[ARM] 5195/1: ARMv7 Oprofile support

Add Oprofile kernel support for ARMv7.
Tested on OMAP3430 and OMAP3530 chipsets (Cortex-A8).

Signed-off-by: Jean Pihet <jpihet@mvista.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>

5 files changed, 520 insertions, 0 deletions

diff --git a/arch/arm/oprofile/Makefile b/arch/arm/oprofile/Makefile
index e61d0cc520b7..88e31f549f50 100644
--- a/arch/arm/oprofile/Makefile
+++ b/arch/arm/oprofile/Makefile
@@ -11,3 +11,4 @@ oprofile-$(CONFIG_CPU_XSCALE)		+= op_model_xscale.o
 oprofile-$(CONFIG_OPROFILE_ARM11_CORE)	+= op_model_arm11_core.o
 oprofile-$(CONFIG_OPROFILE_ARMV6)	+= op_model_v6.o
 oprofile-$(CONFIG_OPROFILE_MPCORE)	+= op_model_mpcore.o
+oprofile-$(CONFIG_OPROFILE_ARMV7)	+= op_model_v7.o
diff --git a/arch/arm/oprofile/common.c b/arch/arm/oprofile/common.c
index 0a5cf3a6438b..3fcd752d6146 100644
--- a/arch/arm/oprofile/common.c
+++ b/arch/arm/oprofile/common.c
@@ -145,6 +145,10 @@ int __init oprofile_arch_init(struct oprofile_operations *ops)
 	spec = &op_mpcore_spec;
 #endif
 
+#ifdef CONFIG_OPROFILE_ARMV7
+	spec = &op_armv7_spec;
+#endif
+
 	if (spec) {
 		ret = spec->init();
 		if (ret < 0)
diff --git a/arch/arm/oprofile/op_arm_model.h b/arch/arm/oprofile/op_arm_model.h
index 4899c629aa03..8c4e4f6a1de3 100644
--- a/arch/arm/oprofile/op_arm_model.h
+++ b/arch/arm/oprofile/op_arm_model.h
@@ -26,6 +26,7 @@ extern struct op_arm_model_spec op_xscale_spec;
 
 extern struct op_arm_model_spec op_armv6_spec;
 extern struct op_arm_model_spec op_mpcore_spec;
+extern struct op_arm_model_spec op_armv7_spec;
 
 extern void arm_backtrace(struct pt_regs * const regs, unsigned int depth);
 
diff --git a/arch/arm/oprofile/op_model_v7.c b/arch/arm/oprofile/op_model_v7.c
new file mode 100644
index 000000000000..f20295f14adb
--- /dev/null
+++ b/arch/arm/oprofile/op_model_v7.c
@@ -0,0 +1,411 @@
+/**
+ * op_model_v7.c
+ * ARM V7 (Cortex A8) Event Monitor Driver
+ *
+ * Copyright 2008 Jean Pihet <jpihet@mvista.com>
+ * Copyright 2004 ARM SMP Development Team
+ *
+ * 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/types.h>
+#include <linux/errno.h>
+#include <linux/oprofile.h>
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/smp.h>
+
+#include "op_counter.h"
+#include "op_arm_model.h"
+#include "op_model_v7.h"
+
+/* #define DEBUG */
+
+
+/*
+ * ARM V7 PMNC support
+ */
+
+static u32 cnt_en[CNTMAX];
+
+static inline void armv7_pmnc_write(u32 val)
+{
+	val &= PMNC_MASK;
+	asm volatile("mcr p15, 0, %0, c9, c12, 0" : : "r" (val));
+}
+
+static inline u32 armv7_pmnc_read(void)
+{
+	u32 val;
+
+	asm volatile("mrc p15, 0, %0, c9, c12, 0" : "=r" (val));
+	return val;
+}
+
+static inline u32 armv7_pmnc_enable_counter(unsigned int cnt)
+{
+	u32 val;
+
+	if (cnt >= CNTMAX) {
+		printk(KERN_ERR "oprofile: CPU%u enabling wrong PMNC counter"
+			" %d\n", smp_processor_id(), cnt);
+		return -1;
+	}
+
+	if (cnt == CCNT)
+		val = CNTENS_C;
+	else
+		val = (1 << (cnt - CNT0));
+
+	val &= CNTENS_MASK;
+	asm volatile("mcr p15, 0, %0, c9, c12, 1" : : "r" (val));
+
+	return cnt;
+}
+
+static inline u32 armv7_pmnc_disable_counter(unsigned int cnt)
+{
+	u32 val;
+
+	if (cnt >= CNTMAX) {
+		printk(KERN_ERR "oprofile: CPU%u disabling wrong PMNC counter"
+			" %d\n", smp_processor_id(), cnt);
+		return -1;
+	}
+
+	if (cnt == CCNT)
+		val = CNTENC_C;
+	else
+		val = (1 << (cnt - CNT0));
+
+	val &= CNTENC_MASK;
+	asm volatile("mcr p15, 0, %0, c9, c12, 2" : : "r" (val));
+
+	return cnt;
+}
+
+static inline u32 armv7_pmnc_enable_intens(unsigned int cnt)
+{
+	u32 val;
+
+	if (cnt >= CNTMAX) {
+		printk(KERN_ERR "oprofile: CPU%u enabling wrong PMNC counter"
+			" interrupt enable %d\n", smp_processor_id(), cnt);
+		return -1;
+	}
+
+	if (cnt == CCNT)
+		val = INTENS_C;
+	else
+		val = (1 << (cnt - CNT0));
+
+	val &= INTENS_MASK;
+	asm volatile("mcr p15, 0, %0, c9, c14, 1" : : "r" (val));
+
+	return cnt;
+}
+
+static inline u32 armv7_pmnc_getreset_flags(void)
+{
+	u32 val;
+
+	/* Read */
+	asm volatile("mrc p15, 0, %0, c9, c12, 3" : "=r" (val));
+
+	/* Write to clear flags */
+	val &= FLAG_MASK;
+	asm volatile("mcr p15, 0, %0, c9, c12, 3" : : "r" (val));
+
+	return val;
+}
+
+static inline int armv7_pmnc_select_counter(unsigned int cnt)
+{
+	u32 val;
+
+	if ((cnt == CCNT) || (cnt >= CNTMAX)) {
+		printk(KERN_ERR "oprofile: CPU%u selecting wrong PMNC counteri"
+			" %d\n", smp_processor_id(), cnt);
+		return -1;
+	}
+
+	val = (cnt - CNT0) & SELECT_MASK;
+	asm volatile("mcr p15, 0, %0, c9, c12, 5" : : "r" (val));
+
+	return cnt;
+}
+
+static inline void armv7_pmnc_write_evtsel(unsigned int cnt, u32 val)
+{
+	if (armv7_pmnc_select_counter(cnt) == cnt) {
+		val &= EVTSEL_MASK;
+		asm volatile("mcr p15, 0, %0, c9, c13, 1" : : "r" (val));
+	}
+}
+
+static void armv7_pmnc_reset_counter(unsigned int cnt)
+{
+	u32 cpu_cnt = CPU_COUNTER(smp_processor_id(), cnt);
+	u32 val = -(u32)counter_config[cpu_cnt].count;
+
+	switch (cnt) {
+	case CCNT:
+		armv7_pmnc_disable_counter(cnt);
+
+		asm volatile("mcr p15, 0, %0, c9, c13, 0" : : "r" (val));
+
+		if (cnt_en[cnt] != 0)
+		    armv7_pmnc_enable_counter(cnt);
+
+		break;
+
+	case CNT0:
+	case CNT1:
+	case CNT2:
+	case CNT3:
+		armv7_pmnc_disable_counter(cnt);
+
+		if (armv7_pmnc_select_counter(cnt) == cnt)
+		    asm volatile("mcr p15, 0, %0, c9, c13, 2" : : "r" (val));
+
+		if (cnt_en[cnt] != 0)
+		    armv7_pmnc_enable_counter(cnt);
+
+		break;
+
+	default:
+		printk(KERN_ERR "oprofile: CPU%u resetting wrong PMNC counter"
+			" %d\n", smp_processor_id(), cnt);
+		break;
+	}
+}
+
+int armv7_setup_pmnc(void)
+{
+	unsigned int cnt;
+
+	if (armv7_pmnc_read() & PMNC_E) {
+		printk(KERN_ERR "oprofile: CPU%u PMNC still enabled when setup"
+			" new event counter.\n", smp_processor_id());
+		return -EBUSY;
+	}
+
+	/*
+	 * Initialize & Reset PMNC: C bit, D bit and P bit.
+	 *  Note: Using a slower count for CCNT (D bit: divide by 64) results
+	 *   in a more stable system
+	 */
+	armv7_pmnc_write(PMNC_P | PMNC_C | PMNC_D);
+
+
+	for (cnt = CCNT; cnt < CNTMAX; cnt++) {
+		unsigned long event;
+		u32 cpu_cnt = CPU_COUNTER(smp_processor_id(), cnt);
+
+		/*
+		 * Disable counter
+		 */
+		armv7_pmnc_disable_counter(cnt);
+		cnt_en[cnt] = 0;
+
+		if (!counter_config[cpu_cnt].enabled)
+			continue;
+
+		event = counter_config[cpu_cnt].event & 255;
+
+		/*
+		 * Set event (if destined for PMNx counters)
+		 * We don't need to set the event if it's a cycle count
+		 */
+		if (cnt != CCNT)
+			armv7_pmnc_write_evtsel(cnt, event);
+
+		/*
+		 * Enable interrupt for this counter
+		 */
+		armv7_pmnc_enable_intens(cnt);
+
+		/*
+		 * Reset counter
+		 */
+		armv7_pmnc_reset_counter(cnt);
+
+		/*
+		 * Enable counter
+		 */
+		armv7_pmnc_enable_counter(cnt);
+		cnt_en[cnt] = 1;
+	}
+
+	return 0;
+}
+
+static inline void armv7_start_pmnc(void)
+{
+	armv7_pmnc_write(armv7_pmnc_read() | PMNC_E);
+}
+
+static inline void armv7_stop_pmnc(void)
+{
+	armv7_pmnc_write(armv7_pmnc_read() & ~PMNC_E);
+}
+
+/*
+ * CPU counters' IRQ handler (one IRQ per CPU)
+ */
+static irqreturn_t armv7_pmnc_interrupt(int irq, void *arg)
+{
+	struct pt_regs *regs = get_irq_regs();
+	unsigned int cnt;
+	u32 flags;
+
+
+	/*
+	 * Stop IRQ generation
+	 */
+	armv7_stop_pmnc();
+
+	/*
+	 * Get and reset overflow status flags
+	 */
+	flags = armv7_pmnc_getreset_flags();
+
+	/*
+	 * Cycle counter
+	 */
+	if (flags & FLAG_C) {
+		u32 cpu_cnt = CPU_COUNTER(smp_processor_id(), CCNT);
+		armv7_pmnc_reset_counter(CCNT);
+		oprofile_add_sample(regs, cpu_cnt);
+	}
+
+	/*
+	 * PMNC counters 0:3
+	 */
+	for (cnt = CNT0; cnt < CNTMAX; cnt++) {
+		if (flags & (1 << (cnt - CNT0))) {
+			u32 cpu_cnt = CPU_COUNTER(smp_processor_id(), cnt);
+			armv7_pmnc_reset_counter(cnt);
+			oprofile_add_sample(regs, cpu_cnt);
+		}
+	}
+
+	/*
+	 * Allow IRQ generation
+	 */
+	armv7_start_pmnc();
+
+	return IRQ_HANDLED;
+}
+
+int armv7_request_interrupts(int *irqs, int nr)
+{
+	unsigned int i;
+	int ret = 0;
+
+	for (i = 0; i < nr; i++) {
+		ret = request_irq(irqs[i], armv7_pmnc_interrupt,
+				IRQF_DISABLED, "CP15 PMNC", NULL);
+		if (ret != 0) {
+			printk(KERN_ERR "oprofile: unable to request IRQ%u"
+				" for ARMv7\n",
+			       irqs[i]);
+			break;
+		}
+	}
+
+	if (i != nr)
+		while (i-- != 0)
+			free_irq(irqs[i], NULL);
+
+	return ret;
+}
+
+void armv7_release_interrupts(int *irqs, int nr)
+{
+	unsigned int i;
+
+	for (i = 0; i < nr; i++)
+		free_irq(irqs[i], NULL);
+}
+
+#ifdef DEBUG
+static void armv7_pmnc_dump_regs(void)
+{
+	u32 val;
+	unsigned int cnt;
+
+	printk(KERN_INFO "PMNC registers dump:\n");
+
+	asm volatile("mrc p15, 0, %0, c9, c12, 0" : "=r" (val));
+	printk(KERN_INFO "PMNC  =0x%08x\n", val);
+
+	asm volatile("mrc p15, 0, %0, c9, c12, 1" : "=r" (val));
+	printk(KERN_INFO "CNTENS=0x%08x\n", val);
+
+	asm volatile("mrc p15, 0, %0, c9, c14, 1" : "=r" (val));
+	printk(KERN_INFO "INTENS=0x%08x\n", val);
+
+	asm volatile("mrc p15, 0, %0, c9, c12, 3" : "=r" (val));
+	printk(KERN_INFO "FLAGS =0x%08x\n", val);
+
+	asm volatile("mrc p15, 0, %0, c9, c12, 5" : "=r" (val));
+	printk(KERN_INFO "SELECT=0x%08x\n", val);
+
+	asm volatile("mrc p15, 0, %0, c9, c13, 0" : "=r" (val));
+	printk(KERN_INFO "CCNT  =0x%08x\n", val);
+
+	for (cnt = CNT0; cnt < CNTMAX; cnt++) {
+		armv7_pmnc_select_counter(cnt);
+		asm volatile("mrc p15, 0, %0, c9, c13, 2" : "=r" (val));
+		printk(KERN_INFO "CNT[%d] count =0x%08x\n", cnt-CNT0, val);
+		asm volatile("mrc p15, 0, %0, c9, c13, 1" : "=r" (val));
+		printk(KERN_INFO "CNT[%d] evtsel=0x%08x\n", cnt-CNT0, val);
+	}
+}
+#endif
+
+
+static int irqs[] = {
+#ifdef CONFIG_ARCH_OMAP3
+	INT_34XX_BENCH_MPU_EMUL,
+#endif
+};
+
+static void armv7_pmnc_stop(void)
+{
+#ifdef DEBUG
+	armv7_pmnc_dump_regs();
+#endif
+	armv7_stop_pmnc();
+	armv7_release_interrupts(irqs, ARRAY_SIZE(irqs));
+}
+
+static int armv7_pmnc_start(void)
+{
+	int ret;
+
+#ifdef DEBUG
+	armv7_pmnc_dump_regs();
+#endif
+	ret = armv7_request_interrupts(irqs, ARRAY_SIZE(irqs));
+	if (ret >= 0)
+		armv7_start_pmnc();
+
+	return ret;
+}
+
+static int armv7_detect_pmnc(void)
+{
+	return 0;
+}
+
+struct op_arm_model_spec op_armv7_spec = {
+	.init		= armv7_detect_pmnc,
+	.num_counters	= 5,
+	.setup_ctrs	= armv7_setup_pmnc,
+	.start		= armv7_pmnc_start,
+	.stop		= armv7_pmnc_stop,
+	.name		= "arm/armv7",
+};
diff --git a/arch/arm/oprofile/op_model_v7.h b/arch/arm/oprofile/op_model_v7.h
new file mode 100644
index 000000000000..0e19bcc2e100
--- /dev/null
+++ b/arch/arm/oprofile/op_model_v7.h
@@ -0,0 +1,103 @@
+/**
+ * op_model_v7.h
+ * ARM v7 (Cortex A8) Event Monitor Driver
+ *
+ * Copyright 2008 Jean Pihet <jpihet@mvista.com>
+ * Copyright 2004 ARM SMP Development Team
+ * Copyright 2000-2004 Deepak Saxena <dsaxena@mvista.com>
+ * Copyright 2000-2004 MontaVista Software Inc
+ * Copyright 2004 Dave Jiang <dave.jiang@intel.com>
+ * Copyright 2004 Intel Corporation
+ * Copyright 2004 Zwane Mwaikambo <zwane@arm.linux.org.uk>
+ * Copyright 2004 Oprofile Authors
+ *
+ * Read the file COPYING
+ *
+ * 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 OP_MODEL_V7_H
+#define OP_MODEL_V7_H
+
+/*
+ * Per-CPU PMNC: config reg
+ */
+#define PMNC_E		(1 << 0)	/* Enable all counters */
+#define PMNC_P		(1 << 1)	/* Reset all counters */
+#define PMNC_C		(1 << 2)	/* Cycle counter reset */
+#define PMNC_D		(1 << 3)	/* CCNT counts every 64th cpu cycle */
+#define PMNC_X		(1 << 4)	/* Export to ETM */
+#define PMNC_DP		(1 << 5)	/* Disable CCNT if non-invasive debug*/
+#define	PMNC_MASK	0x3f		/* Mask for writable bits */
+
+/*
+ * Available counters
+ */
+#define CCNT 		0
+#define CNT0 		1
+#define CNT1 		2
+#define CNT2 		3
+#define CNT3 		4
+#define CNTMAX 		5
+
+#define CPU_COUNTER(cpu, counter)	((cpu) * CNTMAX + (counter))
+
+/*
+ * CNTENS: counters enable reg
+ */
+#define CNTENS_P0	(1 << 0)
+#define CNTENS_P1	(1 << 1)
+#define CNTENS_P2	(1 << 2)
+#define CNTENS_P3	(1 << 3)
+#define CNTENS_C	(1 << 31)
+#define	CNTENS_MASK	0x8000000f	/* Mask for writable bits */
+
+/*
+ * CNTENC: counters disable reg
+ */
+#define CNTENC_P0	(1 << 0)
+#define CNTENC_P1	(1 << 1)
+#define CNTENC_P2	(1 << 2)
+#define CNTENC_P3	(1 << 3)
+#define CNTENC_C	(1 << 31)
+#define	CNTENC_MASK	0x8000000f	/* Mask for writable bits */
+
+/*
+ * INTENS: counters overflow interrupt enable reg
+ */
+#define INTENS_P0	(1 << 0)
+#define INTENS_P1	(1 << 1)
+#define INTENS_P2	(1 << 2)
+#define INTENS_P3	(1 << 3)
+#define INTENS_C	(1 << 31)
+#define	INTENS_MASK	0x8000000f	/* Mask for writable bits */
+
+/*
+ * EVTSEL: Event selection reg
+ */
+#define	EVTSEL_MASK	0x7f		/* Mask for writable bits */
+
+/*
+ * SELECT: Counter selection reg
+ */
+#define	SELECT_MASK	0x1f		/* Mask for writable bits */
+
+/*
+ * FLAG: counters overflow flag status reg
+ */
+#define FLAG_P0		(1 << 0)
+#define FLAG_P1		(1 << 1)
+#define FLAG_P2		(1 << 2)
+#define FLAG_P3		(1 << 3)
+#define FLAG_C		(1 << 31)
+#define	FLAG_MASK	0x8000000f	/* Mask for writable bits */
+
+
+int armv7_setup_pmu(void);
+int armv7_start_pmu(void);
+int armv7_stop_pmu(void);
+int armv7_request_interrupts(int *, int);
+void armv7_release_interrupts(int *, int);
+
+#endif