[PATCH v6 00/11] Enable PMUs in ACPI systems

@@ -24,6 +24,7 @@
 #include <asm/sysreg.h>
 #include <asm/virt.h>
 
+#include <linux/acpi.h>
 #include <linux/of.h>
 #include <linux/perf/arm_pmu.h>
 #include <linux/platform_device.h>

@@ -1044,9 +1045,19 @@ static const struct of_device_id armv8_pmu_of_device_ids[] = {
 	{},
 };
 
+static const struct pmu_probe_info armv8_pmu_probe_table[] = {
+	PMU_PROBE(0, 0, armv8_pmuv3_init), /* if all else fails... */
+	{ /* sentinel value */ }
+};
+
 static int armv8_pmu_device_probe(struct platform_device *pdev)
 {
-	return arm_pmu_device_probe(pdev, armv8_pmu_of_device_ids, NULL);
+	if (acpi_disabled)
+		return arm_pmu_device_probe(pdev, armv8_pmu_of_device_ids,
+					    NULL);
+
+	return arm_pmu_device_probe(pdev, armv8_pmu_of_device_ids,
+				    armv8_pmu_probe_table);
 }
 
 static struct platform_driver armv8_pmu_driver = {

@@ -1009,7 +1009,7 @@ int arm_pmu_device_probe(struct platform_device *pdev,
 		ret = of_pmu_irq_cfg(pmu);
 		if (!ret)
 			ret = init_fn(pmu);
-	} else {
+	} else if (probe_table) {
 		cpumask_setall(&pmu->supported_cpus);
 		ret = probe_current_pmu(pmu, probe_table);
 	}

@@ -147,6 +147,9 @@ struct pmu_probe_info {
 #define XSCALE_PMU_PROBE(_version, _fn) \
 	PMU_PROBE(ARM_CPU_IMP_INTEL << 24 | _version, ARM_PMU_XSCALE_MASK, _fn)
 
+#define ARMV8_PMU_PART_PROBE(_part, _fn) \
+	PMU_PROBE((_part) << MIDR_PARTNUM_SHIFT, MIDR_PARTNUM_MASK, _fn)
+
 int arm_pmu_device_probe(struct platform_device *pdev,
 			 const struct of_device_id *of_table,
 			 const struct pmu_probe_info *probe_table);

@@ -191,13 +191,23 @@
 #define ARMV8_THUNDER_PERFCTR_L1I_CACHE_PREF_MISS		0xED
 
 /* PMUv3 HW events mapping. */
+
+/*
+ * ARMv8 Architectural defined events, not all of these may
+ * be supported on any given implementation. Undefined events will
+ * be disabled at run-time.
+ */
 static const unsigned armv8_pmuv3_perf_map[PERF_COUNT_HW_MAX] = {
 	PERF_MAP_ALL_UNSUPPORTED,
 	[PERF_COUNT_HW_CPU_CYCLES]		= ARMV8_PMUV3_PERFCTR_CPU_CYCLES,
 	[PERF_COUNT_HW_INSTRUCTIONS]		= ARMV8_PMUV3_PERFCTR_INST_RETIRED,
 	[PERF_COUNT_HW_CACHE_REFERENCES]	= ARMV8_PMUV3_PERFCTR_L1D_CACHE,
 	[PERF_COUNT_HW_CACHE_MISSES]		= ARMV8_PMUV3_PERFCTR_L1D_CACHE_REFILL,
+	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= ARMV8_PMUV3_PERFCTR_PC_WRITE_RETIRED,
 	[PERF_COUNT_HW_BRANCH_MISSES]		= ARMV8_PMUV3_PERFCTR_BR_MIS_PRED,
+	[PERF_COUNT_HW_BUS_CYCLES]		= ARMV8_PMUV3_PERFCTR_BUS_CYCLES,
+	[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND]	= ARMV8_PMUV3_PERFCTR_STALL_FRONTEND,
+	[PERF_COUNT_HW_STALLED_CYCLES_BACKEND]	= ARMV8_PMUV3_PERFCTR_STALL_BACKEND,
 };
 
 /* ARM Cortex-A53 HW events mapping. */

@@ -259,6 +269,15 @@ static const unsigned armv8_pmuv3_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
 	[C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)]	= ARMV8_PMUV3_PERFCTR_L1D_CACHE,
 	[C(L1D)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV8_PMUV3_PERFCTR_L1D_CACHE_REFILL,
 
+	[C(L1I)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV8_PMUV3_PERFCTR_L1I_CACHE,
+	[C(L1I)][C(OP_READ)][C(RESULT_MISS)]	= ARMV8_PMUV3_PERFCTR_L1I_CACHE_REFILL,
+
+	[C(DTLB)][C(OP_READ)][C(RESULT_MISS)]	= ARMV8_PMUV3_PERFCTR_L1D_TLB_REFILL,
+	[C(DTLB)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV8_PMUV3_PERFCTR_L1D_TLB,
+
+	[C(ITLB)][C(OP_READ)][C(RESULT_MISS)]	= ARMV8_PMUV3_PERFCTR_L1I_TLB_REFILL,
+	[C(ITLB)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV8_PMUV3_PERFCTR_L1I_TLB,
+
 	[C(BPU)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV8_PMUV3_PERFCTR_BR_PRED,
 	[C(BPU)][C(OP_READ)][C(RESULT_MISS)]	= ARMV8_PMUV3_PERFCTR_BR_MIS_PRED,
 	[C(BPU)][C(OP_WRITE)][C(RESULT_ACCESS)]	= ARMV8_PMUV3_PERFCTR_BR_PRED,

@@ -906,9 +925,22 @@ static void armv8pmu_reset(void *info)
 
 static int armv8_pmuv3_map_event(struct perf_event *event)
 {
-	return armpmu_map_event(event, &armv8_pmuv3_perf_map,
-				&armv8_pmuv3_perf_cache_map,
-				ARMV8_PMU_EVTYPE_EVENT);
+	int hw_event_id;
+	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
+
+	hw_event_id = armpmu_map_event(event, &armv8_pmuv3_perf_map,
+				       &armv8_pmuv3_perf_cache_map,
+				       ARMV8_PMU_EVTYPE_EVENT);
+	if (hw_event_id < 0)
+		return hw_event_id;
+
+	/* disable micro/arch events not supported by this PMU */
+	if ((hw_event_id < ARMV8_PMUV3_MAX_COMMON_EVENTS) &&
+		!test_bit(hw_event_id, armpmu->pmceid_bitmap)) {
+			return -EOPNOTSUPP;
+	}
+
+	return hw_event_id;
 }
 
 static int armv8_a53_map_event(struct perf_event *event)

@@ -1045,8 +1077,13 @@ static const struct of_device_id armv8_pmu_of_device_ids[] = {
 	{},
 };
 
+/*
+ * Non DT systems have their micro/arch events probed at run-time.
+ * A fairly complete list of generic events are provided and ones that
+ * aren't supported by the current PMU are disabled.
+ */
 static const struct pmu_probe_info armv8_pmu_probe_table[] = {
-	PMU_PROBE(0, 0, armv8_pmuv3_init), /* if all else fails... */
+	PMU_PROBE(0, 0, armv8_pmuv3_init), /* enable all defined counters */
 	{ /* sentinel value */ }
 };
 

@@ -1099,7 +1099,7 @@ static int armv8_pmu_device_probe(struct platform_device *pdev)
 
 static struct platform_driver armv8_pmu_driver = {
 	.driver		= {
-		.name	= "armv8-pmu",
+		.name	= ARMV8_PMU_PDEV_NAME,
 		.of_match_table = armv8_pmu_of_device_ids,
 	},
 	.probe		= armv8_pmu_device_probe,

@@ -154,6 +154,8 @@ int arm_pmu_device_probe(struct platform_device *pdev,
 			 const struct of_device_id *of_table,
 			 const struct pmu_probe_info *probe_table);
 
+#define ARMV8_PMU_PDEV_NAME "armv8-pmu"
+
 #endif /* CONFIG_ARM_PMU */
 
 #endif /* __ARM_PMU_H__ */

@@ -507,13 +507,14 @@ static unsigned int cpu_count = 1;
 
 #ifdef CONFIG_ACPI
 /*
- * acpi_map_gic_cpu_interface - parse processor MADT entry
+ * acpi_verify_and_map_madt - parse processor MADT entry
  *
  * Carry out sanity checks on MADT processor entry and initialize
- * cpu_logical_map on success
+ * cpu_logical_map, the ACPI parking protocol, NUMA mapping
+ * and the PMU interrupts on success
  */
 static void __init
-acpi_map_gic_cpu_interface(struct acpi_madt_generic_interrupt *processor)
+acpi_verify_and_map_madt(struct acpi_madt_generic_interrupt *processor)
 {
 	u64 hwid = processor->arm_mpidr;
 

@@ -566,7 +567,7 @@ acpi_map_gic_cpu_interface(struct acpi_madt_generic_interrupt *processor)
 }
 
 static int __init
-acpi_parse_gic_cpu_interface(struct acpi_subtable_header *header,
+acpi_parse_madt_common(struct acpi_subtable_header *header,
 			     const unsigned long end)
 {
 	struct acpi_madt_generic_interrupt *processor;

@@ -577,7 +578,7 @@ acpi_parse_gic_cpu_interface(struct acpi_subtable_header *header,
 
 	acpi_table_print_madt_entry(header);
 
-	acpi_map_gic_cpu_interface(processor);
+	acpi_verify_and_map_madt(processor);
 
 	return 0;
 }

@@ -660,7 +661,7 @@ void __init smp_init_cpus(void)
 		 * we need for SMP init
 		 */
 		acpi_table_parse_madt(ACPI_MADT_TYPE_GENERIC_INTERRUPT,
-				      acpi_parse_gic_cpu_interface, 0);
+				      acpi_parse_madt_common, 0);
 
 	if (cpu_count > NR_CPUS)
 		pr_warn("no. of cores (%d) greater than configured maximum of %d - clipping\n",

@@ -37,6 +37,7 @@
 #include <linux/completion.h>
 #include <linux/of.h>
 #include <linux/irq_work.h>
+#include <linux/perf/arm_pmu.h>
 
 #include <asm/alternative.h>
 #include <asm/atomic.h>

@@ -541,6 +542,7 @@ acpi_verify_and_map_madt(struct acpi_madt_generic_interrupt *processor)
 			return;
 		}
 		bootcpu_valid = true;
+		arm_pmu_parse_acpi(0, processor);
 		return;
 	}
 

@@ -561,6 +563,9 @@ acpi_verify_and_map_madt(struct acpi_madt_generic_interrupt *processor)
 	 */
 	acpi_set_mailbox_entry(cpu_count, processor);
 
+	/* get PMU irq info */
+	arm_pmu_parse_acpi(cpu_count, processor);
+
 	early_map_cpu_to_node(cpu_count, acpi_numa_get_nid(cpu_count, hwid));
 
 	cpu_count++;

@@ -12,4 +12,8 @@ config ARM_PMU
 	  Say y if you want to use CPU performance monitors on ARM-based
 	  systems.
 
+config ARM_PMU_ACPI
+	def_bool y
+	depends on ARM_PMU && ACPI
+
 endmenu

@@ -1 +1,2 @@
 obj-$(CONFIG_ARM_PMU) += arm_pmu.o
+obj-$(CONFIG_ARM_PMU_ACPI) += arm_pmu_acpi.o

@@ -0,0 +1,100 @@
+/*
+ * PMU support
+ *
+ * Copyright (C) 2015 Red Hat Inc.
+ * Author: Mark Salter <msalter@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.  See
+ * the COPYING file in the top-level directory.
+ *
+ */
+
+#include <linux/perf/arm_pmu.h>
+#include <linux/platform_device.h>
+#include <linux/acpi.h>
+#include <linux/irq.h>
+#include <linux/irqdesc.h>
+
+struct pmu_irq {
+	int gsi;
+	int trigger;
+};
+
+static struct pmu_irq pmu_irqs[NR_CPUS] __initdata;
+
+/*
+ * Called from acpi_map_gic_cpu_interface()'s MADT parsing during boot.
+ * This routine saves off the GSI's and their trigger state for use when we are
+ * ready to build the PMU platform device.
+*/
+void __init arm_pmu_parse_acpi(int cpu, struct acpi_madt_generic_interrupt *gic)
+{
+	pmu_irqs[cpu].gsi = gic->performance_interrupt;
+	if (gic->flags & ACPI_MADT_PERFORMANCE_IRQ_MODE)
+		pmu_irqs[cpu].trigger = ACPI_EDGE_SENSITIVE;
+	else
+		pmu_irqs[cpu].trigger = ACPI_LEVEL_SENSITIVE;
+}
+
+static int __init pmu_acpi_init(void)
+{
+	struct platform_device *pdev;
+	struct pmu_irq *pirq = pmu_irqs;
+	struct resource	*res, *r;
+	int err = -ENOMEM;
+	int i, count, irq;
+
+	if (acpi_disabled)
+		return 0;
+
+	/* Must have irq for boot cpu, at least */
+	if (pirq->gsi == 0)
+		return -EINVAL;
+
+	irq = acpi_register_gsi(NULL, pirq->gsi, pirq->trigger,
+				ACPI_ACTIVE_HIGH);
+
+	if (irq_is_percpu(irq))
+		count = 1;
+	else
+		for (i = 1, count = 1; i < NR_CPUS; i++)
+			if (pmu_irqs[i].gsi)
+				++count;
+
+	pdev = platform_device_alloc(ARMV8_PMU_PDEV_NAME, -1);
+	if (!pdev)
+		goto err_free_gsi;
+
+	res = kcalloc(count, sizeof(*res), GFP_KERNEL);
+	if (!res)
+		goto err_free_device;
+
+	for (i = 0, r = res; i < count; i++, pirq++, r++) {
+		if (i)
+			irq = acpi_register_gsi(NULL, pirq->gsi, pirq->trigger,
+						ACPI_ACTIVE_HIGH);
+		r->start = r->end = irq;
+		r->flags = IORESOURCE_IRQ;
+		if (pirq->trigger == ACPI_EDGE_SENSITIVE)
+			r->flags |= IORESOURCE_IRQ_HIGHEDGE;
+		else
+			r->flags |= IORESOURCE_IRQ_HIGHLEVEL;
+	}
+
+	err = platform_device_add_resources(pdev, res, count);
+	if (!err)
+		err = platform_device_add(pdev);
+	kfree(res);
+	if (!err)
+		return 0;
+
+err_free_device:
+	platform_device_put(pdev);
+
+err_free_gsi:
+	for (i = 0; i < count; i++)
+		acpi_unregister_gsi(pmu_irqs[i].gsi);
+
+	return err;
+}
+arch_initcall(pmu_acpi_init);

@@ -158,4 +158,11 @@ int arm_pmu_device_probe(struct platform_device *pdev,
 
 #endif /* CONFIG_ARM_PMU */
 
+#ifdef CONFIG_ARM_PMU_ACPI
+struct acpi_madt_generic_interrupt;
+void arm_pmu_parse_acpi(int cpu, struct acpi_madt_generic_interrupt *gic);
+#else
+#define arm_pmu_parse_acpi(a, b) do { } while (0)
+#endif /* CONFIG_ARM_PMU_ACPI */
+
 #endif /* __ARM_PMU_H__ */

@@ -81,6 +81,8 @@
 #define ARM_CPU_XSCALE_ARCH_V2		0x4000
 #define ARM_CPU_XSCALE_ARCH_V3		0x6000
 
+#define ARM_PARTNUM(cpuid_id) (cpuid_id & ARM_CPU_PART_MASK)
+
 extern unsigned int processor_id;
 
 #ifdef CONFIG_CPU_CP15

@@ -180,7 +182,7 @@ static inline unsigned int __attribute_const__ read_cpuid_implementor(void)
  */
 static inline unsigned int __attribute_const__ read_cpuid_part(void)
 {
-	return read_cpuid_id() & ARM_CPU_PART_MASK;
+	return ARM_PARTNUM(read_cpuid_id());
 }
 
 static inline unsigned int __attribute_const__ __deprecated read_cpuid_part_number(void)

@@ -208,6 +210,8 @@ static inline unsigned int __attribute_const__ read_cpuid_mpidr(void)
 	return read_cpuid(CPUID_MPIDR);
 }
 
+#define read_specific_cpuid(cpu_num) per_cpu_ptr(&cpu_data, cpu_num)->cpuid
+
 /*
  * Intel's XScale3 core supports some v6 features (supersections, L2)
  * but advertises itself as v5 as it does not support the v6 ISA.  For

@@ -38,6 +38,7 @@
 #define MIDR_PARTNUM_MASK	(0xfff << MIDR_PARTNUM_SHIFT)
 #define MIDR_PARTNUM(midr)	\
 	(((midr) & MIDR_PARTNUM_MASK) >> MIDR_PARTNUM_SHIFT)
+#define ARM_PARTNUM MIDR_PARTNUM
 #define MIDR_ARCHITECTURE_SHIFT	16
 #define MIDR_ARCHITECTURE_MASK	(0xf << MIDR_ARCHITECTURE_SHIFT)
 #define MIDR_ARCHITECTURE(midr)	\

@@ -126,6 +127,9 @@ static inline u32 __attribute_const__ read_cpuid_cachetype(void)
 {
 	return read_cpuid(CTR_EL0);
 }
+
+#define read_specific_cpuid(cpu_num) per_cpu_ptr(&cpu_data, cpu_num)->reg_midr
+
 #endif /* __ASSEMBLY__ */
 
 #endif

@@ -11,6 +11,7 @@
  */
 #define pr_fmt(fmt) "hw perfevents: " fmt
 
+#include <linux/acpi.h>
 #include <linux/bitmap.h>
 #include <linux/cpumask.h>
 #include <linux/cpu_pm.h>

@@ -24,6 +25,7 @@
 #include <linux/irq.h>
 #include <linux/irqdesc.h>
 
+#include <asm/cpu.h>
 #include <asm/cputype.h>
 #include <asm/irq_regs.h>
 

@@ -872,25 +874,57 @@ static void cpu_pmu_destroy(struct arm_pmu *cpu_pmu)
 }
 
 /*
- * CPU PMU identification and probing.
+ * CPU PMU identification and probing. Its possible to have
+ * multiple CPU types in an ARM machine. Assure that we are
+ * picking the right PMU types based on the CPU in question
  */
-static int probe_current_pmu(struct arm_pmu *pmu,
-			     const struct pmu_probe_info *info)
+static int probe_plat_pmu(struct arm_pmu *pmu,
+			     const struct pmu_probe_info *info,
+			     unsigned int pmuid)
 {
-	int cpu = get_cpu();
-	unsigned int cpuid = read_cpuid_id();
 	int ret = -ENODEV;
+	int cpu;
+	int aff_ctr = 0;
+	static int duplicate_pmus;
+	struct platform_device *pdev = pmu->plat_device;
+	int irq = platform_get_irq(pdev, 0);
+
+	if (irq >= 0 && !irq_is_percpu(irq)) {
+		pmu->irq_affinity = kcalloc(pdev->num_resources, sizeof(int),
+					    GFP_KERNEL);
+		if (!pmu->irq_affinity)
+			return -ENOMEM;
+	}
+
+	for_each_possible_cpu(cpu) {
+		unsigned int cpuid = read_specific_cpuid(cpu);
 
-	pr_info("probing PMU on CPU %d\n", cpu);
+		if (cpuid == pmuid) {
+			cpumask_set_cpu(cpu, &pmu->supported_cpus);
+			if (pmu->irq_affinity) {
+				pmu->irq_affinity[aff_ctr] = cpu;
+				aff_ctr++;
+			}
+		}
+	}
 
+	/* find the type of PMU given the CPU */
 	for (; info->init != NULL; info++) {
-		if ((cpuid & info->mask) != info->cpuid)
+		if ((pmuid & info->mask) != info->cpuid)
 			continue;
 		ret = info->init(pmu);
+		if ((!info->cpuid) && (duplicate_pmus)) {
+			pmu->name = kasprintf(GFP_KERNEL, "%s_%d",
+					    pmu->name, duplicate_pmus);
+			if (!pmu->name) {
+				kfree(pmu->irq_affinity);
+				ret = -ENOMEM;
+			}
+		}
+		duplicate_pmus++;
 		break;
 	}
 
-	put_cpu();
 	return ret;
 }
 

@@ -1010,8 +1044,7 @@ int arm_pmu_device_probe(struct platform_device *pdev,
 		if (!ret)
 			ret = init_fn(pmu);
 	} else if (probe_table) {
-		cpumask_setall(&pmu->supported_cpus);
-		ret = probe_current_pmu(pmu, probe_table);
+		ret = probe_plat_pmu(pmu, probe_table, read_cpuid_id());
 	}
 
 	if (ret) {

@@ -533,6 +533,26 @@ static struct attribute_group armv8_pmuv3_events_attr_group = {
 
 PMU_FORMAT_ATTR(event, "config:0-9");
 
+static ssize_t
+cpumask_show(struct device *dev, struct device_attribute *attr, char *page)
+{
+	struct pmu *pmu = dev_get_drvdata(dev);
+	struct arm_pmu *cpu_pmu = container_of(pmu, struct arm_pmu, pmu);
+
+	return cpumap_print_to_pagebuf(true, page, &cpu_pmu->supported_cpus);
+}
+static DEVICE_ATTR_RO(cpumask);
+
+static struct attribute *armv8_pmuv3_attrs[] = {
+	 &dev_attr_cpumask.attr,
+	 NULL,
+};
+
+static struct attribute_group armv8_pmuv3_attr_group = {
+	.attrs = armv8_pmuv3_attrs,
+};
+
+
 static struct attribute *armv8_pmuv3_format_attrs[] = {
 	&format_attr_event.attr,
 	NULL,

@@ -544,6 +564,7 @@ static struct attribute_group armv8_pmuv3_format_attr_group = {
 };
 
 static const struct attribute_group *armv8_pmuv3_attr_groups[] = {
+	&armv8_pmuv3_attr_group,
 	&armv8_pmuv3_events_attr_group,
 	&armv8_pmuv3_format_attr_group,
 	NULL,

@@ -1,23 +1,36 @@
 /*
- * PMU support
+ * ARM ACPI PMU support
  *
  * Copyright (C) 2015 Red Hat Inc.
+ * Copyright (C) 2016 ARM Ltd.
  * Author: Mark Salter <msalter@redhat.com>
+ *         Jeremy Linton <jeremy.linton@arm.com>
  *
  * This work is licensed under the terms of the GNU GPL, version 2.  See
  * the COPYING file in the top-level directory.
  *
  */
 
+#define pr_fmt(fmt) "ACPI-PMU: " fmt
+
+#include <asm/cpu.h>
 #include <linux/perf/arm_pmu.h>
 #include <linux/platform_device.h>
 #include <linux/acpi.h>
 #include <linux/irq.h>
 #include <linux/irqdesc.h>
+#include <linux/list.h>
 
 struct pmu_irq {
-	int gsi;
-	int trigger;
+	int  gsi;
+	int  trigger;
+	bool registered;
+};
+
+struct pmu_types {
+	struct list_head list;
+	int		 cpu_type;
+	int		 cpu_count;
 };
 
 static struct pmu_irq pmu_irqs[NR_CPUS] __initdata;

@@ -36,6 +49,124 @@ void __init arm_pmu_parse_acpi(int cpu, struct acpi_madt_generic_interrupt *gic)
 		pmu_irqs[cpu].trigger = ACPI_LEVEL_SENSITIVE;
 }
 
+/* Count number and type of CPU cores in the system. */
+void __init arm_pmu_acpi_determine_cpu_types(struct list_head *pmus)
+{
+	int i;
+
+	for_each_possible_cpu(i) {
+		struct cpuinfo_arm64 *cinfo = per_cpu_ptr(&cpu_data, i);
+		u32 partnum = MIDR_PARTNUM(cinfo->reg_midr);
+		struct pmu_types *pmu;
+
+		list_for_each_entry(pmu, pmus, list) {
+			if (pmu->cpu_type == partnum) {
+				pmu->cpu_count++;
+				break;
+			}
+		}
+
+		/* we didn't find the CPU type, add an entry to identify it */
+		if (&pmu->list == pmus) {
+			pmu = kcalloc(1, sizeof(struct pmu_types), GFP_KERNEL);
+			if (!pmu) {
+				pr_warn("Unable to allocate pmu_types\n");
+			} else {
+				pmu->cpu_type = partnum;
+				pmu->cpu_count++;
+				list_add_tail(&pmu->list, pmus);
+			}
+		}
+	}
+}
+
+/*
+ * Registers the group of PMU interfaces which correspond to the 'last_cpu_id'.
+ * This group utilizes 'count' resources in the 'res'.
+ */
+int __init arm_pmu_acpi_register_pmu(int count, struct resource *res,
+					    int last_cpu_id)
+{
+	int i;
+	int err = -ENOMEM;
+	bool free_gsi = false;
+	struct platform_device *pdev;
+
+	if (count) {
+		pdev = platform_device_alloc(ARMV8_PMU_PDEV_NAME, last_cpu_id);
+		if (pdev) {
+			err = platform_device_add_resources(pdev, res, count);
+			if (!err) {
+				err = platform_device_add(pdev);
+				if (err) {
+					pr_warn("Unable to register PMU device\n");
+					free_gsi = true;
+				}
+			} else {
+				pr_warn("Unable to add resources to device\n");
+				free_gsi = true;
+				platform_device_put(pdev);
+			}
+		} else {
+			pr_warn("Unable to allocate platform device\n");
+			free_gsi = true;
+		}
+	}
+
+	/* unmark (and possibly unregister) registered GSIs */
+	for_each_possible_cpu(i) {
+		if (pmu_irqs[i].registered) {
+			if (free_gsi)
+				acpi_unregister_gsi(pmu_irqs[i].gsi);
+			pmu_irqs[i].registered = false;
+		}
+	}
+
+	return err;
+}
+
+/*
+ * For the given cpu/pmu type, walk all known GSIs, register them, and add
+ * them to the resource structure. Return the number of GSI's contained
+ * in the res structure, and the id of the last CPU/PMU we added.
+ */
+int __init arm_pmu_acpi_gsi_res(struct pmu_types *pmus,
+				       struct resource *res, int *last_cpu_id)
+{
+	int i, count;
+	int irq;
+
+	pr_info("Setting up %d PMUs for CPU type %X\n", pmus->cpu_count,
+							pmus->cpu_type);
+	/* lets group all the PMU's from similar CPU's together */
+	count = 0;
+	for_each_possible_cpu(i) {
+		struct cpuinfo_arm64 *cinfo = per_cpu_ptr(&cpu_data, i);
+
+		if (pmus->cpu_type == MIDR_PARTNUM(cinfo->reg_midr)) {
+			if (pmu_irqs[i].gsi == 0)
+				continue;
+
+			irq = acpi_register_gsi(NULL, pmu_irqs[i].gsi,
+						pmu_irqs[i].trigger,
+						ACPI_ACTIVE_HIGH);
+
+			res[count].start = res[count].end = irq;
+			res[count].flags = IORESOURCE_IRQ;
+
+			if (pmu_irqs[i].trigger == ACPI_EDGE_SENSITIVE)
+				res[count].flags |= IORESOURCE_IRQ_HIGHEDGE;
+			else
+				res[count].flags |= IORESOURCE_IRQ_HIGHLEVEL;
+
+			pmu_irqs[i].registered = true;
+			count++;
+			(*last_cpu_id) = cinfo->reg_midr;
+		}
+	}
+	return count;
+}
+
 static int __init pmu_acpi_init(void)
 {
 	struct platform_device *pdev;

@@ -1044,7 +1044,12 @@ int arm_pmu_device_probe(struct platform_device *pdev,
 		if (!ret)
 			ret = init_fn(pmu);
 	} else if (probe_table) {
-		ret = probe_plat_pmu(pmu, probe_table, read_cpuid_id());
+		if (acpi_disabled) {
+			/* use the current cpu. */
+			ret = probe_plat_pmu(pmu, probe_table,
+					     read_cpuid_id());
+		} else
+			ret = probe_plat_pmu(pmu, probe_table, pdev->id);
 	}
 
 	if (ret) {

@@ -50,7 +50,7 @@ void __init arm_pmu_parse_acpi(int cpu, struct acpi_madt_generic_interrupt *gic)
 }
 
 /* Count number and type of CPU cores in the system. */
-void __init arm_pmu_acpi_determine_cpu_types(struct list_head *pmus)
+static void __init arm_pmu_acpi_determine_cpu_types(struct list_head *pmus)
 {
 	int i;
 

@@ -84,7 +84,7 @@ void __init arm_pmu_acpi_determine_cpu_types(struct list_head *pmus)
  * Registers the group of PMU interfaces which correspond to the 'last_cpu_id'.
  * This group utilizes 'count' resources in the 'res'.
  */
-int __init arm_pmu_acpi_register_pmu(int count, struct resource *res,
+static int __init arm_pmu_acpi_register_pmu(int count, struct resource *res,
 					    int last_cpu_id)
 {
 	int i;

@@ -130,7 +130,7 @@ int __init arm_pmu_acpi_register_pmu(int count, struct resource *res,
  * them to the resource structure. Return the number of GSI's contained
  * in the res structure, and the id of the last CPU/PMU we added.
  */
-int __init arm_pmu_acpi_gsi_res(struct pmu_types *pmus,
+static int __init arm_pmu_acpi_gsi_res(struct pmu_types *pmus,
 				       struct resource *res, int *last_cpu_id)
 {
 	int i, count;

@@ -169,63 +169,39 @@ int __init arm_pmu_acpi_gsi_res(struct pmu_types *pmus,
 
 static int __init pmu_acpi_init(void)
 {
-	struct platform_device *pdev;
-	struct pmu_irq *pirq = pmu_irqs;
-	struct resource	*res, *r;
+	struct resource	*res;
 	int err = -ENOMEM;
-	int i, count, irq;
+	int count, cpu_id;
+	struct pmu_types *pmu, *safe_temp;
+	LIST_HEAD(pmus);
 
 	if (acpi_disabled)
 		return 0;
 
-	/* Must have irq for boot cpu, at least */
-	if (pirq->gsi == 0)
-		return -EINVAL;
-
-	irq = acpi_register_gsi(NULL, pirq->gsi, pirq->trigger,
-				ACPI_ACTIVE_HIGH);
-
-	if (irq_is_percpu(irq))
-		count = 1;
-	else
-		for (i = 1, count = 1; i < NR_CPUS; i++)
-			if (pmu_irqs[i].gsi)
-				++count;
-
-	pdev = platform_device_alloc(ARMV8_PMU_PDEV_NAME, -1);
-	if (!pdev)
-		goto err_free_gsi;
-
-	res = kcalloc(count, sizeof(*res), GFP_KERNEL);
-	if (!res)
-		goto err_free_device;
-
-	for (i = 0, r = res; i < count; i++, pirq++, r++) {
-		if (i)
-			irq = acpi_register_gsi(NULL, pirq->gsi, pirq->trigger,
-						ACPI_ACTIVE_HIGH);
-		r->start = r->end = irq;
-		r->flags = IORESOURCE_IRQ;
-		if (pirq->trigger == ACPI_EDGE_SENSITIVE)
-			r->flags |= IORESOURCE_IRQ_HIGHEDGE;
-		else
-			r->flags |= IORESOURCE_IRQ_HIGHLEVEL;
+	arm_pmu_acpi_determine_cpu_types(&pmus);
+
+	list_for_each_entry_safe(pmu, safe_temp, &pmus, list) {
+		res = kcalloc(pmu->cpu_count,
+			      sizeof(struct resource), GFP_KERNEL);
+
+		/* for a given PMU type collect all the GSIs. */
+		if (res) {
+			count = arm_pmu_acpi_gsi_res(pmu, res,
+						     &cpu_id);
+			/*
+			 * register this set of interrupts
+			 * with a new PMU device
+			 */
+			err = arm_pmu_acpi_register_pmu(count, res, cpu_id);
+			kfree(res);
+		} else
+			pr_warn("PMU unable to allocate interrupt resource space\n");
+
+		list_del(&pmu->list);
+		kfree(pmu);
 	}
 
-	err = platform_device_add_resources(pdev, res, count);
-	if (!err)
-		err = platform_device_add(pdev);
-	kfree(res);
-	if (!err)
-		return 0;
-
-err_free_device:
-	platform_device_put(pdev);
-
-err_free_gsi:
-	for (i = 0; i < count; i++)
-		acpi_unregister_gsi(pmu_irqs[i].gsi);
-
 	return err;
 }
+
 arch_initcall(pmu_acpi_init);

@@ -878,12 +878,13 @@ ARM PMU PROFILING AND DEBUGGING
 M:	Will Deacon <will.deacon@arm.com>
 R:	Mark Rutland <mark.rutland@arm.com>
 S:	Maintained
+L:	linux-arm-kernel at lists.infradead.org (moderated for non-subscribers)
 F:	arch/arm*/kernel/perf_*
 F:	arch/arm/oprofile/common.c
 F:	arch/arm*/kernel/hw_breakpoint.c
 F:	arch/arm*/include/asm/hw_breakpoint.h
 F:	arch/arm*/include/asm/perf_event.h
-F:	drivers/perf/arm_pmu.c
+F:	drivers/perf/arm_pmu*
 F:	include/linux/perf/arm_pmu.h
 
 ARM PORT