Merge remote branch 'powerpc/next'

53 files changed, 1278 insertions, 500 deletions

diff --git a/arch/powerpc/include/asm/checksum.h b/arch/powerpc/include/asm/checksum.h
index 7cdf358337cf..ce0c28495f9a 100644
--- a/arch/powerpc/include/asm/checksum.h
+++ b/arch/powerpc/include/asm/checksum.h
@@ -52,12 +52,22 @@ extern __wsum csum_partial(const void *buff, int len, __wsum sum);
 extern __wsum csum_partial_copy_generic(const void *src, void *dst,
 					      int len, __wsum sum,
 					      int *src_err, int *dst_err);
+
+#ifdef __powerpc64__
+#define _HAVE_ARCH_COPY_AND_CSUM_FROM_USER
+extern __wsum csum_and_copy_from_user(const void __user *src, void *dst,
+				      int len, __wsum sum, int *err_ptr);
+#define HAVE_CSUM_COPY_USER
+extern __wsum csum_and_copy_to_user(const void *src, void __user *dst,
+				    int len, __wsum sum, int *err_ptr);
+#else
 /*
  * the same as csum_partial, but copies from src to dst while it
  * checksums.
  */
 #define csum_partial_copy_from_user(src, dst, len, sum, errp)   \
         csum_partial_copy_generic((__force const void *)(src), (dst), (len), (sum), (errp), NULL)
+#endif
 
 #define csum_partial_copy_nocheck(src, dst, len, sum)   \
         csum_partial_copy_generic((src), (dst), (len), (sum), NULL, NULL)
diff --git a/arch/powerpc/include/asm/compat.h b/arch/powerpc/include/asm/compat.h
index a11d4eac4f97..2296112e247b 100644
--- a/arch/powerpc/include/asm/compat.h
+++ b/arch/powerpc/include/asm/compat.h
@@ -143,7 +143,7 @@ static inline void __user *arch_compat_alloc_user_space(long len)
 	 * We cant access below the stack pointer in the 32bit ABI and
 	 * can access 288 bytes in the 64bit ABI
 	 */
-	if (!(test_thread_flag(TIF_32BIT)))
+	if (!is_32bit_task())
 		usp -= 288;
 
 	return (void __user *) (usp - len);
@@ -213,7 +213,7 @@ struct compat_shmid64_ds {
 
 static inline int is_compat_task(void)
 {
-	return test_thread_flag(TIF_32BIT);
+	return is_32bit_task();
 }
 
 #endif /* __KERNEL__ */
diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h
index 3a40a992e594..f3a1fdd9cf08 100644
--- a/arch/powerpc/include/asm/cputable.h
+++ b/arch/powerpc/include/asm/cputable.h
@@ -198,6 +198,7 @@ extern const char *powerpc_base_platform;
 #define CPU_FTR_CP_USE_DCBTZ		LONG_ASM_CONST(0x0040000000000000)
 #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)
 
 #ifndef __ASSEMBLY__
 
@@ -392,28 +393,31 @@ extern const char *powerpc_base_platform;
 	    CPU_FTR_MMCRA | CPU_FTR_CTRL)
 #define CPU_FTRS_POWER4	(CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \
 	    CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \
-	    CPU_FTR_MMCRA | CPU_FTR_CP_USE_DCBTZ)
+	    CPU_FTR_MMCRA | CPU_FTR_CP_USE_DCBTZ | \
+	    CPU_FTR_STCX_CHECKS_ADDRESS)
 #define CPU_FTRS_PPC970	(CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \
 	    CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \
 	    CPU_FTR_ALTIVEC_COMP | CPU_FTR_CAN_NAP | CPU_FTR_MMCRA | \
-	    CPU_FTR_CP_USE_DCBTZ)
+	    CPU_FTR_CP_USE_DCBTZ | CPU_FTR_STCX_CHECKS_ADDRESS)
 #define CPU_FTRS_POWER5	(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_PURR | CPU_FTR_STCX_CHECKS_ADDRESS)
 #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_DSCR | CPU_FTR_UNALIGNED_LD_STD | \
+	    CPU_FTR_STCX_CHECKS_ADDRESS)
 #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_DSCR | CPU_FTR_SAO  | CPU_FTR_ASYM_SMT | \
+	    CPU_FTR_STCX_CHECKS_ADDRESS)
 #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 | \
diff --git a/arch/powerpc/include/asm/dma-mapping.h b/arch/powerpc/include/asm/dma-mapping.h
index 8c9c6ad2004e..6d2416a85709 100644
--- a/arch/powerpc/include/asm/dma-mapping.h
+++ b/arch/powerpc/include/asm/dma-mapping.h
@@ -127,19 +127,7 @@ static inline int dma_supported(struct device *dev, u64 mask)
 	return dma_ops->dma_supported(dev, mask);
 }
 
-static inline int dma_set_mask(struct device *dev, u64 dma_mask)
-{
-	struct dma_map_ops *dma_ops = get_dma_ops(dev);
-
-	if (unlikely(dma_ops == NULL))
-		return -EIO;
-	if (dma_ops->set_dma_mask != NULL)
-		return dma_ops->set_dma_mask(dev, dma_mask);
-	if (!dev->dma_mask || !dma_supported(dev, dma_mask))
-		return -EIO;
-	*dev->dma_mask = dma_mask;
-	return 0;
-}
+extern int dma_set_mask(struct device *dev, u64 dma_mask);
 
 static inline void *dma_alloc_coherent(struct device *dev, size_t size,
 				       dma_addr_t *dma_handle, gfp_t flag)
diff --git a/arch/powerpc/include/asm/elf.h b/arch/powerpc/include/asm/elf.h
index c376eda15313..2b917c69ed15 100644
--- a/arch/powerpc/include/asm/elf.h
+++ b/arch/powerpc/include/asm/elf.h
@@ -250,7 +250,7 @@ do {								\
  * the 64bit ABI has never had these issues dont enable the workaround
  * even if we have an executable stack.
  */
-# define elf_read_implies_exec(ex, exec_stk) (test_thread_flag(TIF_32BIT) ? \
+# define elf_read_implies_exec(ex, exec_stk) (is_32bit_task() ? \
 		(exec_stk == EXSTACK_DEFAULT) : 0)
 #else 
 # define SET_PERSONALITY(ex) \
diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h
index 57c400071995..7778d6f0c878 100644
--- a/arch/powerpc/include/asm/exception-64s.h
+++ b/arch/powerpc/include/asm/exception-64s.h
@@ -137,7 +137,8 @@
 	li	r10,0;							   \
 	ld	r11,exception_marker@toc(r2);				   \
 	std	r10,RESULT(r1);		/* clear regs->result		*/ \
-	std	r11,STACK_FRAME_OVERHEAD-16(r1); /* mark the frame	*/
+	std	r11,STACK_FRAME_OVERHEAD-16(r1); /* mark the frame	*/ \
+	ACCOUNT_STOLEN_TIME
 
 /*
  * Exception vectors.
diff --git a/arch/powerpc/include/asm/kvm_fpu.h b/arch/powerpc/include/asm/kvm_fpu.h
index c3d4f0518a67..92daae132492 100644
--- a/arch/powerpc/include/asm/kvm_fpu.h
+++ b/arch/powerpc/include/asm/kvm_fpu.h
@@ -82,7 +82,7 @@ FPD_THREE_IN(fmadd)
 FPD_THREE_IN(fnmsub)
 FPD_THREE_IN(fnmadd)
 
-extern void kvm_cvt_fd(u32 *from, u64 *to, u64 *fpscr);
-extern void kvm_cvt_df(u64 *from, u32 *to, u64 *fpscr);
+extern void kvm_cvt_fd(u32 *from, u64 *to);
+extern void kvm_cvt_df(u64 *from, u32 *to);
 
 #endif
diff --git a/arch/powerpc/include/asm/lppaca.h b/arch/powerpc/include/asm/lppaca.h
index 14b592dfb4e8..7f5e0fefebb0 100644
--- a/arch/powerpc/include/asm/lppaca.h
+++ b/arch/powerpc/include/asm/lppaca.h
@@ -153,6 +153,8 @@ struct lppaca {
 
 extern struct lppaca lppaca[];
 
+#define lppaca_of(cpu)	(*paca[cpu].lppaca_ptr)
+
 /*
  * SLB shadow buffer structure as defined in the PAPR.  The save_area
  * contains adjacent ESID and VSID pairs for each shadowed SLB.  The
@@ -170,6 +172,33 @@ struct slb_shadow {
 
 extern struct slb_shadow slb_shadow[];
 
+/*
+ * Layout of entries in the hypervisor's dispatch trace log buffer.
+ */
+struct dtl_entry {
+	u8	dispatch_reason;
+	u8	preempt_reason;
+	u16	processor_id;
+	u32	enqueue_to_dispatch_time;
+	u32	ready_to_enqueue_time;
+	u32	waiting_to_ready_time;
+	u64	timebase;
+	u64	fault_addr;
+	u64	srr0;
+	u64	srr1;
+};
+
+#define DISPATCH_LOG_BYTES	4096	/* bytes per cpu */
+#define N_DISPATCH_LOG		(DISPATCH_LOG_BYTES / sizeof(struct dtl_entry))
+
+/*
+ * When CONFIG_VIRT_CPU_ACCOUNTING = y, the cpu accounting code controls
+ * reading from the dispatch trace log.  If other code wants to consume
+ * DTL entries, it can set this pointer to a function that will get
+ * called once for each DTL entry that gets processed.
+ */
+extern void (*dtl_consumer)(struct dtl_entry *entry, u64 index);
+
 #endif /* CONFIG_PPC_BOOK3S */
 #endif /* __KERNEL__ */
 #endif /* _ASM_POWERPC_LPPACA_H */
diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h
index adc8e6cdf339..d045b0145537 100644
--- a/arch/powerpc/include/asm/machdep.h
+++ b/arch/powerpc/include/asm/machdep.h
@@ -102,6 +102,9 @@ struct machdep_calls {
 	void		(*pci_dma_dev_setup)(struct pci_dev *dev);
 	void		(*pci_dma_bus_setup)(struct pci_bus *bus);
 
+	/* Platform set_dma_mask override */
+	int		(*dma_set_mask)(struct device *dev, u64 dma_mask);
+
 	int		(*probe)(void);
 	void		(*setup_arch)(void); /* Optional, may be NULL */
 	void		(*init_early)(void);
diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h
index 1ff6662f7faf..6af6c1613409 100644
--- a/arch/powerpc/include/asm/paca.h
+++ b/arch/powerpc/include/asm/paca.h
@@ -85,6 +85,8 @@ struct paca_struct {
 	u8 kexec_state;		/* set when kexec down has irqs off */
 #ifdef CONFIG_PPC_STD_MMU_64
 	struct slb_shadow *slb_shadow_ptr;
+	struct dtl_entry *dispatch_log;
+	struct dtl_entry *dispatch_log_end;
 
 	/*
 	 * Now, starting in cacheline 2, the exception save areas
@@ -134,8 +136,14 @@ struct paca_struct {
 	/* Stuff for accurate time accounting */
 	u64 user_time;			/* accumulated usermode TB ticks */
 	u64 system_time;		/* accumulated system TB ticks */
-	u64 startpurr;			/* PURR/TB value snapshot */
+	u64 user_time_scaled;		/* accumulated usermode SPURR ticks */
+	u64 starttime;			/* TB value snapshot */
+	u64 starttime_user;		/* TB value on exit to usermode */
 	u64 startspurr;			/* SPURR value snapshot */
+	u64 utime_sspurr;		/* ->user_time when ->startspurr set */
+	u64 stolen_time;		/* TB ticks taken by hypervisor */
+	u64 dtl_ridx;			/* read index in dispatch log */
+	struct dtl_entry *dtl_curr;	/* pointer corresponding to dtl_ridx */
 
 #ifdef CONFIG_KVM_BOOK3S_HANDLER
 	/* We use this to store guest state in */
diff --git a/arch/powerpc/include/asm/page_64.h b/arch/powerpc/include/asm/page_64.h
index 358ff14ea25e..932f88dcf6fa 100644
--- a/arch/powerpc/include/asm/page_64.h
+++ b/arch/powerpc/include/asm/page_64.h
@@ -163,7 +163,7 @@ do {						\
 #endif /* !CONFIG_HUGETLB_PAGE */
 
 #define VM_DATA_DEFAULT_FLAGS \
-	(test_thread_flag(TIF_32BIT) ? \
+	(is_32bit_task() ? \
 	 VM_DATA_DEFAULT_FLAGS32 : VM_DATA_DEFAULT_FLAGS64)
 
 /*
@@ -179,7 +179,7 @@ do {						\
 					 VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
 
 #define VM_STACK_DEFAULT_FLAGS \
-	(test_thread_flag(TIF_32BIT) ? \
+	(is_32bit_task() ? \
 	 VM_STACK_DEFAULT_FLAGS32 : VM_STACK_DEFAULT_FLAGS64)
 
 #include <asm-generic/getorder.h>
diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h
index 498fe09263d3..98210067c1cc 100644
--- a/arch/powerpc/include/asm/ppc_asm.h
+++ b/arch/powerpc/include/asm/ppc_asm.h
@@ -9,6 +9,7 @@
 #include <asm/asm-compat.h>
 #include <asm/processor.h>
 #include <asm/ppc-opcode.h>
+#include <asm/firmware.h>
 
 #ifndef __ASSEMBLY__
 #error __FILE__ should only be used in assembler files
@@ -26,17 +27,13 @@
 #ifndef CONFIG_VIRT_CPU_ACCOUNTING
 #define ACCOUNT_CPU_USER_ENTRY(ra, rb)
 #define ACCOUNT_CPU_USER_EXIT(ra, rb)
+#define ACCOUNT_STOLEN_TIME
 #else
 #define ACCOUNT_CPU_USER_ENTRY(ra, rb)					\
 	beq	2f;			/* if from kernel mode */	\
-BEGIN_FTR_SECTION;							\
-	mfspr	ra,SPRN_PURR;		/* get processor util. reg */	\
-END_FTR_SECTION_IFSET(CPU_FTR_PURR);					\
-BEGIN_FTR_SECTION;							\
-	MFTB(ra);			/* or get TB if no PURR */	\
-END_FTR_SECTION_IFCLR(CPU_FTR_PURR);					\
-	ld	rb,PACA_STARTPURR(r13);					\
-	std	ra,PACA_STARTPURR(r13);					\
+	MFTB(ra);			/* get timebase */		\
+	ld	rb,PACA_STARTTIME_USER(r13);				\
+	std	ra,PACA_STARTTIME(r13);					\
 	subf	rb,rb,ra;		/* subtract start value */	\
 	ld	ra,PACA_USER_TIME(r13);					\
 	add	ra,ra,rb;		/* add on to user time */	\
@@ -44,19 +41,34 @@ END_FTR_SECTION_IFCLR(CPU_FTR_PURR);					\
 2:
 
 #define ACCOUNT_CPU_USER_EXIT(ra, rb)					\
-BEGIN_FTR_SECTION;							\
-	mfspr	ra,SPRN_PURR;		/* get processor util. reg */	\
-END_FTR_SECTION_IFSET(CPU_FTR_PURR);					\
-BEGIN_FTR_SECTION;							\
-	MFTB(ra);			/* or get TB if no PURR */	\
-END_FTR_SECTION_IFCLR(CPU_FTR_PURR);					\
-	ld	rb,PACA_STARTPURR(r13);					\
-	std	ra,PACA_STARTPURR(r13);					\
+	MFTB(ra);			/* get timebase */		\
+	ld	rb,PACA_STARTTIME(r13);					\
+	std	ra,PACA_STARTTIME_USER(r13);				\
 	subf	rb,rb,ra;		/* subtract start value */	\
 	ld	ra,PACA_SYSTEM_TIME(r13);				\
-	add	ra,ra,rb;		/* add on to user time */	\
-	std	ra,PACA_SYSTEM_TIME(r13);
-#endif
+	add	ra,ra,rb;		/* add on to system time */	\
+	std	ra,PACA_SYSTEM_TIME(r13)
+
+#ifdef CONFIG_PPC_SPLPAR
+#define ACCOUNT_STOLEN_TIME						\
+BEGIN_FW_FTR_SECTION;							\
+	beq	33f;							\
+	/* from user - see if there are any DTL entries to process */	\
+	ld	r10,PACALPPACAPTR(r13);	/* get ptr to VPA */		\
+	ld	r11,PACA_DTL_RIDX(r13);	/* get log read index */	\
+	ld	r10,LPPACA_DTLIDX(r10);	/* get log write index */	\
+	cmpd	cr1,r11,r10;						\
+	beq+	cr1,33f;						\
+	bl	.accumulate_stolen_time;				\
+33:									\
+END_FW_FTR_SECTION_IFSET(FW_FEATURE_SPLPAR)
+
+#else  /* CONFIG_PPC_SPLPAR */
+#define ACCOUNT_STOLEN_TIME
+
+#endif /* CONFIG_PPC_SPLPAR */
+
+#endif /* CONFIG_VIRT_CPU_ACCOUNTING */
 
 /*
  * Macros for storing registers into and loading registers from
diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index 19c05b0f74be..4c14187ba02d 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -118,7 +118,7 @@ extern struct task_struct *last_task_used_spe;
 #define TASK_UNMAPPED_BASE_USER32 (PAGE_ALIGN(TASK_SIZE_USER32 / 4))
 #define TASK_UNMAPPED_BASE_USER64 (PAGE_ALIGN(TASK_SIZE_USER64 / 4))
 
-#define TASK_UNMAPPED_BASE ((test_thread_flag(TIF_32BIT)) ? \
+#define TASK_UNMAPPED_BASE ((is_32bit_task()) ? \
 		TASK_UNMAPPED_BASE_USER32 : TASK_UNMAPPED_BASE_USER64 )
 #endif
 
@@ -128,7 +128,7 @@ extern struct task_struct *last_task_used_spe;
 #define STACK_TOP_USER64 TASK_SIZE_USER64
 #define STACK_TOP_USER32 TASK_SIZE_USER32
 
-#define STACK_TOP (test_thread_flag(TIF_32BIT) ? \
+#define STACK_TOP (is_32bit_task() ? \
 		   STACK_TOP_USER32 : STACK_TOP_USER64)
 
 #define STACK_TOP_MAX STACK_TOP_USER64
diff --git a/arch/powerpc/include/asm/systbl.h b/arch/powerpc/include/asm/systbl.h
index 3d212669a130..aa0f1ebb4aaf 100644
--- a/arch/powerpc/include/asm/systbl.h
+++ b/arch/powerpc/include/asm/systbl.h
@@ -329,3 +329,22 @@ COMPAT_SYS(rt_tgsigqueueinfo)
 SYSCALL(fanotify_init)
 COMPAT_SYS(fanotify_mark)
 SYSCALL_SPU(prlimit64)
+SYSCALL_SPU(socket)
+SYSCALL_SPU(bind)
+SYSCALL_SPU(connect)
+SYSCALL_SPU(listen)
+SYSCALL_SPU(accept)
+SYSCALL_SPU(getsockname)
+SYSCALL_SPU(getpeername)
+SYSCALL_SPU(socketpair)
+SYSCALL_SPU(send)
+SYSCALL_SPU(sendto)
+COMPAT_SYS_SPU(recv)
+COMPAT_SYS_SPU(recvfrom)
+SYSCALL_SPU(shutdown)
+COMPAT_SYS_SPU(setsockopt)
+COMPAT_SYS_SPU(getsockopt)
+COMPAT_SYS_SPU(sendmsg)
+COMPAT_SYS_SPU(recvmsg)
+COMPAT_SYS_SPU(recvmmsg)
+SYSCALL_SPU(accept4)
diff --git a/arch/powerpc/include/asm/system.h b/arch/powerpc/include/asm/system.h
index 6c294acac848..0b3fe78be71b 100644
--- a/arch/powerpc/include/asm/system.h
+++ b/arch/powerpc/include/asm/system.h
@@ -154,8 +154,8 @@ extern void enable_kernel_spe(void);
 extern void giveup_spe(struct task_struct *);
 extern void load_up_spe(struct task_struct *);
 extern int fix_alignment(struct pt_regs *);
-extern void cvt_fd(float *from, double *to, struct thread_struct *thread);
-extern void cvt_df(double *from, float *to, struct thread_struct *thread);
+extern void cvt_fd(float *from, double *to);
+extern void cvt_df(double *from, float *to);
 
 #ifndef CONFIG_SMP
 extern void discard_lazy_cpu_state(void);
diff --git a/arch/powerpc/include/asm/time.h b/arch/powerpc/include/asm/time.h
index dc779dfcf258..fe6f7c2c9c68 100644
--- a/arch/powerpc/include/asm/time.h
+++ b/arch/powerpc/include/asm/time.h
@@ -34,7 +34,6 @@ extern void to_tm(int tim, struct rtc_time * tm);
 extern void GregorianDay(struct rtc_time *tm);
 
 extern void generic_calibrate_decr(void);
-extern void snapshot_timebase(void);
 
 extern void set_dec_cpu6(unsigned int val);
 
@@ -212,12 +211,8 @@ struct cpu_usage {
 DECLARE_PER_CPU(struct cpu_usage, cpu_usage_array);
 
 #if defined(CONFIG_VIRT_CPU_ACCOUNTING)
-extern void calculate_steal_time(void);
-extern void snapshot_timebases(void);
 #define account_process_vtime(tsk)		account_process_tick(tsk, 0)
 #else
-#define calculate_steal_time()			do { } while (0)
-#define snapshot_timebases()			do { } while (0)
 #define account_process_vtime(tsk)		do { } while (0)
 #endif
 
diff --git a/arch/powerpc/include/asm/unistd.h b/arch/powerpc/include/asm/unistd.h
index 597e6f9d094a..6151937657f6 100644
--- a/arch/powerpc/include/asm/unistd.h
+++ b/arch/powerpc/include/asm/unistd.h
@@ -348,10 +348,29 @@
 #define __NR_fanotify_init	323
 #define __NR_fanotify_mark	324
 #define __NR_prlimit64		325
+#define __NR_socket		326
+#define __NR_bind		327
+#define __NR_connect		328
+#define __NR_listen		329
+#define __NR_accept		330
+#define __NR_getsockname	331
+#define __NR_getpeername	332
+#define __NR_socketpair		333
+#define __NR_send		334
+#define __NR_sendto		335
+#define __NR_recv		336
+#define __NR_recvfrom		337
+#define __NR_shutdown		338
+#define __NR_setsockopt		339
+#define __NR_getsockopt		340
+#define __NR_sendmsg		341
+#define __NR_recvmsg		342
+#define __NR_recvmmsg		343
+#define __NR_accept4		344
 
 #ifdef __KERNEL__
 
-#define __NR_syscalls		326
+#define __NR_syscalls		345
 
 #define __NR__exit __NR_exit
 #define NR_syscalls	__NR_syscalls
diff --git a/arch/powerpc/kernel/align.c b/arch/powerpc/kernel/align.c
index b876e989220b..8184ee97e484 100644
--- a/arch/powerpc/kernel/align.c
+++ b/arch/powerpc/kernel/align.c
@@ -889,7 +889,7 @@ int fix_alignment(struct pt_regs *regs)
 #ifdef CONFIG_PPC_FPU
 			preempt_disable();
 			enable_kernel_fp();
-			cvt_df(&data.dd, (float *)&data.v[4], &current->thread);
+			cvt_df(&data.dd, (float *)&data.v[4]);
 			preempt_enable();
 #else
 			return 0;
@@ -933,7 +933,7 @@ int fix_alignment(struct pt_regs *regs)
 #ifdef CONFIG_PPC_FPU
 		preempt_disable();
 		enable_kernel_fp();
-		cvt_fd((float *)&data.v[4], &data.dd, &current->thread);
+		cvt_fd((float *)&data.v[4], &data.dd);
 		preempt_enable();
 #else
 		return 0;
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 1c0607ddccc0..c63494090854 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -181,17 +181,19 @@ int main(void)
 	       offsetof(struct slb_shadow, save_area[SLB_NUM_BOLTED - 1].vsid));
 	DEFINE(SLBSHADOW_STACKESID,
 	       offsetof(struct slb_shadow, save_area[SLB_NUM_BOLTED - 1].esid));
+	DEFINE(SLBSHADOW_SAVEAREA, offsetof(struct slb_shadow, save_area));
 	DEFINE(LPPACASRR0, offsetof(struct lppaca, saved_srr0));
 	DEFINE(LPPACASRR1, offsetof(struct lppaca, saved_srr1));
 	DEFINE(LPPACAANYINT, offsetof(struct lppaca, int_dword.any_int));
 	DEFINE(LPPACADECRINT, offsetof(struct lppaca, int_dword.fields.decr_int));
-	DEFINE(SLBSHADOW_SAVEAREA, offsetof(struct slb_shadow, save_area));
+	DEFINE(LPPACA_DTLIDX, offsetof(struct lppaca, dtl_idx));
+	DEFINE(PACA_DTL_RIDX, offsetof(struct paca_struct, dtl_ridx));
 #endif /* CONFIG_PPC_STD_MMU_64 */
 	DEFINE(PACAEMERGSP, offsetof(struct paca_struct, emergency_sp));
 	DEFINE(PACAHWCPUID, offsetof(struct paca_struct, hw_cpu_id));
 	DEFINE(PACAKEXECSTATE, offsetof(struct paca_struct, kexec_state));
-	DEFINE(PACA_STARTPURR, offsetof(struct paca_struct, startpurr));
-	DEFINE(PACA_STARTSPURR, offsetof(struct paca_struct, startspurr));
+	DEFINE(PACA_STARTTIME, offsetof(struct paca_struct, starttime));
+	DEFINE(PACA_STARTTIME_USER, offsetof(struct paca_struct, starttime_user));
 	DEFINE(PACA_USER_TIME, offsetof(struct paca_struct, user_time));
 	DEFINE(PACA_SYSTEM_TIME, offsetof(struct paca_struct, system_time));
 	DEFINE(PACA_TRAP_SAVE, offsetof(struct paca_struct, trap_save));
diff --git a/arch/powerpc/kernel/dma.c b/arch/powerpc/kernel/dma.c
index 84d6367ec003..f368c075c90b 100644
--- a/arch/powerpc/kernel/dma.c
+++ b/arch/powerpc/kernel/dma.c
@@ -12,6 +12,7 @@
 #include <linux/memblock.h>
 #include <asm/bug.h>
 #include <asm/abs_addr.h>
+#include <asm/machdep.h>
 
 /*
  * Generic direct DMA implementation
@@ -154,6 +155,23 @@ EXPORT_SYMBOL(dma_direct_ops);
 
 #define PREALLOC_DMA_DEBUG_ENTRIES (1 << 16)
 
+int dma_set_mask(struct device *dev, u64 dma_mask)
+{
+	struct dma_map_ops *dma_ops = get_dma_ops(dev);
+
+	if (ppc_md.dma_set_mask)
+		return ppc_md.dma_set_mask(dev, dma_mask);
+	if (unlikely(dma_ops == NULL))
+		return -EIO;
+	if (dma_ops->set_dma_mask != NULL)
+		return dma_ops->set_dma_mask(dev, dma_mask);
+	if (!dev->dma_mask || !dma_supported(dev, dma_mask))
+		return -EIO;
+	*dev->dma_mask = dma_mask;
+	return 0;
+}
+EXPORT_SYMBOL(dma_set_mask);
+
 static int __init dma_init(void)
 {
        dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES);
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index 42e9d908914a..d82878c4daa6 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -97,6 +97,24 @@ system_call_common:
 	addi	r9,r1,STACK_FRAME_OVERHEAD
 	ld	r11,exception_marker@toc(r2)
 	std	r11,-16(r9)		/* "regshere" marker */
+#if defined(CONFIG_VIRT_CPU_ACCOUNTING) && defined(CONFIG_PPC_SPLPAR)
+BEGIN_FW_FTR_SECTION
+	beq	33f
+	/* if from user, see if there are any DTL entries to process */
+	ld	r10,PACALPPACAPTR(r13)	/* get ptr to VPA */
+	ld	r11,PACA_DTL_RIDX(r13)	/* get log read index */
+	ld	r10,LPPACA_DTLIDX(r10)	/* get log write index */
+	cmpd	cr1,r11,r10
+	beq+	cr1,33f
+	bl	.accumulate_stolen_time
+	REST_GPR(0,r1)
+	REST_4GPRS(3,r1)
+	REST_2GPRS(7,r1)
+	addi	r9,r1,STACK_FRAME_OVERHEAD
+33:
+END_FW_FTR_SECTION_IFSET(FW_FEATURE_SPLPAR)
+#endif /* CONFIG_VIRT_CPU_ACCOUNTING && CONFIG_PPC_SPLPAR */
+
 #ifdef CONFIG_TRACE_IRQFLAGS
 	bl	.trace_hardirqs_on
 	REST_GPR(0,r1)
@@ -202,7 +220,9 @@ syscall_exit:
 	bge-	syscall_error
 syscall_error_cont:
 	ld	r7,_NIP(r1)
+BEGIN_FTR_SECTION
 	stdcx.	r0,0,r1			/* to clear the reservation */
+END_FTR_SECTION_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS)
 	andi.	r6,r8,MSR_PR
 	ld	r4,_LINK(r1)
 	/*
@@ -419,6 +439,17 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
 	sync
 #endif /* CONFIG_SMP */
 
+	/*
+	 * If we optimise away the clear of the reservation in system
+	 * calls because we know the CPU tracks the address of the
+	 * reservation, then we need to clear it here to cover the
+	 * case that the kernel context switch path has no larx
+	 * instructions.
+	 */
+BEGIN_FTR_SECTION
+	ldarx	r6,0,r1
+END_FTR_SECTION_IFSET(CPU_FTR_STCX_CHECKS_ADDRESS)
+
 	addi	r6,r4,-THREAD	/* Convert THREAD to 'current' */
 	std	r6,PACACURRENT(r13)	/* Set new 'current' */
 
@@ -576,7 +607,16 @@ ALT_FW_FTR_SECTION_END_IFCLR(FW_FEATURE_ISERIES)
 	andi.	r0,r3,MSR_RI
 	beq-	unrecov_restore
 
+	/*
+	 * Clear the reservation. If we know the CPU tracks the address of
+	 * the reservation then we can potentially save some cycles and use
+	 * a larx. On POWER6 and POWER7 this is significantly faster.
+	 */
+BEGIN_FTR_SECTION
 	stdcx.	r0,0,r1		/* to clear the reservation */
+FTR_SECTION_ELSE
+	ldarx	r4,0,r1
+ALT_FTR_SECTION_END_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS)
 
 	/*
 	 * Clear RI before restoring r13.  If we are returning to
diff --git a/arch/powerpc/kernel/fpu.S b/arch/powerpc/kernel/fpu.S
index fc8f5b14019c..e86c040ae585 100644
--- a/arch/powerpc/kernel/fpu.S
+++ b/arch/powerpc/kernel/fpu.S
@@ -163,24 +163,14 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX)
 /*
  * These are used in the alignment trap handler when emulating
  * single-precision loads and stores.
- * We restore and save the fpscr so the task gets the same result
- * and exceptions as if the cpu had performed the load or store.
  */
 
 _GLOBAL(cvt_fd)
-	lfd	0,THREAD_FPSCR(r5)	/* load up fpscr value */
-	MTFSF_L(0)
 	lfs	0,0(r3)
 	stfd	0,0(r4)
-	mffs	0
-	stfd	0,THREAD_FPSCR(r5)	/* save new fpscr value */
 	blr
 
 _GLOBAL(cvt_df)
-	lfd	0,THREAD_FPSCR(r5)	/* load up fpscr value */
-	MTFSF_L(0)
 	lfd	0,0(r3)
 	stfs	0,0(r4)
-	mffs	0
-	stfd	0,THREAD_FPSCR(r5)	/* save new fpscr value */
 	blr
diff --git a/arch/powerpc/kernel/lparcfg.c b/arch/powerpc/kernel/lparcfg.c
index 50362b6ef6e9..8d9e3b9cda64 100644
--- a/arch/powerpc/kernel/lparcfg.c
+++ b/arch/powerpc/kernel/lparcfg.c
@@ -56,7 +56,7 @@ static unsigned long get_purr(void)
 
 	for_each_possible_cpu(cpu) {
 		if (firmware_has_feature(FW_FEATURE_ISERIES))
-			sum_purr += lppaca[cpu].emulated_time_base;
+			sum_purr += lppaca_of(cpu).emulated_time_base;
 		else {
 			struct cpu_usage *cu;
 
@@ -263,7 +263,7 @@ static void parse_ppp_data(struct seq_file *m)
 	           ppp_data.active_system_procs);
 
 	/* pool related entries are apropriate for shared configs */
-	if (lppaca[0].shared_proc) {
+	if (lppaca_of(0).shared_proc) {
 		unsigned long pool_idle_time, pool_procs;
 
 		seq_printf(m, "pool=%d\n", ppp_data.pool_num);
@@ -460,8 +460,8 @@ static void pseries_cmo_data(struct seq_file *m)
 		return;
 
 	for_each_possible_cpu(cpu) {
-		cmo_faults += lppaca[cpu].cmo_faults;
-		cmo_fault_time += lppaca[cpu].cmo_fault_time;
+		cmo_faults += lppaca_of(cpu).cmo_faults;
+		cmo_fault_time += lppaca_of(cpu).cmo_fault_time;
 	}
 
 	seq_printf(m, "cmo_faults=%lu\n", cmo_faults);
@@ -479,8 +479,8 @@ static void splpar_dispatch_data(struct seq_file *m)
 	unsigned long dispatch_dispersions = 0;
 
 	for_each_possible_cpu(cpu) {
-		dispatches += lppaca[cpu].yield_count;
-		dispatch_dispersions += lppaca[cpu].dispersion_count;
+		dispatches += lppaca_of(cpu).yield_count;
+		dispatch_dispersions += lppaca_of(cpu).dispersion_count;
 	}
 
 	seq_printf(m, "dispatches=%lu\n", dispatches);
@@ -545,7 +545,7 @@ static int pseries_lparcfg_data(struct seq_file *m, void *v)
 	seq_printf(m, "partition_potential_processors=%d\n",
 		   partition_potential_processors);
 
-	seq_printf(m, "shared_processor_mode=%d\n", lppaca[0].shared_proc);
+	seq_printf(m, "shared_processor_mode=%d\n", lppaca_of(0).shared_proc);
 
 	seq_printf(m, "slb_size=%d\n", mmu_slb_size);
 
diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c
index d0a26f1770fe..1e068a46e6c3 100644
--- a/arch/powerpc/kernel/paca.c
+++ b/arch/powerpc/kernel/paca.c
@@ -27,6 +27,20 @@ extern unsigned long __toc_start;
 #ifdef CONFIG_PPC_BOOK3S
 
 /*
+ * We only have to have statically allocated lppaca structs on
+ * legacy iSeries, which supports at most 64 cpus.
+ */
+#ifdef CONFIG_PPC_ISERIES
+#if NR_CPUS < 64
+#define NR_LPPACAS	NR_CPUS
+#else
+#define NR_LPPACAS	64
+#endif
+#else /* not iSeries */
+#define NR_LPPACAS	1
+#endif
+
+/*
  * The structure which the hypervisor knows about - this structure
  * should not cross a page boundary.  The vpa_init/register_vpa call
  * is now known to fail if the lppaca structure crosses a page
@@ -36,7 +50,7 @@ extern unsigned long __toc_start;
  * will suffice to ensure that it doesn't cross a page boundary.
  */
 struct lppaca lppaca[] = {
-	[0 ... (NR_CPUS-1)] = {
+	[0 ... (NR_LPPACAS-1)] = {
 		.desc = 0xd397d781,	/* "LpPa" */
 		.size = sizeof(struct lppaca),
 		.dyn_proc_status = 2,
@@ -49,6 +63,54 @@ struct lppaca lppaca[] = {
 	},
 };
 
+static struct lppaca *extra_lppacas;
+static long __initdata lppaca_size;
+
+static void allocate_lppacas(int nr_cpus, unsigned long limit)
+{
+	if (nr_cpus <= NR_LPPACAS)
+		return;
+
+	lppaca_size = PAGE_ALIGN(sizeof(struct lppaca) *
+				 (nr_cpus - NR_LPPACAS));
+	extra_lppacas = __va(memblock_alloc_base(lppaca_size,
+						 PAGE_SIZE, limit));
+}
+
+static struct lppaca *new_lppaca(int cpu)
+{
+	struct lppaca *lp;
+
+	if (cpu < NR_LPPACAS)
+		return &lppaca[cpu];
+
+	lp = extra_lppacas + (cpu - NR_LPPACAS);
+	*lp = lppaca[0];
+
+	return lp;
+}
+
+static void free_lppacas(void)
+{
+	long new_size = 0, nr;
+
+	if (!lppaca_size)
+		return;
+	nr = num_possible_cpus() - NR_LPPACAS;
+	if (nr > 0)
+		new_size = PAGE_ALIGN(nr * sizeof(struct lppaca));
+	if (new_size >= lppaca_size)
+		return;
+
+	memblock_free(__pa(extra_lppacas) + new_size, lppaca_size - new_size);
+	lppaca_size = new_size;
+}
+
+#else
+
+static inline void allocate_lppacas(int, unsigned long) { }
+static inline void free_lppacas(void) { }
+
 #endif /* CONFIG_PPC_BOOK3S */
 
 #ifdef CONFIG_PPC_STD_MMU_64
@@ -88,7 +150,7 @@ void __init initialise_paca(struct paca_struct *new_paca, int cpu)
 	unsigned long kernel_toc = (unsigned long)(&__toc_start) + 0x8000UL;
 
 #ifdef CONFIG_PPC_BOOK3S
-	new_paca->lppaca_ptr = &lppaca[cpu];
+	new_paca->lppaca_ptr = new_lppaca(cpu);
 #else
 	new_paca->kernel_pgd = swapper_pg_dir;
 #endif
@@ -144,6 +206,8 @@ void __init allocate_pacas(void)
 	printk(KERN_DEBUG "Allocated %u bytes for %d pacas at %p\n",
 		paca_size, nr_cpus, paca);
 
+	allocate_lppacas(nr_cpus, limit);
+
 	/* Can't use for_each_*_cpu, as they aren't functional yet */
 	for (cpu = 0; cpu < nr_cpus; cpu++)
 		initialise_paca(&paca[cpu], cpu);
@@ -164,4 +228,6 @@ void __init free_unused_pacas(void)
 		paca_size - new_size);
 
 	paca_size = new_size;
+
+	free_lppacas();
 }
diff --git a/arch/powerpc/kernel/ppc970-pmu.c b/arch/powerpc/kernel/ppc970-pmu.c
index 8eff48e20dba..3fee685de4df 100644
--- a/arch/powerpc/kernel/ppc970-pmu.c
+++ b/arch/powerpc/kernel/ppc970-pmu.c
@@ -169,9 +169,11 @@ static int p970_marked_instr_event(u64 event)
 	switch (unit) {
 	case PM_VPU:
 		mask = 0x4c;		/* byte 0 bits 2,3,6 */
+		break;
 	case PM_LSU0:
 		/* byte 2 bits 0,2,3,4,6; all of byte 1 */
 		mask = 0x085dff00;
+		break;
 	case PM_LSU1L:
 		mask = 0x50 << 24;	/* byte 3 bits 4,6 */
 		break;
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index b1c648a36b03..84906d3fc860 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -517,7 +517,6 @@ struct task_struct *__switch_to(struct task_struct *prev,
 
 	account_system_vtime(current);
 	account_process_vtime(current);
-	calculate_steal_time();
 
 	/*
 	 * We can't take a PMU exception inside _switch() since there is a
@@ -1298,14 +1297,3 @@ unsigned long randomize_et_dyn(unsigned long base)
 
 	return ret;
 }
-
-#ifdef CONFIG_SMP
-int arch_sd_sibling_asym_packing(void)
-{
-	if (cpu_has_feature(CPU_FTR_ASYM_SMT)) {
-		printk_once(KERN_INFO "Enabling Asymmetric SMT scheduling\n");
-		return SD_ASYM_PACKING;
-	}
-	return 0;
-}
-#endif
diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c
index 11f3cd9c832f..286d9783d93f 100644
--- a/arch/powerpc/kernel/ptrace.c
+++ b/arch/powerpc/kernel/ptrace.c
@@ -1681,7 +1681,7 @@ long do_syscall_trace_enter(struct pt_regs *regs)
 
 	if (unlikely(current->audit_context)) {
 #ifdef CONFIG_PPC64
-		if (!test_thread_flag(TIF_32BIT))
+		if (!is_32bit_task())
 			audit_syscall_entry(AUDIT_ARCH_PPC64,
 					    regs->gpr[0],
 					    regs->gpr[3], regs->gpr[4],
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 0008bc58e826..68034bbf2e4f 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -508,9 +508,6 @@ int __devinit start_secondary(void *unused)
 	if (smp_ops->take_timebase)
 		smp_ops->take_timebase();
 
-	if (system_state > SYSTEM_BOOTING)
-		snapshot_timebase();
-
 	secondary_cpu_time_init();
 
 	ipi_call_lock();
@@ -575,11 +572,18 @@ void __init smp_cpus_done(unsigned int max_cpus)
 
 	free_cpumask_var(old_mask);
 
-	snapshot_timebases();
-
 	dump_numa_cpu_topology();
 }
 
+int arch_sd_sibling_asym_packing(void)
+{
+	if (cpu_has_feature(CPU_FTR_ASYM_SMT)) {
+		printk_once(KERN_INFO "Enabling Asymmetric SMT scheduling\n");
+		return SD_ASYM_PACKING;
+	}
+	return 0;
+}
+
 #ifdef CONFIG_HOTPLUG_CPU
 int __cpu_disable(void)
 {
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 8533b3b83f5d..bcb738b9ff8c 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -164,8 +164,6 @@ unsigned long ppc_proc_freq;
 EXPORT_SYMBOL(ppc_proc_freq);
 unsigned long ppc_tb_freq;
 
-static DEFINE_PER_CPU(u64, last_jiffy);
-
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING
 /*
  * Factors for converting from cputime_t (timebase ticks) to
@@ -185,6 +183,8 @@ DEFINE_PER_CPU(unsigned long, cputime_scaled_last_delta);
 
 cputime_t cputime_one_jiffy;
 
+void (*dtl_consumer)(struct dtl_entry *, u64);
+
 static void calc_cputime_factors(void)
 {
 	struct div_result res;
@@ -200,62 +200,153 @@ static void calc_cputime_factors(void)
 }
 
 /*
- * Read the PURR on systems that have it, otherwise the timebase.
+ * Read the SPURR on systems that have it, otherwise the PURR,
+ * or if that doesn't exist return the timebase value passed in.
  */
-static u64 read_purr(void)
+static u64 read_spurr(u64 tb)
 {
+	if (cpu_has_feature(CPU_FTR_SPURR))
+		return mfspr(SPRN_SPURR);
 	if (cpu_has_feature(CPU_FTR_PURR))
 		return mfspr(SPRN_PURR);
-	return mftb();
+	return tb;
 }
 
+#ifdef CONFIG_PPC_SPLPAR
+
 /*
- * Read the SPURR on systems that have it, otherwise the purr
+ * Scan the dispatch trace log and count up the stolen time.
+ * Should be called with interrupts disabled.
  */
-static u64 read_spurr(u64 purr)
+static u64 scan_dispatch_log(u64 stop_tb)
 {
-	/*
-	 * cpus without PURR won't have a SPURR
-	 * We already know the former when we use this, so tell gcc
-	 */
-	if (cpu_has_feature(CPU_FTR_PURR) && cpu_has_feature(CPU_FTR_SPURR))
-		return mfspr(SPRN_SPURR);
-	return purr;
+	u64 i = local_paca->dtl_ridx;
+	struct dtl_entry *dtl = local_paca->dtl_curr;
+	struct dtl_entry *dtl_end = local_paca->dispatch_log_end;
+	struct lppaca *vpa = local_paca->lppaca_ptr;
+	u64 tb_delta;
+	u64 stolen = 0;
+	u64 dtb;
+
+	if (i == vpa->dtl_idx)
+		return 0;
+	while (i < vpa->dtl_idx) {
+		if (dtl_consumer)
+			dtl_consumer(dtl, i);
+		dtb = dtl->timebase;
+		tb_delta = dtl->enqueue_to_dispatch_time +
+			dtl->ready_to_enqueue_time;
+		barrier();
+		if (i + N_DISPATCH_LOG < vpa->dtl_idx) {
+			/* buffer has overflowed */
+			i = vpa->dtl_idx - N_DISPATCH_LOG;
+			dtl = local_paca->dispatch_log + (i % N_DISPATCH_LOG);
+			continue;
+		}
+		if (dtb > stop_tb)
+			break;
+		stolen += tb_delta;
+		++i;
+		++dtl;
+		if (dtl == dtl_end)
+			dtl = local_paca->dispatch_log;
+	}
+	local_paca->dtl_ridx = i;
+	local_paca->dtl_curr = dtl;
+	return stolen;
 }
 
 /*
+ * Accumulate stolen time by scanning the dispatch trace log.
+ * Called on entry from user mode.
+ */
+void accumulate_stolen_time(void)
+{
+	u64 sst, ust;
+
+	sst = scan_dispatch_log(get_paca()->starttime_user);
+	ust = scan_dispatch_log(get_paca()->starttime);
+	get_paca()->system_time -= sst;
+	get_paca()->user_time -= ust;
+	get_paca()->stolen_time += ust + sst;
+}
+
+static inline u64 calculate_stolen_time(u64 stop_tb)
+{
+	u64 stolen = 0;
+
+	if (get_paca()->dtl_ridx != get_paca()->lppaca_ptr->dtl_idx) {
+		stolen = scan_dispatch_log(stop_tb);
+		get_paca()->system_time -= stolen;
+	}
+
+	stolen += get_paca()->stolen_time;
+	get_paca()->stolen_time = 0;
+	return stolen;
+}
+
+#else /* CONFIG_PPC_SPLPAR */
+static inline u64 calculate_stolen_time(u64 stop_tb)
+{
+	return 0;
+}
+
+#endif /* CONFIG_PPC_SPLPAR */
+
+/*
  * Account time for a transition between system, hard irq
  * or soft irq state.
  */
 void account_system_vtime(struct task_struct *tsk)
 {
-	u64 now, nowscaled, delta, deltascaled, sys_time;
+	u64 now, nowscaled, delta, deltascaled;
 	unsigned long flags;
+	u64 stolen, udelta, sys_scaled, user_scaled;
 
 	local_irq_save(flags);
-	now = read_purr();
+	now = mftb();
 	nowscaled = read_spurr(now);
-	delta = now - get_paca()->startpurr;
+	get_paca()->system_time += now - get_paca()->starttime;
+	get_paca()->starttime = now;
 	deltascaled = nowscaled - get_paca()->startspurr;
-	get_paca()->startpurr = now;
 	get_paca()->startspurr = nowscaled;
-	if (!in_interrupt()) {
-		/* deltascaled includes both user and system time.
-		 * Hence scale it based on the purr ratio to estimate
-		 * the system time */
-		sys_time = get_paca()->system_time;
-		if (get_paca()->user_time)
-			deltascaled = deltascaled * sys_time /
-			     (sys_time + get_paca()->user_time);
-		delta += sys_time;
-		get_paca()->system_time = 0;
+
+	stolen = calculate_stolen_time(now);
+
+	delta = get_paca()->system_time;
+	get_paca()->system_time = 0;
+	udelta = get_paca()->user_time - get_paca()->utime_sspurr;
+	get_paca()->utime_sspurr = get_paca()->user_time;
+
+	/*
+	 * Because we don't read the SPURR on every kernel entry/exit,
+	 * deltascaled includes both user and system SPURR ticks.
+	 * Apportion these ticks to system SPURR ticks and user
+	 * SPURR ticks in the same ratio as the system time (delta)
+	 * and user time (udelta) values obtained from the timebase
+	 * over the same interval.  The system ticks get accounted here;
+	 * the user ticks get saved up in paca->user_time_scaled to be
+	 * used by account_process_tick.
+	 */
+	sys_scaled = delta;
+	user_scaled = udelta;
+	if (deltascaled != delta + udelta) {
+		if (udelta) {
+			sys_scaled = deltascaled * delta / (delta + udelta);
+			user_scaled = deltascaled - sys_scaled;
+		} else {
+			sys_scaled = deltascaled;
+		}
+	}
+	get_paca()->user_time_scaled += user_scaled;
+
+	if (in_irq() || idle_task(smp_processor_id()) != tsk) {
+		account_system_time(tsk, 0, delta, sys_scaled);
+		if (stolen)
+			account_steal_time(stolen);
+	} else {
+		account_idle_time(delta + stolen);
 	}
-	if (in_irq() || idle_task(smp_processor_id()) != tsk)
-		account_system_time(tsk, 0, delta, deltascaled);
-	else
-		account_idle_time(delta);
-	__get_cpu_var(cputime_last_delta) = delta;
-	__get_cpu_var(cputime_scaled_last_delta) = deltascaled;
 	local_irq_restore(flags);
 }
 EXPORT_SYMBOL_GPL(account_system_vtime);
@@ -265,125 +356,26 @@ EXPORT_SYMBOL_GPL(account_system_vtime);
  * by the exception entry and exit code to the generic process
  * user and system time records.
  * Must be called with interrupts disabled.
+ * Assumes that account_system_vtime() has been called recently
+ * (i.e. since the last entry from usermode) so that
+ * get_paca()->user_time_scaled is up to date.
  */
 void account_process_tick(struct task_struct *tsk, int user_tick)
 {
 	cputime_t utime, utimescaled;
 
 	utime = get_paca()->user_time;
+	utimescaled = get_paca()->user_time_scaled;
 	get_paca()->user_time = 0;
-	utimescaled = cputime_to_scaled(utime);
+	get_paca()->user_time_scaled = 0;
+	get_paca()->utime_sspurr = 0;
 	account_user_time(tsk, utime, utimescaled);
 }
 
-/*
- * Stuff for accounting stolen time.
- */
-struct cpu_purr_data {
-	int	initialized;			/* thread is running */
-	u64	tb;			/* last TB value read */
-	u64	purr;			/* last PURR value read */
-	u64	spurr;			/* last SPURR value read */
-};
-
-/*
- * Each entry in the cpu_purr_data array is manipulated only by its
- * "owner" cpu -- usually in the timer interrupt but also occasionally
- * in process context for cpu online.  As long as cpus do not touch
- * each others' cpu_purr_data, disabling local interrupts is
- * sufficient to serialize accesses.
- */
-static DEFINE_PER_CPU(struct cpu_purr_data, cpu_purr_data);
-
-static void snapshot_tb_and_purr(void *data)
-{
-	unsigned long flags;
-	struct cpu_purr_data *p = &__get_cpu_var(cpu_purr_data);
-
-	local_irq_save(flags);
-	p->tb = get_tb_or_rtc();
-	p->purr = mfspr(SPRN_PURR);
-	wmb();
-	p->initialized = 1;
-	local_irq_restore(flags);
-}
-
-/*
- * Called during boot when all cpus have come up.
- */
-void snapshot_timebases(void)
-{
-	if (!cpu_has_feature(CPU_FTR_PURR))
-		return;
-	on_each_cpu(snapshot_tb_and_purr, NULL, 1);
-}
-
-/*
- * Must be called with interrupts disabled.
- */
-void calculate_steal_time(void)
-{
-	u64 tb, purr;
-	s64 stolen;
-	struct cpu_purr_data *pme;
-
-	pme = &__get_cpu_var(cpu_purr_data);
-	if (!pme->initialized)
-		return;		/* !CPU_FTR_PURR or early in early boot */
-	tb = mftb();
-	purr = mfspr(SPRN_PURR);
-	stolen = (tb - pme->tb) - (purr - pme->purr);
-	if (stolen > 0) {
-		if (idle_task(smp_processor_id()) != current)
-			account_steal_time(stolen);
-		else
-			account_idle_time(stolen);
-	}
-	pme->tb = tb;
-	pme->purr = purr;
-}
-
-#ifdef CONFIG_PPC_SPLPAR
-/*
- * Must be called before the cpu is added to the online map when
- * a cpu is being brought up at runtime.
- */
-static void snapshot_purr(void)
-{
-	struct cpu_purr_data *pme;
-	unsigned long flags;
-
-	if (!cpu_has_feature(CPU_FTR_PURR))
-		return;
-	local_irq_save(flags);
-	pme = &__get_cpu_var(cpu_purr_data);
-	pme->tb = mftb();
-	pme->purr = mfspr(SPRN_PURR);
-	pme->initialized = 1;
-	local_irq_restore(flags);
-}
-
-#endif /* CONFIG_PPC_SPLPAR */
-
 #else /* ! CONFIG_VIRT_CPU_ACCOUNTING */
 #define calc_cputime_factors()
-#define calculate_steal_time()		do { } while (0)
 #endif
 
-#if !(defined(CONFIG_VIRT_CPU_ACCOUNTING) && defined(CONFIG_PPC_SPLPAR))
-#define snapshot_purr()			do { } while (0)
-#endif
-
-/*
- * Called when a cpu comes up after the system has finished booting,
- * i.e. as a result of a hotplug cpu action.
- */
-void snapshot_timebase(void)
-{
-	__get_cpu_var(last_jiffy) = get_tb_or_rtc();
-	snapshot_purr();
-}
-
 void __delay(unsigned long loops)
 {
 	unsigned long start;
@@ -585,8 +577,6 @@ void timer_interrupt(struct pt_regs * regs)
 	old_regs = set_irq_regs(regs);
 	irq_enter();
 
-	calculate_steal_time();
-
 	if (test_perf_event_pending()) {
 		clear_perf_event_pending();
 		perf_event_do_pending();
diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c
index 13002fe206e7..fd8728729abc 100644
--- a/arch/powerpc/kernel/vdso.c
+++ b/arch/powerpc/kernel/vdso.c
@@ -159,7 +159,7 @@ static void dump_vdso_pages(struct vm_area_struct * vma)
 {
 	int i;
 
-	if (!vma || test_thread_flag(TIF_32BIT)) {
+	if (!vma || is_32bit_task()) {
 		printk("vDSO32 @ %016lx:\n", (unsigned long)vdso32_kbase);
 		for (i=0; i<vdso32_pages; i++) {
 			struct page *pg = virt_to_page(vdso32_kbase +
@@ -170,7 +170,7 @@ static void dump_vdso_pages(struct vm_area_struct * vma)
 			dump_one_vdso_page(pg, upg);
 		}
 	}
-	if (!vma || !test_thread_flag(TIF_32BIT)) {
+	if (!vma || !is_32bit_task()) {
 		printk("vDSO64 @ %016lx:\n", (unsigned long)vdso64_kbase);
 		for (i=0; i<vdso64_pages; i++) {
 			struct page *pg = virt_to_page(vdso64_kbase +
@@ -200,7 +200,7 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 		return 0;
 
 #ifdef CONFIG_PPC64
-	if (test_thread_flag(TIF_32BIT)) {
+	if (is_32bit_task()) {
 		vdso_pagelist = vdso32_pagelist;
 		vdso_pages = vdso32_pages;
 		vdso_base = VDSO32_MBASE;
diff --git a/arch/powerpc/kvm/book3s_paired_singles.c b/arch/powerpc/kvm/book3s_paired_singles.c
index 474f2e24050a..35a701f3ece4 100644
--- a/arch/powerpc/kvm/book3s_paired_singles.c
+++ b/arch/powerpc/kvm/book3s_paired_singles.c
@@ -159,7 +159,7 @@
 
 static inline void kvmppc_sync_qpr(struct kvm_vcpu *vcpu, int rt)
 {
-	kvm_cvt_df(&vcpu->arch.fpr[rt], &vcpu->arch.qpr[rt], &vcpu->arch.fpscr);
+	kvm_cvt_df(&vcpu->arch.fpr[rt], &vcpu->arch.qpr[rt]);
 }
 
 static void kvmppc_inject_pf(struct kvm_vcpu *vcpu, ulong eaddr, bool is_store)
@@ -204,7 +204,7 @@ static int kvmppc_emulate_fpr_load(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	/* put in registers */
 	switch (ls_type) {
 	case FPU_LS_SINGLE:
-		kvm_cvt_fd((u32*)tmp, &vcpu->arch.fpr[rs], &vcpu->arch.fpscr);
+		kvm_cvt_fd((u32*)tmp, &vcpu->arch.fpr[rs]);
 		vcpu->arch.qpr[rs] = *((u32*)tmp);
 		break;
 	case FPU_LS_DOUBLE:
@@ -230,7 +230,7 @@ static int kvmppc_emulate_fpr_store(struct kvm_run *run, struct kvm_vcpu *vcpu,
 
 	switch (ls_type) {
 	case FPU_LS_SINGLE:
-		kvm_cvt_df(&vcpu->arch.fpr[rs], (u32*)tmp, &vcpu->arch.fpscr);
+		kvm_cvt_df(&vcpu->arch.fpr[rs], (u32*)tmp);
 		val = *((u32*)tmp);
 		len = sizeof(u32);
 		break;
@@ -296,7 +296,7 @@ static int kvmppc_emulate_psq_load(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	emulated = EMULATE_DONE;
 
 	/* put in registers */
-	kvm_cvt_fd(&tmp[0], &vcpu->arch.fpr[rs], &vcpu->arch.fpscr);
+	kvm_cvt_fd(&tmp[0], &vcpu->arch.fpr[rs]);
 	vcpu->arch.qpr[rs] = tmp[1];
 
 	dprintk(KERN_INFO "KVM: PSQ_LD [0x%x, 0x%x] at 0x%lx (%d)\n", tmp[0],
@@ -314,7 +314,7 @@ static int kvmppc_emulate_psq_store(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	u32 tmp[2];
 	int len = w ? sizeof(u32) : sizeof(u64);
 
-	kvm_cvt_df(&vcpu->arch.fpr[rs], &tmp[0], &vcpu->arch.fpscr);
+	kvm_cvt_df(&vcpu->arch.fpr[rs], &tmp[0]);
 	tmp[1] = vcpu->arch.qpr[rs];
 
 	r = kvmppc_st(vcpu, &addr, len, tmp, true);
@@ -516,9 +516,9 @@ static int kvmppc_ps_three_in(struct kvm_vcpu *vcpu, bool rc,
 	WARN_ON(rc);
 
 	/* PS0 */
-	kvm_cvt_df(&fpr[reg_in1], &ps0_in1, &vcpu->arch.fpscr);
-	kvm_cvt_df(&fpr[reg_in2], &ps0_in2, &vcpu->arch.fpscr);
-	kvm_cvt_df(&fpr[reg_in3], &ps0_in3, &vcpu->arch.fpscr);
+	kvm_cvt_df(&fpr[reg_in1], &ps0_in1);
+	kvm_cvt_df(&fpr[reg_in2], &ps0_in2);
+	kvm_cvt_df(&fpr[reg_in3], &ps0_in3);
 
 	if (scalar & SCALAR_LOW)
 		ps0_in2 = qpr[reg_in2];
@@ -529,7 +529,7 @@ static int kvmppc_ps_three_in(struct kvm_vcpu *vcpu, bool rc,
 			  ps0_in1, ps0_in2, ps0_in3, ps0_out);
 
 	if (!(scalar & SCALAR_NO_PS0))
-		kvm_cvt_fd(&ps0_out, &fpr[reg_out], &vcpu->arch.fpscr);
+		kvm_cvt_fd(&ps0_out, &fpr[reg_out]);
 
 	/* PS1 */
 	ps1_in1 = qpr[reg_in1];
@@ -566,12 +566,12 @@ static int kvmppc_ps_two_in(struct kvm_vcpu *vcpu, bool rc,
 	WARN_ON(rc);
 
 	/* PS0 */
-	kvm_cvt_df(&fpr[reg_in1], &ps0_in1, &vcpu->arch.fpscr);
+	kvm_cvt_df(&fpr[reg_in1], &ps0_in1);
 
 	if (scalar & SCALAR_LOW)
 		ps0_in2 = qpr[reg_in2];
 	else
-		kvm_cvt_df(&fpr[reg_in2], &ps0_in2, &vcpu->arch.fpscr);
+		kvm_cvt_df(&fpr[reg_in2], &ps0_in2);
 
 	func(&vcpu->arch.fpscr, &ps0_out, &ps0_in1, &ps0_in2);
 
@@ -579,7 +579,7 @@ static int kvmppc_ps_two_in(struct kvm_vcpu *vcpu, bool rc,
 		dprintk(KERN_INFO "PS2 ps0 -> f(0x%x, 0x%x) = 0x%x\n",
 				  ps0_in1, ps0_in2, ps0_out);
 
-		kvm_cvt_fd(&ps0_out, &fpr[reg_out], &vcpu->arch.fpscr);
+		kvm_cvt_fd(&ps0_out, &fpr[reg_out]);
 	}
 
 	/* PS1 */
@@ -615,13 +615,13 @@ static int kvmppc_ps_one_in(struct kvm_vcpu *vcpu, bool rc,
 	WARN_ON(rc);
 
 	/* PS0 */
-	kvm_cvt_df(&fpr[reg_in], &ps0_in, &vcpu->arch.fpscr);
+	kvm_cvt_df(&fpr[reg_in], &ps0_in);
 	func(&vcpu->arch.fpscr, &ps0_out, &ps0_in);
 
 	dprintk(KERN_INFO "PS1 ps0 -> f(0x%x) = 0x%x\n",
 			  ps0_in, ps0_out);
 
-	kvm_cvt_fd(&ps0_out, &fpr[reg_out], &vcpu->arch.fpscr);
+	kvm_cvt_fd(&ps0_out, &fpr[reg_out]);
 
 	/* PS1 */
 	ps1_in = qpr[reg_in];
@@ -671,7 +671,7 @@ int kvmppc_emulate_paired_single(struct kvm_run *run, struct kvm_vcpu *vcpu)
 #ifdef DEBUG
 	for (i = 0; i < ARRAY_SIZE(vcpu->arch.fpr); i++) {
 		u32 f;
-		kvm_cvt_df(&vcpu->arch.fpr[i], &f, &vcpu->arch.fpscr);
+		kvm_cvt_df(&vcpu->arch.fpr[i], &f);
 		dprintk(KERN_INFO "FPR[%d] = 0x%x / 0x%llx    QPR[%d] = 0x%x\n",
 			i, f, vcpu->arch.fpr[i], i, vcpu->arch.qpr[i]);
 	}
@@ -796,8 +796,7 @@ int kvmppc_emulate_paired_single(struct kvm_run *run, struct kvm_vcpu *vcpu)
 			vcpu->arch.fpr[ax_rd] = vcpu->arch.fpr[ax_ra];
 			/* vcpu->arch.qpr[ax_rd] = vcpu->arch.fpr[ax_rb]; */
 			kvm_cvt_df(&vcpu->arch.fpr[ax_rb],
-				   &vcpu->arch.qpr[ax_rd],
-				   &vcpu->arch.fpscr);
+				   &vcpu->arch.qpr[ax_rd]);
 			break;
 		case OP_4X_PS_MERGE01:
 			WARN_ON(rcomp);
@@ -808,19 +807,16 @@ int kvmppc_emulate_paired_single(struct kvm_run *run, struct kvm_vcpu *vcpu)
 			WARN_ON(rcomp);
 			/* vcpu->arch.fpr[ax_rd] = vcpu->arch.qpr[ax_ra]; */
 			kvm_cvt_fd(&vcpu->arch.qpr[ax_ra],
-				   &vcpu->arch.fpr[ax_rd],
-				   &vcpu->arch.fpscr);
+				   &vcpu->arch.fpr[ax_rd]);
 			/* vcpu->arch.qpr[ax_rd] = vcpu->arch.fpr[ax_rb]; */
 			kvm_cvt_df(&vcpu->arch.fpr[ax_rb],
-				   &vcpu->arch.qpr[ax_rd],
-				   &vcpu->arch.fpscr);
+				   &vcpu->arch.qpr[ax_rd]);
 			break;
 		case OP_4X_PS_MERGE11:
 			WARN_ON(rcomp);
 			/* vcpu->arch.fpr[ax_rd] = vcpu->arch.qpr[ax_ra]; */
 			kvm_cvt_fd(&vcpu->arch.qpr[ax_ra],
-				   &vcpu->arch.fpr[ax_rd],
-				   &vcpu->arch.fpscr);
+				   &vcpu->arch.fpr[ax_rd]);
 			vcpu->arch.qpr[ax_rd] = vcpu->arch.qpr[ax_rb];
 			break;
 		}
@@ -1255,7 +1251,7 @@ int kvmppc_emulate_paired_single(struct kvm_run *run, struct kvm_vcpu *vcpu)
 #ifdef DEBUG
 	for (i = 0; i < ARRAY_SIZE(vcpu->arch.fpr); i++) {
 		u32 f;
-		kvm_cvt_df(&vcpu->arch.fpr[i], &f, &vcpu->arch.fpscr);
+		kvm_cvt_df(&vcpu->arch.fpr[i], &f);
 		dprintk(KERN_INFO "FPR[%d] = 0x%x\n", i, f);
 	}
 #endif
diff --git a/arch/powerpc/kvm/fpu.S b/arch/powerpc/kvm/fpu.S
index cb34bbe16113..bf68d597549e 100644
--- a/arch/powerpc/kvm/fpu.S
+++ b/arch/powerpc/kvm/fpu.S
@@ -273,19 +273,11 @@ FPD_THREE_IN(fnmsub)
 FPD_THREE_IN(fnmadd)
 
 _GLOBAL(kvm_cvt_fd)
-	lfd	0,0(r5)			/* load up fpscr value */
-	MTFSF_L(0)
 	lfs	0,0(r3)
 	stfd	0,0(r4)
-	mffs	0
-	stfd	0,0(r5)			/* save new fpscr value */
 	blr
 
 _GLOBAL(kvm_cvt_df)
-	lfd	0,0(r5)			/* load up fpscr value */
-	MTFSF_L(0)
 	lfd	0,0(r3)
 	stfs	0,0(r4)
-	mffs	0
-	stfd	0,0(r5)			/* save new fpscr value */
 	blr
diff --git a/arch/powerpc/lib/Makefile b/arch/powerpc/lib/Makefile
index 5bb89c828070..ad4a36848f25 100644
--- a/arch/powerpc/lib/Makefile
+++ b/arch/powerpc/lib/Makefile
@@ -17,7 +17,8 @@ obj-$(CONFIG_PPC32)	+= div64.o copy_32.o
 obj-$(CONFIG_HAS_IOMEM)	+= devres.o
 
 obj-$(CONFIG_PPC64)	+= copypage_64.o copyuser_64.o \
-			   memcpy_64.o usercopy_64.o mem_64.o string.o
+			   memcpy_64.o usercopy_64.o mem_64.o string.o \
+			   checksum_wrappers_64.o
 obj-$(CONFIG_XMON)	+= sstep.o ldstfp.o
 obj-$(CONFIG_KPROBES)	+= sstep.o ldstfp.o
 obj-$(CONFIG_HAVE_HW_BREAKPOINT)	+= sstep.o ldstfp.o
diff --git a/arch/powerpc/lib/checksum_64.S b/arch/powerpc/lib/checksum_64.S
index ef96c6c58efc..18245af38aea 100644
--- a/arch/powerpc/lib/checksum_64.S
+++ b/arch/powerpc/lib/checksum_64.S
@@ -65,165 +65,393 @@ _GLOBAL(csum_tcpudp_magic)
 	srwi	r3,r3,16
 	blr
 
+#define STACKFRAMESIZE 256
+#define STK_REG(i)	(112 + ((i)-14)*8)
+
 /*
  * Computes the checksum of a memory block at buff, length len,
  * and adds in "sum" (32-bit).
  *
- * This code assumes at least halfword alignment, though the length
- * can be any number of bytes.  The sum is accumulated in r5.
- *
  * csum_partial(r3=buff, r4=len, r5=sum)
  */
 _GLOBAL(csum_partial)
-        subi	r3,r3,8		/* we'll offset by 8 for the loads */
-        srdi.	r6,r4,3         /* divide by 8 for doubleword count */
-        addic   r5,r5,0         /* clear carry */
-        beq	3f              /* if we're doing < 8 bytes */
-        andi.	r0,r3,2         /* aligned on a word boundary already? */
-        beq+	1f
-        lhz     r6,8(r3)        /* do 2 bytes to get aligned */
-        addi    r3,r3,2
-        subi    r4,r4,2
-        addc    r5,r5,r6
-        srdi.   r6,r4,3         /* recompute number of doublewords */
-        beq     3f              /* any left? */
-1:      mtctr   r6
-2:      ldu     r6,8(r3)        /* main sum loop */
-        adde    r5,r5,r6
-        bdnz    2b
-        andi.	r4,r4,7         /* compute bytes left to sum after doublewords */
-3:	cmpwi	0,r4,4		/* is at least a full word left? */
-	blt	4f
-	lwz	r6,8(r3)	/* sum this word */
+	addic	r0,r5,0			/* clear carry */
+
+	srdi.	r6,r4,3			/* less than 8 bytes? */
+	beq	.Lcsum_tail_word
+
+	/*
+	 * If only halfword aligned, align to a double word. Since odd
+	 * aligned addresses should be rare and they would require more
+	 * work to calculate the correct checksum, we ignore that case
+	 * and take the potential slowdown of unaligned loads.
+	 */
+	rldicl. r6,r3,64-1,64-2		/* r6 = (r3 & 0x3) >> 1 */
+	beq	.Lcsum_aligned
+
+	li	r7,4
+	sub	r6,r7,r6
+	mtctr	r6
+
+1:
+	lhz	r6,0(r3)		/* align to doubleword */
+	subi	r4,r4,2
+	addi	r3,r3,2
+	adde	r0,r0,r6
+	bdnz	1b
+
+.Lcsum_aligned:
+	/*
+	 * We unroll the loop such that each iteration is 64 bytes with an
+	 * entry and exit limb of 64 bytes, meaning a minimum size of
+	 * 128 bytes.
+	 */
+	srdi.	r6,r4,7
+	beq	.Lcsum_tail_doublewords		/* len < 128 */
+
+	srdi	r6,r4,6
+	subi	r6,r6,1
+	mtctr	r6
+
+	stdu	r1,-STACKFRAMESIZE(r1)
+	std	r14,STK_REG(r14)(r1)
+	std	r15,STK_REG(r15)(r1)
+	std	r16,STK_REG(r16)(r1)
+
+	ld	r6,0(r3)
+	ld	r9,8(r3)
+
+	ld	r10,16(r3)
+	ld	r11,24(r3)
+
+	/*
+	 * On POWER6 and POWER7 back to back addes take 2 cycles because of
+	 * the XER dependency. This means the fastest this loop can go is
+	 * 16 cycles per iteration. The scheduling of the loop below has
+	 * been shown to hit this on both POWER6 and POWER7.
+	 */
+	.align 5
+2:
+	adde	r0,r0,r6
+	ld	r12,32(r3)
+	ld	r14,40(r3)
+
+	adde	r0,r0,r9
+	ld	r15,48(r3)
+	ld	r16,56(r3)
+	addi	r3,r3,64
+
+	adde	r0,r0,r10
+
+	adde	r0,r0,r11
+
+	adde	r0,r0,r12
+
+	adde	r0,r0,r14
+
+	adde	r0,r0,r15
+	ld	r6,0(r3)
+	ld	r9,8(r3)
+
+	adde	r0,r0,r16
+	ld	r10,16(r3)
+	ld	r11,24(r3)
+	bdnz	2b
+
+
+	adde	r0,r0,r6
+	ld	r12,32(r3)
+	ld	r14,40(r3)
+
+	adde	r0,r0,r9
+	ld	r15,48(r3)
+	ld	r16,56(r3)
+	addi	r3,r3,64
+
+	adde	r0,r0,r10
+	adde	r0,r0,r11
+	adde	r0,r0,r12
+	adde	r0,r0,r14
+	adde	r0,r0,r15
+	adde	r0,r0,r16
+
+	ld	r14,STK_REG(r14)(r1)
+	ld	r15,STK_REG(r15)(r1)
+	ld	r16,STK_REG(r16)(r1)
+	addi	r1,r1,STACKFRAMESIZE
+
+	andi.	r4,r4,63
+
+.Lcsum_tail_doublewords:		/* Up to 127 bytes to go */
+	srdi.	r6,r4,3
+	beq	.Lcsum_tail_word
+
+	mtctr	r6
+3:
+	ld	r6,0(r3)
+	addi	r3,r3,8
+	adde	r0,r0,r6
+	bdnz	3b
+
+	andi.	r4,r4,7
+
+.Lcsum_tail_word:			/* Up to 7 bytes to go */
+	srdi.	r6,r4,2
+	beq	.Lcsum_tail_halfword
+
+	lwz	r6,0(r3)
 	addi	r3,r3,4
+	adde	r0,r0,r6
 	subi	r4,r4,4
-	adde	r5,r5,r6
-4:	cmpwi	0,r4,2		/* is at least a halfword left? */
-        blt+	5f
-        lhz     r6,8(r3)        /* sum this halfword */
-        addi    r3,r3,2
-        subi    r4,r4,2
-        adde    r5,r5,r6
-5:	cmpwi	0,r4,1		/* is at least a byte left? */
-        bne+    6f
-        lbz     r6,8(r3)        /* sum this byte */
-        slwi    r6,r6,8         /* this byte is assumed to be the upper byte of a halfword */
-        adde    r5,r5,r6
-6:      addze	r5,r5		/* add in final carry */
-	rldicl  r4,r5,32,0      /* fold two 32-bit halves together */
-        add     r3,r4,r5
-        srdi    r3,r3,32
-        blr
+
+.Lcsum_tail_halfword:			/* Up to 3 bytes to go */
+	srdi.	r6,r4,1
+	beq	.Lcsum_tail_byte
+
+	lhz	r6,0(r3)
+	addi	r3,r3,2
+	adde	r0,r0,r6
+	subi	r4,r4,2
+
+.Lcsum_tail_byte:			/* Up to 1 byte to go */
+	andi.	r6,r4,1
+	beq	.Lcsum_finish
+
+	lbz	r6,0(r3)
+	sldi	r9,r6,8			/* Pad the byte out to 16 bits */
+	adde	r0,r0,r9
+
+.Lcsum_finish:
+	addze	r0,r0			/* add in final carry */
+	rldicl	r4,r0,32,0		/* fold two 32 bit halves together */
+	add	r3,r4,r0
+	srdi	r3,r3,32
+	blr
+
+
+	.macro source
+100:
+	.section __ex_table,"a"
+	.align 3
+	.llong 100b,.Lsrc_error
+	.previous
+	.endm
+
+	.macro dest
+200:
+	.section __ex_table,"a"
+	.align 3
+	.llong 200b,.Ldest_error
+	.previous
+	.endm
 
 /*
  * Computes the checksum of a memory block at src, length len,
  * and adds in "sum" (32-bit), while copying the block to dst.
  * If an access exception occurs on src or dst, it stores -EFAULT
- * to *src_err or *dst_err respectively, and (for an error on
- * src) zeroes the rest of dst.
- *
- * This code needs to be reworked to take advantage of 64 bit sum+copy.
- * However, due to tokenring halfword alignment problems this will be very
- * tricky.  For now we'll leave it until we instrument it somehow.
+ * to *src_err or *dst_err respectively. The caller must take any action
+ * required in this case (zeroing memory, recalculating partial checksum etc).
  *
  * csum_partial_copy_generic(r3=src, r4=dst, r5=len, r6=sum, r7=src_err, r8=dst_err)
  */
 _GLOBAL(csum_partial_copy_generic)
-	addic	r0,r6,0
-	subi	r3,r3,4
-	subi	r4,r4,4
-	srwi.	r6,r5,2
-	beq	3f		/* if we're doing < 4 bytes */
-	andi.	r9,r4,2		/* Align dst to longword boundary */
-	beq+	1f
-81:	lhz	r6,4(r3)	/* do 2 bytes to get aligned */
-	addi	r3,r3,2
+	addic	r0,r6,0			/* clear carry */
+
+	srdi.	r6,r5,3			/* less than 8 bytes? */
+	beq	.Lcopy_tail_word
+
+	/*
+	 * If only halfword aligned, align to a double word. Since odd
+	 * aligned addresses should be rare and they would require more
+	 * work to calculate the correct checksum, we ignore that case
+	 * and take the potential slowdown of unaligned loads.
+	 *
+	 * If the source and destination are relatively unaligned we only
+	 * align the source. This keeps things simple.
+	 */
+	rldicl. r6,r3,64-1,64-2		/* r6 = (r3 & 0x3) >> 1 */
+	beq	.Lcopy_aligned
+
+	li	r7,4
+	sub	r6,r7,r6
+	mtctr	r6
+
+1:
+source;	lhz	r6,0(r3)		/* align to doubleword */
 	subi	r5,r5,2
-91:	sth	r6,4(r4)
-	addi	r4,r4,2
-	addc	r0,r0,r6
-	srwi.	r6,r5,2		/* # words to do */
-	beq	3f
-1:	mtctr	r6
-82:	lwzu	r6,4(r3)	/* the bdnz has zero overhead, so it should */
-92:	stwu	r6,4(r4)	/* be unnecessary to unroll this loop */
-	adde	r0,r0,r6
-	bdnz	82b
-	andi.	r5,r5,3
-3:	cmpwi	0,r5,2
-	blt+	4f
-83:	lhz	r6,4(r3)
 	addi	r3,r3,2
-	subi	r5,r5,2
-93:	sth	r6,4(r4)
+	adde	r0,r0,r6
+dest;	sth	r6,0(r4)
 	addi	r4,r4,2
+	bdnz	1b
+
+.Lcopy_aligned:
+	/*
+	 * We unroll the loop such that each iteration is 64 bytes with an
+	 * entry and exit limb of 64 bytes, meaning a minimum size of
+	 * 128 bytes.
+	 */
+	srdi.	r6,r5,7
+	beq	.Lcopy_tail_doublewords		/* len < 128 */
+
+	srdi	r6,r5,6
+	subi	r6,r6,1
+	mtctr	r6
+
+	stdu	r1,-STACKFRAMESIZE(r1)
+	std	r14,STK_REG(r14)(r1)
+	std	r15,STK_REG(r15)(r1)
+	std	r16,STK_REG(r16)(r1)
+
+source;	ld	r6,0(r3)
+source;	ld	r9,8(r3)
+
+source;	ld	r10,16(r3)
+source;	ld	r11,24(r3)
+
+	/*
+	 * On POWER6 and POWER7 back to back addes take 2 cycles because of
+	 * the XER dependency. This means the fastest this loop can go is
+	 * 16 cycles per iteration. The scheduling of the loop below has
+	 * been shown to hit this on both POWER6 and POWER7.
+	 */
+	.align 5
+2:
 	adde	r0,r0,r6
-4:	cmpwi	0,r5,1
-	bne+	5f
-84:	lbz	r6,4(r3)
-94:	stb	r6,4(r4)
-	slwi	r6,r6,8		/* Upper byte of word */
+source;	ld	r12,32(r3)
+source;	ld	r14,40(r3)
+
+	adde	r0,r0,r9
+source;	ld	r15,48(r3)
+source;	ld	r16,56(r3)
+	addi	r3,r3,64
+
+	adde	r0,r0,r10
+dest;	std	r6,0(r4)
+dest;	std	r9,8(r4)
+
+	adde	r0,r0,r11
+dest;	std	r10,16(r4)
+dest;	std	r11,24(r4)
+
+	adde	r0,r0,r12
+dest;	std	r12,32(r4)
+dest;	std	r14,40(r4)
+
+	adde	r0,r0,r14
+dest;	std	r15,48(r4)
+dest;	std	r16,56(r4)
+	addi	r4,r4,64
+
+	adde	r0,r0,r15
+source;	ld	r6,0(r3)
+source;	ld	r9,8(r3)
+
+	adde	r0,r0,r16
+source;	ld	r10,16(r3)
+source;	ld	r11,24(r3)
+	bdnz	2b
+
+
 	adde	r0,r0,r6
-5:	addze	r3,r0		/* add in final carry (unlikely with 64-bit regs) */
-        rldicl  r4,r3,32,0      /* fold 64 bit value */
-        add     r3,r4,r3
-        srdi    r3,r3,32
-	blr
+source;	ld	r12,32(r3)
+source;	ld	r14,40(r3)
 
-/* These shouldn't go in the fixup section, since that would
-   cause the ex_table addresses to get out of order. */
+	adde	r0,r0,r9
+source;	ld	r15,48(r3)
+source;	ld	r16,56(r3)
+	addi	r3,r3,64
+
+	adde	r0,r0,r10
+dest;	std	r6,0(r4)
+dest;	std	r9,8(r4)
+
+	adde	r0,r0,r11
+dest;	std	r10,16(r4)
+dest;	std	r11,24(r4)
+
+	adde	r0,r0,r12
+dest;	std	r12,32(r4)
+dest;	std	r14,40(r4)
+
+	adde	r0,r0,r14
+dest;	std	r15,48(r4)
+dest;	std	r16,56(r4)
+	addi	r4,r4,64
+
+	adde	r0,r0,r15
+	adde	r0,r0,r16
+
+	ld	r14,STK_REG(r14)(r1)
+	ld	r15,STK_REG(r15)(r1)
+	ld	r16,STK_REG(r16)(r1)
+	addi	r1,r1,STACKFRAMESIZE
+
+	andi.	r5,r5,63
+
+.Lcopy_tail_doublewords:		/* Up to 127 bytes to go */
+	srdi.	r6,r5,3
+	beq	.Lcopy_tail_word
 
-	.globl src_error_1
-src_error_1:
-	li	r6,0
-	subi	r5,r5,2
-95:	sth	r6,4(r4)
-	addi	r4,r4,2
-	srwi.	r6,r5,2
-	beq	3f
 	mtctr	r6
-	.globl src_error_2
-src_error_2:
-	li	r6,0
-96:	stwu	r6,4(r4)
-	bdnz	96b
-3:	andi.	r5,r5,3
-	beq	src_error
-	.globl src_error_3
-src_error_3:
-	li	r6,0
-	mtctr	r5
-	addi	r4,r4,3
-97:	stbu	r6,1(r4)
-	bdnz	97b
-	.globl src_error
-src_error:
+3:
+source;	ld	r6,0(r3)
+	addi	r3,r3,8
+	adde	r0,r0,r6
+dest;	std	r6,0(r4)
+	addi	r4,r4,8
+	bdnz	3b
+
+	andi.	r5,r5,7
+
+.Lcopy_tail_word:			/* Up to 7 bytes to go */
+	srdi.	r6,r5,2
+	beq	.Lcopy_tail_halfword
+
+source;	lwz	r6,0(r3)
+	addi	r3,r3,4
+	adde	r0,r0,r6
+dest;	stw	r6,0(r4)
+	addi	r4,r4,4
+	subi	r5,r5,4
+
+.Lcopy_tail_halfword:			/* Up to 3 bytes to go */
+	srdi.	r6,r5,1
+	beq	.Lcopy_tail_byte
+
+source;	lhz	r6,0(r3)
+	addi	r3,r3,2
+	adde	r0,r0,r6
+dest;	sth	r6,0(r4)
+	addi	r4,r4,2
+	subi	r5,r5,2
+
+.Lcopy_tail_byte:			/* Up to 1 byte to go */
+	andi.	r6,r5,1
+	beq	.Lcopy_finish
+
+source;	lbz	r6,0(r3)
+	sldi	r9,r6,8			/* Pad the byte out to 16 bits */
+	adde	r0,r0,r9
+dest;	stb	r6,0(r4)
+
+.Lcopy_finish:
+	addze	r0,r0			/* add in final carry */
+	rldicl	r4,r0,32,0		/* fold two 32 bit halves together */
+	add	r3,r4,r0
+	srdi	r3,r3,32
+	blr
+
+.Lsrc_error:
 	cmpdi	0,r7,0
-	beq	1f
+	beqlr
 	li	r6,-EFAULT
 	stw	r6,0(r7)
-1:	addze	r3,r0
 	blr
 
-	.globl dst_error
-dst_error:
+.Ldest_error:
 	cmpdi	0,r8,0
-	beq	1f
+	beqlr
 	li	r6,-EFAULT
 	stw	r6,0(r8)
-1:	addze	r3,r0
 	blr
-
-.section __ex_table,"a"
-	.align  3
-	.llong	81b,src_error_1
-	.llong	91b,dst_error
-	.llong	82b,src_error_2
-	.llong	92b,dst_error
-	.llong	83b,src_error_3
-	.llong	93b,dst_error
-	.llong	84b,src_error_3
-	.llong	94b,dst_error
-	.llong	95b,dst_error
-	.llong	96b,dst_error
-	.llong	97b,dst_error
diff --git a/arch/powerpc/lib/checksum_wrappers_64.c b/arch/powerpc/lib/checksum_wrappers_64.c
new file mode 100644
index 000000000000..769b817fbb32
--- /dev/null
+++ b/arch/powerpc/lib/checksum_wrappers_64.c
@@ -0,0 +1,102 @@
+/*
+ * 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 <linux/module.h>
+#include <linux/compiler.h>
+#include <linux/types.h>
+#include <asm/checksum.h>
+#include <asm/uaccess.h>
+
+__wsum csum_and_copy_from_user(const void __user *src, void *dst,
+			       int len, __wsum sum, int *err_ptr)
+{
+	unsigned int csum;
+
+	might_sleep();
+
+	*err_ptr = 0;
+
+	if (!len) {
+		csum = 0;
+		goto out;
+	}
+
+	if (unlikely((len < 0) || !access_ok(VERIFY_READ, src, len))) {
+		*err_ptr = -EFAULT;
+		csum = (__force unsigned int)sum;
+		goto out;
+	}
+
+	csum = csum_partial_copy_generic((void __force *)src, dst,
+					 len, sum, err_ptr, NULL);
+
+	if (unlikely(*err_ptr)) {
+		int missing = __copy_from_user(dst, src, len);
+
+		if (missing) {
+			memset(dst + len - missing, 0, missing);
+			*err_ptr = -EFAULT;
+		} else {
+			*err_ptr = 0;
+		}
+
+		csum = csum_partial(dst, len, sum);
+	}
+
+out:
+	return (__force __wsum)csum;
+}
+EXPORT_SYMBOL(csum_and_copy_from_user);
+
+__wsum csum_and_copy_to_user(const void *src, void __user *dst, int len,
+			     __wsum sum, int *err_ptr)
+{
+	unsigned int csum;
+
+	might_sleep();
+
+	*err_ptr = 0;
+
+	if (!len) {
+		csum = 0;
+		goto out;
+	}
+
+	if (unlikely((len < 0) || !access_ok(VERIFY_WRITE, dst, len))) {
+		*err_ptr = -EFAULT;
+		csum = -1; /* invalid checksum */
+		goto out;
+	}
+
+	csum = csum_partial_copy_generic(src, (void __force *)dst,
+					 len, sum, NULL, err_ptr);
+
+	if (unlikely(*err_ptr)) {
+		csum = csum_partial(src, len, sum);
+
+		if (copy_to_user(dst, src, len)) {
+			*err_ptr = -EFAULT;
+			csum = -1; /* invalid checksum */
+		}
+	}
+
+out:
+	return (__force __wsum)csum;
+}
+EXPORT_SYMBOL(csum_and_copy_to_user);
diff --git a/arch/powerpc/lib/copy_32.S b/arch/powerpc/lib/copy_32.S
index 74a7f4130b4c..55f19f9fd708 100644
--- a/arch/powerpc/lib/copy_32.S
+++ b/arch/powerpc/lib/copy_32.S
@@ -62,7 +62,7 @@
 
 	.text
 	.stabs	"arch/powerpc/lib/",N_SO,0,0,0f
-	.stabs	"copy32.S",N_SO,0,0,0f
+	.stabs	"copy_32.S",N_SO,0,0,0f
 0:
 
 CACHELINE_BYTES = L1_CACHE_BYTES
diff --git a/arch/powerpc/lib/ldstfp.S b/arch/powerpc/lib/ldstfp.S
index f6448636baf5..6a85380520b6 100644
--- a/arch/powerpc/lib/ldstfp.S
+++ b/arch/powerpc/lib/ldstfp.S
@@ -17,6 +17,8 @@
 #include <asm/asm-offsets.h>
 #include <linux/errno.h>
 
+#ifdef CONFIG_PPC_FPU
+
 #define STKFRM	(PPC_MIN_STKFRM + 16)
 
 	.macro	extab	instr,handler
@@ -81,7 +83,7 @@ _GLOBAL(do_lfs)
 	mfmsr	r6
 	ori	r7,r6,MSR_FP
 	cmpwi	cr7,r3,0
-	mtmsrd	r7
+	MTMSRD(r7)
 	isync
 	beq	cr7,1f
 	stfd	fr0,STKFRM-16(r1)
@@ -93,7 +95,7 @@ _GLOBAL(do_lfs)
 	lfd	fr0,STKFRM-16(r1)
 4:	PPC_LL	r0,STKFRM+PPC_LR_STKOFF(r1)
 	mtlr	r0
-	mtmsrd	r6
+	MTMSRD(r6)
 	isync
 	mr	r3,r9
 	addi	r1,r1,STKFRM
@@ -108,7 +110,7 @@ _GLOBAL(do_lfd)
 	mfmsr	r6
 	ori	r7,r6,MSR_FP
 	cmpwi	cr7,r3,0
-	mtmsrd	r7
+	MTMSRD(r7)
 	isync
 	beq	cr7,1f
 	stfd	fr0,STKFRM-16(r1)
@@ -120,7 +122,7 @@ _GLOBAL(do_lfd)
 	lfd	fr0,STKFRM-16(r1)
 4:	PPC_LL	r0,STKFRM+PPC_LR_STKOFF(r1)
 	mtlr	r0
-	mtmsrd	r6
+	MTMSRD(r6)
 	isync
 	mr	r3,r9
 	addi	r1,r1,STKFRM
@@ -135,7 +137,7 @@ _GLOBAL(do_stfs)
 	mfmsr	r6
 	ori	r7,r6,MSR_FP
 	cmpwi	cr7,r3,0
-	mtmsrd	r7
+	MTMSRD(r7)
 	isync
 	beq	cr7,1f
 	stfd	fr0,STKFRM-16(r1)
@@ -147,7 +149,7 @@ _GLOBAL(do_stfs)
 	lfd	fr0,STKFRM-16(r1)
 4:	PPC_LL	r0,STKFRM+PPC_LR_STKOFF(r1)
 	mtlr	r0
-	mtmsrd	r6
+	MTMSRD(r6)
 	isync
 	mr	r3,r9
 	addi	r1,r1,STKFRM
@@ -162,7 +164,7 @@ _GLOBAL(do_stfd)
 	mfmsr	r6
 	ori	r7,r6,MSR_FP
 	cmpwi	cr7,r3,0
-	mtmsrd	r7
+	MTMSRD(r7)
 	isync
 	beq	cr7,1f
 	stfd	fr0,STKFRM-16(r1)
@@ -174,7 +176,7 @@ _GLOBAL(do_stfd)
 	lfd	fr0,STKFRM-16(r1)
 4:	PPC_LL	r0,STKFRM+PPC_LR_STKOFF(r1)
 	mtlr	r0
-	mtmsrd	r6
+	MTMSRD(r6)
 	isync
 	mr	r3,r9
 	addi	r1,r1,STKFRM
@@ -229,7 +231,7 @@ _GLOBAL(do_lvx)
 	oris	r7,r6,MSR_VEC@h
 	cmpwi	cr7,r3,0
 	li	r8,STKFRM-16
-	mtmsrd	r7
+	MTMSRD(r7)
 	isync
 	beq	cr7,1f
 	stvx	vr0,r1,r8
@@ -241,7 +243,7 @@ _GLOBAL(do_lvx)
 	lvx	vr0,r1,r8
 4:	PPC_LL	r0,STKFRM+PPC_LR_STKOFF(r1)
 	mtlr	r0
-	mtmsrd	r6
+	MTMSRD(r6)
 	isync
 	mr	r3,r9
 	addi	r1,r1,STKFRM
@@ -257,7 +259,7 @@ _GLOBAL(do_stvx)
 	oris	r7,r6,MSR_VEC@h
 	cmpwi	cr7,r3,0
 	li	r8,STKFRM-16
-	mtmsrd	r7
+	MTMSRD(r7)
 	isync
 	beq	cr7,1f
 	stvx	vr0,r1,r8
@@ -269,7 +271,7 @@ _GLOBAL(do_stvx)
 	lvx	vr0,r1,r8
 4:	PPC_LL	r0,STKFRM+PPC_LR_STKOFF(r1)
 	mtlr	r0
-	mtmsrd	r6
+	MTMSRD(r6)
 	isync
 	mr	r3,r9
 	addi	r1,r1,STKFRM
@@ -325,7 +327,7 @@ _GLOBAL(do_lxvd2x)
 	oris	r7,r6,MSR_VSX@h
 	cmpwi	cr7,r3,0
 	li	r8,STKFRM-16
-	mtmsrd	r7
+	MTMSRD(r7)
 	isync
 	beq	cr7,1f
 	STXVD2X(0,r1,r8)
@@ -337,7 +339,7 @@ _GLOBAL(do_lxvd2x)
 	LXVD2X(0,r1,r8)
 4:	PPC_LL	r0,STKFRM+PPC_LR_STKOFF(r1)
 	mtlr	r0
-	mtmsrd	r6
+	MTMSRD(r6)
 	isync
 	mr	r3,r9
 	addi	r1,r1,STKFRM
@@ -353,7 +355,7 @@ _GLOBAL(do_stxvd2x)
 	oris	r7,r6,MSR_VSX@h
 	cmpwi	cr7,r3,0
 	li	r8,STKFRM-16
-	mtmsrd	r7
+	MTMSRD(r7)
 	isync
 	beq	cr7,1f
 	STXVD2X(0,r1,r8)
@@ -365,7 +367,7 @@ _GLOBAL(do_stxvd2x)
 	LXVD2X(0,r1,r8)
 4:	PPC_LL	r0,STKFRM+PPC_LR_STKOFF(r1)
 	mtlr	r0
-	mtmsrd	r6
+	MTMSRD(r6)
 	isync
 	mr	r3,r9
 	addi	r1,r1,STKFRM
@@ -373,3 +375,5 @@ _GLOBAL(do_stxvd2x)
 	extab	2b,3b
 
 #endif /* CONFIG_VSX */
+
+#endif	/* CONFIG_PPC_FPU */
diff --git a/arch/powerpc/lib/locks.c b/arch/powerpc/lib/locks.c
index 58e14fba11b1..9b8182e82166 100644
--- a/arch/powerpc/lib/locks.c
+++ b/arch/powerpc/lib/locks.c
@@ -34,7 +34,7 @@ void __spin_yield(arch_spinlock_t *lock)
 		return;
 	holder_cpu = lock_value & 0xffff;
 	BUG_ON(holder_cpu >= NR_CPUS);
-	yield_count = lppaca[holder_cpu].yield_count;
+	yield_count = lppaca_of(holder_cpu).yield_count;
 	if ((yield_count & 1) == 0)
 		return;		/* virtual cpu is currently running */
 	rmb();
@@ -65,7 +65,7 @@ void __rw_yield(arch_rwlock_t *rw)
 		return;		/* no write lock at present */
 	holder_cpu = lock_value & 0xffff;
 	BUG_ON(holder_cpu >= NR_CPUS);
-	yield_count = lppaca[holder_cpu].yield_count;
+	yield_count = lppaca_of(holder_cpu).yield_count;
 	if ((yield_count & 1) == 0)
 		return;		/* virtual cpu is currently running */
 	rmb();
diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c
index e0a9858d537e..ae5189ab0049 100644
--- a/arch/powerpc/lib/sstep.c
+++ b/arch/powerpc/lib/sstep.c
@@ -30,6 +30,7 @@ extern char system_call_common[];
 #define XER_OV		0x40000000U
 #define XER_CA		0x20000000U
 
+#ifdef CONFIG_PPC_FPU
 /*
  * Functions in ldstfp.S
  */
@@ -41,6 +42,7 @@ extern int do_lvx(int rn, unsigned long ea);
 extern int do_stvx(int rn, unsigned long ea);
 extern int do_lxvd2x(int rn, unsigned long ea);
 extern int do_stxvd2x(int rn, unsigned long ea);
+#endif
 
 /*
  * Determine whether a conditional branch instruction would branch.
@@ -290,6 +292,7 @@ static int __kprobes write_mem(unsigned long val, unsigned long ea, int nb,
 	return write_mem_unaligned(val, ea, nb, regs);
 }
 
+#ifdef CONFIG_PPC_FPU
 /*
  * Check the address and alignment, and call func to do the actual
  * load or store.
@@ -351,6 +354,7 @@ static int __kprobes do_fp_store(int rn, int (*func)(int, unsigned long),
 	}
 	return err;
 }
+#endif
 
 #ifdef CONFIG_ALTIVEC
 /* For Altivec/VMX, no need to worry about alignment */
@@ -1393,6 +1397,7 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
 				regs->gpr[rd] = byterev_4(val);
 			goto ldst_done;
 
+#ifdef CONFIG_PPC_CPU
 		case 535:	/* lfsx */
 		case 567:	/* lfsux */
 			if (!(regs->msr & MSR_FP))
@@ -1424,6 +1429,7 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
 			ea = xform_ea(instr, regs, u);
 			err = do_fp_store(rd, do_stfd, ea, 8, regs);
 			goto ldst_done;
+#endif
 
 #ifdef __powerpc64__
 		case 660:	/* stdbrx */
@@ -1534,6 +1540,7 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
 		} while (++rd < 32);
 		goto instr_done;
 
+#ifdef CONFIG_PPC_FPU
 	case 48:	/* lfs */
 	case 49:	/* lfsu */
 		if (!(regs->msr & MSR_FP))
@@ -1565,6 +1572,7 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
 		ea = dform_ea(instr, regs);
 		err = do_fp_store(rd, do_stfd, ea, 8, regs);
 		goto ldst_done;
+#endif
 
 #ifdef __powerpc64__
 	case 58:	/* ld[u], lwa */
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index 1bd712c33ce2..54f4fb994e99 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -30,6 +30,7 @@
 #include <linux/kprobes.h>
 #include <linux/kdebug.h>
 #include <linux/perf_event.h>
+#include <linux/magic.h>
 
 #include <asm/firmware.h>
 #include <asm/page.h>
@@ -385,6 +386,7 @@ do_sigbus:
 void bad_page_fault(struct pt_regs *regs, unsigned long address, int sig)
 {
 	const struct exception_table_entry *entry;
+	unsigned long *stackend;
 
 	/* Are we prepared to handle this fault?  */
 	if ((entry = search_exception_tables(regs->nip)) != NULL) {
@@ -413,5 +415,9 @@ void bad_page_fault(struct pt_regs *regs, unsigned long address, int sig)
 	printk(KERN_ALERT "Faulting instruction address: 0x%08lx\n",
 		regs->nip);
 
+	stackend = end_of_stack(current);
+	if (current != &init_task && *stackend != STACK_END_MAGIC)
+		printk(KERN_ALERT "Thread overran stack, or stack corrupted\n");
+
 	die("Kernel access of bad area", regs, sig);
 }
diff --git a/arch/powerpc/mm/mmu_context_nohash.c b/arch/powerpc/mm/mmu_context_nohash.c
index ddfd7ad4e1d6..5ce99848d91e 100644
--- a/arch/powerpc/mm/mmu_context_nohash.c
+++ b/arch/powerpc/mm/mmu_context_nohash.c
@@ -334,7 +334,7 @@ static int __cpuinit mmu_context_cpu_notify(struct notifier_block *self,
 	/* We don't touch CPU 0 map, it's allocated at aboot and kept
 	 * around forever
 	 */
-	if (cpu == 0)
+	if (cpu == boot_cpuid)
 		return NOTIFY_OK;
 
 	switch (action) {
@@ -420,9 +420,11 @@ void __init mmu_context_init(void)
 	 */
 	context_map = alloc_bootmem(CTX_MAP_SIZE);
 	context_mm = alloc_bootmem(sizeof(void *) * (last_context + 1));
+#ifndef CONFIG_SMP
 	stale_map[0] = alloc_bootmem(CTX_MAP_SIZE);
+#else
+	stale_map[boot_cpuid] = alloc_bootmem(CTX_MAP_SIZE);
 
-#ifdef CONFIG_SMP
 	register_cpu_notifier(&mmu_context_cpu_nb);
 #endif
 
diff --git a/arch/powerpc/oprofile/backtrace.c b/arch/powerpc/oprofile/backtrace.c
index b4278cfd1f80..f75301f2c85f 100644
--- a/arch/powerpc/oprofile/backtrace.c
+++ b/arch/powerpc/oprofile/backtrace.c
@@ -105,7 +105,7 @@ void op_powerpc_backtrace(struct pt_regs * const regs, unsigned int depth)
 		}
 	} else {
 #ifdef CONFIG_PPC64
-		if (!test_thread_flag(TIF_32BIT)) {
+		if (!is_32bit_task()) {
 			while (depth--) {
 				sp = user_getsp64(sp, first_frame);
 				if (!sp)
diff --git a/arch/powerpc/platforms/cell/ras.c b/arch/powerpc/platforms/cell/ras.c
index 1d3c4effea10..5ec1e47a0d77 100644
--- a/arch/powerpc/platforms/cell/ras.c
+++ b/arch/powerpc/platforms/cell/ras.c
@@ -173,8 +173,10 @@ static int __init cbe_ptcal_enable(void)
 		return -ENODEV;
 
 	size = of_get_property(np, "ibm,cbe-ptcal-size", NULL);
-	if (!size)
+	if (!size) {
+		of_node_put(np);
 		return -ENODEV;
+	}
 
 	pr_debug("%s: enabling PTCAL, size = 0x%x\n", __func__, *size);
 	order = get_order(*size);
diff --git a/arch/powerpc/platforms/cell/spider-pic.c b/arch/powerpc/platforms/cell/spider-pic.c
index 5876e888e412..3f2e557344a3 100644
--- a/arch/powerpc/platforms/cell/spider-pic.c
+++ b/arch/powerpc/platforms/cell/spider-pic.c
@@ -258,8 +258,10 @@ static unsigned int __init spider_find_cascade_and_node(struct spider_pic *pic)
 		return NO_IRQ;
 	imap += intsize + 1;
 	tmp = of_get_property(iic, "#interrupt-cells", NULL);
-	if (tmp == NULL)
+	if (tmp == NULL) {
+		of_node_put(iic);
 		return NO_IRQ;
+	}
 	intsize = *tmp;
 	/* Assume unit is last entry of interrupt specifier */
 	unit = imap[intsize - 1];
diff --git a/arch/powerpc/platforms/chrp/nvram.c b/arch/powerpc/platforms/chrp/nvram.c
index ba3588f2d8e0..d3ceff04ffc7 100644
--- a/arch/powerpc/platforms/chrp/nvram.c
+++ b/arch/powerpc/platforms/chrp/nvram.c
@@ -74,8 +74,10 @@ void __init chrp_nvram_init(void)
 		return;
 
 	nbytes_p = of_get_property(nvram, "#bytes", &proplen);
-	if (nbytes_p == NULL || proplen != sizeof(unsigned int))
+	if (nbytes_p == NULL || proplen != sizeof(unsigned int)) {
+		of_node_put(nvram);
 		return;
+	}
 
 	nvram_size = *nbytes_p;
 
diff --git a/arch/powerpc/platforms/iseries/dt.c b/arch/powerpc/platforms/iseries/dt.c
index 7f45a51fe793..fdb7384c0c4f 100644
--- a/arch/powerpc/platforms/iseries/dt.c
+++ b/arch/powerpc/platforms/iseries/dt.c
@@ -243,7 +243,7 @@ static void __init dt_cpus(struct iseries_flat_dt *dt)
 	pft_size[1] = __ilog2(HvCallHpt_getHptPages() * HW_PAGE_SIZE);
 
 	for (i = 0; i < NR_CPUS; i++) {
-		if (lppaca[i].dyn_proc_status >= 2)
+		if (lppaca_of(i).dyn_proc_status >= 2)
 			continue;
 
 		snprintf(p, 32 - (p - buf), "@%d", i);
@@ -251,7 +251,7 @@ static void __init dt_cpus(struct iseries_flat_dt *dt)
 
 		dt_prop_str(dt, "device_type", device_type_cpu);
 
-		index = lppaca[i].dyn_hv_phys_proc_index;
+		index = lppaca_of(i).dyn_hv_phys_proc_index;
 		d = &xIoHriProcessorVpd[index];
 
 		dt_prop_u32(dt, "i-cache-size", d->xInstCacheSize * 1024);
diff --git a/arch/powerpc/platforms/iseries/smp.c b/arch/powerpc/platforms/iseries/smp.c
index 6590850045af..6c6029914dbc 100644
--- a/arch/powerpc/platforms/iseries/smp.c
+++ b/arch/powerpc/platforms/iseries/smp.c
@@ -91,7 +91,7 @@ static void smp_iSeries_kick_cpu(int nr)
 	BUG_ON((nr < 0) || (nr >= NR_CPUS));
 
 	/* Verify that our partition has a processor nr */
-	if (lppaca[nr].dyn_proc_status >= 2)
+	if (lppaca_of(nr).dyn_proc_status >= 2)
 		return;
 
 	/* The processor is currently spinning, waiting
diff --git a/arch/powerpc/platforms/maple/setup.c b/arch/powerpc/platforms/maple/setup.c
index 3fff8d979b41..fe34c3d9bb74 100644
--- a/arch/powerpc/platforms/maple/setup.c
+++ b/arch/powerpc/platforms/maple/setup.c
@@ -358,6 +358,7 @@ static int __init maple_cpc925_edac_setup(void)
 	model = (const unsigned char *)of_get_property(np, "model", NULL);
 	if (!model) {
 		printk(KERN_ERR "%s: Unabel to get model info\n", __func__);
+		of_node_put(np);
 		return -ENODEV;
 	}
 
diff --git a/arch/powerpc/platforms/powermac/pfunc_core.c b/arch/powerpc/platforms/powermac/pfunc_core.c
index cec635942657..b0c3777528a1 100644
--- a/arch/powerpc/platforms/powermac/pfunc_core.c
+++ b/arch/powerpc/platforms/powermac/pfunc_core.c
@@ -837,8 +837,10 @@ struct pmf_function *__pmf_find_function(struct device_node *target,
 		return NULL;
  find_it:
 	dev = pmf_find_device(actor);
-	if (dev == NULL)
-		return NULL;
+	if (dev == NULL) {
+		result = NULL;
+		goto out;
+	}
 
 	list_for_each_entry(func, &dev->functions, link) {
 		if (name && strcmp(name, func->name))
@@ -850,8 +852,9 @@ struct pmf_function *__pmf_find_function(struct device_node *target,
 		result = func;
 		break;
 	}
-	of_node_put(actor);
 	pmf_put_device(dev);
+out:
+	of_node_put(actor);
 	return result;
 }
 
diff --git a/arch/powerpc/platforms/pseries/dtl.c b/arch/powerpc/platforms/pseries/dtl.c
index a00addb55945..c371bc06434b 100644
--- a/arch/powerpc/platforms/pseries/dtl.c
+++ b/arch/powerpc/platforms/pseries/dtl.c
@@ -23,37 +23,22 @@
 #include <linux/init.h>
 #include <linux/slab.h>
 #include <linux/debugfs.h>
+#include <linux/spinlock.h>
 #include <asm/smp.h>
 #include <asm/system.h>
 #include <asm/uaccess.h>
 #include <asm/firmware.h>
+#include <asm/lppaca.h>
 
 #include "plpar_wrappers.h"
 
-/*
- * Layout of entries in the hypervisor's DTL buffer. Although we don't
- * actually access the internals of an entry (we only need to know the size),
- * we might as well define it here for reference.
- */
-struct dtl_entry {
-	u8	dispatch_reason;
-	u8	preempt_reason;
-	u16	processor_id;
-	u32	enqueue_to_dispatch_time;
-	u32	ready_to_enqueue_time;
-	u32	waiting_to_ready_time;
-	u64	timebase;
-	u64	fault_addr;
-	u64	srr0;
-	u64	srr1;
-};
-
 struct dtl {
 	struct dtl_entry	*buf;
 	struct dentry		*file;
 	int			cpu;
 	int			buf_entries;
 	u64			last_idx;
+	spinlock_t		lock;
 };
 static DEFINE_PER_CPU(struct dtl, cpu_dtl);
 
@@ -72,25 +57,97 @@ static u8 dtl_event_mask = 0x7;
 static int dtl_buf_entries = (16 * 85);
 
 
-static int dtl_enable(struct dtl *dtl)
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING
+struct dtl_ring {
+	u64	write_index;
+	struct dtl_entry *write_ptr;
+	struct dtl_entry *buf;
+	struct dtl_entry *buf_end;
+	u8	saved_dtl_mask;
+};
+
+static DEFINE_PER_CPU(struct dtl_ring, dtl_rings);
+
+static atomic_t dtl_count;
+
+/*
+ * The cpu accounting code controls the DTL ring buffer, and we get
+ * given entries as they are processed.
+ */
+static void consume_dtle(struct dtl_entry *dtle, u64 index)
 {
-	unsigned long addr;
-	int ret, hwcpu;
+	struct dtl_ring *dtlr = &__get_cpu_var(dtl_rings);
+	struct dtl_entry *wp = dtlr->write_ptr;
+	struct lppaca *vpa = local_paca->lppaca_ptr;
 
-	/* only allow one reader */
-	if (dtl->buf)
-		return -EBUSY;
+	if (!wp)
+		return;
 
-	/* we need to store the original allocation size for use during read */
-	dtl->buf_entries = dtl_buf_entries;
+	*wp = *dtle;
+	barrier();
 
-	dtl->buf = kmalloc_node(dtl->buf_entries * sizeof(struct dtl_entry),
-			GFP_KERNEL, cpu_to_node(dtl->cpu));
-	if (!dtl->buf) {
-		printk(KERN_WARNING "%s: buffer alloc failed for cpu %d\n",
-				__func__, dtl->cpu);
-		return -ENOMEM;
-	}
+	/* check for hypervisor ring buffer overflow, ignore this entry if so */
+	if (index + N_DISPATCH_LOG < vpa->dtl_idx)
+		return;
+
+	++wp;
+	if (wp == dtlr->buf_end)
+		wp = dtlr->buf;
+	dtlr->write_ptr = wp;
+
+	/* incrementing write_index makes the new entry visible */
+	smp_wmb();
+	++dtlr->write_index;
+}
+
+static int dtl_start(struct dtl *dtl)
+{
+	struct dtl_ring *dtlr = &per_cpu(dtl_rings, dtl->cpu);
+
+	dtlr->buf = dtl->buf;
+	dtlr->buf_end = dtl->buf + dtl->buf_entries;
+	dtlr->write_index = 0;
+
+	/* setting write_ptr enables logging into our buffer */
+	smp_wmb();
+	dtlr->write_ptr = dtl->buf;
+
+	/* enable event logging */
+	dtlr->saved_dtl_mask = lppaca_of(dtl->cpu).dtl_enable_mask;
+	lppaca_of(dtl->cpu).dtl_enable_mask |= dtl_event_mask;
+
+	dtl_consumer = consume_dtle;
+	atomic_inc(&dtl_count);
+	return 0;
+}
+
+static void dtl_stop(struct dtl *dtl)
+{
+	struct dtl_ring *dtlr = &per_cpu(dtl_rings, dtl->cpu);
+
+	dtlr->write_ptr = NULL;
+	smp_wmb();
+
+	dtlr->buf = NULL;
+
+	/* restore dtl_enable_mask */
+	lppaca_of(dtl->cpu).dtl_enable_mask = dtlr->saved_dtl_mask;
+
+	if (atomic_dec_and_test(&dtl_count))
+		dtl_consumer = NULL;
+}
+
+static u64 dtl_current_index(struct dtl *dtl)
+{
+	return per_cpu(dtl_rings, dtl->cpu).write_index;
+}
+
+#else /* CONFIG_VIRT_CPU_ACCOUNTING */
+
+static int dtl_start(struct dtl *dtl)
+{
+	unsigned long addr;
+	int ret, hwcpu;
 
 	/* Register our dtl buffer with the hypervisor. The HV expects the
 	 * buffer size to be passed in the second word of the buffer */
@@ -102,34 +159,82 @@ static int dtl_enable(struct dtl *dtl)
 	if (ret) {
 		printk(KERN_WARNING "%s: DTL registration for cpu %d (hw %d) "
 		       "failed with %d\n", __func__, dtl->cpu, hwcpu, ret);
-		kfree(dtl->buf);
 		return -EIO;
 	}
 
 	/* set our initial buffer indices */
-	dtl->last_idx = lppaca[dtl->cpu].dtl_idx = 0;
+	lppaca_of(dtl->cpu).dtl_idx = 0;
 
 	/* ensure that our updates to the lppaca fields have occurred before
 	 * we actually enable the logging */
 	smp_wmb();
 
 	/* enable event logging */
-	lppaca[dtl->cpu].dtl_enable_mask = dtl_event_mask;
+	lppaca_of(dtl->cpu).dtl_enable_mask = dtl_event_mask;
 
 	return 0;
 }
 
-static void dtl_disable(struct dtl *dtl)
+static void dtl_stop(struct dtl *dtl)
 {
 	int hwcpu = get_hard_smp_processor_id(dtl->cpu);
 
-	lppaca[dtl->cpu].dtl_enable_mask = 0x0;
+	lppaca_of(dtl->cpu).dtl_enable_mask = 0x0;
 
 	unregister_dtl(hwcpu, __pa(dtl->buf));
+}
+
+static u64 dtl_current_index(struct dtl *dtl)
+{
+	return lppaca_of(dtl->cpu).dtl_idx;
+}
+#endif /* CONFIG_VIRT_CPU_ACCOUNTING */
+
+static int dtl_enable(struct dtl *dtl)
+{
+	long int n_entries;
+	long int rc;
+	struct dtl_entry *buf = NULL;
 
+	/* only allow one reader */
+	if (dtl->buf)
+		return -EBUSY;
+
+	n_entries = dtl_buf_entries;
+	buf = kmalloc_node(n_entries * sizeof(struct dtl_entry),
+			GFP_KERNEL, cpu_to_node(dtl->cpu));
+	if (!buf) {
+		printk(KERN_WARNING "%s: buffer alloc failed for cpu %d\n",
+				__func__, dtl->cpu);
+		return -ENOMEM;
+	}
+
+	spin_lock(&dtl->lock);
+	rc = -EBUSY;
+	if (!dtl->buf) {
+		/* store the original allocation size for use during read */
+		dtl->buf_entries = n_entries;
+		dtl->buf = buf;
+		dtl->last_idx = 0;
+		rc = dtl_start(dtl);
+		if (rc)
+			dtl->buf = NULL;
+	}
+	spin_unlock(&dtl->lock);
+
+	if (rc)
+		kfree(buf);
+	return rc;
+}
+
+static void dtl_disable(struct dtl *dtl)
+{
+	spin_lock(&dtl->lock);
+	dtl_stop(dtl);
 	kfree(dtl->buf);
 	dtl->buf = NULL;
 	dtl->buf_entries = 0;
+	spin_unlock(&dtl->lock);
 }
 
 /* file interface */
@@ -157,8 +262,9 @@ static int dtl_file_release(struct inode *inode, struct file *filp)
 static ssize_t dtl_file_read(struct file *filp, char __user *buf, size_t len,
 		loff_t *pos)
 {
-	int rc, cur_idx, last_idx, n_read, n_req, read_size;
+	long int rc, n_read, n_req, read_size;
 	struct dtl *dtl;
+	u64 cur_idx, last_idx, i;
 
 	if ((len % sizeof(struct dtl_entry)) != 0)
 		return -EINVAL;
@@ -171,41 +277,48 @@ static ssize_t dtl_file_read(struct file *filp, char __user *buf, size_t len,
 	/* actual number of entries read */
 	n_read = 0;
 
-	cur_idx = lppaca[dtl->cpu].dtl_idx;
+	spin_lock(&dtl->lock);
+
+	cur_idx = dtl_current_index(dtl);
 	last_idx = dtl->last_idx;
 
-	if (cur_idx - last_idx > dtl->buf_entries) {
-		pr_debug("%s: hv buffer overflow for cpu %d, samples lost\n",
-				__func__, dtl->cpu);
-	}
+	if (last_idx + dtl->buf_entries <= cur_idx)
+		last_idx = cur_idx - dtl->buf_entries + 1;
+
+	if (last_idx + n_req > cur_idx)
+		n_req = cur_idx - last_idx;
+
+	if (n_req > 0)
+		dtl->last_idx = last_idx + n_req;
+
+	spin_unlock(&dtl->lock);
+
+	if (n_req <= 0)
+		return 0;
 
-	cur_idx  %= dtl->buf_entries;
-	last_idx %= dtl->buf_entries;
+	i = last_idx % dtl->buf_entries;
 
 	/* read the tail of the buffer if we've wrapped */
-	if (last_idx > cur_idx) {
-		read_size = min(n_req, dtl->buf_entries - last_idx);
+	if (i + n_req > dtl->buf_entries) {
+		read_size = dtl->buf_entries - i;
 
-		rc = copy_to_user(buf, &dtl->buf[last_idx],
+		rc = copy_to_user(buf, &dtl->buf[i],
 				read_size * sizeof(struct dtl_entry));
 		if (rc)
 			return -EFAULT;
 
-		last_idx = 0;
+		i = 0;
 		n_req -= read_size;
 		n_read += read_size;
 		buf += read_size * sizeof(struct dtl_entry);
 	}
 
 	/* .. and now the head */
-	read_size = min(n_req, cur_idx - last_idx);
-	rc = copy_to_user(buf, &dtl->buf[last_idx],
-			read_size * sizeof(struct dtl_entry));
+	rc = copy_to_user(buf, &dtl->buf[i], n_req * sizeof(struct dtl_entry));
 	if (rc)
 		return -EFAULT;
 
-	n_read += read_size;
-	dtl->last_idx += n_read;
+	n_read += n_req;
 
 	return n_read * sizeof(struct dtl_entry);
 }
@@ -263,6 +376,7 @@ static int dtl_init(void)
 	/* set up the per-cpu log structures */
 	for_each_possible_cpu(i) {
 		struct dtl *dtl = &per_cpu(cpu_dtl, i);
+		spin_lock_init(&dtl->lock);
 		dtl->cpu = i;
 
 		rc = dtl_setup_file(dtl);
diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c
index cf79b46d8f88..f129040d974c 100644
--- a/arch/powerpc/platforms/pseries/lpar.c
+++ b/arch/powerpc/platforms/pseries/lpar.c
@@ -248,11 +248,13 @@ void vpa_init(int cpu)
 	int hwcpu = get_hard_smp_processor_id(cpu);
 	unsigned long addr;
 	long ret;
+	struct paca_struct *pp;
+	struct dtl_entry *dtl;
 
 	if (cpu_has_feature(CPU_FTR_ALTIVEC))
-		lppaca[cpu].vmxregs_in_use = 1;
+		lppaca_of(cpu).vmxregs_in_use = 1;
 
-	addr = __pa(&lppaca[cpu]);
+	addr = __pa(&lppaca_of(cpu));
 	ret = register_vpa(hwcpu, addr);
 
 	if (ret) {
@@ -274,6 +276,25 @@ void vpa_init(int cpu)
 			       "registration for cpu %d (hw %d) of area %lx "
 			       "returns %ld\n", cpu, hwcpu, addr, ret);
 	}
+
+	/*
+	 * Register dispatch trace log, if one has been allocated.
+	 */
+	pp = &paca[cpu];
+	dtl = pp->dispatch_log;
+	if (dtl) {
+		pp->dtl_ridx = 0;
+		pp->dtl_curr = dtl;
+		lppaca_of(cpu).dtl_idx = 0;
+
+		/* hypervisor reads buffer length from this field */
+		dtl->enqueue_to_dispatch_time = DISPATCH_LOG_BYTES;
+		ret = register_dtl(hwcpu, __pa(dtl));
+		if (ret)
+			pr_warn("DTL registration failed for cpu %d (%ld)\n",
+				cpu, ret);
+		lppaca_of(cpu).dtl_enable_mask = 2;
+	}
 }
 
 static long pSeries_lpar_hpte_insert(unsigned long hpte_group,
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index a6d19e3a505e..d345bfd56bbe 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -273,6 +273,58 @@ static struct notifier_block pci_dn_reconfig_nb = {
 	.notifier_call = pci_dn_reconfig_notifier,
 };
 
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING
+/*
+ * Allocate space for the dispatch trace log for all possible cpus
+ * and register the buffers with the hypervisor.  This is used for
+ * computing time stolen by the hypervisor.
+ */
+static int alloc_dispatch_logs(void)
+{
+	int cpu, ret;
+	struct paca_struct *pp;
+	struct dtl_entry *dtl;
+
+	if (!firmware_has_feature(FW_FEATURE_SPLPAR))
+		return 0;
+
+	for_each_possible_cpu(cpu) {
+		pp = &paca[cpu];
+		dtl = kmalloc_node(DISPATCH_LOG_BYTES, GFP_KERNEL,
+				   cpu_to_node(cpu));
+		if (!dtl) {
+			pr_warn("Failed to allocate dispatch trace log for cpu %d\n",
+				cpu);
+			pr_warn("Stolen time statistics will be unreliable\n");
+			break;
+		}
+
+		pp->dtl_ridx = 0;
+		pp->dispatch_log = dtl;
+		pp->dispatch_log_end = dtl + N_DISPATCH_LOG;
+		pp->dtl_curr = dtl;
+	}
+
+	/* Register the DTL for the current (boot) cpu */
+	dtl = get_paca()->dispatch_log;
+	get_paca()->dtl_ridx = 0;
+	get_paca()->dtl_curr = dtl;
+	get_paca()->lppaca_ptr->dtl_idx = 0;
+
+	/* hypervisor reads buffer length from this field */
+	dtl->enqueue_to_dispatch_time = DISPATCH_LOG_BYTES;
+	ret = register_dtl(hard_smp_processor_id(), __pa(dtl));
+	if (ret)
+		pr_warn("DTL registration failed for boot cpu %d (%d)\n",
+			smp_processor_id(), ret);
+	get_paca()->lppaca_ptr->dtl_enable_mask = 2;
+
+	return 0;
+}
+
+early_initcall(alloc_dispatch_logs);
+#endif /* CONFIG_VIRT_CPU_ACCOUNTING */
+
 static void __init pSeries_setup_arch(void)
 {
 	/* Discover PIC type and setup ppc_md accordingly */
diff --git a/arch/powerpc/sysdev/dart_iommu.c b/arch/powerpc/sysdev/dart_iommu.c
index 559db2b846a9..17cf15ec38be 100644
--- a/arch/powerpc/sysdev/dart_iommu.c
+++ b/arch/powerpc/sysdev/dart_iommu.c
@@ -70,6 +70,8 @@ static int iommu_table_dart_inited;
 static int dart_dirty;
 static int dart_is_u4;
 
+#define DART_U4_BYPASS_BASE	0x8000000000ull
+
 #define DBG(...)
 
 static inline void dart_tlb_invalidate_all(void)
@@ -292,12 +294,20 @@ static void iommu_table_dart_setup(void)
 	set_bit(iommu_table_dart.it_size - 1, iommu_table_dart.it_map);
 }
 
-static void pci_dma_dev_setup_dart(struct pci_dev *dev)
+static void dma_dev_setup_dart(struct device *dev)
 {
 	/* We only have one iommu table on the mac for now, which makes
 	 * things simple. Setup all PCI devices to point to this table
 	 */
-	set_iommu_table_base(&dev->dev, &iommu_table_dart);
+	if (get_dma_ops(dev) == &dma_direct_ops)
+		set_dma_offset(dev, DART_U4_BYPASS_BASE);
+	else
+		set_iommu_table_base(dev, &iommu_table_dart);
+}
+
+static void pci_dma_dev_setup_dart(struct pci_dev *dev)
+{
+	dma_dev_setup_dart(&dev->dev);
 }
 
 static void pci_dma_bus_setup_dart(struct pci_bus *bus)
@@ -315,6 +325,45 @@ static void pci_dma_bus_setup_dart(struct pci_bus *bus)
 		PCI_DN(dn)->iommu_table = &iommu_table_dart;
 }
 
+static bool dart_device_on_pcie(struct device *dev)
+{
+	struct device_node *np = of_node_get(dev->of_node);
+
+	while(np) {
+		if (of_device_is_compatible(np, "U4-pcie") ||
+		    of_device_is_compatible(np, "u4-pcie")) {
+			of_node_put(np);
+			return true;
+		}
+		np = of_get_next_parent(np);
+	}
+	return false;
+}
+
+static int dart_dma_set_mask(struct device *dev, u64 dma_mask)
+{
+	if (!dev->dma_mask || !dma_supported(dev, dma_mask))
+		return -EIO;
+
+	/* U4 supports a DART bypass, we use it for 64-bit capable
+	 * devices to improve performances. However, that only works
+	 * for devices connected to U4 own PCIe interface, not bridged
+	 * through hypertransport. We need the device to support at
+	 * least 40 bits of addresses.
+	 */
+	if (dart_device_on_pcie(dev) && dma_mask >= DMA_BIT_MASK(40)) {
+		dev_info(dev, "Using 64-bit DMA iommu bypass\n");
+		set_dma_ops(dev, &dma_direct_ops);
+	} else {
+		dev_info(dev, "Using 32-bit DMA via iommu\n");
+		set_dma_ops(dev, &dma_iommu_ops);
+	}
+	dma_dev_setup_dart(dev);
+
+	*dev->dma_mask = dma_mask;
+	return 0;
+}
+
 void __init iommu_init_early_dart(void)
 {
 	struct device_node *dn;
@@ -328,20 +377,25 @@ void __init iommu_init_early_dart(void)
 		dart_is_u4 = 1;
 	}
 
+	/* Initialize the DART HW */
+	if (dart_init(dn) != 0)
+		goto bail;
+
 	/* Setup low level TCE operations for the core IOMMU code */
 	ppc_md.tce_build = dart_build;
 	ppc_md.tce_free  = dart_free;
 	ppc_md.tce_flush = dart_flush;
 
-	/* Initialize the DART HW */
-	if (dart_init(dn) == 0) {
-		ppc_md.pci_dma_dev_setup = pci_dma_dev_setup_dart;
-		ppc_md.pci_dma_bus_setup = pci_dma_bus_setup_dart;
+	/* Setup bypass if supported */
+	if (dart_is_u4)
+		ppc_md.dma_set_mask = dart_dma_set_mask;
 
-		/* Setup pci_dma ops */
-		set_pci_dma_ops(&dma_iommu_ops);
-		return;
-	}
+	ppc_md.pci_dma_dev_setup = pci_dma_dev_setup_dart;
+	ppc_md.pci_dma_bus_setup = pci_dma_bus_setup_dart;
+
+	/* Setup pci_dma ops */
+	set_pci_dma_ops(&dma_iommu_ops);
+	return;
 
  bail:
 	/* If init failed, use direct iommu and null setup functions */