Merge branch 'perf' into devel

Conflicts:
	arch/arm/Kconfig

arch/arm/Kconfig

@@ -20,6 +20,8 @@ config ARM
 	select HAVE_GENERIC_DMA_COHERENT
 	select HAVE_KERNEL_GZIP
 	select HAVE_KERNEL_LZO
+	select HAVE_PERF_EVENTS
+	select PERF_USE_VMALLOC
 	help
 	  The ARM series is a line of low-power-consumption RISC chip designs
 	  licensed by ARM Ltd and targeted at embedded applications and
@@ -877,6 +879,11 @@ config XSCALE_PMU
 	depends on CPU_XSCALE && !XSCALE_PMU_TIMER
 	default y
 
+config CPU_HAS_PMU
+	depends on CPU_V6 || CPU_V7 || XSCALE_PMU
+	default y
+	bool
+
 if !MMU
 source "arch/arm/Kconfig-nommu"
 endif
@@ -1181,6 +1188,14 @@ config HIGHPTE
 	depends on HIGHMEM
 	depends on !OUTER_CACHE
 
+config HW_PERF_EVENTS
+	bool "Enable hardware performance counter support for perf events"
+	depends on PERF_EVENTS && CPU_HAS_PMU && (CPU_V6 || CPU_V7)
+	default y
+	help
+	  Enable hardware performance counter support for perf events. If
+	  disabled, perf events will use software events only.
+
 source "mm/Kconfig"
 
 config LEDS

arch/arm/include/asm/perf_event.h

@@ -0,0 +1,31 @@
+/*
+ *  linux/arch/arm/include/asm/perf_event.h
+ *
+ *  Copyright (C) 2009 picoChip Designs Ltd, Jamie Iles
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#ifndef __ARM_PERF_EVENT_H__
+#define __ARM_PERF_EVENT_H__
+
+/*
+ * NOP: on *most* (read: all supported) ARM platforms, the performance
+ * counter interrupts are regular interrupts and not an NMI. This
+ * means that when we receive the interrupt we can call
+ * perf_event_do_pending() that handles all of the work with
+ * interrupts enabled.
+ */
+static inline void
+set_perf_event_pending(void)
+{
+}
+
+/* ARM performance counters start from 1 (in the cp15 accesses) so use the
+ * same indexes here for consistency. */
+#define PERF_EVENT_INDEX_OFFSET 1
+
+#endif /* __ARM_PERF_EVENT_H__ */

arch/arm/include/asm/pmu.h

@@ -0,0 +1,75 @@
+/*
+ *  linux/arch/arm/include/asm/pmu.h
+ *
+ *  Copyright (C) 2009 picoChip Designs Ltd, Jamie Iles
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#ifndef __ARM_PMU_H__
+#define __ARM_PMU_H__
+
+#ifdef CONFIG_CPU_HAS_PMU
+
+struct pmu_irqs {
+	const int   *irqs;
+	int	    num_irqs;
+};
+
+/**
+ * reserve_pmu() - reserve the hardware performance counters
+ *
+ * Reserve the hardware performance counters in the system for exclusive use.
+ * The 'struct pmu_irqs' for the system is returned on success, ERR_PTR()
+ * encoded error on failure.
+ */
+extern const struct pmu_irqs *
+reserve_pmu(void);
+
+/**
+ * release_pmu() - Relinquish control of the performance counters
+ *
+ * Release the performance counters and allow someone else to use them.
+ * Callers must have disabled the counters and released IRQs before calling
+ * this. The 'struct pmu_irqs' returned from reserve_pmu() must be passed as
+ * a cookie.
+ */
+extern int
+release_pmu(const struct pmu_irqs *irqs);
+
+/**
+ * init_pmu() - Initialise the PMU.
+ *
+ * Initialise the system ready for PMU enabling. This should typically set the
+ * IRQ affinity and nothing else. The users (oprofile/perf events etc) will do
+ * the actual hardware initialisation.
+ */
+extern int
+init_pmu(void);
+
+#else /* CONFIG_CPU_HAS_PMU */
+
+static inline const struct pmu_irqs *
+reserve_pmu(void)
+{
+	return ERR_PTR(-ENODEV);
+}
+
+static inline int
+release_pmu(const struct pmu_irqs *irqs)
+{
+	return -ENODEV;
+}
+
+static inline int
+init_pmu(void)
+{
+	return -ENODEV;
+}
+
+#endif /* CONFIG_CPU_HAS_PMU */
+
+#endif /* __ARM_PMU_H__ */

arch/arm/kernel/Makefile

@@ -46,6 +46,8 @@ obj-$(CONFIG_CPU_XSCALE)	+= xscale-cp0.o
 obj-$(CONFIG_CPU_XSC3)		+= xscale-cp0.o
 obj-$(CONFIG_CPU_MOHAWK)	+= xscale-cp0.o
 obj-$(CONFIG_IWMMXT)		+= iwmmxt.o
+obj-$(CONFIG_CPU_HAS_PMU)	+= pmu.o
+obj-$(CONFIG_HW_PERF_EVENTS)	+= perf_event.o
 AFLAGS_iwmmxt.o			:= -Wa,-mcpu=iwmmxt
 
 ifneq ($(CONFIG_ARCH_EBSA110),y)

arch/arm/kernel/pmu.c

@@ -0,0 +1,103 @@
+/*
+ *  linux/arch/arm/kernel/pmu.c
+ *
+ *  Copyright (C) 2009 picoChip Designs Ltd, Jamie Iles
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#include <linux/cpumask.h>
+#include <linux/err.h>
+#include <linux/interrupt.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+
+#include <asm/pmu.h>
+
+/*
+ * Define the IRQs for the system. We could use something like a platform
+ * device but that seems fairly heavyweight for this. Also, the performance
+ * counters can't be removed or hotplugged.
+ *
+ * Ordering is important: init_pmu() will use the ordering to set the affinity
+ * to the corresponding core. e.g. the first interrupt will go to cpu 0, the
+ * second goes to cpu 1 etc.
+ */
+static const int irqs[] = {
+#if defined(CONFIG_ARCH_OMAP2)
+	3,
+#elif defined(CONFIG_ARCH_BCMRING)
+	IRQ_PMUIRQ,
+#elif defined(CONFIG_MACH_REALVIEW_EB)
+	IRQ_EB11MP_PMU_CPU0,
+	IRQ_EB11MP_PMU_CPU1,
+	IRQ_EB11MP_PMU_CPU2,
+	IRQ_EB11MP_PMU_CPU3,
+#elif defined(CONFIG_ARCH_OMAP3)
+	INT_34XX_BENCH_MPU_EMUL,
+#elif defined(CONFIG_ARCH_IOP32X)
+	IRQ_IOP32X_CORE_PMU,
+#elif defined(CONFIG_ARCH_IOP33X)
+	IRQ_IOP33X_CORE_PMU,
+#elif defined(CONFIG_ARCH_PXA)
+	IRQ_PMU,
+#endif
+};
+
+static const struct pmu_irqs pmu_irqs = {
+	.irqs	    = irqs,
+	.num_irqs   = ARRAY_SIZE(irqs),
+};
+
+static volatile long pmu_lock;
+
+const struct pmu_irqs *
+reserve_pmu(void)
+{
+	return test_and_set_bit_lock(0, &pmu_lock) ? ERR_PTR(-EBUSY) :
+		&pmu_irqs;
+}
+EXPORT_SYMBOL_GPL(reserve_pmu);
+
+int
+release_pmu(const struct pmu_irqs *irqs)
+{
+	if (WARN_ON(irqs != &pmu_irqs))
+		return -EINVAL;
+	clear_bit_unlock(0, &pmu_lock);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(release_pmu);
+
+static int
+set_irq_affinity(int irq,
+		 unsigned int cpu)
+{
+#ifdef CONFIG_SMP
+	int err = irq_set_affinity(irq, cpumask_of(cpu));
+	if (err)
+		pr_warning("unable to set irq affinity (irq=%d, cpu=%u)\n",
+			   irq, cpu);
+	return err;
+#else
+	return 0;
+#endif
+}
+
+int
+init_pmu(void)
+{
+	int i, err = 0;
+
+	for (i = 0; i < pmu_irqs.num_irqs; ++i) {
+		err = set_irq_affinity(pmu_irqs.irqs[i], i);
+		if (err)
+			break;
+	}
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(init_pmu);

arch/arm/mm/fault.c

@@ -18,6 +18,7 @@
 #include <linux/page-flags.h>
 #include <linux/sched.h>
 #include <linux/highmem.h>
+#include <linux/perf_event.h>
 
 #include <asm/system.h>
 #include <asm/pgtable.h>
@@ -302,6 +303,12 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 	fault = __do_page_fault(mm, addr, fsr, tsk);
 	up_read(&mm->mmap_sem);
 
+	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, 0, regs, addr);
+	if (fault & VM_FAULT_MAJOR)
+		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, 0, regs, addr);
+	else if (fault & VM_FAULT_MINOR)
+		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, 0, regs, addr);
+
 	/*
 	 * Handle the "normal" case first - VM_FAULT_MAJOR / VM_FAULT_MINOR
 	 */

arch/arm/oprofile/op_model_arm11_core.c

@@ -132,7 +132,7 @@ static irqreturn_t arm11_pmu_interrupt(int irq, void *arg)
 	return IRQ_HANDLED;
 }
 
-int arm11_request_interrupts(int *irqs, int nr)
+int arm11_request_interrupts(const int *irqs, int nr)
 {
 	unsigned int i;
 	int ret = 0;
@@ -153,7 +153,7 @@ int arm11_request_interrupts(int *irqs, int nr)
 	return ret;
 }
 
-void arm11_release_interrupts(int *irqs, int nr)
+void arm11_release_interrupts(const int *irqs, int nr)
 {
 	unsigned int i;
 

arch/arm/oprofile/op_model_arm11_core.h

@@ -39,7 +39,7 @@
 int arm11_setup_pmu(void);
 int arm11_start_pmu(void);
 int arm11_stop_pmu(void);
-int arm11_request_interrupts(int *, int);
+int arm11_request_interrupts(const int *, int);
-void arm11_release_interrupts(int *, int);
+void arm11_release_interrupts(const int *, int);
 
 #endif

arch/arm/oprofile/op_model_mpcore.c

@@ -32,6 +32,7 @@
 /* #define DEBUG */
 #include <linux/types.h>
 #include <linux/errno.h>
+#include <linux/err.h>
 #include <linux/sched.h>
 #include <linux/oprofile.h>
 #include <linux/interrupt.h>
@@ -43,6 +44,7 @@
 #include <mach/hardware.h>
 #include <mach/board-eb.h>
 #include <asm/system.h>
+#include <asm/pmu.h>
 
 #include "op_counter.h"
 #include "op_arm_model.h"
@@ -58,6 +60,7 @@
  * Bitmask of used SCU counters
  */
 static unsigned int scu_em_used;
+static const struct pmu_irqs *pmu_irqs;
 
 /*
  * 2 helper fns take a counter number from 0-7 (not the userspace-visible counter number)
@@ -225,33 +228,40 @@ static int em_setup_ctrs(void)
 	return 0;
 }
 
-static int arm11_irqs[] = {
-	[0]	= IRQ_EB11MP_PMU_CPU0,
-	[1]	= IRQ_EB11MP_PMU_CPU1,
-	[2]	= IRQ_EB11MP_PMU_CPU2,
-	[3]	= IRQ_EB11MP_PMU_CPU3
-};
-
 static int em_start(void)
 {
 	int ret;
 
-	ret = arm11_request_interrupts(arm11_irqs, ARRAY_SIZE(arm11_irqs));
+	pmu_irqs = reserve_pmu();
+	if (IS_ERR(pmu_irqs)) {
+		ret = PTR_ERR(pmu_irqs);
+		goto out;
+	}
+
+	ret = arm11_request_interrupts(pmu_irqs->irqs, pmu_irqs->num_irqs);
 	if (ret == 0) {
 		em_call_function(arm11_start_pmu);
 
 		ret = scu_start();
-		if (ret)
+		if (ret) {
-			arm11_release_interrupts(arm11_irqs, ARRAY_SIZE(arm11_irqs));
+			arm11_release_interrupts(pmu_irqs->irqs,
+						 pmu_irqs->num_irqs);
+		} else {
+			release_pmu(pmu_irqs);
+			pmu_irqs = NULL;
+		}
 	}
+
+out:
 	return ret;
 }
 
 static void em_stop(void)
 {
 	em_call_function(arm11_stop_pmu);
-	arm11_release_interrupts(arm11_irqs, ARRAY_SIZE(arm11_irqs));
+	arm11_release_interrupts(pmu_irqs->irqs, pmu_irqs->num_irqs);
 	scu_stop();
+	release_pmu(pmu_irqs);
 }
 
 /*
@@ -283,15 +293,7 @@ static int em_setup(void)
 	em_route_irq(IRQ_EB11MP_PMU_SCU6, 3);
 	em_route_irq(IRQ_EB11MP_PMU_SCU7, 3);
 
-	/*
+	return init_pmu();
-	 * Send CP15 PMU interrupts to the owner CPU.
-	 */
-	em_route_irq(IRQ_EB11MP_PMU_CPU0, 0);
-	em_route_irq(IRQ_EB11MP_PMU_CPU1, 1);
-	em_route_irq(IRQ_EB11MP_PMU_CPU2, 2);
-	em_route_irq(IRQ_EB11MP_PMU_CPU3, 3);
-
-	return 0;
 }
 
 struct op_arm_model_spec op_mpcore_spec = {

arch/arm/oprofile/op_model_v6.c

@@ -19,39 +19,47 @@
 /* #define DEBUG */
 #include <linux/types.h>
 #include <linux/errno.h>
+#include <linux/err.h>
 #include <linux/sched.h>
 #include <linux/oprofile.h>
 #include <linux/interrupt.h>
 #include <asm/irq.h>
 #include <asm/system.h>
+#include <asm/pmu.h>
 
 #include "op_counter.h"
 #include "op_arm_model.h"
 #include "op_model_arm11_core.h"
 
-static int irqs[] = {
+static const struct pmu_irqs *pmu_irqs;
-#ifdef CONFIG_ARCH_OMAP2
-	3,
-#endif
-#ifdef CONFIG_ARCH_BCMRING
-	IRQ_PMUIRQ, /* for BCMRING, ARM PMU interrupt is 43 */
-#endif
-};
 
 static void armv6_pmu_stop(void)
 {
 	arm11_stop_pmu();
-	arm11_release_interrupts(irqs, ARRAY_SIZE(irqs));
+	arm11_release_interrupts(pmu_irqs->irqs, pmu_irqs->num_irqs);
+	release_pmu(pmu_irqs);
+	pmu_irqs = NULL;
 }
 
 static int armv6_pmu_start(void)
 {
 	int ret;
 
-	ret = arm11_request_interrupts(irqs, ARRAY_SIZE(irqs));
+	pmu_irqs = reserve_pmu();
-	if (ret >= 0)
+	if (IS_ERR(pmu_irqs)) {
-		ret = arm11_start_pmu();
+		ret = PTR_ERR(pmu_irqs);
+		goto out;
+	}
 
+	ret = arm11_request_interrupts(pmu_irqs->irqs, pmu_irqs->num_irqs);
+	if (ret >= 0) {
+		ret = arm11_start_pmu();
+	} else {
+		release_pmu(pmu_irqs);
+		pmu_irqs = NULL;
+	}
+
+out:
 	return ret;
 }
 

arch/arm/oprofile/op_model_v7.c

@@ -11,11 +11,14 @@
  */
 #include <linux/types.h>
 #include <linux/errno.h>
+#include <linux/err.h>
 #include <linux/oprofile.h>
 #include <linux/interrupt.h>
 #include <linux/irq.h>
 #include <linux/smp.h>
 
+#include <asm/pmu.h>
+
 #include "op_counter.h"
 #include "op_arm_model.h"
 #include "op_model_v7.h"
@@ -295,7 +298,7 @@ static irqreturn_t armv7_pmnc_interrupt(int irq, void *arg)
 	return IRQ_HANDLED;
 }
 
-int armv7_request_interrupts(int *irqs, int nr)
+int armv7_request_interrupts(const int *irqs, int nr)
 {
 	unsigned int i;
 	int ret = 0;
@@ -318,7 +321,7 @@ int armv7_request_interrupts(int *irqs, int nr)
 	return ret;
 }
 
-void armv7_release_interrupts(int *irqs, int nr)
+void armv7_release_interrupts(const int *irqs, int nr)
 {
 	unsigned int i;
 
@@ -362,12 +365,7 @@ static void armv7_pmnc_dump_regs(void)
 }
 #endif
 
-
+static const struct pmu_irqs *pmu_irqs;
-static int irqs[] = {
-#ifdef CONFIG_ARCH_OMAP3
-	INT_34XX_BENCH_MPU_EMUL,
-#endif
-};
 
 static void armv7_pmnc_stop(void)
 {
@@ -375,19 +373,29 @@ static void armv7_pmnc_stop(void)
 	armv7_pmnc_dump_regs();
 #endif
 	armv7_stop_pmnc();
-	armv7_release_interrupts(irqs, ARRAY_SIZE(irqs));
+	armv7_release_interrupts(pmu_irqs->irqs, pmu_irqs->num_irqs);
+	release_pmu(pmu_irqs);
+	pmu_irqs = NULL;
 }
 
 static int armv7_pmnc_start(void)
 {
 	int ret;
 
+	pmu_irqs = reserve_pmu();
+	if (IS_ERR(pmu_irqs))
+		return PTR_ERR(pmu_irqs);
+
 #ifdef DEBUG
 	armv7_pmnc_dump_regs();
 #endif
-	ret = armv7_request_interrupts(irqs, ARRAY_SIZE(irqs));
+	ret = armv7_request_interrupts(pmu_irqs->irqs, pmu_irqs->num_irqs);
-	if (ret >= 0)
+	if (ret >= 0) {
 		armv7_start_pmnc();
+	} else {
+		release_pmu(pmu_irqs);
+		pmu_irqs = NULL;
+	}
 
 	return ret;
 }

arch/arm/oprofile/op_model_v7.h

@@ -97,7 +97,7 @@
 int armv7_setup_pmu(void);
 int armv7_start_pmu(void);
 int armv7_stop_pmu(void);
-int armv7_request_interrupts(int *, int);
+int armv7_request_interrupts(const int *, int);
-void armv7_release_interrupts(int *, int);
+void armv7_release_interrupts(const int *, int);
 
 #endif

arch/arm/oprofile/op_model_xscale.c

@@ -17,12 +17,14 @@
 /* #define DEBUG */
 #include <linux/types.h>
 #include <linux/errno.h>
+#include <linux/err.h>
 #include <linux/sched.h>
 #include <linux/oprofile.h>
 #include <linux/interrupt.h>
 #include <linux/irq.h>
 
 #include <asm/cputype.h>
+#include <asm/pmu.h>
 
 #include "op_counter.h"
 #include "op_arm_model.h"
@@ -33,17 +35,6 @@
 #define	PMU_RESET	(CCNT_RESET | PMN_RESET)
 #define PMU_CNT64	0x008	/* Make CCNT count every 64th cycle */
 
-/* TODO do runtime detection */
-#ifdef CONFIG_ARCH_IOP32X
-#define XSCALE_PMU_IRQ  IRQ_IOP32X_CORE_PMU
-#endif
-#ifdef CONFIG_ARCH_IOP33X
-#define XSCALE_PMU_IRQ  IRQ_IOP33X_CORE_PMU
-#endif
-#ifdef CONFIG_ARCH_PXA
-#define XSCALE_PMU_IRQ  IRQ_PMU
-#endif
-
 /*
  * Different types of events that can be counted by the XScale PMU
  * as used by Oprofile userspace. Here primarily for documentation
@@ -367,6 +358,8 @@ static irqreturn_t xscale_pmu_interrupt(int irq, void *arg)
 	return IRQ_HANDLED;
 }
 
+static const struct pmu_irqs *pmu_irqs;
+
 static void xscale_pmu_stop(void)
 {
 	u32 pmnc = read_pmnc();
@@ -374,20 +367,30 @@ static void xscale_pmu_stop(void)
 	pmnc &= ~PMU_ENABLE;
 	write_pmnc(pmnc);
 
-	free_irq(XSCALE_PMU_IRQ, results);
+	free_irq(pmu_irqs->irqs[0], results);
+	release_pmu(pmu_irqs);
+	pmu_irqs = NULL;
 }
 
 static int xscale_pmu_start(void)
 {
 	int ret;
-	u32 pmnc = read_pmnc();
+	u32 pmnc;
 
-	ret = request_irq(XSCALE_PMU_IRQ, xscale_pmu_interrupt, IRQF_DISABLED,
+	pmu_irqs = reserve_pmu();
-			"XScale PMU", (void *)results);
+	if (IS_ERR(pmu_irqs))
+		return PTR_ERR(pmu_irqs);
+
+	pmnc = read_pmnc();
+
+	ret = request_irq(pmu_irqs->irqs[0], xscale_pmu_interrupt,
+			  IRQF_DISABLED, "XScale PMU", (void *)results);
 
 	if (ret < 0) {
 		printk(KERN_ERR "oprofile: unable to request IRQ%d for XScale PMU\n",
-			XSCALE_PMU_IRQ);
+		       pmu_irqs->irqs[0]);
+		release_pmu(pmu_irqs);
+		pmu_irqs = NULL;
 		return ret;
 	}