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

Pull powerpc updates from Benjamin Herrenschmidt:
 "The bulk of this is LE updates.  One should now be able to build an LE
  kernel and even run some things in it.

  I'm still sitting on a handful of patches to enable the new ABI that I
  *might* still send this merge window around, but due to the
  incertainty (they are pretty fresh) I want to keep them separate.

  Other notable changes are some infrastructure bits to better handle
  PCI pass-through under KVM, some bits and pieces added to the new
  PowerNV platform support such as access to the CPU SCOM bus via sysfs,
  and support for EEH error handling on PHB3 (Power8 PCIe).

  We also grew arch_get_random_long() for both pseries and powernv when
  running on P7+ and P8, exploiting the HW rng.

  And finally various embedded updates from freescale"

* 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc: (154 commits)
  powerpc: Fix fatal SLB miss when restoring PPR
  powerpc/powernv: Reserve the correct PE number
  powerpc/powernv: Add PE to its own PELTV
  powerpc/powernv: Add support for indirect XSCOM via debugfs
  powerpc/scom: Improve debugfs interface
  powerpc/scom: Enable 64-bit addresses
  powerpc/boot: Properly handle the base "of" boot wrapper
  powerpc/bpf: Support MOD operation
  powerpc/bpf: Fix DIVWU instruction opcode
  of: Move definition of of_find_next_cache_node into common code.
  powerpc: Remove big endianness assumption in of_find_next_cache_node
  powerpc/tm: Remove interrupt disable in __switch_to()
  powerpc: word-at-a-time optimization for 64-bit Little Endian
  powerpc/bpf: BPF JIT compiler for 64-bit Little Endian
  powerpc: Only save/restore SDR1 if in hypervisor mode
  powerpc/pmu: Fix ADB_PMU_LED_IDE dependencies
  powerpc/nvram: Fix endian issue when using the partition length
  powerpc/nvram: Fix endian issue when reading the NVRAM size
  powerpc/nvram: Scan partitions only once
  powerpc/mpc512x: remove unnecessary #if
  ...

25 files changed, 508 insertions, 204 deletions

diff --git a/arch/powerpc/include/asm/archrandom.h b/arch/powerpc/include/asm/archrandom.h
new file mode 100644
index 00000000000..d853d163ba4
--- /dev/null
+++ b/arch/powerpc/include/asm/archrandom.h
@@ -0,0 +1,32 @@
+#ifndef _ASM_POWERPC_ARCHRANDOM_H
+#define _ASM_POWERPC_ARCHRANDOM_H
+
+#ifdef CONFIG_ARCH_RANDOM
+
+#include <asm/machdep.h>
+
+static inline int arch_get_random_long(unsigned long *v)
+{
+	if (ppc_md.get_random_long)
+		return ppc_md.get_random_long(v);
+
+	return 0;
+}
+
+static inline int arch_get_random_int(unsigned int *v)
+{
+	unsigned long val;
+	int rc;
+
+	rc = arch_get_random_long(&val);
+	if (rc)
+		*v = val;
+
+	return rc;
+}
+
+int powernv_get_random_long(unsigned long *v);
+
+#endif /* CONFIG_ARCH_RANDOM */
+
+#endif /* _ASM_POWERPC_ARCHRANDOM_H */
diff --git a/arch/powerpc/include/asm/checksum.h b/arch/powerpc/include/asm/checksum.h
index ce0c28495f9..8251a3ba870 100644
--- a/arch/powerpc/include/asm/checksum.h
+++ b/arch/powerpc/include/asm/checksum.h
@@ -14,6 +14,9 @@
  * which always checksum on 4 octet boundaries.  ihl is the number
  * of 32-bit words and is always >= 5.
  */
+#ifdef CONFIG_GENERIC_CSUM
+#include <asm-generic/checksum.h>
+#else
 extern __sum16 ip_fast_csum(const void *iph, unsigned int ihl);
 
 /*
@@ -123,5 +126,7 @@ static inline __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
 	return sum;
 #endif
 }
+
+#endif
 #endif /* __KERNEL__ */
 #endif
diff --git a/arch/powerpc/include/asm/emulated_ops.h b/arch/powerpc/include/asm/emulated_ops.h
index 5a8b82aa724..4358e3002f3 100644
--- a/arch/powerpc/include/asm/emulated_ops.h
+++ b/arch/powerpc/include/asm/emulated_ops.h
@@ -43,6 +43,7 @@ extern struct ppc_emulated {
 	struct ppc_emulated_entry popcntb;
 	struct ppc_emulated_entry spe;
 	struct ppc_emulated_entry string;
+	struct ppc_emulated_entry sync;
 	struct ppc_emulated_entry unaligned;
 #ifdef CONFIG_MATH_EMULATION
 	struct ppc_emulated_entry math;
diff --git a/arch/powerpc/include/asm/hvsi.h b/arch/powerpc/include/asm/hvsi.h
index d3f64f36181..d4a5315718c 100644
--- a/arch/powerpc/include/asm/hvsi.h
+++ b/arch/powerpc/include/asm/hvsi.h
@@ -25,7 +25,7 @@
 struct hvsi_header {
 	uint8_t  type;
 	uint8_t  len;
-	uint16_t seqno;
+	__be16 seqno;
 } __attribute__((packed));
 
 struct hvsi_data {
@@ -35,24 +35,24 @@ struct hvsi_data {
 
 struct hvsi_control {
 	struct hvsi_header hdr;
-	uint16_t verb;
+	__be16 verb;
 	/* optional depending on verb: */
-	uint32_t word;
-	uint32_t mask;
+	__be32 word;
+	__be32 mask;
 } __attribute__((packed));
 
 struct hvsi_query {
 	struct hvsi_header hdr;
-	uint16_t verb;
+	__be16 verb;
 } __attribute__((packed));
 
 struct hvsi_query_response {
 	struct hvsi_header hdr;
-	uint16_t verb;
-	uint16_t query_seqno;
+	__be16 verb;
+	__be16 query_seqno;
 	union {
 		uint8_t  version;
-		uint32_t mctrl_word;
+		__be32 mctrl_word;
 	} u;
 } __attribute__((packed));
 
diff --git a/arch/powerpc/include/asm/io.h b/arch/powerpc/include/asm/io.h
index 5a64757dc0d..575fbf81fad 100644
--- a/arch/powerpc/include/asm/io.h
+++ b/arch/powerpc/include/asm/io.h
@@ -21,7 +21,7 @@ extern struct pci_dev *isa_bridge_pcidev;
 /*
  * has legacy ISA devices ?
  */
-#define arch_has_dev_port()	(isa_bridge_pcidev != NULL)
+#define arch_has_dev_port()	(isa_bridge_pcidev != NULL || isa_io_special)
 #endif
 
 #include <linux/device.h>
@@ -113,7 +113,7 @@ extern bool isa_io_special;
 
 /* gcc 4.0 and older doesn't have 'Z' constraint */
 #if __GNUC__ < 4 || (__GNUC__ == 4 && __GNUC_MINOR__ == 0)
-#define DEF_MMIO_IN_LE(name, size, insn)				\
+#define DEF_MMIO_IN_X(name, size, insn)				\
 static inline u##size name(const volatile u##size __iomem *addr)	\
 {									\
 	u##size ret;							\
@@ -122,7 +122,7 @@ static inline u##size name(const volatile u##size __iomem *addr)	\
 	return ret;							\
 }
 
-#define DEF_MMIO_OUT_LE(name, size, insn) 				\
+#define DEF_MMIO_OUT_X(name, size, insn)				\
 static inline void name(volatile u##size __iomem *addr, u##size val)	\
 {									\
 	__asm__ __volatile__("sync;"#insn" %1,0,%2"			\
@@ -130,7 +130,7 @@ static inline void name(volatile u##size __iomem *addr, u##size val)	\
 	IO_SET_SYNC_FLAG();						\
 }
 #else /* newer gcc */
-#define DEF_MMIO_IN_LE(name, size, insn)				\
+#define DEF_MMIO_IN_X(name, size, insn)				\
 static inline u##size name(const volatile u##size __iomem *addr)	\
 {									\
 	u##size ret;							\
@@ -139,7 +139,7 @@ static inline u##size name(const volatile u##size __iomem *addr)	\
 	return ret;							\
 }
 
-#define DEF_MMIO_OUT_LE(name, size, insn) 				\
+#define DEF_MMIO_OUT_X(name, size, insn)				\
 static inline void name(volatile u##size __iomem *addr, u##size val)	\
 {									\
 	__asm__ __volatile__("sync;"#insn" %1,%y0"			\
@@ -148,7 +148,7 @@ static inline void name(volatile u##size __iomem *addr, u##size val)	\
 }
 #endif
 
-#define DEF_MMIO_IN_BE(name, size, insn)				\
+#define DEF_MMIO_IN_D(name, size, insn)				\
 static inline u##size name(const volatile u##size __iomem *addr)	\
 {									\
 	u##size ret;							\
@@ -157,7 +157,7 @@ static inline u##size name(const volatile u##size __iomem *addr)	\
 	return ret;							\
 }
 
-#define DEF_MMIO_OUT_BE(name, size, insn)				\
+#define DEF_MMIO_OUT_D(name, size, insn)				\
 static inline void name(volatile u##size __iomem *addr, u##size val)	\
 {									\
 	__asm__ __volatile__("sync;"#insn"%U0%X0 %1,%0"			\
@@ -165,22 +165,37 @@ static inline void name(volatile u##size __iomem *addr, u##size val)	\
 	IO_SET_SYNC_FLAG();						\
 }
 
+DEF_MMIO_IN_D(in_8,     8, lbz);
+DEF_MMIO_OUT_D(out_8,   8, stb);
 
-DEF_MMIO_IN_BE(in_8,     8, lbz);
-DEF_MMIO_IN_BE(in_be16, 16, lhz);
-DEF_MMIO_IN_BE(in_be32, 32, lwz);
-DEF_MMIO_IN_LE(in_le16, 16, lhbrx);
-DEF_MMIO_IN_LE(in_le32, 32, lwbrx);
+#ifdef __BIG_ENDIAN__
+DEF_MMIO_IN_D(in_be16, 16, lhz);
+DEF_MMIO_IN_D(in_be32, 32, lwz);
+DEF_MMIO_IN_X(in_le16, 16, lhbrx);
+DEF_MMIO_IN_X(in_le32, 32, lwbrx);
 
-DEF_MMIO_OUT_BE(out_8,     8, stb);
-DEF_MMIO_OUT_BE(out_be16, 16, sth);
-DEF_MMIO_OUT_BE(out_be32, 32, stw);
-DEF_MMIO_OUT_LE(out_le16, 16, sthbrx);
-DEF_MMIO_OUT_LE(out_le32, 32, stwbrx);
+DEF_MMIO_OUT_D(out_be16, 16, sth);
+DEF_MMIO_OUT_D(out_be32, 32, stw);
+DEF_MMIO_OUT_X(out_le16, 16, sthbrx);
+DEF_MMIO_OUT_X(out_le32, 32, stwbrx);
+#else
+DEF_MMIO_IN_X(in_be16, 16, lhbrx);
+DEF_MMIO_IN_X(in_be32, 32, lwbrx);
+DEF_MMIO_IN_D(in_le16, 16, lhz);
+DEF_MMIO_IN_D(in_le32, 32, lwz);
+
+DEF_MMIO_OUT_X(out_be16, 16, sthbrx);
+DEF_MMIO_OUT_X(out_be32, 32, stwbrx);
+DEF_MMIO_OUT_D(out_le16, 16, sth);
+DEF_MMIO_OUT_D(out_le32, 32, stw);
+
+#endif /* __BIG_ENDIAN */
 
 #ifdef __powerpc64__
-DEF_MMIO_OUT_BE(out_be64, 64, std);
-DEF_MMIO_IN_BE(in_be64, 64, ld);
+
+#ifdef __BIG_ENDIAN__
+DEF_MMIO_OUT_D(out_be64, 64, std);
+DEF_MMIO_IN_D(in_be64, 64, ld);
 
 /* There is no asm instructions for 64 bits reverse loads and stores */
 static inline u64 in_le64(const volatile u64 __iomem *addr)
@@ -192,6 +207,22 @@ static inline void out_le64(volatile u64 __iomem *addr, u64 val)
 {
 	out_be64(addr, swab64(val));
 }
+#else
+DEF_MMIO_OUT_D(out_le64, 64, std);
+DEF_MMIO_IN_D(in_le64, 64, ld);
+
+/* There is no asm instructions for 64 bits reverse loads and stores */
+static inline u64 in_be64(const volatile u64 __iomem *addr)
+{
+	return swab64(in_le64(addr));
+}
+
+static inline void out_be64(volatile u64 __iomem *addr, u64 val)
+{
+	out_le64(addr, swab64(val));
+}
+
+#endif
 #endif /* __powerpc64__ */
 
 /*
diff --git a/arch/powerpc/include/asm/lppaca.h b/arch/powerpc/include/asm/lppaca.h
index 4470d1e34d2..844c28de7ec 100644
--- a/arch/powerpc/include/asm/lppaca.h
+++ b/arch/powerpc/include/asm/lppaca.h
@@ -84,8 +84,8 @@ struct lppaca {
 	 * the processor is yielded (either because of an OS yield or a
 	 * hypervisor preempt).  An even value implies that the processor is
 	 * currently executing.
-	 * NOTE: This value will ALWAYS be zero for dedicated processors and
-	 * will NEVER be zero for shared processors (ie, initialized to a 1).
+	 * NOTE: Even dedicated processor partitions can yield so this
+	 * field cannot be used to determine if we are shared or dedicated.
 	 */
 	volatile __be32 yield_count;
 	volatile __be32 dispersion_count; /* dispatch changed physical cpu */
@@ -106,15 +106,15 @@ extern struct lppaca lppaca[];
 #define lppaca_of(cpu)	(*paca[cpu].lppaca_ptr)
 
 /*
- * Old kernels used a reserved bit in the VPA to determine if it was running
- * in shared processor mode. New kernels look for a non zero yield count
- * but KVM still needs to set the bit to keep the old stuff happy.
+ * We are using a non architected field to determine if a partition is
+ * shared or dedicated. This currently works on both KVM and PHYP, but
+ * we will have to transition to something better.
  */
 #define LPPACA_OLD_SHARED_PROC		2
 
 static inline bool lppaca_shared_proc(struct lppaca *l)
 {
-	return l->yield_count != 0;
+	return !!(l->__old_status & LPPACA_OLD_SHARED_PROC);
 }
 
 /*
diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h
index 8b480901165..ad3025d0880 100644
--- a/arch/powerpc/include/asm/machdep.h
+++ b/arch/powerpc/include/asm/machdep.h
@@ -78,6 +78,18 @@ struct machdep_calls {
 				    long index);
 	void		(*tce_flush)(struct iommu_table *tbl);
 
+	/* _rm versions are for real mode use only */
+	int		(*tce_build_rm)(struct iommu_table *tbl,
+				     long index,
+				     long npages,
+				     unsigned long uaddr,
+				     enum dma_data_direction direction,
+				     struct dma_attrs *attrs);
+	void		(*tce_free_rm)(struct iommu_table *tbl,
+				    long index,
+				    long npages);
+	void		(*tce_flush_rm)(struct iommu_table *tbl);
+
 	void __iomem *	(*ioremap)(phys_addr_t addr, unsigned long size,
 				   unsigned long flags, void *caller);
 	void		(*iounmap)(volatile void __iomem *token);
@@ -263,6 +275,10 @@ struct machdep_calls {
 	ssize_t (*cpu_probe)(const char *, size_t);
 	ssize_t (*cpu_release)(const char *, size_t);
 #endif
+
+#ifdef CONFIG_ARCH_RANDOM
+	int (*get_random_long)(unsigned long *v);
+#endif
 };
 
 extern void e500_idle(void);
diff --git a/arch/powerpc/include/asm/mmu-hash64.h b/arch/powerpc/include/asm/mmu-hash64.h
index c4cf0119727..807014dde82 100644
--- a/arch/powerpc/include/asm/mmu-hash64.h
+++ b/arch/powerpc/include/asm/mmu-hash64.h
@@ -135,8 +135,8 @@ extern char initial_stab[];
 #ifndef __ASSEMBLY__
 
 struct hash_pte {
-	unsigned long v;
-	unsigned long r;
+	__be64 v;
+	__be64 r;
 };
 
 extern struct hash_pte *htab_address;
diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h
index c5cd72833d6..033c06be1d8 100644
--- a/arch/powerpc/include/asm/opal.h
+++ b/arch/powerpc/include/asm/opal.h
@@ -129,6 +129,9 @@ extern int opal_enter_rtas(struct rtas_args *args,
 #define OPAL_LPC_READ				67
 #define OPAL_LPC_WRITE				68
 #define OPAL_RETURN_CPU				69
+#define OPAL_FLASH_VALIDATE			76
+#define OPAL_FLASH_MANAGE			77
+#define OPAL_FLASH_UPDATE			78
 
 #ifndef __ASSEMBLY__
 
@@ -460,10 +463,12 @@ enum {
 
 enum {
 	OPAL_PHB_ERROR_DATA_TYPE_P7IOC = 1,
+	OPAL_PHB_ERROR_DATA_TYPE_PHB3 = 2
 };
 
 enum {
 	OPAL_P7IOC_NUM_PEST_REGS = 128,
+	OPAL_PHB3_NUM_PEST_REGS = 256
 };
 
 struct OpalIoPhbErrorCommon {
@@ -531,28 +536,94 @@ struct OpalIoP7IOCPhbErrorData {
 	uint64_t pestB[OPAL_P7IOC_NUM_PEST_REGS];
 };
 
+struct OpalIoPhb3ErrorData {
+	struct OpalIoPhbErrorCommon common;
+
+	uint32_t brdgCtl;
+
+	/* PHB3 UTL regs */
+	uint32_t portStatusReg;
+	uint32_t rootCmplxStatus;
+	uint32_t busAgentStatus;
+
+	/* PHB3 cfg regs */
+	uint32_t deviceStatus;
+	uint32_t slotStatus;
+	uint32_t linkStatus;
+	uint32_t devCmdStatus;
+	uint32_t devSecStatus;
+
+	/* cfg AER regs */
+	uint32_t rootErrorStatus;
+	uint32_t uncorrErrorStatus;
+	uint32_t corrErrorStatus;
+	uint32_t tlpHdr1;
+	uint32_t tlpHdr2;
+	uint32_t tlpHdr3;
+	uint32_t tlpHdr4;
+	uint32_t sourceId;
+
+	uint32_t rsv3;
+
+	/* Record data about the call to allocate a buffer */
+	uint64_t errorClass;
+	uint64_t correlator;
+
+	uint64_t nFir;			/* 000 */
+	uint64_t nFirMask;		/* 003 */
+	uint64_t nFirWOF;		/* 008 */
+
+	/* PHB3 MMIO Error Regs */
+	uint64_t phbPlssr;		/* 120 */
+	uint64_t phbCsr;		/* 110 */
+	uint64_t lemFir;		/* C00 */
+	uint64_t lemErrorMask;		/* C18 */
+	uint64_t lemWOF;		/* C40 */
+	uint64_t phbErrorStatus;	/* C80 */
+	uint64_t phbFirstErrorStatus;	/* C88 */
+	uint64_t phbErrorLog0;		/* CC0 */
+	uint64_t phbErrorLog1;		/* CC8 */
+	uint64_t mmioErrorStatus;	/* D00 */
+	uint64_t mmioFirstErrorStatus;	/* D08 */
+	uint64_t mmioErrorLog0;		/* D40 */
+	uint64_t mmioErrorLog1;		/* D48 */
+	uint64_t dma0ErrorStatus;	/* D80 */
+	uint64_t dma0FirstErrorStatus;	/* D88 */
+	uint64_t dma0ErrorLog0;		/* DC0 */
+	uint64_t dma0ErrorLog1;		/* DC8 */
+	uint64_t dma1ErrorStatus;	/* E00 */
+	uint64_t dma1FirstErrorStatus;	/* E08 */
+	uint64_t dma1ErrorLog0;		/* E40 */
+	uint64_t dma1ErrorLog1;		/* E48 */
+	uint64_t pestA[OPAL_PHB3_NUM_PEST_REGS];
+	uint64_t pestB[OPAL_PHB3_NUM_PEST_REGS];
+};
+
 typedef struct oppanel_line {
 	const char * 	line;
 	uint64_t 	line_len;
 } oppanel_line_t;
 
+/* /sys/firmware/opal */
+extern struct kobject *opal_kobj;
+
 /* API functions */
-int64_t opal_console_write(int64_t term_number, int64_t *length,
+int64_t opal_console_write(int64_t term_number, __be64 *length,
 			   const uint8_t *buffer);
-int64_t opal_console_read(int64_t term_number, int64_t *length,
+int64_t opal_console_read(int64_t term_number, __be64 *length,
 			  uint8_t *buffer);
 int64_t opal_console_write_buffer_space(int64_t term_number,
-					int64_t *length);
-int64_t opal_rtc_read(uint32_t *year_month_day,
-		      uint64_t *hour_minute_second_millisecond);
+					__be64 *length);
+int64_t opal_rtc_read(__be32 *year_month_day,
+		      __be64 *hour_minute_second_millisecond);
 int64_t opal_rtc_write(uint32_t year_month_day,
 		       uint64_t hour_minute_second_millisecond);
 int64_t opal_cec_power_down(uint64_t request);
 int64_t opal_cec_reboot(void);
 int64_t opal_read_nvram(uint64_t buffer, uint64_t size, uint64_t offset);
 int64_t opal_write_nvram(uint64_t buffer, uint64_t size, uint64_t offset);
-int64_t opal_handle_interrupt(uint64_t isn, uint64_t *outstanding_event_mask);
-int64_t opal_poll_events(uint64_t *outstanding_event_mask);
+int64_t opal_handle_interrupt(uint64_t isn, __be64 *outstanding_event_mask);
+int64_t opal_poll_events(__be64 *outstanding_event_mask);
 int64_t opal_pci_set_hub_tce_memory(uint64_t hub_id, uint64_t tce_mem_addr,
 				    uint64_t tce_mem_size);
 int64_t opal_pci_set_phb_tce_memory(uint64_t phb_id, uint64_t tce_mem_addr,
@@ -560,9 +631,9 @@ int64_t opal_pci_set_phb_tce_memory(uint64_t phb_id, uint64_t tce_mem_addr,
 int64_t opal_pci_config_read_byte(uint64_t phb_id, uint64_t bus_dev_func,
 				  uint64_t offset, uint8_t *data);
 int64_t opal_pci_config_read_half_word(uint64_t phb_id, uint64_t bus_dev_func,
-				       uint64_t offset, uint16_t *data);
+				       uint64_t offset, __be16 *data);
 int64_t opal_pci_config_read_word(uint64_t phb_id, uint64_t bus_dev_func,
-				  uint64_t offset, uint32_t *data);
+				  uint64_t offset, __be32 *data);
 int64_t opal_pci_config_write_byte(uint64_t phb_id, uint64_t bus_dev_func,
 				   uint64_t offset, uint8_t data);
 int64_t opal_pci_config_write_half_word(uint64_t phb_id, uint64_t bus_dev_func,
@@ -570,14 +641,14 @@ int64_t opal_pci_config_write_half_word(uint64_t phb_id, uint64_t bus_dev_func,
 int64_t opal_pci_config_write_word(uint64_t phb_id, uint64_t bus_dev_func,
 				   uint64_t offset, uint32_t data);
 int64_t opal_set_xive(uint32_t isn, uint16_t server, uint8_t priority);
-int64_t opal_get_xive(uint32_t isn, uint16_t *server, uint8_t *priority);
+int64_t opal_get_xive(uint32_t isn, __be16 *server, uint8_t *priority);
 int64_t opal_register_exception_handler(uint64_t opal_exception,
 					uint64_t handler_address,
 					uint64_t glue_cache_line);
 int64_t opal_pci_eeh_freeze_status(uint64_t phb_id, uint64_t pe_number,
 				   uint8_t *freeze_state,
-				   uint16_t *pci_error_type,
-				   uint64_t *phb_status);
+				   __be16 *pci_error_type,
+				   __be64 *phb_status);
 int64_t opal_pci_eeh_freeze_clear(uint64_t phb_id, uint64_t pe_number,
 				  uint64_t eeh_action_token);
 int64_t opal_pci_shpc(uint64_t phb_id, uint64_t shpc_action, uint8_t *state);
@@ -614,13 +685,13 @@ int64_t opal_pci_msi_eoi(uint64_t phb_id, uint32_t hw_irq);
 int64_t opal_pci_set_xive_pe(uint64_t phb_id, uint32_t pe_number,
 			     uint32_t xive_num);
 int64_t opal_get_xive_source(uint64_t phb_id, uint32_t xive_num,
-			     int32_t *interrupt_source_number);
+			     __be32 *interrupt_source_number);
 int64_t opal_get_msi_32(uint64_t phb_id, uint32_t mve_number, uint32_t xive_num,
-			uint8_t msi_range, uint32_t *msi_address,
-			uint32_t *message_data);
+			uint8_t msi_range, __be32 *msi_address,
+			__be32 *message_data);
 int64_t opal_get_msi_64(uint64_t phb_id, uint32_t mve_number,
 			uint32_t xive_num, uint8_t msi_range,
-			uint64_t *msi_address, uint32_t *message_data);
+			__be64 *msi_address, __be32 *message_data);
 int64_t opal_start_cpu(uint64_t thread_number, uint64_t start_address);
 int64_t opal_query_cpu_status(uint64_t thread_number, uint8_t *thread_status);
 int64_t opal_write_oppanel(oppanel_line_t *lines, uint64_t num_lines);
@@ -642,7 +713,7 @@ int64_t opal_pci_fence_phb(uint64_t phb_id);
 int64_t opal_pci_reinit(uint64_t phb_id, uint8_t reinit_scope);
 int64_t opal_pci_mask_pe_error(uint64_t phb_id, uint16_t pe_number, uint8_t error_type, uint8_t mask_action);
 int64_t opal_set_slot_led_status(uint64_t phb_id, uint64_t slot_id, uint8_t led_type, uint8_t led_action);
-int64_t opal_get_epow_status(uint64_t *status);
+int64_t opal_get_epow_status(__be64 *status);
 int64_t opal_set_system_attention_led(uint8_t led_action);
 int64_t opal_pci_next_error(uint64_t phb_id, uint64_t *first_frozen_pe,
 			    uint16_t *pci_error_type, uint16_t *severity);
@@ -656,6 +727,9 @@ int64_t opal_lpc_write(uint32_t chip_id, enum OpalLPCAddressType addr_type,
 		       uint32_t addr, uint32_t data, uint32_t sz);
 int64_t opal_lpc_read(uint32_t chip_id, enum OpalLPCAddressType addr_type,
 		      uint32_t addr, uint32_t *data, uint32_t sz);
+int64_t opal_validate_flash(uint64_t buffer, uint32_t *size, uint32_t *result);
+int64_t opal_manage_flash(uint8_t op);
+int64_t opal_update_flash(uint64_t blk_list);
 
 /* Internal functions */
 extern int early_init_dt_scan_opal(unsigned long node, const char *uname, int depth, void *data);
@@ -684,6 +758,7 @@ extern int opal_set_rtc_time(struct rtc_time *tm);
 extern void opal_get_rtc_time(struct rtc_time *tm);
 extern unsigned long opal_get_boot_time(void);
 extern void opal_nvram_init(void);
+extern void opal_flash_init(void);
 
 extern int opal_machine_check(struct pt_regs *regs);
 
diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h
index b9f426212d3..32e4e212b9c 100644
--- a/arch/powerpc/include/asm/page.h
+++ b/arch/powerpc/include/asm/page.h
@@ -78,7 +78,7 @@ extern unsigned int HPAGE_SHIFT;
  *
  * Also, KERNELBASE >= PAGE_OFFSET and PHYSICAL_START >= MEMORY_START
  *
- * There are two was to determine a physical address from a virtual one:
+ * There are two ways to determine a physical address from a virtual one:
  * va = pa + PAGE_OFFSET - MEMORY_START
  * va = pa + KERNELBASE - PHYSICAL_START
  *
@@ -403,7 +403,7 @@ void arch_free_page(struct page *page, int order);
 
 struct vm_area_struct;
 
-#ifdef CONFIG_PPC_64K_PAGES
+#if defined(CONFIG_PPC_64K_PAGES) && defined(CONFIG_PPC64)
 typedef pte_t *pgtable_t;
 #else
 typedef struct page *pgtable_t;
diff --git a/arch/powerpc/include/asm/pgtable-ppc64.h b/arch/powerpc/include/asm/pgtable-ppc64.h
index 46db09414a1..4a191c47286 100644
--- a/arch/powerpc/include/asm/pgtable-ppc64.h
+++ b/arch/powerpc/include/asm/pgtable-ppc64.h
@@ -394,6 +394,8 @@ static inline void mark_hpte_slot_valid(unsigned char *hpte_slot_array,
 	hpte_slot_array[index] = hidx << 4 | 0x1 << 3;
 }
 
+struct page *realmode_pfn_to_page(unsigned long pfn);
+
 static inline char *get_hpte_slot_array(pmd_t *pmdp)
 {
 	/*
diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h
index d7fe9f5b46d..3132bb9365f 100644
--- a/arch/powerpc/include/asm/ppc-opcode.h
+++ b/arch/powerpc/include/asm/ppc-opcode.h
@@ -143,6 +143,8 @@
 #define PPC_INST_LSWX			0x7c00042a
 #define PPC_INST_LWARX			0x7c000028
 #define PPC_INST_LWSYNC			0x7c2004ac
+#define PPC_INST_SYNC			0x7c0004ac
+#define PPC_INST_SYNC_MASK		0xfc0007fe
 #define PPC_INST_LXVD2X			0x7c000698
 #define PPC_INST_MCRXR			0x7c000400
 #define PPC_INST_MCRXR_MASK		0xfc0007fe
@@ -181,6 +183,7 @@
 #define PPC_INST_TLBIVAX		0x7c000624
 #define PPC_INST_TLBSRX_DOT		0x7c0006a5
 #define PPC_INST_XXLOR			0xf0000510
+#define PPC_INST_XXSWAPD		0xf0000250
 #define PPC_INST_XVCPSGNDP		0xf0000780
 #define PPC_INST_TRECHKPT		0x7c0007dd
 #define PPC_INST_TRECLAIM		0x7c00075d
@@ -200,6 +203,7 @@
 /* Misc instructions for BPF compiler */
 #define PPC_INST_LD			0xe8000000
 #define PPC_INST_LHZ			0xa0000000
+#define PPC_INST_LHBRX			0x7c00062c
 #define PPC_INST_LWZ			0x80000000
 #define PPC_INST_STD			0xf8000000
 #define PPC_INST_STDU			0xf8000001
@@ -218,7 +222,7 @@
 #define PPC_INST_MULLW			0x7c0001d6
 #define PPC_INST_MULHWU			0x7c000016
 #define PPC_INST_MULLI			0x1c000000
-#define PPC_INST_DIVWU			0x7c0003d6
+#define PPC_INST_DIVWU			0x7c000396
 #define PPC_INST_RLWINM			0x54000000
 #define PPC_INST_RLDICR			0x78000004
 #define PPC_INST_SLW			0x7c000030
@@ -344,6 +348,8 @@
 					       VSX_XX1((s), a, b))
 #define XXLOR(t, a, b)		stringify_in_c(.long PPC_INST_XXLOR | \
 					       VSX_XX3((t), a, b))
+#define XXSWAPD(t, a)		stringify_in_c(.long PPC_INST_XXSWAPD | \
+					       VSX_XX3((t), a, a))
 #define XVCPSGNDP(t, a, b)	stringify_in_c(.long (PPC_INST_XVCPSGNDP | \
 					       VSX_XX3((t), (a), (b))))
 
diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h
index 599545738af..3c1acc31a09 100644
--- a/arch/powerpc/include/asm/ppc_asm.h
+++ b/arch/powerpc/include/asm/ppc_asm.h
@@ -98,123 +98,51 @@ END_FW_FTR_SECTION_IFSET(FW_FEATURE_SPLPAR)
 #define REST_8GPRS(n, base)	REST_4GPRS(n, base); REST_4GPRS(n+4, base)
 #define REST_10GPRS(n, base)	REST_8GPRS(n, base); REST_2GPRS(n+8, base)
 
-#define SAVE_FPR(n, base)	stfd	n,THREAD_FPR0+8*TS_FPRWIDTH*(n)(base)
+#define SAVE_FPR(n, base)	stfd	n,8*TS_FPRWIDTH*(n)(base)
 #define SAVE_2FPRS(n, base)	SAVE_FPR(n, base); SAVE_FPR(n+1, base)
 #define SAVE_4FPRS(n, base)	SAVE_2FPRS(n, base); SAVE_2FPRS(n+2, base)
 #define SAVE_8FPRS(n, base)	SAVE_4FPRS(n, base); SAVE_4FPRS(n+4, base)
 #define SAVE_16FPRS(n, base)	SAVE_8FPRS(n, base); SAVE_8FPRS(n+8, base)
 #define SAVE_32FPRS(n, base)	SAVE_16FPRS(n, base); SAVE_16FPRS(n+16, base)
-#define REST_FPR(n, base)	lfd	n,THREAD_FPR0+8*TS_FPRWIDTH*(n)(base)
+#define REST_FPR(n, base)	lfd	n,8*TS_FPRWIDTH*(n)(base)
 #define REST_2FPRS(n, base)	REST_FPR(n, base); REST_FPR(n+1, base)
 #define REST_4FPRS(n, base)	REST_2FPRS(n, base); REST_2FPRS(n+2, base)
 #define REST_8FPRS(n, base)	REST_4FPRS(n, base); REST_4FPRS(n+4, base)
 #define REST_16FPRS(n, base)	REST_8FPRS(n, base); REST_8FPRS(n+8, base)
 #define REST_32FPRS(n, base)	REST_16FPRS(n, base); REST_16FPRS(n+16, base)
 
-#define SAVE_VR(n,b,base)	li b,THREAD_VR0+(16*(n));  stvx n,base,b
+#define SAVE_VR(n,b,base)	li b,16*(n);  stvx n,base,b
 #define SAVE_2VRS(n,b,base)	SAVE_VR(n,b,base); SAVE_VR(n+1,b,base)
 #define SAVE_4VRS(n,b,base)	SAVE_2VRS(n,b,base); SAVE_2VRS(n+2,b,base)
 #define SAVE_8VRS(n,b,base)	SAVE_4VRS(n,b,base); SAVE_4VRS(n+4,b,base)
 #define SAVE_16VRS(n,b,base)	SAVE_8VRS(n,b,base); SAVE_8VRS(n+8,b,base)
 #define SAVE_32VRS(n,b,base)	SAVE_16VRS(n,b,base); SAVE_16VRS(n+16,b,base)
-#define REST_VR(n,b,base)	li b,THREAD_VR0+(16*(n)); lvx n,base,b
+#define REST_VR(n,b,base)	li b,16*(n); lvx n,base,b
 #define REST_2VRS(n,b,base)	REST_VR(n,b,base); REST_VR(n+1,b,base)
 #define REST_4VRS(n,b,base)	REST_2VRS(n,b,base); REST_2VRS(n+2,b,base)
 #define REST_8VRS(n,b,base)	REST_4VRS(n,b,base); REST_4VRS(n+4,b,base)
 #define REST_16VRS(n,b,base)	REST_8VRS(n,b,base); REST_8VRS(n+8,b,base)
 #define REST_32VRS(n,b,base)	REST_16VRS(n,b,base); REST_16VRS(n+16,b,base)
 
-/* Save/restore FPRs, VRs and VSRs from their checkpointed backups in
- * thread_struct:
- */
-#define SAVE_FPR_TRANSACT(n, base)	stfd n,THREAD_TRANSACT_FPR0+	\
-					8*TS_FPRWIDTH*(n)(base)
-#define SAVE_2FPRS_TRANSACT(n, base)	SAVE_FPR_TRANSACT(n, base);	\
-					SAVE_FPR_TRANSACT(n+1, base)
-#define SAVE_4FPRS_TRANSACT(n, base)	SAVE_2FPRS_TRANSACT(n, base);	\
-					SAVE_2FPRS_TRANSACT(n+2, base)
-#define SAVE_8FPRS_TRANSACT(n, base)	SAVE_4FPRS_TRANSACT(n, base);	\
-					SAVE_4FPRS_TRANSACT(n+4, base)
-#define SAVE_16FPRS_TRANSACT(n, base)	SAVE_8FPRS_TRANSACT(n, base);	\
-					SAVE_8FPRS_TRANSACT(n+8, base)
-#define SAVE_32FPRS_TRANSACT(n, base)	SAVE_16FPRS_TRANSACT(n, base);	\
-					SAVE_16FPRS_TRANSACT(n+16, base)
-
-#define REST_FPR_TRANSACT(n, base)	lfd	n,THREAD_TRANSACT_FPR0+	\
-					8*TS_FPRWIDTH*(n)(base)
-#define REST_2FPRS_TRANSACT(n, base)	REST_FPR_TRANSACT(n, base);	\
-					REST_FPR_TRANSACT(n+1, base)
-#define REST_4FPRS_TRANSACT(n, base)	REST_2FPRS_TRANSACT(n, base);	\
-					REST_2FPRS_TRANSACT(n+2, base)
-#define REST_8FPRS_TRANSACT(n, base)	REST_4FPRS_TRANSACT(n, base);	\
-					REST_4FPRS_TRANSACT(n+4, base)
-#define REST_16FPRS_TRANSACT(n, base)	REST_8FPRS_TRANSACT(n, base);	\
-					REST_8FPRS_TRANSACT(n+8, base)
-#define REST_32FPRS_TRANSACT(n, base)	REST_16FPRS_TRANSACT(n, base);	\
-					REST_16FPRS_TRANSACT(n+16, base)
-
-
-#define SAVE_VR_TRANSACT(n,b,base)	li b,THREAD_TRANSACT_VR0+(16*(n)); \
-					stvx n,b,base
-#define SAVE_2VRS_TRANSACT(n,b,base)	SAVE_VR_TRANSACT(n,b,base);	\
-					SAVE_VR_TRANSACT(n+1,b,base)
-#define SAVE_4VRS_TRANSACT(n,b,base)	SAVE_2VRS_TRANSACT(n,b,base);	\
-					SAVE_2VRS_TRANSACT(n+2,b,base)
-#define SAVE_8VRS_TRANSACT(n,b,base)	SAVE_4VRS_TRANSACT(n,b,base);	\
-					SAVE_4VRS_TRANSACT(n+4,b,base)
-#define SAVE_16VRS_TRANSACT(n,b,base)	SAVE_8VRS_TRANSACT(n,b,base);	\
-					SAVE_8VRS_TRANSACT(n+8,b,base)
-#define SAVE_32VRS_TRANSACT(n,b,base)	SAVE_16VRS_TRANSACT(n,b,base);	\
-					SAVE_16VRS_TRANSACT(n+16,b,base)
-
-#define REST_VR_TRANSACT(n,b,base)	li b,THREAD_TRANSACT_VR0+(16*(n)); \
-					lvx n,b,base
-#define REST_2VRS_TRANSACT(n,b,base)	REST_VR_TRANSACT(n,b,base);	\
-					REST_VR_TRANSACT(n+1,b,base)
-#define REST_4VRS_TRANSACT(n,b,base)	REST_2VRS_TRANSACT(n,b,base);	\
-					REST_2VRS_TRANSACT(n+2,b,base)
-#define REST_8VRS_TRANSACT(n,b,base)	REST_4VRS_TRANSACT(n,b,base);	\
-					REST_4VRS_TRANSACT(n+4,b,base)
-#define REST_16VRS_TRANSACT(n,b,base)	REST_8VRS_TRANSACT(n,b,base);	\
-					REST_8VRS_TRANSACT(n+8,b,base)
-#define REST_32VRS_TRANSACT(n,b,base)	REST_16VRS_TRANSACT(n,b,base);	\
-					REST_16VRS_TRANSACT(n+16,b,base)
-
-
-#define SAVE_VSR_TRANSACT(n,b,base)	li b,THREAD_TRANSACT_VSR0+(16*(n)); \
-					STXVD2X(n,R##base,R##b)
-#define SAVE_2VSRS_TRANSACT(n,b,base)	SAVE_VSR_TRANSACT(n,b,base);	\
-	                                SAVE_VSR_TRANSACT(n+1,b,base)
-#define SAVE_4VSRS_TRANSACT(n,b,base)	SAVE_2VSRS_TRANSACT(n,b,base);	\
-	                                SAVE_2VSRS_TRANSACT(n+2,b,base)
-#define SAVE_8VSRS_TRANSACT(n,b,base)	SAVE_4VSRS_TRANSACT(n,b,base);	\
-	                                SAVE_4VSRS_TRANSACT(n+4,b,base)
-#define SAVE_16VSRS_TRANSACT(n,b,base)	SAVE_8VSRS_TRANSACT(n,b,base);	\
-	                                SAVE_8VSRS_TRANSACT(n+8,b,base)
-#define SAVE_32VSRS_TRANSACT(n,b,base)	SAVE_16VSRS_TRANSACT(n,b,base);	\
-	                                SAVE_16VSRS_TRANSACT(n+16,b,base)
-
-#define REST_VSR_TRANSACT(n,b,base)	li b,THREAD_TRANSACT_VSR0+(16*(n)); \
-					LXVD2X(n,R##base,R##b)
-#define REST_2VSRS_TRANSACT(n,b,base)	REST_VSR_TRANSACT(n,b,base);    \
-	                                REST_VSR_TRANSACT(n+1,b,base)
-#define REST_4VSRS_TRANSACT(n,b,base)	REST_2VSRS_TRANSACT(n,b,base);	\
-	                                REST_2VSRS_TRANSACT(n+2,b,base)
-#define REST_8VSRS_TRANSACT(n,b,base)	REST_4VSRS_TRANSACT(n,b,base);	\
-	                                REST_4VSRS_TRANSACT(n+4,b,base)
-#define REST_16VSRS_TRANSACT(n,b,base)	REST_8VSRS_TRANSACT(n,b,base);	\
-	                                REST_8VSRS_TRANSACT(n+8,b,base)
-#define REST_32VSRS_TRANSACT(n,b,base)	REST_16VSRS_TRANSACT(n,b,base);	\
-	                                REST_16VSRS_TRANSACT(n+16,b,base)
+#ifdef __BIG_ENDIAN__
+#define STXVD2X_ROT(n,b,base)		STXVD2X(n,b,base)
+#define LXVD2X_ROT(n,b,base)		LXVD2X(n,b,base)
+#else
+#define STXVD2X_ROT(n,b,base)		XXSWAPD(n,n);		\
+					STXVD2X(n,b,base);	\
+					XXSWAPD(n,n)
 
+#define LXVD2X_ROT(n,b,base)		LXVD2X(n,b,base);	\
+					XXSWAPD(n,n)
+#endif
 /* Save the lower 32 VSRs in the thread VSR region */
-#define SAVE_VSR(n,b,base)	li b,THREAD_VSR0+(16*(n));  STXVD2X(n,R##base,R##b)
+#define SAVE_VSR(n,b,base)	li b,16*(n);  STXVD2X_ROT(n,R##base,R##b)
 #define SAVE_2VSRS(n,b,base)	SAVE_VSR(n,b,base); SAVE_VSR(n+1,b,base)
 #define SAVE_4VSRS(n,b,base)	SAVE_2VSRS(n,b,base); SAVE_2VSRS(n+2,b,base)
 #define SAVE_8VSRS(n,b,base)	SAVE_4VSRS(n,b,base); SAVE_4VSRS(n+4,b,base)
 #define SAVE_16VSRS(n,b,base)	SAVE_8VSRS(n,b,base); SAVE_8VSRS(n+8,b,base)
 #define SAVE_32VSRS(n,b,base)	SAVE_16VSRS(n,b,base); SAVE_16VSRS(n+16,b,base)
-#define REST_VSR(n,b,base)	li b,THREAD_VSR0+(16*(n)); LXVD2X(n,R##base,R##b)
+#define REST_VSR(n,b,base)	li b,16*(n); LXVD2X_ROT(n,R##base,R##b)
 #define REST_2VSRS(n,b,base)	REST_VSR(n,b,base); REST_VSR(n+1,b,base)
 #define REST_4VSRS(n,b,base)	REST_2VSRS(n,b,base); REST_2VSRS(n+2,b,base)
 #define REST_8VSRS(n,b,base)	REST_4VSRS(n,b,base); REST_4VSRS(n+4,b,base)
@@ -478,13 +406,6 @@ BEGIN_FTR_SECTION_NESTED(945)						\
 	std	ra,TASKTHREADPPR(rb);					\
 END_FTR_SECTION_NESTED(CPU_FTR_HAS_PPR,CPU_FTR_HAS_PPR,945)
 
-#define RESTORE_PPR(ra, rb)						\
-BEGIN_FTR_SECTION_NESTED(946)						\
-	ld	ra,PACACURRENT(r13);					\
-	ld	rb,TASKTHREADPPR(ra);					\
-	mtspr	SPRN_PPR,rb;	/* Restore PPR */			\
-END_FTR_SECTION_NESTED(CPU_FTR_HAS_PPR,CPU_FTR_HAS_PPR,946)
-
 #endif
 
 /*
@@ -832,6 +753,35 @@ END_FTR_SECTION_NESTED(CPU_FTR_HAS_PPR,CPU_FTR_HAS_PPR,946)
 #define N_SLINE	68
 #define N_SO	100
 
-#endif /*  __ASSEMBLY__ */
+/*
+ * Create an endian fixup trampoline
+ *
+ * This starts with a "tdi 0,0,0x48" instruction which is
+ * essentially a "trap never", and thus akin to a nop.
+ *
+ * The opcode for this instruction read with the wrong endian
+ * however results in a b . + 8
+ *
+ * So essentially we use that trick to execute the following
+ * trampoline in "reverse endian" if we are running with the
+ * MSR_LE bit set the "wrong" way for whatever endianness the
+ * kernel is built for.
+ */
 
+#ifdef CONFIG_PPC_BOOK3E
+#define FIXUP_ENDIAN
+#else
+#define FIXUP_ENDIAN						   \
+	tdi   0,0,0x48;	  /* Reverse endian of b . + 8		*/ \
+	b     $+36;	  /* Skip trampoline if endian is good	*/ \
+	.long 0x05009f42; /* bcl 20,31,$+4			*/ \
+	.long 0xa602487d; /* mflr r10				*/ \
+	.long 0x1c004a39; /* addi r10,r10,28			*/ \
+	.long 0xa600607d; /* mfmsr r11				*/ \
+	.long 0x01006b69; /* xori r11,r11,1			*/ \
+	.long 0xa6035a7d; /* mtsrr0 r10				*/ \
+	.long 0xa6037b7d; /* mtsrr1 r11				*/ \
+	.long 0x2400004c  /* rfid				*/
+#endif /* !CONFIG_PPC_BOOK3E */
+#endif /*  __ASSEMBLY__ */
 #endif /* _ASM_POWERPC_PPC_ASM_H */
diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index ce4de5aed7b..7794b2b04eb 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -14,8 +14,18 @@
 
 #ifdef CONFIG_VSX
 #define TS_FPRWIDTH 2
+
+#ifdef __BIG_ENDIAN__
+#define TS_FPROFFSET 0
+#define TS_VSRLOWOFFSET 1
+#else
+#define TS_FPROFFSET 1
+#define TS_VSRLOWOFFSET 0
+#endif
+
 #else
 #define TS_FPRWIDTH 1
+#define TS_FPROFFSET 0
 #endif
 
 #ifdef CONFIG_PPC64
@@ -142,26 +152,22 @@ typedef struct {
 	unsigned long seg;
 } mm_segment_t;
 
-#define TS_FPROFFSET 0
-#define TS_VSRLOWOFFSET 1
-#define TS_FPR(i) fpr[i][TS_FPROFFSET]
-#define TS_TRANS_FPR(i) transact_fpr[i][TS_FPROFFSET]
+#define TS_FPR(i) fp_state.fpr[i][TS_FPROFFSET]
+#define TS_TRANS_FPR(i) transact_fp.fpr[i][TS_FPROFFSET]
 
-struct thread_struct {
-	unsigned long	ksp;		/* Kernel stack pointer */
-#ifdef CONFIG_PPC64
-	unsigned long	ksp_vsid;
-#endif
-	struct pt_regs	*regs;		/* Pointer to saved register state */
-	mm_segment_t	fs;		/* for get_fs() validation */
-#ifdef CONFIG_BOOKE
-	/* BookE base exception scratch space; align on cacheline */
-	unsigned long	normsave[8] ____cacheline_aligned;
-#endif
-#ifdef CONFIG_PPC32
-	void		*pgdir;		/* root of page-table tree */
-	unsigned long	ksp_limit;	/* if ksp <= ksp_limit stack overflow */
-#endif
+/* FP and VSX 0-31 register set */
+struct thread_fp_state {
+	u64	fpr[32][TS_FPRWIDTH] __attribute__((aligned(16)));
+	u64	fpscr;		/* Floating point status */
+};
+
+/* Complete AltiVec register set including VSCR */
+struct thread_vr_state {
+	vector128	vr[32] __attribute__((aligned(16)));
+	vector128	vscr __attribute__((aligned(16)));
+};
+
+struct debug_reg {
 #ifdef CONFIG_PPC_ADV_DEBUG_REGS
 	/*
 	 * The following help to manage the use of Debug Control Registers
@@ -198,13 +204,26 @@ struct thread_struct {
 	unsigned long	dvc2;
 #endif
 #endif
-	/* FP and VSX 0-31 register set */
-	double		fpr[32][TS_FPRWIDTH] __attribute__((aligned(16)));
-	struct {
+};
 
-		unsigned int pad;
-		unsigned int val;	/* Floating point status */
-	} fpscr;
+struct thread_struct {
+	unsigned long	ksp;		/* Kernel stack pointer */
+#ifdef CONFIG_PPC64
+	unsigned long	ksp_vsid;
+#endif
+	struct pt_regs	*regs;		/* Pointer to saved register state */
+	mm_segment_t	fs;		/* for get_fs() validation */
+#ifdef CONFIG_BOOKE
+	/* BookE base exception scratch space; align on cacheline */
+	unsigned long	normsave[8] ____cacheline_aligned;
+#endif
+#ifdef CONFIG_PPC32
+	void		*pgdir;		/* root of page-table tree */
+	unsigned long	ksp_limit;	/* if ksp <= ksp_limit stack overflow */
+#endif
+	struct debug_reg debug;
+	struct thread_fp_state	fp_state;
+	struct thread_fp_state	*fp_save_area;
 	int		fpexc_mode;	/* floating-point exception mode */
 	unsigned int	align_ctl;	/* alignment handling control */
 #ifdef CONFIG_PPC64
@@ -222,10 +241,8 @@ struct thread_struct {
 	struct arch_hw_breakpoint hw_brk; /* info on the hardware breakpoint */
 	unsigned long	trap_nr;	/* last trap # on this thread */
 #ifdef CONFIG_ALTIVEC
-	/* Complete AltiVec register set */
-	vector128	vr[32] __attribute__((aligned(16)));
-	/* AltiVec status */
-	vector128	vscr __attribute__((aligned(16)));
+	struct thread_vr_state vr_state;
+	struct thread_vr_state *vr_save_area;
 	unsigned long	vrsave;
 	int		used_vr;	/* set if process has used altivec */
 #endif /* CONFIG_ALTIVEC */
@@ -262,13 +279,8 @@ struct thread_struct {
 	 * transact_fpr[] is the new set of transactional values.
 	 * VRs work the same way.
 	 */
-	double		transact_fpr[32][TS_FPRWIDTH];
-	struct {
-		unsigned int pad;
-		unsigned int val;	/* Floating point status */
-	} transact_fpscr;
-	vector128	transact_vr[32] __attribute__((aligned(16)));
-	vector128	transact_vscr __attribute__((aligned(16)));
+	struct thread_fp_state transact_fp;
+	struct thread_vr_state transact_vr;
 	unsigned long	transact_vrsave;
 #endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
 #ifdef CONFIG_KVM_BOOK3S_32_HANDLER
@@ -322,8 +334,6 @@ struct thread_struct {
 	.ksp = INIT_SP, \
 	.regs = (struct pt_regs *)INIT_SP - 1, /* XXX bogus, I think */ \
 	.fs = KERNEL_DS, \
-	.fpr = {{0}}, \
-	.fpscr = { .val = 0, }, \
 	.fpexc_mode = 0, \
 	.ppr = INIT_PPR, \
 }
@@ -361,6 +371,11 @@ extern int set_endian(struct task_struct *tsk, unsigned int val);
 extern int get_unalign_ctl(struct task_struct *tsk, unsigned long adr);
 extern int set_unalign_ctl(struct task_struct *tsk, unsigned int val);
 
+extern void load_fp_state(struct thread_fp_state *fp);
+extern void store_fp_state(struct thread_fp_state *fp);
+extern void load_vr_state(struct thread_vr_state *vr);
+extern void store_vr_state(struct thread_vr_state *vr);
+
 static inline unsigned int __unpack_fe01(unsigned long msr_bits)
 {
 	return ((msr_bits & MSR_FE0) >> 10) | ((msr_bits & MSR_FE1) >> 8);
diff --git a/arch/powerpc/include/asm/prom.h b/arch/powerpc/include/asm/prom.h
index 7d0c7f3a717..bf09e5a065b 100644
--- a/arch/powerpc/include/asm/prom.h
+++ b/arch/powerpc/include/asm/prom.h
@@ -44,9 +44,6 @@ void of_parse_dma_window(struct device_node *dn, const __be32 *dma_window,
 
 extern void kdump_move_device_tree(void);
 
-/* cache lookup */
-struct device_node *of_find_next_cache_node(struct device_node *np);
-
 #ifdef CONFIG_NUMA
 extern int of_node_to_nid(struct device_node *device);
 #else
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index 10d1ef016bf..126f6e98f84 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -115,7 +115,12 @@
 #define MSR_64BIT	MSR_SF
 
 /* Server variant */
-#define MSR_		(MSR_ME | MSR_RI | MSR_IR | MSR_DR | MSR_ISF |MSR_HV)
+#define __MSR		(MSR_ME | MSR_RI | MSR_IR | MSR_DR | MSR_ISF |MSR_HV)
+#ifdef __BIG_ENDIAN__
+#define MSR_		__MSR
+#else
+#define MSR_		(__MSR | MSR_LE)
+#endif
 #define MSR_KERNEL	(MSR_ | MSR_64BIT)
 #define MSR_USER32	(MSR_ | MSR_PR | MSR_EE)
 #define MSR_USER64	(MSR_USER32 | MSR_64BIT)
diff --git a/arch/powerpc/include/asm/reg_booke.h b/arch/powerpc/include/asm/reg_booke.h
index ed8f836da09..2e31aacd8ac 100644
--- a/arch/powerpc/include/asm/reg_booke.h
+++ b/arch/powerpc/include/asm/reg_booke.h
@@ -381,7 +381,7 @@
 #define DBCR0_IA34T	0x00004000	/* Instr Addr 3-4 range Toggle */
 #define DBCR0_FT	0x00000001	/* Freeze Timers on debug event */
 
-#define dbcr_iac_range(task)	((task)->thread.dbcr0)
+#define dbcr_iac_range(task)	((task)->thread.debug.dbcr0)
 #define DBCR_IAC12I	DBCR0_IA12			/* Range Inclusive */
 #define DBCR_IAC12X	(DBCR0_IA12 | DBCR0_IA12X)	/* Range Exclusive */
 #define DBCR_IAC12MODE	(DBCR0_IA12 | DBCR0_IA12X)	/* IAC 1-2 Mode Bits */
@@ -395,7 +395,7 @@
 #define DBCR1_DAC1W	0x20000000	/* DAC1 Write Debug Event */
 #define DBCR1_DAC2W	0x10000000	/* DAC2 Write Debug Event */
 
-#define dbcr_dac(task)	((task)->thread.dbcr1)
+#define dbcr_dac(task)	((task)->thread.debug.dbcr1)
 #define DBCR_DAC1R	DBCR1_DAC1R
 #define DBCR_DAC1W	DBCR1_DAC1W
 #define DBCR_DAC2R	DBCR1_DAC2R
@@ -441,7 +441,7 @@
 #define DBCR0_CRET	0x00000020	/* Critical Return Debug Event */
 #define DBCR0_FT	0x00000001	/* Freeze Timers on debug event */
 
-#define dbcr_dac(task)	((task)->thread.dbcr0)
+#define dbcr_dac(task)	((task)->thread.debug.dbcr0)
 #define DBCR_DAC1R	DBCR0_DAC1R
 #define DBCR_DAC1W	DBCR0_DAC1W
 #define DBCR_DAC2R	DBCR0_DAC2R
@@ -475,7 +475,7 @@
 #define DBCR1_IAC34MX	0x000000C0	/* Instr Addr 3-4 range eXclusive */
 #define DBCR1_IAC34AT	0x00000001	/* Instr Addr 3-4 range Toggle */
 
-#define dbcr_iac_range(task)	((task)->thread.dbcr1)
+#define dbcr_iac_range(task)	((task)->thread.debug.dbcr1)
 #define DBCR_IAC12I	DBCR1_IAC12M	/* Range Inclusive */
 #define DBCR_IAC12X	DBCR1_IAC12MX	/* Range Exclusive */
 #define DBCR_IAC12MODE	DBCR1_IAC12MX	/* IAC 1-2 Mode Bits */
diff --git a/arch/powerpc/include/asm/scom.h b/arch/powerpc/include/asm/scom.h
index 0cabfd7bc2d..f5cde45b116 100644
--- a/arch/powerpc/include/asm/scom.h
+++ b/arch/powerpc/include/asm/scom.h
@@ -54,8 +54,8 @@ struct scom_controller {
 	scom_map_t (*map)(struct device_node *ctrl_dev, u64 reg, u64 count);
 	void (*unmap)(scom_map_t map);
 
-	u64 (*read)(scom_map_t map, u32 reg);
-	void (*write)(scom_map_t map, u32 reg, u64 value);
+	int (*read)(scom_map_t map, u64 reg, u64 *value);
+	int (*write)(scom_map_t map, u64 reg, u64 value);
 };
 
 extern const struct scom_controller *scom_controller;
@@ -133,10 +133,18 @@ static inline void scom_unmap(scom_map_t map)
  * scom_read - Read a SCOM register
  * @map: Result of scom_map
  * @reg: Register index within that map
+ * @value: Updated with the value read
+ *
+ * Returns 0 (success) or a negative error code
  */
-static inline u64 scom_read(scom_map_t map, u32 reg)
+static inline int scom_read(scom_map_t map, u64 reg, u64 *value)
 {
-	return scom_controller->read(map, reg);
+	int rc;
+
+	rc = scom_controller->read(map, reg, value);
+	if (rc)
+		*value = 0xfffffffffffffffful;
+	return rc;
 }
 
 /**
@@ -144,12 +152,15 @@ static inline u64 scom_read(scom_map_t map, u32 reg)
  * @map: Result of scom_map
  * @reg: Register index within that map
  * @value: Value to write
+ *
+ * Returns 0 (success) or a negative error code
  */
-static inline void scom_write(scom_map_t map, u32 reg, u64 value)
+static inline int scom_write(scom_map_t map, u64 reg, u64 value)
 {
-	scom_controller->write(map, reg, value);
+	return scom_controller->write(map, reg, value);
 }
 
+
 #endif /* CONFIG_PPC_SCOM */
 #endif /* __ASSEMBLY__ */
 #endif /* __KERNEL__ */
diff --git a/arch/powerpc/include/asm/setup.h b/arch/powerpc/include/asm/setup.h
index d3ca85529b8..703a8412dac 100644
--- a/arch/powerpc/include/asm/setup.h
+++ b/arch/powerpc/include/asm/setup.h
@@ -23,6 +23,10 @@ extern void reloc_got2(unsigned long);
 
 #define PTRRELOC(x)	((typeof(x)) add_reloc_offset((unsigned long)(x)))
 
+void check_for_initrd(void);
+void do_init_bootmem(void);
+void setup_panic(void);
+
 #endif /* !__ASSEMBLY__ */
 
 #endif	/* _ASM_POWERPC_SETUP_H */
diff --git a/arch/powerpc/include/asm/sfp-machine.h b/arch/powerpc/include/asm/sfp-machine.h
index 3a7a67a0d00..d89beaba26f 100644
--- a/arch/powerpc/include/asm/sfp-machine.h
+++ b/arch/powerpc/include/asm/sfp-machine.h
@@ -125,7 +125,7 @@
 #define FP_EX_DIVZERO         (1 << (31 - 5))
 #define FP_EX_INEXACT         (1 << (31 - 6))
 
-#define __FPU_FPSCR	(current->thread.fpscr.val)
+#define __FPU_FPSCR	(current->thread.fp_state.fpscr)
 
 /* We only actually write to the destination register
  * if exceptions signalled (if any) will not trap.
diff --git a/arch/powerpc/include/asm/string.h b/arch/powerpc/include/asm/string.h
index e40010abcaf..0dffad6bcc8 100644
--- a/arch/powerpc/include/asm/string.h
+++ b/arch/powerpc/include/asm/string.h
@@ -10,7 +10,9 @@
 #define __HAVE_ARCH_STRNCMP
 #define __HAVE_ARCH_STRCAT
 #define __HAVE_ARCH_MEMSET
+#ifdef __BIG_ENDIAN__
 #define __HAVE_ARCH_MEMCPY
+#endif
 #define __HAVE_ARCH_MEMMOVE
 #define __HAVE_ARCH_MEMCMP
 #define __HAVE_ARCH_MEMCHR
@@ -22,7 +24,9 @@ extern int strcmp(const char *,const char *);
 extern int strncmp(const char *, const char *, __kernel_size_t);
 extern char * strcat(char *, const char *);
 extern void * memset(void *,int,__kernel_size_t);
+#ifdef __BIG_ENDIAN__
 extern void * memcpy(void *,const void *,__kernel_size_t);
+#endif
 extern void * memmove(void *,const void *,__kernel_size_t);
 extern int memcmp(const void *,const void *,__kernel_size_t);
 extern void * memchr(const void *,int,__kernel_size_t);
diff --git a/arch/powerpc/include/asm/switch_to.h b/arch/powerpc/include/asm/switch_to.h
index 2be5618cdec..9ee12610af0 100644
--- a/arch/powerpc/include/asm/switch_to.h
+++ b/arch/powerpc/include/asm/switch_to.h
@@ -35,6 +35,7 @@ extern void giveup_vsx(struct task_struct *);
 extern void enable_kernel_spe(void);
 extern void giveup_spe(struct task_struct *);
 extern void load_up_spe(struct task_struct *);
+extern void switch_booke_debug_regs(struct thread_struct *new_thread);
 
 #ifndef CONFIG_SMP
 extern void discard_lazy_cpu_state(void);
diff --git a/arch/powerpc/include/asm/word-at-a-time.h b/arch/powerpc/include/asm/word-at-a-time.h
index d0b6d4ac6dd..9a5c928bb3c 100644
--- a/arch/powerpc/include/asm/word-at-a-time.h
+++ b/arch/powerpc/include/asm/word-at-a-time.h
@@ -8,6 +8,8 @@
 #include <linux/kernel.h>
 #include <asm/asm-compat.h>
 
+#ifdef __BIG_ENDIAN__
+
 struct word_at_a_time {
 	const unsigned long high_bits, low_bits;
 };
@@ -38,4 +40,80 @@ static inline bool has_zero(unsigned long val, unsigned long *data, const struct
 	return (val + c->high_bits) & ~rhs;
 }
 
+#else
+
+struct word_at_a_time {
+	const unsigned long one_bits, high_bits;
+};
+
+#define WORD_AT_A_TIME_CONSTANTS { REPEAT_BYTE(0x01), REPEAT_BYTE(0x80) }
+
+#ifdef CONFIG_64BIT
+
+/* Alan Modra's little-endian strlen tail for 64-bit */
+#define create_zero_mask(mask) (mask)
+
+static inline unsigned long find_zero(unsigned long mask)
+{
+	unsigned long leading_zero_bits;
+	long trailing_zero_bit_mask;
+
+	asm ("addi %1,%2,-1\n\t"
+	     "andc %1,%1,%2\n\t"
+	     "popcntd %0,%1"
+	     : "=r" (leading_zero_bits), "=&r" (trailing_zero_bit_mask)
+	     : "r" (mask));
+	return leading_zero_bits >> 3;
+}
+
+#else	/* 32-bit case */
+
+/*
+ * This is largely generic for little-endian machines, but the
+ * optimal byte mask counting is probably going to be something
+ * that is architecture-specific. If you have a reliably fast
+ * bit count instruction, that might be better than the multiply
+ * and shift, for example.
+ */
+
+/* Carl Chatfield / Jan Achrenius G+ version for 32-bit */
+static inline long count_masked_bytes(long mask)
+{
+	/* (000000 0000ff 00ffff ffffff) -> ( 1 1 2 3 ) */
+	long a = (0x0ff0001+mask) >> 23;
+	/* Fix the 1 for 00 case */
+	return a & mask;
+}
+
+static inline unsigned long create_zero_mask(unsigned long bits)
+{
+	bits = (bits - 1) & ~bits;
+	return bits >> 7;
+}
+
+static inline unsigned long find_zero(unsigned long mask)
+{
+	return count_masked_bytes(mask);
+}
+
+#endif
+
+/* Return nonzero if it has a zero */
+static inline unsigned long has_zero(unsigned long a, unsigned long *bits, const struct word_at_a_time *c)
+{
+	unsigned long mask = ((a - c->one_bits) & ~a) & c->high_bits;
+	*bits = mask;
+	return mask;
+}
+
+static inline unsigned long prep_zero_mask(unsigned long a, unsigned long bits, const struct word_at_a_time *c)
+{
+	return bits;
+}
+
+/* The mask we created is directly usable as a bytemask */
+#define zero_bytemask(mask) (mask)
+
+#endif
+
 #endif /* _ASM_WORD_AT_A_TIME_H */
diff --git a/arch/powerpc/include/asm/xor.h b/arch/powerpc/include/asm/xor.h
index c82eb12a5b1..0abb97f3be1 100644
--- a/arch/powerpc/include/asm/xor.h
+++ b/arch/powerpc/include/asm/xor.h
@@ -1 +1,68 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ * Copyright (C) IBM Corporation, 2012
+ *
+ * Author: Anton Blanchard <anton@au.ibm.com>
+ */
+#ifndef _ASM_POWERPC_XOR_H
+#define _ASM_POWERPC_XOR_H
+
+#ifdef CONFIG_ALTIVEC
+
+#include <asm/cputable.h>
+
+void xor_altivec_2(unsigned long bytes, unsigned long *v1_in,
+		   unsigned long *v2_in);
+void xor_altivec_3(unsigned long bytes, unsigned long *v1_in,
+		   unsigned long *v2_in, unsigned long *v3_in);
+void xor_altivec_4(unsigned long bytes, unsigned long *v1_in,
+		   unsigned long *v2_in, unsigned long *v3_in,
+		   unsigned long *v4_in);
+void xor_altivec_5(unsigned long bytes, unsigned long *v1_in,
+		   unsigned long *v2_in, unsigned long *v3_in,
+		   unsigned long *v4_in, unsigned long *v5_in);
+
+static struct xor_block_template xor_block_altivec = {
+	.name = "altivec",
+	.do_2 = xor_altivec_2,
+	.do_3 = xor_altivec_3,
+	.do_4 = xor_altivec_4,
+	.do_5 = xor_altivec_5,
+};
+
+#define XOR_SPEED_ALTIVEC()				\
+	do {						\
+		if (cpu_has_feature(CPU_FTR_ALTIVEC))	\
+			xor_speed(&xor_block_altivec);	\
+	} while (0)
+#else
+#define XOR_SPEED_ALTIVEC()
+#endif
+
+/* Also try the generic routines. */
 #include <asm-generic/xor.h>
+
+#undef XOR_TRY_TEMPLATES
+#define XOR_TRY_TEMPLATES				\
+do {							\
+	xor_speed(&xor_block_8regs);			\
+	xor_speed(&xor_block_8regs_p);			\
+	xor_speed(&xor_block_32regs);			\
+	xor_speed(&xor_block_32regs_p);			\
+	XOR_SPEED_ALTIVEC();				\
+} while (0)
+
+#endif /* _ASM_POWERPC_XOR_H */
diff --git a/arch/powerpc/include/uapi/asm/byteorder.h b/arch/powerpc/include/uapi/asm/byteorder.h
index aa6cc4fac96..ca931d07400 100644
--- a/arch/powerpc/include/uapi/asm/byteorder.h
+++ b/arch/powerpc/include/uapi/asm/byteorder.h
@@ -7,6 +7,10 @@
  * as published by the Free Software Foundation; either version
  * 2 of the License, or (at your option) any later version.
  */
+#ifdef __LITTLE_ENDIAN__
+#include <linux/byteorder/little_endian.h>
+#else
 #include <linux/byteorder/big_endian.h>
+#endif
 
 #endif /* _ASM_POWERPC_BYTEORDER_H */