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: (72 commits)
  powerpc/pseries: Fix build of topology stuff without CONFIG_NUMA
  powerpc/pseries: Fix VPHN build errors on non-SMP systems
  powerpc/83xx: add mpc8308_p1m DMA controller device-tree node
  powerpc/83xx: add DMA controller to mpc8308 device-tree node
  powerpc/512x: try to free dma descriptors in case of allocation failure
  powerpc/512x: add MPC8308 dma support
  powerpc/512x: fix the hanged dma transfer issue
  powerpc/512x: scatter/gather dma fix
  powerpc/powermac: Make auto-loading of therm_pm72 possible
  of/address: Use propper endianess in get_flags
  powerpc/pci: Use printf extension %pR for struct resource
  powerpc: Remove unnecessary casts of void ptr
  powerpc: Disable VPHN polling during a suspend operation
  powerpc/pseries: Poll VPA for topology changes and update NUMA maps
  powerpc: iommu: Add device name to iommu error printks
  powerpc: Record vma->phys_addr in ioremap()
  powerpc: Update compat_arch_ptrace
  powerpc: Fix PPC_PTRACE_SETHWDEBUG on PPC_BOOK3S
  powerpc/time: printk time stamp init not correct
  powerpc: Minor cleanups for machdep.h
  ...

Documentation/kernel-parameters.txt

@@ -403,6 +403,10 @@ and is between 256 and 4096 characters. It is defined in the file
 	bttv.pll=	See Documentation/video4linux/bttv/Insmod-options
 	bttv.tuner=	and Documentation/video4linux/bttv/CARDLIST
 
+	bulk_remove=off	[PPC]  This parameter disables the use of the pSeries
+			firmware feature for flushing multiple hpte entries
+			at a time.
+
 	c101=		[NET] Moxa C101 synchronous serial card
 
 	cachesize=	[BUGS=X86-32] Override level 2 CPU cache size detection.
@@ -1490,6 +1494,10 @@ and is between 256 and 4096 characters. It is defined in the file
 	mtdparts=	[MTD]
 			See drivers/mtd/cmdlinepart.c.
 
+	multitce=off	[PPC]  This parameter disables the use of the pSeries
+			firmware feature for updating multiple TCE entries
+			at a time.
+
 	onenand.bdry=	[HW,MTD] Flex-OneNAND Boundary Configuration
 
 			Format: [die0_boundary][,die0_lock][,die1_boundary][,die1_lock]

Documentation/powerpc/booting-without-of.txt

@@ -131,7 +131,7 @@ order to avoid the degeneration that had become the ppc32 kernel entry
 point and the way a new platform should be added to the kernel. The
 legacy iSeries platform breaks those rules as it predates this scheme,
 but no new board support will be accepted in the main tree that
-doesn't follows them properly.  In addition, since the advent of the
+doesn't follow them properly.  In addition, since the advent of the
 arch/powerpc merged architecture for ppc32 and ppc64, new 32-bit
 platforms and 32-bit platforms which move into arch/powerpc will be
 required to use these rules as well.
@@ -1025,7 +1025,7 @@ dtc source code can be found at
 
 WARNING: This version is still in early development stage; the
 resulting device-tree "blobs" have not yet been validated with the
-kernel. The current generated bloc lacks a useful reserve map (it will
+kernel. The current generated block lacks a useful reserve map (it will
 be fixed to generate an empty one, it's up to the bootloader to fill
 it up) among others. The error handling needs work, bugs are lurking,
 etc...

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

@@ -0,0 +1,52 @@
+PPC4xx Clock Power Management (CPM) node
+
+Required properties:
+	- compatible		: compatible list, currently only "ibm,cpm"
+	- dcr-access-method	: "native"
+	- dcr-reg		: < DCR register range >
+
+Optional properties:
+	- er-offset		: All 4xx SoCs with a CPM controller have
+				  one of two different order for the CPM
+				  registers. Some have the CPM registers
+				  in the following order (ER,FR,SR). The
+				  others have them in the following order
+				  (SR,ER,FR). For the second case set
+				  er-offset = <1>.
+	- unused-units		: specifier consist of one cell. For each
+				  bit in the cell, the corresponding bit
+				  in CPM will be set to turn off unused
+				  devices.
+	- idle-doze		: specifier consist of one cell. For each
+				  bit in the cell, the corresponding bit
+				  in CPM will be set to turn off unused
+				  devices. This is usually just CPM[CPU].
+	- standby		: specifier consist of one cell. For each
+				  bit in the cell, the corresponding bit
+				  in CPM will be set on standby and
+				  restored on resume.
+	- suspend		: specifier consist of one cell. For each
+				  bit in the cell, the corresponding bit
+				  in CPM will be set on suspend (mem) and
+				  restored on resume. Note, for standby
+				  and suspend the corresponding bits can
+				  be different or the same. Usually for
+				  standby only class 2 and 3 units are set.
+				  However, the interface does not care.
+				  If they are the same, the additional
+				  power saving will be seeing if support
+				  is available to put the DDR in self
+				  refresh mode and any additional power
+				  saving techniques for the specific SoC.
+
+Example:
+	CPM0: cpm {
+		compatible = "ibm,cpm";
+		dcr-access-method = "native";
+		dcr-reg = <0x160 0x003>;
+		er-offset = <0>;
+		unused-units = <0x00000100>;
+		idle-doze = <0x02000000>;
+		standby = <0xfeff0000>;
+		suspend = <0xfeff791d>;
+};

arch/powerpc/Kconfig

@@ -20,6 +20,9 @@ config WORD_SIZE
 config ARCH_PHYS_ADDR_T_64BIT
        def_bool PPC64 || PHYS_64BIT
 
+config ARCH_DMA_ADDR_T_64BIT
+	def_bool ARCH_PHYS_ADDR_T_64BIT
+
 config MMU
 	bool
 	default y
@@ -209,7 +212,7 @@ config ARCH_HIBERNATION_POSSIBLE
 config ARCH_SUSPEND_POSSIBLE
 	def_bool y
 	depends on ADB_PMU || PPC_EFIKA || PPC_LITE5200 || PPC_83xx || \
-		   PPC_85xx || PPC_86xx || PPC_PSERIES
+		   PPC_85xx || PPC_86xx || PPC_PSERIES || 44x || 40x
 
 config PPC_DCR_NATIVE
 	bool
@@ -595,13 +598,11 @@ config EXTRA_TARGETS
 
 	  If unsure, leave blank
 
-if !44x || BROKEN
 config ARCH_WANTS_FREEZER_CONTROL
 	def_bool y
 	depends on ADB_PMU
 
 source kernel/power/Kconfig
-endif
 
 config SECCOMP
 	bool "Enable seccomp to safely compute untrusted bytecode"
@@ -682,6 +683,15 @@ config FSL_PMC
 	  Freescale MPC85xx/MPC86xx power management controller support
 	  (suspend/resume). For MPC83xx see platforms/83xx/suspend.c
 
+config PPC4xx_CPM
+	bool
+	default y
+	depends on SUSPEND && (44x || 40x)
+	help
+	  PPC4xx Clock Power Management (CPM) support (suspend/resume).
+	  It also enables support for two different idle states (idle-wait
+	  and idle-doze).
+
 config 4xx_SOC
 	bool
 

arch/powerpc/boot/dts/canyonlands.dts

@@ -105,6 +105,15 @@
 		dcr-reg = <0x00c 0x002>;
 	};
 
+	CPM0: cpm {
+		compatible = "ibm,cpm";
+		dcr-access-method = "native";
+		dcr-reg = <0x160 0x003>;
+		unused-units = <0x00000100>;
+		idle-doze = <0x02000000>;
+		standby = <0xfeff791d>;
+	};
+
 	L2C0: l2c {
 		compatible = "ibm,l2-cache-460ex", "ibm,l2-cache";
 		dcr-reg = <0x020 0x008		/* Internal SRAM DCR's */
@@ -270,28 +279,6 @@
 				interrupts = <0x1 0x4>;
 			};
 
-			UART2: serial@ef600500 {
-				device_type = "serial";
-				compatible = "ns16550";
-				reg = <0xef600500 0x00000008>;
-				virtual-reg = <0xef600500>;
-				clock-frequency = <0>; /* Filled in by U-Boot */
-				current-speed = <0>; /* Filled in by U-Boot */
-				interrupt-parent = <&UIC1>;
-				interrupts = <28 0x4>;
-			};
-
-			UART3: serial@ef600600 {
-				device_type = "serial";
-				compatible = "ns16550";
-				reg = <0xef600600 0x00000008>;
-				virtual-reg = <0xef600600>;
-				clock-frequency = <0>; /* Filled in by U-Boot */
-				current-speed = <0>; /* Filled in by U-Boot */
-				interrupt-parent = <&UIC1>;
-				interrupts = <29 0x4>;
-			};
-
 			IIC0: i2c@ef600700 {
 				compatible = "ibm,iic-460ex", "ibm,iic";
 				reg = <0xef600700 0x00000014>;

arch/powerpc/boot/dts/kilauea.dts

@@ -82,6 +82,15 @@
 		interrupt-parent = <&UIC0>;
 	};
 
+	CPM0: cpm {
+		compatible = "ibm,cpm";
+		dcr-access-method = "native";
+		dcr-reg = <0x0b0 0x003>;
+		unused-units = <0x00000000>;
+		idle-doze = <0x02000000>;
+		standby = <0xe3e74800>;
+	};
+
 	plb {
 		compatible = "ibm,plb-405ex", "ibm,plb4";
 		#address-cells = <1>;

arch/powerpc/boot/dts/mpc8308_p1m.dts

@@ -297,6 +297,14 @@
 			interrupt-parent = < &ipic >;
 		};
 
+		dma@2c000 {
+			compatible = "fsl,mpc8308-dma", "fsl,mpc5121-dma";
+			reg = <0x2c000 0x1800>;
+			interrupts = <3 0x8
+					94 0x8>;
+			interrupt-parent = < &ipic >;
+		};
+
 	};
 
 	pci0: pcie@e0009000 {

arch/powerpc/boot/dts/mpc8308rdb.dts

@@ -265,6 +265,14 @@
 			interrupt-parent = < &ipic >;
 		};
 
+		dma@2c000 {
+			compatible = "fsl,mpc8308-dma", "fsl,mpc5121-dma";
+			reg = <0x2c000 0x1800>;
+			interrupts = <3 0x8
+					94 0x8>;
+			interrupt-parent = < &ipic >;
+		};
+
 	};
 
 	pci0: pcie@e0009000 {

arch/powerpc/configs/40x/kilauea_defconfig

@@ -12,6 +12,8 @@ CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
 # CONFIG_BLK_DEV_BSG is not set
 CONFIG_KILAUEA=y
+CONFIG_NO_HZ=y
+CONFIG_HIGH_RES_TIMERS=y
 # CONFIG_WALNUT is not set
 CONFIG_SPARSE_IRQ=y
 CONFIG_PCI=y
@@ -42,6 +44,9 @@ CONFIG_MTD_PHYSMAP_OF=y
 CONFIG_MTD_NAND=y
 CONFIG_MTD_NAND_NDFC=y
 CONFIG_PROC_DEVICETREE=y
+CONFIG_PM=y
+CONFIG_SUSPEND=y
+CONFIG_PPC4xx_CPM=y
 CONFIG_BLK_DEV_RAM=y
 CONFIG_BLK_DEV_RAM_SIZE=35000
 # CONFIG_MISC_DEVICES is not set

arch/powerpc/configs/44x/canyonlands_defconfig

@@ -42,6 +42,9 @@ CONFIG_MTD_PHYSMAP_OF=y
 CONFIG_MTD_NAND=y
 CONFIG_MTD_NAND_NDFC=y
 CONFIG_PROC_DEVICETREE=y
+CONFIG_PM=y
+CONFIG_SUSPEND=y
+CONFIG_PPC4xx_CPM=y
 CONFIG_BLK_DEV_RAM=y
 CONFIG_BLK_DEV_RAM_SIZE=35000
 # CONFIG_MISC_DEVICES is not set

arch/powerpc/include/asm/bitops.h

@@ -267,7 +267,16 @@ static __inline__ int fls64(__u64 x)
 #include <asm-generic/bitops/fls64.h>
 #endif /* __powerpc64__ */
 
+#ifdef CONFIG_PPC64
+unsigned int __arch_hweight8(unsigned int w);
+unsigned int __arch_hweight16(unsigned int w);
+unsigned int __arch_hweight32(unsigned int w);
+unsigned long __arch_hweight64(__u64 w);
+#include <asm-generic/bitops/const_hweight.h>
+#else
 #include <asm-generic/bitops/hweight.h>
+#endif
+
 #include <asm-generic/bitops/find.h>
 
 /* Little-endian versions */

arch/powerpc/include/asm/cputable.h

@@ -199,6 +199,8 @@ extern const char *powerpc_base_platform;
 #define CPU_FTR_UNALIGNED_LD_STD	LONG_ASM_CONST(0x0080000000000000)
 #define CPU_FTR_ASYM_SMT		LONG_ASM_CONST(0x0100000000000000)
 #define CPU_FTR_STCX_CHECKS_ADDRESS	LONG_ASM_CONST(0x0200000000000000)
+#define CPU_FTR_POPCNTB			LONG_ASM_CONST(0x0400000000000000)
+#define CPU_FTR_POPCNTD			LONG_ASM_CONST(0x0800000000000000)
 
 #ifndef __ASSEMBLY__
 
@@ -403,21 +405,22 @@ extern const char *powerpc_base_platform;
 	    CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \
 	    CPU_FTR_MMCRA | CPU_FTR_SMT | \
 	    CPU_FTR_COHERENT_ICACHE | CPU_FTR_LOCKLESS_TLBIE | \
-	    CPU_FTR_PURR | CPU_FTR_STCX_CHECKS_ADDRESS)
+	    CPU_FTR_PURR | CPU_FTR_STCX_CHECKS_ADDRESS | \
+	    CPU_FTR_POPCNTB)
 #define CPU_FTRS_POWER6 (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \
 	    CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \
 	    CPU_FTR_MMCRA | CPU_FTR_SMT | \
 	    CPU_FTR_COHERENT_ICACHE | CPU_FTR_LOCKLESS_TLBIE | \
 	    CPU_FTR_PURR | CPU_FTR_SPURR | CPU_FTR_REAL_LE | \
 	    CPU_FTR_DSCR | CPU_FTR_UNALIGNED_LD_STD | \
-	    CPU_FTR_STCX_CHECKS_ADDRESS)
+	    CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB)
 #define CPU_FTRS_POWER7 (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \
 	    CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \
 	    CPU_FTR_MMCRA | CPU_FTR_SMT | \
 	    CPU_FTR_COHERENT_ICACHE | CPU_FTR_LOCKLESS_TLBIE | \
 	    CPU_FTR_PURR | CPU_FTR_SPURR | CPU_FTR_REAL_LE | \
 	    CPU_FTR_DSCR | CPU_FTR_SAO  | CPU_FTR_ASYM_SMT | \
-	    CPU_FTR_STCX_CHECKS_ADDRESS)
+	    CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD)
 #define CPU_FTRS_CELL	(CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \
 	    CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \
 	    CPU_FTR_ALTIVEC_COMP | CPU_FTR_MMCRA | CPU_FTR_SMT | \

arch/powerpc/include/asm/cputhreads.h

@@ -61,22 +61,25 @@ static inline cpumask_t cpu_online_cores_map(void)
 	return cpu_thread_mask_to_cores(cpu_online_map);
 }
 
-static inline int cpu_thread_to_core(int cpu)
+#ifdef CONFIG_SMP
-{
+int cpu_core_index_of_thread(int cpu);
-	return cpu >> threads_shift;
+int cpu_first_thread_of_core(int core);
-}
+#else
+static inline int cpu_core_index_of_thread(int cpu) { return cpu; }
+static inline int cpu_first_thread_of_core(int core) { return core; }
+#endif
 
 static inline int cpu_thread_in_core(int cpu)
 {
 	return cpu & (threads_per_core - 1);
 }
 
-static inline int cpu_first_thread_in_core(int cpu)
+static inline int cpu_first_thread_sibling(int cpu)
 {
 	return cpu & ~(threads_per_core - 1);
 }
 
-static inline int cpu_last_thread_in_core(int cpu)
+static inline int cpu_last_thread_sibling(int cpu)
 {
 	return cpu | (threads_per_core - 1);
 }

arch/powerpc/include/asm/device.h

@@ -9,6 +9,12 @@
 struct dma_map_ops;
 struct device_node;
 
+/*
+ * Arch extensions to struct device.
+ *
+ * When adding fields, consider macio_add_one_device in
+ * drivers/macintosh/macio_asic.c
+ */
 struct dev_archdata {
 	/* DMA operations on that device */
 	struct dma_map_ops	*dma_ops;

arch/powerpc/include/asm/firmware.h

@@ -46,6 +46,7 @@
 #define FW_FEATURE_PS3_LV1	ASM_CONST(0x0000000000800000)
 #define FW_FEATURE_BEAT		ASM_CONST(0x0000000001000000)
 #define FW_FEATURE_CMO		ASM_CONST(0x0000000002000000)
+#define FW_FEATURE_VPHN		ASM_CONST(0x0000000004000000)
 
 #ifndef __ASSEMBLY__
 
@@ -59,7 +60,7 @@ enum {
 		FW_FEATURE_VIO | FW_FEATURE_RDMA | FW_FEATURE_LLAN |
 		FW_FEATURE_BULK_REMOVE | FW_FEATURE_XDABR |
 		FW_FEATURE_MULTITCE | FW_FEATURE_SPLPAR | FW_FEATURE_LPAR |
-		FW_FEATURE_CMO,
+		FW_FEATURE_CMO | FW_FEATURE_VPHN,
 	FW_FEATURE_PSERIES_ALWAYS = 0,
 	FW_FEATURE_ISERIES_POSSIBLE = FW_FEATURE_ISERIES | FW_FEATURE_LPAR,
 	FW_FEATURE_ISERIES_ALWAYS = FW_FEATURE_ISERIES | FW_FEATURE_LPAR,

arch/powerpc/include/asm/hvcall.h

@@ -232,7 +232,9 @@
 #define H_GET_EM_PARMS		0x2B8
 #define H_SET_MPP		0x2D0
 #define H_GET_MPP		0x2D4
-#define MAX_HCALL_OPCODE	H_GET_MPP
+#define H_HOME_NODE_ASSOCIATIVITY 0x2EC
+#define H_BEST_ENERGY		0x2F4
+#define MAX_HCALL_OPCODE	H_BEST_ENERGY
 
 #ifndef __ASSEMBLY__
 

arch/powerpc/include/asm/lppaca.h

@@ -62,7 +62,10 @@ struct lppaca {
 	volatile u32 dyn_pir;		// Dynamic ProcIdReg value	x20-x23
 	u32	dsei_data;           	// DSEI data                  	x24-x27
 	u64	sprg3;               	// SPRG3 value                	x28-x2F
-	u8	reserved3[80];		// Reserved			x30-x7F
+	u8	reserved3[40];		// Reserved			x30-x57
+	volatile u8 vphn_assoc_counts[8]; // Virtual processor home node
+					// associativity change counters x58-x5F
+	u8	reserved4[32];		// Reserved			x60-x7F
 
 //=============================================================================
 // CACHE_LINE_2 0x0080 - 0x00FF Contains local read-write data

arch/powerpc/include/asm/machdep.h

@@ -27,9 +27,7 @@ struct iommu_table;
 struct rtc_time;
 struct file;
 struct pci_controller;
-#ifdef CONFIG_KEXEC
 struct kimage;
-#endif
 
 #ifdef CONFIG_SMP
 struct smp_ops_t {
@@ -72,7 +70,7 @@ struct machdep_calls {
 					     int psize, int ssize);
 	void		(*flush_hash_range)(unsigned long number, int local);
 
-	/* special for kexec, to be called in real mode, linar mapping is
+	/* special for kexec, to be called in real mode, linear mapping is
 	 * destroyed as well */
 	void		(*hpte_clear_all)(void);
 
@@ -324,8 +322,6 @@ extern sys_ctrler_t sys_ctrler;
 
 #endif /* CONFIG_PPC_PMAC */
 
-extern void setup_pci_ptrs(void);
-
 #ifdef CONFIG_SMP
 /* Poor default implementations */
 extern void __devinit smp_generic_give_timebase(void);

arch/powerpc/include/asm/mmzone.h

@@ -33,6 +33,9 @@ extern int numa_cpu_lookup_table[];
 extern cpumask_var_t node_to_cpumask_map[];
 #ifdef CONFIG_MEMORY_HOTPLUG
 extern unsigned long max_pfn;
+u64 memory_hotplug_max(void);
+#else
+#define memory_hotplug_max() memblock_end_of_DRAM()
 #endif
 
 /*
@@ -42,6 +45,8 @@ extern unsigned long max_pfn;
 #define node_start_pfn(nid)	(NODE_DATA(nid)->node_start_pfn)
 #define node_end_pfn(nid)	(NODE_DATA(nid)->node_end_pfn)
 
+#else
+#define memory_hotplug_max() memblock_end_of_DRAM()
 #endif /* CONFIG_NEED_MULTIPLE_NODES */
 
 #endif /* __KERNEL__ */

arch/powerpc/include/asm/nvram.h

@@ -10,31 +10,7 @@
 #ifndef _ASM_POWERPC_NVRAM_H
 #define _ASM_POWERPC_NVRAM_H
 
-#include <linux/errno.h>
+/* Signatures for nvram partitions */
-
-#define NVRW_CNT 0x20
-#define NVRAM_HEADER_LEN 16 /* sizeof(struct nvram_header) */
-#define NVRAM_BLOCK_LEN 16
-#define NVRAM_MAX_REQ (2080/NVRAM_BLOCK_LEN)
-#define NVRAM_MIN_REQ (1056/NVRAM_BLOCK_LEN)
-
-#define NVRAM_AS0  0x74
-#define NVRAM_AS1  0x75
-#define NVRAM_DATA 0x77
-
-
-/* RTC Offsets */
-
-#define MOTO_RTC_SECONDS	0x1FF9
-#define MOTO_RTC_MINUTES	0x1FFA
-#define MOTO_RTC_HOURS		0x1FFB
-#define MOTO_RTC_DAY_OF_WEEK	0x1FFC
-#define MOTO_RTC_DAY_OF_MONTH	0x1FFD
-#define MOTO_RTC_MONTH		0x1FFE
-#define MOTO_RTC_YEAR		0x1FFF
-#define MOTO_RTC_CONTROLA       0x1FF8
-#define MOTO_RTC_CONTROLB       0x1FF9
-
 #define NVRAM_SIG_SP	0x02	/* support processor */
 #define NVRAM_SIG_OF	0x50	/* open firmware config */
 #define NVRAM_SIG_FW	0x51	/* general firmware */
@@ -49,32 +25,19 @@
 #define NVRAM_SIG_OS	0xa0	/* OS defined */
 #define NVRAM_SIG_PANIC	0xa1	/* Apple OSX "panic" */
 
-/* If change this size, then change the size of NVNAME_LEN */
-struct nvram_header {
-	unsigned char signature;
-	unsigned char checksum;
-	unsigned short length;
-	char name[12];
-};
-
 #ifdef __KERNEL__
 
+#include <linux/errno.h>
 #include <linux/list.h>
 
-struct nvram_partition {
+#ifdef CONFIG_PPC_PSERIES
-	struct list_head partition;
-	struct nvram_header header;
-	unsigned int index;
-};
-
-
 extern int nvram_write_error_log(char * buff, int length,
 					 unsigned int err_type, unsigned int err_seq);
 extern int nvram_read_error_log(char * buff, int length,
 					 unsigned int * err_type, unsigned int *err_seq);
 extern int nvram_clear_error_log(void);
-
 extern int pSeries_nvram_init(void);
+#endif /* CONFIG_PPC_PSERIES */
 
 #ifdef CONFIG_MMIO_NVRAM
 extern int mmio_nvram_init(void);
@@ -85,6 +48,13 @@ static inline int mmio_nvram_init(void)
 }
 #endif
 
+extern int __init nvram_scan_partitions(void);
+extern loff_t nvram_create_partition(const char *name, int sig,
+				     int req_size, int min_size);
+extern int nvram_remove_partition(const char *name, int sig);
+extern int nvram_get_partition_size(loff_t data_index);
+extern loff_t nvram_find_partition(const char *name, int sig, int *out_size);
+
 #endif /* __KERNEL__ */
 
 /* PowerMac specific nvram stuffs */

arch/powerpc/include/asm/ppc-opcode.h

@@ -36,6 +36,8 @@
 #define PPC_INST_NOP			0x60000000
 #define PPC_INST_POPCNTB		0x7c0000f4
 #define PPC_INST_POPCNTB_MASK		0xfc0007fe
+#define PPC_INST_POPCNTD		0x7c0003f4
+#define PPC_INST_POPCNTW		0x7c0002f4
 #define PPC_INST_RFCI			0x4c000066
 #define PPC_INST_RFDI			0x4c00004e
 #define PPC_INST_RFMCI			0x4c00004c
@@ -88,6 +90,12 @@
 					__PPC_RB(b) | __PPC_EH(eh))
 #define PPC_MSGSND(b)		stringify_in_c(.long PPC_INST_MSGSND | \
 					__PPC_RB(b))
+#define PPC_POPCNTB(a, s)	stringify_in_c(.long PPC_INST_POPCNTB | \
+					__PPC_RA(a) | __PPC_RS(s))
+#define PPC_POPCNTD(a, s)	stringify_in_c(.long PPC_INST_POPCNTD | \
+					__PPC_RA(a) | __PPC_RS(s))
+#define PPC_POPCNTW(a, s)	stringify_in_c(.long PPC_INST_POPCNTW | \
+					__PPC_RA(a) | __PPC_RS(s))
 #define PPC_RFCI		stringify_in_c(.long PPC_INST_RFCI)
 #define PPC_RFDI		stringify_in_c(.long PPC_INST_RFDI)
 #define PPC_RFMCI		stringify_in_c(.long PPC_INST_RFMCI)

arch/powerpc/include/asm/processor.h

@@ -122,7 +122,6 @@ extern struct task_struct *last_task_used_spe;
 		TASK_UNMAPPED_BASE_USER32 : TASK_UNMAPPED_BASE_USER64 )
 #endif
 
-#ifdef __KERNEL__
 #ifdef __powerpc64__
 
 #define STACK_TOP_USER64 TASK_SIZE_USER64
@@ -139,7 +138,6 @@ extern struct task_struct *last_task_used_spe;
 #define STACK_TOP_MAX	STACK_TOP
 
 #endif /* __powerpc64__ */
-#endif /* __KERNEL__ */
 
 typedef struct {
 	unsigned long seg;

arch/powerpc/include/asm/topology.h

@@ -106,9 +106,22 @@ static inline void sysfs_remove_device_from_node(struct sys_device *dev,
 						int nid)
 {
 }
-
 #endif /* CONFIG_NUMA */
 
+#if defined(CONFIG_NUMA) && defined(CONFIG_PPC_SPLPAR)
+extern int start_topology_update(void);
+extern int stop_topology_update(void);
+#else
+static inline int start_topology_update(void)
+{
+	return 0;
+}
+static inline int stop_topology_update(void)
+{
+	return 0;
+}
+#endif /* CONFIG_NUMA && CONFIG_PPC_SPLPAR */
+
 #include <asm-generic/topology.h>
 
 #ifdef CONFIG_SMP

arch/powerpc/include/asm/vdso_datapage.h

@@ -116,9 +116,7 @@ struct vdso_data {
 
 #endif /* CONFIG_PPC64 */
 
-#ifdef __KERNEL__
 extern struct vdso_data *vdso_data;
-#endif
 
 #endif /* __ASSEMBLY__ */
 

arch/powerpc/kernel/Makefile

@@ -29,8 +29,10 @@ endif
 obj-y				:= cputable.o ptrace.o syscalls.o \
 				   irq.o align.o signal_32.o pmc.o vdso.o \
 				   init_task.o process.o systbl.o idle.o \
-				   signal.o sysfs.o cacheinfo.o
+				   signal.o sysfs.o cacheinfo.o time.o \
-obj-y				+= vdso32/
+				   prom.o traps.o setup-common.o \
+				   udbg.o misc.o io.o dma.o \
+				   misc_$(CONFIG_WORD_SIZE).o vdso32/
 obj-$(CONFIG_PPC64)		+= setup_64.o sys_ppc32.o \
 				   signal_64.o ptrace32.o \
 				   paca.o nvram_64.o firmware.o
@@ -80,9 +82,6 @@ extra-$(CONFIG_FSL_BOOKE)	:= head_fsl_booke.o
 extra-$(CONFIG_8xx)		:= head_8xx.o
 extra-y				+= vmlinux.lds
 
-obj-y				+= time.o prom.o traps.o setup-common.o \
-				   udbg.o misc.o io.o dma.o \
-				   misc_$(CONFIG_WORD_SIZE).o
 obj-$(CONFIG_PPC32)		+= entry_32.o setup_32.o
 obj-$(CONFIG_PPC64)		+= dma-iommu.o iommu.o
 obj-$(CONFIG_KGDB)		+= kgdb.o

arch/powerpc/kernel/asm-offsets.c

@@ -209,7 +209,6 @@ int main(void)
 	DEFINE(RTASENTRY, offsetof(struct rtas_t, entry));
 
 	/* Interrupt register frame */
-	DEFINE(STACK_FRAME_OVERHEAD, STACK_FRAME_OVERHEAD);
 	DEFINE(INT_FRAME_SIZE, STACK_INT_FRAME_SIZE);
 	DEFINE(SWITCH_FRAME_SIZE, STACK_FRAME_OVERHEAD + sizeof(struct pt_regs));
 #ifdef CONFIG_PPC64

arch/powerpc/kernel/cputable.c

@@ -457,16 +457,26 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.dcache_bsize		= 128,
 		.num_pmcs		= 6,
 		.pmc_type		= PPC_PMC_IBM,
-		.cpu_setup		= __setup_cpu_power7,
-		.cpu_restore		= __restore_cpu_power7,
 		.oprofile_cpu_type	= "ppc64/power7",
 		.oprofile_type		= PPC_OPROFILE_POWER4,
-		.oprofile_mmcra_sihv	= POWER6_MMCRA_SIHV,
-		.oprofile_mmcra_sipr	= POWER6_MMCRA_SIPR,
-		.oprofile_mmcra_clear	= POWER6_MMCRA_THRM |
-			POWER6_MMCRA_OTHER,
 		.platform		= "power7",
 	},
+	{	/* Power7+ */
+		.pvr_mask		= 0xffff0000,
+		.pvr_value		= 0x004A0000,
+		.cpu_name		= "POWER7+ (raw)",
+		.cpu_features		= CPU_FTRS_POWER7,
+		.cpu_user_features	= COMMON_USER_POWER7,
+		.mmu_features		= MMU_FTR_HPTE_TABLE |
+			MMU_FTR_TLBIE_206,
+		.icache_bsize		= 128,
+		.dcache_bsize		= 128,
+		.num_pmcs		= 6,
+		.pmc_type		= PPC_PMC_IBM,
+		.oprofile_cpu_type	= "ppc64/power7",
+		.oprofile_type		= PPC_OPROFILE_POWER4,
+		.platform		= "power7+",
+	},
 	{	/* Cell Broadband Engine */
 		.pvr_mask		= 0xffff0000,
 		.pvr_value		= 0x00700000,

arch/powerpc/kernel/crash_dump.c

@@ -19,6 +19,7 @@
 #include <asm/prom.h>
 #include <asm/firmware.h>
 #include <asm/uaccess.h>
+#include <asm/rtas.h>
 
 #ifdef DEBUG
 #include <asm/udbg.h>
@@ -141,3 +142,35 @@ ssize_t copy_oldmem_page(unsigned long pfn, char *buf,
 
 	return csize;
 }
+
+#ifdef CONFIG_PPC_RTAS
+/*
+ * The crashkernel region will almost always overlap the RTAS region, so
+ * we have to be careful when shrinking the crashkernel region.
+ */
+void crash_free_reserved_phys_range(unsigned long begin, unsigned long end)
+{
+	unsigned long addr;
+	const u32 *basep, *sizep;
+	unsigned int rtas_start = 0, rtas_end = 0;
+
+	basep = of_get_property(rtas.dev, "linux,rtas-base", NULL);
+	sizep = of_get_property(rtas.dev, "rtas-size", NULL);
+
+	if (basep && sizep) {
+		rtas_start = *basep;
+		rtas_end = *basep + *sizep;
+	}
+
+	for (addr = begin; addr < end; addr += PAGE_SIZE) {
+		/* Does this page overlap with the RTAS region? */
+		if (addr <= rtas_end && ((addr + PAGE_SIZE) > rtas_start))
+			continue;
+
+		ClearPageReserved(pfn_to_page(addr >> PAGE_SHIFT));
+		init_page_count(pfn_to_page(addr >> PAGE_SHIFT));
+		free_page((unsigned long)__va(addr));
+		totalram_pages++;
+	}
+}
+#endif

arch/powerpc/kernel/dma-iommu.c

@@ -19,7 +19,7 @@ static void *dma_iommu_alloc_coherent(struct device *dev, size_t size,
 				      dma_addr_t *dma_handle, gfp_t flag)
 {
 	return iommu_alloc_coherent(dev, get_iommu_table_base(dev), size,
-				    dma_handle, device_to_mask(dev), flag,
+				    dma_handle, dev->coherent_dma_mask, flag,
 				    dev_to_node(dev));
 }
 

arch/powerpc/kernel/entry_32.S

@@ -31,6 +31,7 @@
 #include <asm/asm-offsets.h>
 #include <asm/unistd.h>
 #include <asm/ftrace.h>
+#include <asm/ptrace.h>
 
 #undef SHOW_SYSCALLS
 #undef SHOW_SYSCALLS_TASK

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

@@ -13,6 +13,7 @@
  */
 
 #include <asm/exception-64s.h>
+#include <asm/ptrace.h>
 
 /*
  * We layout physical memory as follows:

arch/powerpc/kernel/fpu.S

@@ -23,6 +23,7 @@
 #include <asm/thread_info.h>
 #include <asm/ppc_asm.h>
 #include <asm/asm-offsets.h>
+#include <asm/ptrace.h>
 
 #ifdef CONFIG_VSX
 #define REST_32FPVSRS(n,c,base)						\

arch/powerpc/kernel/head_40x.S

@@ -40,6 +40,7 @@
 #include <asm/thread_info.h>
 #include <asm/ppc_asm.h>
 #include <asm/asm-offsets.h>
+#include <asm/ptrace.h>
 
 /* As with the other PowerPC ports, it is expected that when code
  * execution begins here, the following registers contain valid, yet

arch/powerpc/kernel/head_44x.S

@@ -37,6 +37,7 @@
 #include <asm/thread_info.h>
 #include <asm/ppc_asm.h>
 #include <asm/asm-offsets.h>
+#include <asm/ptrace.h>
 #include <asm/synch.h>
 #include "head_booke.h"
 

arch/powerpc/kernel/head_64.S

@@ -38,6 +38,7 @@
 #include <asm/page_64.h>
 #include <asm/irqflags.h>
 #include <asm/kvm_book3s_asm.h>
+#include <asm/ptrace.h>
 
 /* The physical memory is layed out such that the secondary processor
  * spin code sits at 0x0000...0x00ff. On server, the vectors follow
@@ -96,7 +97,7 @@ __secondary_hold_acknowledge:
 	.llong hvReleaseData-KERNELBASE
 #endif /* CONFIG_PPC_ISERIES */
 
-#ifdef CONFIG_CRASH_DUMP
+#ifdef CONFIG_RELOCATABLE
 	/* This flag is set to 1 by a loader if the kernel should run
 	 * at the loaded address instead of the linked address.  This
 	 * is used by kexec-tools to keep the the kdump kernel in the
@@ -384,12 +385,10 @@ _STATIC(__after_prom_start)
 	/* process relocations for the final address of the kernel */
 	lis	r25,PAGE_OFFSET@highest	/* compute virtual base of kernel */
 	sldi	r25,r25,32
-#ifdef CONFIG_CRASH_DUMP
 	lwz	r7,__run_at_load-_stext(r26)
-	cmplwi	cr0,r7,1	/* kdump kernel ? - stay where we are */
+	cmplwi	cr0,r7,1	/* flagged to stay where we are ? */
 	bne	1f
 	add	r25,r25,r26
-#endif
 1:	mr	r3,r25
 	bl	.relocate
 #endif

arch/powerpc/kernel/head_8xx.S

@@ -29,6 +29,7 @@
 #include <asm/thread_info.h>
 #include <asm/ppc_asm.h>
 #include <asm/asm-offsets.h>
+#include <asm/ptrace.h>
 
 /* Macro to make the code more readable. */
 #ifdef CONFIG_8xx_CPU6

arch/powerpc/kernel/head_fsl_booke.S

@@ -41,6 +41,7 @@
 #include <asm/ppc_asm.h>
 #include <asm/asm-offsets.h>
 #include <asm/cache.h>
+#include <asm/ptrace.h>
 #include "head_booke.h"
 
 /* As with the other PowerPC ports, it is expected that when code

arch/powerpc/kernel/iommu.c

@@ -311,8 +311,9 @@ int iommu_map_sg(struct device *dev, struct iommu_table *tbl,
 		/* Handle failure */
 		if (unlikely(entry == DMA_ERROR_CODE)) {
 			if (printk_ratelimit())
-				printk(KERN_INFO "iommu_alloc failed, tbl %p vaddr %lx"
+				dev_info(dev, "iommu_alloc failed, tbl %p "
-				       " npages %lx\n", tbl, vaddr, npages);
+					 "vaddr %lx npages %lu\n", tbl, vaddr,
+					 npages);
 			goto failure;
 		}
 
@@ -579,9 +580,9 @@ dma_addr_t iommu_map_page(struct device *dev, struct iommu_table *tbl,
 					 attrs);
 		if (dma_handle == DMA_ERROR_CODE) {
 			if (printk_ratelimit())  {
-				printk(KERN_INFO "iommu_alloc failed, "
+				dev_info(dev, "iommu_alloc failed, tbl %p "
-						"tbl %p vaddr %p npages %d\n",
+					 "vaddr %p npages %d\n", tbl, vaddr,
-						tbl, vaddr, npages);
+					 npages);
 			}
 		} else
 			dma_handle |= (uaddr & ~IOMMU_PAGE_MASK);
@@ -627,7 +628,8 @@ void *iommu_alloc_coherent(struct device *dev, struct iommu_table *tbl,
 	 * the tce tables.
 	 */
 	if (order >= IOMAP_MAX_ORDER) {
-		printk("iommu_alloc_consistent size too large: 0x%lx\n", size);
+		dev_info(dev, "iommu_alloc_consistent size too large: 0x%lx\n",
+			 size);
 		return NULL;
 	}
 

arch/powerpc/kernel/misc.S

@@ -122,8 +122,3 @@ _GLOBAL(longjmp)
 	mtlr	r0
 	mr	r3,r4
 	blr
-
-_GLOBAL(__setup_cpu_power7)
-_GLOBAL(__restore_cpu_power7)
-	/* place holder */
-	blr

arch/powerpc/kernel/misc_32.S

@@ -30,6 +30,7 @@
 #include <asm/processor.h>
 #include <asm/kexec.h>
 #include <asm/bug.h>
+#include <asm/ptrace.h>
 
 	.text
 

arch/powerpc/kernel/misc_64.S

@@ -25,6 +25,7 @@
 #include <asm/cputable.h>
 #include <asm/thread_info.h>
 #include <asm/kexec.h>
+#include <asm/ptrace.h>
 
 	.text
 

arch/powerpc/kernel/nvram_64.c

@@ -34,15 +34,26 @@
 
 #undef DEBUG_NVRAM
 
-static struct nvram_partition * nvram_part;
+#define NVRAM_HEADER_LEN	sizeof(struct nvram_header)
-static long nvram_error_log_index = -1;
+#define NVRAM_BLOCK_LEN		NVRAM_HEADER_LEN
-static long nvram_error_log_size = 0;
 
-struct err_log_info {
+/* If change this size, then change the size of NVNAME_LEN */
-	int error_type;
+struct nvram_header {
-	unsigned int seq_num;
+	unsigned char signature;
+	unsigned char checksum;
+	unsigned short length;
+	/* Terminating null required only for names < 12 chars. */
+	char name[12];
 };
 
+struct nvram_partition {
+	struct list_head partition;
+	struct nvram_header header;
+	unsigned int index;
+};
+
+static LIST_HEAD(nvram_partitions);
+
 static loff_t dev_nvram_llseek(struct file *file, loff_t offset, int origin)
 {
 	int size;
@@ -186,14 +197,12 @@ static struct miscdevice nvram_dev = {
 #ifdef DEBUG_NVRAM
 static void __init nvram_print_partitions(char * label)
 {
-	struct list_head * p;
 	struct nvram_partition * tmp_part;
 	
 	printk(KERN_WARNING "--------%s---------\n", label);
 	printk(KERN_WARNING "indx\t\tsig\tchks\tlen\tname\n");
-	list_for_each(p, &nvram_part->partition) {
+	list_for_each_entry(tmp_part, &nvram_partitions, partition) {
-		tmp_part = list_entry(p, struct nvram_partition, partition);
+		printk(KERN_WARNING "%4d    \t%02x\t%02x\t%d\t%12s\n",
-		printk(KERN_WARNING "%4d    \t%02x\t%02x\t%d\t%s\n",
 		       tmp_part->index, tmp_part->header.signature,
 		       tmp_part->header.checksum, tmp_part->header.length,
 		       tmp_part->header.name);
@@ -228,95 +237,113 @@ static unsigned char __init nvram_checksum(struct nvram_header *p)
 	return c_sum;
 }
 
-static int __init nvram_remove_os_partition(void)
+/**
+ * nvram_remove_partition - Remove one or more partitions in nvram
+ * @name: name of the partition to remove, or NULL for a
+ *        signature only match
+ * @sig: signature of the partition(s) to remove
+ */
+
+int __init nvram_remove_partition(const char *name, int sig)
 {
-	struct list_head *i;
+	struct nvram_partition *part, *prev, *tmp;
-	struct list_head *j;
-	struct nvram_partition * part;
-	struct nvram_partition * cur_part;
 	int rc;
 
-	list_for_each(i, &nvram_part->partition) {
+	list_for_each_entry(part, &nvram_partitions, partition) {
-		part = list_entry(i, struct nvram_partition, partition);
+		if (part->header.signature != sig)
-		if (part->header.signature != NVRAM_SIG_OS)
+			continue;
+		if (name && strncmp(name, part->header.name, 12))
 			continue;
 
-		/* Make os partition a free partition */
+		/* Make partition a free partition */
 		part->header.signature = NVRAM_SIG_FREE;
-		sprintf(part->header.name, "wwwwwwwwwwww");
+		strncpy(part->header.name, "wwwwwwwwwwww", 12);
 		part->header.checksum = nvram_checksum(&part->header);
-
-		/* Merge contiguous free partitions backwards */
-		list_for_each_prev(j, &part->partition) {
-			cur_part = list_entry(j, struct nvram_partition, partition);
-			if (cur_part == nvram_part || cur_part->header.signature != NVRAM_SIG_FREE) {
-				break;
-			}
-			
-			part->header.length += cur_part->header.length;
-			part->header.checksum = nvram_checksum(&part->header);
-			part->index = cur_part->index;
-
-			list_del(&cur_part->partition);
-			kfree(cur_part);
-			j = &part->partition; /* fixup our loop */
-		}
-		
-		/* Merge contiguous free partitions forwards */
-		list_for_each(j, &part->partition) {
-			cur_part = list_entry(j, struct nvram_partition, partition);
-			if (cur_part == nvram_part || cur_part->header.signature != NVRAM_SIG_FREE) {
-				break;
-			}
-
-			part->header.length += cur_part->header.length;
-			part->header.checksum = nvram_checksum(&part->header);
-
-			list_del(&cur_part->partition);
-			kfree(cur_part);
-			j = &part->partition; /* fixup our loop */
-		}
-		
 		rc = nvram_write_header(part);
 		if (rc <= 0) {
-			printk(KERN_ERR "nvram_remove_os_partition: nvram_write failed (%d)\n", rc);
+			printk(KERN_ERR "nvram_remove_partition: nvram_write failed (%d)\n", rc);
 			return rc;
 		}
+	}
 
+	/* Merge contiguous ones */
+	prev = NULL;
+	list_for_each_entry_safe(part, tmp, &nvram_partitions, partition) {
+		if (part->header.signature != NVRAM_SIG_FREE) {
+			prev = NULL;
+			continue;
+		}
+		if (prev) {
+			prev->header.length += part->header.length;
+			prev->header.checksum = nvram_checksum(&part->header);
+			rc = nvram_write_header(part);
+			if (rc <= 0) {
+				printk(KERN_ERR "nvram_remove_partition: nvram_write failed (%d)\n", rc);
+				return rc;
+			}
+			list_del(&part->partition);
+			kfree(part);
+		} else
+			prev = part;
 	}
 	
 	return 0;
 }
 
-/* nvram_create_os_partition
+/**
+ * nvram_create_partition - Create a partition in nvram
+ * @name: name of the partition to create
+ * @sig: signature of the partition to create
+ * @req_size: size of data to allocate in bytes
+ * @min_size: minimum acceptable size (0 means req_size)
  *
- * Create a OS linux partition to buffer error logs.
+ * Returns a negative error code or a positive nvram index
- * Will create a partition starting at the first free
+ * of the beginning of the data area of the newly created
- * space found if space has enough room.
+ * partition. If you provided a min_size smaller than req_size
+ * you need to query for the actual size yourself after the
+ * call using nvram_partition_get_size().
  */
-static int __init nvram_create_os_partition(void)
+loff_t __init nvram_create_partition(const char *name, int sig,
+				     int req_size, int min_size)
 {
 	struct nvram_partition *part;
 	struct nvram_partition *new_part;
 	struct nvram_partition *free_part = NULL;
-	int seq_init[2] = { 0, 0 };
+	static char nv_init_vals[16];
 	loff_t tmp_index;
 	long size = 0;
 	int rc;
 
+	/* Convert sizes from bytes to blocks */
+	req_size = _ALIGN_UP(req_size, NVRAM_BLOCK_LEN) / NVRAM_BLOCK_LEN;
+	min_size = _ALIGN_UP(min_size, NVRAM_BLOCK_LEN) / NVRAM_BLOCK_LEN;
+
+	/* If no minimum size specified, make it the same as the
+	 * requested size
+	 */
+	if (min_size == 0)
+		min_size = req_size;
+	if (min_size > req_size)
+		return -EINVAL;
+
+	/* Now add one block to each for the header */
+	req_size += 1;
+	min_size += 1;
+
 	/* Find a free partition that will give us the maximum needed size 
 	   If can't find one that will give us the minimum size needed */
-	list_for_each_entry(part, &nvram_part->partition, partition) {
+	list_for_each_entry(part, &nvram_partitions, partition) {
 		if (part->header.signature != NVRAM_SIG_FREE)
 			continue;
 
-		if (part->header.length >= NVRAM_MAX_REQ) {
+		if (part->header.length >= req_size) {
-			size = NVRAM_MAX_REQ;
+			size = req_size;
 			free_part = part;
 			break;
 		}
-		if (!size && part->header.length >= NVRAM_MIN_REQ) {
+		if (part->header.length > size &&
-			size = NVRAM_MIN_REQ;
+		    part->header.length >= min_size) {
+			size = part->header.length;
 			free_part = part;
 		}
 	}
@@ -326,136 +353,95 @@ static int __init nvram_create_os_partition(void)
 	/* Create our OS partition */
 	new_part = kmalloc(sizeof(*new_part), GFP_KERNEL);
 	if (!new_part) {
-		printk(KERN_ERR "nvram_create_os_partition: kmalloc failed\n");
+		pr_err("nvram_create_os_partition: kmalloc failed\n");
 		return -ENOMEM;
 	}
 
 	new_part->index = free_part->index;
-	new_part->header.signature = NVRAM_SIG_OS;
+	new_part->header.signature = sig;
 	new_part->header.length = size;
-	strcpy(new_part->header.name, "ppc64,linux");
+	strncpy(new_part->header.name, name, 12);
 	new_part->header.checksum = nvram_checksum(&new_part->header);
 
 	rc = nvram_write_header(new_part);
 	if (rc <= 0) {
-		printk(KERN_ERR "nvram_create_os_partition: nvram_write_header "
+		pr_err("nvram_create_os_partition: nvram_write_header "
-				"failed (%d)\n", rc);
-		return rc;
-	}
-
-	/* make sure and initialize to zero the sequence number and the error
-	   type logged */
-	tmp_index = new_part->index + NVRAM_HEADER_LEN;
-	rc = ppc_md.nvram_write((char *)&seq_init, sizeof(seq_init), &tmp_index);
-	if (rc <= 0) {
-		printk(KERN_ERR "nvram_create_os_partition: nvram_write "
 		       "failed (%d)\n", rc);
 		return rc;
 	}
-	
-	nvram_error_log_index = new_part->index + NVRAM_HEADER_LEN;
-	nvram_error_log_size = ((part->header.length - 1) *
-				NVRAM_BLOCK_LEN) - sizeof(struct err_log_info);
-	
 	list_add_tail(&new_part->partition, &free_part->partition);
 
-	if (free_part->header.length <= size) {
+	/* Adjust or remove the partition we stole the space from */
+	if (free_part->header.length > size) {
+		free_part->index += size * NVRAM_BLOCK_LEN;
+		free_part->header.length -= size;
+		free_part->header.checksum = nvram_checksum(&free_part->header);
+		rc = nvram_write_header(free_part);
+		if (rc <= 0) {
+			pr_err("nvram_create_os_partition: nvram_write_header "
+			       "failed (%d)\n", rc);
+			return rc;
+		}
+	} else {
 		list_del(&free_part->partition);
 		kfree(free_part);
-		return 0;
 	} 
 
-	/* Adjust the partition we stole the space from */
+	/* Clear the new partition */
-	free_part->index += size * NVRAM_BLOCK_LEN;
+	for (tmp_index = new_part->index + NVRAM_HEADER_LEN;
-	free_part->header.length -= size;
+	     tmp_index <  ((size - 1) * NVRAM_BLOCK_LEN);
-	free_part->header.checksum = nvram_checksum(&free_part->header);
+	     tmp_index += NVRAM_BLOCK_LEN) {
-	
+		rc = ppc_md.nvram_write(nv_init_vals, NVRAM_BLOCK_LEN, &tmp_index);
-	rc = nvram_write_header(free_part);
+		if (rc <= 0) {
-	if (rc <= 0) {
+			pr_err("nvram_create_partition: nvram_write failed (%d)\n", rc);
-		printk(KERN_ERR "nvram_create_os_partition: nvram_write_header "
+			return rc;
-		       "failed (%d)\n", rc);
-		return rc;
-	}
-
-	return 0;
-}
-
-
-/* nvram_setup_partition
- *
- * This will setup the partition we need for buffering the
- * error logs and cleanup partitions if needed.
- *
- * The general strategy is the following:
- * 1.) If there is ppc64,linux partition large enough then use it.
- * 2.) If there is not a ppc64,linux partition large enough, search
- * for a free partition that is large enough.
- * 3.) If there is not a free partition large enough remove 
- * _all_ OS partitions and consolidate the space.
- * 4.) Will first try getting a chunk that will satisfy the maximum
- * error log size (NVRAM_MAX_REQ).
- * 5.) If the max chunk cannot be allocated then try finding a chunk
- * that will satisfy the minum needed (NVRAM_MIN_REQ).
- */
-static int __init nvram_setup_partition(void)
-{
-	struct list_head * p;
-	struct nvram_partition * part;
-	int rc;
-
-	/* For now, we don't do any of this on pmac, until I
-	 * have figured out if it's worth killing some unused stuffs
-	 * in our nvram, as Apple defined partitions use pretty much
-	 * all of the space
-	 */
-	if (machine_is(powermac))
-		return -ENOSPC;
-
-	/* see if we have an OS partition that meets our needs.
-	   will try getting the max we need.  If not we'll delete
-	   partitions and try again. */
-	list_for_each(p, &nvram_part->partition) {
-		part = list_entry(p, struct nvram_partition, partition);
-		if (part->header.signature != NVRAM_SIG_OS)
-			continue;
-
-		if (strcmp(part->header.name, "ppc64,linux"))
-			continue;
-
-		if (part->header.length >= NVRAM_MIN_REQ) {
-			/* found our partition */
-			nvram_error_log_index = part->index + NVRAM_HEADER_LEN;
-			nvram_error_log_size = ((part->header.length - 1) *
-						NVRAM_BLOCK_LEN) - sizeof(struct err_log_info);
-			return 0;
 		}
 	}
 	
-	/* try creating a partition with the free space we have */
+	return new_part->index + NVRAM_HEADER_LEN;
-	rc = nvram_create_os_partition();
+}
-	if (!rc) {
-		return 0;
-	}
 
-	/* need to free up some space */
+/**
-	rc = nvram_remove_os_partition();
+ * nvram_get_partition_size - Get the data size of an nvram partition
-	if (rc) {
+ * @data_index: This is the offset of the start of the data of
-		return rc;
+ *              the partition. The same value that is returned by
-	}
+ *              nvram_create_partition().
+ */
+int nvram_get_partition_size(loff_t data_index)
+{
+	struct nvram_partition *part;
 	
-	/* create a partition in this new space */
+	list_for_each_entry(part, &nvram_partitions, partition) {
-	rc = nvram_create_os_partition();
+		if (part->index + NVRAM_HEADER_LEN == data_index)
-	if (rc) {
+			return (part->header.length - 1) * NVRAM_BLOCK_LEN;
-		printk(KERN_ERR "nvram_create_os_partition: Could not find a "
-		       "NVRAM partition large enough\n");
-		return rc;
 	}
-	
+	return -1;
-	return 0;
 }
 
 
-static int __init nvram_scan_partitions(void)
+/**
+ * nvram_find_partition - Find an nvram partition by signature and name
+ * @name: Name of the partition or NULL for any name
+ * @sig: Signature to test against
+ * @out_size: if non-NULL, returns the size of the data part of the partition
+ */
+loff_t nvram_find_partition(const char *name, int sig, int *out_size)
+{
+	struct nvram_partition *p;
+
+	list_for_each_entry(p, &nvram_partitions, partition) {
+		if (p->header.signature == sig &&
+		    (!name || !strncmp(p->header.name, name, 12))) {
+			if (out_size)
+				*out_size = (p->header.length - 1) *
+					NVRAM_BLOCK_LEN;
+			return p->index + NVRAM_HEADER_LEN;
+		}
+	}
+	return 0;
+}
+
+int __init nvram_scan_partitions(void)
 {
 	loff_t cur_index = 0;
 	struct nvram_header phead;
@@ -465,7 +451,7 @@ static int __init nvram_scan_partitions(void)
 	int total_size;
 	int err;
 
-	if (ppc_md.nvram_size == NULL)
+	if (ppc_md.nvram_size == NULL || ppc_md.nvram_size() <= 0)
 		return -ENODEV;
 	total_size = ppc_md.nvram_size();
 	
@@ -512,12 +498,16 @@ static int __init nvram_scan_partitions(void)
 		
 		memcpy(&tmp_part->header, &phead, NVRAM_HEADER_LEN);
 		tmp_part->index = cur_index;
-		list_add_tail(&tmp_part->partition, &nvram_part->partition);
+		list_add_tail(&tmp_part->partition, &nvram_partitions);
 		
 		cur_index += phead.length * NVRAM_BLOCK_LEN;
 	}
 	err = 0;
 
+#ifdef DEBUG_NVRAM
+	nvram_print_partitions("NVRAM Partitions");
+#endif
+
  out:
 	kfree(header);
 	return err;
@@ -525,9 +515,10 @@ static int __init nvram_scan_partitions(void)
 
 static int __init nvram_init(void)
 {
-	int error;
 	int rc;
 	
+	BUILD_BUG_ON(NVRAM_BLOCK_LEN != 16);
+
 	if (ppc_md.nvram_size == NULL || ppc_md.nvram_size() <= 0)
 		return  -ENODEV;
 
@@ -537,29 +528,6 @@ static int __init nvram_init(void)
 		return rc;
 	}
   	
-  	/* initialize our anchor for the nvram partition list */
-  	nvram_part = kmalloc(sizeof(struct nvram_partition), GFP_KERNEL);
-  	if (!nvram_part) {
-  		printk(KERN_ERR "nvram_init: Failed kmalloc\n");
-  		return -ENOMEM;
-  	}
-  	INIT_LIST_HEAD(&nvram_part->partition);
-  
-  	/* Get all the NVRAM partitions */
-  	error = nvram_scan_partitions();
-  	if (error) {
-  		printk(KERN_ERR "nvram_init: Failed nvram_scan_partitions\n");
-  		return error;
-  	}
-  		
-  	if(nvram_setup_partition()) 
-  		printk(KERN_WARNING "nvram_init: Could not find nvram partition"
-  		       " for nvram buffered error logging.\n");
-  
-#ifdef DEBUG_NVRAM
-	nvram_print_partitions("NVRAM Partitions");
-#endif
-
   	return rc;
 }
 
@@ -568,135 +536,6 @@ void __exit nvram_cleanup(void)
         misc_deregister( &nvram_dev );
 }
 
-
-#ifdef CONFIG_PPC_PSERIES
-
-/* nvram_write_error_log
- *
- * We need to buffer the error logs into nvram to ensure that we have
- * the failure information to decode.  If we have a severe error there
- * is no way to guarantee that the OS or the machine is in a state to
- * get back to user land and write the error to disk.  For example if
- * the SCSI device driver causes a Machine Check by writing to a bad
- * IO address, there is no way of guaranteeing that the device driver
- * is in any state that is would also be able to write the error data
- * captured to disk, thus we buffer it in NVRAM for analysis on the
- * next boot.
- *
- * In NVRAM the partition containing the error log buffer will looks like:
- * Header (in bytes):
- * +-----------+----------+--------+------------+------------------+
- * | signature | checksum | length | name       | data             |
- * |0          |1         |2      3|4         15|16        length-1|
- * +-----------+----------+--------+------------+------------------+
- *
- * The 'data' section would look like (in bytes):
- * +--------------+------------+-----------------------------------+
- * | event_logged | sequence # | error log                         |
- * |0            3|4          7|8            nvram_error_log_size-1|
- * +--------------+------------+-----------------------------------+
- *
- * event_logged: 0 if event has not been logged to syslog, 1 if it has
- * sequence #: The unique sequence # for each event. (until it wraps)
- * error log: The error log from event_scan
- */
-int nvram_write_error_log(char * buff, int length,
-                          unsigned int err_type, unsigned int error_log_cnt)
-{
-	int rc;
-	loff_t tmp_index;
-	struct err_log_info info;
-	
-	if (nvram_error_log_index == -1) {
-		return -ESPIPE;
-	}
-
-	if (length > nvram_error_log_size) {
-		length = nvram_error_log_size;
-	}
-
-	info.error_type = err_type;
-	info.seq_num = error_log_cnt;
-
-	tmp_index = nvram_error_log_index;
-
-	rc = ppc_md.nvram_write((char *)&info, sizeof(struct err_log_info), &tmp_index);
-	if (rc <= 0) {
-		printk(KERN_ERR "nvram_write_error_log: Failed nvram_write (%d)\n", rc);
-		return rc;
-	}
-
-	rc = ppc_md.nvram_write(buff, length, &tmp_index);
-	if (rc <= 0) {
-		printk(KERN_ERR "nvram_write_error_log: Failed nvram_write (%d)\n", rc);
-		return rc;
-	}
-	
-	return 0;
-}
-
-/* nvram_read_error_log
- *
- * Reads nvram for error log for at most 'length'
- */
-int nvram_read_error_log(char * buff, int length,
-                         unsigned int * err_type, unsigned int * error_log_cnt)
-{
-	int rc;
-	loff_t tmp_index;
-	struct err_log_info info;
-	
-	if (nvram_error_log_index == -1)
-		return -1;
-
-	if (length > nvram_error_log_size)
-		length = nvram_error_log_size;
-
-	tmp_index = nvram_error_log_index;
-
-	rc = ppc_md.nvram_read((char *)&info, sizeof(struct err_log_info), &tmp_index);
-	if (rc <= 0) {
-		printk(KERN_ERR "nvram_read_error_log: Failed nvram_read (%d)\n", rc);
-		return rc;
-	}
-
-	rc = ppc_md.nvram_read(buff, length, &tmp_index);
-	if (rc <= 0) {
-		printk(KERN_ERR "nvram_read_error_log: Failed nvram_read (%d)\n", rc);
-		return rc;
-	}
-
-	*error_log_cnt = info.seq_num;
-	*err_type = info.error_type;
-
-	return 0;
-}
-
-/* This doesn't actually zero anything, but it sets the event_logged
- * word to tell that this event is safely in syslog.
- */
-int nvram_clear_error_log(void)
-{
-	loff_t tmp_index;
-	int clear_word = ERR_FLAG_ALREADY_LOGGED;
-	int rc;
-
-	if (nvram_error_log_index == -1)
-		return -1;
-
-	tmp_index = nvram_error_log_index;
-	
-	rc = ppc_md.nvram_write((char *)&clear_word, sizeof(int), &tmp_index);
-	if (rc <= 0) {
-		printk(KERN_ERR "nvram_clear_error_log: Failed nvram_write (%d)\n", rc);
-		return rc;
-	}
-
-	return 0;
-}
-
-#endif /* CONFIG_PPC_PSERIES */
-
 module_init(nvram_init);
 module_exit(nvram_cleanup);
 MODULE_LICENSE("GPL");

arch/powerpc/kernel/pci_64.c

@@ -193,8 +193,7 @@ int __devinit pcibios_map_io_space(struct pci_bus *bus)
 	hose->io_resource.start += io_virt_offset;
 	hose->io_resource.end += io_virt_offset;
 
-	pr_debug("  hose->io_resource=0x%016llx...0x%016llx\n",
+	pr_debug("  hose->io_resource=%pR\n", &hose->io_resource);
-		 hose->io_resource.start, hose->io_resource.end);
 
 	return 0;
 }

arch/powerpc/kernel/ppc_ksyms.c

@@ -186,3 +186,10 @@ EXPORT_SYMBOL(__mtdcr);
 EXPORT_SYMBOL(__mfdcr);
 #endif
 EXPORT_SYMBOL(empty_zero_page);
+
+#ifdef CONFIG_PPC64
+EXPORT_SYMBOL(__arch_hweight8);
+EXPORT_SYMBOL(__arch_hweight16);
+EXPORT_SYMBOL(__arch_hweight32);
+EXPORT_SYMBOL(__arch_hweight64);
+#endif

arch/powerpc/kernel/ppc_save_regs.S

@@ -11,6 +11,7 @@
 #include <asm/processor.h>
 #include <asm/ppc_asm.h>
 #include <asm/asm-offsets.h>
+#include <asm/ptrace.h>
 
 /*
  * Grab the register values as they are now.

arch/powerpc/kernel/ptrace.c

@@ -1316,6 +1316,10 @@ static int set_dac_range(struct task_struct *child,
 static long ppc_set_hwdebug(struct task_struct *child,
 		     struct ppc_hw_breakpoint *bp_info)
 {
+#ifndef CONFIG_PPC_ADV_DEBUG_REGS
+	unsigned long dabr;
+#endif
+
 	if (bp_info->version != 1)
 		return -ENOTSUPP;
 #ifdef CONFIG_PPC_ADV_DEBUG_REGS
@@ -1353,11 +1357,10 @@ static long ppc_set_hwdebug(struct task_struct *child,
 	/*
 	 * We only support one data breakpoint
 	 */
-	if (((bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_RW) == 0) ||
+	if ((bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_RW) == 0 ||
-	    ((bp_info->trigger_type & ~PPC_BREAKPOINT_TRIGGER_RW) != 0) ||
+	    (bp_info->trigger_type & ~PPC_BREAKPOINT_TRIGGER_RW) != 0 ||
-	    (bp_info->trigger_type != PPC_BREAKPOINT_TRIGGER_WRITE) ||
+	    bp_info->addr_mode != PPC_BREAKPOINT_MODE_EXACT ||
-	    (bp_info->addr_mode != PPC_BREAKPOINT_MODE_EXACT) ||
+	    bp_info->condition_mode != PPC_BREAKPOINT_CONDITION_NONE)
-	    (bp_info->condition_mode != PPC_BREAKPOINT_CONDITION_NONE))
 		return -EINVAL;
 
 	if (child->thread.dabr)
@@ -1366,7 +1369,14 @@ static long ppc_set_hwdebug(struct task_struct *child,
 	if ((unsigned long)bp_info->addr >= TASK_SIZE)
 		return -EIO;
 
-	child->thread.dabr = (unsigned long)bp_info->addr;
+	dabr = (unsigned long)bp_info->addr & ~7UL;
+	dabr |= DABR_TRANSLATION;
+	if (bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_READ)
+		dabr |= DABR_DATA_READ;
+	if (bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_WRITE)
+		dabr |= DABR_DATA_WRITE;
+
+	child->thread.dabr = dabr;
 
 	return 1;
 #endif /* !CONFIG_PPC_ADV_DEBUG_DVCS */

arch/powerpc/kernel/ptrace32.c

@@ -280,7 +280,11 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
 		/* We only support one DABR and no IABRS at the moment */
 		if (addr > 0)
 			break;
+#ifdef CONFIG_PPC_ADV_DEBUG_REGS
+		ret = put_user(child->thread.dac1, (u32 __user *)data);
+#else
 		ret = put_user(child->thread.dabr, (u32 __user *)data);
+#endif
 		break;
 	}
 
@@ -312,6 +316,9 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
 	case PTRACE_SET_DEBUGREG:
 	case PTRACE_SYSCALL:
 	case PTRACE_CONT:
+	case PPC_PTRACE_GETHWDBGINFO:
+	case PPC_PTRACE_SETHWDEBUG:
+	case PPC_PTRACE_DELHWDEBUG:
 		ret = arch_ptrace(child, request, addr, data);
 		break;
 

arch/powerpc/kernel/rtas.c

@@ -41,6 +41,7 @@
 #include <asm/atomic.h>
 #include <asm/time.h>
 #include <asm/mmu.h>
+#include <asm/topology.h>
 
 struct rtas_t rtas = {
 	.lock = __ARCH_SPIN_LOCK_UNLOCKED
@@ -713,6 +714,7 @@ static int __rtas_suspend_last_cpu(struct rtas_suspend_me_data *data, int wake_w
 	int cpu;
 
 	slb_set_size(SLB_MIN_SIZE);
+	stop_topology_update();
 	printk(KERN_DEBUG "calling ibm,suspend-me on cpu %i\n", smp_processor_id());
 
 	while (rc == H_MULTI_THREADS_ACTIVE && !atomic_read(&data->done) &&
@@ -728,6 +730,7 @@ static int __rtas_suspend_last_cpu(struct rtas_suspend_me_data *data, int wake_w
 		rc = atomic_read(&data->error);
 
 	atomic_set(&data->error, rc);
+	start_topology_update();
 
 	if (wake_when_done) {
 		atomic_set(&data->done, 1);

arch/powerpc/kernel/setup_64.c

@@ -437,8 +437,8 @@ static void __init irqstack_early_init(void)
 	unsigned int i;
 
 	/*
-	 * interrupt stacks must be under 256MB, we cannot afford to take
+	 * Interrupt stacks must be in the first segment since we
-	 * SLB misses on them.
+	 * cannot afford to take SLB misses on them.
 	 */
 	for_each_possible_cpu(i) {
 		softirq_ctx[i] = (struct thread_info *)

arch/powerpc/kernel/smp.c

@@ -466,7 +466,20 @@ out:
 	return id;
 }
 
-/* Must be called when no change can occur to cpu_present_mask,
+/* Helper routines for cpu to core mapping */
+int cpu_core_index_of_thread(int cpu)
+{
+	return cpu >> threads_shift;
+}
+EXPORT_SYMBOL_GPL(cpu_core_index_of_thread);
+
+int cpu_first_thread_of_core(int core)
+{
+	return core << threads_shift;
+}
+EXPORT_SYMBOL_GPL(cpu_first_thread_of_core);
+
+/* Must be called when no change can occur to cpu_present_map,
  * i.e. during cpu online or offline.
  */
 static struct device_node *cpu_to_l2cache(int cpu)
@@ -514,7 +527,7 @@ int __devinit start_secondary(void *unused)
 	notify_cpu_starting(cpu);
 	set_cpu_online(cpu, true);
 	/* Update sibling maps */
-	base = cpu_first_thread_in_core(cpu);
+	base = cpu_first_thread_sibling(cpu);
 	for (i = 0; i < threads_per_core; i++) {
 		if (cpu_is_offline(base + i))
 			continue;
@@ -600,7 +613,7 @@ int __cpu_disable(void)
 		return err;
 
 	/* Update sibling maps */
-	base = cpu_first_thread_in_core(cpu);
+	base = cpu_first_thread_sibling(cpu);
 	for (i = 0; i < threads_per_core; i++) {
 		cpumask_clear_cpu(cpu, cpu_sibling_mask(base + i));
 		cpumask_clear_cpu(base + i, cpu_sibling_mask(cpu));

arch/powerpc/kernel/time.c

@@ -155,7 +155,7 @@ EXPORT_SYMBOL_GPL(rtc_lock);
 
 static u64 tb_to_ns_scale __read_mostly;
 static unsigned tb_to_ns_shift __read_mostly;
-static unsigned long boot_tb __read_mostly;
+static u64 boot_tb __read_mostly;
 
 extern struct timezone sys_tz;
 static long timezone_offset;

arch/powerpc/kernel/vector.S

@@ -5,6 +5,7 @@
 #include <asm/cputable.h>
 #include <asm/thread_info.h>
 #include <asm/page.h>
+#include <asm/ptrace.h>
 
 /*
  * load_up_altivec(unused, unused, tsk)

arch/powerpc/kernel/vio.c

@@ -600,6 +600,11 @@ static void vio_dma_iommu_unmap_sg(struct device *dev,
 	vio_cmo_dealloc(viodev, alloc_size);
 }
 
+static int vio_dma_iommu_dma_supported(struct device *dev, u64 mask)
+{
+        return dma_iommu_ops.dma_supported(dev, mask);
+}
+
 struct dma_map_ops vio_dma_mapping_ops = {
 	.alloc_coherent = vio_dma_iommu_alloc_coherent,
 	.free_coherent  = vio_dma_iommu_free_coherent,
@@ -607,6 +612,7 @@ struct dma_map_ops vio_dma_mapping_ops = {
 	.unmap_sg       = vio_dma_iommu_unmap_sg,
 	.map_page       = vio_dma_iommu_map_page,
 	.unmap_page     = vio_dma_iommu_unmap_page,
+	.dma_supported  = vio_dma_iommu_dma_supported,
 
 };
 
@@ -858,8 +864,7 @@ static void vio_cmo_bus_remove(struct vio_dev *viodev)
 
 static void vio_cmo_set_dma_ops(struct vio_dev *viodev)
 {
-	vio_dma_mapping_ops.dma_supported = dma_iommu_ops.dma_supported;
+	set_dma_ops(&viodev->dev, &vio_dma_mapping_ops);
-	viodev->dev.archdata.dma_ops = &vio_dma_mapping_ops;
 }
 
 /**
@@ -1244,7 +1249,7 @@ struct vio_dev *vio_register_device_node(struct device_node *of_node)
 	if (firmware_has_feature(FW_FEATURE_CMO))
 		vio_cmo_set_dma_ops(viodev);
 	else
-		viodev->dev.archdata.dma_ops = &dma_iommu_ops;
+		set_dma_ops(&viodev->dev, &dma_iommu_ops);
 	set_iommu_table_base(&viodev->dev, vio_build_iommu_table(viodev));
 	set_dev_node(&viodev->dev, of_node_to_nid(of_node));
 
@@ -1252,6 +1257,10 @@ struct vio_dev *vio_register_device_node(struct device_node *of_node)
 	viodev->dev.parent = &vio_bus_device.dev;
 	viodev->dev.bus = &vio_bus_type;
 	viodev->dev.release = vio_dev_release;
+        /* needed to ensure proper operation of coherent allocations
+         * later, in case driver doesn't set it explicitly */
+        dma_set_mask(&viodev->dev, DMA_BIT_MASK(64));
+        dma_set_coherent_mask(&viodev->dev, DMA_BIT_MASK(64));
 
 	/* register with generic device framework */
 	if (device_register(&viodev->dev)) {

arch/powerpc/lib/Makefile

@@ -16,7 +16,7 @@ obj-$(CONFIG_HAS_IOMEM)	+= devres.o
 
 obj-$(CONFIG_PPC64)	+= copypage_64.o copyuser_64.o \
 			   memcpy_64.o usercopy_64.o mem_64.o string.o \
-			   checksum_wrappers_64.o
+			   checksum_wrappers_64.o hweight_64.o
 obj-$(CONFIG_XMON)	+= sstep.o ldstfp.o
 obj-$(CONFIG_KPROBES)	+= sstep.o ldstfp.o
 obj-$(CONFIG_HAVE_HW_BREAKPOINT)	+= sstep.o ldstfp.o

arch/powerpc/lib/hweight_64.S

@@ -0,0 +1,110 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ * Copyright (C) IBM Corporation, 2010
+ *
+ * Author: Anton Blanchard <anton@au.ibm.com>
+ */
+#include <asm/processor.h>
+#include <asm/ppc_asm.h>
+
+/* Note: This code relies on -mminimal-toc */
+
+_GLOBAL(__arch_hweight8)
+BEGIN_FTR_SECTION
+	b .__sw_hweight8
+	nop
+	nop
+FTR_SECTION_ELSE
+	PPC_POPCNTB(r3,r3)
+	clrldi	r3,r3,64-8
+	blr
+ALT_FTR_SECTION_END_IFCLR(CPU_FTR_POPCNTB)
+
+_GLOBAL(__arch_hweight16)
+BEGIN_FTR_SECTION
+	b .__sw_hweight16
+	nop
+	nop
+	nop
+	nop
+FTR_SECTION_ELSE
+  BEGIN_FTR_SECTION_NESTED(50)
+	PPC_POPCNTB(r3,r3)
+	srdi	r4,r3,8
+	add	r3,r4,r3
+	clrldi	r3,r3,64-8
+	blr
+  FTR_SECTION_ELSE_NESTED(50)
+	clrlwi  r3,r3,16
+	PPC_POPCNTW(r3,r3)
+	clrldi	r3,r3,64-8
+	blr
+  ALT_FTR_SECTION_END_NESTED_IFCLR(CPU_FTR_POPCNTD, 50)
+ALT_FTR_SECTION_END_IFCLR(CPU_FTR_POPCNTB)
+
+_GLOBAL(__arch_hweight32)
+BEGIN_FTR_SECTION
+	b .__sw_hweight32
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+FTR_SECTION_ELSE
+  BEGIN_FTR_SECTION_NESTED(51)
+	PPC_POPCNTB(r3,r3)
+	srdi	r4,r3,16
+	add	r3,r4,r3
+	srdi	r4,r3,8
+	add	r3,r4,r3
+	clrldi	r3,r3,64-8
+	blr
+  FTR_SECTION_ELSE_NESTED(51)
+	PPC_POPCNTW(r3,r3)
+	clrldi	r3,r3,64-8
+	blr
+  ALT_FTR_SECTION_END_NESTED_IFCLR(CPU_FTR_POPCNTD, 51)
+ALT_FTR_SECTION_END_IFCLR(CPU_FTR_POPCNTB)
+
+_GLOBAL(__arch_hweight64)
+BEGIN_FTR_SECTION
+	b .__sw_hweight64
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+FTR_SECTION_ELSE
+  BEGIN_FTR_SECTION_NESTED(52)
+	PPC_POPCNTB(r3,r3)
+	srdi	r4,r3,32
+	add	r3,r4,r3
+	srdi	r4,r3,16
+	add	r3,r4,r3
+	srdi	r4,r3,8
+	add	r3,r4,r3
+	clrldi	r3,r3,64-8
+	blr
+  FTR_SECTION_ELSE_NESTED(52)
+	PPC_POPCNTD(r3,r3)
+	clrldi	r3,r3,64-8
+	blr
+  ALT_FTR_SECTION_END_NESTED_IFCLR(CPU_FTR_POPCNTD, 52)
+ALT_FTR_SECTION_END_IFCLR(CPU_FTR_POPCNTB)

arch/powerpc/mm/hash_utils_64.c

@@ -1070,7 +1070,7 @@ void hash_preload(struct mm_struct *mm, unsigned long ea,
 		  unsigned long access, unsigned long trap)
 {
 	unsigned long vsid;
-	void *pgdir;
+	pgd_t *pgdir;
 	pte_t *ptep;
 	unsigned long flags;
 	int rc, ssize, local = 0;

arch/powerpc/mm/mmu_context_nohash.c

@@ -111,8 +111,8 @@ static unsigned int steal_context_smp(unsigned int id)
 		 * a core map instead but this will do for now.
 		 */
 		for_each_cpu(cpu, mm_cpumask(mm)) {
-			for (i = cpu_first_thread_in_core(cpu);
+			for (i = cpu_first_thread_sibling(cpu);
-			     i <= cpu_last_thread_in_core(cpu); i++)
+			     i <= cpu_last_thread_sibling(cpu); i++)
 				__set_bit(id, stale_map[i]);
 			cpu = i - 1;
 		}
@@ -264,14 +264,14 @@ void switch_mmu_context(struct mm_struct *prev, struct mm_struct *next)
 	 */
 	if (test_bit(id, stale_map[cpu])) {
 		pr_hardcont(" | stale flush %d [%d..%d]",
-			    id, cpu_first_thread_in_core(cpu),
+			    id, cpu_first_thread_sibling(cpu),
-			    cpu_last_thread_in_core(cpu));
+			    cpu_last_thread_sibling(cpu));
 
 		local_flush_tlb_mm(next);
 
 		/* XXX This clear should ultimately be part of local_flush_tlb_mm */
-		for (i = cpu_first_thread_in_core(cpu);
+		for (i = cpu_first_thread_sibling(cpu);
-		     i <= cpu_last_thread_in_core(cpu); i++) {
+		     i <= cpu_last_thread_sibling(cpu); i++) {
 			__clear_bit(id, stale_map[i]);
 		}
 	}

arch/powerpc/mm/numa.c

@@ -20,10 +20,15 @@
 #include <linux/memblock.h>
 #include <linux/of.h>
 #include <linux/pfn.h>
+#include <linux/cpuset.h>
+#include <linux/node.h>
 #include <asm/sparsemem.h>
 #include <asm/prom.h>
 #include <asm/system.h>
 #include <asm/smp.h>
+#include <asm/firmware.h>
+#include <asm/paca.h>
+#include <asm/hvcall.h>
 
 static int numa_enabled = 1;
 
@@ -163,7 +168,7 @@ static void __init get_node_active_region(unsigned long start_pfn,
 	work_with_active_regions(nid, get_active_region_work_fn, node_ar);
 }
 
-static void __cpuinit map_cpu_to_node(int cpu, int node)
+static void map_cpu_to_node(int cpu, int node)
 {
 	numa_cpu_lookup_table[cpu] = node;
 
@@ -173,7 +178,7 @@ static void __cpuinit map_cpu_to_node(int cpu, int node)
 		cpumask_set_cpu(cpu, node_to_cpumask_map[node]);
 }
 
-#ifdef CONFIG_HOTPLUG_CPU
+#if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_PPC_SPLPAR)
 static void unmap_cpu_from_node(unsigned long cpu)
 {
 	int node = numa_cpu_lookup_table[cpu];
@@ -187,7 +192,7 @@ static void unmap_cpu_from_node(unsigned long cpu)
 		       cpu, node);
 	}
 }
-#endif /* CONFIG_HOTPLUG_CPU */
+#endif /* CONFIG_HOTPLUG_CPU || CONFIG_PPC_SPLPAR */
 
 /* must hold reference to node during call */
 static const int *of_get_associativity(struct device_node *dev)
@@ -246,32 +251,41 @@ static void initialize_distance_lookup_table(int nid,
 /* Returns nid in the range [0..MAX_NUMNODES-1], or -1 if no useful numa
  * info is found.
  */
-static int of_node_to_nid_single(struct device_node *device)
+static int associativity_to_nid(const unsigned int *associativity)
 {
 	int nid = -1;
-	const unsigned int *tmp;
 
 	if (min_common_depth == -1)
 		goto out;
 
-	tmp = of_get_associativity(device);
+	if (associativity[0] >= min_common_depth)
-	if (!tmp)
+		nid = associativity[min_common_depth];
-		goto out;
-
-	if (tmp[0] >= min_common_depth)
-		nid = tmp[min_common_depth];
 
 	/* POWER4 LPAR uses 0xffff as invalid node */
 	if (nid == 0xffff || nid >= MAX_NUMNODES)
 		nid = -1;
 
-	if (nid > 0 && tmp[0] >= distance_ref_points_depth)
+	if (nid > 0 && associativity[0] >= distance_ref_points_depth)
-		initialize_distance_lookup_table(nid, tmp);
+		initialize_distance_lookup_table(nid, associativity);
 
 out:
 	return nid;
 }
 
+/* Returns the nid associated with the given device tree node,
+ * or -1 if not found.
+ */
+static int of_node_to_nid_single(struct device_node *device)
+{
+	int nid = -1;
+	const unsigned int *tmp;
+
+	tmp = of_get_associativity(device);
+	if (tmp)
+		nid = associativity_to_nid(tmp);
+	return nid;
+}
+
 /* Walk the device tree upwards, looking for an associativity id */
 int of_node_to_nid(struct device_node *device)
 {
@@ -1247,4 +1261,275 @@ int hot_add_scn_to_nid(unsigned long scn_addr)
 	return nid;
 }
 
+static u64 hot_add_drconf_memory_max(void)
+{
+        struct device_node *memory = NULL;
+        unsigned int drconf_cell_cnt = 0;
+        u64 lmb_size = 0;
+        const u32 *dm = 0;
+
+        memory = of_find_node_by_path("/ibm,dynamic-reconfiguration-memory");
+        if (memory) {
+                drconf_cell_cnt = of_get_drconf_memory(memory, &dm);
+                lmb_size = of_get_lmb_size(memory);
+                of_node_put(memory);
+        }
+        return lmb_size * drconf_cell_cnt;
+}
+
+/*
+ * memory_hotplug_max - return max address of memory that may be added
+ *
+ * This is currently only used on systems that support drconfig memory
+ * hotplug.
+ */
+u64 memory_hotplug_max(void)
+{
+        return max(hot_add_drconf_memory_max(), memblock_end_of_DRAM());
+}
 #endif /* CONFIG_MEMORY_HOTPLUG */
+
+/* Vrtual Processor Home Node (VPHN) support */
+#ifdef CONFIG_PPC_SPLPAR
+#define VPHN_NR_CHANGE_CTRS (8)
+static u8 vphn_cpu_change_counts[NR_CPUS][VPHN_NR_CHANGE_CTRS];
+static cpumask_t cpu_associativity_changes_mask;
+static int vphn_enabled;
+static void set_topology_timer(void);
+
+/*
+ * Store the current values of the associativity change counters in the
+ * hypervisor.
+ */
+static void setup_cpu_associativity_change_counters(void)
+{
+	int cpu = 0;
+
+	for_each_possible_cpu(cpu) {
+		int i = 0;
+		u8 *counts = vphn_cpu_change_counts[cpu];
+		volatile u8 *hypervisor_counts = lppaca[cpu].vphn_assoc_counts;
+
+		for (i = 0; i < VPHN_NR_CHANGE_CTRS; i++) {
+			counts[i] = hypervisor_counts[i];
+		}
+	}
+}
+
+/*
+ * The hypervisor maintains a set of 8 associativity change counters in
+ * the VPA of each cpu that correspond to the associativity levels in the
+ * ibm,associativity-reference-points property. When an associativity
+ * level changes, the corresponding counter is incremented.
+ *
+ * Set a bit in cpu_associativity_changes_mask for each cpu whose home
+ * node associativity levels have changed.
+ *
+ * Returns the number of cpus with unhandled associativity changes.
+ */
+static int update_cpu_associativity_changes_mask(void)
+{
+	int cpu = 0, nr_cpus = 0;
+	cpumask_t *changes = &cpu_associativity_changes_mask;
+
+	cpumask_clear(changes);
+
+	for_each_possible_cpu(cpu) {
+		int i, changed = 0;
+		u8 *counts = vphn_cpu_change_counts[cpu];
+		volatile u8 *hypervisor_counts = lppaca[cpu].vphn_assoc_counts;
+
+		for (i = 0; i < VPHN_NR_CHANGE_CTRS; i++) {
+			if (hypervisor_counts[i] > counts[i]) {
+				counts[i] = hypervisor_counts[i];
+				changed = 1;
+			}
+		}
+		if (changed) {
+			cpumask_set_cpu(cpu, changes);
+			nr_cpus++;
+		}
+	}
+
+	return nr_cpus;
+}
+
+/* 6 64-bit registers unpacked into 12 32-bit associativity values */
+#define VPHN_ASSOC_BUFSIZE (6*sizeof(u64)/sizeof(u32))
+
+/*
+ * Convert the associativity domain numbers returned from the hypervisor
+ * to the sequence they would appear in the ibm,associativity property.
+ */
+static int vphn_unpack_associativity(const long *packed, unsigned int *unpacked)
+{
+	int i = 0;
+	int nr_assoc_doms = 0;
+	const u16 *field = (const u16*) packed;
+
+#define VPHN_FIELD_UNUSED	(0xffff)
+#define VPHN_FIELD_MSB		(0x8000)
+#define VPHN_FIELD_MASK		(~VPHN_FIELD_MSB)
+
+	for (i = 0; i < VPHN_ASSOC_BUFSIZE; i++) {
+		if (*field == VPHN_FIELD_UNUSED) {
+			/* All significant fields processed, and remaining
+			 * fields contain the reserved value of all 1's.
+			 * Just store them.
+			 */
+			unpacked[i] = *((u32*)field);
+			field += 2;
+		}
+		else if (*field & VPHN_FIELD_MSB) {
+			/* Data is in the lower 15 bits of this field */
+			unpacked[i] = *field & VPHN_FIELD_MASK;
+			field++;
+			nr_assoc_doms++;
+		}
+		else {
+			/* Data is in the lower 15 bits of this field
+			 * concatenated with the next 16 bit field
+			 */
+			unpacked[i] = *((u32*)field);
+			field += 2;
+			nr_assoc_doms++;
+		}
+	}
+
+	return nr_assoc_doms;
+}
+
+/*
+ * Retrieve the new associativity information for a virtual processor's
+ * home node.
+ */
+static long hcall_vphn(unsigned long cpu, unsigned int *associativity)
+{
+	long rc = 0;
+	long retbuf[PLPAR_HCALL9_BUFSIZE] = {0};
+	u64 flags = 1;
+	int hwcpu = get_hard_smp_processor_id(cpu);
+
+	rc = plpar_hcall9(H_HOME_NODE_ASSOCIATIVITY, retbuf, flags, hwcpu);
+	vphn_unpack_associativity(retbuf, associativity);
+
+	return rc;
+}
+
+static long vphn_get_associativity(unsigned long cpu,
+					unsigned int *associativity)
+{
+	long rc = 0;
+
+	rc = hcall_vphn(cpu, associativity);
+
+	switch (rc) {
+	case H_FUNCTION:
+		printk(KERN_INFO
+			"VPHN is not supported. Disabling polling...\n");
+		stop_topology_update();
+		break;
+	case H_HARDWARE:
+		printk(KERN_ERR
+			"hcall_vphn() experienced a hardware fault "
+			"preventing VPHN. Disabling polling...\n");
+		stop_topology_update();
+	}
+
+	return rc;
+}
+
+/*
+ * Update the node maps and sysfs entries for each cpu whose home node
+ * has changed.
+ */
+int arch_update_cpu_topology(void)
+{
+	int cpu = 0, nid = 0, old_nid = 0;
+	unsigned int associativity[VPHN_ASSOC_BUFSIZE] = {0};
+	struct sys_device *sysdev = NULL;
+
+	for_each_cpu_mask(cpu, cpu_associativity_changes_mask) {
+		vphn_get_associativity(cpu, associativity);
+		nid = associativity_to_nid(associativity);
+
+		if (nid < 0 || !node_online(nid))
+			nid = first_online_node;
+
+		old_nid = numa_cpu_lookup_table[cpu];
+
+		/* Disable hotplug while we update the cpu
+		 * masks and sysfs.
+		 */
+		get_online_cpus();
+		unregister_cpu_under_node(cpu, old_nid);
+		unmap_cpu_from_node(cpu);
+		map_cpu_to_node(cpu, nid);
+		register_cpu_under_node(cpu, nid);
+		put_online_cpus();
+
+		sysdev = get_cpu_sysdev(cpu);
+		if (sysdev)
+			kobject_uevent(&sysdev->kobj, KOBJ_CHANGE);
+	}
+
+	return 1;
+}
+
+static void topology_work_fn(struct work_struct *work)
+{
+	rebuild_sched_domains();
+}
+static DECLARE_WORK(topology_work, topology_work_fn);
+
+void topology_schedule_update(void)
+{
+	schedule_work(&topology_work);
+}
+
+static void topology_timer_fn(unsigned long ignored)
+{
+	if (!vphn_enabled)
+		return;
+	if (update_cpu_associativity_changes_mask() > 0)
+		topology_schedule_update();
+	set_topology_timer();
+}
+static struct timer_list topology_timer =
+	TIMER_INITIALIZER(topology_timer_fn, 0, 0);
+
+static void set_topology_timer(void)
+{
+	topology_timer.data = 0;
+	topology_timer.expires = jiffies + 60 * HZ;
+	add_timer(&topology_timer);
+}
+
+/*
+ * Start polling for VPHN associativity changes.
+ */
+int start_topology_update(void)
+{
+	int rc = 0;
+
+	if (firmware_has_feature(FW_FEATURE_VPHN)) {
+		vphn_enabled = 1;
+		setup_cpu_associativity_change_counters();
+		init_timer_deferrable(&topology_timer);
+		set_topology_timer();
+		rc = 1;
+	}
+
+	return rc;
+}
+__initcall(start_topology_update);
+
+/*
+ * Disable polling for VPHN associativity changes.
+ */
+int stop_topology_update(void)
+{
+	vphn_enabled = 0;
+	return del_timer_sync(&topology_timer);
+}
+#endif /* CONFIG_PPC_SPLPAR */

arch/powerpc/mm/pgtable_32.c

@@ -78,7 +78,7 @@ pgd_t *pgd_alloc(struct mm_struct *mm)
 
 	/* pgdir take page or two with 4K pages and a page fraction otherwise */
 #ifndef CONFIG_PPC_4K_PAGES
-	ret = (pgd_t *)kzalloc(1 << PGDIR_ORDER, GFP_KERNEL);
+	ret = kzalloc(1 << PGDIR_ORDER, GFP_KERNEL);
 #else
 	ret = (pgd_t *)__get_free_pages(GFP_KERNEL|__GFP_ZERO,
 			PGDIR_ORDER - PAGE_SHIFT);
@@ -230,6 +230,7 @@ __ioremap_caller(phys_addr_t addr, unsigned long size, unsigned long flags,
 		area = get_vm_area_caller(size, VM_IOREMAP, caller);
 		if (area == 0)
 			return NULL;
+		area->phys_addr = p;
 		v = (unsigned long) area->addr;
 	} else {
 		v = (ioremap_bot -= size);

arch/powerpc/mm/pgtable_64.c

@@ -223,6 +223,8 @@ void __iomem * __ioremap_caller(phys_addr_t addr, unsigned long size,
 					    caller);
 		if (area == NULL)
 			return NULL;
+
+		area->phys_addr = paligned;
 		ret = __ioremap_at(paligned, area->addr, size, flags);
 		if (!ret)
 			vunmap(area->addr);

arch/powerpc/platforms/44x/Makefile

@@ -1,4 +1,7 @@
-obj-$(CONFIG_44x)	:= misc_44x.o idle.o
+obj-$(CONFIG_44x)	+= misc_44x.o
+ifneq ($(CONFIG_PPC4xx_CPM),y)
+obj-$(CONFIG_44x)	+= idle.o
+endif
 obj-$(CONFIG_PPC44x_SIMPLE) += ppc44x_simple.o
 obj-$(CONFIG_EBONY)	+= ebony.o
 obj-$(CONFIG_SAM440EP) 	+= sam440ep.o

arch/powerpc/platforms/Kconfig

@@ -313,13 +313,14 @@ config OF_RTC
 source "arch/powerpc/sysdev/bestcomm/Kconfig"
 
 config MPC8xxx_GPIO
-	bool "MPC8xxx GPIO support"
+	bool "MPC512x/MPC8xxx GPIO support"
-	depends on PPC_MPC831x || PPC_MPC834x || PPC_MPC837x || FSL_SOC_BOOKE || PPC_86xx
+	depends on PPC_MPC512x || PPC_MPC831x || PPC_MPC834x || PPC_MPC837x || \
+		   FSL_SOC_BOOKE || PPC_86xx
 	select GENERIC_GPIO
 	select ARCH_REQUIRE_GPIOLIB
 	help
 	  Say Y here if you're going to use hardware that connects to the
-	  MPC831x/834x/837x/8572/8610 GPIOs.
+	  MPC512x/831x/834x/837x/8572/8610 GPIOs.
 
 config SIMPLE_GPIO
 	bool "Support for simple, memory-mapped GPIO controllers"

arch/powerpc/platforms/cell/beat_iommu.c

@@ -76,7 +76,7 @@ static void __init celleb_init_direct_mapping(void)
 
 static void celleb_dma_dev_setup(struct device *dev)
 {
-	dev->archdata.dma_ops = get_pci_dma_ops();
+	set_dma_ops(dev, &dma_direct_ops);
 	set_dma_offset(dev, celleb_dma_direct_offset);
 }
 
@@ -106,7 +106,6 @@ static struct notifier_block celleb_of_bus_notifier = {
 static int __init celleb_init_iommu(void)
 {
 	celleb_init_direct_mapping();
-	set_pci_dma_ops(&dma_direct_ops);
 	ppc_md.pci_dma_dev_setup = celleb_pci_dma_dev_setup;
 	bus_register_notifier(&platform_bus_type, &celleb_of_bus_notifier);
 

arch/powerpc/platforms/cell/spufs/lscsa_alloc.c

@@ -36,10 +36,9 @@ static int spu_alloc_lscsa_std(struct spu_state *csa)
 	struct spu_lscsa *lscsa;
 	unsigned char *p;
 
-	lscsa = vmalloc(sizeof(struct spu_lscsa));
+	lscsa = vzalloc(sizeof(struct spu_lscsa));
 	if (!lscsa)
 		return -ENOMEM;
-	memset(lscsa, 0, sizeof(struct spu_lscsa));
 	csa->lscsa = lscsa;
 
 	/* Set LS pages reserved to allow for user-space mapping. */

arch/powerpc/platforms/chrp/time.c

@@ -29,6 +29,10 @@
 
 extern spinlock_t rtc_lock;
 
+#define NVRAM_AS0  0x74
+#define NVRAM_AS1  0x75
+#define NVRAM_DATA 0x77
+
 static int nvram_as1 = NVRAM_AS1;
 static int nvram_as0 = NVRAM_AS0;
 static int nvram_data = NVRAM_DATA;

arch/powerpc/platforms/iseries/mf.c

@@ -1045,71 +1045,9 @@ static const struct file_operations mf_side_proc_fops = {
 	.write		= mf_side_proc_write,
 };
 
-#if 0
-static void mf_getSrcHistory(char *buffer, int size)
-{
-	struct IplTypeReturnStuff return_stuff;
-	struct pending_event *ev = new_pending_event();
-	int rc = 0;
-	char *pages[4];
-
-	pages[0] = kmalloc(4096, GFP_ATOMIC);
-	pages[1] = kmalloc(4096, GFP_ATOMIC);
-	pages[2] = kmalloc(4096, GFP_ATOMIC);
-	pages[3] = kmalloc(4096, GFP_ATOMIC);
-	if ((ev == NULL) || (pages[0] == NULL) || (pages[1] == NULL)
-			 || (pages[2] == NULL) || (pages[3] == NULL))
-		return -ENOMEM;
-
-	return_stuff.xType = 0;
-	return_stuff.xRc = 0;
-	return_stuff.xDone = 0;
-	ev->event.hp_lp_event.xSubtype = 6;
-	ev->event.hp_lp_event.x.xSubtypeData =
-		subtype_data('M', 'F', 'V', 'I');
-	ev->event.data.vsp_cmd.xEvent = &return_stuff;
-	ev->event.data.vsp_cmd.cmd = 4;
-	ev->event.data.vsp_cmd.lp_index = HvLpConfig_getLpIndex();
-	ev->event.data.vsp_cmd.result_code = 0xFF;
-	ev->event.data.vsp_cmd.reserved = 0;
-	ev->event.data.vsp_cmd.sub_data.page[0] = iseries_hv_addr(pages[0]);
-	ev->event.data.vsp_cmd.sub_data.page[1] = iseries_hv_addr(pages[1]);
-	ev->event.data.vsp_cmd.sub_data.page[2] = iseries_hv_addr(pages[2]);
-	ev->event.data.vsp_cmd.sub_data.page[3] = iseries_hv_addr(pages[3]);
-	mb();
-	if (signal_event(ev) != 0)
-		return;
-
- 	while (return_stuff.xDone != 1)
- 		udelay(10);
- 	if (return_stuff.xRc == 0)
- 		memcpy(buffer, pages[0], size);
-	kfree(pages[0]);
-	kfree(pages[1]);
-	kfree(pages[2]);
-	kfree(pages[3]);
-}
-#endif
-
 static int mf_src_proc_show(struct seq_file *m, void *v)
 {
-#if 0
-	int len;
-
-	mf_getSrcHistory(page, count);
-	len = count;
-	len -= off;
-	if (len < count) {
-		*eof = 1;
-		if (len <= 0)
-			return 0;
-	} else
-		len = count;
-	*start = page + off;
-	return len;
-#else
 	return 0;
-#endif
 }
 
 static int mf_src_proc_open(struct inode *inode, struct file *file)

arch/powerpc/platforms/pasemi/iommu.c

@@ -156,20 +156,12 @@ static void iommu_table_iobmap_setup(void)
 
 static void pci_dma_bus_setup_pasemi(struct pci_bus *bus)
 {
-	struct device_node *dn;
-
 	pr_debug("pci_dma_bus_setup, bus %p, bus->self %p\n", bus, bus->self);
 
 	if (!iommu_table_iobmap_inited) {
 		iommu_table_iobmap_inited = 1;
 		iommu_table_iobmap_setup();
 	}
-
-	dn = pci_bus_to_OF_node(bus);
-
-	if (dn)
-		PCI_DN(dn)->iommu_table = &iommu_table_iobmap;
-
 }
 
 
@@ -192,9 +184,6 @@ static void pci_dma_dev_setup_pasemi(struct pci_dev *dev)
 	set_iommu_table_base(&dev->dev, &iommu_table_iobmap);
 }
 
-static void pci_dma_bus_setup_null(struct pci_bus *b) { }
-static void pci_dma_dev_setup_null(struct pci_dev *d) { }
-
 int __init iob_init(struct device_node *dn)
 {
 	unsigned long tmp;
@@ -251,14 +240,8 @@ void __init iommu_init_early_pasemi(void)
 	iommu_off = of_chosen &&
 			of_get_property(of_chosen, "linux,iommu-off", NULL);
 #endif
-	if (iommu_off) {
+	if (iommu_off)
-		/* Direct I/O, IOMMU off */
-		ppc_md.pci_dma_dev_setup = pci_dma_dev_setup_null;
-		ppc_md.pci_dma_bus_setup = pci_dma_bus_setup_null;
-		set_pci_dma_ops(&dma_direct_ops);
-
 		return;
-	}
 
 	iob_init(NULL);
 

arch/powerpc/platforms/powermac/setup.c

@@ -506,6 +506,15 @@ static int __init pmac_declare_of_platform_devices(void)
 		of_platform_device_create(np, "smu", NULL);
 		of_node_put(np);
 	}
+	np = of_find_node_by_type(NULL, "fcu");
+	if (np == NULL) {
+		/* Some machines have strangely broken device-tree */
+		np = of_find_node_by_path("/u3@0,f8000000/i2c@f8001000/fan@15e");
+	}
+	if (np) {
+		of_platform_device_create(np, "temperature", NULL);
+		of_node_put(np);
+	}
 
 	return 0;
 }

arch/powerpc/platforms/pseries/Kconfig

@@ -33,6 +33,16 @@ config PSERIES_MSI
        depends on PCI_MSI && EEH
        default y
 
+config PSERIES_ENERGY
+	tristate "pSeries energy management capabilities driver"
+	depends on PPC_PSERIES
+	default y
+	help
+	  Provides interface to platform energy management capabilities
+	  on supported PSERIES platforms.
+	  Provides: /sys/devices/system/cpu/pseries_(de)activation_hint_list
+	  and /sys/devices/system/cpu/cpuN/pseries_(de)activation_hint
+
 config SCANLOG
 	tristate "Scanlog dump interface"
 	depends on RTAS_PROC && PPC_PSERIES

arch/powerpc/platforms/pseries/Makefile

@@ -11,6 +11,7 @@ obj-$(CONFIG_EEH)	+= eeh.o eeh_cache.o eeh_driver.o eeh_event.o eeh_sysfs.o
 obj-$(CONFIG_KEXEC)	+= kexec.o
 obj-$(CONFIG_PCI)	+= pci.o pci_dlpar.o
 obj-$(CONFIG_PSERIES_MSI)	+= msi.o
+obj-$(CONFIG_PSERIES_ENERGY)	+= pseries_energy.o
 
 obj-$(CONFIG_HOTPLUG_CPU)	+= hotplug-cpu.o
 obj-$(CONFIG_MEMORY_HOTPLUG)	+= hotplug-memory.o

arch/powerpc/platforms/pseries/firmware.c

@@ -55,6 +55,7 @@ firmware_features_table[FIRMWARE_MAX_FEATURES] = {
 	{FW_FEATURE_XDABR,		"hcall-xdabr"},
 	{FW_FEATURE_MULTITCE,		"hcall-multi-tce"},
 	{FW_FEATURE_SPLPAR,		"hcall-splpar"},
+	{FW_FEATURE_VPHN,		"hcall-vphn"},
 };
 
 /* Build up the firmware features bitmask using the contents of

arch/powerpc/platforms/pseries/hvCall.S

@@ -11,6 +11,7 @@
 #include <asm/processor.h>
 #include <asm/ppc_asm.h>
 #include <asm/asm-offsets.h>
+#include <asm/ptrace.h>
 	
 #define STK_PARM(i)     (48 + ((i)-3)*8)
 

arch/powerpc/platforms/pseries/iommu.c

@@ -140,7 +140,7 @@ static int tce_build_pSeriesLP(struct iommu_table *tbl, long tcenum,
 	return ret;
 }
 
-static DEFINE_PER_CPU(u64 *, tce_page) = NULL;
+static DEFINE_PER_CPU(u64 *, tce_page);
 
 static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum,
 				     long npages, unsigned long uaddr,
@@ -323,14 +323,13 @@ static void iommu_table_setparms(struct pci_controller *phb,
 static void iommu_table_setparms_lpar(struct pci_controller *phb,
 				      struct device_node *dn,
 				      struct iommu_table *tbl,
-				      const void *dma_window,
+				      const void *dma_window)
-				      int bussubno)
 {
 	unsigned long offset, size;
 
-	tbl->it_busno  = bussubno;
 	of_parse_dma_window(dn, dma_window, &tbl->it_index, &offset, &size);
 
+	tbl->it_busno = phb->bus->number;
 	tbl->it_base   = 0;
 	tbl->it_blocksize  = 16;
 	tbl->it_type = TCE_PCI;
@@ -450,14 +449,10 @@ static void pci_dma_bus_setup_pSeriesLP(struct pci_bus *bus)
 	if (!ppci->iommu_table) {
 		tbl = kzalloc_node(sizeof(struct iommu_table), GFP_KERNEL,
 				   ppci->phb->node);
-		iommu_table_setparms_lpar(ppci->phb, pdn, tbl, dma_window,
+		iommu_table_setparms_lpar(ppci->phb, pdn, tbl, dma_window);
-			bus->number);
 		ppci->iommu_table = iommu_init_table(tbl, ppci->phb->node);
 		pr_debug("  created table: %p\n", ppci->iommu_table);
 	}
-
-	if (pdn != dn)
-		PCI_DN(dn)->iommu_table = ppci->iommu_table;
 }
 
 
@@ -533,21 +528,11 @@ static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev)
 	}
 	pr_debug("  parent is %s\n", pdn->full_name);
 
-	/* Check for parent == NULL so we don't try to setup the empty EADS
-	 * slots on POWER4 machines.
-	 */
-	if (dma_window == NULL || pdn->parent == NULL) {
-		pr_debug("  no dma window for device, linking to parent\n");
-		set_iommu_table_base(&dev->dev, PCI_DN(pdn)->iommu_table);
-		return;
-	}
-
 	pci = PCI_DN(pdn);
 	if (!pci->iommu_table) {
 		tbl = kzalloc_node(sizeof(struct iommu_table), GFP_KERNEL,
 				   pci->phb->node);
-		iommu_table_setparms_lpar(pci->phb, pdn, tbl, dma_window,
+		iommu_table_setparms_lpar(pci->phb, pdn, tbl, dma_window);
-			pci->phb->bus->number);
 		pci->iommu_table = iommu_init_table(tbl, pci->phb->node);
 		pr_debug("  created table: %p\n", pci->iommu_table);
 	} else {
@@ -571,8 +556,7 @@ static int iommu_reconfig_notifier(struct notifier_block *nb, unsigned long acti
 
 	switch (action) {
 	case PSERIES_RECONFIG_REMOVE:
-		if (pci && pci->iommu_table &&
+		if (pci && pci->iommu_table)
-		    of_get_property(np, "ibm,dma-window", NULL))
 			iommu_free_table(pci->iommu_table, np->full_name);
 		break;
 	default:
@@ -589,13 +573,8 @@ static struct notifier_block iommu_reconfig_nb = {
 /* These are called very early. */
 void iommu_init_early_pSeries(void)
 {
-	if (of_chosen && of_get_property(of_chosen, "linux,iommu-off", NULL)) {
+	if (of_chosen && of_get_property(of_chosen, "linux,iommu-off", NULL))
-		/* Direct I/O, IOMMU off */
-		ppc_md.pci_dma_dev_setup = NULL;
-		ppc_md.pci_dma_bus_setup = NULL;
-		set_pci_dma_ops(&dma_direct_ops);
 		return;
-	}
 
 	if (firmware_has_feature(FW_FEATURE_LPAR)) {
 		if (firmware_has_feature(FW_FEATURE_MULTITCE)) {
@@ -622,3 +601,17 @@ void iommu_init_early_pSeries(void)
 	set_pci_dma_ops(&dma_iommu_ops);
 }
 
+static int __init disable_multitce(char *str)
+{
+	if (strcmp(str, "off") == 0 &&
+	    firmware_has_feature(FW_FEATURE_LPAR) &&
+	    firmware_has_feature(FW_FEATURE_MULTITCE)) {
+		printk(KERN_INFO "Disabling MULTITCE firmware feature\n");
+		ppc_md.tce_build = tce_build_pSeriesLP;
+		ppc_md.tce_free	 = tce_free_pSeriesLP;
+		powerpc_firmware_features &= ~FW_FEATURE_MULTITCE;
+	}
+	return 1;
+}
+
+__setup("multitce=", disable_multitce);

arch/powerpc/platforms/pseries/lpar.c

@@ -627,6 +627,18 @@ static void pSeries_lpar_flush_hash_range(unsigned long number, int local)
 		spin_unlock_irqrestore(&pSeries_lpar_tlbie_lock, flags);
 }
 
+static int __init disable_bulk_remove(char *str)
+{
+	if (strcmp(str, "off") == 0 &&
+	    firmware_has_feature(FW_FEATURE_BULK_REMOVE)) {
+			printk(KERN_INFO "Disabling BULK_REMOVE firmware feature");
+			powerpc_firmware_features &= ~FW_FEATURE_BULK_REMOVE;
+	}
+	return 1;
+}
+
+__setup("bulk_remove=", disable_bulk_remove);
+
 void __init hpte_init_lpar(void)
 {
 	ppc_md.hpte_invalidate	= pSeries_lpar_hpte_invalidate;

arch/powerpc/platforms/pseries/nvram.c

@@ -22,11 +22,25 @@
 #include <asm/prom.h>
 #include <asm/machdep.h>
 
+/* Max bytes to read/write in one go */
+#define NVRW_CNT 0x20
+
 static unsigned int nvram_size;
 static int nvram_fetch, nvram_store;
 static char nvram_buf[NVRW_CNT];	/* assume this is in the first 4GB */
 static DEFINE_SPINLOCK(nvram_lock);
 
+static long nvram_error_log_index = -1;
+static long nvram_error_log_size = 0;
+
+struct err_log_info {
+	int error_type;
+	unsigned int seq_num;
+};
+#define NVRAM_MAX_REQ		2079
+#define NVRAM_MIN_REQ		1055
+
+#define NVRAM_LOG_PART_NAME	"ibm,rtas-log"
 
 static ssize_t pSeries_nvram_read(char *buf, size_t count, loff_t *index)
 {
@@ -119,6 +133,197 @@ static ssize_t pSeries_nvram_get_size(void)
 	return nvram_size ? nvram_size : -ENODEV;
 }
 
+
+/* nvram_write_error_log
+ *
+ * We need to buffer the error logs into nvram to ensure that we have
+ * the failure information to decode.  If we have a severe error there
+ * is no way to guarantee that the OS or the machine is in a state to
+ * get back to user land and write the error to disk.  For example if
+ * the SCSI device driver causes a Machine Check by writing to a bad
+ * IO address, there is no way of guaranteeing that the device driver
+ * is in any state that is would also be able to write the error data
+ * captured to disk, thus we buffer it in NVRAM for analysis on the
+ * next boot.
+ *
+ * In NVRAM the partition containing the error log buffer will looks like:
+ * Header (in bytes):
+ * +-----------+----------+--------+------------+------------------+
+ * | signature | checksum | length | name       | data             |
+ * |0          |1         |2      3|4         15|16        length-1|
+ * +-----------+----------+--------+------------+------------------+
+ *
+ * The 'data' section would look like (in bytes):
+ * +--------------+------------+-----------------------------------+
+ * | event_logged | sequence # | error log                         |
+ * |0            3|4          7|8            nvram_error_log_size-1|
+ * +--------------+------------+-----------------------------------+
+ *
+ * event_logged: 0 if event has not been logged to syslog, 1 if it has
+ * sequence #: The unique sequence # for each event. (until it wraps)
+ * error log: The error log from event_scan
+ */
+int nvram_write_error_log(char * buff, int length,
+                          unsigned int err_type, unsigned int error_log_cnt)
+{
+	int rc;
+	loff_t tmp_index;
+	struct err_log_info info;
+	
+	if (nvram_error_log_index == -1) {
+		return -ESPIPE;
+	}
+
+	if (length > nvram_error_log_size) {
+		length = nvram_error_log_size;
+	}
+
+	info.error_type = err_type;
+	info.seq_num = error_log_cnt;
+
+	tmp_index = nvram_error_log_index;
+
+	rc = ppc_md.nvram_write((char *)&info, sizeof(struct err_log_info), &tmp_index);
+	if (rc <= 0) {
+		printk(KERN_ERR "nvram_write_error_log: Failed nvram_write (%d)\n", rc);
+		return rc;
+	}
+
+	rc = ppc_md.nvram_write(buff, length, &tmp_index);
+	if (rc <= 0) {
+		printk(KERN_ERR "nvram_write_error_log: Failed nvram_write (%d)\n", rc);
+		return rc;
+	}
+	
+	return 0;
+}
+
+/* nvram_read_error_log
+ *
+ * Reads nvram for error log for at most 'length'
+ */
+int nvram_read_error_log(char * buff, int length,
+                         unsigned int * err_type, unsigned int * error_log_cnt)
+{
+	int rc;
+	loff_t tmp_index;
+	struct err_log_info info;
+	
+	if (nvram_error_log_index == -1)
+		return -1;
+
+	if (length > nvram_error_log_size)
+		length = nvram_error_log_size;
+
+	tmp_index = nvram_error_log_index;
+
+	rc = ppc_md.nvram_read((char *)&info, sizeof(struct err_log_info), &tmp_index);
+	if (rc <= 0) {
+		printk(KERN_ERR "nvram_read_error_log: Failed nvram_read (%d)\n", rc);
+		return rc;
+	}
+
+	rc = ppc_md.nvram_read(buff, length, &tmp_index);
+	if (rc <= 0) {
+		printk(KERN_ERR "nvram_read_error_log: Failed nvram_read (%d)\n", rc);
+		return rc;
+	}
+
+	*error_log_cnt = info.seq_num;
+	*err_type = info.error_type;
+
+	return 0;
+}
+
+/* This doesn't actually zero anything, but it sets the event_logged
+ * word to tell that this event is safely in syslog.
+ */
+int nvram_clear_error_log(void)
+{
+	loff_t tmp_index;
+	int clear_word = ERR_FLAG_ALREADY_LOGGED;
+	int rc;
+
+	if (nvram_error_log_index == -1)
+		return -1;
+
+	tmp_index = nvram_error_log_index;
+	
+	rc = ppc_md.nvram_write((char *)&clear_word, sizeof(int), &tmp_index);
+	if (rc <= 0) {
+		printk(KERN_ERR "nvram_clear_error_log: Failed nvram_write (%d)\n", rc);
+		return rc;
+	}
+
+	return 0;
+}
+
+/* pseries_nvram_init_log_partition
+ *
+ * This will setup the partition we need for buffering the
+ * error logs and cleanup partitions if needed.
+ *
+ * The general strategy is the following:
+ * 1.) If there is log partition large enough then use it.
+ * 2.) If there is none large enough, search
+ * for a free partition that is large enough.
+ * 3.) If there is not a free partition large enough remove 
+ * _all_ OS partitions and consolidate the space.
+ * 4.) Will first try getting a chunk that will satisfy the maximum
+ * error log size (NVRAM_MAX_REQ).
+ * 5.) If the max chunk cannot be allocated then try finding a chunk
+ * that will satisfy the minum needed (NVRAM_MIN_REQ).
+ */
+static int __init pseries_nvram_init_log_partition(void)
+{
+	loff_t p;
+	int size;
+
+	/* Scan nvram for partitions */
+	nvram_scan_partitions();
+
+	/* Lookg for ours */
+	p = nvram_find_partition(NVRAM_LOG_PART_NAME, NVRAM_SIG_OS, &size);
+
+	/* Found one but too small, remove it */
+	if (p && size < NVRAM_MIN_REQ) {
+		pr_info("nvram: Found too small "NVRAM_LOG_PART_NAME" partition"
+			",removing it...");
+		nvram_remove_partition(NVRAM_LOG_PART_NAME, NVRAM_SIG_OS);
+		p = 0;
+	}
+
+	/* Create one if we didn't find */
+	if (!p) {
+		p = nvram_create_partition(NVRAM_LOG_PART_NAME, NVRAM_SIG_OS,
+					   NVRAM_MAX_REQ, NVRAM_MIN_REQ);
+		/* No room for it, try to get rid of any OS partition
+		 * and try again
+		 */
+		if (p == -ENOSPC) {
+			pr_info("nvram: No room to create "NVRAM_LOG_PART_NAME
+				" partition, deleting all OS partitions...");
+			nvram_remove_partition(NULL, NVRAM_SIG_OS);
+			p = nvram_create_partition(NVRAM_LOG_PART_NAME,
+						   NVRAM_SIG_OS, NVRAM_MAX_REQ,
+						   NVRAM_MIN_REQ);
+		}
+	}
+
+	if (p <= 0) {
+		pr_err("nvram: Failed to find or create "NVRAM_LOG_PART_NAME
+		       " partition, err %d\n", (int)p);
+		return 0;
+	}
+
+	nvram_error_log_index = p;
+	nvram_error_log_size = nvram_get_partition_size(p) -
+		sizeof(struct err_log_info);
+	
+	return 0;
+}
+machine_arch_initcall(pseries, pseries_nvram_init_log_partition);
+
 int __init pSeries_nvram_init(void)
 {
 	struct device_node *nvram;

arch/powerpc/platforms/pseries/pseries_energy.c

@@ -0,0 +1,326 @@
+/*
+ * POWER platform energy management driver
+ * Copyright (C) 2010 IBM Corporation
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * version 2 as published by the Free Software Foundation.
+ *
+ * This pseries platform device driver provides access to
+ * platform energy management capabilities.
+ */
+
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/errno.h>
+#include <linux/init.h>
+#include <linux/seq_file.h>
+#include <linux/sysdev.h>
+#include <linux/cpu.h>
+#include <linux/of.h>
+#include <asm/cputhreads.h>
+#include <asm/page.h>
+#include <asm/hvcall.h>
+
+
+#define MODULE_VERS "1.0"
+#define MODULE_NAME "pseries_energy"
+
+/* Driver flags */
+
+static int sysfs_entries;
+
+/* Helper routines */
+
+/*
+ * Routine to detect firmware support for hcall
+ * return 1 if H_BEST_ENERGY is supported
+ * else return 0
+ */
+
+static int check_for_h_best_energy(void)
+{
+	struct device_node *rtas = NULL;
+	const char *hypertas, *s;
+	int length;
+	int rc = 0;
+
+	rtas = of_find_node_by_path("/rtas");
+	if (!rtas)
+		return 0;
+
+	hypertas = of_get_property(rtas, "ibm,hypertas-functions", &length);
+	if (!hypertas) {
+		of_node_put(rtas);
+		return 0;
+	}
+
+	/* hypertas will have list of strings with hcall names */
+	for (s = hypertas; s < hypertas + length; s += strlen(s) + 1) {
+		if (!strncmp("hcall-best-energy-1", s, 19)) {
+			rc = 1; /* Found the string */
+			break;
+		}
+	}
+	of_node_put(rtas);
+	return rc;
+}
+
+/* Helper Routines to convert between drc_index to cpu numbers */
+
+static u32 cpu_to_drc_index(int cpu)
+{
+	struct device_node *dn = NULL;
+	const int *indexes;
+	int i;
+	int rc = 1;
+	u32 ret = 0;
+
+	dn = of_find_node_by_path("/cpus");
+	if (dn == NULL)
+		goto err;
+	indexes = of_get_property(dn, "ibm,drc-indexes", NULL);
+	if (indexes == NULL)
+		goto err_of_node_put;
+	/* Convert logical cpu number to core number */
+	i = cpu_core_index_of_thread(cpu);
+	/*
+	 * The first element indexes[0] is the number of drc_indexes
+	 * returned in the list.  Hence i+1 will get the drc_index
+	 * corresponding to core number i.
+	 */
+	WARN_ON(i > indexes[0]);
+	ret = indexes[i + 1];
+	rc = 0;
+
+err_of_node_put:
+	of_node_put(dn);
+err:
+	if (rc)
+		printk(KERN_WARNING "cpu_to_drc_index(%d) failed", cpu);
+	return ret;
+}
+
+static int drc_index_to_cpu(u32 drc_index)
+{
+	struct device_node *dn = NULL;
+	const int *indexes;
+	int i, cpu = 0;
+	int rc = 1;
+
+	dn = of_find_node_by_path("/cpus");
+	if (dn == NULL)
+		goto err;
+	indexes = of_get_property(dn, "ibm,drc-indexes", NULL);
+	if (indexes == NULL)
+		goto err_of_node_put;
+	/*
+	 * First element in the array is the number of drc_indexes
+	 * returned.  Search through the list to find the matching
+	 * drc_index and get the core number
+	 */
+	for (i = 0; i < indexes[0]; i++) {
+		if (indexes[i + 1] == drc_index)
+			break;
+	}
+	/* Convert core number to logical cpu number */
+	cpu = cpu_first_thread_of_core(i);
+	rc = 0;
+
+err_of_node_put:
+	of_node_put(dn);
+err:
+	if (rc)
+		printk(KERN_WARNING "drc_index_to_cpu(%d) failed", drc_index);
+	return cpu;
+}
+
+/*
+ * pseries hypervisor call H_BEST_ENERGY provides hints to OS on
+ * preferred logical cpus to activate or deactivate for optimized
+ * energy consumption.
+ */
+
+#define FLAGS_MODE1	0x004E200000080E01
+#define FLAGS_MODE2	0x004E200000080401
+#define FLAGS_ACTIVATE  0x100
+
+static ssize_t get_best_energy_list(char *page, int activate)
+{
+	int rc, cnt, i, cpu;
+	unsigned long retbuf[PLPAR_HCALL9_BUFSIZE];
+	unsigned long flags = 0;
+	u32 *buf_page;
+	char *s = page;
+
+	buf_page = (u32 *) get_zeroed_page(GFP_KERNEL);
+	if (!buf_page)
+		return -ENOMEM;
+
+	flags = FLAGS_MODE1;
+	if (activate)
+		flags |= FLAGS_ACTIVATE;
+
+	rc = plpar_hcall9(H_BEST_ENERGY, retbuf, flags, 0, __pa(buf_page),
+				0, 0, 0, 0, 0, 0);
+	if (rc != H_SUCCESS) {
+		free_page((unsigned long) buf_page);
+		return -EINVAL;
+	}
+
+	cnt = retbuf[0];
+	for (i = 0; i < cnt; i++) {
+		cpu = drc_index_to_cpu(buf_page[2*i+1]);
+		if ((cpu_online(cpu) && !activate) ||
+		    (!cpu_online(cpu) && activate))
+			s += sprintf(s, "%d,", cpu);
+	}
+	if (s > page) { /* Something to show */
+		s--; /* Suppress last comma */
+		s += sprintf(s, "\n");
+	}
+
+	free_page((unsigned long) buf_page);
+	return s-page;
+}
+
+static ssize_t get_best_energy_data(struct sys_device *dev,
+					char *page, int activate)
+{
+	int rc;
+	unsigned long retbuf[PLPAR_HCALL9_BUFSIZE];
+	unsigned long flags = 0;
+
+	flags = FLAGS_MODE2;
+	if (activate)
+		flags |= FLAGS_ACTIVATE;
+
+	rc = plpar_hcall9(H_BEST_ENERGY, retbuf, flags,
+				cpu_to_drc_index(dev->id),
+				0, 0, 0, 0, 0, 0, 0);
+
+	if (rc != H_SUCCESS)
+		return -EINVAL;
+
+	return sprintf(page, "%lu\n", retbuf[1] >> 32);
+}
+
+/* Wrapper functions */
+
+static ssize_t cpu_activate_hint_list_show(struct sysdev_class *class,
+			struct sysdev_class_attribute *attr, char *page)
+{
+	return get_best_energy_list(page, 1);
+}
+
+static ssize_t cpu_deactivate_hint_list_show(struct sysdev_class *class,
+			struct sysdev_class_attribute *attr, char *page)
+{
+	return get_best_energy_list(page, 0);
+}
+
+static ssize_t percpu_activate_hint_show(struct sys_device *dev,
+			struct sysdev_attribute *attr, char *page)
+{
+	return get_best_energy_data(dev, page, 1);
+}
+
+static ssize_t percpu_deactivate_hint_show(struct sys_device *dev,
+			struct sysdev_attribute *attr, char *page)
+{
+	return get_best_energy_data(dev, page, 0);
+}
+
+/*
+ * Create sysfs interface:
+ * /sys/devices/system/cpu/pseries_activate_hint_list
+ * /sys/devices/system/cpu/pseries_deactivate_hint_list
+ *	Comma separated list of cpus to activate or deactivate
+ * /sys/devices/system/cpu/cpuN/pseries_activate_hint
+ * /sys/devices/system/cpu/cpuN/pseries_deactivate_hint
+ *	Per-cpu value of the hint
+ */
+
+struct sysdev_class_attribute attr_cpu_activate_hint_list =
+		_SYSDEV_CLASS_ATTR(pseries_activate_hint_list, 0444,
+		cpu_activate_hint_list_show, NULL);
+
+struct sysdev_class_attribute attr_cpu_deactivate_hint_list =
+		_SYSDEV_CLASS_ATTR(pseries_deactivate_hint_list, 0444,
+		cpu_deactivate_hint_list_show, NULL);
+
+struct sysdev_attribute attr_percpu_activate_hint =
+		_SYSDEV_ATTR(pseries_activate_hint, 0444,
+		percpu_activate_hint_show, NULL);
+
+struct sysdev_attribute attr_percpu_deactivate_hint =
+		_SYSDEV_ATTR(pseries_deactivate_hint, 0444,
+		percpu_deactivate_hint_show, NULL);
+
+static int __init pseries_energy_init(void)
+{
+	int cpu, err;
+	struct sys_device *cpu_sys_dev;
+
+	if (!check_for_h_best_energy()) {
+		printk(KERN_INFO "Hypercall H_BEST_ENERGY not supported\n");
+		return 0;
+	}
+	/* Create the sysfs files */
+	err = sysfs_create_file(&cpu_sysdev_class.kset.kobj,
+				&attr_cpu_activate_hint_list.attr);
+	if (!err)
+		err = sysfs_create_file(&cpu_sysdev_class.kset.kobj,
+				&attr_cpu_deactivate_hint_list.attr);
+
+	if (err)
+		return err;
+	for_each_possible_cpu(cpu) {
+		cpu_sys_dev = get_cpu_sysdev(cpu);
+		err = sysfs_create_file(&cpu_sys_dev->kobj,
+				&attr_percpu_activate_hint.attr);
+		if (err)
+			break;
+		err = sysfs_create_file(&cpu_sys_dev->kobj,
+				&attr_percpu_deactivate_hint.attr);
+		if (err)
+			break;
+	}
+
+	if (err)
+		return err;
+
+	sysfs_entries = 1; /* Removed entries on cleanup */
+	return 0;
+
+}
+
+static void __exit pseries_energy_cleanup(void)
+{
+	int cpu;
+	struct sys_device *cpu_sys_dev;
+
+	if (!sysfs_entries)
+		return;
+
+	/* Remove the sysfs files */
+	sysfs_remove_file(&cpu_sysdev_class.kset.kobj,
+				&attr_cpu_activate_hint_list.attr);
+
+	sysfs_remove_file(&cpu_sysdev_class.kset.kobj,
+				&attr_cpu_deactivate_hint_list.attr);
+
+	for_each_possible_cpu(cpu) {
+		cpu_sys_dev = get_cpu_sysdev(cpu);
+		sysfs_remove_file(&cpu_sys_dev->kobj,
+				&attr_percpu_activate_hint.attr);
+		sysfs_remove_file(&cpu_sys_dev->kobj,
+				&attr_percpu_deactivate_hint.attr);
+	}
+}
+
+module_init(pseries_energy_init);
+module_exit(pseries_energy_cleanup);
+MODULE_DESCRIPTION("Driver for pSeries platform energy management");
+MODULE_AUTHOR("Vaidyanathan Srinivasan");
+MODULE_LICENSE("GPL");

arch/powerpc/sysdev/Makefile

@@ -41,6 +41,7 @@ obj-$(CONFIG_OF_RTC)		+= of_rtc.o
 ifeq ($(CONFIG_PCI),y)
 obj-$(CONFIG_4xx)		+= ppc4xx_pci.o
 endif
+obj-$(CONFIG_PPC4xx_CPM)	+= ppc4xx_cpm.o
 obj-$(CONFIG_PPC4xx_GPIO)	+= ppc4xx_gpio.o
 
 obj-$(CONFIG_CPM)		+= cpm_common.o

arch/powerpc/sysdev/dart_iommu.c

@@ -312,17 +312,10 @@ static void pci_dma_dev_setup_dart(struct pci_dev *dev)
 
 static void pci_dma_bus_setup_dart(struct pci_bus *bus)
 {
-	struct device_node *dn;
-
 	if (!iommu_table_dart_inited) {
 		iommu_table_dart_inited = 1;
 		iommu_table_dart_setup();
 	}
-
-	dn = pci_bus_to_OF_node(bus);
-
-	if (dn)
-		PCI_DN(dn)->iommu_table = &iommu_table_dart;
 }
 
 static bool dart_device_on_pcie(struct device *dev)
@@ -373,7 +366,7 @@ void __init iommu_init_early_dart(void)
 	if (dn == NULL) {
 		dn = of_find_compatible_node(NULL, "dart", "u4-dart");
 		if (dn == NULL)
-			goto bail;
+			return;	/* use default direct_dma_ops */
 		dart_is_u4 = 1;
 	}
 

arch/powerpc/sysdev/mpc8xxx_gpio.c

@@ -1,5 +1,5 @@
 /*
- * GPIOs on MPC8349/8572/8610 and compatible
+ * GPIOs on MPC512x/8349/8572/8610 and compatible
  *
  * Copyright (C) 2008 Peter Korsgaard <jacmet@sunsite.dk>
  *
@@ -26,6 +26,7 @@
 #define GPIO_IER		0x0c
 #define GPIO_IMR		0x10
 #define GPIO_ICR		0x14
+#define GPIO_ICR2		0x18
 
 struct mpc8xxx_gpio_chip {
 	struct of_mm_gpio_chip mm_gc;
@@ -37,6 +38,7 @@ struct mpc8xxx_gpio_chip {
 	 */
 	u32 data;
 	struct irq_host *irq;
+	void *of_dev_id_data;
 };
 
 static inline u32 mpc8xxx_gpio2mask(unsigned int gpio)
@@ -215,6 +217,51 @@ static int mpc8xxx_irq_set_type(unsigned int virq, unsigned int flow_type)
 	return 0;
 }
 
+static int mpc512x_irq_set_type(unsigned int virq, unsigned int flow_type)
+{
+	struct mpc8xxx_gpio_chip *mpc8xxx_gc = get_irq_chip_data(virq);
+	struct of_mm_gpio_chip *mm = &mpc8xxx_gc->mm_gc;
+	unsigned long gpio = virq_to_hw(virq);
+	void __iomem *reg;
+	unsigned int shift;
+	unsigned long flags;
+
+	if (gpio < 16) {
+		reg = mm->regs + GPIO_ICR;
+		shift = (15 - gpio) * 2;
+	} else {
+		reg = mm->regs + GPIO_ICR2;
+		shift = (15 - (gpio % 16)) * 2;
+	}
+
+	switch (flow_type) {
+	case IRQ_TYPE_EDGE_FALLING:
+	case IRQ_TYPE_LEVEL_LOW:
+		spin_lock_irqsave(&mpc8xxx_gc->lock, flags);
+		clrsetbits_be32(reg, 3 << shift, 2 << shift);
+		spin_unlock_irqrestore(&mpc8xxx_gc->lock, flags);
+		break;
+
+	case IRQ_TYPE_EDGE_RISING:
+	case IRQ_TYPE_LEVEL_HIGH:
+		spin_lock_irqsave(&mpc8xxx_gc->lock, flags);
+		clrsetbits_be32(reg, 3 << shift, 1 << shift);
+		spin_unlock_irqrestore(&mpc8xxx_gc->lock, flags);
+		break;
+
+	case IRQ_TYPE_EDGE_BOTH:
+		spin_lock_irqsave(&mpc8xxx_gc->lock, flags);
+		clrbits32(reg, 3 << shift);
+		spin_unlock_irqrestore(&mpc8xxx_gc->lock, flags);
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static struct irq_chip mpc8xxx_irq_chip = {
 	.name		= "mpc8xxx-gpio",
 	.unmask		= mpc8xxx_irq_unmask,
@@ -226,6 +273,11 @@ static struct irq_chip mpc8xxx_irq_chip = {
 static int mpc8xxx_gpio_irq_map(struct irq_host *h, unsigned int virq,
 				irq_hw_number_t hw)
 {
+	struct mpc8xxx_gpio_chip *mpc8xxx_gc = h->host_data;
+
+	if (mpc8xxx_gc->of_dev_id_data)
+		mpc8xxx_irq_chip.set_type = mpc8xxx_gc->of_dev_id_data;
+
 	set_irq_chip_data(virq, h->host_data);
 	set_irq_chip_and_handler(virq, &mpc8xxx_irq_chip, handle_level_irq);
 	set_irq_type(virq, IRQ_TYPE_NONE);
@@ -253,11 +305,20 @@ static struct irq_host_ops mpc8xxx_gpio_irq_ops = {
 	.xlate	= mpc8xxx_gpio_irq_xlate,
 };
 
+static struct of_device_id mpc8xxx_gpio_ids[] __initdata = {
+	{ .compatible = "fsl,mpc8349-gpio", },
+	{ .compatible = "fsl,mpc8572-gpio", },
+	{ .compatible = "fsl,mpc8610-gpio", },
+	{ .compatible = "fsl,mpc5121-gpio", .data = mpc512x_irq_set_type, },
+	{}
+};
+
 static void __init mpc8xxx_add_controller(struct device_node *np)
 {
 	struct mpc8xxx_gpio_chip *mpc8xxx_gc;
 	struct of_mm_gpio_chip *mm_gc;
 	struct gpio_chip *gc;
+	const struct of_device_id *id;
 	unsigned hwirq;
 	int ret;
 
@@ -297,6 +358,10 @@ static void __init mpc8xxx_add_controller(struct device_node *np)
 	if (!mpc8xxx_gc->irq)
 		goto skip_irq;
 
+	id = of_match_node(mpc8xxx_gpio_ids, np);
+	if (id)
+		mpc8xxx_gc->of_dev_id_data = id->data;
+
 	mpc8xxx_gc->irq->host_data = mpc8xxx_gc;
 
 	/* ack and mask all irqs */
@@ -321,13 +386,7 @@ static int __init mpc8xxx_add_gpiochips(void)
 {
 	struct device_node *np;
 
-	for_each_compatible_node(np, NULL, "fsl,mpc8349-gpio")
+	for_each_matching_node(np, mpc8xxx_gpio_ids)
-		mpc8xxx_add_controller(np);
-
-	for_each_compatible_node(np, NULL, "fsl,mpc8572-gpio")
-		mpc8xxx_add_controller(np);
-
-	for_each_compatible_node(np, NULL, "fsl,mpc8610-gpio")
 		mpc8xxx_add_controller(np);
 
 	for_each_compatible_node(np, NULL, "fsl,qoriq-gpio")

arch/powerpc/sysdev/ppc4xx_cpm.c

@@ -0,0 +1,346 @@
+/*
+ * PowerPC 4xx Clock and Power Management
+ *
+ * Copyright (C) 2010, Applied Micro Circuits Corporation
+ * Victor Gallardo (vgallardo@apm.com)
+ *
+ * Based on arch/powerpc/platforms/44x/idle.c:
+ * Jerone Young <jyoung5@us.ibm.com>
+ * Copyright 2008 IBM Corp.
+ *
+ * Based on arch/powerpc/sysdev/fsl_pmc.c:
+ * Anton Vorontsov <avorontsov@ru.mvista.com>
+ * Copyright 2009  MontaVista Software, Inc.
+ *
+ * See file CREDITS for list of people who contributed to this
+ * project.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation; either version 2 of
+ * the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston,
+ * MA 02111-1307 USA
+ */
+
+#include <linux/kernel.h>
+#include <linux/of_platform.h>
+#include <linux/sysfs.h>
+#include <linux/cpu.h>
+#include <linux/suspend.h>
+#include <asm/dcr.h>
+#include <asm/dcr-native.h>
+#include <asm/machdep.h>
+
+#define CPM_ER	0
+#define CPM_FR	1
+#define CPM_SR	2
+
+#define CPM_IDLE_WAIT	0
+#define CPM_IDLE_DOZE	1
+
+struct cpm {
+	dcr_host_t	dcr_host;
+	unsigned int	dcr_offset[3];
+	unsigned int	powersave_off;
+	unsigned int	unused;
+	unsigned int	idle_doze;
+	unsigned int	standby;
+	unsigned int	suspend;
+};
+
+static struct cpm cpm;
+
+struct cpm_idle_mode {
+	unsigned int enabled;
+	const char  *name;
+};
+
+static struct cpm_idle_mode idle_mode[] = {
+	[CPM_IDLE_WAIT] = { 1, "wait" }, /* default */
+	[CPM_IDLE_DOZE] = { 0, "doze" },
+};
+
+static unsigned int cpm_set(unsigned int cpm_reg, unsigned int mask)
+{
+	unsigned int value;
+
+	/* CPM controller supports 3 different types of sleep interface
+	 * known as class 1, 2 and 3. For class 1 units, they are
+	 * unconditionally put to sleep when the corresponding CPM bit is
+	 * set. For class 2 and 3 units this is not case; if they can be
+	 * put to to sleep, they will. Here we do not verify, we just
+	 * set them and expect them to eventually go off when they can.
+	 */
+	value = dcr_read(cpm.dcr_host, cpm.dcr_offset[cpm_reg]);
+	dcr_write(cpm.dcr_host, cpm.dcr_offset[cpm_reg], value | mask);
+
+	/* return old state, to restore later if needed */
+	return value;
+}
+
+static void cpm_idle_wait(void)
+{
+	unsigned long msr_save;
+
+	/* save off initial state */
+	msr_save = mfmsr();
+	/* sync required when CPM0_ER[CPU] is set */
+	mb();
+	/* set wait state MSR */
+	mtmsr(msr_save|MSR_WE|MSR_EE|MSR_CE|MSR_DE);
+	isync();
+	/* return to initial state */
+	mtmsr(msr_save);
+	isync();
+}
+
+static void cpm_idle_sleep(unsigned int mask)
+{
+	unsigned int er_save;
+
+	/* update CPM_ER state */
+	er_save = cpm_set(CPM_ER, mask);
+
+	/* go to wait state so that CPM0_ER[CPU] can take effect */
+	cpm_idle_wait();
+
+	/* restore CPM_ER state */
+	dcr_write(cpm.dcr_host, cpm.dcr_offset[CPM_ER], er_save);
+}
+
+static void cpm_idle_doze(void)
+{
+	cpm_idle_sleep(cpm.idle_doze);
+}
+
+static void cpm_idle_config(int mode)
+{
+	int i;
+
+	if (idle_mode[mode].enabled)
+		return;
+
+	for (i = 0; i < ARRAY_SIZE(idle_mode); i++)
+		idle_mode[i].enabled = 0;
+
+	idle_mode[mode].enabled = 1;
+}
+
+static ssize_t cpm_idle_show(struct kobject *kobj,
+			     struct kobj_attribute *attr, char *buf)
+{
+	char *s = buf;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(idle_mode); i++) {
+		if (idle_mode[i].enabled)
+			s += sprintf(s, "[%s] ", idle_mode[i].name);
+		else
+			s += sprintf(s, "%s ", idle_mode[i].name);
+	}
+
+	*(s-1) = '\n'; /* convert the last space to a newline */
+
+	return s - buf;
+}
+
+static ssize_t cpm_idle_store(struct kobject *kobj,
+			      struct kobj_attribute *attr,
+			      const char *buf, size_t n)
+{
+	int i;
+	char *p;
+	int len;
+
+	p = memchr(buf, '\n', n);
+	len = p ? p - buf : n;
+
+	for (i = 0; i < ARRAY_SIZE(idle_mode); i++) {
+		if (strncmp(buf, idle_mode[i].name, len) == 0) {
+			cpm_idle_config(i);
+			return n;
+		}
+	}
+
+	return -EINVAL;
+}
+
+static struct kobj_attribute cpm_idle_attr =
+	__ATTR(idle, 0644, cpm_idle_show, cpm_idle_store);
+
+static void cpm_idle_config_sysfs(void)
+{
+	struct sys_device *sys_dev;
+	unsigned long ret;
+
+	sys_dev = get_cpu_sysdev(0);
+
+	ret = sysfs_create_file(&sys_dev->kobj,
+				&cpm_idle_attr.attr);
+	if (ret)
+		printk(KERN_WARNING
+		       "cpm: failed to create idle sysfs entry\n");
+}
+
+static void cpm_idle(void)
+{
+	if (idle_mode[CPM_IDLE_DOZE].enabled)
+		cpm_idle_doze();
+	else
+		cpm_idle_wait();
+}
+
+static int cpm_suspend_valid(suspend_state_t state)
+{
+	switch (state) {
+	case PM_SUSPEND_STANDBY:
+		return !!cpm.standby;
+	case PM_SUSPEND_MEM:
+		return !!cpm.suspend;
+	default:
+		return 0;
+	}
+}
+
+static void cpm_suspend_standby(unsigned int mask)
+{
+	unsigned long tcr_save;
+
+	/* disable decrement interrupt */
+	tcr_save = mfspr(SPRN_TCR);
+	mtspr(SPRN_TCR, tcr_save & ~TCR_DIE);
+
+	/* go to sleep state */
+	cpm_idle_sleep(mask);
+
+	/* restore decrement interrupt */
+	mtspr(SPRN_TCR, tcr_save);
+}
+
+static int cpm_suspend_enter(suspend_state_t state)
+{
+	switch (state) {
+	case PM_SUSPEND_STANDBY:
+		cpm_suspend_standby(cpm.standby);
+		break;
+	case PM_SUSPEND_MEM:
+		cpm_suspend_standby(cpm.suspend);
+		break;
+	}
+
+	return 0;
+}
+
+static struct platform_suspend_ops cpm_suspend_ops = {
+	.valid		= cpm_suspend_valid,
+	.enter		= cpm_suspend_enter,
+};
+
+static int cpm_get_uint_property(struct device_node *np,
+				 const char *name)
+{
+	int len;
+	const unsigned int *prop = of_get_property(np, name, &len);
+
+	if (prop == NULL || len < sizeof(u32))
+		return 0;
+
+	return *prop;
+}
+
+static int __init cpm_init(void)
+{
+	struct device_node *np;
+	int dcr_base, dcr_len;
+	int ret = 0;
+
+	if (!cpm.powersave_off) {
+		cpm_idle_config(CPM_IDLE_WAIT);
+		ppc_md.power_save = &cpm_idle;
+	}
+
+	np = of_find_compatible_node(NULL, NULL, "ibm,cpm");
+	if (!np) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	dcr_base = dcr_resource_start(np, 0);
+	dcr_len = dcr_resource_len(np, 0);
+
+	if (dcr_base == 0 || dcr_len == 0) {
+		printk(KERN_ERR "cpm: could not parse dcr property for %s\n",
+		       np->full_name);
+		ret = -EINVAL;
+		goto out;
+	}
+
+	cpm.dcr_host = dcr_map(np, dcr_base, dcr_len);
+
+	if (!DCR_MAP_OK(cpm.dcr_host)) {
+		printk(KERN_ERR "cpm: failed to map dcr property for %s\n",
+		       np->full_name);
+		ret = -EINVAL;
+		goto out;
+	}
+
+	/* All 4xx SoCs with a CPM controller have one of two
+	 * different order for the CPM registers. Some have the
+	 * CPM registers in the following order (ER,FR,SR). The
+	 * others have them in the following order (SR,ER,FR).
+	 */
+
+	if (cpm_get_uint_property(np, "er-offset") == 0) {
+		cpm.dcr_offset[CPM_ER] = 0;
+		cpm.dcr_offset[CPM_FR] = 1;
+		cpm.dcr_offset[CPM_SR] = 2;
+	} else {
+		cpm.dcr_offset[CPM_ER] = 1;
+		cpm.dcr_offset[CPM_FR] = 2;
+		cpm.dcr_offset[CPM_SR] = 0;
+	}
+
+	/* Now let's see what IPs to turn off for the following modes */
+
+	cpm.unused = cpm_get_uint_property(np, "unused-units");
+	cpm.idle_doze = cpm_get_uint_property(np, "idle-doze");
+	cpm.standby = cpm_get_uint_property(np, "standby");
+	cpm.suspend = cpm_get_uint_property(np, "suspend");
+
+	/* If some IPs are unused let's turn them off now */
+
+	if (cpm.unused) {
+		cpm_set(CPM_ER, cpm.unused);
+		cpm_set(CPM_FR, cpm.unused);
+	}
+
+	/* Now let's export interfaces */
+
+	if (!cpm.powersave_off && cpm.idle_doze)
+		cpm_idle_config_sysfs();
+
+	if (cpm.standby || cpm.suspend)
+		suspend_set_ops(&cpm_suspend_ops);
+out:
+	if (np)
+		of_node_put(np);
+	return ret;
+}
+
+late_initcall(cpm_init);
+
+static int __init cpm_powersave_off(char *arg)
+{
+	cpm.powersave_off = 1;
+	return 0;
+}
+__setup("powersave=off", cpm_powersave_off);

arch/powerpc/sysdev/tsi108_dev.c

@@ -84,8 +84,8 @@ static int __init tsi108_eth_of_init(void)
 		memset(&tsi_eth_data, 0, sizeof(tsi_eth_data));
 
 		ret = of_address_to_resource(np, 0, &r[0]);
-		DBG("%s: name:start->end = %s:0x%lx-> 0x%lx\n",
+		DBG("%s: name:start->end = %s:%pR\n",
-			__func__,r[0].name, r[0].start, r[0].end);
+		    __func__, r[0].name, &r[0]);
 		if (ret)
 			goto err;
 
@@ -93,8 +93,8 @@ static int __init tsi108_eth_of_init(void)
 		r[1].start = irq_of_parse_and_map(np, 0);
 		r[1].end = irq_of_parse_and_map(np, 0);
 		r[1].flags = IORESOURCE_IRQ;
-		DBG("%s: name:start->end = %s:0x%lx-> 0x%lx\n",
+		DBG("%s: name:start->end = %s:%pR\n",
-			__func__,r[1].name, r[1].start, r[1].end);
+			__func__, r[1].name, &r[1]);
 
 		tsi_eth_dev =
 		    platform_device_register_simple("tsi-ethernet", i++, &r[0],

drivers/char/hvc_vio.c

@@ -39,7 +39,7 @@
 
 #include "hvc_console.h"
 
-char hvc_driver_name[] = "hvc_console";
+static const char hvc_driver_name[] = "hvc_console";
 
 static struct vio_device_id hvc_driver_table[] __devinitdata = {
 	{"serial", "hvterm1"},

drivers/dma/Kconfig

@@ -109,7 +109,7 @@ config FSL_DMA
 
 config MPC512X_DMA
 	tristate "Freescale MPC512x built-in DMA engine support"
-	depends on PPC_MPC512x
+	depends on PPC_MPC512x || PPC_MPC831x
 	select DMA_ENGINE
 	---help---
 	  Enable support for the Freescale MPC512x built-in DMA engine.

drivers/dma/mpc512x_dma.c

@@ -1,6 +1,7 @@
 /*
  * Copyright (C) Freescale Semicondutor, Inc. 2007, 2008.
  * Copyright (C) Semihalf 2009
+ * Copyright (C) Ilya Yanok, Emcraft Systems 2010
  *
  * Written by Piotr Ziecik <kosmo@semihalf.com>. Hardware description
  * (defines, structures and comments) was taken from MPC5121 DMA driver
@@ -70,6 +71,8 @@
 #define MPC_DMA_DMAES_SBE	(1 << 1)
 #define MPC_DMA_DMAES_DBE	(1 << 0)
 
+#define MPC_DMA_DMAGPOR_SNOOP_ENABLE	(1 << 6)
+
 #define MPC_DMA_TSIZE_1		0x00
 #define MPC_DMA_TSIZE_2		0x01
 #define MPC_DMA_TSIZE_4		0x02
@@ -104,7 +107,10 @@ struct __attribute__ ((__packed__)) mpc_dma_regs {
 	/* 0x30 */
 	u32 dmahrsh;		/* DMA hw request status high(ch63~32) */
 	u32 dmahrsl;		/* DMA hardware request status low(ch31~0) */
-	u32 dmaihsa;		/* DMA interrupt high select AXE(ch63~32) */
+	union {
+		u32 dmaihsa;	/* DMA interrupt high select AXE(ch63~32) */
+		u32 dmagpor;	/* (General purpose register on MPC8308) */
+	};
 	u32 dmailsa;		/* DMA interrupt low select AXE(ch31~0) */
 	/* 0x40 ~ 0xff */
 	u32 reserve0[48];	/* Reserved */
@@ -195,7 +201,9 @@ struct mpc_dma {
 	struct mpc_dma_regs __iomem	*regs;
 	struct mpc_dma_tcd __iomem	*tcd;
 	int				irq;
+	int				irq2;
 	uint				error_status;
+	int				is_mpc8308;
 
 	/* Lock for error_status field in this structure */
 	spinlock_t			error_status_lock;
@@ -252,11 +260,13 @@ static void mpc_dma_execute(struct mpc_dma_chan *mchan)
 		prev = mdesc;
 	}
 
-	prev->tcd->start = 0;
 	prev->tcd->int_maj = 1;
 
 	/* Send first descriptor in chain into hardware */
 	memcpy_toio(&mdma->tcd[cid], first->tcd, sizeof(struct mpc_dma_tcd));
+
+	if (first != prev)
+		mdma->tcd[cid].e_sg = 1;
 	out_8(&mdma->regs->dmassrt, cid);
 }
 
@@ -274,6 +284,9 @@ static void mpc_dma_irq_process(struct mpc_dma *mdma, u32 is, u32 es, int off)
 
 		spin_lock(&mchan->lock);
 
+		out_8(&mdma->regs->dmacint, ch + off);
+		out_8(&mdma->regs->dmacerr, ch + off);
+
 		/* Check error status */
 		if (es & (1 << ch))
 			list_for_each_entry(mdesc, &mchan->active, node)
@@ -302,36 +315,68 @@ static irqreturn_t mpc_dma_irq(int irq, void *data)
 	spin_unlock(&mdma->error_status_lock);
 
 	/* Handle interrupt on each channel */
-	mpc_dma_irq_process(mdma, in_be32(&mdma->regs->dmainth),
+	if (mdma->dma.chancnt > 32) {
+		mpc_dma_irq_process(mdma, in_be32(&mdma->regs->dmainth),
 					in_be32(&mdma->regs->dmaerrh), 32);
+	}
 	mpc_dma_irq_process(mdma, in_be32(&mdma->regs->dmaintl),
 					in_be32(&mdma->regs->dmaerrl), 0);
 
-	/* Ack interrupt on all channels */
-	out_be32(&mdma->regs->dmainth, 0xFFFFFFFF);
-	out_be32(&mdma->regs->dmaintl, 0xFFFFFFFF);
-	out_be32(&mdma->regs->dmaerrh, 0xFFFFFFFF);
-	out_be32(&mdma->regs->dmaerrl, 0xFFFFFFFF);
-
 	/* Schedule tasklet */
 	tasklet_schedule(&mdma->tasklet);
 
 	return IRQ_HANDLED;
 }
 
-/* DMA Tasklet */
+/* proccess completed descriptors */
-static void mpc_dma_tasklet(unsigned long data)
+static void mpc_dma_process_completed(struct mpc_dma *mdma)
 {
-	struct mpc_dma *mdma = (void *)data;
 	dma_cookie_t last_cookie = 0;
 	struct mpc_dma_chan *mchan;
 	struct mpc_dma_desc *mdesc;
 	struct dma_async_tx_descriptor *desc;
 	unsigned long flags;
 	LIST_HEAD(list);
-	uint es;
 	int i;
 
+	for (i = 0; i < mdma->dma.chancnt; i++) {
+		mchan = &mdma->channels[i];
+
+		/* Get all completed descriptors */
+		spin_lock_irqsave(&mchan->lock, flags);
+		if (!list_empty(&mchan->completed))
+			list_splice_tail_init(&mchan->completed, &list);
+		spin_unlock_irqrestore(&mchan->lock, flags);
+
+		if (list_empty(&list))
+			continue;
+
+		/* Execute callbacks and run dependencies */
+		list_for_each_entry(mdesc, &list, node) {
+			desc = &mdesc->desc;
+
+			if (desc->callback)
+				desc->callback(desc->callback_param);
+
+			last_cookie = desc->cookie;
+			dma_run_dependencies(desc);
+		}
+
+		/* Free descriptors */
+		spin_lock_irqsave(&mchan->lock, flags);
+		list_splice_tail_init(&list, &mchan->free);
+		mchan->completed_cookie = last_cookie;
+		spin_unlock_irqrestore(&mchan->lock, flags);
+	}
+}
+
+/* DMA Tasklet */
+static void mpc_dma_tasklet(unsigned long data)
+{
+	struct mpc_dma *mdma = (void *)data;
+	unsigned long flags;
+	uint es;
+
 	spin_lock_irqsave(&mdma->error_status_lock, flags);
 	es = mdma->error_status;
 	mdma->error_status = 0;
@@ -370,35 +415,7 @@ static void mpc_dma_tasklet(unsigned long data)
 			dev_err(mdma->dma.dev, "- Destination Bus Error\n");
 	}
 
-	for (i = 0; i < mdma->dma.chancnt; i++) {
+	mpc_dma_process_completed(mdma);
-		mchan = &mdma->channels[i];
-
-		/* Get all completed descriptors */
-		spin_lock_irqsave(&mchan->lock, flags);
-		if (!list_empty(&mchan->completed))
-			list_splice_tail_init(&mchan->completed, &list);
-		spin_unlock_irqrestore(&mchan->lock, flags);
-
-		if (list_empty(&list))
-			continue;
-
-		/* Execute callbacks and run dependencies */
-		list_for_each_entry(mdesc, &list, node) {
-			desc = &mdesc->desc;
-
-			if (desc->callback)
-				desc->callback(desc->callback_param);
-
-			last_cookie = desc->cookie;
-			dma_run_dependencies(desc);
-		}
-
-		/* Free descriptors */
-		spin_lock_irqsave(&mchan->lock, flags);
-		list_splice_tail_init(&list, &mchan->free);
-		mchan->completed_cookie = last_cookie;
-		spin_unlock_irqrestore(&mchan->lock, flags);
-	}
 }
 
 /* Submit descriptor to hardware */
@@ -563,6 +580,7 @@ static struct dma_async_tx_descriptor *
 mpc_dma_prep_memcpy(struct dma_chan *chan, dma_addr_t dst, dma_addr_t src,
 					size_t len, unsigned long flags)
 {
+	struct mpc_dma *mdma = dma_chan_to_mpc_dma(chan);
 	struct mpc_dma_chan *mchan = dma_chan_to_mpc_dma_chan(chan);
 	struct mpc_dma_desc *mdesc = NULL;
 	struct mpc_dma_tcd *tcd;
@@ -577,8 +595,11 @@ mpc_dma_prep_memcpy(struct dma_chan *chan, dma_addr_t dst, dma_addr_t src,
 	}
 	spin_unlock_irqrestore(&mchan->lock, iflags);
 
-	if (!mdesc)
+	if (!mdesc) {
+		/* try to free completed descriptors */
+		mpc_dma_process_completed(mdma);
 		return NULL;
+	}
 
 	mdesc->error = 0;
 	tcd = mdesc->tcd;
@@ -591,7 +612,8 @@ mpc_dma_prep_memcpy(struct dma_chan *chan, dma_addr_t dst, dma_addr_t src,
 		tcd->dsize = MPC_DMA_TSIZE_32;
 		tcd->soff = 32;
 		tcd->doff = 32;
-	} else if (IS_ALIGNED(src | dst | len, 16)) {
+	} else if (!mdma->is_mpc8308 && IS_ALIGNED(src | dst | len, 16)) {
+		/* MPC8308 doesn't support 16 byte transfers */
 		tcd->ssize = MPC_DMA_TSIZE_16;
 		tcd->dsize = MPC_DMA_TSIZE_16;
 		tcd->soff = 16;
@@ -651,6 +673,15 @@ static int __devinit mpc_dma_probe(struct platform_device *op,
 		return -EINVAL;
 	}
 
+	if (of_device_is_compatible(dn, "fsl,mpc8308-dma")) {
+		mdma->is_mpc8308 = 1;
+		mdma->irq2 = irq_of_parse_and_map(dn, 1);
+		if (mdma->irq2 == NO_IRQ) {
+			dev_err(dev, "Error mapping IRQ!\n");
+			return -EINVAL;
+		}
+	}
+
 	retval = of_address_to_resource(dn, 0, &res);
 	if (retval) {
 		dev_err(dev, "Error parsing memory region!\n");
@@ -681,11 +712,23 @@ static int __devinit mpc_dma_probe(struct platform_device *op,
 		return -EINVAL;
 	}
 
+	if (mdma->is_mpc8308) {
+		retval = devm_request_irq(dev, mdma->irq2, &mpc_dma_irq, 0,
+				DRV_NAME, mdma);
+		if (retval) {
+			dev_err(dev, "Error requesting IRQ2!\n");
+			return -EINVAL;
+		}
+	}
+
 	spin_lock_init(&mdma->error_status_lock);
 
 	dma = &mdma->dma;
 	dma->dev = dev;
-	dma->chancnt = MPC_DMA_CHANNELS;
+	if (!mdma->is_mpc8308)
+		dma->chancnt = MPC_DMA_CHANNELS;
+	else
+		dma->chancnt = 16; /* MPC8308 DMA has only 16 channels */
 	dma->device_alloc_chan_resources = mpc_dma_alloc_chan_resources;
 	dma->device_free_chan_resources = mpc_dma_free_chan_resources;
 	dma->device_issue_pending = mpc_dma_issue_pending;
@@ -721,26 +764,40 @@ static int __devinit mpc_dma_probe(struct platform_device *op,
 	 * - Round-robin group arbitration,
 	 * - Round-robin channel arbitration.
 	 */
-	out_be32(&mdma->regs->dmacr, MPC_DMA_DMACR_EDCG |
+	if (!mdma->is_mpc8308) {
-				MPC_DMA_DMACR_ERGA | MPC_DMA_DMACR_ERCA);
+		out_be32(&mdma->regs->dmacr, MPC_DMA_DMACR_EDCG |
+					MPC_DMA_DMACR_ERGA | MPC_DMA_DMACR_ERCA);
 
-	/* Disable hardware DMA requests */
+		/* Disable hardware DMA requests */
-	out_be32(&mdma->regs->dmaerqh, 0);
+		out_be32(&mdma->regs->dmaerqh, 0);
-	out_be32(&mdma->regs->dmaerql, 0);
+		out_be32(&mdma->regs->dmaerql, 0);
 
-	/* Disable error interrupts */
+		/* Disable error interrupts */
-	out_be32(&mdma->regs->dmaeeih, 0);
+		out_be32(&mdma->regs->dmaeeih, 0);
-	out_be32(&mdma->regs->dmaeeil, 0);
+		out_be32(&mdma->regs->dmaeeil, 0);
 
-	/* Clear interrupts status */
+		/* Clear interrupts status */
-	out_be32(&mdma->regs->dmainth, 0xFFFFFFFF);
+		out_be32(&mdma->regs->dmainth, 0xFFFFFFFF);
-	out_be32(&mdma->regs->dmaintl, 0xFFFFFFFF);
+		out_be32(&mdma->regs->dmaintl, 0xFFFFFFFF);
-	out_be32(&mdma->regs->dmaerrh, 0xFFFFFFFF);
+		out_be32(&mdma->regs->dmaerrh, 0xFFFFFFFF);
-	out_be32(&mdma->regs->dmaerrl, 0xFFFFFFFF);
+		out_be32(&mdma->regs->dmaerrl, 0xFFFFFFFF);
 
-	/* Route interrupts to IPIC */
+		/* Route interrupts to IPIC */
-	out_be32(&mdma->regs->dmaihsa, 0);
+		out_be32(&mdma->regs->dmaihsa, 0);
-	out_be32(&mdma->regs->dmailsa, 0);
+		out_be32(&mdma->regs->dmailsa, 0);
+	} else {
+		/* MPC8308 has 16 channels and lacks some registers */
+		out_be32(&mdma->regs->dmacr, MPC_DMA_DMACR_ERCA);
+
+		/* enable snooping */
+		out_be32(&mdma->regs->dmagpor, MPC_DMA_DMAGPOR_SNOOP_ENABLE);
+		/* Disable error interrupts */
+		out_be32(&mdma->regs->dmaeeil, 0);
+
+		/* Clear interrupts status */
+		out_be32(&mdma->regs->dmaintl, 0xFFFF);
+		out_be32(&mdma->regs->dmaerrl, 0xFFFF);
+	}
 
 	/* Register DMA engine */
 	dev_set_drvdata(dev, mdma);

drivers/macintosh/macio_asic.c

@@ -387,11 +387,10 @@ static struct macio_dev * macio_add_one_device(struct macio_chip *chip,
 	/* Set the DMA ops to the ones from the PCI device, this could be
 	 * fishy if we didn't know that on PowerMac it's always direct ops
 	 * or iommu ops that will work fine
+	 *
+	 * To get all the fields, copy all archdata
 	 */
-	dev->ofdev.dev.archdata.dma_ops =
+	dev->ofdev.dev.archdata = chip->lbus.pdev->dev.archdata;
-		chip->lbus.pdev->dev.archdata.dma_ops;
-	dev->ofdev.dev.archdata.dma_data =
-		chip->lbus.pdev->dev.archdata.dma_data;
 #endif /* CONFIG_PCI */
 
 #ifdef DEBUG

drivers/macintosh/therm_pm72.c

@@ -2213,6 +2213,9 @@ static void fcu_lookup_fans(struct device_node *fcu_node)
 static int fcu_of_probe(struct platform_device* dev, const struct of_device_id *match)
 {
 	state = state_detached;
+	of_dev = dev;
+
+	dev_info(&dev->dev, "PowerMac G5 Thermal control driver %s\n", VERSION);
 
 	/* Lookup the fans in the device tree */
 	fcu_lookup_fans(dev->dev.of_node);
@@ -2235,6 +2238,7 @@ static const struct of_device_id fcu_match[] =
 	},
 	{},
 };
+MODULE_DEVICE_TABLE(of, fcu_match);
 
 static struct of_platform_driver fcu_of_platform_driver = 
 {
@@ -2252,8 +2256,6 @@ static struct of_platform_driver fcu_of_platform_driver =
  */
 static int __init therm_pm72_init(void)
 {
-	struct device_node *np;
-
 	rackmac = of_machine_is_compatible("RackMac3,1");
 
 	if (!of_machine_is_compatible("PowerMac7,2") &&
@@ -2261,34 +2263,12 @@ static int __init therm_pm72_init(void)
 	    !rackmac)
 	    	return -ENODEV;
 
-	printk(KERN_INFO "PowerMac G5 Thermal control driver %s\n", VERSION);
+	return of_register_platform_driver(&fcu_of_platform_driver);
-
-	np = of_find_node_by_type(NULL, "fcu");
-	if (np == NULL) {
-		/* Some machines have strangely broken device-tree */
-		np = of_find_node_by_path("/u3@0,f8000000/i2c@f8001000/fan@15e");
-		if (np == NULL) {
-			    printk(KERN_ERR "Can't find FCU in device-tree !\n");
-			    return -ENODEV;
-		}
-	}
-	of_dev = of_platform_device_create(np, "temperature", NULL);
-	if (of_dev == NULL) {
-		printk(KERN_ERR "Can't register FCU platform device !\n");
-		return -ENODEV;
-	}
-
-	of_register_platform_driver(&fcu_of_platform_driver);
-	
-	return 0;
 }
 
 static void __exit therm_pm72_exit(void)
 {
 	of_unregister_platform_driver(&fcu_of_platform_driver);
-
-	if (of_dev)
-		of_device_unregister(of_dev);
 }
 
 module_init(therm_pm72_init);

drivers/ps3/Makefile

@@ -1,6 +1,6 @@
 obj-$(CONFIG_PS3_VUART) += ps3-vuart.o
 obj-$(CONFIG_PS3_PS3AV) += ps3av_mod.o
-ps3av_mod-objs		+= ps3av.o ps3av_cmd.o
+ps3av_mod-y		:= ps3av.o ps3av_cmd.o
 obj-$(CONFIG_PPC_PS3) += sys-manager-core.o
 obj-$(CONFIG_PS3_SYS_MANAGER) += ps3-sys-manager.o
 obj-$(CONFIG_PS3_STORAGE) += ps3stor_lib.o

drivers/rtc/rtc-cmos.c

@@ -687,7 +687,8 @@ cmos_do_probe(struct device *dev, struct resource *ports, int rtc_irq)
 #if	defined(CONFIG_ATARI)
 	address_space = 64;
 #elif defined(__i386__) || defined(__x86_64__) || defined(__arm__) \
-			|| defined(__sparc__) || defined(__mips__)
+			|| defined(__sparc__) || defined(__mips__) \
+			|| defined(__powerpc__)
 	address_space = 128;
 #else
 #warning Assuming 128 bytes of RTC+NVRAM address space, not 64 bytes.