Merge branch 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc

* 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc: (92 commits)
  powerpc: Remove unused 'protect4gb' boot parameter
  powerpc: Build-in e1000e for pseries & ppc64_defconfig
  powerpc/pseries: Make request_ras_irqs() available to other pseries code
  powerpc/numa: Use ibm,architecture-vec-5 to detect form 1 affinity
  powerpc/numa: Set a smaller value for RECLAIM_DISTANCE to enable zone reclaim
  powerpc: Use smt_snooze_delay=-1 to always busy loop
  powerpc: Remove check of ibm,smt-snooze-delay OF property
  powerpc/kdump: Fix race in kdump shutdown
  powerpc/kexec: Fix race in kexec shutdown
  powerpc/kexec: Speedup kexec hash PTE tear down
  powerpc/pseries: Add hcall to read 4 ptes at a time in real mode
  powerpc: Use more accurate limit for first segment memory allocations
  powerpc/kdump: Use chip->shutdown to disable IRQs
  powerpc/kdump: CPUs assume the context of the oopsing CPU
  powerpc/crashdump: Do not fail on NULL pointer dereferencing
  powerpc/eeh: Fix oops when probing in early boot
  powerpc/pci: Check devices status property when scanning OF tree
  powerpc/vio: Switch VIO Bus PM to use generic helpers
  powerpc: Avoid bad relocations in iSeries code
  powerpc: Use common cpu_die (fixes SMP+SUSPEND build)
  ...

Documentation/powerpc/dts-bindings/4xx/reboot.txt

+Reboot property to control system reboot on PPC4xx systems:
+
+By setting "reset_type" to one of the following values, the default
+software reset mechanism may be overidden. Here the possible values of
+"reset_type":
+
+      1 - PPC4xx core reset
+      2 - PPC4xx chip reset
+      3 - PPC4xx system reset (default)
+
+Example:
+
+		cpu@0 {
+			device_type = "cpu";
+			model = "PowerPC,440SPe";
+			...
+			reset-type = <2>;	/* Use chip-reset */
+		};

Documentation/powerpc/dts-bindings/fsl/8xxx_gpio.txt

@@ -11,7 +11,7 @@ Required properties:
   83xx, "fsl,mpc8572-gpio" for 85xx and "fsl,mpc8610-gpio" for 86xx.
 - #gpio-cells : Should be two. The first cell is the pin number and the
   second cell is used to specify optional parameters (currently unused).
- - interrupts : Interrupt mapping for GPIO IRQ (currently unused).
+ - interrupts : Interrupt mapping for GPIO IRQ.
  - interrupt-parent : Phandle for the interrupt controller that
    services interrupts for this device.
 - gpio-controller : Marks the port as GPIO controller.
@@ -38,3 +38,23 @@ Example of gpio-controller nodes for a MPC8347 SoC:
 
 See booting-without-of.txt for details of how to specify GPIO
 information for devices.
+
+To use GPIO pins as interrupt sources for peripherals, specify the
+GPIO controller as the interrupt parent and define GPIO number +
+trigger mode using the interrupts property, which is defined like
+this:
+
+interrupts = <number trigger>, where:
+ - number: GPIO pin (0..31)
+ - trigger: trigger mode:
+	2 = trigger on falling edge
+	3 = trigger on both edges
+
+Example of device using this is:
+
+	funkyfpga@0 {
+		compatible = "funky-fpga";
+		...
+		interrupts = <4 3>;
+		interrupt-parent = <&gpio1>;
+	};

arch/powerpc/Kconfig

@@ -140,6 +140,7 @@ config PPC
 	select HAVE_SYSCALL_WRAPPERS if PPC64
 	select GENERIC_ATOMIC64 if PPC32
 	select HAVE_PERF_EVENTS
+	select HAVE_REGS_AND_STACK_ACCESS_API
 
 config EARLY_PRINTK
 	bool

arch/powerpc/Kconfig.debug

@@ -44,6 +44,18 @@ config DEBUG_STACK_USAGE
 
 	  This option will slow down process creation somewhat.
 
+config DEBUG_PER_CPU_MAPS
+	bool "Debug access to per_cpu maps"
+	depends on DEBUG_KERNEL
+	depends on SMP
+	default n
+	---help---
+	  Say Y to verify that the per_cpu map being accessed has
+	  been setup.  Adds a fair amount of code to kernel memory
+	  and decreases performance.
+
+	  Say N if unsure.
+
 config HCALL_STATS
 	bool "Hypervisor call instrumentation"
 	depends on PPC_PSERIES && DEBUG_FS && TRACEPOINTS

arch/powerpc/boot/Makefile

@@ -44,6 +44,7 @@ $(obj)/cuboot-taishan.o: BOOTCFLAGS += -mcpu=405
 $(obj)/cuboot-katmai.o: BOOTCFLAGS += -mcpu=405
 $(obj)/cuboot-acadia.o: BOOTCFLAGS += -mcpu=405
 $(obj)/treeboot-walnut.o: BOOTCFLAGS += -mcpu=405
+$(obj)/treeboot-iss4xx.o: BOOTCFLAGS += -mcpu=405
 $(obj)/virtex405-head.o: BOOTAFLAGS += -mcpu=405
 
 
@@ -77,7 +78,7 @@ src-plat := of.c cuboot-52xx.c cuboot-824x.c cuboot-83xx.c cuboot-85xx.c holly.c
 		cuboot-warp.c cuboot-85xx-cpm2.c cuboot-yosemite.c simpleboot.c \
 		virtex405-head.S virtex.c redboot-83xx.c cuboot-sam440ep.c \
 		cuboot-acadia.c cuboot-amigaone.c cuboot-kilauea.c \
-		gamecube-head.S gamecube.c wii-head.S wii.c
+		gamecube-head.S gamecube.c wii-head.S wii.c treeboot-iss4xx.c
 src-boot := $(src-wlib) $(src-plat) empty.c
 
 src-boot := $(addprefix $(obj)/, $(src-boot))
@@ -169,7 +170,7 @@ quiet_cmd_wrap	= WRAP    $@
 		$(if $3, -s $3)$(if $4, -d $4)$(if $5, -i $5) vmlinux
 
 image-$(CONFIG_PPC_PSERIES)		+= zImage.pseries
-image-$(CONFIG_PPC_MAPLE)		+= zImage.pseries
+image-$(CONFIG_PPC_MAPLE)		+= zImage.maple
 image-$(CONFIG_PPC_IBM_CELL_BLADE)	+= zImage.pseries
 image-$(CONFIG_PPC_PS3)			+= dtbImage.ps3
 image-$(CONFIG_PPC_CELLEB)		+= zImage.pseries
@@ -206,6 +207,8 @@ image-$(CONFIG_TAISHAN)			+= cuImage.taishan
 image-$(CONFIG_KATMAI)			+= cuImage.katmai
 image-$(CONFIG_WARP)			+= cuImage.warp
 image-$(CONFIG_YOSEMITE)		+= cuImage.yosemite
+image-$(CONFIG_ISS4xx)			+= treeImage.iss4xx \
+					   treeImage.iss4xx-mpic
 
 # Board ports in arch/powerpc/platform/8xx/Kconfig
 image-$(CONFIG_MPC86XADS)		+= cuImage.mpc866ads
@@ -351,7 +354,7 @@ install: $(CONFIGURE) $(addprefix $(obj)/, $(image-y))
 clean-files += $(image-) $(initrd-) cuImage.* dtbImage.* treeImage.* \
 	zImage zImage.initrd zImage.chrp zImage.coff zImage.holly \
 	zImage.iseries zImage.miboot zImage.pmac zImage.pseries \
-	simpleImage.* otheros.bld *.dtb
+	zImage.maple simpleImage.* otheros.bld *.dtb
 
 # clean up files cached by wrapper
 clean-kernel := vmlinux.strip vmlinux.bin

arch/powerpc/boot/dts/iss4xx-mpic.dts

+/*
+ * Device Tree Source for IBM Embedded PPC 476 Platform
+ *
+ * Copyright 2010 Torez Smith, IBM Corporation.
+ *
+ * Based on earlier code:
+ *     Copyright (c) 2006, 2007 IBM Corp.
+ *     Josh Boyer <jwboyer@linux.vnet.ibm.com>, David Gibson <dwg@au1.ibm.com>
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2.  This program is licensed "as is" without
+ * any warranty of any kind, whether express or implied.
+ */
+
+/dts-v1/;
+
+/memreserve/ 0x01f00000 0x00100000;
+
+/ {
+	#address-cells = <2>;
+	#size-cells = <1>;
+	model = "ibm,iss-4xx";
+	compatible = "ibm,iss-4xx";
+	dcr-parent = <&{/cpus/cpu@0}>;
+
+	aliases {
+		serial0 = &UART0;
+	};
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		cpu@0 {
+			device_type = "cpu";
+			model = "PowerPC,4xx"; // real CPU changed in sim
+			reg = <0>;
+			clock-frequency = <100000000>; // 100Mhz :-)
+			timebase-frequency = <100000000>;
+			i-cache-line-size = <32>;
+			d-cache-line-size = <32>;
+			i-cache-size = <32768>;
+			d-cache-size = <32768>;
+			dcr-controller;
+			dcr-access-method = "native";
+			status = "ok";
+		};
+		cpu@1 {
+			device_type = "cpu";
+			model = "PowerPC,4xx"; // real CPU changed in sim
+			reg = <1>;
+			clock-frequency = <100000000>; // 100Mhz :-)
+			timebase-frequency = <100000000>;
+			i-cache-line-size = <32>;
+			d-cache-line-size = <32>;
+			i-cache-size = <32768>;
+			d-cache-size = <32768>;
+			dcr-controller;
+			dcr-access-method = "native";
+			status = "disabled";
+			enable-method = "spin-table";
+			cpu-release-addr = <0 0x01f00100>;
+		};
+		cpu@2 {
+			device_type = "cpu";
+			model = "PowerPC,4xx"; // real CPU changed in sim
+			reg = <2>;
+			clock-frequency = <100000000>; // 100Mhz :-)
+			timebase-frequency = <100000000>;
+			i-cache-line-size = <32>;
+			d-cache-line-size = <32>;
+			i-cache-size = <32768>;
+			d-cache-size = <32768>;
+			dcr-controller;
+			dcr-access-method = "native";
+			status = "disabled";
+			enable-method = "spin-table";
+			cpu-release-addr = <0 0x01f00200>;
+		};
+		cpu@3 {
+			device_type = "cpu";
+			model = "PowerPC,4xx"; // real CPU changed in sim
+			reg = <3>;
+			clock-frequency = <100000000>; // 100Mhz :-)
+			timebase-frequency = <100000000>;
+			i-cache-line-size = <32>;
+			d-cache-line-size = <32>;
+			i-cache-size = <32768>;
+			d-cache-size = <32768>;
+			dcr-controller;
+			dcr-access-method = "native";
+			status = "disabled";
+			enable-method = "spin-table";
+			cpu-release-addr = <0 0x01f00300>;
+		};
+	};
+
+	memory {
+		device_type = "memory";
+		reg =  <0x00000000 0x00000000 0x00000000>; // Filled in by zImage
+
+	};
+
+	MPIC: interrupt-controller {
+		compatible = "chrp,open-pic";
+		interrupt-controller;
+		dcr-reg = <0xffc00000 0x00030000>;
+		#address-cells = <0>;
+		#size-cells = <0>;
+		#interrupt-cells = <2>;
+
+	};
+
+	plb {
+		compatible = "ibm,plb-4xx", "ibm,plb4"; /* Could be PLB6, doesn't matter */
+		#address-cells = <2>;
+		#size-cells = <1>;
+		ranges;
+		clock-frequency = <0>; // Filled in by zImage
+
+		POB0: opb {
+			compatible = "ibm,opb-4xx", "ibm,opb";
+			#address-cells = <1>;
+			#size-cells = <1>;
+			/* Wish there was a nicer way of specifying a full 32-bit
+			   range */
+			ranges = <0x00000000 0x00000001 0x00000000 0x80000000
+				  0x80000000 0x00000001 0x80000000 0x80000000>;
+			clock-frequency = <0>; // Filled in by zImage
+			UART0: serial@40000200 {
+				device_type = "serial";
+				compatible = "ns16550a";
+				reg = <0x40000200 0x00000008>;
+				virtual-reg = <0xe0000200>;
+				clock-frequency = <11059200>;
+				current-speed = <115200>;
+				interrupt-parent = <&MPIC>;
+				interrupts = <0x0 0x2>;
+			};
+		};
+	};
+
+	nvrtc {
+		compatible = "ds1743-nvram", "ds1743", "rtc-ds1743";
+		reg = <0 0xEF703000 0x2000>;
+	};
+	iss-block {
+		compatible = "ibm,iss-sim-block-device";
+		reg = <0 0xEF701000 0x1000>;
+	};
+
+	chosen {
+		linux,stdout-path = "/plb/opb/serial@40000200";
+	};
+};

arch/powerpc/boot/dts/iss4xx.dts

+/*
+ * Device Tree Source for IBM Embedded PPC 476 Platform
+ *
+ * Copyright 2010 Torez Smith, IBM Corporation.
+ *
+ * Based on earlier code:
+ *    Copyright (c) 2006, 2007 IBM Corp.
+ *    Josh Boyer <jwboyer@linux.vnet.ibm.com>, David Gibson <dwg@au1.ibm.com>
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2.  This program is licensed "as is" without
+ * any warranty of any kind, whether express or implied.
+ */
+
+/dts-v1/;
+
+/ {
+	#address-cells = <2>;
+	#size-cells = <1>;
+	model = "ibm,iss-4xx";
+	compatible = "ibm,iss-4xx";
+	dcr-parent = <&{/cpus/cpu@0}>;
+
+	aliases {
+		serial0 = &UART0;
+	};
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		cpu@0 {
+			device_type = "cpu";
+			model = "PowerPC,4xx"; // real CPU changed in sim
+			reg = <0x00000000>;
+			clock-frequency = <100000000>; // 100Mhz :-)
+			timebase-frequency = <100000000>;
+			i-cache-line-size = <32>; // may need fixup in sim
+			d-cache-line-size = <32>; // may need fixup in sim
+			i-cache-size = <32768>; /* may need fixup in sim */
+			d-cache-size = <32768>; /* may need fixup in sim */
+			dcr-controller;
+			dcr-access-method = "native";
+		};
+	};
+
+	memory {
+		device_type = "memory";
+		reg = <0x00000000 0x00000000 0x00000000>; // Filled in by zImage
+	};
+
+	UIC0: interrupt-controller0 {
+		compatible = "ibm,uic-4xx", "ibm,uic";
+		interrupt-controller;
+		cell-index = <0>;
+		dcr-reg = <0x0c0 0x009>;
+		#address-cells = <0>;
+		#size-cells = <0>;
+		#interrupt-cells = <2>;
+
+	};
+
+	UIC1: interrupt-controller1 {
+		compatible = "ibm,uic-4xx", "ibm,uic";
+		interrupt-controller;
+		cell-index = <1>;
+		dcr-reg = <0x0d0 0x009>;
+		#address-cells = <0>;
+		#size-cells = <0>;
+		#interrupt-cells = <2>;
+		interrupts = <0x1e 0x4 0x1f 0x4>; /* cascade */
+		interrupt-parent = <&UIC0>;
+	};
+
+	plb {
+		compatible = "ibm,plb-4xx", "ibm,plb4"; /* Could be PLB6, doesn't matter */
+		#address-cells = <2>;
+		#size-cells = <1>;
+		ranges;
+		clock-frequency = <0>; // Filled in by zImage
+
+		POB0: opb {
+			compatible = "ibm,opb-4xx", "ibm,opb";
+			#address-cells = <1>;
+			#size-cells = <1>;
+			/* Wish there was a nicer way of specifying a full 32-bit
+			   range */
+			ranges = <0x00000000 0x00000001 0x00000000 0x80000000
+				  0x80000000 0x00000001 0x80000000 0x80000000>;
+			clock-frequency = <0>; // Filled in by zImage
+			UART0: serial@40000200 {
+				device_type = "serial";
+				compatible = "ns16550a";
+				reg = <0x40000200 0x00000008>;
+				virtual-reg = <0xe0000200>;
+				clock-frequency = <11059200>;
+				current-speed = <115200>;
+				interrupt-parent = <&UIC0>;
+				interrupts = <0x0 0x4>;
+			};
+		};
+	};
+
+	nvrtc {
+		compatible = "ds1743-nvram", "ds1743", "rtc-ds1743";
+		reg = <0 0xEF703000 0x2000>;
+	};
+	iss-block {
+		compatible = "ibm,iss-sim-block-device";
+		reg = <0 0xEF701000 0x1000>;
+	};
+
+	chosen {
+		linux,stdout-path = "/plb/opb/serial@40000200";
+	};
+};

arch/powerpc/boot/dts/mpc8315erdb.dts

@@ -292,7 +292,7 @@ crypto@30000 {
 			fsl,num-channels = <4>;
 			fsl,channel-fifo-len = <24>;
 			fsl,exec-units-mask = <0x97c>;
-			fsl,descriptor-types-mask = <0x3ab0abf>;
+			fsl,descriptor-types-mask = <0x3a30abf>;
 		};
 
 		sata@18000 {
@@ -463,4 +463,18 @@ pcie@0 {
 				  0 0x00800000>;
 		};
 	};
+
+	leds {
+		compatible = "gpio-leds";
+
+		pwr {
+			gpios = <&mcu_pio 0 0>;
+			default-state = "on";
+		};
+
+		hdd {
+			gpios = <&mcu_pio 1 0>;
+			linux,default-trigger = "ide-disk";
+		};
+	};
 };

arch/powerpc/boot/dts/mpc8377_rdb.dts

@@ -486,4 +486,18 @@ pcie@0 {
 				  0 0x00800000>;
 		};
 	};
+
+	leds {
+		compatible = "gpio-leds";
+
+		pwr {
+			gpios = <&mcu_pio 0 0>;
+			default-state = "on";
+		};
+
+		hdd {
+			gpios = <&mcu_pio 1 0>;
+			linux,default-trigger = "ide-disk";
+		};
+	};
 };

arch/powerpc/boot/dts/mpc8378_rdb.dts

@@ -470,4 +470,18 @@ pcie@0 {
 				  0 0x00800000>;
 		};
 	};
+
+	leds {
+		compatible = "gpio-leds";
+
+		pwr {
+			gpios = <&mcu_pio 0 0>;
+			default-state = "on";
+		};
+
+		hdd {
+			gpios = <&mcu_pio 1 0>;
+			linux,default-trigger = "ide-disk";
+		};
+	};
 };

arch/powerpc/boot/dts/mpc8379_rdb.dts

@@ -436,4 +436,18 @@ pci0: pci@e0008500 {
 		compatible = "fsl,mpc8349-pci";
 		device_type = "pci";
 	};
+
+	leds {
+		compatible = "gpio-leds";
+
+		pwr {
+			gpios = <&mcu_pio 0 0>;
+			default-state = "on";
+		};
+
+		hdd {
+			gpios = <&mcu_pio 1 0>;
+			linux,default-trigger = "ide-disk";
+		};
+	};
 };

arch/powerpc/boot/dts/p1020rdb.dts

@@ -19,6 +19,9 @@ / {
 	aliases {
 		serial0 = &serial0;
 		serial1 = &serial1;
+		ethernet0 = &enet0;
+		ethernet1 = &enet1;
+		ethernet2 = &enet2;
 		pci0 = &pci0;
 		pci1 = &pci1;
 	};
@@ -346,6 +349,122 @@ dma-channel@180 {
 			};
 		};
 
+		mdio@24000 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			compatible = "fsl,etsec2-mdio";
+			reg = <0x24000 0x1000 0xb0030 0x4>;
+
+			phy0: ethernet-phy@0 {
+				interrupt-parent = <&mpic>;
+				interrupts = <3 1>;
+				reg = <0x0>;
+			};
+
+			phy1: ethernet-phy@1 {
+				interrupt-parent = <&mpic>;
+				interrupts = <2 1>;
+				reg = <0x1>;
+			};
+		};
+
+		mdio@25000 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			compatible = "fsl,etsec2-tbi";
+			reg = <0x25000 0x1000 0xb1030 0x4>;
+
+			tbi0: tbi-phy@11 {
+				reg = <0x11>;
+				device_type = "tbi-phy";
+			};
+		};
+
+		enet0: ethernet@b0000 {
+			#address-cells = <1>;
+			#size-cells = <1>;
+			device_type = "network";
+			model = "eTSEC";
+			compatible = "fsl,etsec2";
+			fsl,num_rx_queues = <0x8>;
+			fsl,num_tx_queues = <0x8>;
+			local-mac-address = [ 00 00 00 00 00 00 ];
+			interrupt-parent = <&mpic>;
+			fixed-link = <1 1 1000 0 0>;
+			phy-connection-type = "rgmii-id";
+
+			queue-group@0 {
+				#address-cells = <1>;
+				#size-cells = <1>;
+				reg = <0xb0000 0x1000>;
+				interrupts = <29 2 30 2 34 2>;
+			};
+
+			queue-group@1 {
+				#address-cells = <1>;
+				#size-cells = <1>;
+				reg = <0xb4000 0x1000>;
+				interrupts = <17 2 18 2 24 2>;
+			};
+		};
+
+		enet1: ethernet@b1000 {
+			#address-cells = <1>;
+			#size-cells = <1>;
+			device_type = "network";
+			model = "eTSEC";
+			compatible = "fsl,etsec2";
+			fsl,num_rx_queues = <0x8>;
+			fsl,num_tx_queues = <0x8>;
+			local-mac-address = [ 00 00 00 00 00 00 ];
+			interrupt-parent = <&mpic>;
+			phy-handle = <&phy0>;
+			tbi-handle = <&tbi0>;
+			phy-connection-type = "sgmii";
+
+			queue-group@0 {
+				#address-cells = <1>;
+				#size-cells = <1>;
+				reg = <0xb1000 0x1000>;
+				interrupts = <35 2 36 2 40 2>;
+			};
+
+			queue-group@1 {
+				#address-cells = <1>;
+				#size-cells = <1>;
+				reg = <0xb5000 0x1000>;
+				interrupts = <51 2 52 2 67 2>;
+			};
+		};
+
+		enet2: ethernet@b2000 {
+			#address-cells = <1>;
+			#size-cells = <1>;
+			device_type = "network";
+			model = "eTSEC";
+			compatible = "fsl,etsec2";
+			fsl,num_rx_queues = <0x8>;
+			fsl,num_tx_queues = <0x8>;
+			local-mac-address = [ 00 00 00 00 00 00 ];
+			interrupt-parent = <&mpic>;
+			phy-handle = <&phy1>;
+			phy-connection-type = "rgmii-id";
+
+			queue-group@0 {
+				#address-cells = <1>;
+				#size-cells = <1>;
+				reg = <0xb2000 0x1000>;
+				interrupts = <31 2 32 2 33 2>;
+			};
+
+			queue-group@1 {
+				#address-cells = <1>;
+				#size-cells = <1>;
+				reg = <0xb6000 0x1000>;
+				interrupts = <25 2 26 2 27 2>;
+			};
+		};
+
 		usb@22000 {
 			#address-cells = <1>;
 			#size-cells = <0>;
@@ -356,6 +475,11 @@ 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 {
 			#address-cells = <1>;
 			#size-cells = <0>;
@@ -365,6 +489,7 @@ usb@23000 {
 			interrupts = <46 0x2>;
 			phy_type = "ulpi";
 		};
+		*/
 
 		sdhci@2e000 {
 			compatible = "fsl,p1020-esdhc", "fsl,esdhc";

arch/powerpc/boot/treeboot-iss4xx.c

+/*
+ * Copyright 2010 Ben. Herrenschmidt, IBM Corporation.
+ *
+ * Based on earlier code:
+ *   Copyright (C) Paul Mackerras 1997.
+ *
+ *   Matt Porter <mporter@kernel.crashing.org>
+ *   Copyright 2002-2005 MontaVista Software Inc.
+ *
+ *   Eugene Surovegin <eugene.surovegin@zultys.com> or <ebs@ebshome.net>
+ *   Copyright (c) 2003, 2004 Zultys Technologies
+ *
+ *    Copyright 2007 David Gibson, 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 <stdarg.h>
+#include <stddef.h>
+#include "types.h"
+#include "elf.h"
+#include "string.h"
+#include "stdio.h"
+#include "page.h"
+#include "ops.h"
+#include "reg.h"
+#include "io.h"
+#include "dcr.h"
+#include "4xx.h"
+#include "44x.h"
+#include "libfdt.h"
+
+BSS_STACK(4096);
+
+static void iss_4xx_fixups(void)
+{
+	ibm4xx_sdram_fixup_memsize();
+}
+
+#define SPRN_PIR	0x11E	/* Processor Indentification Register */
+void platform_init(void)
+{
+	unsigned long end_of_ram = 0x08000000;
+	unsigned long avail_ram = end_of_ram - (unsigned long)_end;
+	u32 pir_reg;
+
+	simple_alloc_init(_end, avail_ram, 128, 64);
+	platform_ops.fixups = iss_4xx_fixups;
+	platform_ops.exit = ibm44x_dbcr_reset;
+	pir_reg = mfspr(SPRN_PIR);
+	fdt_set_boot_cpuid_phys(_dtb_start, pir_reg);
+	fdt_init(_dtb_start);
+	serial_console_init();
+}

arch/powerpc/boot/wrapper

@@ -149,6 +149,10 @@ pseries)
     platformo=$object/of.o
     link_address='0x4000000'
     ;;
+maple)
+    platformo=$object/of.o
+    link_address='0x400000'
+    ;;
 pmac|chrp)
     platformo=$object/of.o
     ;;
@@ -237,6 +241,9 @@ gamecube|wii)
     link_address='0x600000'
     platformo="$object/$platform-head.o $object/$platform.o"
     ;;
+treeboot-iss4xx-mpic)
+    platformo="$object/treeboot-iss4xx.o"
+    ;;
 esac
 
 vmz="$tmpdir/`basename \"$kernel\"`.$ext"
@@ -321,7 +328,7 @@ fi
 
 # post-processing needed for some platforms
 case "$platform" in
-pseries|chrp)
+pseries|chrp|maple)
     $objbin/addnote "$ofile"
     ;;
 coff)

arch/powerpc/configs/ppc64_defconfig

@@ -988,7 +988,7 @@ CONFIG_ACENIC=m
 CONFIG_ACENIC_OMIT_TIGON_I=y
 # CONFIG_DL2K is not set
 CONFIG_E1000=y
-CONFIG_E1000E=m
+CONFIG_E1000E=y
 # CONFIG_IP1000 is not set
 # CONFIG_IGB is not set
 # CONFIG_NS83820 is not set

arch/powerpc/configs/pseries_defconfig

@@ -804,7 +804,7 @@ CONFIG_ACENIC=m
 CONFIG_ACENIC_OMIT_TIGON_I=y
 # CONFIG_DL2K is not set
 CONFIG_E1000=y
-CONFIG_E1000E=m
+CONFIG_E1000E=y
 # CONFIG_IP1000 is not set
 # CONFIG_IGB is not set
 # CONFIG_NS83820 is not set

arch/powerpc/include/asm/cache.h

@@ -12,8 +12,12 @@
 #define L1_CACHE_SHIFT		6
 #define MAX_COPY_PREFETCH	4
 #elif defined(CONFIG_PPC32)
-#define L1_CACHE_SHIFT		5
 #define MAX_COPY_PREFETCH	4
+#if defined(CONFIG_PPC_47x)
+#define L1_CACHE_SHIFT		7
+#else
+#define L1_CACHE_SHIFT		5
+#endif
 #else /* CONFIG_PPC64 */
 #define L1_CACHE_SHIFT		7
 #endif

arch/powerpc/include/asm/cputable.h

@@ -72,6 +72,7 @@ extern int machine_check_4xx(struct pt_regs *regs);
 extern int machine_check_440A(struct pt_regs *regs);
 extern int machine_check_e500(struct pt_regs *regs);
 extern int machine_check_e200(struct pt_regs *regs);
+extern int machine_check_47x(struct pt_regs *regs);
 
 /* NOTE WELL: Update identify_cpu() if fields are added or removed! */
 struct cpu_spec {
@@ -365,6 +366,7 @@ extern const char *powerpc_base_platform;
 #define CPU_FTRS_44X	(CPU_FTR_USE_TB | CPU_FTR_NODSISRALIGN | CPU_FTR_NOEXECUTE)
 #define CPU_FTRS_440x6	(CPU_FTR_USE_TB | CPU_FTR_NODSISRALIGN | CPU_FTR_NOEXECUTE | \
 	    CPU_FTR_INDEXED_DCR)
+#define CPU_FTRS_47X	(CPU_FTRS_440x6)
 #define CPU_FTRS_E200	(CPU_FTR_USE_TB | CPU_FTR_SPE_COMP | \
 	    CPU_FTR_NODSISRALIGN | CPU_FTR_COHERENT_ICACHE | \
 	    CPU_FTR_UNIFIED_ID_CACHE | CPU_FTR_NOEXECUTE)
@@ -453,6 +455,9 @@ enum {
 #ifdef CONFIG_44x
 	    CPU_FTRS_44X | CPU_FTRS_440x6 |
 #endif
+#ifdef CONFIG_PPC_47x
+	    CPU_FTRS_47X |
+#endif
 #ifdef CONFIG_E200
 	    CPU_FTRS_E200 |
 #endif

arch/powerpc/include/asm/hvcall.h

@@ -228,6 +228,7 @@
 #define H_JOIN			0x298
 #define H_VASI_STATE            0x2A4
 #define H_ENABLE_CRQ		0x2B0
+#define H_GET_EM_PARMS		0x2B8
 #define H_SET_MPP		0x2D0
 #define H_GET_MPP		0x2D4
 #define MAX_HCALL_OPCODE	H_GET_MPP
@@ -281,6 +282,7 @@ long plpar_hcall_raw(unsigned long opcode, unsigned long *retbuf, ...);
  */
 #define PLPAR_HCALL9_BUFSIZE 9
 long plpar_hcall9(unsigned long opcode, unsigned long *retbuf, ...);
+long plpar_hcall9_raw(unsigned long opcode, unsigned long *retbuf, ...);
 
 /* For hcall instrumentation.  One structure per-hcall, per-CPU */
 struct hcall_stats {

arch/powerpc/include/asm/kexec.h

@@ -31,6 +31,10 @@
 #define KEXEC_ARCH KEXEC_ARCH_PPC
 #endif
 
+#define KEXEC_STATE_NONE 0
+#define KEXEC_STATE_IRQS_OFF 1
+#define KEXEC_STATE_REAL_MODE 2
+
 #ifndef __ASSEMBLY__
 #include <linux/cpumask.h>
 #include <asm/reg.h>

arch/powerpc/include/asm/mmu-44x.h

@@ -40,7 +40,7 @@
 #define PPC44x_TLB_I		0x00000400      /* Caching is inhibited */
 #define PPC44x_TLB_M		0x00000200      /* Memory is coherent */
 #define PPC44x_TLB_G		0x00000100      /* Memory is guarded */
-#define PPC44x_TLB_E		0x00000080      /* Memory is guarded */
+#define PPC44x_TLB_E		0x00000080      /* Memory is little endian */
 
 #define PPC44x_TLB_PERM_MASK	0x0000003f
 #define PPC44x_TLB_UX		0x00000020      /* User execution */
@@ -53,6 +53,52 @@
 /* Number of TLB entries */
 #define PPC44x_TLB_SIZE		64
 
+/* 47x bits */
+#define PPC47x_MMUCR_TID	0x0000ffff
+#define PPC47x_MMUCR_STS	0x00010000
+
+/* Page identification fields */
+#define PPC47x_TLB0_EPN_MASK	0xfffff000      /* Effective Page Number */
+#define PPC47x_TLB0_VALID	0x00000800      /* Valid flag */
+#define PPC47x_TLB0_TS		0x00000400	/* Translation address space */
+#define PPC47x_TLB0_4K		0x00000000
+#define PPC47x_TLB0_16K		0x00000010
+#define PPC47x_TLB0_64K		0x00000030
+#define PPC47x_TLB0_1M		0x00000070
+#define PPC47x_TLB0_16M		0x000000f0
+#define PPC47x_TLB0_256M	0x000001f0
+#define PPC47x_TLB0_1G		0x000003f0
+#define PPC47x_TLB0_BOLTED_R	0x00000008	/* tlbre only */
+
+/* Translation fields */
+#define PPC47x_TLB1_RPN_MASK	0xfffff000      /* Real Page Number */
+#define PPC47x_TLB1_ERPN_MASK	0x000003ff
+
+/* Storage attribute and access control fields */
+#define PPC47x_TLB2_ATTR_MASK	0x0003ff80
+#define PPC47x_TLB2_IL1I	0x00020000      /* Memory is guarded */
+#define PPC47x_TLB2_IL1D	0x00010000      /* Memory is guarded */
+#define PPC47x_TLB2_U0		0x00008000      /* User 0 */
+#define PPC47x_TLB2_U1		0x00004000      /* User 1 */
+#define PPC47x_TLB2_U2		0x00002000      /* User 2 */
+#define PPC47x_TLB2_U3		0x00001000      /* User 3 */
+#define PPC47x_TLB2_W		0x00000800      /* Caching is write-through */
+#define PPC47x_TLB2_I		0x00000400      /* Caching is inhibited */
+#define PPC47x_TLB2_M		0x00000200      /* Memory is coherent */
+#define PPC47x_TLB2_G		0x00000100      /* Memory is guarded */
+#define PPC47x_TLB2_E		0x00000080      /* Memory is little endian */
+#define PPC47x_TLB2_PERM_MASK	0x0000003f
+#define PPC47x_TLB2_UX		0x00000020      /* User execution */
+#define PPC47x_TLB2_UW		0x00000010      /* User write */
+#define PPC47x_TLB2_UR		0x00000008      /* User read */
+#define PPC47x_TLB2_SX		0x00000004      /* Super execution */
+#define PPC47x_TLB2_SW		0x00000002      /* Super write */
+#define PPC47x_TLB2_SR		0x00000001      /* Super read */
+#define PPC47x_TLB2_U_RWX	(PPC47x_TLB2_UX|PPC47x_TLB2_UW|PPC47x_TLB2_UR)
+#define PPC47x_TLB2_S_RWX	(PPC47x_TLB2_SX|PPC47x_TLB2_SW|PPC47x_TLB2_SR)
+#define PPC47x_TLB2_S_RW	(PPC47x_TLB2_SW | PPC47x_TLB2_SR)
+#define PPC47x_TLB2_IMG		(PPC47x_TLB2_I | PPC47x_TLB2_M | PPC47x_TLB2_G)
+
 #ifndef __ASSEMBLY__
 
 extern unsigned int tlb_44x_hwater;
@@ -79,12 +125,15 @@ typedef struct {
 
 #if (PAGE_SHIFT == 12)
 #define PPC44x_TLBE_SIZE	PPC44x_TLB_4K
+#define PPC47x_TLBE_SIZE	PPC47x_TLB0_4K
 #define mmu_virtual_psize	MMU_PAGE_4K
 #elif (PAGE_SHIFT == 14)
 #define PPC44x_TLBE_SIZE	PPC44x_TLB_16K
+#define PPC47x_TLBE_SIZE	PPC47x_TLB0_16K
 #define mmu_virtual_psize	MMU_PAGE_16K
 #elif (PAGE_SHIFT == 16)
 #define PPC44x_TLBE_SIZE	PPC44x_TLB_64K
+#define PPC47x_TLBE_SIZE	PPC47x_TLB0_64K
 #define mmu_virtual_psize	MMU_PAGE_64K
 #elif (PAGE_SHIFT == 18)
 #define PPC44x_TLBE_SIZE	PPC44x_TLB_256K

arch/powerpc/include/asm/mmu.h

@@ -18,6 +18,7 @@
 #define MMU_FTR_TYPE_44x		ASM_CONST(0x00000008)
 #define MMU_FTR_TYPE_FSL_E		ASM_CONST(0x00000010)
 #define MMU_FTR_TYPE_3E			ASM_CONST(0x00000020)
+#define MMU_FTR_TYPE_47x		ASM_CONST(0x00000040)
 
 /*
  * This is individual features

arch/powerpc/include/asm/mmzone.h

@@ -30,7 +30,7 @@ extern struct pglist_data *node_data[];
  */
 
 extern int numa_cpu_lookup_table[];
-extern cpumask_t numa_cpumask_lookup_table[];
+extern cpumask_var_t node_to_cpumask_map[];
 #ifdef CONFIG_MEMORY_HOTPLUG
 extern unsigned long max_pfn;
 #endif

arch/powerpc/include/asm/mpic.h

@@ -463,9 +463,6 @@ extern void mpic_cpu_set_priority(int prio);
 /* Request IPIs on primary mpic */
 extern void mpic_request_ipis(void);
 
-/* Send an IPI (non offseted number 0..3) */
-extern void mpic_send_ipi(unsigned int ipi_no, unsigned int cpu_mask);
-
 /* Send a message (IPI) to a given target (cpu number or MSG_*) */
 void smp_mpic_message_pass(int target, int msg);
 

arch/powerpc/include/asm/paca.h

@@ -82,6 +82,7 @@ struct paca_struct {
 	s16 hw_cpu_id;			/* Physical processor number */
 	u8 cpu_start;			/* At startup, processor spins until */
 					/* this becomes non-zero. */
+	u8 kexec_state;		/* set when kexec down has irqs off */
 #ifdef CONFIG_PPC_STD_MMU_64
 	struct slb_shadow *slb_shadow_ptr;
 

arch/powerpc/include/asm/parport.h

@@ -19,6 +19,8 @@ static int __devinit parport_pc_find_nonpci_ports (int autoirq, int autodma)
 	u32 io1, io2;
 	int propsize;
 	int count = 0;
+	int virq;
+
 	for (np = NULL; (np = of_find_compatible_node(np,
 						      "parallel",
 						      "pnpPNP,400")) != NULL;) {
@@ -26,10 +28,13 @@ static int __devinit parport_pc_find_nonpci_ports (int autoirq, int autodma)
 		if (!prop || propsize > 6*sizeof(u32))
 			continue;
 		io1 = prop[1]; io2 = prop[2];
-		prop = of_get_property(np, "interrupts", NULL);
-		if (!prop)
+
+		virq = irq_of_parse_and_map(np, 0);
+		if (virq == NO_IRQ)
 			continue;
-		if (parport_pc_probe_port(io1, io2, prop[0], autodma, NULL, 0) != NULL)
+
+		if (parport_pc_probe_port(io1, io2, virq, autodma, NULL, 0)
+				!= NULL)
 			count++;
 	}
 	return count;

arch/powerpc/include/asm/pgalloc-64.h

@@ -11,6 +11,12 @@
 #include <linux/cpumask.h>
 #include <linux/percpu.h>
 
+struct vmemmap_backing {
+	struct vmemmap_backing *list;
+	unsigned long phys;
+	unsigned long virt_addr;
+};
+
 /*
  * Functions that deal with pagetables that could be at any level of
  * the table need to be passed an "index_size" so they know how to

arch/powerpc/include/asm/pgtable-ppc32.h

@@ -287,7 +287,7 @@ static inline void __ptep_set_access_flags(pte_t *ptep, pte_t entry)
 #define pmd_page_vaddr(pmd)	\
 	((unsigned long) __va(pmd_val(pmd) & PAGE_MASK))
 #define pmd_page(pmd)		\
-	(mem_map + (pmd_val(pmd) >> PAGE_SHIFT))
+	pfn_to_page(pmd_val(pmd) >> PAGE_SHIFT)
 #else
 #define pmd_page_vaddr(pmd)	\
 	((unsigned long) (pmd_val(pmd) & PAGE_MASK))

arch/powerpc/include/asm/ptrace.h

@@ -89,6 +89,7 @@ struct pt_regs {
 
 #define instruction_pointer(regs) ((regs)->nip)
 #define user_stack_pointer(regs) ((regs)->gpr[1])
+#define kernel_stack_pointer(regs) ((regs)->gpr[1])
 #define regs_return_value(regs) ((regs)->gpr[3])
 
 #ifdef CONFIG_SMP
@@ -141,6 +142,69 @@ do {									      \
 #define arch_has_block_step()	(!cpu_has_feature(CPU_FTR_601))
 #define ARCH_HAS_USER_SINGLE_STEP_INFO
 
+/*
+ * kprobe-based event tracer support
+ */
+
+#include <linux/stddef.h>
+#include <linux/thread_info.h>
+extern int regs_query_register_offset(const char *name);
+extern const char *regs_query_register_name(unsigned int offset);
+#define MAX_REG_OFFSET (offsetof(struct pt_regs, dsisr))
+
+/**
+ * regs_get_register() - get register value from its offset
+ * @regs:	   pt_regs from which register value is gotten
+ * @offset:    offset number of the register.
+ *
+ * regs_get_register returns the value of a register whose offset from @regs.
+ * The @offset is the offset of the register in struct pt_regs.
+ * If @offset is bigger than MAX_REG_OFFSET, this returns 0.
+ */
+static inline unsigned long regs_get_register(struct pt_regs *regs,
+						unsigned int offset)
+{
+	if (unlikely(offset > MAX_REG_OFFSET))
+		return 0;
+	return *(unsigned long *)((unsigned long)regs + offset);
+}
+
+/**
+ * regs_within_kernel_stack() - check the address in the stack
+ * @regs:      pt_regs which contains kernel stack pointer.
+ * @addr:      address which is checked.
+ *
+ * regs_within_kernel_stack() checks @addr is within the kernel stack page(s).
+ * If @addr is within the kernel stack, it returns true. If not, returns false.
+ */
+
+static inline bool regs_within_kernel_stack(struct pt_regs *regs,
+						unsigned long addr)
+{
+	return ((addr & ~(THREAD_SIZE - 1))  ==
+		(kernel_stack_pointer(regs) & ~(THREAD_SIZE - 1)));
+}
+
+/**
+ * regs_get_kernel_stack_nth() - get Nth entry of the stack
+ * @regs:	pt_regs which contains kernel stack pointer.
+ * @n:		stack entry number.
+ *
+ * regs_get_kernel_stack_nth() returns @n th entry of the kernel stack which
+ * is specified by @regs. If the @n th entry is NOT in the kernel stack,
+ * this returns 0.
+ */
+static inline unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs,
+						      unsigned int n)
+{
+	unsigned long *addr = (unsigned long *)kernel_stack_pointer(regs);
+	addr += n;
+	if (regs_within_kernel_stack(regs, (unsigned long)addr))
+		return *addr;
+	else
+		return 0;
+}
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* __KERNEL__ */

arch/powerpc/include/asm/reg.h

@@ -817,6 +817,7 @@
 #define PVR_403GC	0x00200200
 #define PVR_403GCX	0x00201400
 #define PVR_405GP	0x40110000
+#define PVR_476		0x11a52000
 #define PVR_STB03XXX	0x40310000
 #define PVR_NP405H	0x41410000
 #define PVR_NP405L	0x41610000
@@ -853,6 +854,9 @@
 #define PVR_8245	0x80811014
 #define PVR_8260	PVR_8240
 
+/* 476 Simulator seems to currently have the PVR of the 602... */
+#define PVR_476_ISS	0x00052000
+
 /* 64-bit processors */
 /* XXX the prefix should be PVR_, we'll do a global sweep to fix it one day */
 #define PV_NORTHSTAR	0x0033

arch/powerpc/include/asm/reg_booke.h

@@ -191,6 +191,10 @@
 #define MCSR_DCFP	0x01000000 /* D-Cache Flush Parity Error */
 #define MCSR_IMPE	0x00800000 /* Imprecise Machine Check Exception */
 
+#define PPC47x_MCSR_GPR	0x01000000 /* GPR parity error */
+#define PPC47x_MCSR_FPR	0x00800000 /* FPR parity error */
+#define PPC47x_MCSR_IPR	0x00400000 /* Imprecise Machine Check Exception */
+
 #ifdef CONFIG_E500
 #define MCSR_MCP 	0x80000000UL /* Machine Check Input Pin */
 #define MCSR_ICPERR 	0x40000000UL /* I-Cache Parity Error */
@@ -604,5 +608,25 @@
 #define DBCR_JOI	0x00000002	/* JTAG Serial Outbound Int. Enable */
 #define DBCR_JII	0x00000001	/* JTAG Serial Inbound Int. Enable */
 #endif /* 403GCX */
+
+/* Some 476 specific registers */
+#define SPRN_SSPCR		830
+#define SPRN_USPCR		831
+#define SPRN_ISPCR		829
+#define SPRN_MMUBE0		820
+#define MMUBE0_IBE0_SHIFT	24
+#define MMUBE0_IBE1_SHIFT	16
+#define MMUBE0_IBE2_SHIFT	8
+#define MMUBE0_VBE0		0x00000004
+#define MMUBE0_VBE1		0x00000002
+#define MMUBE0_VBE2		0x00000001
+#define SPRN_MMUBE1		821
+#define MMUBE1_IBE3_SHIFT	24
+#define MMUBE1_IBE4_SHIFT	16
+#define MMUBE1_IBE5_SHIFT	8
+#define MMUBE1_VBE3		0x00000004
+#define MMUBE1_VBE4		0x00000002
+#define MMUBE1_VBE5		0x00000001
+
 #endif /* __ASM_POWERPC_REG_BOOKE_H__ */
 #endif /* __KERNEL__ */

arch/powerpc/include/asm/smp.h

@@ -40,7 +40,7 @@ extern void smp_message_recv(int);
 DECLARE_PER_CPU(unsigned int, cpu_pvr);
 
 #ifdef CONFIG_HOTPLUG_CPU
-extern void fixup_irqs(cpumask_t map);
+extern void fixup_irqs(const struct cpumask *map);
 int generic_cpu_disable(void);
 int generic_cpu_enable(unsigned int cpu);
 void generic_cpu_die(unsigned int cpu);
@@ -68,8 +68,19 @@ static inline void set_hard_smp_processor_id(int cpu, int phys)
 }
 #endif
 
-DECLARE_PER_CPU(cpumask_t, cpu_sibling_map);
-DECLARE_PER_CPU(cpumask_t, cpu_core_map);
+DECLARE_PER_CPU(cpumask_var_t, cpu_sibling_map);
+DECLARE_PER_CPU(cpumask_var_t, cpu_core_map);
+
+static inline struct cpumask *cpu_sibling_mask(int cpu)
+{
+	return per_cpu(cpu_sibling_map, cpu);
+}
+
+static inline struct cpumask *cpu_core_mask(int cpu)
+{
+	return per_cpu(cpu_core_map, cpu);
+}
+
 extern int cpu_to_core_id(int cpu);
 
 /* Since OpenPIC has only 4 IPIs, we use slightly different message numbers.
@@ -93,7 +104,6 @@ void smp_init_pSeries(void);
 void smp_init_cell(void);
 void smp_init_celleb(void);
 void smp_setup_cpu_maps(void);
-void smp_setup_cpu_sibling_map(void);
 
 extern int __cpu_disable(void);
 extern void __cpu_die(unsigned int cpu);

arch/powerpc/include/asm/topology.h

@@ -8,6 +8,26 @@ struct device_node;
 
 #ifdef CONFIG_NUMA
 
+/*
+ * Before going off node we want the VM to try and reclaim from the local
+ * node. It does this if the remote distance is larger than RECLAIM_DISTANCE.
+ * With the default REMOTE_DISTANCE of 20 and the default RECLAIM_DISTANCE of
+ * 20, we never reclaim and go off node straight away.
+ *
+ * To fix this we choose a smaller value of RECLAIM_DISTANCE.
+ */
+#define RECLAIM_DISTANCE 10
+
+/*
+ * Before going off node we want the VM to try and reclaim from the local
+ * node. It does this if the remote distance is larger than RECLAIM_DISTANCE.
+ * With the default REMOTE_DISTANCE of 20 and the default RECLAIM_DISTANCE of
+ * 20, we never reclaim and go off node straight away.
+ *
+ * To fix this we choose a smaller value of RECLAIM_DISTANCE.
+ */
+#define RECLAIM_DISTANCE 10
+
 #include <asm/mmzone.h>
 
 static inline int cpu_to_node(int cpu)
@@ -19,7 +39,7 @@ static inline int cpu_to_node(int cpu)
 
 #define cpumask_of_node(node) ((node) == -1 ?				\
 			       cpu_all_mask :				\
-			       &numa_cpumask_lookup_table[node])
+			       node_to_cpumask_map[node])
 
 int of_node_to_nid(struct device_node *device);
 
@@ -102,8 +122,8 @@ static inline void sysfs_remove_device_from_node(struct sys_device *dev,
 #ifdef CONFIG_PPC64
 #include <asm/smp.h>
 
-#define topology_thread_cpumask(cpu)	(&per_cpu(cpu_sibling_map, cpu))
-#define topology_core_cpumask(cpu)	(&per_cpu(cpu_core_map, cpu))
+#define topology_thread_cpumask(cpu)	(per_cpu(cpu_sibling_map, cpu))
+#define topology_core_cpumask(cpu)	(per_cpu(cpu_core_map, cpu))
 #define topology_core_id(cpu)		(cpu_to_core_id(cpu))
 #endif
 #endif

arch/powerpc/kernel/asm-offsets.c

@@ -183,6 +183,7 @@ int main(void)
 #endif /* CONFIG_PPC_STD_MMU_64 */
 	DEFINE(PACAEMERGSP, offsetof(struct paca_struct, emergency_sp));
 	DEFINE(PACAHWCPUID, offsetof(struct paca_struct, hw_cpu_id));
+	DEFINE(PACAKEXECSTATE, offsetof(struct paca_struct, kexec_state));
 	DEFINE(PACA_STARTPURR, offsetof(struct paca_struct, startpurr));
 	DEFINE(PACA_STARTSPURR, offsetof(struct paca_struct, startspurr));
 	DEFINE(PACA_USER_TIME, offsetof(struct paca_struct, user_time));
@@ -447,6 +448,14 @@ int main(void)
 	DEFINE(PGD_T_LOG2, PGD_T_LOG2);
 	DEFINE(PTE_T_LOG2, PTE_T_LOG2);
 #endif
+#ifdef CONFIG_FSL_BOOKE
+	DEFINE(TLBCAM_SIZE, sizeof(struct tlbcam));
+	DEFINE(TLBCAM_MAS0, offsetof(struct tlbcam, MAS0));
+	DEFINE(TLBCAM_MAS1, offsetof(struct tlbcam, MAS1));
+	DEFINE(TLBCAM_MAS2, offsetof(struct tlbcam, MAS2));
+	DEFINE(TLBCAM_MAS3, offsetof(struct tlbcam, MAS3));
+	DEFINE(TLBCAM_MAS7, offsetof(struct tlbcam, MAS7));
+#endif
 
 #ifdef CONFIG_KVM_EXIT_TIMING
 	DEFINE(VCPU_TIMING_EXIT_TBU, offsetof(struct kvm_vcpu,

arch/powerpc/kernel/cputable.c

@@ -1701,6 +1701,35 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.machine_check		= machine_check_440A,
 		.platform		= "ppc440",
 	},
+	{ /* 476 core */
+		.pvr_mask		= 0xffff0000,
+		.pvr_value		= 0x11a50000,
+		.cpu_name		= "476",
+		.cpu_features		= CPU_FTRS_47X,
+		.cpu_user_features	= COMMON_USER_BOOKE |
+			PPC_FEATURE_HAS_FPU,
+		.mmu_features		= MMU_FTR_TYPE_47x |
+			MMU_FTR_USE_TLBIVAX_BCAST | MMU_FTR_LOCK_BCAST_INVAL,
+		.icache_bsize		= 32,
+		.dcache_bsize		= 128,
+		.machine_check		= machine_check_47x,
+		.platform		= "ppc470",
+	},
+	{ /* 476 iss */
+		.pvr_mask		= 0xffff0000,
+		.pvr_value		= 0x00050000,
+		.cpu_name		= "476",
+		.cpu_features		= CPU_FTRS_47X,
+		.cpu_user_features	= COMMON_USER_BOOKE |
+			PPC_FEATURE_HAS_FPU,
+		.cpu_user_features	= COMMON_USER_BOOKE,
+		.mmu_features		= MMU_FTR_TYPE_47x |
+			MMU_FTR_USE_TLBIVAX_BCAST | MMU_FTR_LOCK_BCAST_INVAL,
+		.icache_bsize		= 32,
+		.dcache_bsize		= 128,
+		.machine_check		= machine_check_47x,
+		.platform		= "ppc470",
+	},
 	{	/* default match */
 		.pvr_mask		= 0x00000000,
 		.pvr_value		= 0x00000000,

arch/powerpc/kernel/crash.c

@@ -162,6 +162,32 @@ static void crash_kexec_prepare_cpus(int cpu)
 	/* Leave the IPI callback set */
 }
 
+/* wait for all the CPUs to hit real mode but timeout if they don't come in */
+static void crash_kexec_wait_realmode(int cpu)
+{
+	unsigned int msecs;
+	int i;
+
+	msecs = 10000;
+	for (i=0; i < NR_CPUS && msecs > 0; i++) {
+		if (i == cpu)
+			continue;
+
+		while (paca[i].kexec_state < KEXEC_STATE_REAL_MODE) {
+			barrier();
+			if (!cpu_possible(i)) {
+				break;
+			}
+			if (!cpu_online(i)) {
+				break;
+			}
+			msecs--;
+			mdelay(1);
+		}
+	}
+	mb();
+}
+
 /*
  * This function will be called by secondary cpus or by kexec cpu
  * if soft-reset is activated to stop some CPUs.
@@ -347,10 +373,12 @@ int crash_shutdown_unregister(crash_shutdown_t handler)
 EXPORT_SYMBOL(crash_shutdown_unregister);
 
 static unsigned long crash_shutdown_buf[JMP_BUF_LEN];
+static int crash_shutdown_cpu = -1;
 
 static int handle_fault(struct pt_regs *regs)
 {
-	longjmp(crash_shutdown_buf, 1);
+	if (crash_shutdown_cpu == smp_processor_id())
+		longjmp(crash_shutdown_buf, 1);
 	return 0;
 }
 
@@ -375,11 +403,14 @@ void default_machine_crash_shutdown(struct pt_regs *regs)
 	for_each_irq(i) {
 		struct irq_desc *desc = irq_to_desc(i);
 
+		if (!desc || !desc->chip || !desc->chip->eoi)
+			continue;
+
 		if (desc->status & IRQ_INPROGRESS)
 			desc->chip->eoi(i);
 
 		if (!(desc->status & IRQ_DISABLED))
-			desc->chip->disable(i);
+			desc->chip->shutdown(i);
 	}
 
 	/*
@@ -388,6 +419,7 @@ void default_machine_crash_shutdown(struct pt_regs *regs)
 	 */
 	old_handler = __debugger_fault_handler;
 	__debugger_fault_handler = handle_fault;
+	crash_shutdown_cpu = smp_processor_id();
 	for (i = 0; crash_shutdown_handles[i]; i++) {
 		if (setjmp(crash_shutdown_buf) == 0) {
 			/*
@@ -401,6 +433,7 @@ void default_machine_crash_shutdown(struct pt_regs *regs)
 			asm volatile("sync; isync");
 		}
 	}
+	crash_shutdown_cpu = -1;
 	__debugger_fault_handler = old_handler;
 
 	/*
@@ -412,6 +445,7 @@ void default_machine_crash_shutdown(struct pt_regs *regs)
 	crash_kexec_prepare_cpus(crashing_cpu);
 	cpu_set(crashing_cpu, cpus_in_crash);
 	crash_kexec_stop_spus();
+	crash_kexec_wait_realmode(crashing_cpu);
 	if (ppc_md.kexec_cpu_down)
 		ppc_md.kexec_cpu_down(1, 0);
 }

arch/powerpc/kernel/entry_32.S

@@ -373,11 +373,13 @@ syscall_exit_cont:
 	bnel-	load_dbcr0
 #endif
 #ifdef CONFIG_44x
+BEGIN_MMU_FTR_SECTION
 	lis	r4,icache_44x_need_flush@ha
 	lwz	r5,icache_44x_need_flush@l(r4)
 	cmplwi	cr0,r5,0
 	bne-	2f
 1:
+END_MMU_FTR_SECTION_IFCLR(MMU_FTR_TYPE_47x)
 #endif /* CONFIG_44x */
 BEGIN_FTR_SECTION
 	lwarx	r7,0,r1
@@ -848,6 +850,9 @@ resume_kernel:
 	/* interrupts are hard-disabled at this point */
 restore:
 #ifdef CONFIG_44x
+BEGIN_MMU_FTR_SECTION
+	b	1f
+END_MMU_FTR_SECTION_IFSET(MMU_FTR_TYPE_47x)
 	lis	r4,icache_44x_need_flush@ha
 	lwz	r5,icache_44x_need_flush@l(r4)
 	cmplwi	cr0,r5,0

arch/powerpc/kernel/exceptions-64s.S

@@ -735,8 +735,11 @@ _STATIC(do_hash_page)
 	std	r3,_DAR(r1)
 	std	r4,_DSISR(r1)
 
-	andis.	r0,r4,0xa450		/* weird error? */
+	andis.	r0,r4,0xa410		/* weird error? */
 	bne-	handle_page_fault	/* if not, try to insert a HPTE */
+	andis.  r0,r4,DSISR_DABRMATCH@h
+	bne-    handle_dabr_fault
+
 BEGIN_FTR_SECTION
 	andis.	r0,r4,0x0020		/* Is it a segment table fault? */
 	bne-	do_ste_alloc		/* If so handle it */
@@ -823,6 +826,14 @@ END_FW_FTR_SECTION_IFCLR(FW_FEATURE_ISERIES)
 	bl	.raw_local_irq_restore
 	b	11f
 
+/* We have a data breakpoint exception - handle it */
+handle_dabr_fault:
+	ld      r4,_DAR(r1)
+	ld      r5,_DSISR(r1)
+	addi    r3,r1,STACK_FRAME_OVERHEAD
+	bl      .do_dabr
+	b       .ret_from_except_lite
+
 /* Here we have a page fault that hash_page can't handle. */
 handle_page_fault:
 	ENABLE_INTS

arch/powerpc/kernel/head_8xx.S

@@ -71,9 +71,6 @@ _ENTRY(_start);
  * in the first level table, but that would require many changes to the
  * Linux page directory/table functions that I don't want to do right now.
  *
- * I used to use SPRG2 for a temporary register in the TLB handler, but it
- * has since been put to other uses.  I now use a hack to save a register
- * and the CCR at memory location 0.....Someday I'll fix this.....
  *	-- Dan
  */
 	.globl	__start
@@ -302,8 +299,13 @@ InstructionTLBMiss:
 	DO_8xx_CPU6(0x3f80, r3)
 	mtspr	SPRN_M_TW, r10	/* Save a couple of working registers */
 	mfcr	r10
+#ifdef CONFIG_8xx_CPU6
 	stw	r10, 0(r0)
 	stw	r11, 4(r0)
+#else
+	mtspr	SPRN_DAR, r10
+	mtspr	SPRN_SPRG2, r11
+#endif
 	mfspr	r10, SPRN_SRR0	/* Get effective address of fault */
 #ifdef CONFIG_8xx_CPU15
 	addi	r11, r10, 0x1000
@@ -318,12 +320,16 @@ InstructionTLBMiss:
 	/* If we are faulting a kernel address, we have to use the
 	 * kernel page tables.
 	 */
+#ifdef CONFIG_MODULES
+	/* Only modules will cause ITLB Misses as we always
+	 * pin the first 8MB of kernel memory */
 	andi.	r11, r10, 0x0800	/* Address >= 0x80000000 */
 	beq	3f
 	lis	r11, swapper_pg_dir@h
 	ori	r11, r11, swapper_pg_dir@l
 	rlwimi	r10, r11, 0, 2, 19
 3:
+#endif
 	lwz	r11, 0(r10)	/* Get the level 1 entry */
 	rlwinm.	r10, r11,0,0,19	/* Extract page descriptor page address */
 	beq	2f		/* If zero, don't try to find a pte */
@@ -339,31 +345,35 @@ InstructionTLBMiss:
 	mfspr	r11, SPRN_MD_TWC	/* ....and get the pte address */
 	lwz	r10, 0(r11)	/* Get the pte */
 
+#ifdef CONFIG_SWAP
 	andi.	r11, r10, _PAGE_ACCESSED | _PAGE_PRESENT
 	cmpwi	cr0, r11, _PAGE_ACCESSED | _PAGE_PRESENT
 	bne-	cr0, 2f
-
-	/* Clear PP lsb, 0x400 */
-	rlwinm 	r10, r10, 0, 22, 20
-
+#endif
 	/* The Linux PTE won't go exactly into the MMU TLB.
-	 * Software indicator bits 22 and 28 must be clear.
+	 * Software indicator bits 21 and 28 must be clear.
 	 * Software indicator bits 24, 25, 26, and 27 must be
 	 * set.  All other Linux PTE bits control the behavior
 	 * of the MMU.
 	 */
 	li	r11, 0x00f0
-	rlwimi	r10, r11, 0, 24, 28	/* Set 24-27, clear 28 */
+	rlwimi	r10, r11, 0, 0x07f8	/* Set 24-27, clear 21-23,28 */
 	DO_8xx_CPU6(0x2d80, r3)
 	mtspr	SPRN_MI_RPN, r10	/* Update TLB entry */
 
-	mfspr	r10, SPRN_M_TW	/* Restore registers */
+	/* Restore registers */
+#ifndef CONFIG_8xx_CPU6
+	mfspr	r10, SPRN_DAR
+	mtcr	r10
+	mtspr	SPRN_DAR, r11	/* Tag DAR */
+	mfspr	r11, SPRN_SPRG2
+#else
 	lwz	r11, 0(r0)
 	mtcr	r11
 	lwz	r11, 4(r0)
-#ifdef CONFIG_8xx_CPU6
 	lwz	r3, 8(r0)
 #endif
+	mfspr	r10, SPRN_M_TW
 	rfi
 2:
 	mfspr	r11, SPRN_SRR1
@@ -373,13 +383,20 @@ InstructionTLBMiss:
 	rlwinm	r11, r11, 0, 0xffff
 	mtspr	SPRN_SRR1, r11
 
-	mfspr	r10, SPRN_M_TW	/* Restore registers */
+	/* Restore registers */
+#ifndef CONFIG_8xx_CPU6
+	mfspr	r10, SPRN_DAR
+	mtcr	r10
+	li	r11, 0x00f0
+	mtspr	SPRN_DAR, r11	/* Tag DAR */
+	mfspr	r11, SPRN_SPRG2
+#else
 	lwz	r11, 0(r0)
 	mtcr	r11
 	lwz	r11, 4(r0)
-#ifdef CONFIG_8xx_CPU6
 	lwz	r3, 8(r0)
 #endif
+	mfspr	r10, SPRN_M_TW
 	b	InstructionAccess
 
 	. = 0x1200
@@ -390,8 +407,13 @@ DataStoreTLBMiss:
 	DO_8xx_CPU6(0x3f80, r3)
 	mtspr	SPRN_M_TW, r10	/* Save a couple of working registers */
 	mfcr	r10
+#ifdef CONFIG_8xx_CPU6
 	stw	r10, 0(r0)
 	stw	r11, 4(r0)
+#else
+	mtspr	SPRN_DAR, r10
+	mtspr	SPRN_SPRG2, r11
+#endif
 	mfspr	r10, SPRN_M_TWB	/* Get level 1 table entry address */
 
 	/* If we are faulting a kernel address, we have to use the
@@ -438,15 +460,14 @@ DataStoreTLBMiss:
 	 * r11 = ((r10 & PRESENT) & ((r10 & ACCESSED) >> 5));
 	 * r10 = (r10 & ~PRESENT) | r11;
 	 */
+#ifdef CONFIG_SWAP
 	rlwinm	r11, r10, 32-5, _PAGE_PRESENT
 	and	r11, r11, r10
 	rlwimi	r10, r11, 0, _PAGE_PRESENT
-
+#endif
 	/* Honour kernel RO, User NA */
 	/* 0x200 == Extended encoding, bit 22 */
-	/* r11 =  (r10 & _PAGE_USER) >> 2 */
-	rlwinm	r11, r10, 32-2, 0x200
-	or	r10, r11, r10
+	rlwimi	r10, r10, 32-2, 0x200 /* Copy USER to bit 22, 0x200 */
 	/* r11 =  (r10 & _PAGE_RW) >> 1 */
 	rlwinm	r11, r10, 32-1, 0x200
 	or	r10, r11, r10
@@ -460,18 +481,24 @@ DataStoreTLBMiss:
 	 * of the MMU.
 	 */
 2:	li	r11, 0x00f0
-	mtspr	SPRN_DAR,r11	/* Tag DAR */
 	rlwimi	r10, r11, 0, 24, 28	/* Set 24-27, clear 28 */
 	DO_8xx_CPU6(0x3d80, r3)
 	mtspr	SPRN_MD_RPN, r10	/* Update TLB entry */
 
-	mfspr	r10, SPRN_M_TW	/* Restore registers */
+	/* Restore registers */
+#ifndef CONFIG_8xx_CPU6
+	mfspr	r10, SPRN_DAR
+	mtcr	r10
+	mtspr	SPRN_DAR, r11	/* Tag DAR */
+	mfspr	r11, SPRN_SPRG2
+#else
+	mtspr	SPRN_DAR, r11	/* Tag DAR */
 	lwz	r11, 0(r0)
 	mtcr	r11
 	lwz	r11, 4(r0)
-#ifdef CONFIG_8xx_CPU6
 	lwz	r3, 8(r0)
 #endif
+	mfspr	r10, SPRN_M_TW
 	rfi
 
 /* This is an instruction TLB error on the MPC8xx.  This could be due
@@ -683,9 +710,6 @@ start_here:
 	tophys(r4,r2)
 	addi	r4,r4,THREAD	/* init task's THREAD */
 	mtspr	SPRN_SPRG_THREAD,r4
-	li	r3,0
-	/* XXX What is that for ? SPRG2 appears otherwise unused on 8xx */
-	mtspr	SPRN_SPRG2,r3	/* 0 => r1 has kernel sp */
 
 	/* stack */
 	lis	r1,init_thread_union@ha

arch/powerpc/kernel/head_booke.h

 #ifndef __HEAD_BOOKE_H__
 #define __HEAD_BOOKE_H__
 
+#include <asm/ptrace.h>	/* for STACK_FRAME_REGS_MARKER */
 /*
  * Macros used for common Book-e exception handling
  */
@@ -48,6 +49,9 @@
 	stw	r10,0(r11);						     \
 	rlwinm	r9,r9,0,14,12;		/* clear MSR_WE (necessary?)	   */\
 	stw	r0,GPR0(r11);						     \
+	lis	r10, STACK_FRAME_REGS_MARKER@ha;/* exception frame marker */ \
+	addi	r10, r10, STACK_FRAME_REGS_MARKER@l;			     \
+	stw	r10, 8(r11);						     \
 	SAVE_4GPRS(3, r11);						     \
 	SAVE_2GPRS(7, r11)
 

arch/powerpc/kernel/head_fsl_booke.S

@@ -639,6 +639,13 @@ interrupt_base:
 	rlwinm	r12,r12,0,16,1
 	mtspr	SPRN_MAS1,r12
 
+	/* Make up the required permissions for kernel code */
+#ifdef CONFIG_PTE_64BIT
+	li	r13,_PAGE_PRESENT | _PAGE_BAP_SX
+	oris	r13,r13,_PAGE_ACCESSED@h
+#else
+	li	r13,_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_EXEC
+#endif
 	b	4f
 
 	/* Get the PGD for the current thread */
@@ -646,15 +653,15 @@ interrupt_base:
 	mfspr	r11,SPRN_SPRG_THREAD
 	lwz	r11,PGDIR(r11)
 
-4:
-	/* Make up the required permissions */
+	/* Make up the required permissions for user code */
 #ifdef CONFIG_PTE_64BIT
-	li	r13,_PAGE_PRESENT | _PAGE_EXEC
+	li	r13,_PAGE_PRESENT | _PAGE_BAP_UX
 	oris	r13,r13,_PAGE_ACCESSED@h
 #else
 	li	r13,_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_EXEC
 #endif
 
+4:
 	FIND_PTE
 	andc.	r13,r13,r11		/* Check permission */
 

arch/powerpc/kernel/iommu.c

@@ -43,20 +43,9 @@
 #define DBG(...)
 
 static int novmerge;
-static int protect4gb = 1;
 
 static void __iommu_free(struct iommu_table *, dma_addr_t, unsigned int);
 
-static int __init setup_protect4gb(char *str)
-{
-	if (strcmp(str, "on") == 0)
-		protect4gb = 1;
-	else if (strcmp(str, "off") == 0)
-		protect4gb = 0;
-
-	return 1;
-}
-
 static int __init setup_iommu(char *str)
 {
 	if (!strcmp(str, "novmerge"))
@@ -66,7 +55,6 @@ static int __init setup_iommu(char *str)
 	return 1;
 }
 
-__setup("protect4gb=", setup_protect4gb);
 __setup("iommu=", setup_iommu);
 
 static unsigned long iommu_range_alloc(struct device *dev,

arch/powerpc/kernel/irq.c

@@ -284,30 +284,33 @@ u64 arch_irq_stat_cpu(unsigned int cpu)
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
-void fixup_irqs(cpumask_t map)
+void fixup_irqs(const struct cpumask *map)
 {
 	struct irq_desc *desc;
 	unsigned int irq;
 	static int warned;
+	cpumask_var_t mask;
 
-	for_each_irq(irq) {
-		cpumask_t mask;
+	alloc_cpumask_var(&mask, GFP_KERNEL);
 
+	for_each_irq(irq) {
 		desc = irq_to_desc(irq);
 		if (desc && desc->status & IRQ_PER_CPU)
 			continue;
 
-		cpumask_and(&mask, desc->affinity, &map);
-		if (any_online_cpu(mask) == NR_CPUS) {
+		cpumask_and(mask, desc->affinity, map);
+		if (cpumask_any(mask) >= nr_cpu_ids) {
 			printk("Breaking affinity for irq %i\n", irq);
-			mask = map;
+			cpumask_copy(mask, map);
 		}
 		if (desc->chip->set_affinity)
-			desc->chip->set_affinity(irq, &mask);
+			desc->chip->set_affinity(irq, mask);
 		else if (desc->action && !(warned++))
 			printk("Cannot set affinity for irq %i\n", irq);
 	}
 
+	free_cpumask_var(mask);
+
 	local_irq_enable();
 	mdelay(1);
 	local_irq_disable();

arch/powerpc/kernel/kprobes.c

@@ -114,6 +114,9 @@ static void __kprobes prepare_singlestep(struct kprobe *p, struct pt_regs *regs)
 #ifdef CONFIG_PPC_ADV_DEBUG_REGS
 	regs->msr &= ~MSR_CE;
 	mtspr(SPRN_DBCR0, mfspr(SPRN_DBCR0) | DBCR0_IC | DBCR0_IDM);
+#ifdef CONFIG_PPC_47x
+	isync();
+#endif
 #endif
 
 	/*

arch/powerpc/kernel/lparcfg.c

@@ -38,7 +38,7 @@
 #include <asm/vio.h>
 #include <asm/mmu.h>
 
-#define MODULE_VERS "1.8"
+#define MODULE_VERS "1.9"
 #define MODULE_NAME "lparcfg"
 
 /* #define LPARCFG_DEBUG */
@@ -487,6 +487,14 @@ static void splpar_dispatch_data(struct seq_file *m)
 	seq_printf(m, "dispatch_dispersions=%lu\n", dispatch_dispersions);
 }
 
+static void parse_em_data(struct seq_file *m)
+{
+	unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
+
+	if (plpar_hcall(H_GET_EM_PARMS, retbuf) == H_SUCCESS)
+		seq_printf(m, "power_mode_data=%016lx\n", retbuf[0]);
+}
+
 static int pseries_lparcfg_data(struct seq_file *m, void *v)
 {
 	int partition_potential_processors;
@@ -541,6 +549,8 @@ static int pseries_lparcfg_data(struct seq_file *m, void *v)
 
 	seq_printf(m, "slb_size=%d\n", mmu_slb_size);
 
+	parse_em_data(m);
+
 	return 0;
 }
 

arch/powerpc/kernel/machine_kexec_64.c

@@ -155,33 +155,38 @@ void kexec_copy_flush(struct kimage *image)
 
 #ifdef CONFIG_SMP
 
-/* FIXME: we should schedule this function to be called on all cpus based
- * on calling the interrupts, but we would like to call it off irq level
- * so that the interrupt controller is clean.
- */
+static int kexec_all_irq_disabled = 0;
+
 static void kexec_smp_down(void *arg)
 {
+	local_irq_disable();
+	mb(); /* make sure our irqs are disabled before we say they are */
+	get_paca()->kexec_state = KEXEC_STATE_IRQS_OFF;
+	while(kexec_all_irq_disabled == 0)
+		cpu_relax();
+	mb(); /* make sure all irqs are disabled before this */
+	/*
+	 * Now every CPU has IRQs off, we can clear out any pending
+	 * IPIs and be sure that no more will come in after this.
+	 */
 	if (ppc_md.kexec_cpu_down)
 		ppc_md.kexec_cpu_down(0, 1);
 
-	local_irq_disable();
 	kexec_smp_wait();
 	/* NOTREACHED */
 }
 
-static void kexec_prepare_cpus(void)
+static void kexec_prepare_cpus_wait(int wait_state)
 {
 	int my_cpu, i, notified=-1;
 
-	smp_call_function(kexec_smp_down, NULL, /* wait */0);
 	my_cpu = get_cpu();
-
-	/* check the others cpus are now down (via paca hw cpu id == -1) */
+	/* Make sure each CPU has atleast made it to the state we need */
 	for (i=0; i < NR_CPUS; i++) {
 		if (i == my_cpu)
 			continue;
 
-		while (paca[i].hw_cpu_id != -1) {
+		while (paca[i].kexec_state < wait_state) {
 			barrier();
 			if (!cpu_possible(i)) {
 				printk("kexec: cpu %d hw_cpu_id %d is not"
@@ -201,20 +206,35 @@ static void kexec_prepare_cpus(void)
 			}
 			if (i != notified) {
 				printk( "kexec: waiting for cpu %d (physical"
-						" %d) to go down\n",
-						i, paca[i].hw_cpu_id);
+						" %d) to enter %i state\n",
+					i, paca[i].hw_cpu_id, wait_state);
 				notified = i;
 			}
 		}
 	}
+	mb();
+}
+
+static void kexec_prepare_cpus(void)
+{
+
+	smp_call_function(kexec_smp_down, NULL, /* wait */0);
+	local_irq_disable();
+	mb(); /* make sure IRQs are disabled before we say they are */
+	get_paca()->kexec_state = KEXEC_STATE_IRQS_OFF;
+
+	kexec_prepare_cpus_wait(KEXEC_STATE_IRQS_OFF);
+	/* we are sure every CPU has IRQs off at this point */
+	kexec_all_irq_disabled = 1;
 
 	/* after we tell the others to go down */
 	if (ppc_md.kexec_cpu_down)
 		ppc_md.kexec_cpu_down(0, 0);
 
-	put_cpu();
+	/* Before removing MMU mapings make sure all CPUs have entered real mode */
+	kexec_prepare_cpus_wait(KEXEC_STATE_REAL_MODE);
 
-	local_irq_disable();
+	put_cpu();
 }
 
 #else /* ! SMP */

arch/powerpc/kernel/misc_32.S

@@ -441,7 +441,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE)
 	addi	r3,r3,L1_CACHE_BYTES
 	bdnz	0b
 	sync
-#ifndef CONFIG_44x
+#ifdef CONFIG_44x
 	/* We don't flush the icache on 44x. Those have a virtual icache
 	 * and we don't have access to the virtual address here (it's
 	 * not the page vaddr but where it's mapped in user space). The
@@ -449,15 +449,19 @@ END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE)
 	 * a change in the address space occurs, before returning to
 	 * user space
 	 */
+BEGIN_MMU_FTR_SECTION
+	blr
+END_MMU_FTR_SECTION_IFSET(MMU_FTR_TYPE_44x)
+#endif /* CONFIG_44x */
 	mtctr	r4
 1:	icbi	0,r6
 	addi	r6,r6,L1_CACHE_BYTES
 	bdnz	1b
 	sync
 	isync
-#endif /* CONFIG_44x */
 	blr
 
+#ifndef CONFIG_BOOKE
 /*
  * Flush a particular page from the data cache to RAM, identified
  * by its physical address.  We turn off the MMU so we can just use
@@ -490,6 +494,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE)
 	mtmsr	r10				/* restore DR */
 	isync
 	blr
+#endif /* CONFIG_BOOKE */
 
 /*
  * Clear pages using the dcbz instruction, which doesn't cause any

arch/powerpc/kernel/misc_64.S

@@ -24,6 +24,7 @@
 #include <asm/asm-offsets.h>
 #include <asm/cputable.h>
 #include <asm/thread_info.h>
+#include <asm/kexec.h>
 
 	.text
 
@@ -471,6 +472,10 @@ _GLOBAL(kexec_wait)
 1:	mflr	r5
 	addi	r5,r5,kexec_flag-1b
 
+	li	r4,KEXEC_STATE_REAL_MODE
+	stb	r4,PACAKEXECSTATE(r13)
+	SYNC
+
 99:	HMT_LOW
 #ifdef CONFIG_KEXEC		/* use no memory without kexec */
 	lwz	r4,0(r5)
@@ -494,14 +499,11 @@ kexec_flag:
  * note: this is a terminal routine, it does not save lr
  *
  * get phys id from paca
- * set paca id to -1 to say we got here
  * switch to real mode
  * join other cpus in kexec_wait(phys_id)
  */
 _GLOBAL(kexec_smp_wait)
 	lhz	r3,PACAHWCPUID(r13)
-	li	r4,-1
-	sth	r4,PACAHWCPUID(r13)	/* let others know we left */
 	bl	real_mode
 	b	.kexec_wait
 

arch/powerpc/kernel/paca.c

@@ -18,6 +18,7 @@
 #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
  * field correctly */
@@ -97,6 +98,7 @@ void __init initialise_paca(struct paca_struct *new_paca, int cpu)
 	new_paca->kernelbase = (unsigned long) _stext;
 	new_paca->kernel_msr = MSR_KERNEL;
 	new_paca->hw_cpu_id = 0xffff;
+	new_paca->kexec_state = KEXEC_STATE_NONE;
 	new_paca->__current = &init_task;
 #ifdef CONFIG_PPC_STD_MMU_64
 	new_paca->slb_shadow_ptr = &slb_shadow[cpu];

arch/powerpc/kernel/pci_of_scan.c

@@ -310,6 +310,8 @@ static void __devinit __of_scan_bus(struct device_node *node,
 	/* Scan direct children */
 	for_each_child_of_node(node, child) {
 		pr_debug("  * %s\n", child->full_name);
+		if (!of_device_is_available(child))
+			continue;
 		reg = of_get_property(child, "reg", &reglen);
 		if (reg == NULL || reglen < 20)
 			continue;

arch/powerpc/kernel/process.c

@@ -371,6 +371,9 @@ int set_dabr(unsigned long dabr)
 	/* XXX should we have a CPU_FTR_HAS_DABR ? */
 #ifdef CONFIG_PPC_ADV_DEBUG_REGS
 	mtspr(SPRN_DAC1, dabr);
+#ifdef CONFIG_PPC_47x
+	isync();
+#endif
 #elif defined(CONFIG_PPC_BOOK3S)
 	mtspr(SPRN_DABR, dabr);
 #endif

arch/powerpc/kernel/ptrace.c

@@ -38,6 +38,109 @@
 #include <asm/pgtable.h>
 #include <asm/system.h>
 
+/*
+ * The parameter save area on the stack is used to store arguments being passed
+ * to callee function and is located at fixed offset from stack pointer.
+ */
+#ifdef CONFIG_PPC32
+#define PARAMETER_SAVE_AREA_OFFSET	24  /* bytes */
+#else /* CONFIG_PPC32 */
+#define PARAMETER_SAVE_AREA_OFFSET	48  /* bytes */
+#endif
+
+struct pt_regs_offset {
+	const char *name;
+	int offset;
+};
+
+#define STR(s)	#s			/* convert to string */
+#define REG_OFFSET_NAME(r) {.name = #r, .offset = offsetof(struct pt_regs, r)}
+#define GPR_OFFSET_NAME(num)	\
+	{.name = STR(gpr##num), .offset = offsetof(struct pt_regs, gpr[num])}
+#define REG_OFFSET_END {.name = NULL, .offset = 0}
+
+static const struct pt_regs_offset regoffset_table[] = {
+	GPR_OFFSET_NAME(0),
+	GPR_OFFSET_NAME(1),
+	GPR_OFFSET_NAME(2),
+	GPR_OFFSET_NAME(3),
+	GPR_OFFSET_NAME(4),
+	GPR_OFFSET_NAME(5),
+	GPR_OFFSET_NAME(6),
+	GPR_OFFSET_NAME(7),
+	GPR_OFFSET_NAME(8),
+	GPR_OFFSET_NAME(9),
+	GPR_OFFSET_NAME(10),
+	GPR_OFFSET_NAME(11),
+	GPR_OFFSET_NAME(12),
+	GPR_OFFSET_NAME(13),
+	GPR_OFFSET_NAME(14),
+	GPR_OFFSET_NAME(15),
+	GPR_OFFSET_NAME(16),
+	GPR_OFFSET_NAME(17),
+	GPR_OFFSET_NAME(18),
+	GPR_OFFSET_NAME(19),
+	GPR_OFFSET_NAME(20),
+	GPR_OFFSET_NAME(21),
+	GPR_OFFSET_NAME(22),
+	GPR_OFFSET_NAME(23),
+	GPR_OFFSET_NAME(24),
+	GPR_OFFSET_NAME(25),
+	GPR_OFFSET_NAME(26),
+	GPR_OFFSET_NAME(27),
+	GPR_OFFSET_NAME(28),
+	GPR_OFFSET_NAME(29),
+	GPR_OFFSET_NAME(30),
+	GPR_OFFSET_NAME(31),
+	REG_OFFSET_NAME(nip),
+	REG_OFFSET_NAME(msr),
+	REG_OFFSET_NAME(ctr),
+	REG_OFFSET_NAME(link),
+	REG_OFFSET_NAME(xer),
+	REG_OFFSET_NAME(ccr),
+#ifdef CONFIG_PPC64
+	REG_OFFSET_NAME(softe),
+#else
+	REG_OFFSET_NAME(mq),
+#endif
+	REG_OFFSET_NAME(trap),
+	REG_OFFSET_NAME(dar),
+	REG_OFFSET_NAME(dsisr),
+	REG_OFFSET_END,
+};
+
+/**
+ * regs_query_register_offset() - query register offset from its name
+ * @name:	the name of a register
+ *
+ * regs_query_register_offset() returns the offset of a register in struct
+ * pt_regs from its name. If the name is invalid, this returns -EINVAL;
+ */
+int regs_query_register_offset(const char *name)
+{
+	const struct pt_regs_offset *roff;
+	for (roff = regoffset_table; roff->name != NULL; roff++)
+		if (!strcmp(roff->name, name))
+			return roff->offset;
+	return -EINVAL;
+}
+
+/**
+ * regs_query_register_name() - query register name from its offset
+ * @offset:	the offset of a register in struct pt_regs.
+ *
+ * regs_query_register_name() returns the name of a register from its
+ * offset in struct pt_regs. If the @offset is invalid, this returns NULL;
+ */
+const char *regs_query_register_name(unsigned int offset)
+{
+	const struct pt_regs_offset *roff;
+	for (roff = regoffset_table; roff->name != NULL; roff++)
+		if (roff->offset == offset)
+			return roff->name;
+	return NULL;
+}
+
 /*
  * does not yet catch signals sent when the child dies.
  * in exit.c or in signal.c.

arch/powerpc/kernel/rtas.c

@@ -691,10 +691,14 @@ void rtas_os_term(char *str)
 {
 	int status;
 
-	if (panic_timeout)
-		return;
-
-	if (RTAS_UNKNOWN_SERVICE == rtas_token("ibm,os-term"))
+	/*
+	 * Firmware with the ibm,extended-os-term property is guaranteed
+	 * to always return from an ibm,os-term call. Earlier versions without
+	 * this property may terminate the partition which we want to avoid
+	 * since it interferes with panic_timeout.
+	 */
+	if (RTAS_UNKNOWN_SERVICE == rtas_token("ibm,os-term") ||
+	    RTAS_UNKNOWN_SERVICE == rtas_token("ibm,extended-os-term"))
 		return;
 
 	snprintf(rtas_os_term_buf, 2048, "OS panic: %s", str);
@@ -705,8 +709,7 @@ void rtas_os_term(char *str)
 	} while (rtas_busy_delay(status));
 
 	if (status != 0)
-		printk(KERN_EMERG "ibm,os-term call failed %d\n",
-			       status);
+		printk(KERN_EMERG "ibm,os-term call failed %d\n", status);
 }
 
 static int ibm_suspend_me_token = RTAS_UNKNOWN_SERVICE;

arch/powerpc/kernel/rtasd.c

@@ -411,9 +411,9 @@ static void rtas_event_scan(struct work_struct *w)
 
 	get_online_cpus();
 
-	cpu = next_cpu(smp_processor_id(), cpu_online_map);
-	if (cpu == NR_CPUS) {
-		cpu = first_cpu(cpu_online_map);
+	cpu = cpumask_next(smp_processor_id(), cpu_online_mask);
+        if (cpu >= nr_cpu_ids) {
+		cpu = cpumask_first(cpu_online_mask);
 
 		if (first_pass) {
 			first_pass = 0;
@@ -466,8 +466,8 @@ static void start_event_scan(void)
 	/* Retreive errors from nvram if any */
 	retreive_nvram_error_log();
 
-	schedule_delayed_work_on(first_cpu(cpu_online_map), &event_scan_work,
-				 event_scan_delay);
+	schedule_delayed_work_on(cpumask_first(cpu_online_mask),
+				 &event_scan_work, event_scan_delay);
 }
 
 static int __init rtas_init(void)
@@ -490,6 +490,12 @@ static int __init rtas_init(void)
 		return -ENODEV;
 	}
 
+	if (!rtas_event_scan_rate) {
+		/* Broken firmware: take a rate of zero to mean don't scan */
+		printk(KERN_DEBUG "rtasd: scan rate is 0, not scanning\n");
+		return 0;
+	}
+
 	/* Make room for the sequence number */
 	rtas_error_log_max = rtas_get_error_log_max();
 	rtas_error_log_buffer_max = rtas_error_log_max + sizeof(int);

arch/powerpc/kernel/setup-common.c

@@ -161,45 +161,44 @@ extern u32 cpu_temp_both(unsigned long cpu);
 DEFINE_PER_CPU(unsigned int, cpu_pvr);
 #endif
 
-static int show_cpuinfo(struct seq_file *m, void *v)
+static void show_cpuinfo_summary(struct seq_file *m)
 {
-	unsigned long cpu_id = (unsigned long)v - 1;
-	unsigned int pvr;
-	unsigned short maj;
-	unsigned short min;
-
-	if (cpu_id == NR_CPUS) {
-		struct device_node *root;
-		const char *model = NULL;
+	struct device_node *root;
+	const char *model = NULL;
 #if defined(CONFIG_SMP) && defined(CONFIG_PPC32)
-		unsigned long bogosum = 0;
-		int i;
-		for_each_online_cpu(i)
-			bogosum += loops_per_jiffy;
-		seq_printf(m, "total bogomips\t: %lu.%02lu\n",
-			   bogosum/(500000/HZ), bogosum/(5000/HZ) % 100);
+	unsigned long bogosum = 0;
+	int i;
+	for_each_online_cpu(i)
+		bogosum += loops_per_jiffy;
+	seq_printf(m, "total bogomips\t: %lu.%02lu\n",
+		   bogosum/(500000/HZ), bogosum/(5000/HZ) % 100);
 #endif /* CONFIG_SMP && CONFIG_PPC32 */
-		seq_printf(m, "timebase\t: %lu\n", ppc_tb_freq);
-		if (ppc_md.name)
-			seq_printf(m, "platform\t: %s\n", ppc_md.name);
-		root = of_find_node_by_path("/");
-		if (root)
-			model = of_get_property(root, "model", NULL);
-		if (model)
-			seq_printf(m, "model\t\t: %s\n", model);
-		of_node_put(root);
-
-		if (ppc_md.show_cpuinfo != NULL)
-			ppc_md.show_cpuinfo(m);
+	seq_printf(m, "timebase\t: %lu\n", ppc_tb_freq);
+	if (ppc_md.name)
+		seq_printf(m, "platform\t: %s\n", ppc_md.name);
+	root = of_find_node_by_path("/");
+	if (root)
+		model = of_get_property(root, "model", NULL);
+	if (model)
+		seq_printf(m, "model\t\t: %s\n", model);
+	of_node_put(root);
+
+	if (ppc_md.show_cpuinfo != NULL)
+		ppc_md.show_cpuinfo(m);
 
 #ifdef CONFIG_PPC32
-		/* Display the amount of memory */
-		seq_printf(m, "Memory\t\t: %d MB\n",
-			   (unsigned int)(total_memory / (1024 * 1024)));
+	/* Display the amount of memory */
+	seq_printf(m, "Memory\t\t: %d MB\n",
+		   (unsigned int)(total_memory / (1024 * 1024)));
 #endif
+}
 
-		return 0;
-	}
+static int show_cpuinfo(struct seq_file *m, void *v)
+{
+	unsigned long cpu_id = (unsigned long)v - 1;
+	unsigned int pvr;
+	unsigned short maj;
+	unsigned short min;
 
 	/* We only show online cpus: disable preempt (overzealous, I
 	 * knew) to prevent cpu going down. */
@@ -308,19 +307,28 @@ static int show_cpuinfo(struct seq_file *m, void *v)
 #endif
 
 	preempt_enable();
+
+	/* If this is the last cpu, print the summary */
+	if (cpumask_next(cpu_id, cpu_online_mask) >= nr_cpu_ids)
+		show_cpuinfo_summary(m);
+
 	return 0;
 }
 
 static void *c_start(struct seq_file *m, loff_t *pos)
 {
-	unsigned long i = *pos;
-
-	return i <= NR_CPUS ? (void *)(i + 1) : NULL;
+	if (*pos == 0)	/* just in case, cpu 0 is not the first */
+		*pos = cpumask_first(cpu_online_mask);
+	else
+		*pos = cpumask_next(*pos - 1, cpu_online_mask);
+	if ((*pos) < nr_cpu_ids)
+		return (void *)(unsigned long)(*pos + 1);
+	return NULL;
 }
 
 static void *c_next(struct seq_file *m, void *v, loff_t *pos)
 {
-	++*pos;
+	(*pos)++;
 	return c_start(m, pos);
 }
 
@@ -386,14 +394,14 @@ static void __init cpu_init_thread_core_maps(int tpc)
 
 /**
  * setup_cpu_maps - initialize the following cpu maps:
- *                  cpu_possible_map
- *                  cpu_present_map
+ *                  cpu_possible_mask
+ *                  cpu_present_mask
  *
  * Having the possible map set up early allows us to restrict allocations
  * of things like irqstacks to num_possible_cpus() rather than NR_CPUS.
  *
  * We do not initialize the online map here; cpus set their own bits in
- * cpu_online_map as they come up.
+ * cpu_online_mask as they come up.
  *
  * This function is valid only for Open Firmware systems.  finish_device_tree
  * must be called before using this.

arch/powerpc/kernel/setup_64.c

@@ -424,9 +424,18 @@ void __init setup_system(void)
 	DBG(" <- setup_system()\n");
 }
 
+static u64 slb0_limit(void)
+{
+	if (cpu_has_feature(CPU_FTR_1T_SEGMENT)) {
+		return 1UL << SID_SHIFT_1T;
+	}
+	return 1UL << SID_SHIFT;
+}
+
 #ifdef CONFIG_IRQSTACKS
 static void __init irqstack_early_init(void)
 {
+	u64 limit = slb0_limit();
 	unsigned int i;
 
 	/*
@@ -436,10 +445,10 @@ static void __init irqstack_early_init(void)
 	for_each_possible_cpu(i) {
 		softirq_ctx[i] = (struct thread_info *)
 			__va(lmb_alloc_base(THREAD_SIZE,
-					    THREAD_SIZE, 0x10000000));
+					    THREAD_SIZE, limit));
 		hardirq_ctx[i] = (struct thread_info *)
 			__va(lmb_alloc_base(THREAD_SIZE,
-					    THREAD_SIZE, 0x10000000));
+					    THREAD_SIZE, limit));
 	}
 }
 #else
@@ -470,7 +479,7 @@ static void __init exc_lvl_early_init(void)
  */
 static void __init emergency_stack_init(void)
 {
-	unsigned long limit;
+	u64 limit;
 	unsigned int i;
 
 	/*
@@ -482,7 +491,7 @@ static void __init emergency_stack_init(void)
 	 * bringup, we need to get at them in real mode. This means they
 	 * must also be within the RMO region.
 	 */
-	limit = min(0x10000000ULL, lmb.rmo_size);
+	limit = min(slb0_limit(), lmb.rmo_size);
 
 	for_each_possible_cpu(i) {
 		unsigned long sp;
@@ -573,12 +582,6 @@ void ppc64_boot_msg(unsigned int src, const char *msg)
 	printk("[boot]%04x %s\n", src, msg);
 }
 
-void cpu_die(void)
-{
-	if (ppc_md.cpu_die)
-		ppc_md.cpu_die();
-}
-
 #ifdef CONFIG_SMP
 #define PCPU_DYN_SIZE		()
 

arch/powerpc/kernel/smp.c

@@ -59,8 +59,8 @@
 
 struct thread_info *secondary_ti;
 
-DEFINE_PER_CPU(cpumask_t, cpu_sibling_map) = CPU_MASK_NONE;
-DEFINE_PER_CPU(cpumask_t, cpu_core_map) = CPU_MASK_NONE;
+DEFINE_PER_CPU(cpumask_var_t, cpu_sibling_map);
+DEFINE_PER_CPU(cpumask_var_t, cpu_core_map);
 
 EXPORT_PER_CPU_SYMBOL(cpu_sibling_map);
 EXPORT_PER_CPU_SYMBOL(cpu_core_map);
@@ -271,6 +271,16 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
 	smp_store_cpu_info(boot_cpuid);
 	cpu_callin_map[boot_cpuid] = 1;
 
+	for_each_possible_cpu(cpu) {
+		zalloc_cpumask_var_node(&per_cpu(cpu_sibling_map, cpu),
+					GFP_KERNEL, cpu_to_node(cpu));
+		zalloc_cpumask_var_node(&per_cpu(cpu_core_map, cpu),
+					GFP_KERNEL, cpu_to_node(cpu));
+	}
+
+	cpumask_set_cpu(boot_cpuid, cpu_sibling_mask(boot_cpuid));
+	cpumask_set_cpu(boot_cpuid, cpu_core_mask(boot_cpuid));
+
 	if (smp_ops)
 		if (smp_ops->probe)
 			max_cpus = smp_ops->probe();
@@ -289,10 +299,6 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
 void __devinit smp_prepare_boot_cpu(void)
 {
 	BUG_ON(smp_processor_id() != boot_cpuid);
-
-	set_cpu_online(boot_cpuid, true);
-	cpu_set(boot_cpuid, per_cpu(cpu_sibling_map, boot_cpuid));
-	cpu_set(boot_cpuid, per_cpu(cpu_core_map, boot_cpuid));
 #ifdef CONFIG_PPC64
 	paca[boot_cpuid].__current = current;
 #endif
@@ -313,7 +319,7 @@ int generic_cpu_disable(void)
 	set_cpu_online(cpu, false);
 #ifdef CONFIG_PPC64
 	vdso_data->processorCount--;
-	fixup_irqs(cpu_online_map);
+	fixup_irqs(cpu_online_mask);
 #endif
 	return 0;
 }
@@ -333,7 +339,7 @@ int generic_cpu_enable(unsigned int cpu)
 		cpu_relax();
 
 #ifdef CONFIG_PPC64
-	fixup_irqs(cpu_online_map);
+	fixup_irqs(cpu_online_mask);
 	/* counter the irq disable in fixup_irqs */
 	local_irq_enable();
 #endif
@@ -462,7 +468,7 @@ int cpu_to_core_id(int cpu)
 	return id;
 }
 
-/* Must be called when no change can occur to cpu_present_map,
+/* Must be called when no change can occur to cpu_present_mask,
  * i.e. during cpu online or offline.
  */
 static struct device_node *cpu_to_l2cache(int cpu)
@@ -495,6 +501,14 @@ int __devinit start_secondary(void *unused)
 	current->active_mm = &init_mm;
 
 	smp_store_cpu_info(cpu);
+
+#if defined(CONFIG_BOOKE) || defined(CONFIG_40x)
+	/* Clear any pending timer interrupts */
+	mtspr(SPRN_TSR, TSR_ENW | TSR_WIS | TSR_DIS | TSR_FIS);
+
+	/* Enable decrementer interrupt */
+	mtspr(SPRN_TCR, TCR_DIE);
+#endif
 	set_dec(tb_ticks_per_jiffy);
 	preempt_disable();
 	cpu_callin_map[cpu] = 1;
@@ -517,15 +531,15 @@ int __devinit start_secondary(void *unused)
 	for (i = 0; i < threads_per_core; i++) {
 		if (cpu_is_offline(base + i))
 			continue;
-		cpu_set(cpu, per_cpu(cpu_sibling_map, base + i));
-		cpu_set(base + i, per_cpu(cpu_sibling_map, cpu));
+		cpumask_set_cpu(cpu, cpu_sibling_mask(base + i));
+		cpumask_set_cpu(base + i, cpu_sibling_mask(cpu));
 
 		/* cpu_core_map should be a superset of
 		 * cpu_sibling_map even if we don't have cache
 		 * information, so update the former here, too.
 		 */
-		cpu_set(cpu, per_cpu(cpu_core_map, base +i));
-		cpu_set(base + i, per_cpu(cpu_core_map, cpu));
+		cpumask_set_cpu(cpu, cpu_core_mask(base + i));
+		cpumask_set_cpu(base + i, cpu_core_mask(cpu));
 	}
 	l2_cache = cpu_to_l2cache(cpu);
 	for_each_online_cpu(i) {
@@ -533,8 +547,8 @@ int __devinit start_secondary(void *unused)
 		if (!np)
 			continue;
 		if (np == l2_cache) {
-			cpu_set(cpu, per_cpu(cpu_core_map, i));
-			cpu_set(i, per_cpu(cpu_core_map, cpu));
+			cpumask_set_cpu(cpu, cpu_core_mask(i));
+			cpumask_set_cpu(i, cpu_core_mask(cpu));
 		}
 		of_node_put(np);
 	}
@@ -554,19 +568,22 @@ int setup_profiling_timer(unsigned int multiplier)
 
 void __init smp_cpus_done(unsigned int max_cpus)
 {
-	cpumask_t old_mask;
+	cpumask_var_t old_mask;
 
 	/* We want the setup_cpu() here to be called from CPU 0, but our
 	 * init thread may have been "borrowed" by another CPU in the meantime
 	 * se we pin us down to CPU 0 for a short while
 	 */
-	old_mask = current->cpus_allowed;
-	set_cpus_allowed(current, cpumask_of_cpu(boot_cpuid));
+	alloc_cpumask_var(&old_mask, GFP_NOWAIT);
+	cpumask_copy(old_mask, &current->cpus_allowed);
+	set_cpus_allowed_ptr(current, cpumask_of(boot_cpuid));
 	
 	if (smp_ops && smp_ops->setup_cpu)
 		smp_ops->setup_cpu(boot_cpuid);
 
-	set_cpus_allowed(current, old_mask);
+	set_cpus_allowed_ptr(current, old_mask);
+
+	free_cpumask_var(old_mask);
 
 	snapshot_timebases();
 
@@ -591,10 +608,10 @@ int __cpu_disable(void)
 	/* Update sibling maps */
 	base = cpu_first_thread_in_core(cpu);
 	for (i = 0; i < threads_per_core; i++) {
-		cpu_clear(cpu, per_cpu(cpu_sibling_map, base + i));
-		cpu_clear(base + i, per_cpu(cpu_sibling_map, cpu));
-		cpu_clear(cpu, per_cpu(cpu_core_map, base +i));
-		cpu_clear(base + i, per_cpu(cpu_core_map, cpu));
+		cpumask_clear_cpu(cpu, cpu_sibling_mask(base + i));
+		cpumask_clear_cpu(base + i, cpu_sibling_mask(cpu));
+		cpumask_clear_cpu(cpu, cpu_core_mask(base + i));
+		cpumask_clear_cpu(base + i, cpu_core_mask(cpu));
 	}
 
 	l2_cache = cpu_to_l2cache(cpu);
@@ -603,8 +620,8 @@ int __cpu_disable(void)
 		if (!np)
 			continue;
 		if (np == l2_cache) {
-			cpu_clear(cpu, per_cpu(cpu_core_map, i));
-			cpu_clear(i, per_cpu(cpu_core_map, cpu));
+			cpumask_clear_cpu(cpu, cpu_core_mask(i));
+			cpumask_clear_cpu(i, cpu_core_mask(cpu));
 		}
 		of_node_put(np);
 	}
@@ -631,4 +648,10 @@ void cpu_hotplug_driver_unlock()
 {
 	mutex_unlock(&powerpc_cpu_hotplug_driver_mutex);
 }
+
+void cpu_die(void)
+{
+	if (ppc_md.cpu_die)
+		ppc_md.cpu_die();
+}
 #endif

arch/powerpc/kernel/sysfs.c

@@ -35,7 +35,7 @@ static DEFINE_PER_CPU(struct cpu, cpu_devices);
 #ifdef CONFIG_PPC64
 
 /* Time in microseconds we delay before sleeping in the idle loop */
-DEFINE_PER_CPU(unsigned long, smt_snooze_delay) = { 100 };
+DEFINE_PER_CPU(long, smt_snooze_delay) = { 100 };
 
 static ssize_t store_smt_snooze_delay(struct sys_device *dev,
 				      struct sysdev_attribute *attr,
@@ -44,9 +44,9 @@ static ssize_t store_smt_snooze_delay(struct sys_device *dev,
 {
 	struct cpu *cpu = container_of(dev, struct cpu, sysdev);
 	ssize_t ret;
-	unsigned long snooze;
+	long snooze;
 
-	ret = sscanf(buf, "%lu", &snooze);
+	ret = sscanf(buf, "%ld", &snooze);
 	if (ret != 1)
 		return -EINVAL;
 
@@ -61,53 +61,23 @@ static ssize_t show_smt_snooze_delay(struct sys_device *dev,
 {
 	struct cpu *cpu = container_of(dev, struct cpu, sysdev);
 
-	return sprintf(buf, "%lu\n", per_cpu(smt_snooze_delay, cpu->sysdev.id));
+	return sprintf(buf, "%ld\n", per_cpu(smt_snooze_delay, cpu->sysdev.id));
 }
 
 static SYSDEV_ATTR(smt_snooze_delay, 0644, show_smt_snooze_delay,
 		   store_smt_snooze_delay);
 
-/* Only parse OF options if the matching cmdline option was not specified */
-static int smt_snooze_cmdline;
-
-static int __init smt_setup(void)
-{
-	struct device_node *options;
-	const unsigned int *val;
-	unsigned int cpu;
-
-	if (!cpu_has_feature(CPU_FTR_SMT))
-		return -ENODEV;
-
-	options = of_find_node_by_path("/options");
-	if (!options)
-		return -ENODEV;
-
-	val = of_get_property(options, "ibm,smt-snooze-delay", NULL);
-	if (!smt_snooze_cmdline && val) {
-		for_each_possible_cpu(cpu)
-			per_cpu(smt_snooze_delay, cpu) = *val;
-	}
-
-	of_node_put(options);
-	return 0;
-}
-__initcall(smt_setup);
-
 static int __init setup_smt_snooze_delay(char *str)
 {
 	unsigned int cpu;
-	int snooze;
+	long snooze;
 
 	if (!cpu_has_feature(CPU_FTR_SMT))
 		return 1;
 
-	smt_snooze_cmdline = 1;
-
-	if (get_option(&str, &snooze)) {
-		for_each_possible_cpu(cpu)
-			per_cpu(smt_snooze_delay, cpu) = snooze;
-	}
+	snooze = simple_strtol(str, NULL, 10);
+	for_each_possible_cpu(cpu)
+		per_cpu(smt_snooze_delay, cpu) = snooze;
 
 	return 1;
 }

arch/powerpc/kernel/traps.c

@@ -380,6 +380,46 @@ int machine_check_440A(struct pt_regs *regs)
 	}
 	return 0;
 }
+
+int machine_check_47x(struct pt_regs *regs)
+{
+	unsigned long reason = get_mc_reason(regs);
+	u32 mcsr;
+
+	printk(KERN_ERR "Machine check in kernel mode.\n");
+	if (reason & ESR_IMCP) {
+		printk(KERN_ERR
+		       "Instruction Synchronous Machine Check exception\n");
+		mtspr(SPRN_ESR, reason & ~ESR_IMCP);
+		return 0;
+	}
+	mcsr = mfspr(SPRN_MCSR);
+	if (mcsr & MCSR_IB)
+		printk(KERN_ERR "Instruction Read PLB Error\n");
+	if (mcsr & MCSR_DRB)
+		printk(KERN_ERR "Data Read PLB Error\n");
+	if (mcsr & MCSR_DWB)
+		printk(KERN_ERR "Data Write PLB Error\n");
+	if (mcsr & MCSR_TLBP)
+		printk(KERN_ERR "TLB Parity Error\n");
+	if (mcsr & MCSR_ICP) {
+		flush_instruction_cache();
+		printk(KERN_ERR "I-Cache Parity Error\n");
+	}
+	if (mcsr & MCSR_DCSP)
+		printk(KERN_ERR "D-Cache Search Parity Error\n");
+	if (mcsr & PPC47x_MCSR_GPR)
+		printk(KERN_ERR "GPR Parity Error\n");
+	if (mcsr & PPC47x_MCSR_FPR)
+		printk(KERN_ERR "FPR Parity Error\n");
+	if (mcsr & PPC47x_MCSR_IPR)
+		printk(KERN_ERR "Machine Check exception is imprecise\n");
+
+	/* Clear MCSR */
+	mtspr(SPRN_MCSR, mcsr);
+
+	return 0;
+}
 #elif defined(CONFIG_E500)
 int machine_check_e500(struct pt_regs *regs)
 {

arch/powerpc/kernel/vio.c

@@ -645,8 +645,10 @@ void vio_cmo_set_dev_desired(struct vio_dev *viodev, size_t desired)
 			found = 1;
 			break;
 		}
-	if (!found)
+	if (!found) {
+		spin_unlock_irqrestore(&vio_cmo.lock, flags);
 		return;
+	}
 
 	/* Increase/decrease in desired device entitlement */
 	if (desired >= viodev->cmo.desired) {
@@ -958,9 +960,12 @@ viodev_cmo_rd_attr(allocated);
 
 static ssize_t name_show(struct device *, struct device_attribute *, char *);
 static ssize_t devspec_show(struct device *, struct device_attribute *, char *);
+static ssize_t modalias_show(struct device *dev, struct device_attribute *attr,
+			     char *buf);
 static struct device_attribute vio_cmo_dev_attrs[] = {
 	__ATTR_RO(name),
 	__ATTR_RO(devspec),
+	__ATTR_RO(modalias),
 	__ATTR(cmo_desired,       S_IWUSR|S_IRUSR|S_IWGRP|S_IRGRP|S_IROTH,
 	       viodev_cmo_desired_show, viodev_cmo_desired_set),
 	__ATTR(cmo_entitled,      S_IRUGO, viodev_cmo_entitled_show,      NULL),
@@ -1320,9 +1325,27 @@ static ssize_t devspec_show(struct device *dev,
 	return sprintf(buf, "%s\n", of_node ? of_node->full_name : "none");
 }
 
+static ssize_t modalias_show(struct device *dev, struct device_attribute *attr,
+			     char *buf)
+{
+	const struct vio_dev *vio_dev = to_vio_dev(dev);
+	struct device_node *dn;
+	const char *cp;
+
+	dn = dev->archdata.of_node;
+	if (!dn)
+		return -ENODEV;
+	cp = of_get_property(dn, "compatible", NULL);
+	if (!cp)
+		return -ENODEV;
+
+	return sprintf(buf, "vio:T%sS%s\n", vio_dev->type, cp);
+}
+
 static struct device_attribute vio_dev_attrs[] = {
 	__ATTR_RO(name),
 	__ATTR_RO(devspec),
+	__ATTR_RO(modalias),
 	__ATTR_NULL
 };
 
@@ -1365,6 +1388,7 @@ static struct bus_type vio_bus_type = {
 	.match = vio_bus_match,
 	.probe = vio_bus_probe,
 	.remove = vio_bus_remove,
+	.pm = GENERIC_SUBSYS_PM_OPS,
 };
 
 /**

arch/powerpc/lib/string.S

@@ -28,7 +28,7 @@ _GLOBAL(strcpy)
 /* This clears out any unused part of the destination buffer,
    just as the libc version does.  -- paulus */
 _GLOBAL(strncpy)
-	cmpwi	0,r5,0
+	PPC_LCMPI 0,r5,0
 	beqlr
 	mtctr	r5
 	addi	r6,r3,-1
@@ -39,7 +39,7 @@ _GLOBAL(strncpy)
 	bdnzf	2,1b		/* dec ctr, branch if ctr != 0 && !cr0.eq */
 	bnelr			/* if we didn't hit a null char, we're done */
 	mfctr	r5
-	cmpwi	0,r5,0		/* any space left in destination buffer? */
+	PPC_LCMPI 0,r5,0	/* any space left in destination buffer? */
 	beqlr			/* we know r0 == 0 here */
 2:	stbu	r0,1(r6)	/* clear it out if so */
 	bdnz	2b
@@ -70,8 +70,8 @@ _GLOBAL(strcmp)
 	blr
 
 _GLOBAL(strncmp)
-	PPC_LCMPI r5,0
-	beqlr
+	PPC_LCMPI 0,r5,0
+	beq-	2f
 	mtctr	r5
 	addi	r5,r3,-1
 	addi	r4,r4,-1
@@ -82,6 +82,8 @@ _GLOBAL(strncmp)
 	beqlr	1
 	bdnzt	eq,1b
 	blr
+2:	li	r3,0
+	blr
 
 _GLOBAL(strlen)
 	addi	r4,r3,-1
@@ -92,8 +94,8 @@ _GLOBAL(strlen)
 	blr
 
 _GLOBAL(memcmp)
-	cmpwi	0,r5,0
-	ble-	2f
+	PPC_LCMPI 0,r5,0
+	beq-	2f
 	mtctr	r5
 	addi	r6,r3,-1
 	addi	r4,r4,-1
@@ -106,8 +108,8 @@ _GLOBAL(memcmp)
 	blr
 
 _GLOBAL(memchr)
-	cmpwi	0,r5,0
-	ble-	2f
+	PPC_LCMPI 0,r5,0
+	beq-	2f
 	mtctr	r5
 	addi	r3,r3,-1
 1:	lbzu	r0,1(r3)

arch/powerpc/mm/44x_mmu.c

@@ -38,7 +38,9 @@ unsigned int tlb_44x_index; /* = 0 */
 unsigned int tlb_44x_hwater = PPC44x_TLB_SIZE - 1 - PPC44x_EARLY_TLBS;
 int icache_44x_need_flush;
 
-static void __init ppc44x_update_tlb_hwater(void)
+unsigned long tlb_47x_boltmap[1024/8];
+
+static void __cpuinit ppc44x_update_tlb_hwater(void)
 {
 	extern unsigned int tlb_44x_patch_hwater_D[];
 	extern unsigned int tlb_44x_patch_hwater_I[];
@@ -59,7 +61,7 @@ static void __init ppc44x_update_tlb_hwater(void)
 }
 
 /*
- * "Pins" a 256MB TLB entry in AS0 for kernel lowmem
+ * "Pins" a 256MB TLB entry in AS0 for kernel lowmem for 44x type MMU
  */
 static void __init ppc44x_pin_tlb(unsigned int virt, unsigned int phys)
 {
@@ -67,12 +69,18 @@ static void __init ppc44x_pin_tlb(unsigned int virt, unsigned int phys)
 
 	ppc44x_update_tlb_hwater();
 
+	mtspr(SPRN_MMUCR, 0);
+
 	__asm__ __volatile__(
 		"tlbwe	%2,%3,%4\n"
 		"tlbwe	%1,%3,%5\n"
 		"tlbwe	%0,%3,%6\n"
 	:
+#ifdef CONFIG_PPC47x
+	: "r" (PPC47x_TLB2_S_RWX),
+#else
 	: "r" (PPC44x_TLB_SW | PPC44x_TLB_SR | PPC44x_TLB_SX | PPC44x_TLB_G),
+#endif
 	  "r" (phys),
 	  "r" (virt | PPC44x_TLB_VALID | PPC44x_TLB_256M),
 	  "r" (entry),
@@ -81,8 +89,93 @@ static void __init ppc44x_pin_tlb(unsigned int virt, unsigned int phys)
 	  "i" (PPC44x_TLB_ATTRIB));
 }
 
+static int __init ppc47x_find_free_bolted(void)
+{
+	unsigned int mmube0 = mfspr(SPRN_MMUBE0);
+	unsigned int mmube1 = mfspr(SPRN_MMUBE1);
+
+	if (!(mmube0 & MMUBE0_VBE0))
+		return 0;
+	if (!(mmube0 & MMUBE0_VBE1))
+		return 1;
+	if (!(mmube0 & MMUBE0_VBE2))
+		return 2;
+	if (!(mmube1 & MMUBE1_VBE3))
+		return 3;
+	if (!(mmube1 & MMUBE1_VBE4))
+		return 4;
+	if (!(mmube1 & MMUBE1_VBE5))
+		return 5;
+	return -1;
+}
+
+static void __init ppc47x_update_boltmap(void)
+{
+	unsigned int mmube0 = mfspr(SPRN_MMUBE0);
+	unsigned int mmube1 = mfspr(SPRN_MMUBE1);
+
+	if (mmube0 & MMUBE0_VBE0)
+		__set_bit((mmube0 >> MMUBE0_IBE0_SHIFT) & 0xff,
+			  tlb_47x_boltmap);
+	if (mmube0 & MMUBE0_VBE1)
+		__set_bit((mmube0 >> MMUBE0_IBE1_SHIFT) & 0xff,
+			  tlb_47x_boltmap);
+	if (mmube0 & MMUBE0_VBE2)
+		__set_bit((mmube0 >> MMUBE0_IBE2_SHIFT) & 0xff,
+			  tlb_47x_boltmap);
+	if (mmube1 & MMUBE1_VBE3)
+		__set_bit((mmube1 >> MMUBE1_IBE3_SHIFT) & 0xff,
+			  tlb_47x_boltmap);
+	if (mmube1 & MMUBE1_VBE4)
+		__set_bit((mmube1 >> MMUBE1_IBE4_SHIFT) & 0xff,
+			  tlb_47x_boltmap);
+	if (mmube1 & MMUBE1_VBE5)
+		__set_bit((mmube1 >> MMUBE1_IBE5_SHIFT) & 0xff,
+			  tlb_47x_boltmap);
+}
+
+/*
+ * "Pins" a 256MB TLB entry in AS0 for kernel lowmem for 47x type MMU
+ */
+static void __cpuinit ppc47x_pin_tlb(unsigned int virt, unsigned int phys)
+{
+	unsigned int rA;
+	int bolted;
+
+	/* Base rA is HW way select, way 0, bolted bit set */
+	rA = 0x88000000;
+
+	/* Look for a bolted entry slot */
+	bolted = ppc47x_find_free_bolted();
+	BUG_ON(bolted < 0);
+
+	/* Insert bolted slot number */
+	rA |= bolted << 24;
+
+	pr_debug("256M TLB entry for 0x%08x->0x%08x in bolt slot %d\n",
+		 virt, phys, bolted);
+
+	mtspr(SPRN_MMUCR, 0);
+
+	__asm__ __volatile__(
+		"tlbwe	%2,%3,0\n"
+		"tlbwe	%1,%3,1\n"
+		"tlbwe	%0,%3,2\n"
+		:
+		: "r" (PPC47x_TLB2_SW | PPC47x_TLB2_SR |
+		       PPC47x_TLB2_SX
+#ifdef CONFIG_SMP
+		       | PPC47x_TLB2_M
+#endif
+		       ),
+		  "r" (phys),
+		  "r" (virt | PPC47x_TLB0_VALID | PPC47x_TLB0_256M),
+		  "r" (rA));
+}
+
 void __init MMU_init_hw(void)
 {
+	/* This is not useful on 47x but won't hurt either */
 	ppc44x_update_tlb_hwater();
 
 	flush_instruction_cache();
@@ -95,8 +188,51 @@ unsigned long __init mmu_mapin_ram(unsigned long top)
 	/* Pin in enough TLBs to cover any lowmem not covered by the
 	 * initial 256M mapping established in head_44x.S */
 	for (addr = PPC_PIN_SIZE; addr < lowmem_end_addr;
-	     addr += PPC_PIN_SIZE)
-		ppc44x_pin_tlb(addr + PAGE_OFFSET, addr);
+	     addr += PPC_PIN_SIZE) {
+		if (mmu_has_feature(MMU_FTR_TYPE_47x))
+			ppc47x_pin_tlb(addr + PAGE_OFFSET, addr);
+		else
+			ppc44x_pin_tlb(addr + PAGE_OFFSET, addr);
+	}
+	if (mmu_has_feature(MMU_FTR_TYPE_47x)) {
+		ppc47x_update_boltmap();
 
+#ifdef DEBUG
+		{
+			int i;
+
+			printk(KERN_DEBUG "bolted entries: ");
+			for (i = 0; i < 255; i++) {
+				if (test_bit(i, tlb_47x_boltmap))
+					printk("%d ", i);
+			}
+			printk("\n");
+		}
+#endif /* DEBUG */
+	}
 	return total_lowmem;
 }
+
+#ifdef CONFIG_SMP
+void __cpuinit mmu_init_secondary(int cpu)
+{
+	unsigned long addr;
+
+	/* Pin in enough TLBs to cover any lowmem not covered by the
+	 * initial 256M mapping established in head_44x.S
+	 *
+	 * WARNING: This is called with only the first 256M of the
+	 * linear mapping in the TLB and we can't take faults yet
+	 * so beware of what this code uses. It runs off a temporary
+	 * stack. current (r2) isn't initialized, smp_processor_id()
+	 * will not work, current thread info isn't accessible, ...
+	 */
+	for (addr = PPC_PIN_SIZE; addr < lowmem_end_addr;
+	     addr += PPC_PIN_SIZE) {
+		if (mmu_has_feature(MMU_FTR_TYPE_47x))
+			ppc47x_pin_tlb(addr + PAGE_OFFSET, addr);
+		else
+			ppc44x_pin_tlb(addr + PAGE_OFFSET, addr);
+	}
+}
+#endif /* CONFIG_SMP */

arch/powerpc/mm/fault.c

@@ -151,13 +151,14 @@ int __kprobes do_page_fault(struct pt_regs *regs, unsigned long address,
 	if (!user_mode(regs) && (address >= TASK_SIZE))
 		return SIGSEGV;
 
-#if !(defined(CONFIG_4xx) || defined(CONFIG_BOOKE))
+#if !(defined(CONFIG_4xx) || defined(CONFIG_BOOKE) || \
+			     defined(CONFIG_PPC_BOOK3S_64))
   	if (error_code & DSISR_DABRMATCH) {
 		/* DABR match */
 		do_dabr(regs, address, error_code);
 		return 0;
 	}
-#endif /* !(CONFIG_4xx || CONFIG_BOOKE)*/
+#endif
 
 	if (in_atomic() || mm == NULL) {
 		if (!user_mode(regs))
@@ -307,7 +308,6 @@ int __kprobes do_page_fault(struct pt_regs *regs, unsigned long address,
 	 * make sure we exit gracefully rather than endlessly redo
 	 * the fault.
 	 */
- survive:
 	ret = handle_mm_fault(mm, vma, address, is_write ? FAULT_FLAG_WRITE : 0);
 	if (unlikely(ret & VM_FAULT_ERROR)) {
 		if (ret & VM_FAULT_OOM)
@@ -359,15 +359,10 @@ int __kprobes do_page_fault(struct pt_regs *regs, unsigned long address,
  */
 out_of_memory:
 	up_read(&mm->mmap_sem);
-	if (is_global_init(current)) {
-		yield();
-		down_read(&mm->mmap_sem);
-		goto survive;
-	}
-	printk("VM: killing process %s\n", current->comm);
-	if (user_mode(regs))
-		do_group_exit(SIGKILL);
-	return SIGKILL;
+	if (!user_mode(regs))
+		return SIGKILL;
+	pagefault_out_of_memory();
+	return 0;
 
 do_sigbus:
 	up_read(&mm->mmap_sem);

arch/powerpc/mm/fsl_booke_mmu.c

@@ -2,7 +2,7 @@
  * Modifications by Kumar Gala (galak@kernel.crashing.org) to support
  * E500 Book E processors.
  *
- * Copyright 2004 Freescale Semiconductor, Inc
+ * Copyright 2004,2010 Freescale Semiconductor, Inc.
  *
  * This file contains the routines for initializing the MMU
  * on the 4xx series of chips.
@@ -56,19 +56,13 @@
 
 unsigned int tlbcam_index;
 
-#define NUM_TLBCAMS	(64)
 
 #if defined(CONFIG_LOWMEM_CAM_NUM_BOOL) && (CONFIG_LOWMEM_CAM_NUM >= NUM_TLBCAMS)
 #error "LOWMEM_CAM_NUM must be less than NUM_TLBCAMS"
 #endif
 
-struct tlbcam {
-	u32	MAS0;
-	u32	MAS1;
-	unsigned long	MAS2;
-	u32	MAS3;
-	u32	MAS7;
-} TLBCAM[NUM_TLBCAMS];
+#define NUM_TLBCAMS	(64)
+struct tlbcam TLBCAM[NUM_TLBCAMS];
 
 struct tlbcamrange {
 	unsigned long start;
@@ -109,19 +103,6 @@ unsigned long p_mapped_by_tlbcam(phys_addr_t pa)
 	return 0;
 }
 
-void loadcam_entry(int idx)
-{
-	mtspr(SPRN_MAS0, TLBCAM[idx].MAS0);
-	mtspr(SPRN_MAS1, TLBCAM[idx].MAS1);
-	mtspr(SPRN_MAS2, TLBCAM[idx].MAS2);
-	mtspr(SPRN_MAS3, TLBCAM[idx].MAS3);
-
-	if (mmu_has_feature(MMU_FTR_BIG_PHYS))
-		mtspr(SPRN_MAS7, TLBCAM[idx].MAS7);
-
-	asm volatile("isync;tlbwe;isync" : : : "memory");
-}
-
 /*
  * Set up one of the I/D BAT (block address translation) register pairs.
  * The parameters are not checked; in particular size must be a power

arch/powerpc/mm/init_64.c

@@ -252,6 +252,47 @@ static void __meminit vmemmap_create_mapping(unsigned long start,
 }
 #endif /* CONFIG_PPC_BOOK3E */
 
+struct vmemmap_backing *vmemmap_list;
+
+static __meminit struct vmemmap_backing * vmemmap_list_alloc(int node)
+{
+	static struct vmemmap_backing *next;
+	static int num_left;
+
+	/* allocate a page when required and hand out chunks */
+	if (!next || !num_left) {
+		next = vmemmap_alloc_block(PAGE_SIZE, node);
+		if (unlikely(!next)) {
+			WARN_ON(1);
+			return NULL;
+		}
+		num_left = PAGE_SIZE / sizeof(struct vmemmap_backing);
+	}
+
+	num_left--;
+
+	return next++;
+}
+
+static __meminit void vmemmap_list_populate(unsigned long phys,
+					    unsigned long start,
+					    int node)
+{
+	struct vmemmap_backing *vmem_back;
+
+	vmem_back = vmemmap_list_alloc(node);
+	if (unlikely(!vmem_back)) {
+		WARN_ON(1);
+		return;
+	}
+
+	vmem_back->phys = phys;
+	vmem_back->virt_addr = start;
+	vmem_back->list = vmemmap_list;
+
+	vmemmap_list = vmem_back;
+}
+
 int __meminit vmemmap_populate(struct page *start_page,
 			       unsigned long nr_pages, int node)
 {
@@ -276,6 +317,8 @@ int __meminit vmemmap_populate(struct page *start_page,
 		if (!p)
 			return -ENOMEM;
 
+		vmemmap_list_populate(__pa(p), start, node);
+
 		pr_debug("      * %016lx..%016lx allocated at %p\n",
 			 start, start + page_size, p);
 

arch/powerpc/mm/mmu_context_nohash.c

@@ -395,10 +395,18 @@ void __init mmu_context_init(void)
 	 * the PID/TID comparison is disabled, so we can use a TID of zero
 	 * to represent all kernel pages as shared among all contexts.
 	 * 	-- Dan
+	 *
+	 * The IBM 47x core supports 16-bit PIDs, thus 65535 contexts. We
+	 * should normally never have to steal though the facility is
+	 * present if needed.
+	 *      -- BenH
 	 */
 	if (mmu_has_feature(MMU_FTR_TYPE_8xx)) {
 		first_context = 0;
 		last_context = 15;
+	} else if (mmu_has_feature(MMU_FTR_TYPE_47x)) {
+		first_context = 1;
+		last_context = 65535;
 	} else {
 		first_context = 1;
 		last_context = 255;

arch/powerpc/mm/mmu_decl.h

@@ -69,12 +69,7 @@ static inline void _tlbil_va(unsigned long address, unsigned int pid,
 }
 #endif /* CONIFG_8xx */
 
-/*
- * As of today, we don't support tlbivax broadcast on any
- * implementation. When that becomes the case, this will be
- * an extern.
- */
-#ifdef CONFIG_PPC_BOOK3E
+#if defined(CONFIG_PPC_BOOK3E) || defined(CONFIG_PPC_47x)
 extern void _tlbivax_bcast(unsigned long address, unsigned int pid,
 			   unsigned int tsize, unsigned int ind);
 #else
@@ -149,7 +144,15 @@ extern unsigned long mmu_mapin_ram(unsigned long top);
 extern void MMU_init_hw(void);
 extern unsigned long mmu_mapin_ram(unsigned long top);
 extern void adjust_total_lowmem(void);
-
+extern void loadcam_entry(unsigned int index);
+
+struct tlbcam {
+	u32	MAS0;
+	u32	MAS1;
+	unsigned long	MAS2;
+	u32	MAS3;
+	u32	MAS7;
+};
 #elif defined(CONFIG_PPC32)
 /* anything 32-bit except 4xx or 8xx */
 extern void MMU_init_hw(void);

arch/powerpc/mm/pgtable_64.c

@@ -265,6 +265,14 @@ void __iomem * ioremap_flags(phys_addr_t addr, unsigned long size,
 	/* we don't want to let _PAGE_USER and _PAGE_EXEC leak out */
 	flags &= ~(_PAGE_USER | _PAGE_EXEC);
 
+#ifdef _PAGE_BAP_SR
+	/* _PAGE_USER contains _PAGE_BAP_SR on BookE using the new PTE format
+	 * which means that we just cleared supervisor access... oops ;-) This
+	 * restores it
+	 */
+	flags |= _PAGE_BAP_SR;
+#endif
+
 	if (ppc_md.ioremap)
 		return ppc_md.ioremap(addr, size, flags, caller);
 	return __ioremap_caller(addr, size, flags, caller);

arch/powerpc/platforms/44x/Makefile

@@ -5,3 +5,4 @@ obj-$(CONFIG_SAM440EP) 	+= sam440ep.o
 obj-$(CONFIG_WARP)	+= warp.o
 obj-$(CONFIG_XILINX_VIRTEX_5_FXT) += virtex.o
 obj-$(CONFIG_XILINX_ML510) += virtex_ml510.o
+obj-$(CONFIG_ISS4xx)	+= iss4xx.o