[ARM] oprofile: add ARM11 SMP support

Add the glue for ARM11 SMP oprofile support, which also supports the
performance monitor in the coherency unit.
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>

arch/arm/oprofile/Kconfig

@@ -27,6 +27,12 @@ config OPROFILE_ARMV6
 	default y
 	select OPROFILE_ARM11_CORE
 
+config OPROFILE_MPCORE
+	bool
+	depends on CPU_V6 && SMP
+	default y
+	select OPROFILE_ARM11_CORE
+
 config OPROFILE_ARM11_CORE
 	bool
 

arch/arm/oprofile/Makefile

@@ -10,3 +10,4 @@ oprofile-y				:= $(DRIVER_OBJS) common.o backtrace.o
 oprofile-$(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

arch/arm/oprofile/common.c

@@ -139,6 +139,10 @@ int __init oprofile_arch_init(struct oprofile_operations *ops)
 	spec = &op_armv6_spec;
 #endif
 
+#ifdef CONFIG_OPROFILE_MPCORE
+	spec = &op_mpcore_spec;
+#endif
+
 	if (spec) {
 		ret = spec->init();
 		if (ret < 0)

arch/arm/oprofile/op_arm_model.h

@@ -25,6 +25,7 @@ extern struct op_arm_model_spec op_xscale_spec;
 #endif
 
 extern struct op_arm_model_spec op_armv6_spec;
+extern struct op_arm_model_spec op_mpcore_spec;
 
 extern void arm_backtrace(struct pt_regs * const regs, unsigned int depth);
 

arch/arm/oprofile/op_model_mpcore.c

+/**
+ * @file op_model_mpcore.c
+ * MPCORE Event Monitor Driver
+ * @remark Copyright 2004 ARM SMP Development Team
+ * @remark Copyright 2000-2004 Deepak Saxena <dsaxena@mvista.com>
+ * @remark Copyright 2000-2004 MontaVista Software Inc
+ * @remark Copyright 2004 Dave Jiang <dave.jiang@intel.com>
+ * @remark Copyright 2004 Intel Corporation
+ * @remark Copyright 2004 Zwane Mwaikambo <zwane@arm.linux.org.uk>
+ * @remark Copyright 2004 Oprofile Authors
+ *
+ * @remark Read the file COPYING
+ *
+ * @author Zwane Mwaikambo
+ *
+ *  Counters:
+ *    0: PMN0 on CPU0, per-cpu configurable event counter
+ *    1: PMN1 on CPU0, per-cpu configurable event counter
+ *    2: CCNT on CPU0
+ *    3: PMN0 on CPU1
+ *    4: PMN1 on CPU1
+ *    5: CCNT on CPU1
+ *    6: PMN0 on CPU1
+ *    7: PMN1 on CPU1
+ *    8: CCNT on CPU1
+ *    9: PMN0 on CPU1
+ *   10: PMN1 on CPU1
+ *   11: CCNT on CPU1
+ *   12-19: configurable SCU event counters
+ */
+
+/* #define DEBUG */
+#include <linux/types.h>
+#include <linux/errno.h>
+#include <linux/sched.h>
+#include <linux/oprofile.h>
+#include <linux/interrupt.h>
+#include <linux/smp.h>
+
+#include <asm/io.h>
+#include <asm/irq.h>
+#include <asm/mach/irq.h>
+#include <asm/hardware.h>
+#include <asm/system.h>
+
+#include "op_counter.h"
+#include "op_arm_model.h"
+#include "op_model_arm11_core.h"
+#include "op_model_mpcore.h"
+
+/*
+ * MPCore SCU event monitor support
+ */
+#define SCU_EVENTMONITORS_VA_BASE __io_address(REALVIEW_MPCORE_SCU_BASE + 0x10)
+
+/*
+ * Bitmask of used SCU counters
+ */
+static unsigned int scu_em_used;
+
+/*
+ * 2 helper fns take a counter number from 0-7 (not the userspace-visible counter number)
+ */
+static inline void scu_reset_counter(struct eventmonitor __iomem *emc, unsigned int n)
+{
+	writel(-(u32)counter_config[SCU_COUNTER(n)].count, &emc->MC[n]);
+}
+
+static inline void scu_set_event(struct eventmonitor __iomem *emc, unsigned int n, u32 event)
+{
+	event &= 0xff;
+	writeb(event, &emc->MCEB[n]);
+}
+
+/*
+ * SCU counters' IRQ handler (one IRQ per counter => 2 IRQs per CPU)
+ */
+static irqreturn_t scu_em_interrupt(int irq, void *arg)
+{
+	struct eventmonitor __iomem *emc = SCU_EVENTMONITORS_VA_BASE;
+	unsigned int cnt;
+
+	cnt = irq - IRQ_PMU_SCU0;
+	oprofile_add_sample(get_irq_regs(), SCU_COUNTER(cnt));
+	scu_reset_counter(emc, cnt);
+
+	/* Clear overflow flag for this counter */
+	writel(1 << (cnt + 16), &emc->PMCR);
+
+	return IRQ_HANDLED;
+}
+
+/* Configure just the SCU counters that the user has requested */
+static void scu_setup(void)
+{
+	struct eventmonitor __iomem *emc = SCU_EVENTMONITORS_VA_BASE;
+	unsigned int i;
+
+	scu_em_used = 0;
+
+	for (i = 0; i < NUM_SCU_COUNTERS; i++) {
+		if (counter_config[SCU_COUNTER(i)].enabled &&
+		    counter_config[SCU_COUNTER(i)].event) {
+			scu_set_event(emc, i, 0); /* disable counter for now */
+			scu_em_used |= 1 << i;
+		}
+	}
+}
+
+static int scu_start(void)
+{
+	struct eventmonitor __iomem *emc = SCU_EVENTMONITORS_VA_BASE;
+	unsigned int temp, i;
+	unsigned long event;
+	int ret = 0;
+
+	/*
+	 * request the SCU counter interrupts that we need
+	 */
+	for (i = 0; i < NUM_SCU_COUNTERS; i++) {
+		if (scu_em_used & (1 << i)) {
+			ret = request_irq(IRQ_PMU_SCU0 + i, scu_em_interrupt, IRQF_DISABLED, "SCU PMU", NULL);
+			if (ret) {
+				printk(KERN_ERR "oprofile: unable to request IRQ%u for SCU Event Monitor\n",
+				       IRQ_PMU_SCU0 + i);
+				goto err_free_scu;
+			}
+		}
+	}
+
+	/*
+	 * clear overflow and enable interrupt for all used counters
+	 */
+	temp = readl(&emc->PMCR);
+	for (i = 0; i < NUM_SCU_COUNTERS; i++) {
+		if (scu_em_used & (1 << i)) {
+			scu_reset_counter(emc, i);
+			event = counter_config[SCU_COUNTER(i)].event;
+			scu_set_event(emc, i, event);
+
+			/* clear overflow/interrupt */
+			temp |= 1 << (i + 16);
+			/* enable interrupt*/
+			temp |= 1 << (i + 8);
+		}
+	}
+
+	/* Enable all 8 counters */
+	temp |= PMCR_E;
+	writel(temp, &emc->PMCR);
+
+	return 0;
+
+ err_free_scu:
+	while (i--)
+		free_irq(IRQ_PMU_SCU0 + i, NULL);
+	return ret;
+}
+
+static void scu_stop(void)
+{
+	struct eventmonitor __iomem *emc = SCU_EVENTMONITORS_VA_BASE;
+	unsigned int temp, i;
+
+	/* Disable counter interrupts */
+	/* Don't disable all 8 counters (with the E bit) as they may be in use */
+	temp = readl(&emc->PMCR);
+	for (i = 0; i < NUM_SCU_COUNTERS; i++) {
+		if (scu_em_used & (1 << i))
+			temp &= ~(1 << (i + 8));
+	}
+	writel(temp, &emc->PMCR);
+
+	/* Free counter interrupts and reset counters */
+	for (i = 0; i < NUM_SCU_COUNTERS; i++) {
+		if (scu_em_used & (1 << i)) {
+			scu_reset_counter(emc, i);
+			free_irq(IRQ_PMU_SCU0 + i, NULL);
+		}
+	}
+}
+
+struct em_function_data {
+	int (*fn)(void);
+	int ret;
+};
+
+static void em_func(void *data)
+{
+	struct em_function_data *d = data;
+	int ret = d->fn();
+	if (ret)
+		d->ret = ret;
+}
+
+static int em_call_function(int (*fn)(void))
+{
+	struct em_function_data data;
+
+	data.fn = fn;
+	data.ret = 0;
+
+	smp_call_function(em_func, &data, 1, 1);
+	em_func(&data);
+
+	return data.ret;
+}
+
+/*
+ * Glue to stick the individual ARM11 PMUs and the SCU
+ * into the oprofile framework.
+ */
+static int em_setup_ctrs(void)
+{
+	int ret;
+
+	/* Configure CPU counters by cross-calling to the other CPUs */
+	ret = em_call_function(arm11_setup_pmu);
+	if (ret == 0)
+		scu_setup();
+
+	return 0;
+}
+
+static int arm11_irqs[] = {
+	[0]	= IRQ_PMU_CPU0,
+	[1]	= IRQ_PMU_CPU1,
+	[2]	= IRQ_PMU_CPU2,
+	[3]	= IRQ_PMU_CPU3
+};
+
+static int em_start(void)
+{
+	int ret;
+
+	ret = arm11_request_interrupts(arm11_irqs, ARRAY_SIZE(arm11_irqs));
+	if (ret == 0) {
+		em_call_function(arm11_start_pmu);
+
+		ret = scu_start();
+		if (ret)
+			arm11_release_interrupts(arm11_irqs, ARRAY_SIZE(arm11_irqs));
+	}
+	return ret;
+}
+
+static void em_stop(void)
+{
+	em_call_function(arm11_stop_pmu);
+	arm11_release_interrupts(arm11_irqs, ARRAY_SIZE(arm11_irqs));
+	scu_stop();
+}
+
+/*
+ * Why isn't there a function to route an IRQ to a specific CPU in
+ * genirq?
+ */
+static void em_route_irq(int irq, unsigned int cpu)
+{
+	irq_desc[irq].affinity = cpumask_of_cpu(cpu);
+	irq_desc[irq].chip->set_affinity(irq, cpumask_of_cpu(cpu));
+}
+
+static int em_setup(void)
+{
+	/*
+	 * Send SCU PMU interrupts to the "owner" CPU.
+	 */
+	em_route_irq(IRQ_PMU_SCU0, 0);
+	em_route_irq(IRQ_PMU_SCU1, 0);
+	em_route_irq(IRQ_PMU_SCU2, 1);
+	em_route_irq(IRQ_PMU_SCU3, 1);
+	em_route_irq(IRQ_PMU_SCU4, 2);
+	em_route_irq(IRQ_PMU_SCU5, 2);
+	em_route_irq(IRQ_PMU_SCU6, 3);
+	em_route_irq(IRQ_PMU_SCU7, 3);
+
+	/*
+	 * Send CP15 PMU interrupts to the owner CPU.
+	 */
+	em_route_irq(IRQ_PMU_CPU0, 0);
+	em_route_irq(IRQ_PMU_CPU1, 1);
+	em_route_irq(IRQ_PMU_CPU2, 2);
+	em_route_irq(IRQ_PMU_CPU3, 3);
+
+	return 0;
+}
+
+struct op_arm_model_spec op_mpcore_spec = {
+	.init		= em_setup,
+	.num_counters	= MPCORE_NUM_COUNTERS,
+	.setup_ctrs	= em_setup_ctrs,
+	.start		= em_start,
+	.stop		= em_stop,
+	.name		= "arm/mpcore",
+};

arch/arm/oprofile/op_model_mpcore.h

+/**
+ * @file op_model_mpcore.c
+ * MPCORE Event Monitor Driver
+ * @remark Copyright 2004 ARM SMP Development Team
+ * @remark Copyright 2000-2004 Deepak Saxena <dsaxena@mvista.com>
+ * @remark Copyright 2000-2004 MontaVista Software Inc
+ * @remark Copyright 2004 Dave Jiang <dave.jiang@intel.com>
+ * @remark Copyright 2004 Intel Corporation
+ * @remark Copyright 2004 Zwane Mwaikambo <zwane@arm.linux.org.uk>
+ * @remark Copyright 2004 Oprofile Authors
+ *
+ * @remark Read the file COPYING
+ *
+ * @author Zwane Mwaikambo
+ */
+#ifndef OP_MODEL_MPCORE_H
+#define OP_MODEL_MPCORE_H
+
+struct eventmonitor {
+	unsigned long PMCR;
+	unsigned char MCEB[8];
+	unsigned long MC[8];
+};
+
+/*
+ * List of userspace counter numbers: note that the structure is important.
+ * The code relies on CPUn's counters being CPU0's counters + 3n
+ * and on CPU0's counters starting at 0
+ */
+
+#define COUNTER_CPU0_PMN0 0
+#define COUNTER_CPU0_PMN1 1
+#define COUNTER_CPU0_CCNT 2
+
+#define COUNTER_CPU1_PMN0 3
+#define COUNTER_CPU1_PMN1 4
+#define COUNTER_CPU1_CCNT 5
+
+#define COUNTER_CPU2_PMN0 6
+#define COUNTER_CPU2_PMN1 7
+#define COUNTER_CPU2_CCNT 8
+
+#define COUNTER_CPU3_PMN0 9
+#define COUNTER_CPU3_PMN1 10
+#define COUNTER_CPU3_CCNT 11
+
+#define COUNTER_SCU_MN0 12
+#define COUNTER_SCU_MN1 13
+#define COUNTER_SCU_MN2 14
+#define COUNTER_SCU_MN3 15
+#define COUNTER_SCU_MN4 16
+#define COUNTER_SCU_MN5 17
+#define COUNTER_SCU_MN6 18
+#define COUNTER_SCU_MN7 19
+#define NUM_SCU_COUNTERS 8
+
+#define SCU_COUNTER(number)	((number) + COUNTER_SCU_MN0)
+
+#define MPCORE_NUM_COUNTERS	SCU_COUNTER(NUM_SCU_COUNTERS)
+
+#endif

include/asm-arm/arch-realview/irqs.h

@@ -65,6 +65,18 @@
 #define IRQ_AACI		(IRQ_GIC_START + INT_AACI)
 #define IRQ_ETH			(IRQ_GIC_START + INT_ETH)
 #define IRQ_USB			(IRQ_GIC_START + INT_USB)
+#define IRQ_PMU_CPU0		(IRQ_GIC_START + INT_PMU_CPU0)
+#define IRQ_PMU_CPU1		(IRQ_GIC_START + INT_PMU_CPU1)
+#define IRQ_PMU_CPU2		(IRQ_GIC_START + INT_PMU_CPU2)
+#define IRQ_PMU_CPU3		(IRQ_GIC_START + INT_PMU_CPU3)
+#define IRQ_PMU_SCU0		(IRQ_GIC_START + INT_PMU_SCU0)
+#define IRQ_PMU_SCU1		(IRQ_GIC_START + INT_PMU_SCU1)
+#define IRQ_PMU_SCU2		(IRQ_GIC_START + INT_PMU_SCU2)
+#define IRQ_PMU_SCU3		(IRQ_GIC_START + INT_PMU_SCU3)
+#define IRQ_PMU_SCU4		(IRQ_GIC_START + INT_PMU_SCU4)
+#define IRQ_PMU_SCU5		(IRQ_GIC_START + INT_PMU_SCU5)
+#define IRQ_PMU_SCU6		(IRQ_GIC_START + INT_PMU_SCU6)
+#define IRQ_PMU_SCU7		(IRQ_GIC_START + INT_PMU_SCU7)
 
 #define IRQMASK_WDOGINT		INTMASK_WDOGINT
 #define IRQMASK_SOFTINT		INTMASK_SOFTINT