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()
  ...

10 files changed, 885 insertions, 300 deletions

diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index 6a4fb29a061..b73396b9390 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 00000000000..75ff47fed7b
--- /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 bb202388170..809fdf94b95 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 07bd308a5fa..db90b0c5c27 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_di