Merge git://git.kernel.org/pub/scm/linux/kernel/git/paulus/powerpc

* git://git.kernel.org/pub/scm/linux/kernel/git/paulus/powerpc: (78 commits)
  [PATCH] powerpc: Add FSL SEC node to documentation
  [PATCH] macintosh: tidy-up driver_register() return values
  [PATCH] powerpc: tidy-up of_register_driver()/driver_register() return values
  [PATCH] powerpc: via-pmu warning fix
  [PATCH] macintosh: cleanup the use of i2c headers
  [PATCH] powerpc: dont allow old RTC to be selected
  [PATCH] powerpc: make powerbook_sleep_grackle static
  [PATCH] powerpc: Fix warning in add_memory
  [PATCH] powerpc: update mailing list addresses
  [PATCH] powerpc: Remove calculation of io hole
  [PATCH] powerpc: iseries: Add bootargs to /chosen
  [PATCH] powerpc: iseries: Add /system-id, /model and /compatible
  [PATCH] powerpc: Add strne2a() to convert a string from EBCDIC to ASCII
  [PATCH] powerpc: iseries: Make more stuff static in platforms/iseries/mf.c
  [PATCH] powerpc: iseries: Remove pointless iSeries_(restart|power_off|halt)
  [PATCH] powerpc: iseries: mf related cleanups
  [PATCH] powerpc: Replace platform_is_lpar() with a firmware feature
  [PATCH] powerpc: trivial: Cleanup whitespace in cputable.h
  [PATCH] powerpc: Remove unused iommu_off logic from pSeries_init_early()
  [PATCH] powerpc: Unconfuse htab_bolt_mapping() callers
  ...

26 files changed, 667 insertions, 80 deletions

diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index c9a660e4c2d..882889b1592 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -136,6 +136,9 @@ int main(void)
 	DEFINE(PACAEMERGSP, offsetof(struct paca_struct, emergency_sp));
 	DEFINE(PACALPPACAPTR, offsetof(struct paca_struct, lppaca_ptr));
 	DEFINE(PACAHWCPUID, offsetof(struct paca_struct, hw_cpu_id));
+	DEFINE(PACA_STARTPURR, offsetof(struct paca_struct, startpurr));
+	DEFINE(PACA_USER_TIME, offsetof(struct paca_struct, user_time));
+	DEFINE(PACA_SYSTEM_TIME, offsetof(struct paca_struct, system_time));
 
 	DEFINE(LPPACASRR0, offsetof(struct lppaca, saved_srr0));
 	DEFINE(LPPACASRR1, offsetof(struct lppaca, saved_srr1));
diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index e4e81374cb9..39e348a3ade 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -894,7 +894,7 @@ struct cpu_spec	cpu_specs[] = {
 		.platform		= "ppc405",
 	},
 	{	/* Xilinx Virtex-II Pro  */
-		.pvr_mask		= 0xffff0000,
+		.pvr_mask		= 0xfffff000,
 		.pvr_value		= 0x20010000,
 		.cpu_name		= "Virtex-II Pro",
 		.cpu_features		= CPU_FTRS_40X,
@@ -904,6 +904,16 @@ struct cpu_spec	cpu_specs[] = {
 		.dcache_bsize		= 32,
 		.platform		= "ppc405",
 	},
+	{	/* Xilinx Virtex-4 FX */
+		.pvr_mask		= 0xfffff000,
+		.pvr_value		= 0x20011000,
+		.cpu_name		= "Virtex-4 FX",
+		.cpu_features		= CPU_FTRS_40X,
+		.cpu_user_features	= PPC_FEATURE_32 |
+			PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC,
+		.icache_bsize		= 32,
+		.dcache_bsize		= 32,
+	},
 	{	/* 405EP */
 		.pvr_mask		= 0xffff0000,
 		.pvr_value		= 0x51210000,
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index 24be0cf86d7..1060155d84c 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -1,6 +1,4 @@
 /*
- *  arch/ppc64/kernel/entry.S
- *
  *  PowerPC version 
  *    Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
  *  Rewritten by Cort Dougan (cort@cs.nmt.edu) for PReP
@@ -63,6 +61,7 @@ system_call_common:
 	std	r12,_MSR(r1)
 	std	r0,GPR0(r1)
 	std	r10,GPR1(r1)
+	ACCOUNT_CPU_USER_ENTRY(r10, r11)
 	std	r2,GPR2(r1)
 	std	r3,GPR3(r1)
 	std	r4,GPR4(r1)
@@ -170,8 +169,9 @@ syscall_error_cont:
 	stdcx.	r0,0,r1			/* to clear the reservation */
 	andi.	r6,r8,MSR_PR
 	ld	r4,_LINK(r1)
-	beq-	1f			/* only restore r13 if */
-	ld	r13,GPR13(r1)		/* returning to usermode */
+	beq-	1f
+	ACCOUNT_CPU_USER_EXIT(r11, r12)
+	ld	r13,GPR13(r1)	/* only restore r13 if returning to usermode */
 1:	ld	r2,GPR2(r1)
 	li	r12,MSR_RI
 	andc	r11,r10,r12
@@ -322,7 +322,7 @@ _GLOBAL(ret_from_fork)
  * the fork code also.
  *
  * The code which creates the new task context is in 'copy_thread'
- * in arch/ppc64/kernel/process.c
+ * in arch/powerpc/kernel/process.c 
  */
 	.align	7
 _GLOBAL(_switch)
@@ -486,6 +486,7 @@ restore:
 	 * userspace
 	 */
 	beq	1f
+	ACCOUNT_CPU_USER_EXIT(r3, r4)
 	REST_GPR(13, r1)
 1:
 	ld	r3,_CTR(r1)
diff --git a/arch/powerpc/kernel/firmware.c b/arch/powerpc/kernel/firmware.c
index 65eae752a52..4d37a3cb80f 100644
--- a/arch/powerpc/kernel/firmware.c
+++ b/arch/powerpc/kernel/firmware.c
@@ -18,28 +18,3 @@
 #include <asm/firmware.h>
 
 unsigned long ppc64_firmware_features;
-
-#ifdef CONFIG_PPC_PSERIES
-firmware_feature_t firmware_features_table[FIRMWARE_MAX_FEATURES] = {
-	{FW_FEATURE_PFT,		"hcall-pft"},
-	{FW_FEATURE_TCE,		"hcall-tce"},
-	{FW_FEATURE_SPRG0,		"hcall-sprg0"},
-	{FW_FEATURE_DABR,		"hcall-dabr"},
-	{FW_FEATURE_COPY,		"hcall-copy"},
-	{FW_FEATURE_ASR,		"hcall-asr"},
-	{FW_FEATURE_DEBUG,		"hcall-debug"},
-	{FW_FEATURE_PERF,		"hcall-perf"},
-	{FW_FEATURE_DUMP,		"hcall-dump"},
-	{FW_FEATURE_INTERRUPT,		"hcall-interrupt"},
-	{FW_FEATURE_MIGRATE,		"hcall-migrate"},
-	{FW_FEATURE_PERFMON,		"hcall-perfmon"},
-	{FW_FEATURE_CRQ,		"hcall-crq"},
-	{FW_FEATURE_VIO,		"hcall-vio"},
-	{FW_FEATURE_RDMA,		"hcall-rdma"},
-	{FW_FEATURE_LLAN,		"hcall-lLAN"},
-	{FW_FEATURE_BULK,		"hcall-bulk"},
-	{FW_FEATURE_XDABR,		"hcall-xdabr"},
-	{FW_FEATURE_MULTITCE,		"hcall-multi-tce"},
-	{FW_FEATURE_SPLPAR,		"hcall-splpar"},
-};
-#endif
diff --git a/arch/powerpc/kernel/head_44x.S b/arch/powerpc/kernel/head_44x.S
index 8b49679fad5..47c7fa148c9 100644
--- a/arch/powerpc/kernel/head_44x.S
+++ b/arch/powerpc/kernel/head_44x.S
@@ -1,6 +1,4 @@
 /*
- * arch/ppc/kernel/head_44x.S
- *
  * Kernel execution entry point code.
  *
  *    Copyright (c) 1995-1996 Gary Thomas <gdt@linuxppc.org>
diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S
index 9b65029dd2a..35084f3a841 100644
--- a/arch/powerpc/kernel/head_64.S
+++ b/arch/powerpc/kernel/head_64.S
@@ -1,6 +1,4 @@
 /*
- *  arch/ppc64/kernel/head.S
- *
  *  PowerPC version
  *    Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
  *
@@ -279,6 +277,7 @@ exception_marker:
 	std	r10,0(r1);		/* make stack chain pointer	*/ \
 	std	r0,GPR0(r1);		/* save r0 in stackframe	*/ \
 	std	r10,GPR1(r1);		/* save r1 in stackframe	*/ \
+	ACCOUNT_CPU_USER_ENTRY(r9, r10);				   \
 	std	r2,GPR2(r1);		/* save r2 in stackframe	*/ \
 	SAVE_4GPRS(3, r1);		/* save r3 - r6 in stackframe	*/ \
 	SAVE_2GPRS(7, r1);		/* save r7, r8 in stackframe	*/ \
@@ -846,6 +845,14 @@ fast_exception_return:
 	ld	r11,_NIP(r1)
 	andi.	r3,r12,MSR_RI		/* check if RI is set */
 	beq-	unrecov_fer
+
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING
+	andi.	r3,r12,MSR_PR
+	beq	2f
+	ACCOUNT_CPU_USER_EXIT(r3, r4)
+2:
+#endif
+
 	ld	r3,_CCR(r1)
 	ld	r4,_LINK(r1)
 	ld	r5,_CTR(r1)
diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S
index bc6d1ac5523..28941f5ce67 100644
--- a/arch/powerpc/kernel/head_8xx.S
+++ b/arch/powerpc/kernel/head_8xx.S
@@ -1,6 +1,4 @@
 /*
- *  arch/ppc/kernel/except_8xx.S
- *
  *  PowerPC version
  *    Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
  *  Rewritten by Cort Dougan (cort@cs.nmt.edu) for PReP
diff --git a/arch/powerpc/kernel/head_booke.h b/arch/powerpc/kernel/head_booke.h
new file mode 100644
index 00000000000..8536e767616
--- /dev/null
+++ b/arch/powerpc/kernel/head_booke.h
@@ -0,0 +1,363 @@
+#ifndef __HEAD_BOOKE_H__
+#define __HEAD_BOOKE_H__
+
+/*
+ * Macros used for common Book-e exception handling
+ */
+
+#define SET_IVOR(vector_number, vector_label)		\
+		li	r26,vector_label@l; 		\
+		mtspr	SPRN_IVOR##vector_number,r26;	\
+		sync
+
+#define NORMAL_EXCEPTION_PROLOG						     \
+	mtspr	SPRN_SPRG0,r10;		/* save two registers to work with */\
+	mtspr	SPRN_SPRG1,r11;						     \
+	mtspr	SPRN_SPRG4W,r1;						     \
+	mfcr	r10;			/* save CR in r10 for now	   */\
+	mfspr	r11,SPRN_SRR1;		/* check whether user or kernel    */\
+	andi.	r11,r11,MSR_PR;						     \
+	beq	1f;							     \
+	mfspr	r1,SPRN_SPRG3;		/* if from user, start at top of   */\
+	lwz	r1,THREAD_INFO-THREAD(r1); /* this thread's kernel stack   */\
+	addi	r1,r1,THREAD_SIZE;					     \
+1:	subi	r1,r1,INT_FRAME_SIZE;	/* Allocate an exception frame     */\
+	mr	r11,r1;							     \
+	stw	r10,_CCR(r11);          /* save various registers	   */\
+	stw	r12,GPR12(r11);						     \
+	stw	r9,GPR9(r11);						     \
+	mfspr	r10,SPRN_SPRG0;						     \
+	stw	r10,GPR10(r11);						     \
+	mfspr	r12,SPRN_SPRG1;						     \
+	stw	r12,GPR11(r11);						     \
+	mflr	r10;							     \
+	stw	r10,_LINK(r11);						     \
+	mfspr	r10,SPRN_SPRG4R;					     \
+	mfspr	r12,SPRN_SRR0;						     \
+	stw	r10,GPR1(r11);						     \
+	mfspr	r9,SPRN_SRR1;						     \
+	stw	r10,0(r11);						     \
+	rlwinm	r9,r9,0,14,12;		/* clear MSR_WE (necessary?)	   */\
+	stw	r0,GPR0(r11);						     \
+	SAVE_4GPRS(3, r11);						     \
+	SAVE_2GPRS(7, r11)
+
+/* To handle the additional exception priority levels on 40x and Book-E
+ * processors we allocate a 4k stack per additional priority level. The various
+ * head_xxx.S files allocate space (exception_stack_top) for each priority's
+ * stack times the number of CPUs
+ *
+ * On 40x critical is the only additional level
+ * On 44x/e500 we have critical and machine check
+ * On e200 we have critical and debug (machine check occurs via critical)
+ *
+ * Additionally we reserve a SPRG for each priority level so we can free up a
+ * GPR to use as the base for indirect access to the exception stacks.  This
+ * is necessary since the MMU is always on, for Book-E parts, and the stacks
+ * are offset from KERNELBASE.
+ *
+ */
+#define BOOKE_EXCEPTION_STACK_SIZE	(8192)
+
+/* CRIT_SPRG only used in critical exception handling */
+#define CRIT_SPRG	SPRN_SPRG2
+/* MCHECK_SPRG only used in machine check exception handling */
+#define MCHECK_SPRG	SPRN_SPRG6W
+
+#define MCHECK_STACK_TOP	(exception_stack_top - 4096)
+#define CRIT_STACK_TOP		(exception_stack_top)
+
+/* only on e200 for now */
+#define DEBUG_STACK_TOP		(exception_stack_top - 4096)
+#define DEBUG_SPRG		SPRN_SPRG6W
+
+#ifdef CONFIG_SMP
+#define BOOKE_LOAD_EXC_LEVEL_STACK(level)		\
+	mfspr	r8,SPRN_PIR;				\
+	mulli	r8,r8,BOOKE_EXCEPTION_STACK_SIZE;	\
+	neg	r8,r8;					\
+	addis	r8,r8,level##_STACK_TOP@ha;		\
+	addi	r8,r8,level##_STACK_TOP@l
+#else
+#define BOOKE_LOAD_EXC_LEVEL_STACK(level)		\
+	lis	r8,level##_STACK_TOP@h;			\
+	ori	r8,r8,level##_STACK_TOP@l
+#endif
+
+/*
+ * Exception prolog for critical/machine check exceptions.  This is a
+ * little different from the normal exception prolog above since a
+ * critical/machine check exception can potentially occur at any point
+ * during normal exception processing. Thus we cannot use the same SPRG
+ * registers as the normal prolog above. Instead we use a portion of the
+ * critical/machine check exception stack at low physical addresses.
+ */
+#define EXC_LEVEL_EXCEPTION_PROLOG(exc_level, exc_level_srr0, exc_level_srr1) \
+	mtspr	exc_level##_SPRG,r8;					     \
+	BOOKE_LOAD_EXC_LEVEL_STACK(exc_level);/* r8 points to the exc_level stack*/ \
+	stw	r10,GPR10-INT_FRAME_SIZE(r8);				     \
+	stw	r11,GPR11-INT_FRAME_SIZE(r8);				     \
+	mfcr	r10;			/* save CR in r10 for now	   */\
+	mfspr	r11,exc_level_srr1;	/* check whether user or kernel    */\
+	andi.	r11,r11,MSR_PR;						     \
+	mr	r11,r8;							     \
+	mfspr	r8,exc_level##_SPRG;					     \
+	beq	1f;							     \
+	/* COMING FROM USER MODE */					     \
+	mfspr	r11,SPRN_SPRG3;		/* if from user, start at top of   */\
+	lwz	r11,THREAD_INFO-THREAD(r11); /* this thread's kernel stack */\
+	addi	r11,r11,THREAD_SIZE;					     \
+1:	subi	r11,r11,INT_FRAME_SIZE;	/* Allocate an exception frame     */\
+	stw	r10,_CCR(r11);          /* save various registers	   */\
+	stw	r12,GPR12(r11);						     \
+	stw	r9,GPR9(r11);						     \
+	mflr	r10;							     \
+	stw	r10,_LINK(r11);						     \
+	mfspr	r12,SPRN_DEAR;		/* save DEAR and ESR in the frame  */\
+	stw	r12,_DEAR(r11);		/* since they may have had stuff   */\
+	mfspr	r9,SPRN_ESR;		/* in them at the point where the  */\
+	stw	r9,_ESR(r11);		/* exception was taken		   */\
+	mfspr	r12,exc_level_srr0;					     \
+	stw	r1,GPR1(r11);						     \
+	mfspr	r9,exc_level_srr1;					     \
+	stw	r1,0(r11);						     \
+	mr	r1,r11;							     \
+	rlwinm	r9,r9,0,14,12;		/* clear MSR_WE (necessary?)	   */\
+	stw	r0,GPR0(r11);						     \
+	SAVE_4GPRS(3, r11);						     \
+	SAVE_2GPRS(7, r11)
+
+#define CRITICAL_EXCEPTION_PROLOG \
+		EXC_LEVEL_EXCEPTION_PROLOG(CRIT, SPRN_CSRR0, SPRN_CSRR1)
+#define DEBUG_EXCEPTION_PROLOG \
+		EXC_LEVEL_EXCEPTION_PROLOG(DEBUG, SPRN_DSRR0, SPRN_DSRR1)
+#define MCHECK_EXCEPTION_PROLOG \
+		EXC_LEVEL_EXCEPTION_PROLOG(MCHECK, SPRN_MCSRR0, SPRN_MCSRR1)
+
+/*
+ * Exception vectors.
+ */
+#define	START_EXCEPTION(label)						     \
+        .align 5;              						     \
+label:
+
+#define FINISH_EXCEPTION(func)					\
+	bl	transfer_to_handler_full;			\
+	.long	func;						\
+	.long	ret_from_except_full
+
+#define EXCEPTION(n, label, hdlr, xfer)				\
+	START_EXCEPTION(label);					\
+	NORMAL_EXCEPTION_PROLOG;				\
+	addi	r3,r1,STACK_FRAME_OVERHEAD;			\
+	xfer(n, hdlr)
+
+#define CRITICAL_EXCEPTION(n, label, hdlr)			\
+	START_EXCEPTION(label);					\
+	CRITICAL_EXCEPTION_PROLOG;				\
+	addi	r3,r1,STACK_FRAME_OVERHEAD;			\
+	EXC_XFER_TEMPLATE(hdlr, n+2, (MSR_KERNEL & ~(MSR_ME|MSR_DE|MSR_CE)), \
+			  NOCOPY, crit_transfer_to_handler, \
+			  ret_from_crit_exc)
+
+#define MCHECK_EXCEPTION(n, label, hdlr)			\
+	START_EXCEPTION(label);					\
+	MCHECK_EXCEPTION_PROLOG;				\
+	mfspr	r5,SPRN_ESR;					\
+	stw	r5,_ESR(r11);					\
+	addi	r3,r1,STACK_FRAME_OVERHEAD;			\
+	EXC_XFER_TEMPLATE(hdlr, n+2, (MSR_KERNEL & ~(MSR_ME|MSR_DE|MSR_CE)), \
+			  NOCOPY, mcheck_transfer_to_handler,   \
+			  ret_from_mcheck_exc)
+
+#define EXC_XFER_TEMPLATE(hdlr, trap, msr, copyee, tfer, ret)	\
+	li	r10,trap;					\
+	stw	r10,_TRAP(r11);					\
+	lis	r10,msr@h;					\
+	ori	r10,r10,msr@l;					\
+	copyee(r10, r9);					\
+	bl	tfer;		 				\
+	.long	hdlr;						\
+	.long	ret
+
+#define COPY_EE(d, s)		rlwimi d,s,0,16,16
+#define NOCOPY(d, s)
+
+#define EXC_XFER_STD(n, hdlr)		\
+	EXC_XFER_TEMPLATE(hdlr, n, MSR_KERNEL, NOCOPY, transfer_to_handler_full, \
+			  ret_from_except_full)
+
+#define EXC_XFER_LITE(n, hdlr)		\
+	EXC_XFER_TEMPLATE(hdlr, n+1, MSR_KERNEL, NOCOPY, transfer_to_handler, \
+			  ret_from_except)
+
+#define EXC_XFER_EE(n, hdlr)		\
+	EXC_XFER_TEMPLATE(hdlr, n, MSR_KERNEL, COPY_EE, transfer_to_handler_full, \
+			  ret_from_except_full)
+
+#define EXC_XFER_EE_LITE(n, hdlr)	\
+	EXC_XFER_TEMPLATE(hdlr, n+1, MSR_KERNEL, COPY_EE, transfer_to_handler, \
+			  ret_from_except)
+
+/* Check for a single step debug exception while in an exception
+ * handler before state has been saved.  This is to catch the case
+ * where an instruction that we are trying to single step causes
+ * an exception (eg ITLB/DTLB miss) and thus the first instruction of
+ * the exception handler generates a single step debug exception.
+ *
+ * If we get a debug trap on the first instruction of an exception handler,
+ * we reset the MSR_DE in the _exception handler's_ MSR (the debug trap is
+ * a critical exception, so we are using SPRN_CSRR1 to manipulate the MSR).
+ * The exception handler was handling a non-critical interrupt, so it will
+ * save (and later restore) the MSR via SPRN_CSRR1, which will still have
+ * the MSR_DE bit set.
+ */
+#ifdef CONFIG_E200
+#define DEBUG_EXCEPTION							      \
+	START_EXCEPTION(Debug);						      \
+	DEBUG_EXCEPTION_PROLOG;						      \
+									      \
+	/*								      \
+	 * If there is a single step or branch-taken exception in an	      \
+	 * exception entry sequence, it was probably meant to apply to	      \
+	 * the code where the exception occurred (since exception entry	      \
+	 * doesn't turn off DE automatically).  We simulate the effect	      \
+	 * of turning off DE on entry to an exception handler by turning      \
+	 * off DE in the CSRR1 value and clearing the debug status.	      \
+	 */								      \
+	mfspr	r10,SPRN_DBSR;		/* check single-step/branch taken */  \
+	andis.	r10,r10,DBSR_IC@h;					      \
+	beq+	2f;							      \
+									      \
+	lis	r10,KERNELBASE@h;	/* check if exception in vectors */   \
+	ori	r10,r10,KERNELBASE@l;					      \
+	cmplw	r12,r10;						      \
+	blt+	2f;			/* addr below exception vectors */    \
+									      \
+	lis	r10,Debug@h;						      \
+	ori	r10,r10,Debug@l;					      \
+	cmplw	r12,r10;						      \
+	bgt+	2f;			/* addr above exception vectors */    \
+									      \
+	/* here it looks like we got an inappropriate debug exception. */     \
+1:	rlwinm	r9,r9,0,~MSR_DE;	/* clear DE in the CDRR1 value */     \
+	lis	r10,DBSR_IC@h;		/* clear the IC event */	      \
+	mtspr	SPRN_DBSR,r10;						      \
+	/* restore state and get out */					      \
+	lwz	r10,_CCR(r11);						      \
+	lwz	r0,GPR0(r11);						      \
+	lwz	r1,GPR1(r11);						      \
+	mtcrf	0x80,r10;						      \
+	mtspr	SPRN_DSRR0,r12;						      \
+	mtspr	SPRN_DSRR1,r9;						      \
+	lwz	r9,GPR9(r11);						      \
+	lwz	r12,GPR12(r11);						      \
+	mtspr	DEBUG_SPRG,r8;						      \
+	BOOKE_LOAD_EXC_LEVEL_STACK(DEBUG); /* r8 points to the debug stack */ \
+	lwz	r10,GPR10-INT_FRAME_SIZE(r8);				      \
+	lwz	r11,GPR11-INT_FRAME_SIZE(r8);				      \
+	mfspr	r8,DEBUG_SPRG;						      \
+									      \
+	RFDI;								      \
+	b	.;							      \
+									      \
+	/* continue normal handling for a critical exception... */	      \
+2:	mfspr	r4,SPRN_DBSR;						      \
+	addi	r3,r1,STACK_FRAME_OVERHEAD;				      \
+	EXC_XFER_TEMPLATE(DebugException, 0x2002, (MSR_KERNEL & ~(MSR_ME|MSR_DE|MSR_CE)), NOCOPY, debug_transfer_to_handler, ret_from_debug_exc)
+#else
+#define DEBUG_EXCEPTION							      \
+	START_EXCEPTION(Debug);						      \
+	CRITICAL_EXCEPTION_PROLOG;					      \
+									      \
+	/*								      \
+	 * If there is a single step or branch-taken exception in an	      \
+	 * exception entry sequence, it was probably meant to apply to	      \
+	 * the code where the exception occurred (since exception entry	      \
+	 * doesn't turn off DE automatically).  We simulate the effect	      \
+	 * of turning off DE on entry to an exception handler by turning      \
+	 * off DE in the CSRR1 value and clearing the debug status.	      \
+	 */								      \
+	mfspr	r10,SPRN_DBSR;		/* check single-step/branch taken */  \
+	andis.	r10,r10,DBSR_IC@h;					      \
+	beq+	2f;							      \
+									      \
+	lis	r10,KERNELBASE@h;	/* check if exception in vectors */   \
+	ori	r10,r10,KERNELBASE@l;					      \
+	cmplw	r12,r10;						      \
+	blt+	2f;			/* addr below exception vectors */    \
+									      \
+	lis	r10,Debug@h;						      \
+	ori	r10,r10,Debug@l;					      \
+	cmplw	r12,r10;						      \
+	bgt+	2f;			/* addr above exception vectors */    \
+									      \
+	/* here it looks like we got an inappropriate debug exception. */     \
+1:	rlwinm	r9,r9,0,~MSR_DE;	/* clear DE in the CSRR1 value */     \
+	lis	r10,DBSR_IC@h;		/* clear the IC event */	      \
+	mtspr	SPRN_DBSR,r10;						      \
+	/* restore state and get out */					      \
+	lwz	r10,_CCR(r11);						      \
+	lwz	r0,GPR0(r11);						      \
+	lwz	r1,GPR1(r11);						      \
+	mtcrf	0x80,r10;						      \
+	mtspr	SPRN_CSRR0,r12;						      \
+	mtspr	SPRN_CSRR1,r9;						      \
+	lwz	r9,GPR9(r11);						      \
+	lwz	r12,GPR12(r11);						      \
+	mtspr	CRIT_SPRG,r8;						      \
+	BOOKE_LOAD_EXC_LEVEL_STACK(CRIT); /* r8 points to the debug stack */  \
+	lwz	r10,GPR10-INT_FRAME_SIZE(r8);				      \
+	lwz	r11,GPR11-INT_FRAME_SIZE(r8);				      \
+	mfspr	r8,CRIT_SPRG;						      \
+									      \
+	rfci;								      \
+	b	.;							      \
+									      \
+	/* continue normal handling for a critical exception... */	      \
+2:	mfspr	r4,SPRN_DBSR;						      \
+	addi	r3,r1,STACK_FRAME_OVERHEAD;				      \
+	EXC_XFER_TEMPLATE(DebugException, 0x2002, (MSR_KERNEL & ~(MSR_ME|MSR_DE|MSR_CE)), NOCOPY, crit_transfer_to_handler, ret_from_crit_exc)
+#endif
+
+#define INSTRUCTION_STORAGE_EXCEPTION					      \
+	START_EXCEPTION(InstructionStorage)				      \
+	NORMAL_EXCEPTION_PROLOG;					      \
+	mfspr	r5,SPRN_ESR;		/* Grab the ESR and save it */	      \
+	stw	r5,_ESR(r11);						      \
+	mr      r4,r12;                 /* Pass SRR0 as arg2 */		      \
+	li      r5,0;                   /* Pass zero as arg3 */		      \
+	EXC_XFER_EE_LITE(0x0400, handle_page_fault)
+
+#define ALIGNMENT_EXCEPTION						      \
+	START_EXCEPTION(Alignment)					      \
+	NORMAL_EXCEPTION_PROLOG;					      \
+	mfspr   r4,SPRN_DEAR;           /* Grab the DEAR and save it */	      \
+	stw     r4,_DEAR(r11);						      \
+	addi    r3,r1,STACK_FRAME_OVERHEAD;				      \
+	EXC_XFER_EE(0x0600, alignment_exception)
+
+#define PROGRAM_EXCEPTION						      \
+	START_EXCEPTION(Program)					      \
+	NORMAL_EXCEPTION_PROLOG;					      \
+	mfspr	r4,SPRN_ESR;		/* Grab the ESR and save it */	      \
+	stw	r4,_ESR(r11);						      \
+	addi	r3,r1,STACK_FRAME_OVERHEAD;				      \
+	EXC_XFER_STD(0x0700, program_check_exception)
+
+#define DECREMENTER_EXCEPTION						      \
+	START_EXCEPTION(Decrementer)					      \
+	NORMAL_EXCEPTION_PROLOG;					      \
+	lis     r0,TSR_DIS@h;           /* Setup the DEC interrupt mask */    \
+	mtspr   SPRN_TSR,r0;		/* Clear the DEC interrupt */	      \
+	addi    r3,r1,STACK_FRAME_OVERHEAD;				      \
+	EXC_XFER_LITE(0x0900, timer_interrupt)
+
+#define FP_UNAVAILABLE_EXCEPTION					      \
+	START_EXCEPTION(FloatingPointUnavailable)			      \
+	NORMAL_EXCEPTION_PROLOG;					      \
+	bne	load_up_fpu;		/* if from user, just load it up */   \
+	addi	r3,r1,STACK_FRAME_OVERHEAD;				      \
+	EXC_XFER_EE_LITE(0x800, kernel_fp_unavailable_exception)
+
+#endif /* __HEAD_BOOKE_H__ */
diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S
index 8d60fa99fc4..dd86bbed762 100644
--- a/arch/powerpc/kernel/head_fsl_booke.S
+++ b/arch/powerpc/kernel/head_fsl_booke.S
@@ -1,6 +1,4 @@
 /*
- * arch/ppc/kernel/head_fsl_booke.S
- *
  * Kernel execution entry point code.
  *
  *    Copyright (c) 1995-1996 Gary Thomas <gdt@linuxppc.org>
@@ -316,6 +314,7 @@ skpinv:	addi	r6,r6,1				/* Increment */
 	 */
 	lis	r2,DBCR0_IDM@h
 	mtspr	SPRN_DBCR0,r2
+	isync
 	/* clear any residual debug events */
 	li	r2,-1
 	mtspr	SPRN_DBSR,r2
@@ -1002,12 +1001,15 @@ _GLOBAL(giveup_fpu)
 _GLOBAL(abort)
 	li	r13,0
         mtspr   SPRN_DBCR0,r13		/* disable all debug events */
+	isync
 	mfmsr	r13
 	ori	r13,r13,MSR_DE@l	/* Enable Debug Events */
 	mtmsr	r13
+	isync
         mfspr   r13,SPRN_DBCR0
         lis	r13,(DBCR0_IDM|DBCR0_RST_CHIP)@h
         mtspr   SPRN_DBCR0,r13
+	isync
 
 _GLOBAL(set_context)
 
diff --git a/arch/powerpc/kernel/iomap.c b/arch/powerpc/kernel/iomap.c
index 6160c8dbb7c..fd8214caede 100644
--- a/arch/powerpc/kernel/iomap.c
+++ b/arch/powerpc/kernel/iomap.c
@@ -1,6 +1,4 @@
 /*
- * arch/ppc64/kernel/iomap.c
- *
  * ppc64 "iomap" interface implementation.
  *
  * (C) Copyright 2004 Linus Torvalds
diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index 946f3219fd2..d9a7fdef59b 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -1,5 +1,4 @@
 /*
- * arch/ppc64/kernel/iommu.c
  * Copyright (C) 2001 Mike Corrigan & Dave Engebretsen, IBM Corporation
  * 
  * Rewrite, cleanup, new allocation schemes, virtual merging: 
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index d1fffce86df..24dc8117b82 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -1,6 +1,4 @@
 /*
- *  arch/ppc/kernel/irq.c
- *
  *  Derived from arch/i386/kernel/irq.c
  *    Copyright (C) 1992 Linus Torvalds
  *  Adapted from arch/i386 by Gary Thomas
@@ -371,6 +369,7 @@ unsigned int real_irq_to_virt_slowpath(unsigned int real_irq)
 	return NO_IRQ;
 
 }
+#endif /* CONFIG_PPC64 */
 
 #ifdef CONFIG_IRQSTACKS
 struct thread_info *softirq_ctx[NR_CPUS];
@@ -394,10 +393,24 @@ void irq_ctx_init(void)
 	}
 }
 
+static inline void do_softirq_onstack(void)
+{
+	struct thread_info *curtp, *irqtp;
+
+	curtp = current_thread_info();
+	irqtp = softirq_ctx[smp_processor_id()];
+	irqtp->task = curtp->task;
+	call_do_softirq(irqtp);
+	irqtp->task = NULL;
+}
+
+#else
+#define do_softirq_onstack()	__do_softirq()
+#endif /* CONFIG_IRQSTACKS */
+
 void do_softirq(void)
 {
 	unsigned long flags;
-	struct thread_info *curtp, *irqtp;
 
 	if (in_interrupt())
 		return;
@@ -405,19 +418,18 @@ void do_softirq(void)
 	local_irq_save(flags);
 
 	if (local_softirq_pending()) {
-		curtp = current_thread_info();
-		irqtp = softirq_ctx[smp_processor_id()];
-		irqtp->task = curtp->task;
-		call_do_softirq(irqtp);
-		irqtp->task = NULL;
+		account_system_vtime(current);
+		local_bh_disable();
+		do_softirq_onstack();
+		account_system_vtime(current);
+		__local_bh_enable();
 	}
 
 	local_irq_restore(flags);
 }
 EXPORT_SYMBOL(do_softirq);
 
-#endif /* CONFIG_IRQSTACKS */
-
+#ifdef CONFIG_PPC64
 static int __init setup_noirqdistrib(char *str)
 {
 	distribute_irqs = 0;
diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c
index cfab48566db..258039fb301 100644
--- a/arch/powerpc/kernel/kprobes.c
+++ b/arch/powerpc/kernel/kprobes.c
@@ -1,6 +1,5 @@
 /*
  *  Kernel Probes (KProbes)
- *  arch/ppc64/kernel/kprobes.c
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
diff --git a/arch/powerpc/kernel/of_device.c b/arch/powerpc/kernel/of_device.c
index 22d83d4d1af..9feeeef5a87 100644
--- a/arch/powerpc/kernel/of_device.c
+++ b/arch/powerpc/kernel/of_device.c
@@ -147,15 +147,12 @@ postcore_initcall(of_bus_driver_init);
 
 int of_register_driver(struct of_platform_driver *drv)
 {
-	int count = 0;
-
 	/* initialize common driver fields */
 	drv->driver.name = drv->name;
 	drv->driver.bus = &of_platform_bus_type;
 
 	/* register with core */
-	count = driver_register(&drv->driver);
-	return count ? count : 1;
+	return driver_register(&drv->driver);
 }
 
 void of_unregister_driver(struct of_platform_driver *drv)
diff --git a/arch/powerpc/kernel/pci_iommu.c b/arch/powerpc/kernel/pci_iommu.c
index bdf15dbbf4f..c336f3e31cf 100644
--- a/arch/powerpc/kernel/pci_iommu.c
+++ b/arch/powerpc/kernel/pci_iommu.c
@@ -1,5 +1,4 @@
 /*
- * arch/ppc64/kernel/pci_iommu.c
  * Copyright (C) 2001 Mike Corrigan & Dave Engebretsen, IBM Corporation
  *
  * Rewrite, cleanup, new allocation schemes:
diff --git a/arch/powerpc/kernel/ppc_ksyms.c b/arch/powerpc/kernel/ppc_ksyms.c
index 63ecbec0520..dfa5398ab3c 100644
--- a/arch/powerpc/kernel/ppc_ksyms.c
+++ b/arch/powerpc/kernel/ppc_ksyms.c
@@ -57,7 +57,6 @@ extern void machine_check_exception(struct pt_regs *regs);
 extern void alignment_exception(struct pt_regs *regs);
 extern void program_check_exception(struct pt_regs *regs);
 extern void single_step_exception(struct pt_regs *regs);
-extern int pmac_newworld;
 extern int sys_sigreturn(struct pt_regs *regs);
 
 EXPORT_SYMBOL(clear_pages);
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index c225cf154bf..1770a066c21 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -1,6 +1,4 @@
 /*
- *  arch/ppc/kernel/process.c
- *
  *  Derived from "arch/i386/kernel/process.c"
  *    Copyright (C) 1995  Linus Torvalds
  *
@@ -47,9 +45,9 @@
 #include <asm/mmu.h>
 #include <asm/prom.h>
 #include <asm/machdep.h>
+#include <asm/time.h>
 #ifdef CONFIG_PPC64
 #include <asm/firmware.h>
-#include <asm/time.h>
 #endif
 
 extern unsigned long _get_SP(void);
@@ -330,6 +328,11 @@ struct task_struct *__switch_to(struct task_struct *prev,
 #endif
 
 	local_irq_save(flags);
+
+	account_system_vtime(current);
+	account_process_vtime(current);
+	calculate_steal_time();
+
 	last = _switch(old_thread, new_thread);
 
 	local_irq_restore(flags);
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index 6dbd2172677..d63cd562d9d 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -829,10 +829,6 @@ void __init unflatten_device_tree(void)
 
 	/* Allocate memory for the expanded device tree */
 	mem = lmb_alloc(size + 4, __alignof__(struct device_node));
-	if (!mem) {
-		DBG("Couldn't allocate memory with lmb_alloc()!\n");
-		panic("Couldn't allocate memory with lmb_alloc()!\n");
-	}
 	mem = (unsigned long) __va(mem);
 
 	((u32 *)mem)[size / 4] = 0xdeadbeef;
diff --git a/arch/powerpc/kernel/ptrace-common.h b/arch/powerpc/kernel/ptrace-common.h
index 5ccbdbe0d5c..c42a860c8d2 100644
--- a/arch/powerpc/kernel/ptrace-common.h
+++ b/arch/powerpc/kernel/ptrace-common.h
@@ -1,6 +1,4 @@
 /*
- *  linux/arch/ppc64/kernel/ptrace-common.h
- *
  *    Copyright (c) 2002 Stephen Rothwell, IBM Coproration
  *    Extracted from ptrace.c and ptrace32.c
  *
diff --git a/arch/powerpc/kernel/rtas-proc.c b/arch/powerpc/kernel/rtas-proc.c
index 7a95b8a2835..1f03fb28cc0 100644
--- a/arch/powerpc/kernel/rtas-proc.c
+++ b/arch/powerpc/kernel/rtas-proc.c
@@ -1,5 +1,4 @@
 /*
- *   arch/ppc64/kernel/rtas-proc.c
  *   Copyright (C) 2000 Tilmann Bitterberg
  *   (tilmann@bitterberg.de)
  *
diff --git a/arch/powerpc/kernel/rtas_pci.c b/arch/powerpc/kernel/rtas_pci.c
index 7442775ef2a..57b539a03fa 100644
--- a/arch/powerpc/kernel/rtas_pci.c
+++ b/arch/powerpc/kernel/rtas_pci.c
@@ -1,6 +1,4 @@
 /*
- * arch/ppc64/kernel/rtas_pci.c
- *
  * Copyright (C) 2001 Dave Engebretsen, IBM Corporation
  * Copyright (C) 2003 Anton Blanchard <anton@au.ibm.com>, IBM
  *
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index f96c49b03ba..2f3fdad3559 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -497,8 +497,6 @@ void __init setup_system(void)
 #endif
 	printk("-----------------------------------------------------\n");
 
-	mm_init_ppc64();
-
 	DBG(" <- setup_system()\n");
 }
 
diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c
index 4324f8a8ba2..47f910380a6 100644
--- a/arch/powerpc/kernel/signal_64.c
+++ b/arch/powerpc/kernel/signal_64.c
@@ -1,6 +1,4 @@
 /*
- *  linux/arch/ppc64/kernel/signal.c
- *
  *  PowerPC version 
  *    Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
  *
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 13595a64f01..805eaedbc30 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -541,7 +541,7 @@ int __devinit start_secondary(void *unused)
 		smp_ops->take_timebase();
 
 	if (system_state > SYSTEM_BOOTING)
-		per_cpu(last_jiffy, cpu) = get_tb();
+		snapshot_timebase();
 
 	spin_lock(&call_lock);
 	cpu_set(cpu, cpu_online_map);
@@ -573,6 +573,8 @@ void __init smp_cpus_done(unsigned int max_cpus)
 
 	set_cpus_allowed(current, old_mask);
 
+	snapshot_timebases();
+
 	dump_numa_cpu_topology();
 }
 
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 86f7e3d154d..4a27218a086 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -51,6 +51,7 @@
 #include <linux/percpu.h>
 #include <linux/rtc.h>
 #include <linux/jiffies.h>
+#include <linux/posix-timers.h>
 
 #include <asm/io.h>
 #include <asm/processor.h>
@@ -98,6 +99,7 @@ unsigned long tb_ticks_per_jiffy;
 unsigned long tb_ticks_per_usec = 100; /* sane default */
 EXPORT_SYMBOL(tb_ticks_per_usec);
 unsigned long tb_ticks_per_sec;
+EXPORT_SYMBOL(tb_ticks_per_sec);	/* for cputime_t conversions */
 u64 tb_to_xs;
 unsigned tb_to_us;
 
@@ -135,6 +137,224 @@ unsigned long tb_last_stamp;
  */
 DEFINE_PER_CPU(unsigned long, last_jiffy);
 
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING
+/*
+ * Factors for converting from cputime_t (timebase ticks) to
+ * jiffies, milliseconds, seconds, and clock_t (1/USER_HZ seconds).
+ * These are all stored as 0.64 fixed-point binary fractions.
+ */
+u64 __cputime_jiffies_factor;
+EXPORT_SYMBOL(__cputime_jiffies_factor);
+u64 __cputime_msec_factor;
+EXPORT_SYMBOL(__cputime_msec_factor);
+u64 __cputime_sec_factor;
+EXPORT_SYMBOL(__cputime_sec_factor);
+u64 __cputime_clockt_factor;
+EXPORT_SYMBOL(__cputime_clockt_factor);
+
+static void calc_cputime_factors(void)
+{
+	struct div_result res;
+
+	div128_by_32(HZ, 0, tb_ticks_per_sec, &res);
+	__cputime_jiffies_factor = res.result_low;
+	div128_by_32(1000, 0, tb_ticks_per_sec, &res);
+	__cputime_msec_factor = res.result_low;
+	div128_by_32(1, 0, tb_ticks_per_sec, &res);
+	__cputime_sec_factor = res.result_low;
+	div128_by_32(USER_HZ, 0, tb_ticks_per_sec, &res);
+	__cputime_clockt_factor = res.result_low;
+}
+
+/*
+ * Read the PURR on systems that have it, otherwise the timebase.
+ */
+static u64 read_purr(void)
+{
+	if (cpu_has_feature(CPU_FTR_PURR))
+		return mfspr(SPRN_PURR);
+	return mftb();
+}
+
+/*
+ * Account time for a transition between system, hard irq
+ * or soft irq state.
+ */
+void account_system_vtime(struct task_struct *tsk)
+{
+	u64 now, delta;
+	unsigned long flags;
+
+	local_irq_save(flags);
+	now = read_purr();
+	delta = now - get_paca()->startpurr;
+	get_paca()->startpurr = now;
+	if (!in_interrupt()) {
+		delta += get_paca()->system_time;
+		get_paca()->system_time = 0;
+	}
+	account_system_time(tsk, 0, delta);
+	local_irq_restore(flags);
+}
+
+/*
+ * Transfer the user and system times accumulated in the paca
+ * by the exception entry and exit code to the generic process
+ * user and system time records.
+ * Must be called with interrupts disabled.
+ */
+void account_process_vtime(struct task_struct *tsk)
+{
+	cputime_t utime;
+
+	utime = get_paca()->user_time;
+	get_paca()->user_time = 0;
+	account_user_time(tsk, utime);
+}
+
+static void account_process_time(struct pt_regs *regs)
+{
+	int cpu = smp_processor_id();
+
+	account_process_vtime(current);
+	run_local_timers();
+	if (rcu_pending(cpu))
+		rcu_check_callbacks(cpu, user_mode(regs));
+	scheduler_tick();
+ 	run_posix_cpu_timers(current);
+}
+
+#ifdef CONFIG_PPC_SPLPAR
+/*
+ * Stuff for accounting stolen time.
+ */
+struct cpu_purr_data {
+	int	initialized;			/* thread is running */
+	u64	tb0;			/* timebase at origin time */
+	u64	purr0;			/* PURR at origin time */
+	u64	tb;			/* last TB value read */
+	u64	purr;			/* last PURR value read */
+	u64	stolen;			/* stolen time so far */
+	spinlock_t lock;
+};
+
+static DEFINE_PER_CPU(struct cpu_purr_data, cpu_purr_data);
+
+static void snapshot_tb_and_purr(void *data)
+{
+	struct cpu_purr_data *p = &__get_cpu_var(cpu_purr_data);
+
+	p->tb0 = mftb();
+	p->purr0 = mfspr(SPRN_PURR);
+	p->tb = p->tb0;
+	p->purr = 0;
+	wmb();
+	p->initialized = 1;
+}
+
+/*
+ * Called during boot when all cpus have come up.
+ */
+void snapshot_timebases(void)
+{
+	int cpu;
+
+	if (!cpu_has_feature(CPU_FTR_PURR))
+		return;
+	for_each_cpu(cpu)
+		spin_lock_init(&per_cpu(cpu_purr_data, cpu).lock);
+	on_each_cpu(snapshot_tb_and_purr, NULL, 0, 1);
+}
+
+void calculate_steal_time(void)
+{
+	u64 tb, purr, t0;
+	s64 stolen;
+	struct cpu_purr_data *p0, *pme, *phim;
+	int cpu;
+
+	if (!cpu_has_feature(CPU_FTR_PURR))
+		return;
+	cpu = smp_processor_id();
+	pme = &per_cpu(cpu_purr_data, cpu);
+	if (!pme->initialized)
+		return;		/* this can happen in early boot */
+	p0 = &per_cpu(cpu_purr_data, cpu & ~1);
+	phim = &per_cpu(cpu_purr_data, cpu ^ 1);
+	spin_lock(&p0->lock);
+	tb = mftb();
+	purr = mfspr(SPRN_PURR) - pme->purr0;
+	if (!phim->initialized || !cpu_online(cpu ^ 1)) {
+		stolen = (tb - pme->tb) - (purr - pme->purr);
+	} else {
+		t0 = pme->tb0;
+		if (phim->tb0 < t0)
+			t0 = phim->tb0;
+		stolen = phim->tb - t0 - phim->purr - purr - p0->stolen;
+	}
+	if (stolen > 0) {
+		account_steal_time(current, stolen);
+		p0->stolen += stolen;
+	}
+	pme->tb = tb;
+	pme->purr = purr;
+	spin_unlock(&p0->lock);
+}
+
+/*
+ * 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)
+{
+	int cpu;
+	u64 purr;
+	struct cpu_purr_data *p0, *pme, *phim;
+	unsigned long flags;
+
+	if (!cpu_has_feature(CPU_FTR_PURR))
+		return;
+	cpu = smp_processor_id();
+	pme = &per_cpu(cpu_purr_data, cpu);
+	p0 = &per_cpu(cpu_purr_data, cpu & ~1);
+	phim = &per_cpu(cpu_purr_data, cpu ^ 1);
+	spin_lock_irqsave(&p0->lock, flags);
+	pme->tb = pme->tb0 = mftb();
+	purr = mfspr(SPRN_PURR);
+	if (!phim->initialized) {
+		pme->purr = 0;
+		pme->purr0 = purr;
+	} else {
+		/* set p->purr and p->purr0 for no change in p0->stolen */
+		pme->purr = phim->tb - phim->tb0 - phim->purr - p0->stolen;
+		pme->purr0 = purr - pme->purr;
+	}
+	pme->initialized = 1;
+	spin_unlock_irqrestore(&p0->lock, flags);
+}
+
+#endif /* CONFIG_PPC_SPLPAR */
+
+#else /* ! CONFIG_VIRT_CPU_ACCOUNTING */
+#define calc_cputime_factors()
+#define account_process_time(regs)	update_process_times(user_mode(regs))
+#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();
+	snapshot_purr();
+}
+
 void __delay(unsigned long loops)
 {
 	unsigned long start;
@@ -392,6 +612,7 @@ static void iSeries_tb_recal(void)
 						new_tb_ticks_per_jiffy, sign, tick_diff );
 				tb_ticks_per_jiffy = new_tb_ticks_per_jiffy;
 				tb_ticks_per_sec   = new_tb_ticks_per_sec;
+				calc_cputime_factors();
 				div128_by_32( XSEC_PER_SEC, 0, tb_ticks_per_sec, &divres );
 				do_gtod.tb_ticks_per_sec = tb_ticks_per_sec;
 				tb_to_xs = divres.result_low;
@@ -440,6 +661,7 @@ void timer_interrupt(struct pt_regs * regs)
 	irq_enter();
 
 	profile_tick(CPU_PROFILING, regs);
+	calculate_steal_time();
 
 #ifdef CONFIG_PPC_ISERIES
 	get_lppaca()->int_dword.fields.decr_int = 0;
@@ -461,7 +683,7 @@ void timer_interrupt(struct pt_regs * regs)
 		 * is the case.
 		 */
 		if (!cpu_is_offline(cpu))
-			update_process_times(user_mode(regs));
+			account_process_time(regs);
 
 		/*
 		 * No need to check whether cpu is offline here; boot_cpuid
@@ -518,13 +740,27 @@ void wakeup_decrementer(void)
 void __init smp_space_timers(unsigned int max_cpus)
 {
 	int i;
+	unsigned long half = tb_ticks_per_jiffy / 2;
 	unsigned long offset = tb_ticks_per_jiffy / max_cpus;
 	unsigned long previous_tb = per_cpu(last_jiffy, boot_cpuid);
 
 	/* make sure tb > per_cpu(last_jiffy, cpu) for all cpus always */
 	previous_tb -= tb_ticks_per_jiffy;
+	/*
+	 * The stolen time calculation for POWER5 shared-processor LPAR
+	 * systems works better if the two threads' timebase interrupts
+	 * are staggered by half a jiffy with respect to each other.
+	 */
 	for_each_cpu(i) {
-		if (i != boot_cpuid) {
+		if (i == boot_cpuid)
+			continue;
+		if (i == (boot_cpuid ^ 1))
+			per_cpu(last_jiffy, i) =
+				per_cpu(last_jiffy, boot_cpuid) - half;
+		else if (i & 1)
+			per_cpu(last_jiffy, i) =
+				per_cpu(last_jiffy, i ^ 1) + half;
+		else {
 			previous_tb += offset;
 			per_cpu(last_jiffy, i) = previous_tb;
 		}
@@ -720,6 +956,7 @@ void __init time_init(void)
 	tb_ticks_per_sec = ppc_tb_freq;
 	tb_ticks_per_usec = ppc_tb_freq / 1000000;
 	tb_to_us = mulhwu_scale_factor(ppc_tb_freq, 1000000);
+	calc_cputime_factors();
 
 	/*
 	 * Calculate the length of each tick in ns.  It will not be
diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c
index 04f7df39ffb..ec837036842 100644
--- a/arch/powerpc/kernel/vdso.c
+++ b/arch/powerpc/kernel/vdso.c
@@ -1,6 +1,4 @@
 /*
- *  linux/arch/ppc64/kernel/vdso.c
- *
  *    Copyright (C) 2004 Benjamin Herrenschmidt, IBM Corp.
  *			 <benh@kernel.crashing.org>
  *