Merge branch 'tracing/core' into tracing/hw-breakpoints

Conflicts: arch/Kconfig kernel/trace/trace.h Merge reason: resolve the conflicts, plus adopt to the new ring-buffer APIs. Signed-off-by: Ingo Molnar <mingo@elte.hu>
author: Ingo Molnar <mingo@elte.hu> 2009-09-07 08:19:51 +0200
committer: Ingo Molnar <mingo@elte.hu> 2009-09-07 08:19:51 +0200
commit: a1922ed661ab2c1637d0b10cde933bd9cd33d965 (patch)
tree: 0f1777542b385ebefd30b3586d830fd8ed6fda5b /arch/powerpc/kernel
parent: 75e33751ca8bbb72dd6f1a74d2810ddc8cbe4bdf (diff)
parent: d28daf923ac5e4a0d7cecebae56f3e339189366b (diff)
26 files changed, 1209 insertions, 346 deletions
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index 612b0c4dc26..b73396b9390 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -4,6 +4,8 @@
 
 CFLAGS_ptrace.o		+= -DUTS_MACHINE='"$(UTS_MACHINE)"'
 
+subdir-ccflags-$(CONFIG_PPC_WERROR) := -Werror
+
 ifeq ($(CONFIG_PPC64),y)
 CFLAGS_prom_init.o	+= -mno-minimal-toc
 endif
@@ -95,9 +97,10 @@ obj64-$(CONFIG_AUDIT)		+= compat_audit.o
 
 obj-$(CONFIG_DYNAMIC_FTRACE)	+= ftrace.o
 obj-$(CONFIG_FUNCTION_GRAPH_TRACER)	+= ftrace.o
-obj-$(CONFIG_PERF_COUNTERS)	+= perf_counter.o power4-pmu.o ppc970-pmu.o \
-				   power5-pmu.o power5+-pmu.o power6-pmu.o \
-				   power7-pmu.o
+obj-$(CONFIG_PPC_PERF_CTRS)	+= perf_counter.o
+obj64-$(CONFIG_PPC_PERF_CTRS)	+= power4-pmu.o ppc970-pmu.o power5-pmu.o \
+				   power5+-pmu.o power6-pmu.o power7-pmu.o
+obj32-$(CONFIG_PPC_PERF_CTRS)	+= mpc7450-pmu.o
 
 obj-$(CONFIG_8XX_MINIMAL_FPEMU) += softemu8xx.o
 
@@ -106,6 +109,7 @@ obj-y				+= iomap.o
 endif
 
 obj-$(CONFIG_PPC64)		+= $(obj64-y)
+obj-$(CONFIG_PPC32)		+= $(obj32-y)
 
 ifneq ($(CONFIG_XMON)$(CONFIG_KEXEC),)
 obj-y				+= ppc_save_regs.o
diff --git a/arch/powerpc/kernel/cpu_setup_6xx.S b/arch/powerpc/kernel/cpu_setup_6xx.S
index 54f767e31a1..1e9949e6885 100644
--- a/arch/powerpc/kernel/cpu_setup_6xx.S
+++ b/arch/powerpc/kernel/cpu_setup_6xx.S
@@ -239,6 +239,9 @@ END_FTR_SECTION_IFSET(CPU_FTR_L3CR)
 	ori	r11,r11,HID0_SGE | HID0_FOLD | HID0_BHTE
 	ori	r11,r11,HID0_LRSTK | HID0_BTIC
 	oris	r11,r11,HID0_DPM@h
+BEGIN_MMU_FTR_SECTION
+	oris	r11,r11,HID0_HIGH_BAT@h
+END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_HIGH_BATS)
 BEGIN_FTR_SECTION
 	xori	r11,r11,HID0_BTIC
 END_FTR_SECTION_IFSET(CPU_FTR_NO_BTIC)
diff --git a/arch/powerpc/kernel/cpu_setup_fsl_booke.S b/arch/powerpc/kernel/cpu_setup_fsl_booke.S
index eb4b9adcedb..0adb50ad803 100644
--- a/arch/powerpc/kernel/cpu_setup_fsl_booke.S
+++ b/arch/powerpc/kernel/cpu_setup_fsl_booke.S
@@ -17,6 +17,40 @@
 #include <asm/cputable.h>
 #include <asm/ppc_asm.h>
 
+_GLOBAL(__e500_icache_setup)
+	mfspr	r0, SPRN_L1CSR1
+	andi.	r3, r0, L1CSR1_ICE
+	bnelr				/* Already enabled */
+	oris	r0, r0, L1CSR1_CPE@h
+	ori	r0, r0, (L1CSR1_ICFI | L1CSR1_ICLFR |  L1CSR1_ICE)
+	mtspr	SPRN_L1CSR1, r0		/* Enable I-Cache */
+	isync
+	blr
+
+_GLOBAL(__e500_dcache_setup)
+	mfspr	r0, SPRN_L1CSR0
+	andi.	r3, r0, L1CSR0_DCE
+	bnelr				/* Already enabled */
+	msync
+	isync
+	li	r0, 0
+	mtspr	SPRN_L1CSR0, r0		/* Disable */
+	msync
+	isync
+	li	r0, (L1CSR0_DCFI | L1CSR0_CLFC)
+	mtspr	SPRN_L1CSR0, r0		/* Invalidate */
+	isync
+1:	mfspr	r0, SPRN_L1CSR0
+	andi.	r3, r0, L1CSR0_CLFC
+	bne+	1b			/* Wait for lock bits reset */
+	oris	r0, r0, L1CSR0_CPE@h
+	ori	r0, r0, L1CSR0_DCE
+	msync
+	isync
+	mtspr	SPRN_L1CSR0, r0		/* Enable */
+	isync
+	blr
+
 _GLOBAL(__setup_cpu_e200)
 	/* enable dedicated debug exception handling resources (Debug APU) */
 	mfspr	r3,SPRN_HID0
@@ -25,7 +59,16 @@ _GLOBAL(__setup_cpu_e200)
 	b	__setup_e200_ivors
 _GLOBAL(__setup_cpu_e500v1)
 _GLOBAL(__setup_cpu_e500v2)
-	b	__setup_e500_ivors
+	mflr	r4
+	bl	__e500_icache_setup
+	bl	__e500_dcache_setup
+	bl	__setup_e500_ivors
+	mtlr	r4
+	blr
 _GLOBAL(__setup_cpu_e500mc)
-	b	__setup_e500mc_ivors
-
+	mflr	r4
+	bl	__e500_icache_setup
+	bl	__e500_dcache_setup
+	bl	__setup_e500mc_ivors
+	mtlr	r4
+	blr
diff --git a/arch/powerpc/kernel/dma.c b/arch/powerpc/kernel/dma.c
index 20a60d661ba..ccf129d47d8 100644
--- a/arch/powerpc/kernel/dma.c
+++ b/arch/powerpc/kernel/dma.c
@@ -7,6 +7,7 @@
 
 #include <linux/device.h>
 #include <linux/dma-mapping.h>
+#include <linux/lmb.h>
 #include <asm/bug.h>
 #include <asm/abs_addr.h>
 
@@ -90,11 +91,10 @@ static void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sg,
 static int dma_direct_dma_supported(struct device *dev, u64 mask)
 {
 #ifdef CONFIG_PPC64
-	/* Could be improved to check for memory though it better be
-	 * done via some global so platforms can set the limit in case
+	/* Could be improved so platforms can set the limit in case
 	 * they have limited DMA windows
 	 */
-	return mask >= DMA_BIT_MASK(32);
+	return mask >= (lmb_end_of_DRAM() - 1);
 #else
 	return 1;
 #endif
diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index 4dd38f12915..3cadba60a4b 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -191,11 +191,49 @@ transfer_to_handler_cont:
 	mflr	r9
 	lwz	r11,0(r9)		/* virtual address of handler */
 	lwz	r9,4(r9)		/* where to go when done */
+#ifdef CONFIG_TRACE_IRQFLAGS
+	lis	r12,reenable_mmu@h
+	ori	r12,r12,reenable_mmu@l
+	mtspr	SPRN_SRR0,r12
+	mtspr	SPRN_SRR1,r10
+	SYNC
+	RFI
+reenable_mmu:				/* re-enable mmu so we can */
+	mfmsr	r10
+	lwz	r12,_MSR(r1)
+	xor	r10,r10,r12
+	andi.	r10,r10,MSR_EE		/* Did EE change? */
+	beq	1f
+
+	/* Save handler and return address into the 2 unused words
+	 * of the STACK_FRAME_OVERHEAD (sneak sneak sneak). Everything
+	 * else can be recovered from the pt_regs except r3 which for
+	 * normal interrupts has been set to pt_regs and for syscalls
+	 * is an argument, so we temporarily use ORIG_GPR3 to save it
+	 */
+	stw	r9,8(r1)
+	stw	r11,12(r1)
+	stw	r3,ORIG_GPR3(r1)
+	bl	trace_hardirqs_off
+	lwz	r0,GPR0(r1)
+	lwz	r3,ORIG_GPR3(r1)
+	lwz	r4,GPR4(r1)
+	lwz	r5,GPR5(r1)
+	lwz	r6,GPR6(r1)
+	lwz	r7,GPR7(r1)
+	lwz	r8,GPR8(r1)
+	lwz	r9,8(r1)
+	lwz	r11,12(r1)
+1:	mtctr	r11
+	mtlr	r9
+	bctr				/* jump to handler */
+#else /* CONFIG_TRACE_IRQFLAGS */
 	mtspr	SPRN_SRR0,r11
 	mtspr	SPRN_SRR1,r10
 	mtlr	r9
 	SYNC
 	RFI				/* jump to handler, enable MMU */
+#endif /* CONFIG_TRACE_IRQFLAGS */
 
 #if defined (CONFIG_6xx) || defined(CONFIG_E500)
 4:	rlwinm	r12,r12,0,~_TLF_NAPPING
@@ -251,6 +289,31 @@ _GLOBAL(DoSyscall)
 #ifdef SHOW_SYSCALLS
 	bl	do_show_syscall
 #endif /* SHOW_SYSCALLS */
+#ifdef CONFIG_TRACE_IRQFLAGS
+	/* Return from syscalls can (and generally will) hard enable
+	 * interrupts. You aren't supposed to call a syscall with
+	 * interrupts disabled in the first place. However, to ensure
+	 * that we get it right vs. lockdep if it happens, we force
+	 * that hard enable here with appropriate tracing if we see
+	 * that we have been called with interrupts off
+	 */
+	mfmsr	r11
+	andi.	r12,r11,MSR_EE
+	bne+	1f
+	/* We came in with interrupts disabled, we enable them now */
+	bl	trace_hardirqs_on
+	mfmsr	r11
+	lwz	r0,GPR0(r1)
+	lwz	r3,GPR3(r1)
+	lwz	r4,GPR4(r1)
+	ori	r11,r11,MSR_EE
+	lwz	r5,GPR5(r1)
+	lwz	r6,GPR6(r1)
+	lwz	r7,GPR7(r1)
+	lwz	r8,GPR8(r1)
+	mtmsr	r11
+1:
+#endif /* CONFIG_TRACE_IRQFLAGS */
 	rlwinm	r10,r1,0,0,(31-THREAD_SHIFT)	/* current_thread_info() */
 	lwz	r11,TI_FLAGS(r10)
 	andi.	r11,r11,_TIF_SYSCALL_T_OR_A
@@ -275,6 +338,7 @@ ret_from_syscall:
 	rlwinm	r12,r1,0,0,(31-THREAD_SHIFT)	/* current_thread_info() */
 	/* disable interrupts so current_thread_info()->flags can't change */
 	LOAD_MSR_KERNEL(r10,MSR_KERNEL)	/* doesn't include MSR_EE */
+	/* Note: We don't bother telling lockdep about it */
 	SYNC
 	MTMSRD(r10)
 	lwz	r9,TI_FLAGS(r12)
@@ -288,6 +352,19 @@ ret_from_syscall:
 	oris	r11,r11,0x1000	/* Set SO bit in CR */
 	stw	r11,_CCR(r1)
 syscall_exit_cont:
+	lwz	r8,_MSR(r1)
+#ifdef CONFIG_TRACE_IRQFLAGS
+	/* If we are going to return from the syscall with interrupts
+	 * off, we trace that here. It shouldn't happen though but we
+	 * want to catch the bugger if it does right ?
+	 */
+	andi.	r10,r8,MSR_EE
+	bne+	1f
+	stw	r3,GPR3(r1)
+	bl      trace_hardirqs_off
+	lwz	r3,GPR3(r1)
+1:
+#endif /* CONFIG_TRACE_IRQFLAGS */
 #if defined(CONFIG_4xx) || defined(CONFIG_BOOKE)
 	/* If the process has its own DBCR0 value, load it up.  The internal
 	   debug mode bit tells us that dbcr0 should be loaded. */
@@ -311,7 +388,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_NEED_PAIRED_STWCX)
 	mtlr	r4
 	mtcr	r5
 	lwz	r7,_NIP(r1)
-	lwz	r8,_MSR(r1)
 	FIX_SRR1(r8, r0)
 	lwz	r2,GPR2(r1)
 	lwz	r1,GPR1(r1)
@@ -394,7 +470,9 @@ syscall_exit_work:
 	andi.	r0,r9,(_TIF_SYSCALL_T_OR_A|_TIF_SINGLESTEP)
 	beq	ret_from_except
 
-	/* Re-enable interrupts */
+	/* Re-enable interrupts. There is no need to trace that with
+	 * lockdep as we are supposed to have IRQs on at this point
+	 */
 	ori	r10,r10,MSR_EE
 	SYNC
 	MTMSRD(r10)
@@ -705,6 +783,7 @@ ret_from_except:
 	/* Hard-disable interrupts so that current_thread_info()->flags
 	 * can't change between when we test it and when we return
 	 * from the interrupt. */
+	/* Note: We don't bother telling lockdep about it */
 	LOAD_MSR_KERNEL(r10,MSR_KERNEL)
 	SYNC			/* Some chip revs have problems here... */
 	MTMSRD(r10)		/* disable interrupts */
@@ -744,11 +823,24 @@ resume_kernel:
 	beq+	restore
 	andi.	r0,r3,MSR_EE	/* interrupts off? */
 	beq	restore		/* don't schedule if so */
+#ifdef CONFIG_TRACE_IRQFLAGS
+	/* Lockdep thinks irqs are enabled, we need to call
+	 * preempt_schedule_irq with IRQs off, so we inform lockdep
+	 * now that we -did- turn them off already
+	 */
+	bl	trace_hardirqs_off
+#endif
 1:	bl	preempt_schedule_irq
 	rlwinm	r9,r1,0,0,(31-THREAD_SHIFT)
 	lwz	r3,TI_FLAGS(r9)
 	andi.	r0,r3,_TIF_NEED_RESCHED
 	bne-	1b
+#ifdef CONFIG_TRACE_IRQFLAGS
+	/* And now, to properly rebalance the above, we tell lockdep they
+	 * are being turned back on, which will happen when we return
+	 */
+	bl	trace_hardirqs_on
+#endif
 #else
 resume_kernel:
 #endif /* CONFIG_PREEMPT */
@@ -765,6 +857,28 @@ restore:
 	stw	r6,icache_44x_need_flush@l(r4)
 1:
 #endif  /* CONFIG_44x */
+
+	lwz	r9,_MSR(r1)
+#ifdef CONFIG_TRACE_IRQFLAGS
+	/* Lockdep doesn't know about the fact that IRQs are temporarily turned
+	 * off in this assembly code while peeking at TI_FLAGS() and such. However
+	 * we need to inform it if the exception turned interrupts off, and we
+	 * are about to trun them back on.
+	 *
+	 * The problem here sadly is that we don't know whether the exceptions was
+	 * one that turned interrupts off or not. So we always tell lockdep about
+	 * turning them on here when we go back to wherever we came from with EE
+	 * on, even if that may meen some redudant calls being tracked. Maybe later
+	 * we could encode what the exception did somewhere or test the exception
+	 * type in the pt_regs but that sounds overkill
+	 */
+	andi.	r10,r9,MSR_EE
+	beq	1f
+	bl	trace_hardirqs_on
+	lwz	r9,_MSR(r1)
+1:
+#endif /* CONFIG_TRACE_IRQFLAGS */
+
 	lwz	r0,GPR0(r1)
 	lwz	r2,GPR2(r1)
 	REST_4GPRS(3, r1)
@@ -782,7 +896,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_NEED_PAIRED_STWCX)
 	stwcx.	r0,0,r1			/* to clear the reservation */
 
 #if !(defined(CONFIG_4xx) || defined(CONFIG_BOOKE))
-	lwz	r9,_MSR(r1)
 	andi.	r10,r9,MSR_RI		/* check if this exception occurred */
 	beql	nonrecoverable		/* at a bad place (MSR:RI = 0) */
 
@@ -805,7 +918,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_NEED_PAIRED_STWCX)
 	MTMSRD(r10)		/* clear the RI bit */
 	.globl exc_exit_restart
 exc_exit_restart:
-	lwz	r9,_MSR(r1)
 	lwz	r12,_NIP(r1)
 	FIX_SRR1(r9,r10)
 	mtspr	SPRN_SRR0,r12
@@ -1035,11 +1147,18 @@ do_work:			/* r10 contains MSR_KERNEL here */
 	beq	do_user_signal
 
 do_resched:			/* r10 contains MSR_KERNEL here */
+	/* Note: We don't need to inform lockdep that we are enabling
+	 * interrupts here. As far as it knows, they are already enabled
+	 */
 	ori	r10,r10,MSR_EE
 	SYNC
 	MTMSRD(r10)		/* hard-enable interrupts */
 	bl	schedule
 recheck:
+	/* Note: And we don't tell it we are disabling them again
+	 * neither. Those disable/enable cycles used to peek at
+	 * TI_FLAGS aren't advertised.
+	 */
 	LOAD_MSR_KERNEL(r10,MSR_KERNEL)
 	SYNC
 	MTMSRD(r10)		/* disable interrupts */
diff --git a/arch/powerpc/kernel/ftrace.c b/arch/powerpc/kernel/ftrace.c
index 1b12696cca0..ce1f3e44c24 100644
--- a/arch/powerpc/kernel/ftrace.c
+++ b/arch/powerpc/kernel/ftrace.c
@@ -586,7 +586,7 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr)
 		return;
 	}
 
-	if (ftrace_push_return_trace(old, self_addr, &trace.depth) == -EBUSY) {
+	if (ftrace_push_return_trace(old, self_addr, &trace.depth, 0) == -EBUSY) {
 		*parent = old;
 		return;
 	}
diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_32.S
index 48469463f89..fc213294275 100644
--- a/arch/powerpc/kernel/head_32.S
+++ b/arch/powerpc/kernel/head_32.S
@@ -1124,9 +1124,8 @@ mmu_off:
 	RFI
 
 /*
- * Use the first pair of BAT registers to map the 1st 16MB
- * of RAM to PAGE_OFFSET.  From this point on we can't safely
- * call OF any more.
+ * On 601, we use 3 BATs to map up to 24M of RAM at _PAGE_OFFSET
+ * (we keep one for debugging) and on others, we use one 256M BAT.
  */
 initial_bats:
 	lis	r11,PAGE_OFFSET@h
@@ -1136,12 +1135,16 @@ initial_bats:
 	bne	4f
 	ori	r11,r11,4		/* set up BAT registers for 601 */
 	li	r8,0x7f			/* valid, block length = 8MB */
-	oris	r9,r11,0x800000@h	/* set up BAT reg for 2nd 8M */
-	oris	r10,r8,0x800000@h	/* set up BAT reg for 2nd 8M */
 	mtspr	SPRN_IBAT0U,r11		/* N.B. 601 has valid bit in */
 	mtspr	SPRN_IBAT0L,r8		/* lower BAT register */
-	mtspr	SPRN_IBAT1U,r9
-	mtspr	SPRN_IBAT1L,r10
+	addis	r11,r11,0x800000@h
+	addis	r8,r8,0x800000@h
+	mtspr	SPRN_IBAT1U,r11
+	mtspr	SPRN_IBAT1L,r8
+	addis	r11,r11,0x800000@h
+	addis	r8,r8,0x800000@h
+	mtspr	SPRN_IBAT2U,r11
+	mtspr	SPRN_IBAT2L,r8
 	isync
 	blr
 
diff --git a/arch/powerpc/kernel/mpc7450-pmu.c b/arch/powerpc/kernel/mpc7450-pmu.c
new file mode 100644
index 00000000000..cc466d039af
--- /dev/null
+++ b/arch/powerpc/kernel/mpc7450-pmu.c
@@ -0,0 +1,417 @@
+/*
+ * Performance counter support for MPC7450-family processors.
+ *
+ * Copyright 2008-2009 Paul Mackerras, IBM Corporation.
+ *
+ * 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.
+ */
+#include <linux/string.h>
+#include <linux/perf_counter.h>
+#include <asm/reg.h>
+#include <asm/cputable.h>
+
+#define N_COUNTER	6	/* Number of hardware counters */
+#define MAX_ALT		3	/* Maximum number of event alternative codes */
+
+/*
+ * Bits in event code for MPC7450 family
+ */
+#define PM_THRMULT_MSKS	0x40000
+#define PM_THRESH_SH	12
+#define PM_THRESH_MSK	0x3f
+#define PM_PMC_SH	8
+#define PM_PMC_MSK	7
+#define PM_PMCSEL_MSK	0x7f
+
+/*
+ * Classify events according to how specific their PMC requirements are.
+ * Result is:
+ *	0: can go on any PMC
+ *	1: can go on PMCs 1-4
+ *	2: can go on PMCs 1,2,4
+ *	3: can go on PMCs 1 or 2
+ *	4: can only go on one PMC
+ *	-1: event code is invalid
+ */
+#define N_CLASSES	5
+
+static int mpc7450_classify_event(u32 event)
+{
+	int pmc;
+
+	pmc = (event >> PM_PMC_SH) & PM_PMC_MSK;
+	if (pmc) {
+		if (pmc > N_COUNTER)
+			return -1;
+		return 4;
+	}
+	event &= PM_PMCSEL_MSK;
+	if (event <= 1)
+		return 0;
+	if (event <= 7)
+		return 1;
+	if (event <= 13)
+		return 2;
+	if (event <= 22)
+		return 3;
+	return -1;
+}
+
+/*
+ * Events using threshold and possible threshold scale:
+ *	code	scale?	name
+ *	11e	N	PM_INSTQ_EXCEED_CYC
+ *	11f	N	PM_ALTV_IQ_EXCEED_CYC
+ *	128	Y	PM_DTLB_SEARCH_EXCEED_CYC
+ *	12b	Y	PM_LD_MISS_EXCEED_L1_CYC
+ *	220	N	PM_CQ_EXCEED_CYC
+ *	30c	N	PM_GPR_RB_EXCEED_CYC
+ *	30d	?	PM_FPR_IQ_EXCEED_CYC ?
+ *	311	Y	PM_ITLB_SEARCH_EXCEED
+ *	410	N	PM_GPR_IQ_EXCEED_CYC
+ */
+
+/*
+ * Return use of threshold and threshold scale bits:
+ * 0 = uses neither, 1 = uses threshold, 2 = uses both
+ */
+static int mpc7450_threshold_use(u32 event)
+{
+	int pmc, sel;
+
+	pmc = (event >> PM_PMC_SH) & PM_PMC_MSK;
+	sel = event & PM_PMCSEL_MSK;
+	switch (pmc) {
+	case 1:
+		if (sel == 0x1e || sel == 0x1f)
+			return 1;
+		if (sel == 0x28 || sel == 0x2b)
+			return 2;
+		break;
+	case 2:
+		if (sel == 0x20)
+			return 1;
+		break;
+	case 3:
+		if (sel == 0xc || sel == 0xd)
+			return 1;
+		if (sel == 0x11)
+			return 2;
+		break;
+	case 4:
+		if (sel == 0x10)
+			return 1;
+		break;
+	}
+	return 0;
+}
+
+/*
+ * Layout of constraint bits:
+ * 33222222222211111111110000000000
+ * 10987654321098765432109876543210
+ *  |<    ><  > < > < ><><><><><><>
+ *  TS TV   G4   G3  G2P6P5P4P3P2P1
+ *
+ * P1 - P6
+ *	0 - 11: Count of events needing PMC1 .. PMC6
+ *
+ * G2
+ *	12 - 14: Count of events needing PMC1 or PMC2
+ *
+ * G3
+ *	16 - 18: Count of events needing PMC1, PMC2 or PMC4
+ *
+ * G4
+ *	20 - 23: Count of events needing PMC1, PMC2, PMC3 or PMC4
+ *
+ * TV
+ *	24 - 29: Threshold value requested
+ *
+ * TS
+ *	30: Threshold scale value requested
+ */
+
+static u32 pmcbits[N_COUNTER][2] = {
+	{ 0x00844002, 0x00111001 },	/* PMC1 mask, value: P1,G2,G3,G4 */
+	{ 0x00844008, 0x00111004 },	/* PMC2: P2,G2,G3,G4 */
+	{ 0x00800020, 0x00100010 },	/* PMC3: P3,G4 */
+	{ 0x00840080, 0x00110040 },	/* PMC4: P4,G3,G4 */
+	{ 0x00000200, 0x00000100 },	/* PMC5: P5 */
+	{ 0x00000800, 0x00000400 }	/* PMC6: P6 */
+};
+
+static u32 classbits[N_CLASSES - 1][2] = {
+	{ 0x00000000, 0x00000000 },	/* class 0: no constraint */
+	{ 0x00800000, 0x00100000 },	/* class 1: G4 */
+	{ 0x00040000, 0x00010000 },	/* class 2: G3 */
+	{ 0x00004000, 0x00001000 },	/* class 3: G2 */
+};
+
+static int mpc7450_get_constraint(u64 event, unsigned long *maskp,
+				  unsigned long *valp)
+{
+	int pmc, class;
+	u32 mask, value;
+	int thresh, tuse;
+
+	class = mpc7450_classify_event(event);
+	if (class < 0)
+		return -1;
+	if (class == 4) {
+		pmc = ((unsigned int)event >> PM_PMC_SH) & PM_PMC_MSK;
+		mask  = pmcbits[pmc - 1][0];
+		value = pmcbits[pmc - 1][1];
+	} else {
+		mask  = classbits[class][0];
+		value = classbits[class][1];
+	}
+
+	tuse = mpc7450_threshold_use(event);
+	if (tuse) {
+		thresh = ((unsigned int)event >> PM_THRESH_SH) & PM_THRESH_MSK;
+		mask  |= 0x3f << 24;
+		value |= thresh << 24;
+		if (tuse == 2) {
+			mask |= 0x40000000;
+			if ((unsigned int)event & PM_THRMULT_MSKS)
+				value |= 0x40000000;
+		}
+	}
+
+	*maskp = mask;
+	*valp = value;
+	return 0;
+}
+
+static const unsigned int event_alternatives[][MAX_ALT] = {
+	{ 0x217, 0x317 },		/* PM_L1_DCACHE_MISS */
+	{ 0x418, 0x50f, 0x60f },	/* PM_SNOOP_RETRY */
+	{ 0x502, 0x602 },		/* PM_L2_HIT */
+	{ 0x503, 0x603 },		/* PM_L3_HIT */
+	{ 0x504, 0x604 },		/* PM_L2_ICACHE_MISS */
+	{ 0x505, 0x605 },		/* PM_L3_ICACHE_MISS */
+	{ 0x506, 0x606 },		/* PM_L2_DCACHE_MISS */
+	{ 0x507, 0x607 },		/* PM_L3_DCACHE_MISS */
+	{ 0x50a, 0x623 },		/* PM_LD_HIT_L3 */
+	{ 0x50b, 0x624 },		/* PM_ST_HIT_L3 */
+	{ 0x50d, 0x60d },		/* PM_L2_TOUCH_HIT */
+	{ 0x50e, 0x60e },		/* PM_L3_TOUCH_HIT */
+	{ 0x512, 0x612 },		/* PM_INT_LOCAL */
+	{ 0x513, 0x61d },		/* PM_L2_MISS */
+	{ 0x514, 0x61e },		/* PM_L3_MISS */
+};
+
+/*
+ * Scan the alternatives table for a match and return the
+ * index into the alternatives table if found, else -1.
+ */
+static int find_alternative(u32 event)
+{
+	int i, j;
+
+	for (i = 0; i < ARRAY_SIZE(event_alternatives); ++i) {
+		if (event < event_alternatives[i][0])
+			break;
+		for (j = 0; j < MAX_ALT && event_alternatives[i][j]; ++j)
+			if (event == event_alternatives[i][j])
+				return i;
+	}
+	return -1;
+}
+
+static int mpc7450_get_alternatives(u64 event, unsigned int flags, u64 alt[])
+{
+	int i, j, nalt = 1;
+	u32 ae;
+
+	alt[0] = event;
+	nalt = 1;
+	i = find_alternative((u32)event);
+	if (i >= 0) {
+		for (j = 0; j < MAX_ALT; ++j) {
+			ae = event_alternatives[i][j];
+			if (ae && ae != (u32)event)
+				alt[nalt++] = ae;
+		}
+	}
+	return nalt;
+}
+
+/*
+ * Bitmaps of which PMCs each class can use for classes 0 - 3.
+ * Bit i is set if PMC i+1 is usable.
+ */
+static const u8 classmap[N_CLASSES] = {
+	0x3f, 0x0f, 0x0b, 0x03, 0
+};
+
+/* Bit position and width of each PMCSEL field */
+static const int pmcsel_shift[N_COUNTER] = {
+	6,	0,	27,	22,	17,	11
+};
+static const u32 pmcsel_mask[N_COUNTER] = {
+	0x7f,	0x3f,	0x1f,	0x1f,	0x1f,	0x3f
+};
+
+/*
+ * Compute MMCR0/1/2 values for a set of events.
+ */
+static int mpc7450_compute_mmcr(u64 event[], int n_ev,
+				unsigned int hwc[], unsigned long mmcr[])
+{
+	u8 event_index[N_CLASSES][N_COUNTER];
+	int n_classevent[N_CLASSES];
+	int i, j, class, tuse;
+	u32 pmc_inuse = 0, pmc_avail;
+	u32 mmcr0 = 0, mmcr1 = 0, mmcr2 = 0;
+	u32 ev, pmc, thresh;
+
+	if (n_ev > N_COUNTER)
+		return -1;
+
+	/* First pass: count usage in each class */
+	for (i = 0; i < N_CLASSES; ++i)
+		n_classevent[i] = 0;
+	for (i = 0; i < n_ev; ++i) {
+		class = mpc7450_classify_event(event[i]);
+		if (class < 0)
+			return -1;
+		j = n_classevent[class]++;
+		event_index[class][j] = i;
+	}
+
+	/* Second pass: allocate PMCs from most specific event to least */
+	for (class = N_CLASSES - 1; class >= 0; --class) {
+		for (i = 0; i < n_classevent[class]; ++i) {
+			ev = event[event_index[class][i]];
+			if (class == 4) {
+				pmc = (ev >> PM_PMC_SH) & PM_PMC_MSK;
+				if (pmc_inuse & (1 << (pmc - 1)))
+					return -1;
+			} else {
+				/* Find a suitable PMC */
+				pmc_avail = classmap[class] & ~pmc_inuse;
+				if (!pmc_avail)
+					return -1;
+				pmc = ffs(pmc_avail);
+			}
+			pmc_inuse |= 1 << (pmc - 1);
+
+			tuse = mpc7450_threshold_use(ev);
+			if (tuse) {
+				thresh = (ev >> PM_THRESH_SH) & PM_THRESH_MSK;
+				mmcr0 |= thresh << 16;
+				if (tuse == 2 && (ev & PM_THRMULT_MSKS))
+					mmcr2 = 0x80000000;
+			}
+			ev &= pmcsel_mask[pmc - 1];
+			ev <<= pmcsel_shift[pmc - 1];
+			if (pmc <= 2)
+				mmcr0 |= ev;
+			else
+				mmcr1 |= ev;
+			hwc[event_index[class][i]] = pmc - 1;
+		}
+	}
+
+	if (pmc_inuse & 1)
+		mmcr0 |= MMCR0_PMC1CE;
+	if (pmc_inuse & 0x3e)
+		mmcr0 |= MMCR0_PMCnCE;
+
+	/* Return MMCRx values */
+	mmcr[0] = mmcr0;
+	mmcr[1] = mmcr1;
+	mmcr[2] = mmcr2;
+	return 0;
+}
+
+/*
+ * Disable counting by a PMC.
+ * Note that the pmc argument is 0-based here, not 1-based.
+ */
+static void mpc7450_disable_pmc(unsigned int pmc, unsigned long mmcr[])
+{
+	if (pmc <= 1)
+		mmcr[0] &= ~(pmcsel_mask[pmc] << pmcsel_shift[pmc]);
+	else
+		mmcr[1] &= ~(pmcsel_mask[pmc] << pmcsel_shift[pmc]);
+}
+
+static int mpc7450_generic_events[] = {
+	[PERF_COUNT_HW_CPU_CYCLES]		= 1,
+	[PERF_COUNT_HW_INSTRUCTIONS]		= 2,
+	[PERF_COUNT_HW_CACHE_MISSES]		= 0x217, /* PM_L1_DCACHE_MISS */
+	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= 0x122, /* PM_BR_CMPL */
+	[PERF_COUNT_HW_BRANCH_MISSES] 		= 0x41c, /* PM_BR_MPRED */
+};
+
+#define C(x)	PERF_COUNT_HW_CACHE_##x
+
+/*
+ * Table of generalized cache-related events.
+ * 0 means not supported, -1 means nonsensical, other values
+ * are event codes.
+ */
+static int mpc7450_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
+	[C(L1D)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	0,		0x225	},
+		[C(OP_WRITE)] = {	0,		0x227	},
+		[C(OP_PREFETCH)] = {	0,		0	},
+	},
+	[C(L1I)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	0x129,		0x115	},
+		[C(OP_WRITE)] = {	-1,		-1	},
+		[C(OP_PREFETCH)] = {	0x634,		0	},
+	},
+	[C(LL)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	0,		0	},
+		[C(OP_WRITE)] = {	0,		0	},
+		[C(OP_PREFETCH)] = {	0,		0	},
+	},
+	[C(DTLB)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	0,		0x312	},
+		[C(OP_WRITE)] = {	-1,		-1	},
+		[C(OP_PREFETCH)] = {	-1,		-1	},
+	},
+	[C(ITLB)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	0,		0x223	},
+		[C(OP_WRITE)] = {	-1,		-1	},
+		[C(OP_PREFETCH)] = {	-1,		-1	},
+	},
+	[C(BPU)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
+		[C(OP_READ)] = {	0x122,		0x41c	},
+		[C(OP_WRITE)] = {	-1,		-1	},
+		[C(OP_PREFETCH)] = {	-1,		-1	},
+	},
+};
+
+struct power_pmu mpc7450_pmu = {
+	.name			= "MPC7450 family",
+	.n_counter		= N_COUNTER,
+	.max_alternatives	= MAX_ALT,
+	.add_fields		= 0x00111555ul,
+	.test_adder		= 0x00301000ul,
+	.compute_mmcr		= mpc7450_compute_mmcr,
+	.get_constraint		= mpc7450_get_constraint,
+	.get_alternatives	= mpc7450_get_alternatives,
+	.disable_pmc		= mpc7450_disable_pmc,
+	.n_generic		= ARRAY_SIZE(mpc7450_generic_events),
+	.generic_events		= mpc7450_generic_events,
+	.cache_events		= &mpc7450_cache_events,
+};
+
+static int init_mpc7450_pmu(void)
+{
+	if (!cur_cpu_spec->oprofile_cpu_type ||
+	    strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc/7450"))
+		return -ENODEV;
+
+	return register_power_pmu(&mpc7450_pmu);
+}
+
+arch_initcall(init_mpc7450_pmu);
diff --git a/arch/powerpc/kernel/of_device.c b/arch/powerpc/kernel/of_device.c
index fa983a59c4c..a359cb08e90 100644
--- a/arch/powerpc/kernel/of_device.c
+++ b/arch/powerpc/kernel/of_device.c
@@ -76,7 +76,7 @@ struct of_device *of_device_alloc(struct device_node *np,
 	dev->dev.archdata.of_node = np;
 
 	if (bus_id)
-		dev_set_name(&dev->dev, bus_id);
+		dev_set_name(&dev->dev, "%s", bus_id);
 	else
 		of_device_make_bus_id(dev);
 
diff --git a/arch/powerpc/kernel/perf_counter.c b/arch/powerpc/kernel/perf_counter.c
index bb202388170..70e1f57f7dd 100644
--- a/arch/powerpc/kernel/perf_counter.c
+++ b/arch/powerpc/kernel/perf_counter.c
@@ -29,7 +29,7 @@ struct cpu_hw_counters {
 	struct perf_counter *counter[MAX_HWCOUNTERS];
 	u64 events[MAX_HWCOUNTERS];
 	unsigned int flags[MAX_HWCOUNTERS];
-	u64 mmcr[3];
+	unsigned long mmcr[3];
 	struct perf_counter *limited_counter[MAX_LIMITED_HWCOUNTERS];
 	u8  limited_hwidx[MAX_LIMITED_HWCOUNTERS];
 };
@@ -46,6 +46,115 @@ struct power_pmu *ppmu;
  */
 static unsigned int freeze_counters_kernel = MMCR0_FCS;
 
+/*
+ * 32-bit doesn't have MMCRA but does have an MMCR2,
+ * and a few other names are different.
+ */
+#ifdef CONFIG_PPC32
+
+#define MMCR0_FCHV		0
+#define MMCR0_PMCjCE		MMCR0_PMCnCE
+
+#define SPRN_MMCRA		SPRN_MMCR2
+#define MMCRA_SAMPLE_ENABLE	0
+
+static inline unsigned long perf_ip_adjust(struct pt_regs *regs)
+{
+	return 0;
+}
+static inline void perf_set_pmu_inuse(int inuse) { }
+static inline void perf_get_data_addr(struct pt_regs *regs, u64 *addrp) { }
+static inline u32 perf_get_misc_flags(struct pt_regs *regs)
+{
+	return 0;
+}
+static inline void perf_read_regs(struct pt_regs *regs) { }
+static inline int perf_intr_is_nmi(struct pt_regs *regs)
+{
+	return 0;
+}
+
+#endif /* CONFIG_PPC32 */
+
+/*
+ * Things that are specific to 64-bit implementations.
+ */
+#ifdef CONFIG_PPC64
+
+static inline unsigned long perf_ip_adjust(struct pt_regs *regs)
+{
+	unsigned long mmcra = regs->dsisr;
+
+	if ((mmcra & MMCRA_SAMPLE_ENABLE) && !(ppmu->flags & PPMU_ALT_SIPR)) {
+		unsigned long slot = (mmcra & MMCRA_SLOT) >> MMCRA_SLOT_SHIFT;
+		if (slot > 1)
+			return 4 * (slot - 1);
+	}
+	return 0;
+}
+
+static inline void perf_set_pmu_inuse(int inuse)
+{
+	get_lppaca()->pmcregs_in_use = inuse;
+}
+
+/*
+ * The user wants a data address recorded.
+ * If we're not doing instruction sampling, give them the SDAR
+ * (sampled data address).  If we are doing instruction sampling, then
+ * only give them the SDAR if it corresponds to the instruction
+ * pointed to by SIAR; this is indicated by the [POWER6_]MMCRA_SDSYNC
+ * bit in MMCRA.
+ */
+static inline void perf_get_data_addr(struct pt_regs *regs, u64 *addrp)
+{
+	unsigned long mmcra = regs->dsisr;
+	unsigned long sdsync = (ppmu->flags & PPMU_ALT_SIPR) ?
+		POWER6_MMCRA_SDSYNC : MMCRA_SDSYNC;
+
+	if (!(mmcra & MMCRA_SAMPLE_ENABLE) || (mmcra & sdsync))
+		*addrp = mfspr(SPRN_SDAR);
+}
+
+static inline u32 perf_get_misc_flags(struct pt_regs *regs)
+{
+	unsigned long mmcra = regs->dsisr;
+
+	if (TRAP(regs) != 0xf00)
+		return 0;	/* not a PMU interrupt */
+
+	if (ppmu->flags & PPMU_ALT_SIPR) {
+		if (mmcra & POWER6_MMCRA_SIHV)
+			return PERF_EVENT_MISC_HYPERVISOR;
+		return (mmcra & POWER6_MMCRA_SIPR) ?
+			PERF_EVENT_MISC_USER : PERF_EVENT_MISC_KERNEL;
+	}
+	if (mmcra & MMCRA_SIHV)
+		return PERF_EVENT_MISC_HYPERVISOR;
+	return (mmcra & MMCRA_SIPR) ? PERF_EVENT_MISC_USER :
+		PERF_EVENT_MISC_KERNEL;
+}
+
+/*
+ * Overload regs->dsisr to store MMCRA so we only need to read it once
+ * on each interrupt.
+ */
+static inline void perf_read_regs(struct pt_regs *regs)
+{
+	regs->dsisr = mfspr(SPRN_MMCRA);
+}
+
+/*
+ * If interrupts were soft-disabled when a PMU interrupt occurs, treat
+ * it as an NMI.
+ */
+static inline int perf_intr_is_nmi(struct pt_regs *regs)
+{
+	return !regs->softe;
+}
+
+#endif /* CONFIG_PPC64 */
+
 static void perf_counter_interrupt(struct pt_regs *regs);
 
 void perf_counter_print_debug(void)
@@ -78,12 +187,14 @@ static unsigned long read_pmc(int idx)
 	case 6:
 		val = mfspr(SPRN_PMC6);
 		break;
+#ifdef CONFIG_PPC64
 	case 7:
 		val = mfspr(SPRN_PMC7);
 		break;
 	case 8:
 		val = mfspr(SPRN_PMC8);
 		break;
+#endif /* CONFIG_PPC64 */
 	default:
 		printk(KERN_ERR "oops trying to read PMC%d\n", idx);
 		val = 0;
@@ -115,12 +226,14 @@ static void write_pmc(int idx, unsigned long val)
 	case 6:
 		mtspr(SPRN_PMC6, val);
 		break;
+#ifdef CONFIG_PPC64
 	case 7:
 		mtspr(SPRN_PMC7, val);
 		break;
 	case 8:
 		mtspr(SPRN_PMC8, val);
 		break;
+#endif /* CONFIG_PPC64 */
 	default:
 		printk(KERN_ERR "oops trying to write PMC%d\n", idx);
 	}
@@ -135,15 +248,15 @@ static void write_pmc(int idx, unsigned long val)
 static int power_check_constraints(u64 event[], unsigned int cflags[],
 				   int n_ev)
 {
-	u64 mask, value, nv;
+	unsigned long mask, value, nv;
 	u64 alternatives[MAX_HWCOUNTERS][MAX_EVENT_ALTERNATIVES];
-	u64 amasks[MAX_HWCOUNTERS][MAX_EVENT_ALTERNATIVES];
-	u64 avalues[MAX_HWCOUNTERS][MAX_EVENT_ALTERNATIVES];
-	u64 smasks[MAX_HWCOUNTERS], svalues[MAX_HWCOUNTERS];
+	unsigned long amasks[MAX_HWCOUNTERS][MAX_EVENT_ALTERNATIVES];
+	unsigned long avalues[MAX_HWCOUNTERS][MAX_EVENT_ALTERNATIVES];
+	unsigned long smasks[MAX_HWCOUNTERS], svalues[MAX_HWCOUNTERS];
 	int n_alt[MAX_HWCOUNTERS], choice[MAX_HWCOUNTERS];
 	int i, j;
-	u64 addf = ppmu->add_fields;
-	u64 tadd = ppmu->test_adder;
+	unsigned long addf = ppmu->add_fields;
+	unsigned long tadd = ppmu->test_adder;
 
 	if (n_ev > ppmu->n_counter)
 		return -1;
@@ -283,7 +396,7 @@ static int check_excludes(struct perf_counter **ctrs, unsigned int cflags[],
 
 static void power_pmu_read(struct perf_counter *counter)
 {
-	long val, delta, prev;
+	s64 val, delta, prev;
 
 	if (!counter->hw.idx)
 		return;
@@ -403,14 +516,14 @@ static void write_mmcr0(struct cpu_hw_counters *cpuhw, unsigned long mmcr0)
 void hw_perf_disable(void)
 {
 	struct cpu_hw_counters *cpuhw;
-	unsigned long ret;
 	unsigned long flags;
 
+	if (!ppmu)
+		return;
 	local_irq_save(flags);
 	cpuhw = &__get_cpu_var(cpu_hw_counters);
 
-	ret = cpuhw->disabled;
-	if (!ret) {
+	if (!cpuhw->disabled) {
 		cpuhw->disabled = 1;
 		cpuhw->n_added = 0;
 
@@ -461,6 +574,8 @@ void hw_perf_enable(void)
 	int n_lim;
 	int idx;
 
+	if (!ppmu)
+		return;
 	local_irq_save(flags);
 	cpuhw = &__get_cpu_var(cpu_hw_counters);
 	if (!cpuhw->disabled) {
@@ -479,7 +594,7 @@ void hw_perf_enable(void)
 		mtspr(SPRN_MMCRA, cpuhw->mmcr[2] & ~MMCRA_SAMPLE_ENABLE);
 		mtspr(SPRN_MMCR1, cpuhw->mmcr[1]);
 		if (cpuhw->n_counters == 0)
-			get_lppaca()->pmcregs_in_use = 0;
+			perf_set_pmu_inuse(0);
 		goto out_enable;
 	}
 
@@ -512,7 +627,7 @@ void hw_perf_enable(void)
 	 * bit set and set the hardware counters to their initial values.
 	 * Then unfreeze the counters.
 	 */
-	get_lppaca()->pmcregs_in_use = 1;
+	perf_set_pmu_inuse(1);
 	mtspr(SPRN_MMCRA, cpuhw->mmcr[2] & ~MMCRA_SAMPLE_ENABLE);
 	mtspr(SPRN_MMCR1, cpuhw->mmcr[1]);
 	mtspr(SPRN_MMCR0, (cpuhw->mmcr[0] & ~(MMCR0_PMC1CE | MMCR0_PMCjCE))
@@ -626,6 +741,8 @@ int hw_perf_group_sched_in(struct perf_counter *group_leader,
 	long i, n, n0;
 	struct perf_counter *sub;
 
+	if (!ppmu)
+		return 0;
 	cpuhw = &__get_cpu_var(cpu_hw_counters);
 	n0 = cpuhw->n_counters;
 	n = collect_events(group_leader, ppmu->n_counter - n0,
@@ -913,6 +1030,8 @@ const struct pmu *hw_perf_counter_init(struct perf_counter *counter)
 	case PERF_TYPE_RAW:
 		ev = counter->attr.config;
 		break;
+	default:
+		return ERR_PTR(-EINVAL);
 	}
 	counter->hw.config_base = ev;
 	counter->hw.idx = 0;
@@ -1007,13 +1126,12 @@ const struct pmu *hw_perf_counter_init(struct perf_counter *counter)
  * things if requested.  Note that interrupts are hard-disabled
  * here so there is no possibility of being interrupted.
  */
-static void record_and_restart(struct perf_counter *counter, long val,
+static void record_and_restart(struct perf_counter *counter, unsigned long val,
 			       struct pt_regs *regs, int nmi)
 {
 	u64 period = counter->hw.sample_period;
 	s64 prev, delta, left;
 	int record = 0;
-	u64 addr, mmcra, sdsync;
 
 	/* we don't have to worry about interrupts here */
 	prev = atomic64_read(&counter->hw.prev_count);
@@ -1033,8 +1151,8 @@ static void record_and_restart(struct perf_counter *counter, long val,
 				left = period;
 			record = 1;
 		}
-		if (left < 0x80000000L)
-			val = 0x80000000L - left;
+		if (left < 0x80000000LL)
+			val = 0x80000000LL - left;
 	}
 
 	/*
@@ -1047,22 +1165,9 @@ static void record_and_restart(struct perf_counter *counter, long val,
 			.period	= counter->hw.last_period,
 		};
 
-		if (counter->attr.sample_type & PERF_SAMPLE_ADDR) {
-			/*
-			 * The user wants a data address recorded.
-			 * If we're not doing instruction sampling,
-			 * give them the SDAR (sampled data address).
-			 * If we are doing instruction sampling, then only
-			 * give them the SDAR if it corresponds to the
-			 * instruction pointed to by SIAR; this is indicated
-			 * by the [POWER6_]MMCRA_SDSYNC bit in MMCRA.
-			 */
-			mmcra = regs->dsisr;
-			sdsync = (ppmu->flags & PPMU_ALT_SIPR) ?
-				POWER6_MMCRA_SDSYNC : MMCRA_SDSYNC;
-			if (!(mmcra & MMCRA_SAMPLE_ENABLE) || (mmcra & sdsync))
-				data.addr = mfspr(SPRN_SDAR);
-		}
+		if (counter->attr.sample_type & PERF_SAMPLE_ADDR)
+			perf_get_data_addr(regs, &data.addr);
+
 		if (perf_counter_overflow(counter, nmi, &data)) {
 			/*
 			 * Interrupts are coming too fast - throttle them
@@ -1088,25 +1193,12 @@ static void record_and_restart(struct perf_counter *counter, long val,
  */
 unsigned long perf_misc_flags(struct pt_regs *regs)
 {
-	unsigned long mmcra;
-
-	if (TRAP(regs) != 0xf00) {
-		/* not a PMU interrupt */
-		return user_mode(regs) ? PERF_EVENT_MISC_USER :
-			PERF_EVENT_MISC_KERNEL;
-	}
+	u32 flags = perf_get_misc_flags(regs);
 
-	mmcra = regs->dsisr;
-	if (ppmu->flags & PPMU_ALT_SIPR) {
-		if (mmcra & POWER6_MMCRA_SIHV)
-			return PERF_EVENT_MISC_HYPERVISOR;
-		return (mmcra & POWER6_MMCRA_SIPR) ? PERF_EVENT_MISC_USER :
-			PERF_EVENT_MISC_KERNEL;
-	}
-	if (mmcra & MMCRA_SIHV)
-		return PERF_EVENT_MISC_HYPERVISOR;
-	return (mmcra & MMCRA_SIPR) ? PERF_EVENT_MISC_USER :
-			PERF_EVENT_MISC_KERNEL;
+	if (flags)
+		return flags;
+	return user_mode(regs) ? PERF_EVENT_MISC_USER :
+		PERF_EVENT_MISC_KERNEL;
 }
 
 /*
@@ -1115,20 +1207,12 @@ unsigned long perf_misc_flags(struct pt_regs *regs)
  */
 unsigned long perf_instruction_pointer(struct pt_regs *regs)
 {
-	unsigned long mmcra;
 	unsigned long ip;
-	unsigned long slot;
 
 	if (TRAP(regs) != 0xf00)
 		return regs->nip;	/* not a PMU interrupt */
 
-	ip = mfspr(SPRN_SIAR);
-	mmcra = regs->dsisr;
-	if ((mmcra & MMCRA_SAMPLE_ENABLE) && !(ppmu->flags & PPMU_ALT_SIPR)) {
-		slot = (mmcra & MMCRA_SLOT) >> MMCRA_SLOT_SHIFT;
-		if (slot > 1)
-			ip += 4 * (slot - 1);
-	}
+	ip = mfspr(SPRN_SIAR) + perf_ip_adjust(regs);
 	return ip;
 }
 
@@ -1140,7 +1224,7 @@ static void perf_counter_interrupt(struct pt_regs *regs)
 	int i;
 	struct cpu_hw_counters *cpuhw = &__get_cpu_var(cpu_hw_counters);
 	struct perf_counter *counter;
-	long val;
+	unsigned long val;
 	int found = 0;
 	int nmi;
 
@@ -1148,16 +1232,9 @@ static void perf_counter_interrupt(struct pt_regs *regs)
 		freeze_limited_counters(cpuhw, mfspr(SPRN_PMC5),
 					mfspr(SPRN_PMC6));
 
-	/*
-	 * Overload regs->dsisr to store MMCRA so we only need to read it once.
-	 */
-	regs->dsisr = mfspr(SPRN_MMCRA);
+	perf_read_regs(regs);
 
-	/*
-	 * If interrupts were soft-disabled when this PMU interrupt
-	 * occurred, treat it as an NMI.
-	 */
-	nmi = !regs->softe;
+	nmi = perf_intr_is_nmi(regs);
 	if (nmi)
 		nmi_enter();
 	else
@@ -1210,54 +1287,28 @@ void hw_perf_counter_setup(int cpu)
 {
 	struct cpu_hw_counters *cpuhw = &per_cpu(cpu_hw_counters, cpu);
 
+	if (!ppmu)
+		return;
 	memset(cpuhw, 0, sizeof(*cpuhw));
 	cpuhw->mmcr[0] = MMCR0_FC;
 }
 
-extern struct power_pmu power4_pmu;
-extern struct power_pmu ppc970_pmu;
-extern struct power_pmu power5_pmu;
-extern struct power_pmu power5p_pmu;
-extern struct power_pmu power6_pmu;
-extern struct power_pmu power7_pmu;
-
-static int init_perf_counters(void)
+int register_power_pmu(struct power_pmu *pmu)
 {
-	unsigned long pvr;
-
-	/* XXX should get this from cputable */
-	pvr = mfspr(SPRN_PVR);
-	switch (PVR_VER(pvr)) {
-	case PV_POWER4:
-	case PV_POWER4p:
-		ppmu = &power4_pmu;
-		break;
-	case PV_970:
-	case PV_970FX:
-	case PV_970MP:
-		ppmu = &ppc970_pmu;
-		break;
-	case PV_POWER5:
-		ppmu = &power5_pmu;
-		break;
-	case PV_POWER5p:
-		ppmu = &power5p_pmu;
-		break;
-	case 0x3e:
-		ppmu = &power6_pmu;
-		break;
-	case 0x3f:
-		ppmu = &power7_pmu;
-		break;
-	}
+	if (ppmu)
+		return -EBUSY;		/* something's already registered */
+
+	ppmu = pmu;
+	pr_info("%s performance monitor hardware support registered\n",
+		pmu->name);
 
+#ifdef MSR_HV
 	/*
 	 * Use FCHV to ignore kernel events if MSR.HV is set.
 	 */
 	if (mfmsr() & MSR_HV)
 		freeze_counters_kernel = MMCR0_FCHV;
+#endif /* CONFIG_PPC64 */
 
 	return 0;
 }
-
-arch_initcall(init_perf_counters);
diff --git a/arch/powerpc/kernel/power4-pmu.c b/arch/powerpc/kernel/power4-pmu.c
index 07bd308a5fa..3c90a3d9173 100644
--- a/arch/powerpc/kernel/power4-pmu.c
+++ b/arch/powerpc/kernel/power4-pmu.c
@@ -10,7 +10,9 @@
  */
 #include <linux/kernel.h>
 #include <linux/perf_counter.h>
+#include <linux/string.h>
 #include <asm/reg.h>
+#include <asm/cputable.h>
 
 /*
  * Bits in event code for POWER4
@@ -179,22 +181,22 @@ static short mmcr1_adder_bits[8] = {
  */
 
 static struct unitinfo {
-	u64	value, mask;
-	int	unit;
-	int	lowerbit;
+	unsigned long	value, mask;
+	int		unit;
+	int		lowerbit;
 } p4_unitinfo[16] = {
-	[PM_FPU]  = { 0x44000000000000ull, 0x88000000000000ull, PM_FPU, 0 },
-	[PM_ISU1] = { 0x20080000000000ull, 0x88000000000000ull, PM_ISU1, 0 },
+	[PM_FPU]  = { 0x44000000000000ul, 0x88000000000000ul, PM_FPU, 0 },
+	[PM_ISU1] = { 0x20080000000000ul, 0x88000000000000ul, PM_ISU1, 0 },
 	[PM_ISU1_ALT] =
-		    { 0x20080000000000ull, 0x88000000000000ull, PM_ISU1, 0 },
-	[PM_IFU]  = { 0x02200000000000ull, 0x08820000000000ull, PM_IFU, 41 },
+		    { 0x20080000000000ul, 0x88000000000000ul, PM_ISU1, 0 },
+	[PM_IFU]  = { 0x02200000000000ul, 0x08820000000000ul, PM_IFU, 41 },
 	[PM_IFU_ALT] =
-		    { 0x02200000000000ull, 0x08820000000000ull, PM_IFU, 41 },
-	[PM_IDU0] = { 0x10100000000000ull, 0x80840000000000ull, PM_IDU0, 1 },
-	[PM_ISU2] = { 0x10140000000000ull, 0x80840000000000ull, PM_ISU2, 0 },
-	[PM_LSU0] = { 0x01400000000000ull, 0x08800000000000ull, PM_LSU0, 0 },
-	[PM_LSU1] = { 0x00000000000000ull, 0x00010000000000ull, PM_LSU1, 40 },
-	[PM_GPS]  = { 0x00000000000000ull, 0x00000000000000ull, PM_GPS, 0 }
+		    { 0x02200000000000ul, 0x08820000000000ul, PM_IFU, 41 },
+	[PM_IDU0] = { 0x10100000000000ul, 0x80840000000000ul, PM_IDU0, 1 },
+	[PM_ISU2] = { 0x10140000000000ul, 0x80840000000000ul, PM_ISU2, 0 },
+	[PM_LSU0] = { 0x01400000000000ul, 0x08800000000000ul, PM_LSU0, 0 },
+	[PM_LSU1] = { 0x00000000000000ul, 0x00010000000000ul, PM_LSU1, 40 },
+	[PM_GPS]  = { 0x00000000000000ul, 0x00000000000000ul, PM_GPS, 0 }
 };
 
 static unsigned char direct_marked_event[8] = {
@@ -249,10 +251,11 @@ static int p4_marked_instr_event(u64 event)
 	return (mask >> (byte * 8 + bit)) & 1;
 }
 
-static int p4_get_constraint(u64 event, u64 *maskp, u64 *valp)
+static int p4_get_constraint(u64 event, unsigned long *maskp,
+			     unsigned long *valp)
 {
 	int pmc, byte, unit, lower, sh;
-	u64 mask = 0, value = 0;
+	unsigned long mask = 0, value = 0;
 	int grp = -1;
 
 	pmc = (event >> PM_PMC_SH) & PM_PMC_MSK;
@@ -282,14 +285,14 @@ static int p4_get_constraint(u64 event, u64 *maskp, u64 *valp)
 		value |= p4_unitinfo[unit].value;
 		sh = p4_unitinfo[unit].lowerbit;
 		if (sh > 1)
-			value |= (u64)lower << sh;
+			value |= (unsigned long)lower << sh;
 		else if (lower != sh)
 			return -1;
 		unit = p4_unitinfo[unit].unit;
 
 		/* Set byte lane select field */
 		mask  |= 0xfULL << (28 - 4 * byte);
-		value |= (u64)unit << (28 - 4 * byte);
+		value |= (unsigned long)unit << (28 - 4 * byte);
 	}
 	if (grp == 0) {
 		/* increment PMC1/2/5/6 field */
@@ -353,9 +356,9 @@ static int p4_get_alternatives(u64 event, unsigned int flags, u64 alt[])
 }
 
 static int p4_compute_mmcr(u64 event[], int n_ev,
-			   unsigned int hwc[], u64 mmcr[])
+			   unsigned int hwc[], unsigned long mmcr[])
 {
-	u64 mmcr0 = 0, mmcr1 = 0, mmcra = 0;
+	unsigned long mmcr0 = 0, mmcr1 = 0, mmcra = 0;
 	unsigned int pmc, unit, byte, psel, lower;
 	unsigned int ttm, grp;
 	unsigned int pmc_inuse = 0;
@@ -429,9 +432,11 @@ static int p4_compute_mmcr(u64 event[], int n_ev,
 		return -1;
 
 	/* Set TTMxSEL fields.  Note, units 1-3 => TTM0SEL codes 0-2 */
-	mmcr1 |= (u64)(unituse[3] * 2 + unituse[2]) << MMCR1_TTM0SEL_SH;
-	mmcr1 |= (u64)(unituse[7] * 3 + unituse[6] * 2) << MMCR1_TTM1SEL_SH;
-	mmcr1 |= (u64)unituse[9] << MMCR1_TTM2SEL_SH;
+	mmcr1 |= (unsigned long)(unituse[3] * 2 + unituse[2])
+		<< MMCR1_TTM0SEL_SH;
+	mmcr1 |= (unsigned long)(unituse[7] * 3 + unituse[6] * 2)
+		<< MMCR1_TTM1SEL_SH;
+	mmcr1 |= (unsigned long)unituse[9] << MMCR1_TTM2SEL_SH;
 
 	/* Set TTCxSEL fields. */
 	if (unitlower & 0xe)
@@ -456,7 +461,8 @@ static int p4_compute_mmcr(u64 event[], int n_ev,
 				ttm = unit - 1;		/* 2->1, 3->2 */
 			else
 				ttm = unit >> 2;
-			mmcr1 |= (u64)ttm << (MMCR1_TD_CP_DBG0SEL_SH - 2*byte);
+			mmcr1 |= (unsigned long)ttm
+				<< (MMCR1_TD_CP_DBG0SEL_SH - 2 * byte);
 		}
 	}
 
@@ -519,7 +525,7 @@ static int p4_compute_mmcr(u64 event[], int n_ev,
 	return 0;
 }
 
-static void p4_disable_pmc(unsigned int pmc, u64 mmcr[])
+static void p4_disable_pmc(unsigned int pmc, unsigned long mmcr[])
 {
 	/*
 	 * Setting the PMCxSEL field to 0 disables PMC x.
@@ -583,16 +589,28 @@ static int power4_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
 	},
 };
 
-struct power_pmu power4_pmu = {
-	.n_counter = 8,
-	.max_alternatives = 5,
-	.add_fields = 0x0000001100005555ull,
-	.test_adder = 0x0011083300000000ull,
-	.compute_mmcr = p4_compute_mmcr,
-	.get_constraint = p4_get_constraint,
-	.get_alternatives = p4_get_alternatives,
-	.disable_pmc = p4_disable_pmc,
-	.n_generic = ARRAY_SIZE(p4_generic_events),
-	.generic_events = p4_generic_events,
-	.cache_events = &power4_cache_events,
+static struct power_pmu power4_pmu = {
+	.name			= "POWER4/4+",
+	.n_counter		= 8,
+	.max_alternatives	= 5,
+	.add_fields		= 0x0000001100005555ul,
+	.test_adder		= 0x0011083300000000ul,
+	.compute_mmcr		= p4_compute_mmcr,
+	.get_constraint		= p4_get_constraint,
+	.get_alternatives	= p4_get_alternatives,
+	.disable_pmc		= p4_disable_pmc,
+	.n_generic		= ARRAY_SIZE(p4_generic_events),
+	.generic_events		= p4_generic_events,
+	.cache_events		= &power4_cache_events,
 };
+
+static int init_power4_pmu(void)
+{
+	if (!cur_cpu_spec->oprofile_cpu_type ||
+	    strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/power4"))
+		return -ENODEV;
+
+	return register_power_pmu(&power4_pmu);
+}
+
+arch_initcall(init_power4_pmu);
diff --git a/arch/powerpc/kernel/power5+-pmu.c b/arch/powerpc/kernel/power5+-pmu.c
index 41e5d2d958d..31918af3e35 100644
--- a/arch/powerpc/kernel/power5+-pmu.c
+++ b/arch/powerpc/kernel/power5+-pmu.c
@@ -10,7 +10,9 @@
  */
 #include <linux/kernel.h>
 #include <linux/perf_counter.h>
+#include <linux/string.h>
 #include <asm/reg.h>
+#include <asm/cputable.h>
 
 /*
  * Bits in event code for POWER5+ (POWER5 GS) and POWER5++ (POWER5 GS DD3)
@@ -126,20 +128,21 @@ static const int grsel_shift[8] = {
 };
 
 /* Masks and values for using events from the various units */
-static u64 unit_cons[PM_LASTUNIT+1][2] = {
-	[PM_FPU] =   { 0x3200000000ull, 0x0100000000ull },
-	[PM_ISU0] =  { 0x0200000000ull, 0x0080000000ull },
-	[PM_ISU1] =  { 0x3200000000ull, 0x3100000000ull },
-	[PM_IFU] =   { 0x3200000000ull, 0x2100000000ull },
-	[PM_IDU] =   { 0x0e00000000ull, 0x0040000000ull },
-	[PM_GRS] =   { 0x0e00000000ull, 0x0c40000000ull },
+static unsigned long unit_cons[PM_LASTUNIT+1][2] = {
+	[PM_FPU] =   { 0x3200000000ul, 0x0100000000ul },
+	[PM_ISU0] =  { 0x0200000000ul, 0x0080000000ul },
+	[PM_ISU1] =  { 0x3200000000ul, 0x3100000000ul },
+	[PM_IFU] =   { 0x3200000000ul, 0x2100000000ul },
+	[PM_IDU] =   { 0x0e00000000ul, 0x0040000000ul },
+	[PM_GRS] =   { 0x0e00000000ul, 0x0c40000000ul },
 };
 
-static int power5p_get_constraint(u64 event, u64 *maskp, u64 *valp)
+static int power5p_get_constraint(u64 event, unsigned long *maskp,
+				  unsigned long *valp)
 {
 	int pmc, byte, unit, sh;
 	int bit, fmask;
-	u64 mask = 0, value = 0;
+	unsigned long mask = 0, value = 0;
 
 	pmc = (event >> PM_PMC_SH) & PM_PMC_MSK;
 	if (pmc) {
@@ -171,17 +174,18 @@ static int power5p_get_constraint(u64 event, u64 *maskp, u64 *valp)
 			bit = event & 7;
 			fmask = (bit == 6)? 7: 3;
 			sh = grsel_shift[bit];
-			mask |= (u64)fmask << sh;
-			value |= (u64)((event >> PM_GRS_SH) & fmask) << sh;
+			mask |= (unsigned long)fmask << sh;
+			value |= (unsigned long)((event >> PM_GRS_SH) & fmask)
+				<< sh;
 		}
 		/* Set byte lane select field */
-		mask  |= 0xfULL << (24 - 4 * byte);
-		value |= (u64)unit << (24 - 4 * byte);
+		mask  |= 0xfUL << (24 - 4 * byte);
+		value |= (unsigned long)unit << (24 - 4 * byte);
 	}
 	if (pmc < 5) {
 		/* need a counter from PMC1-4 set */
-		mask  |= 0x8000000000000ull;
-		value |= 0x1000000000000ull;
+		mask  |= 0x8000000000000ul;
+		value |= 0x1000000000000ul;
 	}
 	*maskp = mask;
 	*valp = value;
@@ -452,10 +456,10 @@ static int power5p_marked_instr_event(u64 event)
 }
 
 static int power5p_compute_mmcr(u64 event[], int n_ev,
-				unsigned int hwc[], u64 mmcr[])
+				unsigned int hwc[], unsigned long mmcr[])
 {
-	u64 mmcr1 = 0;
-	u64 mmcra = 0;
+	unsigned long mmcr1 = 0;
+	unsigned long mmcra = 0;
 	unsigned int pmc, unit, byte, psel;
 	unsigned int ttm;
 	int i, isbus, bit, grsel;
@@ -517,7 +521,7 @@ static int power5p_compute_mmcr(u64 event[], int n_ev,
 			continue;
 		if (ttmuse++)
 			return -1;
-		mmcr1 |= (u64)i << MMCR1_TTM0SEL_SH;
+		mmcr1 |= (unsigned long)i << MMCR1_TTM0SEL_SH;
 	}
 	ttmuse = 0;
 	for (; i <= PM_GRS; ++i) {
@@ -525,7 +529,7 @@ static int power5p_compute_mmcr(u64 event[], int n_ev,
 			continue;
 		if (ttmuse++)
 			return -1;
-		mmcr1 |= (u64)(i & 3) << MMCR1_TTM1SEL_SH;
+		mmcr1 |= (unsigned long)(i & 3) << MMCR1_TTM1SEL_SH;
 	}
 	if (ttmuse > 1)
 		return -1;
@@ -540,10 +544,11 @@ static int power5p_compute_mmcr(u64 event[], int n_ev,
 			unit = PM_ISU0_ALT;
 		} else if (unit == PM_LSU1 + 1) {
 			/* select lower word of LSU1 for this byte */
-			mmcr1 |= 1ull << (MMCR1_TTM3SEL_SH + 3 - byte);
+			mmcr1 |= 1ul << (MMCR1_TTM3SEL_SH + 3 - byte);
 		}
 		ttm = unit >> 2;
-		mmcr1 |= (u64)ttm << (MMCR1_TD_CP_DBG0SEL_SH - 2 * byte);
+		mmcr1 |= (unsigned long)ttm
+			<< (MMCR1_TD_CP_DBG0SEL_SH - 2 * byte);
 	}
 
 	/* Second pass: assign PMCs, set PMCxSEL and PMCx_ADDER_SEL fields */
@@ -568,7 +573,7 @@ static int power5p_compute_mmcr(u64 event[], int n_ev,
 			if (isbus && (byte & 2) &&
 			    (psel == 8 || psel == 0x10 || psel == 0x28))
 				/* add events on higher-numbered bus */
-				mmcr1 |= 1ull << (MMCR1_PMC1_ADDER_SEL_SH - pmc);
+				mmcr1 |= 1ul << (MMCR1_PMC1_ADDER_SEL_SH - pmc);
 		} else {
 			/* Instructions or run cycles on PMC5/6 */
 			--pmc;
@@ -576,7 +581,7 @@ static int power5p_compute_mmcr(u64 event[], int n_ev,
 		if (isbus && unit == PM_GRS) {
 			bit = psel & 7;
 			grsel = (event[i] >> PM_GRS_SH) & PM_GRS_MSK;
-			mmcr1 |= (u64)grsel << grsel_shift[bit];
+			mmcr1 |= (unsigned long)grsel << grsel_shift[bit];
 		}
 		if (power5p_marked_instr_event(event[i]))
 			mmcra |= MMCRA_SAMPLE_ENABLE;
@@ -599,7 +604,7 @@ static int power5p_compute_mmcr(u64 event[], int n_ev,
 	return 0;
 }
 
-static void power5p_disable_pmc(unsigned int pmc, u64 mmcr[])
+static void power5p_disable_pmc(unsigned int pmc, unsigned long mmcr[])
 {
 	if (pmc <= 3)
 		mmcr[1] &= ~(0x7fUL << MMCR1_PMCSEL_SH(pmc));
@@ -654,18 +659,31 @@ static int power5p_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
 	},
 };
 
-struct power_pmu power5p_pmu = {
-	.n_counter = 6,
-	.max_alternatives = MAX_ALT,
-	.add_fields = 0x7000000000055ull,
-	.test_adder = 0x3000040000000ull,
-	.compute_mmcr = power5p_compute_mmcr,
-	.get_constraint = power5p_get_constraint,
-	.get_alternatives = power5p_get_alternatives,
-	.disable_pmc = power5p_disable_pmc,
-	.limited_pmc_event = power5p_limited_pmc_event,
-	.flags = PPMU_LIMITED_PMC5_6,
-	.n_generic = ARRAY_SIZE(power5p_generic_events),
-	.generic_events = power5p_generic_events,
-	.cache_events = &power5p_cache_events,
+static struct power_pmu power5p_pmu = {
+	.name			= "POWER5+/++",
+	.n_counter		= 6,
+	.max_alternatives	= MAX_ALT,
+	.add_fields		= 0x7000000000055ul,
+	.test_adder		= 0x3000040000000ul,
+	.compute_mmcr		= power5p_compute_mmcr,
+	.get_constraint		= power5p_get_constraint,
+	.get_alternatives	= power5p_get_alternatives,
+	.disable_pmc		= power5p_disable_pmc,
+	.limited_pmc_event	= power5p_limited_pmc_event,
+	.flags			= PPMU_LIMITED_PMC5_6,
+	.n_generic		= ARRAY_SIZE(power5p_generic_events),
+	.generic_events		= power5p_generic_events,
+	.cache_events		= &power5p_cache_events,
 };
+
+static int init_power5p_pmu(void)
+{
+	if (!cur_cpu_spec->oprofile_cpu_type ||
+	    (strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/power5+")
+	     && strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/power5++")))
+		return -ENODEV;
+
+	return register_power_pmu(&power5p_pmu);
+}
+
+arch_initcall(init_power5p_pmu);
diff --git a/arch/powerpc/kernel/power5-pmu.c b/arch/powerpc/kernel/power5-pmu.c
index 05600b66221..867f6f66396 100644
--- a/arch/powerpc/kernel/power5-pmu.c
+++ b/arch/powerpc/kernel/power5-pmu.c
@@ -10,7 +10,9 @@
  */
 #include <linux/kernel.h>
 #include <linux/perf_counter.h>
+#include <linux/string.h>
 #include <asm/reg.h>
+#include <asm/cputable.h>
 
 /*
  * Bits in event code for POWER5 (not POWER5++)
@@ -130,20 +132,21 @@ static const int grsel_shift[8] = {
 };
 
 /* Masks and values for using events from the various units */
-static u64 unit_cons[PM_LASTUNIT+1][2] = {
-	[PM_FPU] =   { 0xc0002000000000ull, 0x00001000000000ull },
-	[PM_ISU0] =  { 0x00002000000000ull, 0x00000800000000ull },
-	[PM_ISU1] =  { 0xc0002000000000ull, 0xc0001000000000ull },
-	[PM_IFU] =   { 0xc0002000000000ull, 0x80001000000000ull },
-	[PM_IDU] =   { 0x30002000000000ull, 0x00000400000000ull },
-	[PM_GRS] =   { 0x30002000000000ull, 0x30000400000000ull },
+static unsigned long unit_cons[PM_LASTUNIT+1][2] = {
+	[PM_FPU] =   { 0xc0002000000000ul, 0x00001000000000ul },
+	[PM_ISU0] =  { 0x00002000000000ul, 0x00000800000000ul },
+	[PM_ISU1] =  { 0xc0002000000000ul, 0xc0001000000000ul },
+	[PM_IFU] =   { 0xc0002000000000ul, 0x80001000000000ul },
+	[PM_IDU] =   { 0x30002000000000ul, 0x00000400000000ul },
+	[PM_GRS] =   { 0x30002000000000ul, 0x30000400000000ul },
 };
 
-static int power5_get_constraint(u64 event, u64 *maskp, u64 *valp)
+static int power5_get_constraint(u64 event, unsigned long *maskp,
+				 unsigned long *valp)
 {
 	int pmc, byte, unit, sh;
 	int bit, fmask;
-	u64 mask = 0, value = 0;
+	unsigned long mask = 0, value = 0;
 	int grp = -1;
 
 	pmc = (event >> PM_PMC_SH) & PM_PMC_MSK;
@@ -178,8 +181,9 @@ static int power5_get_constraint(u64 event, u64 *maskp, u64 *valp)
 			bit = event & 7;
 			fmask = (bit == 6)? 7: 3;
 			sh = grsel_shift[bit];
-			mask |= (u64)fmask << sh;
-			value |= (u64)((event >> PM_GRS_SH) & fmask) << sh;
+			mask |= (unsigned long)fmask << sh;
+			value |= (unsigned long)((event >> PM_GRS_SH) & fmask)
+				<< sh;
 		}
 		/*
 		 * Bus events on bytes 0 and 2 can be counted
@@ -188,22 +192,22 @@ static int power5_get_constraint(u64 event, u64 *maskp, u64 *valp)
 		if (!pmc)
 			grp = byte & 1;
 		/* Set byte lane select field */
-		mask  |= 0xfULL << (24 - 4 * byte);
-		value |= (u64)unit << (24 - 4 * byte);
+		mask  |= 0xfUL << (24 - 4 * byte);
+		value |= (unsigned long)unit << (24 - 4 * byte);
 	}
 	if (grp == 0) {
 		/* increment PMC1/2 field */
-		mask  |= 0x200000000ull;
-		value |= 0x080000000ull;
+		mask  |= 0x200000000ul;
+		value |= 0x080000000ul;
 	} else if (grp == 1) {
 		/* increment PMC3/4 field */
-		mask  |= 0x40000000ull;
-		value |= 0x10000000ull;
+		mask  |= 0x40000000ul;
+		value |= 0x10000000ul;
 	}
 	if (pmc < 5) {
 		/* need a counter from PMC1-4 set */
-		mask  |= 0x8000000000000ull;
-		value |= 0x1000000000000ull;
+		mask  |= 0x8000000000000ul;
+		value |= 0x1000000000000ul;
 	}
 	*maskp = mask;
 	*valp = value;
@@ -383,10 +387,10 @@ static int power5_marked_instr_event(u64 event)
 }
 
 static int power5_compute_mmcr(u64 event[], int n_ev,
-			       unsigned int hwc[], u64 mmcr[])
+			       unsigned int hwc[], unsigned long mmcr[])
 {
-	u64 mmcr1 = 0;
-	u64 mmcra = 0;
+	unsigned long mmcr1 = 0;
+	unsigned long mmcra = 0;
 	unsigned int pmc, unit, byte, psel;
 	unsigned int ttm, grp;
 	int i, isbus, bit, grsel;
@@ -457,7 +461,7 @@ static int power5_compute_mmcr(u64 event[], int n_ev,
 			continue;
 		if (ttmuse++)
 			return -1;
-		mmcr1 |= (u64)i << MMCR1_TTM0SEL_SH;
+		mmcr1 |= (unsigned long)i << MMCR1_TTM0SEL_SH;
 	}
 	ttmuse = 0;
 	for (; i <= PM_GRS; ++i) {
@@ -465,7 +469,7 @@ static int power5_compute_mmcr(u64 event[], int n_ev,
 			continue;
 		if (ttmuse++)
 			return -1;
-		mmcr1 |= (u64)(i & 3) << MMCR1_TTM1SEL_SH;
+		mmcr1 |= (unsigned long)(i & 3) << MMCR1_TTM1SEL_SH;
 	}
 	if (ttmuse > 1)
 		return -1;
@@ -480,10 +484,11 @@ static int power5_compute_mmcr(u64 event[], int n_ev,
 			unit = PM_ISU0_ALT;
 		} else if (unit == PM_LSU1 + 1) {
 			/* select lower word of LSU1 for this byte */
-			mmcr1 |= 1ull << (MMCR1_TTM3SEL_SH + 3 - byte);
+			mmcr1 |= 1ul << (MMCR1_TTM3SEL_SH + 3 - byte);
 		}
 		ttm = unit >> 2;
-		mmcr1 |= (u64)ttm << (MMCR1_TD_CP_DBG0SEL_SH - 2 * byte);
+		mmcr1 |= (unsigned long)ttm
+			<< (MMCR1_TD_CP_DBG0SEL_SH - 2 * byte);
 	}
 
 	/* Second pass: assign PMCs, set PMCxSEL and PMCx_ADDER_SEL fields */
@@ -513,7 +518,7 @@ static int power5_compute_mmcr(u64 event[], int n_ev,
 			--pmc;
 			if ((psel == 8 || psel == 0x10) && isbus && (byte & 2))
 				/* add events on higher-numbered bus */
-				mmcr1 |= 1ull << (MMCR1_PMC1_ADDER_SEL_SH - pmc);
+				mmcr1 |= 1ul << (MMCR1_PMC1_ADDER_SEL_SH - pmc);
 		} else {
 			/* Instructions or run cycles on PMC5/6 */
 			--pmc;
@@ -521,7 +526,7 @@ static int power5_compute_mmcr(u64 event[], int n_ev,
 		if (isbus && unit == PM_GRS) {
 			bit = psel & 7;
 			grsel = (event[i] >> PM_GRS_SH) & PM_GRS_MSK;
-			mmcr1 |= (u64)grsel << grsel_shift[bit];
+			mmcr1 |= (unsigned long)grsel << grsel_shift[bit];
 		}
 		if (power5_marked_instr_event(event[i]))
 			mmcra |= MMCRA_SAMPLE_ENABLE;
@@ -541,7 +546,7 @@ static int power5_compute_mmcr(u64 event[], int n_ev,
 	return 0;
 }
 
-static void power5_disable_pmc(unsigned int pmc, u64 mmcr[])
+static void power5_disable_pmc(unsigned int pmc, unsigned long mmcr[])
 {
 	if (pmc <= 3)
 		mmcr[1] &= ~(0x7fUL << MMCR1_PMCSEL_SH(pmc));
@@ -596,16 +601,28 @@ static int power5_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
 	},
 };
 
-struct power_pmu power5_pmu = {
-	.n_counter = 6,
-	.max_alternatives = MAX_ALT,
-	.add_fields = 0x7000090000555ull,
-	.test_adder = 0x3000490000000ull,
-	.compute_mmcr = power5_compute_mmcr,
-	.get_constraint = power5_get_constraint,
-	.get_alternatives = power5_get_alternatives,
-	.disable_pmc = power5_disable_pmc,
-	.n_generic = ARRAY_SIZE(power5_generic_events),
-	.generic_events = power5_generic_events,
-	.cache_events = &power5_cache_events,
+static struct power_pmu power5_pmu = {
+	.name			= "POWER5",
+	.n_counter		= 6,
+	.max_alternatives	= MAX_ALT,
+	.add_fields		= 0x7000090000555ul,
+	.test_adder		= 0x3000490000000ul,
+	.compute_mmcr		= power5_compute_mmcr,
+	.get_constraint		= power5_get_constraint,
+	.get_alternatives	= power5_get_alternatives,
+	.disable_pmc		= power5_disable_pmc,
+	.n_generic		= ARRAY_SIZE(power5_generic_events),
+	.generic_events		= power5_generic_events,
+	.cache_events		= &power5_cache_events,
 };
+
+static int init_power5_pmu(void)
+{
+	if (!cur_cpu_spec->oprofile_cpu_type ||
+	    strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/power5"))
+		return -ENODEV;
+
+	return register_power_pmu(&power5_pmu);
+}
+
+arch_initcall(init_power5_pmu);
diff --git a/arch/powerpc/kernel/power6-pmu.c b/arch/powerpc/kernel/power6-pmu.c
index 46f74bebcfd..fa21890531d 100644
--- a/arch/powerpc/kernel/power6-pmu.c
+++ b/arch/powerpc/kernel/power6-pmu.c
@@ -10,7 +10,9 @@
  */
 #include <linux/kernel.h>
 #include <linux/perf_counter.h>
+#include <linux/string.h>
 #include <asm/reg.h>
+#include <asm/cputable.h>
 
 /*
  * Bits in event code for POWER6
@@ -41,9 +43,9 @@
 #define MMCR1_NESTSEL_SH	45
 #define MMCR1_NESTSEL_MSK	0x7
 #define MMCR1_NESTSEL(m)	(((m) >> MMCR1_NESTSEL_SH) & MMCR1_NESTSEL_MSK)
-#define MMCR1_PMC1_LLA		((u64)1 << 44)
-#define MMCR1_PMC1_LLA_VALUE	((u64)1 << 39)
-#define MMCR1_PMC1_ADDR_SEL	((u64)1 << 35)
+#define MMCR1_PMC1_LLA		(1ul << 44)
+#define MMCR1_PMC1_LLA_VALUE	(1ul << 39)
+#define MMCR1_PMC1_ADDR_SEL	(1ul << 35)
 #define MMCR1_PMC1SEL_SH	24
 #define MMCR1_PMCSEL_SH(n)	(MMCR1_PMC1SEL_SH - (n) * 8)
 #define MMCR1_PMCSEL_MSK	0xff
@@ -173,10 +175,10 @@ static int power6_marked_instr_event(u64 event)
  * Assign PMC numbers and compute MMCR1 value for a set of events
  */
 static int p6_compute_mmcr(u64 event[], int n_ev,
-			   unsigned int hwc[], u64 mmcr[])
+			   unsigned int hwc[], unsigned long mmcr[])
 {
-	u64 mmcr1 = 0;
-	u64 mmcra = 0;
+	unsigned long mmcr1 = 0;
+	unsigned long mmcra = 0;
 	int i;
 	unsigned int pmc, ev, b, u, s, psel;
 	unsigned int ttmset = 0;
@@ -215,7 +217,7 @@ static int p6_compute_mmcr(u64 event[], int n_ev,
 			/* check for conflict on this byte of event bus */
 			if ((ttmset & (1 << b)) && MMCR1_TTMSEL(mmcr1, b) != u)
 				return -1;
-			mmcr1 |= (u64)u << MMCR1_TTMSEL_SH(b);
+			mmcr1 |= (unsigned long)u << MMCR1_TTMSEL_SH(b);
 			ttmset |= 1 << b;
 			if (u == 5) {
 				/* Nest events have a further mux */
@@ -224,7 +226,7 @@ static int p6_compute_mmcr(u64 event[], int n_ev,
 				    MMCR1_NESTSEL(mmcr1) != s)
 					return -1;
 				ttmset |= 0x10;
-				mmcr1 |= (u64)s << MMCR1_NESTSEL_SH;
+				mmcr1 |= (unsigned long)s << MMCR1_NESTSEL_SH;
 			}
 			if (0x30 <= psel && psel <= 0x3d) {
 				/* these need the PMCx_ADDR_SEL bits */
@@ -243,7 +245,7 @@ static int p6_compute_mmcr(u64 event[], int n_ev,
 		if (power6_marked_instr_event(event[i]))
 			mmcra |= MMCRA_SAMPLE_ENABLE;
 		if (pmc < 4)
-			mmcr1 |= (u64)psel << MMCR1_PMCSEL_SH(pmc);
+			mmcr1 |= (unsigned long)psel << MMCR1_PMCSEL_SH(pmc);
 	}
 	mmcr[0] = 0;
 	if (pmc_inuse & 1)
@@ -265,10 +267,11 @@ static int p6_compute_mmcr(u64 event[], int n_ev,
  *	20-23, 24-27, 28-31 ditto for bytes 1, 2, 3
  *	32-34	select field: nest (subunit) event selector
  */
-static int p6_get_constraint(u64 event, u64 *maskp, u64 *valp)
+static int p6_get_constraint(u64 event, unsigned long *maskp,
+			     unsigned long *valp)
 {
 	int pmc, byte, sh, subunit;
-	u64 mask = 0, value = 0;
+	unsigned long mask = 0, value = 0;
 
 	pmc = (event >> PM_PMC_SH) & PM_PMC_MSK;
 	if (pmc) {
@@ -282,11 +285,11 @@ static int p6_get_constraint(u64 event, u64 *maskp, u64 *valp)
 		byte = (event >> PM_BYTE_SH) & PM_BYTE_MSK;
 		sh = byte * 4 + (16 - PM_UNIT_SH);
 		mask |= PM_UNIT_MSKS << sh;
-		value |= (u64)(event & PM_UNIT_MSKS) << sh;
+		value |= (unsigned long)(event & PM_UNIT_MSKS) << sh;
 		if ((event & PM_UNIT_MSKS) == (5 << PM_UNIT_SH)) {
 			subunit = (event >> PM_SUBUNIT_SH) & PM_SUBUNIT_MSK;
-			mask  |= (u64)PM_SUBUNIT_MSK << 32;
-			value |= (u64)subunit << 32;
+			mask  |= (unsigned long)PM_SUBUNIT_MSK << 32;
+			value |= (unsigned long)subunit << 32;
 		}
 	}
 	if (pmc <= 4) {
@@ -458,7 +461,7 @@ static int p6_get_alternatives(u64 event, unsigned int flags, u64 alt[])
 	return nalt;
 }
 
-static void p6_disable_pmc(unsigned int pmc, u64 mmcr[])
+static void p6_disable_pmc(unsigned int pmc, unsigned long mmcr[])
 {
 	/* Set PMCxSEL to 0 to disable PMCx */
 	if (pmc <= 3)
@@ -515,18 +518,30 @@ static int power6_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
 	},
 };
 
-struct power_pmu power6_pmu = {
-	.n_counter = 6,
-	.max_alternatives = MAX_ALT,
-	.add_fields = 0x1555,
-	.test_adder = 0x3000,
-	.compute_mmcr = p6_compute_mmcr,
-	.get_constraint = p6_get_constraint,
-	.get_alternatives = p6_get_alternatives,
-	.disable_pmc = p6_disable_pmc,
-	.limited_pmc_event = p6_limited_pmc_event,
-	.flags = PPMU_LIMITED_PMC5_6 | PPMU_ALT_SIPR,
-	.n_generic = ARRAY_SIZE(power6_generic_events),
-	.generic_events = power6_generic_events,
-	.cache_events = &power6_cache_events,
+static struct power_pmu power6_pmu = {
+	.name			= "POWER6",
+	.n_counter		= 6,
+	.max_alternatives	= MAX_ALT,
+	.add_fields		= 0x1555,
+	.test_adder		= 0x3000,
+	.compute_mmcr		= p6_compute_mmcr,
+	.get_constraint		= p6_get_constraint,
+	.get_alternatives	= p6_get_alternatives,
+	.disable_pmc		= p6_disable_pmc,
+	.limited_pmc_event	= p6_limited_pmc_event,
+	.flags			= PPMU_LIMITED_PMC5_6 | PPMU_ALT_SIPR,
+	.n_generic		= ARRAY_SIZE(power6_generic_events),
+	.generic_events		= power6_generic_events,
+	.cache_events		= &power6_cache_events,
 };
+
+static int init_power6_pmu(void)
+{
+	if (!cur_cpu_spec->oprofile_cpu_type ||
+	    strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/power6"))
+		return -ENODEV;
+
+	return register_power_pmu(&power6_pmu);
+}
+
+arch_initcall(init_power6_pmu);
diff --git a/arch/powerpc/kernel/power7-pmu.c b/arch/powerpc/kernel/power7-pmu.c
index b72e7a19d05..018d094d92f 100644
--- a/arch/powerpc/kernel/power7-pmu.c
+++ b/arch/powerpc/kernel/power7-pmu.c
@@ -10,7 +10,9 @@
  */
 #include <linux/kernel.h>
 #include <linux/perf_counter.h>
+#include <linux/string.h>
 #include <asm/reg.h>
+#include <asm/cputable.h>
 
 /*
  * Bits in event code for POWER7
@@ -71,10 +73,11 @@
  *     0-9: Count of events needing PMC1..PMC5
  */
 
-static int power7_get_constraint(u64 event, u64 *maskp, u64 *valp)
+static int power7_get_constraint(u64 event, unsigned long *maskp,
+				 unsigned long *valp)
 {
 	int pmc, sh;
-	u64 mask = 0, value = 0;
+	unsigned long mask = 0, value = 0;
 
 	pmc = (event >> PM_PMC_SH) & PM_PMC_MSK;
 	if (pmc) {
@@ -224,10 +227,10 @@ static int power7_marked_instr_event(u64 event)
 }
 
 static int power7_compute_mmcr(u64 event[], int n_ev,
-			       unsigned int hwc[], u64 mmcr[])
+			       unsigned int hwc[], unsigned long mmcr[])
 {
-	u64 mmcr1 = 0;
-	u64 mmcra = 0;
+	unsigned long mmcr1 = 0;
+	unsigned long mmcra = 0;
 	unsigned int pmc, unit, combine, l2sel, psel;
 	unsigned int pmc_inuse = 0;
 	int i;
@@ -265,11 +268,14 @@ static int power7_compute_mmcr(u64 event[], int n_ev,
 			--pmc;
 		}
 		if (pmc <= 3) {
-			mmcr1 |= (u64) unit << (MMCR1_TTM0SEL_SH - 4 * pmc);
-			mmcr1 |= (u64) combine << (MMCR1_PMC1_COMBINE_SH - pmc);
+			mmcr1 |= (unsigned long) unit
+				<< (MMCR1_TTM0SEL_SH - 4 * pmc);
+			mmcr1 |= (unsigned long) combine
+				<< (MMCR1_PMC1_COMBINE_SH - pmc);
 			mmcr1 |= psel << MMCR1_PMCSEL_SH(pmc);
 			if (unit == 6)	/* L2 events */
-				mmcr1 |= (u64) l2sel << MMCR1_L2SEL_SH;
+				mmcr1 |= (unsigned long) l2sel
+					<< MMCR1_L2SEL_SH;
 		}
 		if (power7_marked_instr_event(event[i]))
 			mmcra |= MMCRA_SAMPLE_ENABLE;
@@ -287,10 +293,10 @@ static int power7_compute_mmcr(u64 event[], int n_ev,
 	return 0;
 }
 
-static void power7_disable_pmc(unsigned int pmc, u64 mmcr[])
+static void power7_disable_pmc(unsigned int pmc, unsigned long mmcr[])
 {
 	if (pmc <= 3)
-		mmcr[1] &= ~(0xffULL << MMCR1_PMCSEL_SH(pmc));
+		mmcr[1] &= ~(0xffUL << MMCR1_PMCSEL_SH(pmc));
 }
 
 static int power7_generic_events[] = {
@@ -311,7 +317,7 @@ static int power7_generic_events[] = {
  */
 static int power7_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
 	[C(L1D)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
-		[C(OP_READ)] = {	0x400f0,	0xc880	},
+		[C(OP_READ)] = {	0xc880,		0x400f0	},
 		[C(OP_WRITE)] = {	0,		0x300f0	},
 		[C(OP_PREFETCH)] = {	0xd8b8,		0	},
 	},
@@ -321,8 +327,8 @@ static int power7_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
 		[C(OP_PREFETCH)] = {	0x408a,		0	},
 	},
 	[C(LL)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
-		[C(OP_READ)] = {	0x6080,		0x6084	},
-		[C(OP_WRITE)] = {	0x6082,		0x6086	},
+		[C(OP_READ)] = {	0x16080,	0x26080	},
+		[C(OP_WRITE)] = {	0x16082,	0x26082	},
 		[C(OP_PREFETCH)] = {	0,		0	},
 	},
 	[C(DTLB)] = {		/* 	RESULT_ACCESS	RESULT_MISS */
@@ -342,16 +348,29 @@ static int power7_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
 	},
 };
 
-struct power_pmu power7_pmu = {
-	.n_counter = 6,
-	.max_alternatives = MAX_ALT + 1,
-	.add_fields = 0x1555ull,
-	.test_adder = 0x3000ull,
-	.compute_mmcr = power7_compute_mmcr,
-	.get_constraint = power7_get_constraint,
-	.get_alternatives = power7_get_alternatives,
-	.disable_pmc = power7_disable_pmc,
-	.n_generic = ARRAY_SIZE(power7_generic_events),
-	.generic_events = power7_generic_events,
-	.cache_events = &power7_cache_events,
+static struct power_pmu power7_pmu = {
+	.name			= "POWER7",
+	.n_counter		= 6,
+	.max_alternatives	= MAX_ALT + 1,
+	.add_fields		= 0x1555ul,
+	.test_adder		= 0x3000ul,
+	.compute_mmcr		= power7_compute_mmcr,
+	.get_constraint		= power7_get_constraint,
+	.get_alternatives	= power7_get_alternatives,
+	.disable_pmc		= power7_disable_pmc,
+	.flags			= PPMU_ALT_SIPR,
+	.n_generic		= ARRAY_SIZE(power7_generic_events),
+	.generic_events		= power7_generic_events,
+	.cache_events		= &power7_cache_events,
 };
+
+static int init_power7_pmu(void)
+{
+	if (!cur_cpu_spec->oprofile_cpu_type ||
+	    strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/power7"))
+		return -ENODEV;
+
+	return register_power_pmu(&power7_pmu);
+}
+
+arch_initcall(init_power7_pmu);
diff --git a/arch/powerpc/kernel/ppc970-pmu.c b/arch/powerpc/kernel/ppc970-pmu.c
index ba0a357a89f..75dccb71a04 100644
--- a/arch/powerpc/kernel/ppc970-pmu.c
+++ b/arch/powerpc/kernel/ppc970-pmu.c
@@ -11,6 +11,7 @@
 #include <linux/string.h>
 #include <linux/perf_counter.h>
 #include <asm/reg.h>
+#include <asm/cputable.h>
 
 /*
  * Bits in event code for PPC970
@@ -183,7 +184,7 @@ static int p970_marked_instr_event(u64 event)
 }
 
 /* Masks and values for using events from the various units */
-static u64 unit_cons[PM_LASTUNIT+1][2] = {
+static unsigned long unit_cons[PM_LASTUNIT+1][2] = {
 	[PM_FPU] =   { 0xc80000000000ull, 0x040000000000ull },
 	[PM_VPU] =   { 0xc80000000000ull, 0xc40000000000ull },
 	[PM_ISU] =   { 0x080000000000ull, 0x020000000000ull },
@@ -192,10 +193,11 @@ static u64 unit_cons[PM_LASTUNIT+1][2] = {
 	[PM_STS] =   { 0x380000000000ull, 0x310000000000ull },
 };
 
-static int p970_get_constraint(u64 event, u64 *maskp, u64 *valp)
+static int p970_get_constraint(u64 event, unsigned long *maskp,
+			       unsigned long *valp)
 {
 	int pmc, byte, unit, sh, spcsel;
-	u64 mask = 0, value = 0;
+	unsigned long mask = 0, value = 0;
 	int grp = -1;
 
 	pmc = (event >> PM_PMC_SH) & PM_PMC_MSK;
@@ -222,7 +224,7 @@ static int p970_get_constraint(u64 event, u64 *maskp, u64 *valp)
 			grp = byte & 1;
 		/* Set byte lane select field */
 		mask  |= 0xfULL << (28 - 4 * byte);
-		value |= (u64)unit << (28 - 4 * byte);
+		value |= (unsigned long)unit << (28 - 4 * byte);
 	}
 	if (grp == 0) {
 		/* increment PMC1/2/5/6 field */
@@ -236,7 +238,7 @@ static int p970_get_constraint(u64 event, u64 *maskp, u64 *valp)
 	spcsel = (event >> PM_SPCSEL_SH) & PM_SPCSEL_MSK;
 	if (spcsel) {
 		mask  |= 3ull << 48;
-		value |= (u64)spcsel << 48;
+		value |= (unsigned long)spcsel << 48;
 	}
 	*maskp = mask;
 	*valp = value;
@@ -257,9 +259,9 @@ static int p970_get_alternatives(u64 event, unsigned int flags, u64 alt[])
 }
 
 static int p970_compute_mmcr(u64 event[], int n_ev,
-			     unsigned int hwc[], u64 mmcr[])
+			     unsigned int hwc[], unsigned long mmcr[])
 {
-	u64 mmcr0 = 0, mmcr1 = 0, mmcra = 0;
+	unsigned long mmcr0 = 0, mmcr1 = 0, mmcra = 0;
 	unsigned int pmc, unit, byte, psel;
 	unsigned int ttm, grp;
 	unsigned int pmc_inuse = 0;
@@ -320,7 +322,7 @@ static int p970_compute_mmcr(u64 event[], int n_ev,
 			continue;
 		ttm = unitmap[i];
 		++ttmuse[(ttm >> 2) & 1];
-		mmcr1 |= (u64)(ttm & ~4) << MMCR1_TTM1SEL_SH;
+		mmcr1 |= (unsigned long)(ttm & ~4) << MMCR1_TTM1SEL_SH;
 	}
 	/* Check only one unit per TTMx */
 	if (ttmuse[0] > 1 || ttmuse[1] > 1)
@@ -340,7 +342,8 @@ static int p970_compute_mmcr(u64 event[], int n_ev,
 			if (unit == PM_LSU1L && byte >= 2)
 				mmcr1 |= 1ull << (MMCR1_TTM3SEL_SH + 3 - byte);
 		}
-		mmcr1 |= (u64)ttm << (MMCR1_TD_CP_DBG0SEL_SH - 2 * byte);
+		mmcr1 |= (unsigned long)ttm
+			<< (MMCR1_TD_CP_DBG0SEL_SH - 2 * byte);
 	}
 
 	/* Second pass: assign PMCs, set PMCxSEL and PMCx_ADDER_SEL fields */
@@ -386,7 +389,8 @@ static int p970_compute_mmcr(u64 event[], int n_ev,
 	for (pmc = 0; pmc < 2; ++pmc)
 		mmcr0 |= pmcsel[pmc] << (MMCR0_PMC1SEL_SH - 7 * pmc);
 	for (; pmc < 8; ++pmc)
-		mmcr1 |= (u64)pmcsel[pmc] << (MMCR1_PMC3SEL_SH - 5 * (pmc - 2));
+		mmcr1 |= (unsigned long)pmcsel[pmc]
+			<< (MMCR1_PMC3SEL_SH - 5 * (pmc - 2));
 	if (pmc_inuse & 1)
 		mmcr0 |= MMCR0_PMC1CE;
 	if (pmc_inuse & 0xfe)
@@ -401,7 +405,7 @@ static int p970_compute_mmcr(u64 event[], int n_ev,
 	return 0;
 }
 
-static void p970_disable_pmc(unsigned int pmc, u64 mmcr[])
+static void p970_disable_pmc(unsigned int pmc, unsigned long mmcr[])
 {
 	int shift, i;
 
@@ -467,16 +471,29 @@ static int ppc970_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
 	},
 };
 
-struct power_pmu ppc970_pmu = {
-	.n_counter = 8,
-	.max_alternatives = 2,
-	.add_fields = 0x001100005555ull,
-	.test_adder = 0x013300000000ull,
-	.compute_mmcr = p970_compute_mmcr,
-	.get_constraint = p970_get_constraint,
-	.get_alternatives = p970_get_alternatives,
-	.disable_pmc = p970_disable_pmc,
-	.n_generic = ARRAY_SIZE(ppc970_generic_events),
-	.generic_events = ppc970_generic_events,
-	.cache_events = &ppc970_cache_events,
+static struct power_pmu ppc970_pmu = {
+	.name			= "PPC970/FX/MP",
+	.n_counter		= 8,
+	.max_alternatives	= 2,
+	.add_fields		= 0x001100005555ull,
+	.test_adder		= 0x013300000000ull,
+	.compute_mmcr		= p970_compute_mmcr,
+	.get_constraint		= p970_get_constraint,
+	.get_alternatives	= p970_get_alternatives,
+	.disable_pmc		= p970_disable_pmc,
+	.n_generic		= ARRAY_SIZE(ppc970_generic_events),
+	.generic_events		= ppc970_generic_events,
+	.cache_events		= &ppc970_cache_events,
 };
+
+static int init_ppc970_pmu(void)
+{
+	if (!cur_cpu_spec->oprofile_cpu_type ||
+	    (strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/970")
+	     && strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/970MP")))
+		return -ENODEV;
+
+	return register_power_pmu(&ppc970_pmu);
+}
+
+arch_initcall(init_ppc970_pmu);
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 3e7135bbe40..892a9f2e6d7 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -528,7 +528,7 @@ void show_regs(struct pt_regs * regs)
 
 	for (i = 0;  i < 32;  i++) {
 		if ((i % REGS_PER_LINE) == 0)
-			printk("\n" KERN_INFO "GPR%02d: ", i);
+			printk("\nGPR%02d: ", i);
 		printk(REG " ", regs->gpr[i]);
 		if (i == LAST_VOLATILE && !FULL_REGS(regs))
 			break;
diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index ef6f64950e9..a538824616f 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -1947,8 +1947,47 @@ static void __init fixup_device_tree_maple(void)
 	prom_setprop(isa, name, "ranges",
 			isa_ranges, sizeof(isa_ranges));
 }
+
+#define CPC925_MC_START		0xf8000000
+#define CPC925_MC_LENGTH	0x1000000
+/* The values for memory-controller don't have right number of cells */
+static void __init fixup_device_tree_maple_memory_controller(void)
+{
+	phandle mc;
+	u32 mc_reg[4];
+	char *name = "/hostbridge@f8000000";
+	struct prom_t *_prom = &RELOC(prom);
+	u32 ac, sc;
+
+	mc = call_prom("finddevice", 1, 1, ADDR(name));
+	if (!PHANDLE_VALID(mc))
+		return;
+
+	if (prom_getproplen(mc, "reg") != 8)
+		return;
+
+	prom_getprop(_prom->root, "#address-cells", &ac, sizeof(ac));
+	prom_getprop(_prom->root, "#size-cells", &sc, sizeof(sc));
+	if ((ac != 2) || (sc != 2))
+		return;
+
+	if (prom_getprop(mc, "reg", mc_reg, sizeof(mc_reg)) == PROM_ERROR)
+		return;
+
+	if (mc_reg[0] != CPC925_MC_START || mc_reg[1] != CPC925_MC_LENGTH)
+		return;
+
+	prom_printf("Fixing up bogus hostbridge on Maple...\n");
+
+	mc_reg[0] = 0x0;
+	mc_reg[1] = CPC925_MC_START;
+	mc_reg[2] = 0x0;
+	mc_reg[3] = CPC925_MC_LENGTH;
+	prom_setprop(mc, name, "reg", mc_reg, sizeof(mc_reg));
+}
 #else
 #define fixup_device_tree_maple()
+#define fixup_device_tree_maple_memory_controller()
 #endif
 
 #ifdef CONFIG_PPC_CHRP
@@ -2189,6 +2228,7 @@ static void __init fixup_device_tree_efika(void)
 static void __init fixup_device_tree(void)
 {
 	fixup_device_tree_maple();
+	fixup_device_tree_maple_memory_controller();
 	fixup_device_tree_chrp();
 	fixup_device_tree_pmac();
 	fixup_device_tree_efika();
diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c
index 9fa2c7dcd05..ef149880c14 100644
--- a/arch/powerpc/kernel/ptrace.c
+++ b/arch/powerpc/kernel/ptrace.c
@@ -736,15 +736,16 @@ void user_disable_single_step(struct task_struct *task)
 {
 	struct pt_regs *regs = task->thread.regs;
 
-
-#if defined(CONFIG_BOOKE)
-	/* If DAC then do not single step, skip */
-	if (task->thread.dabr)
-		return;
-#endif
-
 	if (regs != NULL) {
-#if defined(CONFIG_40x) || defined(CONFIG_BOOKE)
+#if defined(CONFIG_BOOKE)
+		/* If DAC don't clear DBCRO_IDM or MSR_DE */
+		if (task->thread.dabr)
+			task->thread.dbcr0 &= ~(DBCR0_IC | DBCR0_BT);
+		else {
+			task->thread.dbcr0 &= ~(DBCR0_IC | DBCR0_BT | DBCR0_IDM);
+			regs->msr &= ~MSR_DE;
+		}
+#elif defined(CONFIG_40x)
 		task->thread.dbcr0 &= ~(DBCR0_IC | DBCR0_BT | DBCR0_IDM);
 		regs->msr &= ~MSR_DE;
 #else
diff --git a/arch/powerpc/kernel/ptrace32.c b/arch/powerpc/kernel/ptrace32.c
index 297632cba04..8a6daf4129f 100644
--- a/arch/powerpc/kernel/ptrace32.c
+++ b/arch/powerpc/kernel/ptrace32.c
@@ -21,7 +21,6 @@
 #include <linux/sched.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
-#include <linux/smp_lock.h>
 #include <linux/errno.h>
 #include <linux/ptrace.h>
 #include <linux/regset.h>
diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c
index ee4c7609b64..c434823b8c8 100644
--- a/arch/powerpc/kernel/rtas.c
+++ b/arch/powerpc/kernel/rtas.c
@@ -38,9 +38,10 @@
 #include <asm/syscalls.h>
 #include <asm/smp.h>
 #include <asm/atomic.h>
+#include <asm/time.h>
 
 struct rtas_t rtas = {
-	.lock = SPIN_LOCK_UNLOCKED
+	.lock = __RAW_SPIN_LOCK_UNLOCKED
 };
 EXPORT_SYMBOL(rtas);
 
@@ -67,6 +68,28 @@ unsigned long rtas_rmo_buf;
 void (*rtas_flash_term_hook)(int);
 EXPORT_SYMBOL(rtas_flash_term_hook);
 
+/* RTAS use home made raw locking instead of spin_lock_irqsave
+ * because those can be called from within really nasty contexts
+ * such as having the timebase stopped which would lockup with
+ * normal locks and spinlock debugging enabled
+ */
+static unsigned long lock_rtas(void)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	preempt_disable();
+	__raw_spin_lock_flags(&rtas.lock, flags);
+	return flags;
+}
+
+static void unlock_rtas(unsigned long flags)
+{
+	__raw_spin_unlock(&rtas.lock);
+	local_irq_restore(flags);
+	preempt_enable();
+}
+
 /*
  * call_rtas_display_status and call_rtas_display_status_delay
  * are designed only for very early low-level debugging, which
@@ -79,7 +102,7 @@ static void call_rtas_display_status(char c)
 
 	if (!rtas.base)
 		return;
-	spin_lock_irqsave(&rtas.lock, s);
+	s = lock_rtas();
 
 	args->token = 10;
 	args->nargs = 1;
@@ -89,7 +112,7 @@ static void call_rtas_display_status(char c)
 
 	enter_rtas(__pa(args));
 
-	spin_unlock_irqrestore(&rtas.lock, s);
+	unlock_rtas(s);
 }
 
 static void call_rtas_display_status_delay(char c)
@@ -411,8 +434,7 @@ int rtas_call(int token, int nargs, int nret, int *outputs, ...)
 	if (!rtas.entry || token == RTAS_UNKNOWN_SERVICE)
 		return -1;
 
-	/* Gotta do something different here, use global lock for now... */
-	spin_lock_irqsave(&rtas.lock, s);
+	s = lock_rtas();
 	rtas_args = &rtas.args;
 
 	rtas_args->token = token;
@@ -439,8 +461,7 @@ int rtas_call(int token, int nargs, int nret, int *outputs, ...)
 			outputs[i] = rtas_args->rets[i+1];
 	ret = (nret > 0)? rtas_args->rets[0]: 0;
 
-	/* Gotta do something different here, use global lock for now... */
-	spin_unlock_irqrestore(&rtas.lock, s);
+	unlock_rtas(s);
 
 	if (buff_copy) {
 		log_error(buff_copy, ERR_TYPE_RTAS_LOG, 0);
@@ -837,7 +858,7 @@ asmlinkage int ppc_rtas(struct rtas_args __user *uargs)
 
 	buff_copy = get_errorlog_buffer();
 
-	spin_lock_irqsave(&rtas.lock, flags);
+	flags = lock_rtas();
 
 	rtas.args = args;
 	enter_rtas(__pa(&rtas.args));
@@ -848,7 +869,7 @@ asmlinkage int ppc_rtas(struct rtas_args __user *uargs)
 	if (args.rets[0] == -1)
 		errbuf = __fetch_rtas_last_error(buff_copy);
 
-	spin_unlock_irqrestore(&rtas.lock, flags);
+	unlock_rtas(flags);
 
 	if (buff_copy) {
 		if (errbuf)
@@ -951,3 +972,33 @@ int __init early_init_dt_scan_rtas(unsigned long node,
 	/* break now */
 	return 1;
 }
+
+static raw_spinlock_t timebase_lock;
+static u64 timebase = 0;
+
+void __cpuinit rtas_give_timebase(void)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	hard_irq_disable();
+	__raw_spin_lock(&timebase_lock);
+	rtas_call(rtas_token("freeze-time-base"), 0, 1, NULL);
+	timebase = get_tb();
+	__raw_spin_unlock(&timebase_lock);
+
+	while (timebase)
+		barrier();
+	rtas_call(rtas_token("thaw-time-base"), 0, 1, NULL);
+	local_irq_restore(flags);
+}
+
+void __cpuinit rtas_take_timebase(void)
+{
+	while (!timebase)
+		barrier();
+	__raw_spin_lock(&timebase_lock);
+	set_tb(timebase >> 32, timebase & 0xffffffff);
+	timebase = 0;
+	__raw_spin_unlock(&timebase_lock);
+}
diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c
index 1d154248cf4..e1e3059cf34 100644
--- a/arch/powerpc/kernel/setup_32.c
+++ b/arch/powerpc/kernel/setup_32.c
@@ -119,6 +119,8 @@ notrace unsigned long __init early_init(unsigned long dt_ptr)
  */
 notrace void __init machine_init(unsigned long dt_ptr)
 {
+	lockdep_init();
+
 	/* Enable early debugging if any specified (see udbg.h) */
 	udbg_early_init();
 
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 65484b2200b..0b47de07302 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -68,7 +68,8 @@ EXPORT_PER_CPU_SYMBOL(cpu_core_map);
 /* SMP operations for this machine */
 struct smp_ops_t *smp_ops;
 
-static volatile unsigned int cpu_callin_map[NR_CPUS];
+/* Can't be static due to PowerMac hackery */
+volatile unsigned int cpu_callin_map[NR_CPUS];
 
 int smt_enabled_at_boot = 1;
 
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 15391c2ab01..eae4511ceea 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -53,6 +53,7 @@
 #include <linux/posix-timers.h>
 #include <linux/irq.h>
 #include <linux/delay.h>
+#include <linux/perf_counter.h>
 
 #include <asm/io.h>
 #include <asm/processor.h>
@@ -525,6 +526,26 @@ void __init iSeries_time_init_early(void)
 }
 #endif /* CONFIG_PPC_ISERIES */
 
+#if defined(CONFIG_PERF_COUNTERS) && defined(CONFIG_PPC32)
+DEFINE_PER_CPU(u8, perf_counter_pending);
+
+void set_perf_counter_pending(void)
+{
+	get_cpu_var(perf_counter_pending) = 1;
+	set_dec(1);
+	put_cpu_var(perf_counter_pending);
+}
+
+#define test_perf_counter_pending()	__get_cpu_var(perf_counter_pending)
+#define clear_perf_counter_pending()	__get_cpu_var(perf_counter_pending) = 0
+
+#else  /* CONFIG_PERF_COUNTERS && CONFIG_PPC32 */
+
+#define test_perf_counter_pending()	0
+#define clear_perf_counter_pending()
+
+#endif /* CONFIG_PERF_COUNTERS && CONFIG_PPC32 */
+
 /*
  * For iSeries shared processors, we have to let the hypervisor
  * set the hardware decrementer.  We set a virtual decrementer
@@ -551,6 +572,10 @@ void timer_interrupt(struct pt_regs * regs)
 	set_dec(DECREMENTER_MAX);
 
 #ifdef CONFIG_PPC32
+	if (test_perf_counter_pending()) {
+		clear_perf_counter_pending();
+		perf_counter_do_pending();
+	}
 	if (atomic_read(&ppc_n_lost_interrupts) != 0)
 		do_IRQ(regs);
 #endif
diff --git a/arch/powerpc/kernel/udbg_16550.c b/arch/powerpc/kernel/udbg_16550.c
index 0362a891e54..acb74a17bbb 100644
--- a/arch/powerpc/kernel/udbg_16550.c
+++ b/arch/powerpc/kernel/udbg_16550.c
@@ -219,7 +219,7 @@ void udbg_init_pas_realmode(void)
 #ifdef CONFIG_PPC_EARLY_DEBUG_44x
 #include <platforms/44x/44x.h>
 
-static int udbg_44x_as1_flush(void)
+static void udbg_44x_as1_flush(void)
 {
 	if (udbg_comport) {
 		while ((as1_readb(&udbg_comport->lsr) & LSR_THRE) == 0)
diff --git a/arch/powerpc/kernel/vector.S b/arch/powerpc/kernel/vector.S
index ef36cbbc588..ea4d64644d0 100644
--- a/arch/powerpc/kernel/vector.S
+++ b/arch/powerpc/kernel/vector.S
@@ -80,10 +80,10 @@ _GLOBAL(load_up_altivec)
 	mtvscr	vr0
 	REST_32VRS(0,r4,r5)
 #ifndef CONFIG_SMP
-	/* Update last_task_used_math to 'current' */
+	/* Update last_task_used_altivec to 'current' */
 	subi	r4,r5,THREAD		/* Back to 'current' */
 	fromreal(r4)
-	PPC_STL	r4,ADDROFF(last_task_used_math)(r3)
+	PPC_STL	r4,ADDROFF(last_task_used_altivec)(r3)
 #endif /* CONFIG_SMP */
 	/* restore registers and return */
 	blr
@@ -172,7 +172,7 @@ _GLOBAL(load_up_vsx)
 	oris	r12,r12,MSR_VSX@h
 	std	r12,_MSR(r1)
 #ifndef CONFIG_SMP
-	/* Update last_task_used_math to 'current' */
+	/* Update last_task_used_vsx to 'current' */
 	ld	r4,PACACURRENT(r13)
 	std	r4,0(r3)
 #endif /* CONFIG_SMP */
author	Ingo Molnar <mingo@elte.hu>	2009-09-07 08:19:51 +0200
committer	Ingo Molnar <mingo@elte.hu>	2009-09-07 08:19:51 +0200
commit	a1922ed661ab2c1637d0b10cde933bd9cd33d965 (patch)
tree	0f1777542b385ebefd30b3586d830fd8ed6fda5b /arch/powerpc/kernel
parent	75e33751ca8bbb72dd6f1a74d2810ddc8cbe4bdf (diff)
parent	d28daf923ac5e4a0d7cecebae56f3e339189366b (diff)