Merge branch 'master' of git+ssh://galak@master.kernel.org/pub/scm/linux/kernel/git/galak/powerpc

17 files changed, 477 insertions, 390 deletions

diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 840aad43a98..18810ac55bc 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -137,6 +137,9 @@ 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/crash.c b/arch/powerpc/kernel/crash.c
index 8c21d378f5d..778f22fd85d 100644
--- a/arch/powerpc/kernel/crash.c
+++ b/arch/powerpc/kernel/crash.c
@@ -134,8 +134,10 @@ static void crash_kexec_prepare_cpus(void)
 	 * the crash CPU will send an IPI and wait for other CPUs to
 	 * respond. If not, proceed the kexec boot even though we failed to
 	 * capture other CPU states.
+	 * Delay of at least 10 seconds.
 	 */
-	msecs = 1000000;
+	printk(KERN_ALERT "Sending IPI to other cpus...\n");
+	msecs = 10000;
 	while ((atomic_read(&waiting_for_crash_ipi) > 0) && (--msecs > 0)) {
 		barrier();
 		mdelay(1);
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index 79a0c910f0d..8f606c1889f 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -61,6 +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)
@@ -168,8 +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
@@ -536,6 +538,7 @@ 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/head_32.S b/arch/powerpc/kernel/head_32.S
index 03b25f9359f..a0579e859b2 100644
--- a/arch/powerpc/kernel/head_32.S
+++ b/arch/powerpc/kernel/head_32.S
@@ -714,6 +714,7 @@ AltiVecUnavailable:
 #ifdef CONFIG_ALTIVEC
 	bne	load_up_altivec		/* if from user, just load it up */
 #endif /* CONFIG_ALTIVEC */
+	addi	r3,r1,STACK_FRAME_OVERHEAD
 	EXC_XFER_EE_LITE(0xf20, altivec_unavailable_exception)
 
 PerformanceMonitor:
diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S
index 7ebb73665e9..be3ae773357 100644
--- a/arch/powerpc/kernel/head_64.S
+++ b/arch/powerpc/kernel/head_64.S
@@ -137,7 +137,7 @@ _GLOBAL(__secondary_hold)
 	ori	r24,r24,MSR_RI
 	mtmsrd	r24			/* RI on */
 
-	/* Grab our linux cpu number */
+	/* Grab our physical cpu number */
 	mr	r24,r3
 
 	/* Tell the master cpu we're here */
@@ -151,12 +151,7 @@ _GLOBAL(__secondary_hold)
 	cmpdi	0,r4,1
 	bne	100b
 
-#ifdef CONFIG_HMT
-	SET_REG_IMMEDIATE(r4, .hmt_init)
-	mtctr	r4
-	bctr
-#else
-#ifdef CONFIG_SMP
+#if defined(CONFIG_SMP) || defined(CONFIG_KEXEC)
 	LOAD_REG_IMMEDIATE(r4, .pSeries_secondary_smp_init)
 	mtctr	r4
 	mr	r3,r24
@@ -164,7 +159,6 @@ _GLOBAL(__secondary_hold)
 #else
 	BUG_OPCODE
 #endif
-#endif
 
 /* This value is used to mark exception frames on the stack. */
 	.section ".toc","aw"
@@ -283,6 +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	*/ \
@@ -319,7 +314,6 @@ exception_marker:
 label##_pSeries:					\
 	HMT_MEDIUM;					\
 	mtspr	SPRN_SPRG1,r13;		/* save r13 */	\
-	RUNLATCH_ON(r13);				\
 	EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, label##_common)
 
 #define STD_EXCEPTION_ISERIES(n, label, area)		\
@@ -327,7 +321,6 @@ label##_pSeries:					\
 label##_iSeries:					\
 	HMT_MEDIUM;					\
 	mtspr	SPRN_SPRG1,r13;		/* save r13 */	\
-	RUNLATCH_ON(r13);				\
 	EXCEPTION_PROLOG_ISERIES_1(area);		\
 	EXCEPTION_PROLOG_ISERIES_2;			\
 	b	label##_common
@@ -337,7 +330,6 @@ label##_iSeries:					\
 label##_iSeries:							\
 	HMT_MEDIUM;							\
 	mtspr	SPRN_SPRG1,r13;		/* save r13 */			\
-	RUNLATCH_ON(r13);						\
 	EXCEPTION_PROLOG_ISERIES_1(PACA_EXGEN);				\
 	lbz	r10,PACAPROCENABLED(r13);				\
 	cmpwi	0,r10,0;						\
@@ -390,6 +382,7 @@ label##_common:						\
 label##_common:						\
 	EXCEPTION_PROLOG_COMMON(trap, PACA_EXGEN);	\
 	DISABLE_INTS;					\
+	bl	.ppc64_runlatch_on;			\
 	addi	r3,r1,STACK_FRAME_OVERHEAD;		\
 	bl	hdlr;					\
 	b	.ret_from_except_lite
@@ -407,7 +400,6 @@ __start_interrupts:
 _machine_check_pSeries:
 	HMT_MEDIUM
 	mtspr	SPRN_SPRG1,r13		/* save r13 */
-	RUNLATCH_ON(r13)
 	EXCEPTION_PROLOG_PSERIES(PACA_EXMC, machine_check_common)
 
 	. = 0x300
@@ -434,7 +426,6 @@ END_FTR_SECTION_IFCLR(CPU_FTR_SLB)
 data_access_slb_pSeries:
 	HMT_MEDIUM
 	mtspr	SPRN_SPRG1,r13
-	RUNLATCH_ON(r13)
 	mfspr	r13,SPRN_SPRG3		/* get paca address into r13 */
 	std	r3,PACA_EXSLB+EX_R3(r13)
 	mfspr	r3,SPRN_DAR
@@ -460,7 +451,6 @@ data_access_slb_pSeries:
 instruction_access_slb_pSeries:
 	HMT_MEDIUM
 	mtspr	SPRN_SPRG1,r13
-	RUNLATCH_ON(r13)
 	mfspr	r13,SPRN_SPRG3		/* get paca address into r13 */
 	std	r3,PACA_EXSLB+EX_R3(r13)
 	mfspr	r3,SPRN_SRR0		/* SRR0 is faulting address */
@@ -491,7 +481,6 @@ instruction_access_slb_pSeries:
 	.globl	system_call_pSeries
 system_call_pSeries:
 	HMT_MEDIUM
-	RUNLATCH_ON(r9)
 	mr	r9,r13
 	mfmsr	r10
 	mfspr	r13,SPRN_SPRG3
@@ -575,7 +564,6 @@ slb_miss_user_pseries:
 system_reset_fwnmi:
 	HMT_MEDIUM
 	mtspr	SPRN_SPRG1,r13		/* save r13 */
-	RUNLATCH_ON(r13)
 	EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, system_reset_common)
 
 	.globl machine_check_fwnmi
@@ -583,7 +571,6 @@ system_reset_fwnmi:
 machine_check_fwnmi:
 	HMT_MEDIUM
 	mtspr	SPRN_SPRG1,r13		/* save r13 */
-	RUNLATCH_ON(r13)
 	EXCEPTION_PROLOG_PSERIES(PACA_EXMC, machine_check_common)
 
 #ifdef CONFIG_PPC_ISERIES
@@ -858,6 +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)
@@ -894,7 +889,6 @@ unrecov_fer:
 	.align	7
 	.globl data_access_common
 data_access_common:
-	RUNLATCH_ON(r10)		/* It wont fit in the 0x300 handler */
 	mfspr	r10,SPRN_DAR
 	std	r10,PACA_EXGEN+EX_DAR(r13)
 	mfspr	r10,SPRN_DSISR
@@ -1042,6 +1036,7 @@ hardware_interrupt_common:
 	EXCEPTION_PROLOG_COMMON(0x500, PACA_EXGEN)
 hardware_interrupt_entry:
 	DISABLE_INTS
+	bl	.ppc64_runlatch_on
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	.do_IRQ
 	b	.ret_from_except_lite
@@ -1816,22 +1811,6 @@ _STATIC(start_here_multiplatform)
 	ori	r6,r6,MSR_RI
 	mtmsrd	r6			/* RI on */
 
-#ifdef CONFIG_HMT
-	/* Start up the second thread on cpu 0 */
-	mfspr	r3,SPRN_PVR
-	srwi	r3,r3,16
-	cmpwi	r3,0x34			/* Pulsar  */
-	beq	90f
-	cmpwi	r3,0x36			/* Icestar */
-	beq	90f
-	cmpwi	r3,0x37			/* SStar   */
-	beq	90f
-	b	91f			/* HMT not supported */
-90:	li	r3,0
-	bl	.hmt_start_secondary
-91:
-#endif
-
 	/* The following gets the stack and TOC set up with the regs */
 	/* pointing to the real addr of the kernel stack.  This is   */
 	/* all done to support the C function call below which sets  */
@@ -1945,77 +1924,8 @@ _STATIC(start_here_common)
 
 	bl .start_kernel
 
-_GLOBAL(hmt_init)
-#ifdef CONFIG_HMT
-	LOAD_REG_IMMEDIATE(r5, hmt_thread_data)
-	mfspr	r7,SPRN_PVR
-	srwi	r7,r7,16
-	cmpwi	r7,0x34			/* Pulsar  */
-	beq	90f
-	cmpwi	r7,0x36			/* Icestar */
-	beq	91f
-	cmpwi	r7,0x37			/* SStar   */
-	beq	91f
-	b	101f
-90:	mfspr	r6,SPRN_PIR
-	andi.	r6,r6,0x1f
-	b	92f
-91:	mfspr	r6,SPRN_PIR
-	andi.	r6,r6,0x3ff
-92:	sldi	r4,r24,3
-	stwx	r6,r5,r4
-	bl	.hmt_start_secondary
-	b	101f
-
-__hmt_secondary_hold:
-	LOAD_REG_IMMEDIATE(r5, hmt_thread_data)
-	clrldi	r5,r5,4
-	li	r7,0
-	mfspr	r6,SPRN_PIR
-	mfspr	r8,SPRN_PVR
-	srwi	r8,r8,16
-	cmpwi	r8,0x34
-	bne	93f
-	andi.	r6,r6,0x1f
-	b	103f
-93:	andi.	r6,r6,0x3f
-
-103:	lwzx	r8,r5,r7
-	cmpw	r8,r6
-	beq	104f
-	addi	r7,r7,8
-	b	103b
-
-104:	addi	r7,r7,4
-	lwzx	r9,r5,r7
-	mr	r24,r9
-101:
-#endif
-	mr	r3,r24
-	b	.pSeries_secondary_smp_init
-
-#ifdef CONFIG_HMT
-_GLOBAL(hmt_start_secondary)
-	LOAD_REG_IMMEDIATE(r4,__hmt_secondary_hold)
-	clrldi	r4,r4,4
-	mtspr	SPRN_NIADORM, r4
-	mfspr	r4, SPRN_MSRDORM
-	li	r5, -65
-	and	r4, r4, r5
-	mtspr	SPRN_MSRDORM, r4
-	lis	r4,0xffef
-	ori	r4,r4,0x7403
-	mtspr	SPRN_TSC, r4
-	li	r4,0x1f4
-	mtspr	SPRN_TST, r4
-	mfspr	r4, SPRN_HID0
-	ori	r4, r4, 0x1
-	mtspr	SPRN_HID0, r4
-	mfspr	r4, SPRN_CTRLF
-	oris	r4, r4, 0x40
-	mtspr	SPRN_CTRLT, r4
-	blr
-#endif
+	/* Not reached */
+	BUG_OPCODE
 
 /*
  * We put a few things here that have to be page-aligned.
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index edb2b00edbd..24dc8117b82 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -369,6 +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];
@@ -392,10 +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;
@@ -403,19 +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/lparcfg.c b/arch/powerpc/kernel/lparcfg.c
index 1ae96a8ed7e..e789fef4eb8 100644
--- a/arch/powerpc/kernel/lparcfg.c
+++ b/arch/powerpc/kernel/lparcfg.c
@@ -341,7 +341,7 @@ static int lparcfg_data(struct seq_file *m, void *v)
 	const char *system_id = "";
 	unsigned int *lp_index_ptr, lp_index = 0;
 	struct device_node *rtas_node;
-	int *lrdrp;
+	int *lrdrp = NULL;
 
 	rootdn = find_path_device("/");
 	if (rootdn) {
@@ -362,7 +362,9 @@ static int lparcfg_data(struct seq_file *m, void *v)
 	seq_printf(m, "partition_id=%d\n", (int)lp_index);
 
 	rtas_node = find_path_device("/rtas");
-	lrdrp = (int *)get_property(rtas_node, "ibm,lrdr-capacity", NULL);
+	if (rtas_node)
+		lrdrp = (int *)get_property(rtas_node, "ibm,lrdr-capacity",
+		                            NULL);
 
 	if (lrdrp == NULL) {
 		partition_potential_processors = vdso_data->processorCount;
diff --git a/arch/powerpc/kernel/machine_kexec_64.c b/arch/powerpc/kernel/machine_kexec_64.c
index d6431440c54..ee166c58664 100644
--- a/arch/powerpc/kernel/machine_kexec_64.c
+++ b/arch/powerpc/kernel/machine_kexec_64.c
@@ -26,8 +26,6 @@
 #include <asm/prom.h>
 #include <asm/smp.h>
 
-#define HASH_GROUP_SIZE 0x80	/* size of each hash group, asm/mmu.h */
-
 int default_machine_kexec_prepare(struct kimage *image)
 {
 	int i;
@@ -61,7 +59,7 @@ int default_machine_kexec_prepare(struct kimage *image)
 	 */
 	if (htab_address) {
 		low = __pa(htab_address);
-		high = low + (htab_hash_mask + 1) * HASH_GROUP_SIZE;
+		high = low + htab_size_bytes;
 
 		for (i = 0; i < image->nr_segments; i++) {
 			begin = image->segment[i].mem;
@@ -294,7 +292,7 @@ void default_machine_kexec(struct kimage *image)
 }
 
 /* Values we need to export to the second kernel via the device tree. */
-static unsigned long htab_base, htab_size, kernel_end;
+static unsigned long htab_base, kernel_end;
 
 static struct property htab_base_prop = {
 	.name = "linux,htab-base",
@@ -305,7 +303,7 @@ static struct property htab_base_prop = {
 static struct property htab_size_prop = {
 	.name = "linux,htab-size",
 	.length = sizeof(unsigned long),
-	.value = (unsigned char *)&htab_size,
+	.value = (unsigned char *)&htab_size_bytes,
 };
 
 static struct property kernel_end_prop = {
@@ -331,8 +329,6 @@ static void __init export_htab_values(void)
 
 	htab_base = __pa(htab_address);
 	prom_add_property(node, &htab_base_prop);
-
-	htab_size = 1UL << ppc64_pft_size;
 	prom_add_property(node, &htab_size_prop);
 
  out:
diff --git a/arch/powerpc/kernel/ppc_ksyms.c b/arch/powerpc/kernel/ppc_ksyms.c
index b212d3e64b8..af32922db65 100644
--- a/arch/powerpc/kernel/ppc_ksyms.c
+++ b/arch/powerpc/kernel/ppc_ksyms.c
@@ -78,15 +78,8 @@ EXPORT_SYMBOL(sys_sigreturn);
 EXPORT_SYMBOL(strcpy);
 EXPORT_SYMBOL(strncpy);
 EXPORT_SYMBOL(strcat);
-EXPORT_SYMBOL(strncat);
-EXPORT_SYMBOL(strchr);
-EXPORT_SYMBOL(strrchr);
-EXPORT_SYMBOL(strpbrk);
-EXPORT_SYMBOL(strstr);
 EXPORT_SYMBOL(strlen);
-EXPORT_SYMBOL(strnlen);
 EXPORT_SYMBOL(strcmp);
-EXPORT_SYMBOL(strncmp);
 EXPORT_SYMBOL(strcasecmp);
 
 EXPORT_SYMBOL(csum_partial);
@@ -184,9 +177,6 @@ EXPORT_SYMBOL(adb_try_handler_change);
 EXPORT_SYMBOL(cuda_request);
 EXPORT_SYMBOL(cuda_poll);
 #endif /* CONFIG_ADB_CUDA */
-#ifdef CONFIG_PPC_PMAC
-EXPORT_SYMBOL(sys_ctrler);
-#endif
 #ifdef CONFIG_VT
 EXPORT_SYMBOL(kd_mksound);
 #endif
@@ -204,7 +194,6 @@ EXPORT_SYMBOL(__lshrdi3);
 EXPORT_SYMBOL(memcpy);
 EXPORT_SYMBOL(memset);
 EXPORT_SYMBOL(memmove);
-EXPORT_SYMBOL(memscan);
 EXPORT_SYMBOL(memcmp);
 EXPORT_SYMBOL(memchr);
 
@@ -213,7 +202,6 @@ EXPORT_SYMBOL(screen_info);
 #endif
 
 #ifdef CONFIG_PPC32
-EXPORT_SYMBOL(__delay);
 EXPORT_SYMBOL(timer_interrupt);
 EXPORT_SYMBOL(irq_desc);
 EXPORT_SYMBOL(tb_ticks_per_jiffy);
@@ -221,10 +209,6 @@ EXPORT_SYMBOL(console_drivers);
 EXPORT_SYMBOL(cacheable_memcpy);
 #endif
 
-EXPORT_SYMBOL(__up);
-EXPORT_SYMBOL(__down);
-EXPORT_SYMBOL(__down_interruptible);
-
 #ifdef  CONFIG_8xx
 EXPORT_SYMBOL(cpm_install_handler);
 EXPORT_SYMBOL(cpm_free_handler);
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 1201880cab4..1770a066c21 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -45,9 +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);
@@ -328,6 +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);
@@ -886,3 +891,35 @@ void dump_stack(void)
 	show_stack(current, NULL);
 }
 EXPORT_SYMBOL(dump_stack);
+
+#ifdef CONFIG_PPC64
+void ppc64_runlatch_on(void)
+{
+	unsigned long ctrl;
+
+	if (cpu_has_feature(CPU_FTR_CTRL) && !test_thread_flag(TIF_RUNLATCH)) {
+		HMT_medium();
+
+		ctrl = mfspr(SPRN_CTRLF);
+		ctrl |= CTRL_RUNLATCH;
+		mtspr(SPRN_CTRLT, ctrl);
+
+		set_thread_flag(TIF_RUNLATCH);
+	}
+}
+
+void ppc64_runlatch_off(void)
+{
+	unsigned long ctrl;
+
+	if (cpu_has_feature(CPU_FTR_CTRL) && test_thread_flag(TIF_RUNLATCH)) {
+		HMT_medium();
+
+		clear_thread_flag(TIF_RUNLATCH);
+
+		ctrl = mfspr(SPRN_CTRLF);
+		ctrl &= ~CTRL_RUNLATCH;
+		mtspr(SPRN_CTRLT, ctrl);
+	}
+}
+#endif
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index 82d117c60d7..d63cd562d9d 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -816,8 +816,6 @@ void __init unflatten_device_tree(void)
 {
 	unsigned long start, mem, size;
 	struct device_node **allnextp = &allnodes;
-	char *p = NULL;
-	int l = 0;
 
 	DBG(" -> unflatten_device_tree()\n");
 
@@ -853,19 +851,6 @@ void __init unflatten_device_tree(void)
 	if (of_chosen == NULL)
 		of_chosen = of_find_node_by_path("/chosen@0");
 
-	/* Retreive command line */
-	if (of_chosen != NULL) {
-		p = (char *)get_property(of_chosen, "bootargs", &l);
-		if (p != NULL && l > 0)
-			strlcpy(cmd_line, p, min(l, COMMAND_LINE_SIZE));
-	}
-#ifdef CONFIG_CMDLINE
-	if (l == 0 || (l == 1 && (*p) == 0))
-		strlcpy(cmd_line, CONFIG_CMDLINE, COMMAND_LINE_SIZE);
-#endif /* CONFIG_CMDLINE */
-
-	DBG("Command line is: %s\n", cmd_line);
-
 	DBG(" <- unflatten_device_tree()\n");
 }
 
@@ -936,6 +921,8 @@ static int __init early_init_dt_scan_chosen(unsigned long node,
 {
 	u32 *prop;
 	unsigned long *lprop;
+	unsigned long l;
+	char *p;
 
 	DBG("search \"chosen\", depth: %d, uname: %s\n", depth, uname);
 
@@ -1000,6 +987,41 @@ static int __init early_init_dt_scan_chosen(unsigned long node,
                crashk_res.end = crashk_res.start + *lprop - 1;
 #endif
 
+	/* Retreive command line */
+ 	p = of_get_flat_dt_prop(node, "bootargs", &l);
+	if (p != NULL && l > 0)
+		strlcpy(cmd_line, p, min((int)l, COMMAND_LINE_SIZE));
+
+#ifdef CONFIG_CMDLINE
+	if (l == 0 || (l == 1 && (*p) == 0))
+		strlcpy(cmd_line, CONFIG_CMDLINE, COMMAND_LINE_SIZE);
+#endif /* CONFIG_CMDLINE */
+
+	DBG("Command line is: %s\n", cmd_line);
+
+	if (strstr(cmd_line, "mem=")) {
+		char *p, *q;
+		unsigned long maxmem = 0;
+
+		for (q = cmd_line; (p = strstr(q, "mem=")) != 0; ) {
+			q = p + 4;
+			if (p > cmd_line && p[-1] != ' ')
+				continue;
+			maxmem = simple_strtoul(q, &q, 0);
+			if (*q == 'k' || *q == 'K') {
+				maxmem <<= 10;
+				++q;
+			} else if (*q == 'm' || *q == 'M') {
+				maxmem <<= 20;
+				++q;
+			} else if (*q == 'g' || *q == 'G') {
+				maxmem <<= 30;
+				++q;
+			}
+		}
+		memory_limit = maxmem;
+	}
+
 	/* break now */
 	return 1;
 }
@@ -1120,7 +1142,7 @@ static void __init early_reserve_mem(void)
 			size_32 = *(reserve_map_32++);
 			if (size_32 == 0)
 				break;
-			DBG("reserving: %lx -> %lx\n", base_32, size_32);
+			DBG("reserving: %x -> %x\n", base_32, size_32);
 			lmb_reserve(base_32, size_32);
 		}
 		return;
diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index ec7153f4d47..d34fe537400 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -205,14 +205,6 @@ static cell_t __initdata regbuf[1024];
 
 #define MAX_CPU_THREADS 2
 
-/* TO GO */
-#ifdef CONFIG_HMT
-struct {
-	unsigned int pir;
-	unsigned int threadid;
-} hmt_thread_data[NR_CPUS];
-#endif /* CONFIG_HMT */
-
 /*
  * Error results ... some OF calls will return "-1" on error, some
  * will return 0, some will return either. To simplify, here are
@@ -1319,10 +1311,6 @@ static void __init prom_hold_cpus(void)
 	 */
 	*spinloop = 0;
 
-#ifdef CONFIG_HMT
-	for (i = 0; i < NR_CPUS; i++)
-		RELOC(hmt_thread_data)[i].pir = 0xdeadbeef;
-#endif
 	/* look for cpus */
 	for (node = 0; prom_next_node(&node); ) {
 		type[0] = 0;
@@ -1389,32 +1377,6 @@ static void __init prom_hold_cpus(void)
 		/* Reserve cpu #s for secondary threads.   They start later. */
 		cpuid += cpu_threads;
 	}
-#ifdef CONFIG_HMT
-	/* Only enable HMT on processors that provide support. */
-	if (__is_processor(PV_PULSAR) || 
-	    __is_processor(PV_ICESTAR) ||
-	    __is_processor(PV_SSTAR)) {
-		prom_printf("    starting secondary threads\n");
-
-		for (i = 0; i < NR_CPUS; i += 2) {
-			if (!cpu_online(i))
-				continue;
-
-			if (i == 0) {
-				unsigned long pir = mfspr(SPRN_PIR);
-				if (__is_processor(PV_PULSAR)) {
-					RELOC(hmt_thread_data)[i].pir = 
-						pir & 0x1f;
-				} else {
-					RELOC(hmt_thread_data)[i].pir = 
-						pir & 0x3ff;
-				}
-			}
-		}
-	} else {
-		prom_printf("Processor is not HMT capable\n");
-	}
-#endif
 
 	if (cpuid > NR_CPUS)
 		prom_printf("WARNING: maximum CPUs (" __stringify(NR_CPUS)
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index a717dff695e..f96c49b03ba 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -311,8 +311,6 @@ void smp_release_cpus(void)
 
 	DBG(" <- smp_release_cpus()\n");
 }
-#else
-#define smp_release_cpus()
 #endif /* CONFIG_SMP || CONFIG_KEXEC */
 
 /*
@@ -473,10 +471,12 @@ void __init setup_system(void)
 	check_smt_enabled();
 	smp_setup_cpu_maps();
 
+#ifdef CONFIG_SMP
 	/* Release secondary cpus out of their spinloops at 0x60 now that
 	 * we can map physical -> logical CPU ids
 	 */
 	smp_release_cpus();
+#endif
 
 	printk("Starting Linux PPC64 %s\n", system_utsname.version);
 
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/sys_ppc32.c b/arch/powerpc/kernel/sys_ppc32.c
index 475249dc235..cd75ab2908f 100644
--- a/arch/powerpc/kernel/sys_ppc32.c
+++ b/arch/powerpc/kernel/sys_ppc32.c
@@ -176,7 +176,6 @@ struct timex32 {
 };
 
 extern int do_adjtimex(struct timex *);
-extern void ppc_adjtimex(void);
 
 asmlinkage long compat_sys_adjtimex(struct timex32 __user *utp)
 {
@@ -209,9 +208,6 @@ asmlinkage long compat_sys_adjtimex(struct timex32 __user *utp)
 
 	ret = do_adjtimex(&txc);
 
-	/* adjust the conversion of TB to time of day to track adjtimex */
-	ppc_adjtimex();
-
 	if(put_user(txc.modes, &utp->modes) ||
 	   __put_user(txc.offset, &utp->offset) ||
 	   __put_user(txc.freq, &utp->freq) ||
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 1886045a2fd..4f20a5f15d4 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -50,6 +50,8 @@
 #include <linux/security.h>
 #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>
@@ -97,9 +99,18 @@ 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;
-unsigned long processor_freq;
+
+#define TICKLEN_SCALE	(SHIFT_SCALE - 10)
+u64 last_tick_len;	/* units are ns / 2^TICKLEN_SCALE */
+u64 ticklen_to_xs;	/* 0.64 fraction */
+
+/* If last_tick_len corresponds to about 1/HZ seconds, then
+   last_tick_len << TICKLEN_SHIFT will be about 2^63. */
+#define TICKLEN_SHIFT	(63 - 30 - TICKLEN_SCALE + SHIFT_HZ)
+
 DEFINE_SPINLOCK(rtc_lock);
 EXPORT_SYMBOL_GPL(rtc_lock);
 
@@ -113,10 +124,6 @@ extern unsigned long wall_jiffies;
 extern struct timezone sys_tz;
 static long timezone_offset;
 
-void ppc_adjtimex(void);
-
-static unsigned adjusting_time = 0;
-
 unsigned long ppc_proc_freq;
 unsigned long ppc_tb_freq;
 
@@ -130,6 +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;
@@ -178,8 +403,7 @@ static __inline__ void timer_check_rtc(void)
          */
         if (ppc_md.set_rtc_time && ntp_synced() &&
 	    xtime.tv_sec - last_rtc_update >= 659 &&
-	    abs((xtime.tv_nsec/1000) - (1000000-1000000/HZ)) < 500000/HZ &&
-	    jiffies - wall_jiffies == 1) {
+	    abs((xtime.tv_nsec/1000) - (1000000-1000000/HZ)) < 500000/HZ) {
 		struct rtc_time tm;
 		to_tm(xtime.tv_sec + 1 + timezone_offset, &tm);
 		tm.tm_year -= 1900;
@@ -226,15 +450,14 @@ void do_gettimeofday(struct timeval *tv)
 	if (__USE_RTC()) {
 		/* do this the old way */
 		unsigned long flags, seq;
-		unsigned int sec, nsec, usec, lost;
+		unsigned int sec, nsec, usec;
 
 		do {
 			seq = read_seqbegin_irqsave(&xtime_lock, flags);
 			sec = xtime.tv_sec;
 			nsec = xtime.tv_nsec + tb_ticks_since(tb_last_stamp);
-			lost = jiffies - wall_jiffies;
 		} while (read_seqretry_irqrestore(&xtime_lock, seq, flags));
-		usec = nsec / 1000 + lost * (1000000 / HZ);
+		usec = nsec / 1000;
 		while (usec >= 1000000) {
 			usec -= 1000000;
 			++sec;
@@ -248,23 +471,6 @@ void do_gettimeofday(struct timeval *tv)
 
 EXPORT_SYMBOL(do_gettimeofday);
 
-/* Synchronize xtime with do_gettimeofday */ 
-
-static inline void timer_sync_xtime(unsigned long cur_tb)
-{
-#ifdef CONFIG_PPC64
-	/* why do we do this? */
-	struct timeval my_tv;
-
-	__do_gettimeofday(&my_tv, cur_tb);
-
-	if (xtime.tv_sec <= my_tv.tv_sec) {
-		xtime.tv_sec = my_tv.tv_sec;
-		xtime.tv_nsec = my_tv.tv_usec * 1000;
-	}
-#endif
-}
-
 /*
  * There are two copies of tb_to_xs and stamp_xsec so that no
  * lock is needed to access and use these values in
@@ -323,15 +529,30 @@ static __inline__ void timer_recalc_offset(u64 cur_tb)
 {
 	unsigned long offset;
 	u64 new_stamp_xsec;
+	u64 tlen, t2x;
 
 	if (__USE_RTC())
 		return;
+	tlen = current_tick_length();
 	offset = cur_tb - do_gtod.varp->tb_orig_stamp;
-	if ((offset & 0x80000000u) == 0)
-		return;
-	new_stamp_xsec = do_gtod.varp->stamp_xsec
-		+ mulhdu(offset, do_gtod.varp->tb_to_xs);
-	update_gtod(cur_tb, new_stamp_xsec, do_gtod.varp->tb_to_xs);
+	if (tlen == last_tick_len && offset < 0x80000000u) {
+		/* check that we're still in sync; if not, resync */
+		struct timeval tv;
+		__do_gettimeofday(&tv, cur_tb);
+		if (tv.tv_sec <= xtime.tv_sec &&
+		    (tv.tv_sec < xtime.tv_sec ||
+		     tv.tv_usec * 1000 <= xtime.tv_nsec))
+			return;
+	}
+	if (tlen != last_tick_len) {
+		t2x = mulhdu(tlen << TICKLEN_SHIFT, ticklen_to_xs);
+		last_tick_len = tlen;
+	} else
+		t2x = do_gtod.varp->tb_to_xs;
+	new_stamp_xsec = (u64) xtime.tv_nsec * XSEC_PER_SEC;
+	do_div(new_stamp_xsec, 1000000000);
+	new_stamp_xsec += (u64) xtime.tv_sec * XSEC_PER_SEC;
+	update_gtod(cur_tb, new_stamp_xsec, t2x);
 }
 
 #ifdef CONFIG_SMP
@@ -381,6 +602,7 @@ 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;
@@ -429,6 +651,7 @@ 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;
@@ -450,7 +673,7 @@ 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
@@ -462,13 +685,10 @@ void timer_interrupt(struct pt_regs * regs)
 		write_seqlock(&xtime_lock);
 		tb_last_jiffy += tb_ticks_per_jiffy;
 		tb_last_stamp = per_cpu(last_jiffy, cpu);
-		timer_recalc_offset(tb_last_jiffy);
 		do_timer(regs);
-		timer_sync_xtime(tb_last_jiffy);
+		timer_recalc_offset(tb_last_jiffy);
 		timer_check_rtc();
 		write_sequnlock(&xtime_lock);
-		if (adjusting_time && (time_adjust == 0))
-			ppc_adjtimex();
 	}
 	
 	next_dec = tb_ticks_per_jiffy - ticks;
@@ -492,29 +712,45 @@ void timer_interrupt(struct pt_regs * regs)
 
 void wakeup_decrementer(void)
 {
-	int i;
+	unsigned long ticks;
 
-	set_dec(tb_ticks_per_jiffy);
 	/*
-	 * We don't expect this to be called on a machine with a 601,
-	 * so using get_tbl is fine.
+	 * The timebase gets saved on sleep and restored on wakeup,
+	 * so all we need to do is to reset the decrementer.
 	 */
-	tb_last_stamp = tb_last_jiffy = get_tb();
-	for_each_cpu(i)
-		per_cpu(last_jiffy, i) = tb_last_stamp;
+	ticks = tb_ticks_since(__get_cpu_var(last_jiffy));
+	if (ticks < tb_ticks_per_jiffy)
+		ticks = tb_ticks_per_jiffy - ticks;
+	else
+		ticks = 1;
+	set_dec(ticks);
 }
 
 #ifdef CONFIG_SMP
 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;
 		}
@@ -541,8 +777,8 @@ int do_settimeofday(struct timespec *tv)
 	time_t wtm_sec, new_sec = tv->tv_sec;
 	long wtm_nsec, new_nsec = tv->tv_nsec;
 	unsigned long flags;
-	long int tb_delta;
-	u64 new_xsec, tb_delta_xs;
+	u64 new_xsec;
+	unsigned long tb_delta;
 
 	if ((unsigned long)tv->tv_nsec >= NSEC_PER_SEC)
 		return -EINVAL;
@@ -563,9 +799,19 @@ int do_settimeofday(struct timespec *tv)
 		first_settimeofday = 0;
 	}
 #endif
+
+	/*
+	 * Subtract off the number of nanoseconds since the
+	 * beginning of the last tick.
+	 * Note that since we don't increment jiffies_64 anywhere other
+	 * than in do_timer (since we don't have a lost tick problem),
+	 * wall_jiffies will always be the same as jiffies,
+	 * and therefore the (jiffies - wall_jiffies) computation
+	 * has been removed.
+	 */
 	tb_delta = tb_ticks_since(tb_last_stamp);
-	tb_delta += (jiffies - wall_jiffies) * tb_ticks_per_jiffy;
-	tb_delta_xs = mulhdu(tb_delta, do_gtod.varp->tb_to_xs);
+	tb_delta = mulhdu(tb_delta, do_gtod.varp->tb_to_xs); /* in xsec */
+	new_nsec -= SCALE_XSEC(tb_delta, 1000000000);
 
 	wtm_sec  = wall_to_monotonic.tv_sec + (xtime.tv_sec - new_sec);
 	wtm_nsec = wall_to_monotonic.tv_nsec + (xtime.tv_nsec - new_nsec);
@@ -580,12 +826,12 @@ int do_settimeofday(struct timespec *tv)
 
 	ntp_clear();
 
-	new_xsec = 0;
-	if (new_nsec != 0) {
-		new_xsec = (u64)new_nsec * XSEC_PER_SEC;
+	new_xsec = xtime.tv_nsec;
+	if (new_xsec != 0) {
+		new_xsec *= XSEC_PER_SEC;
 		do_div(new_xsec, NSEC_PER_SEC);
 	}
-	new_xsec += (u64)new_sec * XSEC_PER_SEC - tb_delta_xs;
+	new_xsec += (u64)xtime.tv_sec * XSEC_PER_SEC;
 	update_gtod(tb_last_jiffy, new_xsec, do_gtod.varp->tb_to_xs);
 
 	vdso_data->tz_minuteswest = sys_tz.tz_minuteswest;
@@ -671,7 +917,7 @@ void __init time_init(void)
 	unsigned long flags;
 	unsigned long tm = 0;
 	struct div_result res;
-	u64 scale;
+	u64 scale, x;
 	unsigned shift;
 
         if (ppc_md.time_init != NULL)
@@ -693,11 +939,37 @@ void __init time_init(void)
 	}
 
 	tb_ticks_per_jiffy = ppc_tb_freq / HZ;
-	tb_ticks_per_sec = tb_ticks_per_jiffy * HZ;
+	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);
-	div128_by_32(1024*1024, 0, tb_ticks_per_sec, &res);
-	tb_to_xs = res.result_low;
+	calc_cputime_factors();
+
+	/*
+	 * Calculate the length of each tick in ns.  It will not be
+	 * exactly 1e9/HZ unless ppc_tb_freq is divisible by HZ.
+	 * We compute 1e9 * tb_ticks_per_jiffy / ppc_tb_freq,
+	 * rounded up.
+	 */
+	x = (u64) NSEC_PER_SEC * tb_ticks_per_jiffy + ppc_tb_freq - 1;
+	do_div(x, ppc_tb_freq);
+	tick_nsec = x;
+	last_tick_len = x << TICKLEN_SCALE;
+
+	/*
+	 * Compute ticklen_to_xs, which is a factor which gets multiplied
+	 * by (last_tick_len << TICKLEN_SHIFT) to get a tb_to_xs value.
+	 * It is computed as:
+	 * ticklen_to_xs = 2^N / (tb_ticks_per_jiffy * 1e9)
+	 * where N = 64 + 20 - TICKLEN_SCALE - TICKLEN_SHIFT
+	 * so as to give the result as a 0.64 fixed-point fraction.
+	 */
+	div128_by_32(1ULL << (64 + 20 - TICKLEN_SCALE - TICKLEN_SHIFT), 0,
+		     tb_ticks_per_jiffy, &res);
+	div128_by_32(res.result_high, res.result_low, NSEC_PER_SEC, &res);
+	ticklen_to_xs = res.result_low;
+
+	/* Compute tb_to_xs from tick_nsec */
+	tb_to_xs = mulhdu(last_tick_len << TICKLEN_SHIFT, ticklen_to_xs);
 
 	/*
 	 * Compute scale factor for sched_clock.
@@ -724,6 +996,14 @@ void __init time_init(void)
 		tm = get_boot_time();
 
 	write_seqlock_irqsave(&xtime_lock, flags);
+
+	/* If platform provided a timezone (pmac), we correct the time */
+        if (timezone_offset) {
+		sys_tz.tz_minuteswest = -timezone_offset / 60;
+		sys_tz.tz_dsttime = 0;
+		tm -= timezone_offset;
+        }
+
 	xtime.tv_sec = tm;
 	xtime.tv_nsec = 0;
 	do_gtod.varp = &do_gtod.vars[0];
@@ -738,18 +1018,11 @@ void __init time_init(void)
 	vdso_data->tb_orig_stamp = tb_last_jiffy;
 	vdso_data->tb_update_count = 0;
 	vdso_data->tb_ticks_per_sec = tb_ticks_per_sec;
-	vdso_data->stamp_xsec = xtime.tv_sec * XSEC_PER_SEC;
+	vdso_data->stamp_xsec = (u64) xtime.tv_sec * XSEC_PER_SEC;
 	vdso_data->tb_to_xs = tb_to_xs;
 
 	time_freq = 0;
 
-	/* If platform provided a timezone (pmac), we correct the time */
-        if (timezone_offset) {
-		sys_tz.tz_minuteswest = -timezone_offset / 60;
-		sys_tz.tz_dsttime = 0;
-		xtime.tv_sec -= timezone_offset;
-        }
-
 	last_rtc_update = xtime.tv_sec;
 	set_normalized_timespec(&wall_to_monotonic,
 	                        -xtime.tv_sec, -xtime.tv_nsec);
@@ -759,126 +1032,6 @@ void __init time_init(void)
 	set_dec(tb_ticks_per_jiffy);
 }
 
-/* 
- * After adjtimex is called, adjust the conversion of tb ticks
- * to microseconds to keep do_gettimeofday synchronized 
- * with ntpd.
- *
- * Use the time_adjust, time_freq and time_offset computed by adjtimex to 
- * adjust the frequency.
- */
-
-/* #define DEBUG_PPC_ADJTIMEX 1 */
-
-void ppc_adjtimex(void)
-{
-#ifdef CONFIG_PPC64
-	unsigned long den, new_tb_ticks_per_sec, tb_ticks, old_xsec,
-		new_tb_to_xs, new_xsec, new_stamp_xsec;
-	unsigned long tb_ticks_per_sec_delta;
-	long delta_freq, ltemp;
-	struct div_result divres; 
-	unsigned long flags;
-	long singleshot_ppm = 0;
-
-	/*
-	 * Compute parts per million frequency adjustment to
-	 * accomplish the time adjustment implied by time_offset to be
-	 * applied over the elapsed time indicated by time_constant.
-	 * Use SHIFT_USEC to get it into the same units as
-	 * time_freq.
-	 */
-	if ( time_offset < 0 ) {
-		ltemp = -time_offset;
-		ltemp <<= SHIFT_USEC - SHIFT_UPDATE;
-		ltemp >>= SHIFT_KG + time_constant;
-		ltemp = -ltemp;
-	} else {
-		ltemp = time_offset;
-		ltemp <<= SHIFT_USEC - SHIFT_UPDATE;
-		ltemp >>= SHIFT_KG + time_constant;
-	}
-	
-	/* If there is a single shot time adjustment in progress */
-	if ( time_adjust ) {
-#ifdef DEBUG_PPC_ADJTIMEX
-		printk("ppc_adjtimex: ");
-		if ( adjusting_time == 0 )
-			printk("starting ");
-		printk("single shot time_adjust = %ld\n", time_adjust);
-#endif	
-	
-		adjusting_time = 1;
-		
-		/*
-		 * Compute parts per million frequency adjustment
-		 * to match time_adjust
-		 */
-		singleshot_ppm = tickadj * HZ;	
-		/*
-		 * The adjustment should be tickadj*HZ to match the code in
-		 * linux/kernel/timer.c, but experiments show that this is too
-		 * large. 3/4 of tickadj*HZ seems about right
-		 */
-		singleshot_ppm -= singleshot_ppm / 4;
-		/* Use SHIFT_USEC to get it into the same units as time_freq */
-		singleshot_ppm <<= SHIFT_USEC;
-		if ( time_adjust < 0 )
-			singleshot_ppm = -singleshot_ppm;
-	}
-	else {
-#ifdef DEBUG_PPC_ADJTIMEX
-		if ( adjusting_time )
-			printk("ppc_adjtimex: ending single shot time_adjust\n");
-#endif
-		adjusting_time = 0;
-	}
-	
-	/* Add up all of the frequency adjustments */
-	delta_freq = time_freq + ltemp + singleshot_ppm;
-	
-	/*
-	 * Compute a new value for tb_ticks_per_sec based on
-	 * the frequency adjustment
-	 */
-	den = 1000000 * (1 << (SHIFT_USEC - 8));
-	if ( delta_freq < 0 ) {
-		tb_ticks_per_sec_delta = ( tb_ticks_per_sec * ( (-delta_freq) >> (SHIFT_USEC - 8))) / den;
-		new_tb_ticks_per_sec = tb_ticks_per_sec + tb_ticks_per_sec_delta;
-	}
-	else {
-		tb_ticks_per_sec_delta = ( tb_ticks_per_sec * ( delta_freq >> (SHIFT_USEC - 8))) / den;
-		new_tb_ticks_per_sec = tb_ticks_per_sec - tb_ticks_per_sec_delta;
-	}
-	
-#ifdef DEBUG_PPC_ADJTIMEX
-	printk("ppc_adjtimex: ltemp = %ld, time_freq = %ld, singleshot_ppm = %ld\n", ltemp, time_freq, singleshot_ppm);
-	printk("ppc_adjtimex: tb_ticks_per_sec - base = %ld  new = %ld\n", tb_ticks_per_sec, new_tb_ticks_per_sec);
-#endif
-
-	/*
-	 * Compute a new value of tb_to_xs (used to convert tb to
-	 * microseconds) and a new value of stamp_xsec which is the
-	 * time (in 1/2^20 second units) corresponding to
-	 * tb_orig_stamp.  This new value of stamp_xsec compensates
-	 * for the change in frequency (implied by the new tb_to_xs)
-	 * which guarantees that the current time remains the same.
-	 */
-	write_seqlock_irqsave( &xtime_lock, flags );
-	tb_ticks = get_tb() - do_gtod.varp->tb_orig_stamp;
-	div128_by_32(1024*1024, 0, new_tb_ticks_per_sec, &divres);
-	new_tb_to_xs = divres.result_low;
-	new_xsec = mulhdu(tb_ticks, new_tb_to_xs);
-
-	old_xsec = mulhdu(tb_ticks, do_gtod.varp->tb_to_xs);
-	new_stamp_xsec = do_gtod.varp->stamp_xsec + old_xsec - new_xsec;
-
-	update_gtod(do_gtod.varp->tb_orig_stamp, new_stamp_xsec, new_tb_to_xs);
-
-	write_sequnlock_irqrestore( &xtime_lock, flags );
-#endif /* CONFIG_PPC64 */
-}
-
 
 #define FEBRUARY	2
 #define	STARTOFTIME	1970
diff --git a/arch/powerpc/kernel/vdso64/gettimeofday.S b/arch/powerpc/kernel/vdso64/gettimeofday.S
index ccaeda5136d..4ee871f1cad 100644
--- a/arch/powerpc/kernel/vdso64/gettimeofday.S
+++ b/arch/powerpc/kernel/vdso64/gettimeofday.S
@@ -225,9 +225,9 @@ V_FUNCTION_BEGIN(__do_get_xsec)
   .cfi_startproc
 	/* check for update count & load values */
 1:	ld	r8,CFG_TB_UPDATE_COUNT(r3)
-	andi.	r0,r4,1			/* pending update ? loop */
+	andi.	r0,r8,1			/* pending update ? loop */
 	bne-	1b
-	xor	r0,r4,r4		/* create dependency */
+	xor	r0,r8,r8		/* create dependency */
 	add	r3,r3,r0
 
 	/* Get TB & offset it */