Merge branch 'for-next/perf' into for-next/core

PMU driver cleanups for managing IRQ affinity and exposing event
attributes via sysfs.

* for-next/perf: (36 commits)
  drivers/perf: fix the missed ida_simple_remove() in ddr_perf_probe()
  perf/arm-cmn: Fix invalid pointer when access dtc object sharing the same IRQ number
  arm64: perf: Simplify EVENT ATTR macro in perf_event.c
  drivers/perf: Simplify EVENT ATTR macro in fsl_imx8_ddr_perf.c
  drivers/perf: Simplify EVENT ATTR macro in xgene_pmu.c
  drivers/perf: Simplify EVENT ATTR macro in qcom_l3_pmu.c
  drivers/perf: Simplify EVENT ATTR macro in qcom_l2_pmu.c
  drivers/perf: Simplify EVENT ATTR macro in SMMU PMU driver
  perf: Add EVENT_ATTR_ID to simplify event attributes
  perf/smmuv3: Don't trample existing events with global filter
  perf/hisi: Constify static attribute_group structs
  perf: qcom: Remove redundant dev_err call in qcom_l3_cache_pmu_probe()
  drivers/perf: hisi: Fix data source control
  arm64: perf: Add more support on caps under sysfs
  perf: qcom_l2_pmu: move to use request_irq by IRQF_NO_AUTOEN flag
  arm_pmu: move to use request_irq by IRQF_NO_AUTOEN flag
  perf: arm_spe: use DEVICE_ATTR_RO macro
  perf: xgene_pmu: use DEVICE_ATTR_RO macro
  perf: qcom: use DEVICE_ATTR_RO macro
  perf: arm_pmu: use DEVICE_ATTR_RO macro
  ...

Author: willdeacon

arch/arm/kernel/perf_event_v7.c

@@ -773,10 +773,10 @@ static inline void armv7pmu_write_counter(struct perf_event *event, u64 value)
 		pr_err("CPU%u writing wrong counter %d\n",
 			smp_processor_id(), idx);
 	} else if (idx == ARMV7_IDX_CYCLE_COUNTER) {
-		asm volatile("mcr p15, 0, %0, c9, c13, 0" : : "r" (value));
+		asm volatile("mcr p15, 0, %0, c9, c13, 0" : : "r" ((u32)value));
 	} else {
 		armv7_pmnc_select_counter(idx);
-		asm volatile("mcr p15, 0, %0, c9, c13, 2" : : "r" (value));
+		asm volatile("mcr p15, 0, %0, c9, c13, 2" : : "r" ((u32)value));
 	}
 }
 

arch/arm64/include/asm/perf_event.h

@@ -239,6 +239,11 @@
 /* PMMIR_EL1.SLOTS mask */
 #define ARMV8_PMU_SLOTS_MASK	0xff
 
+#define ARMV8_PMU_BUS_SLOTS_SHIFT 8
+#define ARMV8_PMU_BUS_SLOTS_MASK 0xff
+#define ARMV8_PMU_BUS_WIDTH_SHIFT 16
+#define ARMV8_PMU_BUS_WIDTH_MASK 0xf
+
 #ifdef CONFIG_PERF_EVENTS
 struct pt_regs;
 extern unsigned long perf_instruction_pointer(struct pt_regs *regs);

arch/arm64/kernel/perf_event.c

@@ -165,10 +165,7 @@ armv8pmu_events_sysfs_show(struct device *dev,
 }
 
 #define ARMV8_EVENT_ATTR(name, config)						\
-	(&((struct perf_pmu_events_attr) {					\
-		.attr = __ATTR(name, 0444, armv8pmu_events_sysfs_show, NULL),	\
-		.id = config,							\
-	}).attr.attr)
+	PMU_EVENT_ATTR_ID(name, armv8pmu_events_sysfs_show, config)
 
 static struct attribute *armv8_pmuv3_event_attrs[] = {
 	ARMV8_EVENT_ATTR(sw_incr, ARMV8_PMUV3_PERFCTR_SW_INCR),
@@ -312,13 +309,46 @@ static ssize_t slots_show(struct device *dev, struct device_attribute *attr,
 	struct arm_pmu *cpu_pmu = container_of(pmu, struct arm_pmu, pmu);
 	u32 slots = cpu_pmu->reg_pmmir & ARMV8_PMU_SLOTS_MASK;
 
-	return snprintf(page, PAGE_SIZE, "0x%08x\n", slots);
+	return sysfs_emit(page, "0x%08x\n", slots);
 }
 
 static DEVICE_ATTR_RO(slots);
 
+static ssize_t bus_slots_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);
+	u32 bus_slots = (cpu_pmu->reg_pmmir >> ARMV8_PMU_BUS_SLOTS_SHIFT)
+			& ARMV8_PMU_BUS_SLOTS_MASK;
+
+	return sysfs_emit(page, "0x%08x\n", bus_slots);
+}
+
+static DEVICE_ATTR_RO(bus_slots);
+
+static ssize_t bus_width_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);
+	u32 bus_width = (cpu_pmu->reg_pmmir >> ARMV8_PMU_BUS_WIDTH_SHIFT)
+			& ARMV8_PMU_BUS_WIDTH_MASK;
+	u32 val = 0;
+
+	/* Encoded as Log2(number of bytes), plus one */
+	if (bus_width > 2 && bus_width < 13)
+		val = 1 << (bus_width - 1);
+
+	return sysfs_emit(page, "0x%08x\n", val);
+}
+
+static DEVICE_ATTR_RO(bus_width);
+
 static struct attribute *armv8_pmuv3_caps_attrs[] = {
 	&dev_attr_slots.attr,
+	&dev_attr_bus_slots.attr,
+	&dev_attr_bus_width.attr,
 	NULL,
 };
 

drivers/perf/arm-cci.c

@@ -37,7 +37,7 @@
 
 #define CCI_PMU_CNTR_SIZE(model)	((model)->cntr_size)
 #define CCI_PMU_CNTR_BASE(model, idx)	((idx) * CCI_PMU_CNTR_SIZE(model))
-#define CCI_PMU_CNTR_MASK		((1ULL << 32) -1)
+#define CCI_PMU_CNTR_MASK		((1ULL << 32) - 1)
 #define CCI_PMU_CNTR_LAST(cci_pmu)	(cci_pmu->num_cntrs - 1)
 
 #define CCI_PMU_MAX_HW_CNTRS(model) \
@@ -806,7 +806,7 @@ static int pmu_get_event_idx(struct cci_pmu_hw_events *hw, struct perf_event *ev
 		return cci_pmu->model->get_event_idx(cci_pmu, hw, cci_event);
 
 	/* Generic code to find an unused idx from the mask */
-	for(idx = 0; idx <= CCI_PMU_CNTR_LAST(cci_pmu); idx++)
+	for (idx = 0; idx <= CCI_PMU_CNTR_LAST(cci_pmu); idx++)
 		if (!test_and_set_bit(idx, hw->used_mask))
 			return idx;
 

drivers/perf/arm-ccn.c

@@ -1211,7 +1211,7 @@ static int arm_ccn_pmu_offline_cpu(unsigned int cpu, struct hlist_node *node)
 	perf_pmu_migrate_context(&dt->pmu, cpu, target);
 	dt->cpu = target;
 	if (ccn->irq)
-		WARN_ON(irq_set_affinity_hint(ccn->irq, cpumask_of(dt->cpu)));
+		WARN_ON(irq_set_affinity(ccn->irq, cpumask_of(dt->cpu)));
 	return 0;
 }
 
@@ -1291,7 +1291,7 @@ static int arm_ccn_pmu_init(struct arm_ccn *ccn)
 
 	/* Also make sure that the overflow interrupt is handled by this CPU */
 	if (ccn->irq) {
-		err = irq_set_affinity_hint(ccn->irq, cpumask_of(ccn->dt.cpu));
+		err = irq_set_affinity(ccn->irq, cpumask_of(ccn->dt.cpu));
 		if (err) {
 			dev_err(ccn->dev, "Failed to set interrupt affinity!\n");
 			goto error_set_affinity;
@@ -1325,8 +1325,6 @@ static void arm_ccn_pmu_cleanup(struct arm_ccn *ccn)
 
 	cpuhp_state_remove_instance_nocalls(CPUHP_AP_PERF_ARM_CCN_ONLINE,
 					    &ccn->dt.node);
-	if (ccn->irq)
-		irq_set_affinity_hint(ccn->irq, NULL);
 	for (i = 0; i < ccn->num_xps; i++)
 		writel(0, ccn->xp[i].base + CCN_XP_DT_CONTROL);
 	writel(0, ccn->dt.base + CCN_DT_PMCR);

drivers/perf/arm-cmn.c

@@ -31,7 +31,7 @@
 #define CMN_CI_CHILD_COUNT		GENMASK_ULL(15, 0)
 #define CMN_CI_CHILD_PTR_OFFSET		GENMASK_ULL(31, 16)
 
-#define CMN_CHILD_NODE_ADDR		GENMASK(27,0)
+#define CMN_CHILD_NODE_ADDR		GENMASK(27, 0)
 #define CMN_CHILD_NODE_EXTERNAL		BIT(31)
 
 #define CMN_ADDR_NODE_PTR		GENMASK(27, 14)
@@ -1162,7 +1162,7 @@ static int arm_cmn_pmu_offline_cpu(unsigned int cpu, struct hlist_node *node)
 
 	perf_pmu_migrate_context(&cmn->pmu, cpu, target);
 	for (i = 0; i < cmn->num_dtcs; i++)
-		irq_set_affinity_hint(cmn->dtc[i].irq, cpumask_of(target));
+		irq_set_affinity(cmn->dtc[i].irq, cpumask_of(target));
 	cmn->cpu = target;
 	return 0;
 }
@@ -1212,7 +1212,7 @@ static int arm_cmn_init_irqs(struct arm_cmn *cmn)
 		irq = cmn->dtc[i].irq;
 		for (j = i; j--; ) {
 			if (cmn->dtc[j].irq == irq) {
-				cmn->dtc[j].irq_friend = j - i;
+				cmn->dtc[j].irq_friend = i - j;
 				goto next;
 			}
 		}
@@ -1222,7 +1222,7 @@ static int arm_cmn_init_irqs(struct arm_cmn *cmn)
 		if (err)
 			return err;
 
-		err = irq_set_affinity_hint(irq, cpumask_of(cmn->cpu));
+		err = irq_set_affinity(irq, cpumask_of(cmn->cpu));
 		if (err)
 			return err;
 	next:
@@ -1568,16 +1568,11 @@ static int arm_cmn_probe(struct platform_device *pdev)
 static int arm_cmn_remove(struct platform_device *pdev)
 {
 	struct arm_cmn *cmn = platform_get_drvdata(pdev);
-	int i;
 
 	writel_relaxed(0, cmn->dtc[0].base + CMN_DT_DTC_CTL);
 
 	perf_pmu_unregister(&cmn->pmu);
 	cpuhp_state_remove_instance(arm_cmn_hp_state, &cmn->cpuhp_node);
-
-	for (i = 0; i < cmn->num_dtcs; i++)
-		irq_set_affinity_hint(cmn->dtc[i].irq, NULL);
-
 	return 0;
 }
 

drivers/perf/arm_dmc620_pmu.c

@@ -421,7 +421,7 @@ static struct dmc620_pmu_irq *__dmc620_pmu_get_irq(int irq_num)
 	if (ret)
 		goto out_free_aff;
 
-	ret = irq_set_affinity_hint(irq_num, cpumask_of(irq->cpu));
+	ret = irq_set_affinity(irq_num, cpumask_of(irq->cpu));
 	if (ret)
 		goto out_free_irq;
 
@@ -475,7 +475,6 @@ static void dmc620_pmu_put_irq(struct dmc620_pmu *dmc620_pmu)
 	list_del(&irq->irqs_node);
 	mutex_unlock(&dmc620_pmu_irqs_lock);
 
-	WARN_ON(irq_set_affinity_hint(irq->irq_num, NULL));
 	free_irq(irq->irq_num, irq);
 	cpuhp_state_remove_instance_nocalls(cpuhp_state_num, &irq->node);
 	kfree(irq);
@@ -622,7 +621,7 @@ static int dmc620_pmu_cpu_teardown(unsigned int cpu,
 		perf_pmu_migrate_context(&dmc620_pmu->pmu, irq->cpu, target);
 	mutex_unlock(&dmc620_pmu_irqs_lock);
 
-	WARN_ON(irq_set_affinity_hint(irq->irq_num, cpumask_of(target)));
+	WARN_ON(irq_set_affinity(irq->irq_num, cpumask_of(target)));
 	irq->cpu = target;
 
 	return 0;

drivers/perf/arm_dsu_pmu.c

@@ -687,7 +687,7 @@ static void dsu_pmu_probe_pmu(struct dsu_pmu *dsu_pmu)
 static void dsu_pmu_set_active_cpu(int cpu, struct dsu_pmu *dsu_pmu)
 {
 	cpumask_set_cpu(cpu, &dsu_pmu->active_cpu);
-	if (irq_set_affinity_hint(dsu_pmu->irq, &dsu_pmu->active_cpu))
+	if (irq_set_affinity(dsu_pmu->irq, &dsu_pmu->active_cpu))
 		pr_warn("Failed to set irq affinity to %d\n", cpu);
 }
 
@@ -769,7 +769,6 @@ static int dsu_pmu_device_probe(struct platform_device *pdev)
 	if (rc) {
 		cpuhp_state_remove_instance(dsu_pmu_cpuhp_state,
 						 &dsu_pmu->cpuhp_node);
-		irq_set_affinity_hint(dsu_pmu->irq, NULL);
 	}
 
 	return rc;
@@ -781,7 +780,6 @@ static int dsu_pmu_device_remove(struct platform_device *pdev)
 
 	perf_pmu_unregister(&dsu_pmu->pmu);
 	cpuhp_state_remove_instance(dsu_pmu_cpuhp_state, &dsu_pmu->cpuhp_node);
-	irq_set_affinity_hint(dsu_pmu->irq, NULL);
 
 	return 0;
 }
@@ -840,10 +838,8 @@ static int dsu_pmu_cpu_teardown(unsigned int cpu, struct hlist_node *node)
 
 	dst = dsu_pmu_get_online_cpu_any_but(dsu_pmu, cpu);
 	/* If there are no active CPUs in the DSU, leave IRQ disabled */
-	if (dst >= nr_cpu_ids) {
-		irq_set_affinity_hint(dsu_pmu->irq, NULL);
+	if (dst >= nr_cpu_ids)
 		return 0;
-	}
 
 	perf_pmu_migrate_context(&dsu_pmu->pmu, cpu, dst);
 	dsu_pmu_set_active_cpu(dst, dsu_pmu);

drivers/perf/arm_pmu.c

@@ -563,14 +563,14 @@ static int armpmu_filter_match(struct perf_event *event)
 	return ret;
 }
 
-static ssize_t armpmu_cpumask_show(struct device *dev,
-				   struct device_attribute *attr, char *buf)
+static ssize_t cpus_show(struct device *dev,
+			 struct device_attribute *attr, char *buf)
 {
 	struct arm_pmu *armpmu = to_arm_pmu(dev_get_drvdata(dev));
 	return cpumap_print_to_pagebuf(true, buf, &armpmu->supported_cpus);
 }
 
-static DEVICE_ATTR(cpus, S_IRUGO, armpmu_cpumask_show, NULL);
+static DEVICE_ATTR_RO(cpus);
 
 static struct attribute *armpmu_common_attrs[] = {
 	&dev_attr_cpus.attr,
@@ -644,11 +644,9 @@ int armpmu_request_irq(int irq, int cpu)
 		}
 
 		irq_flags = IRQF_PERCPU |
-			    IRQF_NOBALANCING |
+			    IRQF_NOBALANCING | IRQF_NO_AUTOEN |
 			    IRQF_NO_THREAD;
 
-		irq_set_status_flags(irq, IRQ_NOAUTOEN);
-
 		err = request_nmi(irq, handler, irq_flags, "arm-pmu",
 				  per_cpu_ptr(&cpu_armpmu, cpu));
 
@@ -670,7 +668,7 @@ int armpmu_request_irq(int irq, int cpu)
 						 &cpu_armpmu);
 			irq_ops = &percpu_pmuirq_ops;
 		} else {
-			has_nmi= true;
+			has_nmi = true;
 			irq_ops = &percpu_pmunmi_ops;
 		}
 	} else {
@@ -869,10 +867,8 @@ static struct arm_pmu *__armpmu_alloc(gfp_t flags)
 	int cpu;
 
 	pmu = kzalloc(sizeof(*pmu), flags);
-	if (!pmu) {
-		pr_info("failed to allocate PMU device!\n");
+	if (!pmu)
 		goto out;
-	}
 
 	pmu->hw_events = alloc_percpu_gfp(struct pmu_hw_events, flags);
 	if (!pmu->hw_events) {

drivers/perf/arm_smmuv3_pmu.c

@@ -277,25 +277,27 @@ static int smmu_pmu_apply_event_filter(struct smmu_pmu *smmu_pmu,
 				       struct perf_event *event, int idx)
 {
 	u32 span, sid;
-	unsigned int num_ctrs = smmu_pmu->num_counters;
+	unsigned int cur_idx, num_ctrs = smmu_pmu->num_counters;
 	bool filter_en = !!get_filter_enable(event);
 
 	span = filter_en ? get_filter_span(event) :
 			   SMMU_PMCG_DEFAULT_FILTER_SPAN;
 	sid = filter_en ? get_filter_stream_id(event) :
 			   SMMU_PMCG_DEFAULT_FILTER_SID;
 
-	/* Support individual filter settings */
-	if (!smmu_pmu->global_filter) {
+	cur_idx = find_first_bit(smmu_pmu->used_counters, num_ctrs);
+	/*
+	 * Per-counter filtering, or scheduling the first globally-filtered
+	 * event into an empty PMU so idx == 0 and it works out equivalent.
+	 */
+	if (!smmu_pmu->global_filter || cur_idx == num_ctrs) {
 		smmu_pmu_set_event_filter(event, idx, span, sid);
 		return 0;
 	}
 
-	/* Requested settings same as current global settings*/
-	idx = find_first_bit(smmu_pmu->used_counters, num_ctrs);
-	if (idx == num_ctrs ||
-	    smmu_pmu_check_global_filter(smmu_pmu->events[idx], event)) {
-		smmu_pmu_set_event_filter(event, 0, span, sid);
+	/* Otherwise, must match whatever's currently scheduled */
+	if (smmu_pmu_check_global_filter(smmu_pmu->events[cur_idx], event)) {
+		smmu_pmu_set_evtyper(smmu_pmu, idx, get_event(event));
 		return 0;
 	}
 
@@ -509,11 +511,8 @@ static ssize_t smmu_pmu_event_show(struct device *dev,
 	return sysfs_emit(page, "event=0x%02llx\n", pmu_attr->id);
 }
 
-#define SMMU_EVENT_ATTR(name, config)					\
-	(&((struct perf_pmu_events_attr) {				\
-		.attr = __ATTR(name, 0444, smmu_pmu_event_show, NULL),	\
-		.id = config,						\
-	}).attr.attr)
+#define SMMU_EVENT_ATTR(name, config)			\
+	PMU_EVENT_ATTR_ID(name, smmu_pmu_event_show, config)
 
 static struct attribute *smmu_pmu_events[] = {
 	SMMU_EVENT_ATTR(cycles, 0),
@@ -628,7 +627,7 @@ static int smmu_pmu_offline_cpu(unsigned int cpu, struct hlist_node *node)
 
 	perf_pmu_migrate_context(&smmu_pmu->pmu, cpu, target);
 	smmu_pmu->on_cpu = target;
-	WARN_ON(irq_set_affinity_hint(smmu_pmu->irq, cpumask_of(target)));
+	WARN_ON(irq_set_affinity(smmu_pmu->irq, cpumask_of(target)));
 
 	return 0;
 }
@@ -839,15 +838,14 @@ static int smmu_pmu_probe(struct platform_device *pdev)
 
 	/* Pick one CPU to be the preferred one to use */
 	smmu_pmu->on_cpu = raw_smp_processor_id();
-	WARN_ON(irq_set_affinity_hint(smmu_pmu->irq,
-				      cpumask_of(smmu_pmu->on_cpu)));
+	WARN_ON(irq_set_affinity(smmu_pmu->irq, cpumask_of(smmu_pmu->on_cpu)));
 
 	err = cpuhp_state_add_instance_nocalls(cpuhp_state_num,
 					       &smmu_pmu->node);
 	if (err) {
 		dev_err(dev, "Error %d registering hotplug, PMU @%pa\n",
 			err, &res_0->start);
-		goto out_clear_affinity;
+		return err;
 	}
 
 	err = perf_pmu_register(&smmu_pmu->pmu, name, -1);
@@ -866,8 +864,6 @@ static int smmu_pmu_probe(struct platform_device *pdev)
 
 out_unregister:
 	cpuhp_state_remove_instance_nocalls(cpuhp_state_num, &smmu_pmu->node);
-out_clear_affinity:
-	irq_set_affinity_hint(smmu_pmu->irq, NULL);
 	return err;
 }
 
@@ -877,7 +873,6 @@ static int smmu_pmu_remove(struct platform_device *pdev)
 
 	perf_pmu_unregister(&smmu_pmu->pmu);
 	cpuhp_state_remove_instance_nocalls(cpuhp_state_num, &smmu_pmu->node);
-	irq_set_affinity_hint(smmu_pmu->irq, NULL);
 
 	return 0;
 }