ARM: perf: set cpu affinity to support multiple PMUs

In a system with multiple heterogeneous CPU PMUs and each PMUs can handle
events on a subset of CPUs, probably belonging a the same cluster.

This patch introduces a cpumask to track which CPUs each PMU supports.
It also updates armpmu_event_init to reject cpu-specific events being
initialised for unsupported CPUs. Since process-specific events can be
initialised for all the CPU PMUs,armpmu_start/stop/add are modified to
prevent from being added on unsupported CPUs.

Signed-off-by: Sudeep KarkadaNagesha <sudeep.karkadanagesha@arm.com>

4 files changed, 49 insertions, 7 deletions

diff --git a/Documentation/devicetree/bindings/arm/pmu.txt b/Documentation/devicetree/bindings/arm/pmu.txt
index 343781b9f24..4ce82d045a6 100644
--- a/Documentation/devicetree/bindings/arm/pmu.txt
+++ b/Documentation/devicetree/bindings/arm/pmu.txt
@@ -16,6 +16,9 @@ Required properties:
 	"arm,arm1176-pmu"
 	"arm,arm1136-pmu"
 - interrupts : 1 combined interrupt or 1 per core.
+- cluster : a phandle to the cluster to which it belongs
+	If there are more than one cluster with same CPU type
+	then there should be separate PMU nodes per cluster.
 
 Example:
 
diff --git a/arch/arm/include/asm/pmu.h b/arch/arm/include/asm/pmu.h
index f24edad26c7..3713e57a467 100644
--- a/arch/arm/include/asm/pmu.h
+++ b/arch/arm/include/asm/pmu.h
@@ -65,6 +65,7 @@ struct pmu_hw_events {
 struct arm_pmu {
 	struct pmu	pmu;
 	cpumask_t	active_irqs;
+	cpumask_t	valid_cpus;
 	char		*name;
 	irqreturn_t	(*handle_irq)(int irq_num, void *dev);
 	void		(*enable)(struct perf_event *event);
diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c
index 491573373f6..d847c622a7b 100644
--- a/arch/arm/kernel/perf_event.c
+++ b/arch/arm/kernel/perf_event.c
@@ -12,6 +12,7 @@
  */
 #define pr_fmt(fmt) "hw perfevents: " fmt
 
+#include <linux/cpumask.h>
 #include <linux/kernel.h>
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
@@ -161,6 +162,8 @@ armpmu_stop(struct perf_event *event, int flags)
 	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
 	struct hw_perf_event *hwc = &event->hw;
 
+	if (!cpumask_test_cpu(smp_processor_id(), &armpmu->valid_cpus))
+		return;
 	/*
 	 * ARM pmu always has to update the counter, so ignore
 	 * PERF_EF_UPDATE, see comments in armpmu_start().
@@ -177,6 +180,8 @@ static void armpmu_start(struct perf_event *event, int flags)
 	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
 	struct hw_perf_event *hwc = &event->hw;
 
+	if (!cpumask_test_cpu(smp_processor_id(), &armpmu->valid_cpus))
+		return;
 	/*
 	 * ARM pmu always has to reprogram the period, so ignore
 	 * PERF_EF_RELOAD, see the comment below.
@@ -204,6 +209,9 @@ armpmu_del(struct perf_event *event, int flags)
 	struct hw_perf_event *hwc = &event->hw;
 	int idx = hwc->idx;
 
+	if (!cpumask_test_cpu(smp_processor_id(), &armpmu->valid_cpus))
+		return;
+
 	armpmu_stop(event, PERF_EF_UPDATE);
 	hw_events->events[idx] = NULL;
 	clear_bit(idx, hw_events->used_mask);
@@ -220,6 +228,10 @@ armpmu_add(struct perf_event *event, int flags)
 	int idx;
 	int err = 0;
 
+	/* An event following a process won't be stopped earlier */
+	if (!cpumask_test_cpu(smp_processor_id(), &armpmu->valid_cpus))
+		return 0;
+
 	perf_pmu_disable(event->pmu);
 
 	/* If we don't have a space for the counter then finish early. */
@@ -419,6 +431,10 @@ static int armpmu_event_init(struct perf_event *event)
 	int err = 0;
 	atomic_t *active_events = &armpmu->active_events;
 
+	if (event->cpu != -1 &&
+		!cpumask_test_cpu(event->cpu, &armpmu->valid_cpus))
+		return -ENOENT;
+
 	/* does not support taken branch sampling */
 	if (has_branch_stack(event))
 		return -EOPNOTSUPP;
diff --git a/arch/arm/kernel/perf_event_cpu.c b/arch/arm/kernel/perf_event_cpu.c
index f62d6cb6524..725e225c84b 100644
--- a/arch/arm/kernel/perf_event_cpu.c
+++ b/arch/arm/kernel/perf_event_cpu.c
@@ -136,7 +136,7 @@ static int cpu_pmu_request_irq(struct arm_pmu *cpu_pmu, irq_handler_t handler)
 static void cpu_pmu_init(struct arm_pmu *cpu_pmu)
 {
 	int cpu;
-	for_each_possible_cpu(cpu) {
+	for_each_cpu_mask(cpu, cpu_pmu->valid_cpus) {
 		struct pmu_hw_events *events = &per_cpu(cpu_hw_events, cpu);
 		events->events = per_cpu(hw_events, cpu);
 		events->used_mask = per_cpu(used_mask, cpu);
@@ -149,7 +149,7 @@ static void cpu_pmu_init(struct arm_pmu *cpu_pmu)
 
 	/* Ensure the PMU has sane values out of reset. */
 	if (cpu_pmu->reset)
-		on_each_cpu(cpu_pmu->reset, cpu_pmu, 1);
+		on_each_cpu_mask(&cpu_pmu->valid_cpus, cpu_pmu->reset, cpu_pmu, 1);
 }
 
 /*
@@ -249,6 +249,9 @@ static int probe_current_pmu(struct arm_pmu *pmu)
 		}
 	}
 
+	/* assume PMU support all the CPUs in this case */
+	cpumask_setall(&pmu->valid_cpus);
+
 	put_cpu();
 	return ret;
 }
@@ -256,10 +259,9 @@ static int probe_current_pmu(struct arm_pmu *pmu)
 static int cpu_pmu_device_probe(struct platform_device *pdev)
 {
 	const struct of_device_id *of_id;
-	int (*init_fn)(struct arm_pmu *);
 	struct device_node *node = pdev->dev.of_node;
 	struct arm_pmu *pmu;
-	int ret = -ENODEV;
+	int ret = 0;
 	int cpu;
 
 	pmu = kzalloc(sizeof(struct arm_pmu), GFP_KERNEL);
@@ -269,8 +271,28 @@ static int cpu_pmu_device_probe(struct platform_device *pdev)
 	}
 
 	if (node && (of_id = of_match_node(cpu_pmu_of_device_ids, pdev->dev.of_node))) {
-		init_fn = of_id->data;
-		ret = init_fn(pmu);
+		smp_call_func_t init_fn = (smp_call_func_t)of_id->data;
+		struct device_node *ncluster;
+		int cluster = -1;
+		cpumask_t sibling_mask;
+
+		ncluster = of_parse_phandle(node, "cluster", 0);
+		if (ncluster) {
+			int len;
+			const u32 *hwid;
+			hwid = of_get_property(ncluster, "reg", &len);
+			if (hwid && len == 4)
+				cluster = be32_to_cpup(hwid);
+		}
+		/* set sibling mask to all cpu mask if socket is not specified */
+		if (cluster == -1 ||
+			cluster_to_logical_mask(cluster, &sibling_mask))
+			cpumask_setall(&sibling_mask);
+
+		smp_call_function_any(&sibling_mask, init_fn, pmu, 1);
+
+		/* now set the valid_cpus after init */
+		cpumask_copy(&pmu->valid_cpus, &sibling_mask);
 	} else {
 		ret = probe_current_pmu(pmu);
 	}
@@ -280,7 +302,7 @@ static int cpu_pmu_device_probe(struct platform_device *pdev)
 		goto out_free;
 	}
 
-	for_each_possible_cpu(cpu)
+	for_each_cpu_mask(cpu, pmu->valid_cpus)
 		per_cpu(cpu_pmu, cpu) = pmu;
 
 	pmu->plat_device = pdev;