Merge branch 'perfcounters-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'perfcounters-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (49 commits)
  perfcounter: Handle some IO return values
  perf_counter: Push perf_sample_data through the swcounter code
  perf_counter tools: Define and use our own u64, s64 etc. definitions
  perf_counter: Close race in perf_lock_task_context()
  perf_counter, x86: Improve interactions with fast-gup
  perf_counter: Simplify and fix task migration counting
  perf_counter tools: Add a data file header
  perf_counter: Update userspace callchain sampling uses
  perf_counter: Make callchain samples extensible
  perf report: Filter to parent set by default
  perf_counter tools: Handle lost events
  perf_counter: Add event overlow handling
  fs: Provide empty .set_page_dirty() aop for anon inodes
  perf_counter: tools: Makefile tweaks for 64-bit powerpc
  perf_counter: powerpc: Add processor back-end for MPC7450 family
  perf_counter: powerpc: Make powerpc perf_counter code safe for 32-bit kernels
  perf_counter: powerpc: Change how processor-specific back-ends get selected
  perf_counter: powerpc: Use unsigned long for register and constraint values
  perf_counter: powerpc: Enable use of software counters on 32-bit powerpc
  perf_counter tools: Add and use isprint()
  ...

19 files changed, 1075 insertions, 397 deletions

diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 9fb344d5a86a..bf6cedfa05db 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -126,6 +126,7 @@ config PPC
 	select HAVE_OPROFILE
 	select HAVE_SYSCALL_WRAPPERS if PPC64
 	select GENERIC_ATOMIC64 if PPC32
+	select HAVE_PERF_COUNTERS
 
 config EARLY_PRINTK
 	bool
diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h
index b7f8f4a87cc0..867ab8ed69b3 100644
--- a/arch/powerpc/include/asm/hw_irq.h
+++ b/arch/powerpc/include/asm/hw_irq.h
@@ -131,6 +131,8 @@ static inline int irqs_disabled_flags(unsigned long flags)
 struct irq_chip;
 
 #ifdef CONFIG_PERF_COUNTERS
+
+#ifdef CONFIG_PPC64
 static inline unsigned long test_perf_counter_pending(void)
 {
 	unsigned long x;
@@ -154,15 +156,15 @@ static inline void clear_perf_counter_pending(void)
 		"r" (0),
 		"i" (offsetof(struct paca_struct, perf_counter_pending)));
 }
+#endif /* CONFIG_PPC64 */
 
-#else
+#else  /* CONFIG_PERF_COUNTERS */
 
 static inline unsigned long test_perf_counter_pending(void)
 {
 	return 0;
 }
 
-static inline void set_perf_counter_pending(void) {}
 static inline void clear_perf_counter_pending(void) {}
 #endif /* CONFIG_PERF_COUNTERS */
 
diff --git a/arch/powerpc/include/asm/perf_counter.h b/arch/powerpc/include/asm/perf_counter.h
index cc7c887705b8..8ccd4e155768 100644
--- a/arch/powerpc/include/asm/perf_counter.h
+++ b/arch/powerpc/include/asm/perf_counter.h
@@ -10,6 +10,8 @@
  */
 #include <linux/types.h>
 
+#include <asm/hw_irq.h>
+
 #define MAX_HWCOUNTERS		8
 #define MAX_EVENT_ALTERNATIVES	8
 #define MAX_LIMITED_HWCOUNTERS	2
@@ -19,27 +21,27 @@
  * describe the PMU on a particular POWER-family CPU.
  */
 struct power_pmu {
-	int	n_counter;
-	int	max_alternatives;
-	u64	add_fields;
-	u64	test_adder;
-	int	(*compute_mmcr)(u64 events[], int n_ev,
-				unsigned int hwc[], u64 mmcr[]);
-	int	(*get_constraint)(u64 event, u64 *mskp, u64 *valp);
-	int	(*get_alternatives)(u64 event, unsigned int flags,
-				    u64 alt[]);
-	void	(*disable_pmc)(unsigned int pmc, u64 mmcr[]);
-	int	(*limited_pmc_event)(u64 event);
-	u32	flags;
-	int	n_generic;
-	int	*generic_events;
-	int	(*cache_events)[PERF_COUNT_HW_CACHE_MAX]
+	const char	*name;
+	int		n_counter;
+	int		max_alternatives;
+	unsigned long	add_fields;
+	unsigned long	test_adder;
+	int		(*compute_mmcr)(u64 events[], int n_ev,
+				unsigned int hwc[], unsigned long mmcr[]);
+	int		(*get_constraint)(u64 event, unsigned long *mskp,
+				unsigned long *valp);
+	int		(*get_alternatives)(u64 event, unsigned int flags,
+				u64 alt[]);
+	void		(*disable_pmc)(unsigned int pmc, unsigned long mmcr[]);
+	int		(*limited_pmc_event)(u64 event);
+	u32		flags;
+	int		n_generic;
+	int		*generic_events;
+	int		(*cache_events)[PERF_COUNT_HW_CACHE_MAX]
 			       [PERF_COUNT_HW_CACHE_OP_MAX]
 			       [PERF_COUNT_HW_CACHE_RESULT_MAX];
 };
 
-extern struct power_pmu *ppmu;
-
 /*
  * Values for power_pmu.flags
  */
@@ -53,15 +55,23 @@ extern struct power_pmu *ppmu;
 #define PPMU_LIMITED_PMC_REQD	2	/* have to put this on a limited PMC */
 #define PPMU_ONLY_COUNT_RUN	4	/* only counting in run state */
 
+extern int register_power_pmu(struct power_pmu *);
+
 struct pt_regs;
 extern unsigned long perf_misc_flags(struct pt_regs *regs);
-#define perf_misc_flags(regs)	perf_misc_flags(regs)
-
 extern unsigned long perf_instruction_pointer(struct pt_regs *regs);
 
 /*
- * The power_pmu.get_constraint function returns a 64-bit value and
- * a 64-bit mask that express the constraints between this event and
+ * Only override the default definitions in include/linux/perf_counter.h
+ * if we have hardware PMU support.
+ */
+#ifdef CONFIG_PPC_PERF_CTRS
+#define perf_misc_flags(regs)	perf_misc_flags(regs)
+#endif
+
+/*
+ * The power_pmu.get_constraint function returns a 32/64-bit value and
+ * a 32/64-bit mask that express the constraints between this event and
  * other events.
  *
  * The value and mask are divided up into (non-overlapping) bitfields
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index 6a4fb29a0618..b73396b93905 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -97,9 +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
 
@@ -108,6 +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/mpc7450-pmu.c b/arch/powerpc/kernel/mpc7450-pmu.c
new file mode 100644
index 000000000000..75ff47fed7bf
--- /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 <linux/string.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 (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/perf_counter.c b/arch/powerpc/kernel/perf_counter.c
index bb202388170e..809fdf94b95f 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 +516,12 @@ 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;
 
 	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;
 
@@ -479,7 +590,7 @@ 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 +623,7 @@ 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))
@@ -913,6 +1024,8 @@ 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 +1120,12 @@ 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 +1145,8 @@ 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 +1159,9 @@ 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 +1187,12 @@ 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 +1201,12 @@ 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 +1218,7 @@ 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 +1226,9 @@ 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
@@ -1214,50 +1285,22 @@ void hw_perf_counter_setup(int cpu)
 	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 07bd308a5fa7..db90b0c5c27b 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 +589,27 @@ 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 (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 41e5d2d958d4..f4adca8e98a4 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 +659,30 @@ 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 (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 05600b66221a..29b2c6c0e83a 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 +601,27 @@ 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 (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 46f74bebcfd9..09ae5bf5bda7 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 +518,29 @@ 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 (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 b72e7a19d054..5d755ef7ac8f 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[] = {
@@ -342,16 +348,27 @@ 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,
+	.n_generic		= ARRAY_SIZE(power7_generic_events),
+	.generic_events		= power7_generic_events,
+	.cache_events		= &power7_cache_events,
 };
+
+static int init_power7_pmu(void)
+{
+	if (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 ba0a357a89f4..6637c87fe70e 100644
--- a/arch/powerpc/kernel/ppc970-pmu.c
+++ b/arch/powerpc/kernel/ppc970-pmu.c
@@ -10,7 +10,9 @@
  */
 #include <linux/string.h>
 #include <linux/perf_counter.h>
+#include <linux/string.h>
 #include <asm/reg.h>
+#include <asm/cputable.h>
 
 /*
  * Bits in event code for PPC970
@@ -183,7 +185,7 @@ 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 +194,11 @@ 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 +225,7 @@ 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 +239,7 @@ 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 +260,9 @@ 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 +323,7 @@ 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 +343,8 @@ 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 +390,8 @@ 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 +406,7 @@ 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 +472,28 @@ 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 (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/time.c b/arch/powerpc/kernel/time.c
index 15391c2ab013..eae4511ceeac 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/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype
index c4192542b809..61187bec7506 100644
--- a/arch/powerpc/platforms/Kconfig.cputype
+++ b/arch/powerpc/platforms/Kconfig.cputype
@@ -1,7 +1,7 @@
 config PPC64
 	bool "64-bit kernel"
 	default n
-	select HAVE_PERF_COUNTERS
+	select PPC_HAVE_PMU_SUPPORT
 	help
 	  This option selects whether a 32-bit or a 64-bit kernel
 	  will be built.
@@ -78,6 +78,7 @@ config POWER4_ONLY
 config 6xx
 	def_bool y
 	depends on PPC32 && PPC_BOOK3S
+	select PPC_HAVE_PMU_SUPPORT
 
 config POWER3
 	bool
@@ -246,6 +247,15 @@ config VIRT_CPU_ACCOUNTING
 
 	  If in doubt, say Y here.
 
+config PPC_HAVE_PMU_SUPPORT
+       bool
+
+config PPC_PERF_CTRS
+       def_bool y
+       depends on PERF_COUNTERS && PPC_HAVE_PMU_SUPPORT
+       help
+         This enables the powerpc-specific perf_counter back-end.
+
 config SMP
 	depends on PPC_STD_MMU || FSL_BOOKE
 	bool "Symmetric multi-processing support"
diff --git a/arch/x86/include/asm/perf_counter.h b/arch/x86/include/asm/perf_counter.h
index 876ed97147b3..5fb33e160ea0 100644
--- a/arch/x86/include/asm/perf_counter.h
+++ b/arch/x86/include/asm/perf_counter.h
@@ -84,11 +84,6 @@ union cpuid10_edx {
 #define MSR_ARCH_PERFMON_FIXED_CTR2			0x30b
 #define X86_PMC_IDX_FIXED_BUS_CYCLES			(X86_PMC_IDX_FIXED + 2)
 
-extern void set_perf_counter_pending(void);
-
-#define clear_perf_counter_pending()	do { } while (0)
-#define test_perf_counter_pending()	(0)
-
 #ifdef CONFIG_PERF_COUNTERS
 extern void init_hw_perf_counters(void);
 extern void perf_counters_lapic_init(void);
diff --git a/arch/x86/include/asm/pgtable_32.h b/arch/x86/include/asm/pgtable_32.h
index 31bd120cf2a2..01fd9461d323 100644
--- a/arch/x86/include/asm/pgtable_32.h
+++ b/arch/x86/include/asm/pgtable_32.h
@@ -49,13 +49,17 @@ extern void set_pmd_pfn(unsigned long, unsigned long, pgprot_t);
 #endif
 
 #if defined(CONFIG_HIGHPTE)
+#define __KM_PTE			\
+	(in_nmi() ? KM_NMI_PTE : 	\
+	 in_irq() ? KM_IRQ_PTE :	\
+	 KM_PTE0)
 #define pte_offset_map(dir, address)					\
-	((pte_t *)kmap_atomic_pte(pmd_page(*(dir)), KM_PTE0) +		\
+	((pte_t *)kmap_atomic_pte(pmd_page(*(dir)), __KM_PTE) +		\
 	 pte_index((address)))
 #define pte_offset_map_nested(dir, address)				\
 	((pte_t *)kmap_atomic_pte(pmd_page(*(dir)), KM_PTE1) +		\
 	 pte_index((address)))
-#define pte_unmap(pte) kunmap_atomic((pte), KM_PTE0)
+#define pte_unmap(pte) kunmap_atomic((pte), __KM_PTE)
 #define pte_unmap_nested(pte) kunmap_atomic((pte), KM_PTE1)
 #else
 #define pte_offset_map(dir, address)					\
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index b685ece89d5c..512ee87062c2 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -25,7 +25,12 @@
 #define MAKE_MM_SEG(s)	((mm_segment_t) { (s) })
 
 #define KERNEL_DS	MAKE_MM_SEG(-1UL)
-#define USER_DS		MAKE_MM_SEG(PAGE_OFFSET)
+
+#ifdef CONFIG_X86_32
+# define USER_DS	MAKE_MM_SEG(PAGE_OFFSET)
+#else
+# define USER_DS	MAKE_MM_SEG(__VIRTUAL_MASK)
+#endif
 
 #define get_ds()	(KERNEL_DS)
 #define get_fs()	(current_thread_info()->addr_limit)
diff --git a/arch/x86/kernel/cpu/perf_counter.c b/arch/x86/kernel/cpu/perf_counter.c
index 275bc142cd5d..76dfef23f789 100644
--- a/arch/x86/kernel/cpu/perf_counter.c
+++ b/arch/x86/kernel/cpu/perf_counter.c
@@ -19,6 +19,7 @@
 #include <linux/kdebug.h>
 #include <linux/sched.h>
 #include <linux/uaccess.h>
+#include <linux/highmem.h>
 
 #include <asm/apic.h>
 #include <asm/stacktrace.h>
@@ -389,23 +390,23 @@ static u64 intel_pmu_raw_event(u64 event)
 	return event & CORE_EVNTSEL_MASK;
 }
 
-static const u64 amd_0f_hw_cache_event_ids
+static const u64 amd_hw_cache_event_ids
 				[PERF_COUNT_HW_CACHE_MAX]
 				[PERF_COUNT_HW_CACHE_OP_MAX]
 				[PERF_COUNT_HW_CACHE_RESULT_MAX] =
 {
  [ C(L1D) ] = {
 	[ C(OP_READ) ] = {
-		[ C(RESULT_ACCESS) ] = 0,
-		[ C(RESULT_MISS)   ] = 0,
+		[ C(RESULT_ACCESS) ] = 0x0040, /* Data Cache Accesses        */
+		[ C(RESULT_MISS)   ] = 0x0041, /* Data Cache Misses          */
 	},
 	[ C(OP_WRITE) ] = {
-		[ C(RESULT_ACCESS) ] = 0,
+		[ C(RESULT_ACCESS) ] = 0x0042, /* Data Cache Refills from L2 */
 		[ C(RESULT_MISS)   ] = 0,
 	},
 	[ C(OP_PREFETCH) ] = {
-		[ C(RESULT_ACCESS) ] = 0,
-		[ C(RESULT_MISS)   ] = 0,
+		[ C(RESULT_ACCESS) ] = 0x0267, /* Data Prefetcher :attempts  */
+		[ C(RESULT_MISS)   ] = 0x0167, /* Data Prefetcher :cancelled */
 	},
  },
  [ C(L1I ) ] = {
@@ -418,17 +419,17 @@ static const u64 amd_0f_hw_cache_event_ids
 		[ C(RESULT_MISS)   ] = -1,
 	},
 	[ C(OP_PREFETCH) ] = {
-		[ C(RESULT_ACCESS) ] = 0,
+		[ C(RESULT_ACCESS) ] = 0x014B, /* Prefetch Instructions :Load */
 		[ C(RESULT_MISS)   ] = 0,
 	},
  },
  [ C(LL  ) ] = {
 	[ C(OP_READ) ] = {
-		[ C(RESULT_ACCESS) ] = 0,
-		[ C(RESULT_MISS)   ] = 0,
+		[ C(RESULT_ACCESS) ] = 0x037D, /* Requests to L2 Cache :IC+DC */
+		[ C(RESULT_MISS)   ] = 0x037E, /* L2 Cache Misses : IC+DC     */
 	},
 	[ C(OP_WRITE) ] = {
-		[ C(RESULT_ACCESS) ] = 0,
+		[ C(RESULT_ACCESS) ] = 0x017F, /* L2 Fill/Writeback           */
 		[ C(RESULT_MISS)   ] = 0,
 	},
 	[ C(OP_PREFETCH) ] = {
@@ -438,8 +439,8 @@ static const u64 amd_0f_hw_cache_event_ids
  },
  [ C(DTLB) ] = {
 	[ C(OP_READ) ] = {
-		[ C(RESULT_ACCESS) ] = 0,
-		[ C(RESULT_MISS)   ] = 0,
+		[ C(RESULT_ACCESS) ] = 0x0040, /* Data Cache Accesses        */
+		[ C(RESULT_MISS)   ] = 0x0046, /* L1 DTLB and L2 DLTB Miss   */
 	},
 	[ C(OP_WRITE) ] = {
 		[ C(RESULT_ACCESS) ] = 0,
@@ -1223,6 +1224,8 @@ again:
 		if (!intel_pmu_save_and_restart(counter))
 			continue;
 
+		data.period = counter->hw.last_period;
+
 		if (perf_counter_overflow(counter, 1, &data))
 			intel_pmu_disable_counter(&counter->hw, bit);
 	}
@@ -1459,18 +1462,16 @@ static int intel_pmu_init(void)
 
 static int amd_pmu_init(void)
 {
+	/* Performance-monitoring supported from K7 and later: */
+	if (boot_cpu_data.x86 < 6)
+		return -ENODEV;
+
 	x86_pmu = amd_pmu;
 
-	switch (boot_cpu_data.x86) {
-	case 0x0f:
-	case 0x10:
-	case 0x11:
-		memcpy(hw_cache_event_ids, amd_0f_hw_cache_event_ids,
-		       sizeof(hw_cache_event_ids));
+	/* Events are common for all AMDs */
+	memcpy(hw_cache_event_ids, amd_hw_cache_event_ids,
+	       sizeof(hw_cache_event_ids));
 
-		pr_cont("AMD Family 0f/10/11 events, ");
-		break;
-	}
 	return 0;
 }
 
@@ -1554,9 +1555,9 @@ const struct pmu *hw_perf_counter_init(struct perf_counter *counter)
  */
 
 static inline
-void callchain_store(struct perf_callchain_entry *entry, unsigned long ip)
+void callchain_store(struct perf_callchain_entry *entry, u64 ip)
 {
-	if (entry->nr < MAX_STACK_DEPTH)
+	if (entry->nr < PERF_MAX_STACK_DEPTH)
 		entry->ip[entry->nr++] = ip;
 }
 
@@ -1577,8 +1578,8 @@ static void backtrace_warning(void *data, char *msg)
 
 static int backtrace_stack(void *data, char *name)
 {
-	/* Don't bother with IRQ stacks for now */
-	return -1;
+	/* Process all stacks: */
+	return 0;
 }
 
 static void backtrace_address(void *data, unsigned long addr, int reliable)
@@ -1596,47 +1597,59 @@ static const struct stacktrace_ops backtrace_ops = {
 	.address		= backtrace_address,
 };
 
+#include "../dumpstack.h"
+
 static void
 perf_callchain_kernel(struct pt_regs *regs, struct perf_callchain_entry *entry)
 {
-	unsigned long bp;
-	char *stack;
-	int nr = entry->nr;
+	callchain_store(entry, PERF_CONTEXT_KERNEL);
+	callchain_store(entry, regs->ip);
 
-	callchain_store(entry, instruction_pointer(regs));
+	dump_trace(NULL, regs, NULL, 0, &backtrace_ops, entry);
+}
 
-	stack = ((char *)regs + sizeof(struct pt_regs));
-#ifdef CONFIG_FRAME_POINTER
-	bp = frame_pointer(regs);
-#else
-	bp = 0;
-#endif
+/*
+ * best effort, GUP based copy_from_user() that assumes IRQ or NMI context
+ */
+static unsigned long
+copy_from_user_nmi(void *to, const void __user *from, unsigned long n)
+{
+	unsigned long offset, addr = (unsigned long)from;
+	int type = in_nmi() ? KM_NMI : KM_IRQ0;
+	unsigned long size, len = 0;
+	struct page *page;
+	void *map;
+	int ret;
 
-	dump_trace(NULL, regs, (void *)stack, bp, &backtrace_ops, entry);
+	do {
+		ret = __get_user_pages_fast(addr, 1, 0, &page);
+		if (!ret)
+			break;
 
-	entry->kernel = entry->nr - nr;
-}
+		offset = addr & (PAGE_SIZE - 1);
+		size = min(PAGE_SIZE - offset, n - len);
 
+		map = kmap_atomic(page, type);
+		memcpy(to, map+offset, size);
+		kunmap_atomic(map, type);
+		put_page(page);
 
-struct stack_frame {
-	const void __user	*next_fp;
-	unsigned long		return_address;
-};
+		len  += size;
+		to   += size;
+		addr += size;
+
+	} while (len < n);
+
+	return len;
+}
 
 static int copy_stack_frame(const void __user *fp, struct stack_frame *frame)
 {
-	int ret;
+	unsigned long bytes;
 
-	if (!access_ok(VERIFY_READ, fp, sizeof(*frame)))
-		return 0;
+	bytes = copy_from_user_nmi(frame, fp, sizeof(*frame));
 
-	ret = 1;
-	pagefault_disable();
-	if (__copy_from_user_inatomic(frame, fp, sizeof(*frame)))
-		ret = 0;
-	pagefault_enable();
-
-	return ret;
+	return bytes == sizeof(*frame);
 }
 
 static void
@@ -1644,28 +1657,28 @@ perf_callchain_user(struct pt_regs *regs, struct perf_callchain_entry *entry)
 {
 	struct stack_frame frame;
 	const void __user *fp;
-	int nr = entry->nr;
 
-	regs = (struct pt_regs *)current->thread.sp0 - 1;
-	fp   = (void __user *)regs->bp;
+	if (!user_mode(regs))
+		regs = task_pt_regs(current);
 
+	fp = (void __user *)regs->bp;
+
+	callchain_store(entry, PERF_CONTEXT_USER);
 	callchain_store(entry, regs->ip);
 
-	while (entry->nr < MAX_STACK_DEPTH) {
-		frame.next_fp	     = NULL;
+	while (entry->nr < PERF_MAX_STACK_DEPTH) {
+		frame.next_frame	     = NULL;
 		frame.return_address = 0;
 
 		if (!copy_stack_frame(fp, &frame))
 			break;
 
-		if ((unsigned long)fp < user_stack_pointer(regs))
+		if ((unsigned long)fp < regs->sp)
 			break;
 
 		callchain_store(entry, frame.return_address);
-		fp = frame.next_fp;
+		fp = frame.next_frame;
 	}
-
-	entry->user = entry->nr - nr;
 }
 
 static void
@@ -1701,9 +1714,6 @@ struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
 		entry = &__get_cpu_var(irq_entry);
 
 	entry->nr = 0;
-	entry->hv = 0;
-	entry->kernel = 0;
-	entry->user = 0;
 
 	perf_do_callchain(regs, entry);
 
diff --git a/arch/x86/mm/gup.c b/arch/x86/mm/gup.c
index f97480941269..71da1bca13cb 100644
--- a/arch/x86/mm/gup.c
+++ b/arch/x86/mm/gup.c
@@ -14,7 +14,7 @@
 static inline pte_t gup_get_pte(pte_t *ptep)
 {
 #ifndef CONFIG_X86_PAE
-	return *ptep;
+	return ACCESS_ONCE(*ptep);
 #else
 	/*
 	 * With get_user_pages_fast, we walk down the pagetables without taking
@@ -219,6 +219,62 @@ static int gup_pud_range(pgd_t pgd, unsigned long addr, unsigned long end,
 	return 1;
 }
 
+/*
+ * Like get_user_pages_fast() except its IRQ-safe in that it won't fall
+ * back to the regular GUP.
+ */
+int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
+			  struct page **pages)
+{
+	struct mm_struct *mm = current->mm;
+	unsigned long addr, len, end;
+	unsigned long next;
+	unsigned long flags;
+	pgd_t *pgdp;
+	int nr = 0;
+
+	start &= PAGE_MASK;
+	addr = start;
+	len = (unsigned long) nr_pages << PAGE_SHIFT;
+	end = start + len;
+	if (unlikely(!access_ok(write ? VERIFY_WRITE : VERIFY_READ,
+					(void __user *)start, len)))
+		return 0;
+
+	/*
+	 * XXX: batch / limit 'nr', to avoid large irq off latency
+	 * needs some instrumenting to determine the common sizes used by
+	 * important workloads (eg. DB2), and whether limiting the batch size
+	 * will decrease performance.
+	 *
+	 * It seems like we're in the clear for the moment. Direct-IO is
+	 * the main guy that batches up lots of get_user_pages, and even
+	 * they are limited to 64-at-a-time which is not so many.
+	 */
+	/*
+	 * This doesn't prevent pagetable teardown, but does prevent
+	 * the pagetables and pages from being freed on x86.
+	 *
+	 * So long as we atomically load page table pointers versus teardown
+	 * (which we do on x86, with the above PAE exception), we can follow the
+	 * address down to the the page and take a ref on it.
+	 */
+	local_irq_save(flags);
+	pgdp = pgd_offset(mm, addr);
+	do {
+		pgd_t pgd = *pgdp;
+
+		next = pgd_addr_end(addr, end);
+		if (pgd_none(pgd))
+			break;
+		if (!gup_pud_range(pgd, addr, next, write, pages, &nr))
+			break;
+	} while (pgdp++, addr = next, addr != end);
+	local_irq_restore(flags);
+
+	return nr;
+}
+
 /**
  * get_user_pages_fast() - pin user pages in memory
  * @start:	starting user address