupt
@@ -163,12 +163,12 @@ static struct resource pic_edgectrl_iores = {
         .flags = IORESOURCE_BUSY,
 };
 
-static int i8259_host_match(struct irq_host *h, struct device_node *node)
+static int i8259_host_match(struct irq_domain *h, struct device_node *node)
 {
         return h->of_node == NULL || h->of_node == node;
 }
 
-static int i8259_host_map(struct irq_host *h, unsigned int virq,
+static int i8259_host_map(struct irq_domain *h, unsigned int virq,
                           irq_hw_number_t hw)
 {
         pr_debug("i8259_host_map(%d, 0x%lx)\n", virq, hw);
@@ -185,7 +185,7 @@ static int i8259_host_map(struct irq_host *h, unsigned int virq,
         return 0;
 }
 
-static int i8259_host_xlate(struct irq_host *h, struct device_node *ct,
+static int i8259_host_xlate(struct irq_domain *h, struct device_node *ct,
                             const u32 *intspec, unsigned int intsize,
                             irq_hw_number_t *out_hwirq, unsigned int *out_flags)
 {
@@ -205,13 +205,13 @@ static int i8259_host_xlate(struct irq_host *h, struct device_node *ct,
         return 0;
 }
 
-static struct irq_host_ops i8259_host_ops = {
+static struct irq_domain_ops i8259_host_ops = {
         .match = i8259_host_match,
         .map = i8259_host_map,
         .xlate = i8259_host_xlate,
 };
 
-struct irq_host *i8259_get_host(void)
+struct irq_domain *i8259_get_host(void)
 {
         return i8259_host;
 }
@@ -263,8 +263,7 @@ void i8259_init(struct device_node *node, unsigned long intack_addr)
         raw_spin_unlock_irqrestore(&i8259_lock, flags);
 
         /* create a legacy host */
-        i8259_host = irq_alloc_host(node, IRQ_HOST_MAP_LEGACY,
-                                    0, &i8259_host_ops, 0);
+        i8259_host = irq_domain_add_legacy_isa(node, &i8259_host_ops, NULL);
         if (i8259_host == NULL) {
                 printk(KERN_ERR "i8259: failed to allocate irq host !\n");
                 return;
diff --git a/arch/powerpc/sysdev/ipic.c b/arch/powerpc/sysdev/ipic.c
index 95da897f05a7..b50f97811c25 100644
--- a/arch/powerpc/sysdev/ipic.c
+++ b/arch/powerpc/sysdev/ipic.c
@@ -672,13 +672,13 @@ static struct irq_chip ipic_edge_irq_chip = {
         .irq_set_type   = ipic_set_irq_type,
 };
 
-static int ipic_host_match(struct irq_host *h, struct device_node *node)
+static int ipic_host_match(struct irq_domain *h, struct device_node *node)
 {
         /* Exact match, unless ipic node is NULL */
         return h->of_node == NULL || h->of_node == node;
 }
 
-static int ipic_host_map(struct irq_host *h, unsigned int virq,
+static int ipic_host_map(struct irq_domain *h, unsigned int virq,
                          irq_hw_number_t hw)
 {
         struct ipic *ipic = h->host_data;
@@ -692,26 +692,10 @@ static int ipic_host_map(struct irq_host *h, unsigned int virq,
         return 0;
 }
 
-static int ipic_host_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
-         * LEVEL_LOW (low assertion) or EDGE_FALLING (high-to-low change)
-         */
-        *out_hwirq = intspec[0];
-        if (intsize > 1)
-                *out_flags = intspec[1];
-        else
-                *out_flags = IRQ_TYPE_NONE;
-        return 0;
-}
-
-static struct irq_host_ops ipic_host_ops = {
+static struct irq_domain_ops ipic_host_ops = {
         .match  = ipic_host_match,
         .map    = ipic_host_map,
-        .xlate  = ipic_host_xlate,
+        .xlate  = irq_domain_xlate_onetwocell,
 };
 
 struct ipic * __init ipic_init(struct device_node *node, unsigned int flags)
@@ -728,9 +712,8 @@ struct ipic * __init ipic_init(struct device_node *node, unsigned int flags)
         if (ipic == NULL)
                 return NULL;
 
-        ipic->irqhost = irq_alloc_host(node, IRQ_HOST_MAP_LINEAR,
-                                       NR_IPIC_INTS,
-                                       &ipic_host_ops, 0);
+        ipic->irqhost = irq_domain_add_linear(node, NR_IPIC_INTS,
+                                              &ipic_host_ops, ipic);
         if (ipic->irqhost == NULL) {
                 kfree(ipic);
                 return NULL;
@@ -738,8 +721,6 @@ struct ipic * __init ipic_init(struct device_node *node, unsigned int flags)
 
         ipic->regs = ioremap(res.start, resource_size(&res));
 
-        ipic->irqhost->host_data = ipic;
-
         /* init hw */
         ipic_write(ipic->regs, IPIC_SICNR, 0x0);
 
diff --git a/arch/powerpc/sysdev/ipic.h b/arch/powerpc/sysdev/ipic.h
index 9391c57b0c51..90031d1282e1 100644
--- a/arch/powerpc/sysdev/ipic.h
+++ b/arch/powerpc/sysdev/ipic.h
@@ -43,7 +43,7 @@ struct ipic {
         volatile u32 __iomem    *regs;
 
         /* The remapper for this IPIC */
-        struct irq_host         *irqhost;
+        struct irq_domain               *irqhost;
 };
 
 struct ipic_info {
diff --git a/arch/powerpc/sysdev/mpc8xx_pic.c b/arch/powerpc/sysdev/mpc8xx_pic.c
index 2ca0a85fcce9..d5f5416be310 100644
--- a/arch/powerpc/sysdev/mpc8xx_pic.c
+++ b/arch/powerpc/sysdev/mpc8xx_pic.c
@@ -17,7 +17,7 @@
 
 extern int cpm_get_irq(struct pt_regs *regs);
 
-static struct irq_host *mpc8xx_pic_host;
+static struct irq_domain *mpc8xx_pic_host;
 #define NR_MASK_WORDS   ((NR_IRQS + 31) / 32)
 static unsigned long ppc_cached_irq_mask[NR_MASK_WORDS];
 static sysconf8xx_t __iomem *siu_reg;
@@ -110,7 +110,7 @@ unsigned int mpc8xx_get_irq(void)
 
 }
 
-static int mpc8xx_pic_host_map(struct irq_host *h, unsigned int virq,
+static int mpc8xx_pic_host_map(struct irq_domain *h, unsigned int virq,
                           irq_hw_number_t hw)
 {
         pr_debug("mpc8xx_pic_host_map(%d, 0x%lx)\n", virq, hw);
@@ -121,7 +121,7 @@ static int mpc8xx_pic_host_map(struct irq_host *h, unsigned int virq,
 }
 
 
-static int mpc8xx_pic_host_xlate(struct irq_host *h, struct device_node *ct,
+static int mpc8xx_pic_host_xlate(struct irq_domain *h, struct device_node *ct,
                             const u32 *intspec, unsigned int intsize,
                             irq_hw_number_t *out_hwirq, unsigned int *out_flags)
 {
@@ -142,7 +142,7 @@ static int mpc8xx_pic_host_xlate(struct irq_host *h, struct device_node *ct,
 }
 
 
-static struct irq_host_ops mpc8xx_pic_host_ops = {
+static struct irq_domain_ops mpc8xx_pic_host_ops = {
         .map = mpc8xx_pic_host_map,
         .xlate = mpc8xx_pic_host_xlate,
 };
@@ -171,8 +171,7 @@ int mpc8xx_pic_init(void)
                 goto out;
         }
 
-        mpc8xx_pic_host = irq_alloc_host(np, IRQ_HOST_MAP_LINEAR,
-                                         64, &mpc8xx_pic_host_ops, 64);
+        mpc8xx_pic_host = irq_domain_add_linear(np, 64, &mpc8xx_pic_host_ops, NULL);
         if (mpc8xx_pic_host == NULL) {
                 printk(KERN_ERR "MPC8xx PIC: failed to allocate irq host!\n");
                 ret = -ENOMEM;
diff --git a/arch/powerpc/sysdev/mpic.c b/arch/powerpc/sysdev/mpic.c
index 4e9ccb1015de..9ac71ebd2c40 100644
--- a/arch/powerpc/sysdev/mpic.c
+++ b/arch/powerpc/sysdev/mpic.c
@@ -873,7 +873,7 @@ int mpic_set_irq_type(struct irq_data *d, unsigned int flow_type)
         DBG("mpic: set_irq_type(mpic:@%p,virq:%d,src:0x%x,type:0x%x)\n",
             mpic, d->irq, src, flow_type);
 
-        if (src >= mpic->irq_count)
+        if (src >= mpic->num_sources)
                 return -EINVAL;
 
         if (flow_type == IRQ_TYPE_NONE)
@@ -909,7 +909,7 @@ void mpic_set_vector(unsigned int virq, unsigned int vector)
         DBG("mpic: set_vector(mpic:@%p,virq:%d,src:%d,vector:0x%x)\n",
             mpic, virq, src, vector);
 
-        if (src >= mpic->irq_count)
+        if (src >= mpic->num_sources)
                 return;
 
         vecpri = mpic_irq_read(src, MPIC_INFO(IRQ_VECTOR_PRI));
@@ -926,7 +926,7 @@ void mpic_set_destination(unsigned int virq, unsigned int cpuid)
         DBG("mpic: set_destination(mpic:@%p,virq:%d,src:%d,cpuid:0x%x)\n",
             mpic, virq, src, cpuid);
 
-        if (src >= mpic->irq_count)
+        if (src >= mpic->num_sources)
                 return;
 
         mpic_irq_write(src, MPIC_INFO(IRQ_DESTINATION), 1 << cpuid);
@@ -965,13 +965,13 @@ static struct irq_chip mpic_irq_ht_chip = {
 #endif /* CONFIG_MPIC_U3_HT_IRQS */
 
 
-static int mpic_host_match(struct irq_host *h, struct device_node *node)
+static int mpic_host_match(struct irq_domain *h, struct device_node *node)
 {
         /* Exact match, unless mpic node is NULL */
         return h->of_node == NULL || h->of_node == node;
 }
 
-static int mpic_host_map(struct irq_host *h, unsigned int virq,
+static int mpic_host_map(struct irq_domain *h, unsigned int virq,
                          irq_hw_number_t hw)
 {
         struct mpic *mpic = h->host_data;
@@ -1006,7 +1006,7 @@ static int mpic_host_map(struct irq_host *h, unsigned int virq,
                 return 0;
         }
 
-        if (hw >= mpic->irq_count)
+        if (hw >= mpic->num_sources)
                 return -EINVAL;
 
         mpic_msi_reserve_hwirq(mpic, hw);
@@ -1041,7 +1041,7 @@ static int mpic_host_map(struct irq_host *h, unsigned int virq,
         return 0;
 }
 
-static int mpic_host_xlate(struct irq_host *h, struct device_node *ct,
+static int mpic_host_xlate(struct irq_domain *h, struct device_node *ct,
                            const u32 *intspec, unsigned int intsize,
                            irq_hw_number_t *out_hwirq, unsigned int *out_flags)
 
@@ -1121,13 +1121,13 @@ static void mpic_cascade(unsigned int irq, struct irq_desc *desc)
         BUG_ON(!(mpic->flags & MPIC_SECONDARY));
 
         virq = mpic_get_one_irq(mpic);
-        if (virq != NO_IRQ)
+        if (virq)
                 generic_handle_irq(virq);
 
         chip->irq_eoi(&desc->irq_data);
 }
 
-static struct irq_host_ops mpic_host_ops = {
+static struct irq_domain_ops mpic_host_ops = {
         .match = mpic_host_match,
         .map = mpic_host_map,
         .xlate = mpic_host_xlate,
@@ -1149,6 +1149,7 @@ struct mpic * __init mpic_alloc(struct device_node *node,
         u32 greg_feature;
         const char *vers;
         const u32 *psrc;
+        u32 last_irq;
 
         /* Default MPIC search parameters */
         static const struct of_device_id __initconst mpic_device_id[] = {
@@ -1182,6 +1183,16 @@ struct mpic * __init mpic_alloc(struct device_node *node,
                 }
         }
 
+        /* Read extra device-tree properties into the flags variable */
+        if (of_get_property(node, "big-endian", NULL))
+                flags |= MPIC_BIG_ENDIAN;
+        if (of_get_property(node, "pic-no-reset", NULL))
+                flags |= MPIC_NO_RESET;
+        if (of_get_property(node, "single-cpu-affinity", NULL))
+                flags |= MPIC_SINGLE_DEST_CPU;
+        if (of_device_is_compatible(node, "fsl,mpic"))
+                flags |= MPIC_FSL;
+
         mpic = kzalloc(sizeof(struct mpic), GFP_KERNEL);
         if (mpic == NULL)
                 goto err_of_node_put;
@@ -1189,15 +1200,16 @@ struct mpic * __init mpic_alloc(struct device_node *node,
         mpic->name = name;
         mpic->node = node;
         mpic->paddr = phys_addr;
+        mpic->flags = flags;
 
         mpic->hc_irq = mpic_irq_chip;
         mpic->hc_irq.name = name;
-        if (!(flags & MPIC_SECONDARY))
+        if (!(mpic->flags & MPIC_SECONDARY))
                 mpic->hc_irq.irq_set_affinity = mpic_set_affinity;
 #ifdef CONFIG_MPIC_U3_HT_IRQS
         mpic->hc_ht_irq = mpic_irq_ht_chip;
         mpic->hc_ht_irq.name = name;
-        if (!(flags & MPIC_SECONDARY))
+        if (!(mpic->flags & MPIC_SECONDARY))
                 mpic->hc_ht_irq.irq_set_affinity = mpic_set_affinity;
 #endif /* CONFIG_MPIC_U3_HT_IRQS */
 
@@ -1209,12 +1221,9 @@ struct mpic * __init mpic_alloc(struct device_node *node,
         mpic->hc_tm = mpic_tm_chip;
         mpic->hc_tm.name = name;
 
-        mpic->flags = flags;
-        mpic->isu_size = isu_size;
-        mpic->irq_count = irq_count;
         mpic->num_sources = 0; /* so far */
 
-        if (flags & MPIC_LARGE_VECTORS)
+        if (mpic->flags & MPIC_LARGE_VECTORS)
                 intvec_top = 2047;
         else
                 intvec_top = 255;
@@ -1233,12 +1242,6 @@ struct mpic * __init mpic_alloc(struct device_node *node,
         mpic->ipi_vecs[3]   = intvec_top - 1;
         mpic->spurious_vec  = intvec_top;
 
-        /* Check for "big-endian" in device-tree */
-        if (of_get_property(mpic->node, "big-endian", NULL) != NULL)
-                mpic->flags |= MPIC_BIG_ENDIAN;
-        if (of_device_is_compatible(mpic->node, "fsl,mpic"))
-                mpic->flags |= MPIC_FSL;
-
         /* Look for protected sources */
         psrc = of_get_property(mpic->node, "protected-sources", &psize);
         if (psrc) {
@@ -1254,11 +1257,11 @@ struct mpic * __init mpic_alloc(struct device_node *node,
         }
 
 #ifdef CONFIG_MPIC_WEIRD
-        mpic->hw_set = mpic_infos[MPIC_GET_REGSET(flags)];
+        mpic->hw_set = mpic_infos[MPIC_GET_REGSET(mpic->flags)];
 #endif
 
         /* default register type */
-        if (flags & MPIC_BIG_ENDIAN)
+        if (mpic->flags & MPIC_BIG_ENDIAN)
                 mpic->reg_type = mpic_access_mmio_be;
         else
                 mpic->reg_type = mpic_access_mmio_le;
@@ -1268,10 +1271,10 @@ struct mpic * __init mpic_alloc(struct device_node *node,
          * only if the kernel includes DCR support.
          */
 #ifdef CONFIG_PPC_DCR
-        if (flags & MPIC_USES_DCR)
+        if (mpic->flags & MPIC_USES_DCR)
                 mpic->reg_type = mpic_access_dcr;
 #else
-        BUG_ON(flags & MPIC_USES_DCR);
+        BUG_ON(mpic->flags & MPIC_USES_DCR);
 #endif
 
         /* Map the global registers */
@@ -1283,10 +1286,7 @@ struct mpic * __init mpic_alloc(struct device_node *node,
         /* When using a device-node, reset requests are only honored if the MPIC
          * is allowed to reset.
          */
-        if (of_get_property(mpic->node, "pic-no-reset", NULL))
-                mpic->flags |= MPIC_NO_RESET;
-
-        if ((flags & MPIC_WANTS_RESET) && !(mpic->flags & MPIC_NO_RESET)) {
+        if (!(mpic->flags & MPIC_NO_RESET)) {
                 printk(KERN_DEBUG "mpic: Resetting\n");
                 mpic_write(mpic->gregs, MPIC_INFO(GREG_GLOBAL_CONF_0),
                            mpic_read(mpic->gregs, MPIC_INFO(GREG_GLOBAL_CONF_0))
@@ -1297,31 +1297,17 @@ struct mpic * __init mpic_alloc(struct device_node *node,
         }
 
         /* CoreInt */
-        if (flags & MPIC_ENABLE_COREINT)
+        if (mpic->flags & MPIC_ENABLE_COREINT)
                 mpic_write(mpic->gregs, MPIC_INFO(GREG_GLOBAL_CONF_0),
                            mpic_read(mpic->gregs, MPIC_INFO(GREG_GLOBAL_CONF_0))
                            | MPIC_GREG_GCONF_COREINT);
 
-        if (flags & MPIC_ENABLE_MCK)
+        if (mpic->flags & MPIC_ENABLE_MCK)
                 mpic_write(mpic->gregs, MPIC_INFO(GREG_GLOBAL_CONF_0),
                            mpic_read(mpic->gregs, MPIC_INFO(GREG_GLOBAL_CONF_0))
                            | MPIC_GREG_GCONF_MCK);
 
         /*
-         * 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));
-        if (isu_size == 0) {
-                if (flags & MPIC_BROKEN_FRR_NIRQS)
-                        mpic->num_sources = mpic->irq_count;
-                else
-                        mpic->num_sources =
-                                ((greg_feature & MPIC_GREG_FEATURE_LAST_SRC_MASK)
-                                 >> 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.
          */
@@ -1336,19 +1322,42 @@ struct mpic * __init mpic_alloc(struct device_node *node,
                          0x1000);
         }
 
+        /*
+         * 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));
+
+        /*
+         * By default, the last source number comes from the MPIC, but the
+         * device-tree and board support code can override it on buggy hw.
+         * If we get passed an isu_size (multi-isu MPIC) then we use that
+         * as a default instead of the value read from the HW.
+         */
+        last_irq = (greg_feature & MPIC_GREG_FEATURE_LAST_SRC_MASK)
+                                >> MPIC_GREG_FEATURE_LAST_SRC_SHIFT;    
+        if (isu_size)
+                last_irq = isu_size  * MPIC_MAX_ISU - 1;
+        of_property_read_u32(mpic->node, "last-interrupt-source", &last_irq);
+        if (irq_count)
+                last_irq = irq_count - 1;
+
         /* Initialize main ISU if none provided */
-        if (mpic->isu_size == 0) {
-                mpic->isu_size = mpic->num_sources;
+        if (!isu_size) {
+                isu_size = last_irq + 1;
+                mpic->num_sources = isu_size;
                 mpic_map(mpic, mpic->paddr, &mpic->isus[0],
-                         MPIC_INFO(IRQ_BASE), MPIC_INFO(IRQ_STRIDE) * mpic->isu_size);
+                                MPIC_INFO(IRQ_BASE),
+                                MPIC_INFO(IRQ_STRIDE) * isu_size);
         }
+
+        mpic->isu_size = isu_size;
         mpic->isu_shift = 1 + __ilog2(mpic->isu_size - 1);
         mpic->isu_mask = (1 << mpic->isu_shift) - 1;
 
-        mpic->irqhost = irq_alloc_host(mpic->node, IRQ_HOST_MAP_LINEAR,
-                                       isu_size ? isu_size : mpic->num_sources,
-                                       &mpic_host_ops,
-                                       flags & MPIC_LARGE_VECTORS ? 2048 : 256);
+        mpic->irqhost = irq_domain_add_linear(mpic->node,
+                                       last_irq + 1,
+                                       &mpic_host_ops, mpic);
 
         /*
          * FIXME: The code leaks the MPIC object and mappings here; this
@@ -1357,8 +1366,6 @@ struct mpic * __init mpic_alloc(struct device_node *node,
         if (mpic->irqhost == NULL)
                 return NULL;
 
-        mpic->irqhost->host_data = mpic;
-
         /* Display version */
         switch (greg_feature & MPIC_GREG_FEATURE_VERSION_MASK) {
         case 1:
@@ -1383,7 +1390,7 @@ struct mpic * __init mpic_alloc(struct device_node *node,
         mpic->next = mpics;
         mpics = mpic;
 
-        if (!(flags & MPIC_SECONDARY)) {
+        if (!(mpic->flags & MPIC_SECONDARY)) {
                 mpic_primary = mpic;
                 irq_set_default_host(mpic->irqhost);
         }
@@ -1450,10 +1457,6 @@ void __init mpic_init(struct mpic *mpic)
                                (mpic->ipi_vecs[0] + i));
         }
 
-        /* Initialize interrupt sources */
-        if (mpic->irq_count == 0)
-                mpic->irq_count = mpic->num_sources;
-
         /* Do the HT PIC fixups on U3 broken mpic */
         DBG("MPIC flags: %x\n", mpic->flags);
         if ((mpic->flags & MPIC_U3_HT_IRQS) && !(mpic->flags & MPIC_SECONDARY)) {
diff --git a/arch/powerpc/sysdev/mpic_msgr.c b/arch/powerpc/sysdev/mpic_msgr.c
new file mode 100644
index 000000000000..6e7fa386e76a
--- /dev/null
+++ b/arch/powerpc/sysdev/mpic_msgr.c
@@ -0,0 +1,282 @@
+/*
+ * Copyright 2011-2012, Meador Inge, Mentor Graphics Corporation.
+ *
+ * Some ideas based on un-pushed work done by Vivek Mahajan, Jason Jin, and
+ * Mingkai Hu from 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; version 2 of the
+ * License.
+ *
+ */
+
+#include <linux/list.h>
+#include <linux/of_platform.h>
+#include <linux/errno.h>
+#include <asm/prom.h>
+#include <asm/hw_irq.h>
+#include <asm/ppc-pci.h>
+#include <asm/mpic_msgr.h>
+
+#define MPIC_MSGR_REGISTERS_PER_BLOCK   4
+#define MPIC_MSGR_STRIDE                0x10
+#define MPIC_MSGR_MER_OFFSET            0x100
+#define MSGR_INUSE                      0
+#define MSGR_FREE                       1
+
+static struct mpic_msgr **mpic_msgrs;
+static unsigned int mpic_msgr_count;
+
+static inline void _mpic_msgr_mer_write(struct mpic_msgr *msgr, u32 value)
+{
+        out_be32(msgr->mer, value);
+}
+
+static inline u32 _mpic_msgr_mer_read(struct mpic_msgr *msgr)
+{
+        return in_be32(msgr->mer);
+}
+
+static inline void _mpic_msgr_disable(struct mpic_msgr *msgr)
+{
+        u32 mer = _mpic_msgr_mer_read(msgr);
+
+        _mpic_msgr_mer_write(msgr, mer & ~(1 << msgr->num));
+}
+
+struct mpic_msgr *mpic_msgr_get(unsigned int reg_num)
+{
+        unsigned long flags;
+        struct mpic_msgr *msgr;
+
+        /* Assume busy until proven otherwise.  */
+        msgr = ERR_PTR(-EBUSY);
+
+        if (reg_num >= mpic_msgr_count)
+                return ERR_PTR(-ENODEV);
+
+        raw_spin_lock_irqsave(&msgr->lock, flags);
+        if (mpic_msgrs[reg_num]->in_use == MSGR_FREE) {
+                msgr = mpic_msgrs[reg_num];
+                msgr->in_use = MSGR_INUSE;
+        }
+        raw_spin_unlock_irqrestore(&msgr->lock, flags);
+
+        return msgr;
+}
+EXPORT_SYMBOL_GPL(mpic_msgr_get);
+
+void mpic_msgr_put(struct mpic_msgr *msgr)
+{
+        unsigned long flags;
+
+        raw_spin_lock_irqsave(&msgr->lock, flags);
+        msgr->in_use = MSGR_FREE;
+        _mpic_msgr_disable(msgr);
+        raw_spin_unlock_irqrestore(&msgr->lock, flags);
+}
+EXPORT_SYMBOL_GPL(mpic_msgr_put);
+
+void mpic_msgr_enable(struct mpic_msgr *msgr)
+{
+        unsigned long flags;
+        u32 mer;
+
+        raw_spin_lock_irqsave(&msgr->lock, flags);
+        mer = _mpic_msgr_mer_read(msgr);
+        _mpic_msgr_mer_write(msgr, mer | (1 << msgr->num));
+        raw_spin_unlock_irqrestore(&msgr->lock, flags);
+}
+EXPORT_SYMBOL_GPL(mpic_msgr_enable);
+
+void mpic_msgr_disable(struct mpic_msgr *msgr)
+{
+        unsigned long flags;
+
+        raw_spin_lock_irqsave(&msgr->lock, flags);
+        _mpic_msgr_disable(msgr);
+        raw_spin_unlock_irqrestore(&msgr->lock, flags);
+}
+EXPORT_SYMBOL_GPL(mpic_msgr_disable);
+
+/* The following three functions are used to compute the order and number of
+ * the message register blocks.  They are clearly very inefficent.  However,
+ * they are called *only* a few times during device initialization.
+ */
+static unsigned int mpic_msgr_number_of_blocks(void)
+{
+        unsigned int count;
+        struct device_node *aliases;
+
+        count = 0;
+        aliases = of_find_node_by_name(NULL, "aliases");
+
+        if (aliases) {
+                char buf[32];
+
+                for (;;) {
+                        snprintf(buf, sizeof(buf), "mpic-msgr-block%d", count);
+                        if (!of_find_property(aliases, buf, NULL))
+                                break;
+
+                        count += 1;
+                }
+        }
+
+        return count;
+}
+
+static unsigned int mpic_msgr_number_of_registers(void)
+{
+        return mpic_msgr_number_of_blocks() * MPIC_MSGR_REGISTERS_PER_BLOCK;
+}
+
+static int mpic_msgr_block_number(struct device_node *node)
+{
+        struct device_node *aliases;
+        unsigned int index, number_of_blocks;
+        char buf[64];
+
+        number_of_blocks = mpic_msgr_number_of_blocks();
+        aliases = of_find_node_by_name(NULL, "aliases");
+        if (!aliases)
+                return -1;
+
+        for (index = 0; index < number_of_blocks; ++index) {
+                struct property *prop;
+
+                snprintf(buf, sizeof(buf), "mpic-msgr-block%d", index);
+                prop = of_find_property(aliases, buf, NULL);
+                if (node == of_find_node_by_path(prop->value))
+                        break;
+        }
+
+        return index == number_of_blocks ? -1 : index;
+}
+
+/* The probe function for a single message register block.
+ */
+static __devinit int mpic_msgr_probe(struct platform_device *dev)
+{
+        void __iomem *msgr_block_addr;
+        int block_number;
+        struct resource rsrc;
+        unsigned int i;
+        unsigned int irq_index;
+        struct device_node *np = dev->dev.of_node;
+        unsigned int receive_mask;
+        const unsigned int *prop;
+
+        if (!np) {
+                dev_err(&dev->dev, "Device OF-Node is NULL");
+                return -EFAULT;
+        }
+
+        /* Allocate the message register array upon the first device
+         * registered.
+         */
+        if (!mpic_msgrs) {
+                mpic_msgr_count = mpic_msgr_number_of_registers();
+                dev_info(&dev->dev, "Found %d message registers\n",
+                                mpic_msgr_count);
+
+                mpic_msgrs = kzalloc(sizeof(struct mpic_msgr) * mpic_msgr_count,
+                                                         GFP_KERNEL);
+                if (!mpic_msgrs) {
+                        dev_err(&dev->dev,
+                                "No memory for message register blocks\n");
+                        return -ENOMEM;
+                }
+        }
+        dev_info(&dev->dev, "Of-device full name %s\n", np->full_name);
+
+        /* IO map the message register block. */
+        of_address_to_resource(np, 0, &rsrc);
+        msgr_block_addr = ioremap(rsrc.start, rsrc.end - rsrc.start);
+        if (!msgr_block_addr) {
+                dev_err(&dev->dev, "Failed to iomap MPIC message registers");
+                return -EFAULT;
+        }
+
+        /* Ensure the block has a defined order. */
+        block_number = mpic_msgr_block_number(np);
+        if (block_number < 0) {
+                dev_err(&dev->dev,
+                        "Failed to find message register block alias\n");
+                return -ENODEV;
+        }
+        dev_info(&dev->dev, "Setting up message register block %d\n",
+                        block_number);
+
+        /* Grab the receive mask which specifies what registers can receive
+         * interrupts.
+         */
+        prop = of_get_property(np, "mpic-msgr-receive-mask", NULL);
+        receive_mask = (prop) ? *prop : 0xF;
+
+        /* Build up the appropriate message register data structures. */
+        for (i = 0, irq_index = 0; i < MPIC_MSGR_REGISTERS_PER_BLOCK; ++i) {
+                struct mpic_msgr *msgr;
+                unsigned int reg_number;
+
+                msgr = kzalloc(sizeof(struct mpic_msgr), GFP_KERNEL);
+                if (!msgr) {
+                        dev_err(&dev->dev, "No memory for message register\n");
+                        return -ENOMEM;
+                }
+
+                reg_number = block_number * MPIC_MSGR_REGISTERS_PER_BLOCK + i;
+                msgr->base = msgr_block_addr + i * MPIC_MSGR_STRIDE;
+                msgr->mer = msgr->base + MPIC_MSGR_MER_OFFSET;
+                msgr->in_use = MSGR_FREE;
+                msgr->num = i;
+                raw_spin_lock_init(&msgr->lock);
+
+                if (receive_mask & (1 << i)) {
+                        struct resource irq;
+
+                        if (of_irq_to_resource(np, irq_index, &irq) == NO_IRQ) {
+                                dev_err(&dev->dev,
+                                                "Missing interrupt specifier");
+                                kfree(msgr);
+                                return -EFAULT;
+                        }
+                        msgr->irq = irq.start;
+                        irq_index += 1;
+                } else {
+                        msgr->irq = NO_IRQ;
+                }
+
+                mpic_msgrs[reg_number] = msgr;
+                mpic_msgr_disable(msgr);
+                dev_info(&dev->dev, "Register %d initialized: irq %d\n",
+                                reg_number, msgr->irq);
+
+        }
+
+        return 0;
+}
+
+static const struct of_device_id mpic_msgr_ids[] = {
+        {
+                .compatible = "fsl,mpic-v3.1-msgr",
+                .data = NULL,
+        },
+        {}
+};
+
+static struct platform_driver mpic_msgr_driver = {
+        .driver = {
+                .name = "mpic-msgr",
+                .owner = THIS_MODULE,
+                .of_match_table = mpic_msgr_ids,
+        },
+        .probe = mpic_msgr_probe,
+};
+
+static __init int mpic_msgr_init(void)
+{
+        return platform_driver_register(&mpic_msgr_driver);
+}
+subsys_initcall(mpic_msgr_init);
diff --git a/arch/powerpc/sysdev/mpic_msi.c b/arch/powerpc/sysdev/mpic_msi.c
index 0f67cd79d481..bbf342c88314 100644
--- a/arch/powerpc/sysdev/mpic_msi.c
+++ b/arch/powerpc/sysdev/mpic_msi.c
@@ -32,7 +32,7 @@ void mpic_msi_reserve_hwirq(struct mpic *mpic, irq_hw_number_t hwirq)
 static int mpic_msi_reserve_u3_hwirqs(struct mpic *mpic)
 {
         irq_hw_number_t hwirq;
-        struct irq_host_ops *ops = mpic->irqhost->ops;
+        const struct irq_domain_ops *ops = mpic->irqhost->ops;
         struct device_node *np;
         int flags, index, i;
         struct of_irq oirq;
@@ -54,7 +54,7 @@ static int mpic_msi_reserve_u3_hwirqs(struct mpic *mpic)
         for (i = 100; i < 105; i++)
                 msi_bitmap_reserve_hwirq(&mpic->msi_bitmap, i);
 
-        for (i = 124; i < mpic->irq_count; i++)
+        for (i = 124; i < mpic->num_sources; i++)
                 msi_bitmap_reserve_hwirq(&mpic->msi_bitmap, i);
 
 
@@ -83,7 +83,7 @@ int mpic_msi_init_allocator(struct mpic *mpic)
 {
         int rc;
 
-        rc = msi_bitmap_alloc(&mpic->msi_bitmap, mpic->irq_count,
+        rc = msi_bitmap_alloc(&mpic->msi_bitmap, mpic->num_sources,
                               mpic->irqhost->of_node);
         if (rc)
                 return rc;
diff --git a/arch/powerpc/sysdev/mv64x60_pic.c b/arch/powerpc/sysdev/mv64x60_pic.c
index 14d130268e7a..8848e99a83f2 100644
--- a/arch/powerpc/sysdev/mv64x60_pic.c
+++ b/arch/powerpc/sysdev/mv64x60_pic.c
@@ -70,7 +70,7 @@ static u32 mv64x60_cached_low_mask;
 static u32 mv64x60_cached_high_mask = MV64X60_HIGH_GPP_GROUPS;
 static u32 mv64x60_cached_gpp_mask;
 
-static struct irq_host *mv64x60_irq_host;
+static struct irq_domain *mv64x60_irq_host;
 
 /*
  * mv64x60_chip_low functions
@@ -208,7 +208,7 @@ static struct irq_chip *mv64x60_chips[] = {
         [MV64x60_LEVEL1_GPP]  = &mv64x60_chip_gpp,
 };
 
-static int mv64x60_host_map(struct irq_host *h, unsigned int virq,
+static int mv64x60_host_map(struct irq_domain *h, unsigned int virq,
                           irq_hw_number_t hwirq)
 {
         int level1;
@@ -223,7 +223,7 @@ static int mv64x60_host_map(struct irq_host *h, unsigned int virq,
         return 0;
 }
 
-static struct irq_host_ops mv64x60_host_ops = {
+static struct irq_domain_ops mv64x60_host_ops = {
         .map   = mv64x60_host_map,
 };
 
@@ -250,9 +250,8 @@ void __init mv64x60_init_irq(void)
         paddr = of_translate_address(np, reg);
         mv64x60_irq_reg_base = ioremap(paddr, reg[1]);
 
-        mv64x60_irq_host = irq_alloc_host(np, IRQ_HOST_MAP_LINEAR,
-                                          MV64x60_NUM_IRQS,
-                                          &mv64x60_host_ops, MV64x60_NUM_IRQS);
+        mv64x60_irq_host = irq_domain_add_linear(np, MV64x60_NUM_IRQS,
+                                          &mv64x60_host_ops, NULL);
 
         spin_lock_irqsave(&mv64x60_lock, flags);
         out_le32(mv64x60_gpp_reg_base + MV64x60_GPP_INTR_MASK,
diff --git a/arch/powerpc/sysdev/ppc4xx_pci.c b/arch/powerpc/sysdev/ppc4xx_pci.c
index 4f05f7542346..56e8b3c3c890 100644
--- a/arch/powerpc/sysdev/ppc4xx_pci.c
+++ b/arch/powerpc/sysdev/ppc4xx_pci.c
@@ -1050,6 +1050,74 @@ static struct ppc4xx_pciex_hwops ppc460ex_pcie_hwops __initdata =
         .check_link     = ppc4xx_pciex_check_link_sdr,
 };
 
+static int __init apm821xx_pciex_core_init(struct device_node *np)
+{
+        /* Return the number of pcie port */
+        return 1;
+}
+
+static int apm821xx_pciex_init_port_hw(struct ppc4xx_pciex_port *port)
+{
+        u32 val;
+
+        /*
+         * Do a software reset on PCIe ports.
+         * This code is to fix the issue that pci drivers doesn't re-assign
+         * bus number for PCIE devices after Uboot
+         * scanned and configured all the buses (eg. PCIE NIC IntelPro/1000
+         * PT quad port, SAS LSI 1064E)
+         */
+
+        mtdcri(SDR0, PESDR0_460EX_PHY_CTL_RST, 0x0);
+        mdelay(10);
+
+        if (port->endpoint)
+                val = PTYPE_LEGACY_ENDPOINT << 20;
+        else
+                val = PTYPE_ROOT_PORT << 20;
+
+        val |= LNKW_X1 << 12;
+
+        mtdcri(SDR0, port->sdr_base + PESDRn_DLPSET, val);
+        mtdcri(SDR0, port->sdr_base + PESDRn_UTLSET1, 0x00000000);
+        mtdcri(SDR0, port->sdr_base + PESDRn_UTLSET2, 0x01010000);
+
+        mtdcri(SDR0, PESDR0_460EX_L0CDRCTL, 0x00003230);
+        mtdcri(SDR0, PESDR0_460EX_L0DRV, 0x00000130);
+        mtdcri(SDR0, PESDR0_460EX_L0CLK, 0x00000006);
+
+        mtdcri(SDR0, PESDR0_460EX_PHY_CTL_RST, 0x10000000);
+        mdelay(50);
+        mtdcri(SDR0, PESDR0_460EX_PHY_CTL_RST, 0x30000000);
+
+        mtdcri(SDR0, port->sdr_base + PESDRn_RCSSET,
+                mfdcri(SDR0, port->sdr_base + PESDRn_RCSSET) |
+                (PESDRx_RCSSET_RSTGU | PESDRx_RCSSET_RSTPYN));
+
+        /* Poll for PHY reset */
+        val = PESDR0_460EX_RSTSTA - port->sdr_base;
+        if (ppc4xx_pciex_wait_on_sdr(port, val, 0x1, 1, 100)) {
+                printk(KERN_WARNING "%s: PCIE: Can't reset PHY\n", __func__);
+                return -EBUSY;
+        } else {
+                mtdcri(SDR0, port->sdr_base + PESDRn_RCSSET,
+                        (mfdcri(SDR0, port->sdr_base + PESDRn_RCSSET) &
+                        ~(PESDRx_RCSSET_RSTGU | PESDRx_RCSSET_RSTDL)) |
+                        PESDRx_RCSSET_RSTPYN);
+
+                port->has_ibpre = 1;
+                return 0;
+        }
+}
+
+static struct ppc4xx_pciex_hwops apm821xx_pcie_hwops __initdata = {
+        .want_sdr   = true,
+        .core_init      = apm821xx_pciex_core_init,
+        .port_init_hw   = apm821xx_pciex_init_port_hw,
+        .setup_utl      = ppc460ex_pciex_init_utl,
+        .check_link = ppc4xx_pciex_check_link_sdr,
+};
+
 static int __init ppc460sx_pciex_core_init(struct device_node *np)
 {
         /* HSS drive amplitude */
@@ -1362,6 +1430,8 @@ static int __init ppc4xx_pciex_check_core_init(struct device_node *np)
                 ppc4xx_pciex_hwops = &ppc460ex_pcie_hwops;
         if (of_device_is_compatible(np, "ibm,plb-pciex-460sx"))
                 ppc4xx_pciex_hwops = &ppc460sx_pcie_hwops;
+        if (of_device_is_compatible(np, "ibm,plb-pciex-apm821xx"))
+                ppc4xx_pciex_hwops = &apm821xx_pcie_hwops;
 #endif /* CONFIG_44x    */
 #ifdef CONFIG_40x
         if (of_device_is_compatible(np, "ibm,plb-pciex-405ex"))
diff --git a/arch/powerpc/sysdev/qe_lib/qe_ic.c b/arch/powerpc/sysdev/qe_lib/qe_ic.c
index 73034bd203c4..2fba6ef2f95e 100644
--- a/arch/powerpc/sysdev/qe_lib/qe_ic.c
+++ b/arch/powerpc/sysdev/qe_lib/qe_ic.c
@@ -245,13 +245,13 @@ static struct irq_chip qe_ic_irq_chip = {
         .irq_mask_ack = qe_ic_mask_irq,
 };
 
-static int qe_ic_host_match(struct irq_host *h, struct device_node *node)
+static int qe_ic_host_match(struct irq_domain *h, struct device_node *node)
 {
         /* Exact match, unless qe_ic node is NULL */
         return h->of_node == NULL || h->of_node == node;
 }
 
-static int qe_ic_host_map(struct irq_host *h, unsigned int virq,
+static int qe_ic_host_map(struct irq_domain *h, unsigned int virq,
                           irq_hw_number_t hw)
 {
         struct qe_ic *qe_ic = h->host_data;
@@ -272,23 +272,10 @@ static int qe_ic_host_map(struct irq_host *h, unsigned int virq,
         return 0;
 }
 
-static int qe_ic_host_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)
-{
-        *out_hwirq = intspec[0];
-        if (intsize > 1)
-                *out_flags = intspec[1];
-        else
-                *out_flags = IRQ_TYPE_NONE;
-        return 0;
-}
-
-static struct irq_host_ops qe_ic_host_ops = {
+static struct irq_domain_ops qe_ic_host_ops = {
         .match = qe_ic_host_match,
         .map = qe_ic_host_map,
-        .xlate = qe_ic_host_xlate,
+        .xlate = irq_domain_xlate_onetwocell,
 };
 
 /* Return an interrupt vector or NO_IRQ if no interrupt is pending. */
@@ -339,8 +326,8 @@ void __init qe_ic_init(struct device_node *node, unsigned int flags,
         if (qe_ic == NULL)
                 return;
 
-        qe_ic->irqhost = irq_alloc_host(node, IRQ_HOST_MAP_LINEAR,
-                                        NR_QE_IC_INTS, &qe_ic_host_ops, 0);
+        qe_ic->irqhost = irq_domain_add_linear(node, NR_QE_IC_INTS,
+                                               &qe_ic_host_ops, qe_ic);
         if (qe_ic->irqhost == NULL) {
                 kfree(qe_ic);
                 return;
@@ -348,7 +335,6 @@ void __init qe_ic_init(struct device_node *node, unsigned int flags,
 
         qe_ic->regs = ioremap(res.start, resource_size(&res));
 
-        qe_ic->irqhost->host_data = qe_ic;
         qe_ic->hc_irq = qe_ic_irq_chip;
 
         qe_ic->virq_high = irq_of_parse_and_map(node, 0);
diff --git a/arch/powerpc/sysdev/qe_lib/qe_ic.h b/arch/powerpc/sysdev/qe_lib/qe_ic.h
index c1361d005a8a..c327872ed35c 100644
--- a/arch/powerpc/sysdev/qe_lib/qe_ic.h
+++ b/arch/powerpc/sysdev/qe_lib/qe_ic.h
@@ -79,7 +79,7 @@ struct qe_ic {
         volatile u32 __iomem *regs;
 
         /* The remapper for this QEIC */
-        struct irq_host *irqhost;
+        struct irq_domain *irqhost;
 
         /* The "linux" controller struct */
         struct irq_chip hc_irq;
diff --git a/arch/powerpc/sysdev/tsi108_pci.c b/arch/powerpc/sysdev/tsi108_pci.c
index 4d18658116e5..188012c58f7f 100644
--- a/arch/powerpc/sysdev/tsi108_pci.c
+++ b/arch/powerpc/sysdev/tsi108_pci.c
@@ -51,7 +51,7 @@
 u32 tsi108_pci_cfg_base;
 static u32 tsi108_pci_cfg_phys;
 u32 tsi108_csr_vir_base;
-static struct irq_host *pci_irq_host;
+static struct irq_domain *pci_irq_host;
 
 extern u32 get_vir_csrbase(void);
 extern u32 tsi108_read_reg(u32 reg_offset);
@@ -376,7 +376,7 @@ static struct irq_chip tsi108_pci_irq = {
         .irq_unmask = tsi108_pci_irq_unmask,
 };
 
-static int pci_irq_host_xlate(struct irq_host *h, struct device_node *ct,
+static int pci_irq_host_xlate(struct irq_domain *h, struct device_node *ct,
                             const u32 *intspec, unsigned int intsize,
                             irq_hw_number_t *out_hwirq, unsigned int *out_flags)
 {
@@ -385,7 +385,7 @@ static int pci_irq_host_xlate(struct irq_host *h, struct device_node *ct,
         return 0;
 }
 
-static int pci_irq_host_map(struct irq_host *h, unsigned int virq,
+static int pci_irq_host_map(struct irq_domain *h, unsigned int virq,
                           irq_hw_number_t hw)
 {       unsigned int irq;
         DBG("%s(%d, 0x%lx)\n", __func__, virq, hw);
@@ -397,7 +397,7 @@ static int pci_irq_host_map(struct irq_host *h, unsigned int virq,
         return 0;
 }
 
-static struct irq_host_ops pci_irq_host_ops = {
+static struct irq_domain_ops pci_irq_domain_ops = {
         .map = pci_irq_host_map,
         .xlate = pci_irq_host_xlate,
 };
@@ -419,10 +419,9 @@ void __init tsi108_pci_int_init(struct device_node *node)
 {
         DBG("Tsi108_pci_int_init: initializing PCI interrupts\n");
 
-        pci_irq_host = irq_alloc_host(node, IRQ_HOST_MAP_LEGACY,
-                                      0, &pci_irq_host_ops, 0);
+        pci_irq_host = irq_domain_add_legacy_isa(node, &pci_irq_domain_ops, NULL);
         if (pci_irq_host == NULL) {
-                printk(KERN_ERR "pci_irq_host: failed to allocate irq host !\n");
+                printk(KERN_ERR "pci_irq_host: failed to allocate irq domain!\n");
                 return;
         }
 
diff --git a/arch/powerpc/sysdev/uic.c b/arch/powerpc/sysdev/uic.c
index 063c901b1265..92033936a8f7 100644
--- a/arch/powerpc/sysdev/uic.c
+++ b/arch/powerpc/sysdev/uic.c
@@ -49,7 +49,7 @@ struct uic {
         raw_spinlock_t lock;
 
         /* The remapper for this UIC */
-        struct irq_host *irqhost;
+        struct irq_domain       *irqhost;
 };
 
 static void uic_unmask_irq(struct irq_data *d)
@@ -174,7 +174,7 @@ static struct irq_chip uic_irq_chip = {
         .irq_set_type   = uic_set_irq_type,
 };
 
-static int uic_host_map(struct irq_host *h, unsigned int virq,
+static int uic_host_map(struct irq_domain *h, unsigned int virq,
                         irq_hw_number_t hw)
 {
         struct uic *uic = h->host_data;
@@ -190,21 +190,9 @@ static int uic_host_map(struct irq_host *h, unsigned int virq,
         return 0;
 }
 
-static int uic_host_xlate(struct irq_host *h, struct device_node *ct,
-                          const u32 *intspec, unsigned int intsize,
-                          irq_hw_number_t *out_hwirq, unsigned int *out_type)
-
-{
-        /* UIC intspecs must have 2 cells */
-        BUG_ON(intsize != 2);
-        *out_hwirq = intspec[0];
-        *out_type = intspec[1];
-        return 0;
-}
-
-static struct irq_host_ops uic_host_ops = {
+static struct irq_domain_ops uic_host_ops = {
         .map    = uic_host_map,
-        .xlate  = uic_host_xlate,
+        .xlate  = irq_domain_xlate_twocell,
 };
 
 void uic_irq_cascade(unsigned int virq, struct irq_desc *desc)
@@ -270,13 +258,11 @@ static struct uic * __init uic_init_one(struct device_node *node)
         }
         uic->dcrbase = *dcrreg;
 
-        uic->irqhost = irq_alloc_host(node, IRQ_HOST_MAP_LINEAR,
-                                      NR_UIC_INTS, &uic_host_ops, -1);
+        uic->irqhost = irq_domain_add_linear(node, NR_UIC_INTS, &uic_host_ops,
+                                             uic);
         if (! uic->irqhost)
                 return NULL; /* FIXME: panic? */
 
-        uic->irqhost->host_data = uic;
-
         /* Start with all interrupts disabled, level and non-critical */
         mtdcr(uic->dcrbase + UIC_ER, 0);
         mtdcr(uic->dcrbase + UIC_CR, 0);
diff --git a/arch/powerpc/sysdev/xics/xics-common.c b/arch/powerpc/sysdev/xics/xics-common.c
index d72eda6a4c05..ea5e204e3450 100644
--- a/arch/powerpc/sysdev/xics/xics-common.c
+++ b/arch/powerpc/sysdev/xics/xics-common.c
@@ -40,7 +40,7 @@ unsigned int xics_interrupt_server_size		= 8;
 
 DEFINE_PER_CPU(struct xics_cppr, xics_cppr);
 
-struct irq_host *xics_host;
+struct irq_domain *xics_host;
 
 static LIST_HEAD(ics_list);
 
@@ -212,16 +212,16 @@ void xics_migrate_irqs_away(void)
                 /* We can't set affinity on ISA interrupts */
                 if (virq < NUM_ISA_INTERRUPTS)
                         continue;
-                if (!virq_is_host(virq, xics_host))
-                        continue;
-                irq = (unsigned int)virq_to_hw(virq);
-                /* We need to get IPIs still. */
-                if (irq == XICS_IPI || irq == XICS_IRQ_SPURIOUS)
-                        continue;
                 desc = irq_to_desc(virq);
                 /* We only need to migrate enabled IRQS */
                 if (!desc || !desc->action)
                         continue;
+                if (desc->irq_data.domain != xics_host)
+                        continue;
+                irq = desc->irq_data.hwirq;
+                /* We need to get IPIs still. */
+                if (irq == XICS_IPI || irq == XICS_IRQ_SPURIOUS)
+                        continue;
                 chip = irq_desc_get_chip(desc);
                 if (!chip || !chip->irq_set_affinity)
                         continue;
@@ -301,7 +301,7 @@ int xics_get_irq_server(unsigned int virq, const struct cpumask *cpumask,
 }
 #endif /* CONFIG_SMP */
 
-static int xics_host_match(struct irq_host *h, struct device_node *node)
+static int xics_host_match(struct irq_domain *h, struct device_node *node)
 {
         struct ics *ics;
 
@@ -323,7 +323,7 @@ static struct irq_chip xics_ipi_chip = {
         .irq_unmask = xics_ipi_unmask,
 };
 
-static int xics_host_map(struct irq_host *h, unsigned int virq,
+static int xics_host_map(struct irq_domain *h, unsigned int virq,
                          irq_hw_number_t hw)
 {
         struct ics *ics;
@@ -351,7 +351,7 @@ static int xics_host_map(struct irq_host *h, unsigned int virq,
         return -EINVAL;
 }
 
-static int xics_host_xlate(struct irq_host *h, struct device_node *ct,
+static int xics_host_xlate(struct irq_domain *h, struct device_node *ct,
                            const u32 *intspec, unsigned int intsize,
                            irq_hw_number_t *out_hwirq, unsigned int *out_flags)
 
@@ -366,7 +366,7 @@ static int xics_host_xlate(struct irq_host *h, struct device_node *ct,
         return 0;
 }
 
-static struct irq_host_ops xics_host_ops = {
+static struct irq_domain_ops xics_host_ops = {
         .match = xics_host_match,
         .map = xics_host_map,
         .xlate = xics_host_xlate,
@@ -374,8 +374,7 @@ static struct irq_host_ops xics_host_ops = {
 
 static void __init xics_init_host(void)
 {
-        xics_host = irq_alloc_host(NULL, IRQ_HOST_MAP_TREE, 0, &xics_host_ops,
-                                   XICS_IRQ_SPURIOUS);
+        xics_host = irq_domain_add_tree(NULL, &xics_host_ops, NULL);
         BUG_ON(xics_host == NULL);
         irq_set_default_host(xics_host);
 }
diff --git a/arch/powerpc/sysdev/xilinx_intc.c b/arch/powerpc/sysdev/xilinx_intc.c
index 6183799754af..8d73c3c0bee6 100644
--- a/arch/powerpc/sysdev/xilinx_intc.c
+++ b/arch/powerpc/sysdev/xilinx_intc.c
@@ -40,7 +40,7 @@
 #define XINTC_IVR       24      /* Interrupt Vector */
 #define XINTC_MER       28      /* Master Enable */
 
-static struct irq_host *master_irqhost;
+static struct irq_domain *master_irqhost;
 
 #define XILINX_INTC_MAXIRQS     (32)
 
@@ -141,7 +141,7 @@ static struct irq_chip xilinx_intc_edge_irqchip = {
 /**
  * xilinx_intc_xlate - translate virq# from device tree interrupts property
  */
-static int xilinx_intc_xlate(struct irq_host *h, struct device_node *ct,
+static int xilinx_intc_xlate(struct irq_domain *h, struct device_node *ct,
                                 const u32 *intspec, unsigned int intsize,
                                 irq_hw_number_t *out_hwirq,
                                 unsigned int *out_flags)
@@ -161,7 +161,7 @@ static int xilinx_intc_xlate(struct irq_host *h, struct device_node *ct,
 
         return 0;
 }
-static int xilinx_intc_map(struct irq_host *h, unsigned int virq,
+static int xilinx_intc_map(struct irq_domain *h, unsigned int virq,
                                   irq_hw_number_t irq)
 {
         irq_set_chip_data(virq, h->host_data);
@@ -177,15 +177,15 @@ static int xilinx_intc_map(struct irq_host *h, unsigned int virq,
         return 0;
 }
 
-static struct irq_host_ops xilinx_intc_ops = {
+static struct irq_domain_ops xilinx_intc_ops = {
         .map = xilinx_intc_map,
         .xlate = xilinx_intc_xlate,
 };
 
-struct irq_host * __init
+struct irq_domain * __init
 xilinx_intc_init(struct device_node *np)
 {
-        struct irq_host * irq;
+        struct irq_domain * irq;
         void * regs;
 
         /* Find and map the intc registers */
@@ -200,12 +200,11 @@ xilinx_intc_init(struct device_node *np)
         out_be32(regs + XINTC_IAR, ~(u32) 0); /* Acknowledge pending irqs */
         out_be32(regs + XINTC_MER, 0x3UL); /* Turn on the Master Enable. */
 
-        /* Allocate and initialize an irq_host structure. */
-        irq = irq_alloc_host(np, IRQ_HOST_MAP_LINEAR, XILINX_INTC_MAXIRQS,
-                             &xilinx_intc_ops, -1);
+        /* Allocate and initialize an irq_domain structure. */
+        irq = irq_domain_add_linear(np, XILINX_INTC_MAXIRQS, &xilinx_intc_ops,
+                                    regs);
         if (!irq)
                 panic(__FILE__ ": Cannot allocate IRQ host\n");
-        irq->host_data = regs;
 
         return irq;
 }
diff --git a/arch/powerpc/xmon/ppc-opc.c b/arch/powerpc/xmon/ppc-opc.c
index af3780e52e76..6845e91ba04a 100644
--- a/arch/powerpc/xmon/ppc-opc.c
+++ b/arch/powerpc/xmon/ppc-opc.c
@@ -22,6 +22,7 @@
 
 #include <linux/stddef.h>
 #include <linux/kernel.h>
+#include <linux/bug.h>
 #include "nonstdio.h"
 #include "ppc.h"
 
diff --git a/arch/powerpc/xmon/spu-opc.c b/arch/powerpc/xmon/spu-opc.c
index 530df3d6d7b2..7d37597c4bcd 100644
--- a/arch/powerpc/xmon/spu-opc.c
+++ b/arch/powerpc/xmon/spu-opc.c
@@ -19,6 +19,7 @@
    51 Franklin Street - Fifth Floor, Boston, MA 02110-1301, USA.  */
 
 #include <linux/kernel.h>
+#include <linux/bug.h>
 #include "spu.h"
 
 /* This file holds the Spu opcode table */
diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c
index cb95eea74d3d..68a9cbbab450 100644
--- a/arch/powerpc/xmon/xmon.c
+++ b/arch/powerpc/xmon/xmon.c
@@ -39,7 +39,6 @@
 #include <asm/irq_regs.h>
 #include <asm/spu.h>
 #include <asm/spu_priv1.h>
-#include <asm/firmware.h>
 #include <asm/setjmp.h>
 #include <asm/reg.h>
 
@@ -1437,7 +1436,8 @@ static void excprint(struct pt_regs *fp)
 
         printf("  current = 0x%lx\n", current);
 #ifdef CONFIG_PPC64
-        printf("  paca    = 0x%lx\n", get_paca());
+        printf("  paca    = 0x%lx\t softe: %d\t irq_happened: 0x%02x\n",
+               local_paca, local_paca->soft_enabled, local_paca->irq_happened);
 #endif
         if (current) {
                 printf("    pid   = %ld, comm = %s\n",
@@ -1634,25 +1634,6 @@ static void super_regs(void)
                        mfspr(SPRN_DEC), mfspr(SPRN_SPRG2));
                 printf("sp   = "REG"  sprg3= "REG"\n", sp, mfspr(SPRN_SPRG3));
                 printf("toc  = "REG"  dar  = "REG"\n", toc, mfspr(SPRN_DAR));
-#ifdef CONFIG_PPC_ISERIES
-                if (firmware_has_feature(FW_FEATURE_ISERIES)) {
-                        struct paca_struct *ptrPaca;
-                        struct lppaca *ptrLpPaca;
-
-                        /* Dump out relevant Paca data areas. */
-                        printf("Paca: \n");
-                        ptrPaca = get_paca();
-
-                        printf("  Local Processor Control Area (LpPaca): \n");
-                        ptrLpPaca = ptrPaca->lppaca_ptr;
-                        printf("    Saved Srr0=%.16lx  Saved Srr1=%.16lx \n",
-                               ptrLpPaca->saved_srr0, ptrLpPaca->saved_srr1);
-                        printf("    Saved Gpr3=%.16lx  Saved Gpr4=%.16lx \n",
-                               ptrLpPaca->saved_gpr3, ptrLpPaca->saved_gpr4);
-                        printf("    Saved Gpr5=%.16lx \n",
-                                ptrLpPaca->gpr5_dword.saved_gpr5);
-                }
-#endif
 
                 return;
         }
@@ -2644,7 +2625,7 @@ static void dump_slb(void)
 static void dump_stab(void)
 {
         int i;
-        unsigned long *tmp = (unsigned long *)get_paca()->stab_addr;
+        unsigned long *tmp = (unsigned long *)local_paca->stab_addr;
 
         printf("Segment table contents of cpu %x\n", smp_processor_id());
 
@@ -2855,10 +2836,6 @@ static void dump_tlb_book3e(void)
 
 static void xmon_init(int enable)
 {
-#ifdef CONFIG_PPC_ISERIES
-        if (firmware_has_feature(FW_FEATURE_ISERIES))
-                return;
-#endif
         if (enable) {
                 __debugger = xmon;
                 __debugger_ipi = xmon_ipi;
@@ -2895,10 +2872,6 @@ static struct sysrq_key_op sysrq_xmon_op = {
 
 static int __init setup_xmon_sysrq(void)
 {
-#ifdef CONFIG_PPC_ISERIES
-        if (firmware_has_feature(FW_FEATURE_ISERIES))
-                return 0;
-#endif
         register_sysrq_key('x', &sysrq_xmon_op);
         return 0;
 }