genirq: Add support for percpu_devid IRQ affinity

index 4a86e6b915dd6..9d6a5e99394fa 100644
@@ -44,6 +44,23 @@ struct irq_fwspec {
 	u32			param[IRQ_DOMAIN_IRQ_SPEC_PARAMS];
 };
 
+/**
+ * struct irq_fwspec_info - firmware provided IRQ information structure
+ *
+ * @flags:		Information validity flags
+ * @cpumask:		Affinity mask for this interrupt
+ *
+ * This structure reports firmware-specific information about an
+ * interrupt. The only significant information is the affinity of a
+ * per-CPU interrupt, but this is designed to be extended as required.
+ */
+struct irq_fwspec_info {
+	unsigned long		flags;
+	const struct cpumask	*affinity;
+};
+
+#define IRQ_FWSPEC_INFO_AFFINITY_VALID	BIT(0)
+
 /* Conversion function from of_phandle_args fields to fwspec  */
 void of_phandle_args_to_fwspec(struct device_node *np, const u32 *args,
 			       unsigned int count, struct irq_fwspec *fwspec);

@@ -69,6 +86,9 @@ void of_phandle_args_to_fwspec(struct device_node *np, const u32 *args,
  * @translate:	Given @fwspec, decode the hardware irq number (@out_hwirq) and
  *		linux irq type value (@out_type). This is a generalised @xlate
  *		(over struct irq_fwspec) and is preferred if provided.
+ * @get_fwspec_info:
+ *		Given @fwspec, report additional firmware-provided information in
+ *		@info. Optional.
  * @debug_show:	For domains to show specific data for an interrupt in debugfs.
  *
  * Functions below are provided by the driver and called whenever a new mapping

@@ -96,6 +116,7 @@ struct irq_domain_ops {
 	void	(*deactivate)(struct irq_domain *d, struct irq_data *irq_data);
 	int	(*translate)(struct irq_domain *d, struct irq_fwspec *fwspec,
 			     unsigned long *out_hwirq, unsigned int *out_type);
+	int	(*get_fwspec_info)(struct irq_fwspec *fwspec, struct irq_fwspec_info *info);
 #endif
 #ifdef CONFIG_GENERIC_IRQ_DEBUGFS
 	void	(*debug_show)(struct seq_file *m, struct irq_domain *d,

@@ -602,6 +623,8 @@ void irq_domain_free_irqs_parent(struct irq_domain *domain, unsigned int irq_bas
 
 int irq_domain_disconnect_hierarchy(struct irq_domain *domain, unsigned int virq);
 
+int irq_populate_fwspec_info(struct irq_fwspec *fwspec, struct irq_fwspec_info *info);
+
 static inline bool irq_domain_is_hierarchy(struct irq_domain *domain)
 {
 	return domain->flags & IRQ_DOMAIN_FLAG_HIERARCHY;

@@ -685,6 +708,10 @@ static inline bool irq_domain_is_msi_device(struct irq_domain *domain)
 	return false;
 }
 
+static inline int irq_populate_fwspec_info(struct irq_fwspec *fwspec, struct irq_fwspec_info *info)
+{
+	return -EINVAL;
+}
 #endif	/* CONFIG_IRQ_DOMAIN_HIERARCHY */
 
 #ifdef CONFIG_GENERIC_MSI_IRQ

index dc473faadcc81..2652c4cfd877f 100644
@@ -867,13 +867,9 @@ void of_phandle_args_to_fwspec(struct device_node *np, const u32 *args,
 }
 EXPORT_SYMBOL_GPL(of_phandle_args_to_fwspec);
 
-unsigned int irq_create_fwspec_mapping(struct irq_fwspec *fwspec)
+static struct irq_domain *fwspec_to_domain(struct irq_fwspec *fwspec)
 {
 	struct irq_domain *domain;
-	struct irq_data *irq_data;
-	irq_hw_number_t hwirq;
-	unsigned int type = IRQ_TYPE_NONE;
-	int virq;
 
 	if (fwspec->fwnode) {
 		domain = irq_find_matching_fwspec(fwspec, DOMAIN_BUS_WIRED);

@@ -883,6 +879,32 @@ unsigned int irq_create_fwspec_mapping(struct irq_fwspec *fwspec)
 		domain = irq_default_domain;
 	}
 
+	return domain;
+}
+
+#ifdef CONFIG_IRQ_DOMAIN_HIERARCHY
+int irq_populate_fwspec_info(struct irq_fwspec *fwspec, struct irq_fwspec_info *info)
+{
+	struct irq_domain *domain = fwspec_to_domain(fwspec);
+
+	memset(info, 0, sizeof(*info));
+
+	if (!domain || !domain->ops->get_fwspec_info)
+		return 0;
+
+	return domain->ops->get_fwspec_info(fwspec, info);
+}
+#endif
+
+unsigned int irq_create_fwspec_mapping(struct irq_fwspec *fwspec)
+{
+	unsigned int type = IRQ_TYPE_NONE;
+	struct irq_domain *domain;
+	struct irq_data *irq_data;
+	irq_hw_number_t hwirq;
+	int virq;
+
+	domain = fwspec_to_domain(fwspec);
 	if (!domain) {
 		pr_warn("no irq domain found for %s !\n",
 			of_node_full_name(to_of_node(fwspec->fwnode)));

index 76a856c32c4d0..d1595156c86a4 100644
@@ -300,6 +300,25 @@ int acpi_irq_get(acpi_handle handle, unsigned int index, struct resource *res)
 }
 EXPORT_SYMBOL_GPL(acpi_irq_get);
 
+const struct cpumask *acpi_irq_get_affinity(acpi_handle handle,
+					    unsigned int index)
+{
+	struct irq_fwspec_info info;
+	struct irq_fwspec fwspec;
+	unsigned long flags;
+
+	if (acpi_irq_parse_one(handle, index, &fwspec, &flags))
+		return NULL;
+
+	if (irq_populate_fwspec_info(&fwspec, &info))
+		return NULL;
+
+	if (!(info.flags & IRQ_FWSPEC_INFO_AFFINITY_VALID))
+		return NULL;
+
+	return info.affinity;
+}
+
 /**
  * acpi_set_irq_model - Setup the GSI irqdomain information
  * @model: the value assigned to acpi_irq_model

index 5ff5d99f6ead5..607db773b6721 100644
@@ -1509,12 +1509,19 @@ static inline int acpi_parse_spcr(bool enable_earlycon, bool enable_console)
 
 #if IS_ENABLED(CONFIG_ACPI_GENERIC_GSI)
 int acpi_irq_get(acpi_handle handle, unsigned int index, struct resource *res);
+const struct cpumask *acpi_irq_get_affinity(acpi_handle handle,
+					    unsigned int index);
 #else
 static inline
 int acpi_irq_get(acpi_handle handle, unsigned int index, struct resource *res)
 {
 	return -EINVAL;
 }
+static inline const struct cpumask *acpi_irq_get_affinity(acpi_handle handle,
+							  unsigned int index)
+{
+	return NULL;
+}
 #endif
 
 #ifdef CONFIG_ACPI_LPIT

index 65c3c23255b74..168fde921bd27 100644
@@ -479,6 +479,26 @@ int of_irq_get(struct device_node *dev, int index)
 }
 EXPORT_SYMBOL_GPL(of_irq_get);
 
+const struct cpumask *of_irq_get_affinity(struct device_node *dev, int index)
+{
+	struct of_phandle_args oirq;
+	struct irq_fwspec_info info;
+	struct irq_fwspec fwspec;
+	int rc;
+
+	rc = of_irq_parse_one(dev, index, &oirq);
+	if (rc)
+		return NULL;
+
+	of_phandle_args_to_fwspec(oirq.np, oirq.args, oirq.args_count,
+				  &fwspec);
+
+	if (irq_populate_fwspec_info(&fwspec, &info))
+		return NULL;
+
+	return info.affinity;
+}
+
 /**
  * of_irq_get_byname - Decode a node's IRQ and return it as a Linux IRQ number
  * @dev: pointer to device tree node

index 1db8543dfc8a6..1c2bc02818071 100644
@@ -43,6 +43,8 @@ extern int of_irq_parse_one(struct device_node *device, int index,
 			  struct of_phandle_args *out_irq);
 extern int of_irq_count(struct device_node *dev);
 extern int of_irq_get(struct device_node *dev, int index);
+extern const struct cpumask *of_irq_get_affinity(struct device_node *dev,
+						      int index);
 extern int of_irq_get_byname(struct device_node *dev, const char *name);
 extern int of_irq_to_resource_table(struct device_node *dev,
 		struct resource *res, int nr_irqs);

@@ -76,6 +78,11 @@ static inline int of_irq_get_byname(struct device_node *dev, const char *name)
 {
 	return 0;
 }
+static inline const struct cpumask *of_irq_get_affinity(struct device_node *dev,
+							int index)
+{
+	return NULL;
+}
 static inline int of_irq_to_resource_table(struct device_node *dev,
 					   struct resource *res, int nr_irqs)
 {

index 09450349cf323..3a058f63ef0d3 100644
@@ -150,25 +150,37 @@ devm_platform_ioremap_resource_byname(struct platform_device *pdev,
 EXPORT_SYMBOL_GPL(devm_platform_ioremap_resource_byname);
 #endif /* CONFIG_HAS_IOMEM */
 
+static const struct cpumask *get_irq_affinity(struct platform_device *dev,
+					      unsigned int num)
+{
+	const struct cpumask *mask = NULL;
+#ifndef CONFIG_SPARC
+	struct fwnode_handle *fwnode = dev_fwnode(&dev->dev);
+
+	if (is_of_node(fwnode))
+		mask = of_irq_get_affinity(to_of_node(fwnode), num);
+	else if (is_acpi_device_node(fwnode))
+		mask = acpi_irq_get_affinity(ACPI_HANDLE_FWNODE(fwnode), num);
+#endif
+
+	return mask ?: cpu_possible_mask;
+}
+
 /**
- * platform_get_irq_optional - get an optional IRQ for a device
+ * platform_get_irq_affinity - get an optional IRQ and its affinity for a device
  * @dev: platform device
  * @num: IRQ number index
+ * @affinity: optional cpumask pointer to get the affinity of a per-cpu IRQ
  *
  * Gets an IRQ for a platform device. Device drivers should check the return
  * value for errors so as to not pass a negative integer value to the
- * request_irq() APIs. This is the same as platform_get_irq(), except that it
- * does not print an error message if an IRQ can not be obtained.
- *
- * For example::
- *
- *		int irq = platform_get_irq_optional(pdev, 0);
- *		if (irq < 0)
- *			return irq;
+ * request_irq() APIs. Optional affinity information is provided in the
+ * affinity pointer if available, and NULL otherwise.
  *
  * Return: non-zero IRQ number on success, negative error number on failure.
  */
-int platform_get_irq_optional(struct platform_device *dev, unsigned int num)
+int platform_get_irq_affinity(struct platform_device *dev, unsigned int num,
+			      const struct cpumask **affinity)
 {
 	int ret;
 #ifdef CONFIG_SPARC

@@ -236,8 +248,36 @@ int platform_get_irq_optional(struct platform_device *dev, unsigned int num)
 out:
 	if (WARN(!ret, "0 is an invalid IRQ number\n"))
 		return -EINVAL;
+
+	if (ret > 0 && affinity)
+		*affinity = get_irq_affinity(dev, num);
+
 	return ret;
 }
+EXPORT_SYMBOL_GPL(platform_get_irq_affinity);
+
+/**
+ * platform_get_irq_optional - get an optional IRQ for a device
+ * @dev: platform device
+ * @num: IRQ number index
+ *
+ * Gets an IRQ for a platform device. Device drivers should check the return
+ * value for errors so as to not pass a negative integer value to the
+ * request_irq() APIs. This is the same as platform_get_irq(), except that it
+ * does not print an error message if an IRQ can not be obtained.
+ *
+ * For example::
+ *
+ *		int irq = platform_get_irq_optional(pdev, 0);
+ *		if (irq < 0)
+ *			return irq;
+ *
+ * Return: non-zero IRQ number on success, negative error number on failure.
+ */
+int platform_get_irq_optional(struct platform_device *dev, unsigned int num)
+{
+	return platform_get_irq_affinity(dev, num, NULL);
+}
 EXPORT_SYMBOL_GPL(platform_get_irq_optional);
 
 /**

index 074754c23d330..ad66333ce85ce 100644
@@ -102,6 +102,8 @@ devm_platform_ioremap_resource_byname(struct platform_device *pdev,
 
 extern int platform_get_irq(struct platform_device *, unsigned int);
 extern int platform_get_irq_optional(struct platform_device *, unsigned int);
+extern int platform_get_irq_affinity(struct platform_device *, unsigned int,
+				     const struct cpumask **);
 extern int platform_irq_count(struct platform_device *);
 extern int devm_platform_get_irqs_affinity(struct platform_device *dev,
 					   struct irq_affinity *affd,

index 3de351e66ee84..cf0ba83c6eda6 100644
@@ -69,6 +69,8 @@ struct gic_chip_data {
 	bool			has_rss;
 	unsigned int		ppi_nr;
 	struct partition_desc	**ppi_descs;
+	struct partition_affinity *parts;
+	unsigned int		nr_parts;
 };
 
 #define T241_CHIPS_MAX		4

@@ -1797,11 +1799,58 @@ static int gic_irq_domain_select(struct irq_domain *d,
 	return d == partition_get_domain(gic_data.ppi_descs[ppi_idx]);
 }
 
+static int gic_irq_get_fwspec_info(struct irq_fwspec *fwspec, struct irq_fwspec_info *info)
+{
+	const struct cpumask *mask = NULL;
+
+	info->flags = 0;
+	info->affinity = NULL;
+
+	/* ACPI is not capable of describing PPI affinity -- yet */
+	if (!is_of_node(fwspec->fwnode))
+		return 0;
+
+	/* If the specifier provides an affinity, use it */
+	if (fwspec->param_count == 4 && fwspec->param[3]) {
+		struct fwnode_handle *fw;
+
+		switch (fwspec->param[0]) {
+		case 1:			/* PPI */
+		case 3:			/* EPPI */
+			break;
+		default:
+			return 0;
+		}
+
+		fw = of_fwnode_handle(of_find_node_by_phandle(fwspec->param[3]));
+		if (!fw)
+			return -ENOENT;
+
+		for (int i = 0; i < gic_data.nr_parts; i++) {
+			if (gic_data.parts[i].partition_id == fw) {
+				mask = &gic_data.parts[i].mask;
+				break;
+			}
+		}
+
+		if (!mask)
+			return -ENOENT;
+	} else {
+		mask = cpu_possible_mask;
+	}
+
+	info->affinity = mask;
+	info->flags = IRQ_FWSPEC_INFO_AFFINITY_VALID;
+
+	return 0;
+}
+
 static const struct irq_domain_ops gic_irq_domain_ops = {
 	.translate = gic_irq_domain_translate,
 	.alloc = gic_irq_domain_alloc,
 	.free = gic_irq_domain_free,
 	.select = gic_irq_domain_select,
+	.get_fwspec_info = gic_irq_get_fwspec_info,
 };
 
 static int partition_domain_translate(struct irq_domain *d,

@@ -1840,6 +1889,7 @@ static int partition_domain_translate(struct irq_domain *d,
 static const struct irq_domain_ops partition_domain_ops = {
 	.translate = partition_domain_translate,
 	.select = gic_irq_domain_select,
+	.get_fwspec_info = gic_irq_get_fwspec_info,
 };
 
 static bool gic_enable_quirk_msm8996(void *data)

@@ -2232,6 +2282,9 @@ static void __init gic_populate_ppi_partitions(struct device_node *gic_node)
 		part_idx++;
 	}
 
+	gic_data.parts = parts;
+	gic_data.nr_parts = nr_parts;
+
 	for (i = 0; i < gic_data.ppi_nr; i++) {
 		unsigned int irq;
 		struct partition_desc *desc;

index 032d66dceb8ec..cb8b6f40ce8d3 100644
@@ -651,6 +651,33 @@ static int aic_irq_domain_map(struct irq_domain *id, unsigned int irq,
 	return 0;
 }
 
+static int aic_irq_get_fwspec_info(struct irq_fwspec *fwspec, struct irq_fwspec_info *info)
+{
+	const struct cpumask *mask;
+	u32 intid;
+
+	info->flags = 0;
+	info->affinity = NULL;
+
+	if (fwspec->param[0] != AIC_FIQ)
+		return 0;
+
+	if (fwspec->param_count == 3)
+		intid = fwspec->param[1];
+	else
+		intid = fwspec->param[2];
+
+	if (aic_irqc->fiq_aff[intid])
+		mask = &aic_irqc->fiq_aff[intid]->aff;
+	else
+		mask = cpu_possible_mask;
+
+	info->affinity = mask;
+	info->flags = IRQ_FWSPEC_INFO_AFFINITY_VALID;
+
+	return 0;
+}
+
 static int aic_irq_domain_translate(struct irq_domain *id,
 				    struct irq_fwspec *fwspec,
 				    unsigned long *hwirq,

@@ -753,6 +780,7 @@ static const struct irq_domain_ops aic_irq_domain_ops = {
 	.translate	= aic_irq_domain_translate,
 	.alloc		= aic_irq_domain_alloc,
 	.free		= aic_irq_domain_free,
+	.get_fwspec_info = aic_irq_get_fwspec_info,
 };
 
 /*

index 43643d2c5bdd0..8f17160fec442 100644
@@ -1474,9 +1474,10 @@ static void arm_trbe_remove_cpuhp(struct trbe_drvdata *drvdata)
 static int arm_trbe_probe_irq(struct platform_device *pdev,
 			      struct trbe_drvdata *drvdata)
 {
+	const struct cpumask *affinity;
 	int ret;
 
-	drvdata->irq = platform_get_irq(pdev, 0);
+	drvdata->irq = platform_get_irq_affinity(pdev, 0, &affinity);
 	if (drvdata->irq < 0) {
 		pr_err("IRQ not found for the platform device\n");
 		return drvdata->irq;

@@ -1487,8 +1488,7 @@ static int arm_trbe_probe_irq(struct platform_device *pdev,
 		return -EINVAL;
 	}
 
-	if (irq_get_percpu_devid_partition(drvdata->irq, &drvdata->supported_cpus))
-		return -EINVAL;
+	cpumask_copy(&drvdata->supported_cpus, affinity);
 
 	drvdata->handle = alloc_percpu(struct perf_output_handle *);
 	if (!drvdata->handle)

index 118170a5cedef..9c0494d8a867a 100644
@@ -42,14 +42,13 @@ static int probe_current_pmu(struct arm_pmu *pmu,
 	return ret;
 }
 
-static int pmu_parse_percpu_irq(struct arm_pmu *pmu, int irq)
+static int pmu_parse_percpu_irq(struct arm_pmu *pmu, int irq,
+				const struct cpumask *affinity)
 {
-	int cpu, ret;
 	struct pmu_hw_events __percpu *hw_events = pmu->hw_events;
+	int cpu;
 
-	ret = irq_get_percpu_devid_partition(irq, &pmu->supported_cpus);
-	if (ret)
-		return ret;
+	cpumask_copy(&pmu->supported_cpus, affinity);
 
 	for_each_cpu(cpu, &pmu->supported_cpus)
 		per_cpu(hw_events->irq, cpu) = irq;

@@ -115,9 +114,12 @@ static int pmu_parse_irqs(struct arm_pmu *pmu)
 	}
 
 	if (num_irqs == 1) {
-		int irq = platform_get_irq(pdev, 0);
+		const struct cpumask *affinity;
+		int irq;
+
+		irq = platform_get_irq_affinity(pdev, 0, &affinity);
 		if ((irq > 0) && irq_is_percpu_devid(irq))
-			return pmu_parse_percpu_irq(pmu, irq);
+			return pmu_parse_percpu_irq(pmu, irq, affinity);
 	}
 
 	if (nr_cpu_ids != 1 && !pmu_has_irq_affinity(dev->of_node))

index fa50645feddad..1460b02d20e8b 100644
@@ -1287,8 +1287,10 @@ static void arm_spe_pmu_dev_teardown(struct arm_spe_pmu *spe_pmu)
 static int arm_spe_pmu_irq_probe(struct arm_spe_pmu *spe_pmu)
 {
 	struct platform_device *pdev = spe_pmu->pdev;
-	int irq = platform_get_irq(pdev, 0);
+	const struct cpumask *affinity;
+	int irq;
 
+	irq = platform_get_irq_affinity(pdev, 0, &affinity);
 	if (irq < 0)
 		return -ENXIO;
 

@@ -1297,10 +1299,7 @@ static int arm_spe_pmu_irq_probe(struct arm_spe_pmu *spe_pmu)
 		return -EINVAL;
 	}
 
-	if (irq_get_percpu_devid_partition(irq, &spe_pmu->supported_cpus)) {
-		dev_err(&pdev->dev, "failed to get PPI partition (%d)\n", irq);
-		return -EINVAL;
-	}
+	cpumask_copy(&spe_pmu->supported_cpus, affinity);
 
 	spe_pmu->irq = irq;
 	return 0;

index cf0ba83c6eda6..dd2d6d722fc5e 100644
@@ -230,9 +230,6 @@ static void __init gic_prio_init(void)
 		!cpus_have_group0);
 }
 
-/* rdist_nmi_refs[n] == number of cpus having the rdist interrupt n set as NMI */
-static refcount_t *rdist_nmi_refs;
-
 static struct gic_kvm_info gic_v3_kvm_info __initdata;
 static DEFINE_PER_CPU(bool, has_rss);
 

@@ -608,24 +605,6 @@ static u32 __gic_get_ppi_index(irq_hw_number_t hwirq)
 	}
 }
 
-static u32 __gic_get_rdist_index(irq_hw_number_t hwirq)
-{
-	switch (__get_intid_range(hwirq)) {
-	case SGI_RANGE:
-	case PPI_RANGE:
-		return hwirq;
-	case EPPI_RANGE:
-		return hwirq - EPPI_BASE_INTID + 32;
-	default:
-		unreachable();
-	}
-}
-
-static u32 gic_get_rdist_index(struct irq_data *d)
-{
-	return __gic_get_rdist_index(d->hwirq);
-}
-
 static int gic_irq_nmi_setup(struct irq_data *d)
 {
 	struct irq_desc *desc = irq_to_desc(d->irq);

@@ -646,20 +625,8 @@ static int gic_irq_nmi_setup(struct irq_data *d)
 		return -EINVAL;
 
 	/* desc lock should already be held */
-	if (gic_irq_in_rdist(d)) {
-		u32 idx = gic_get_rdist_index(d);
-
-		/*
-		 * Setting up a percpu interrupt as NMI, only switch handler
-		 * for first NMI
-		 */
-		if (!refcount_inc_not_zero(&rdist_nmi_refs[idx])) {
-			refcount_set(&rdist_nmi_refs[idx], 1);
-			desc->handle_irq = handle_percpu_devid_fasteoi_nmi;
-		}
-	} else {
+	if (!gic_irq_in_rdist(d))
 		desc->handle_irq = handle_fasteoi_nmi;
-	}
 
 	gic_irq_set_prio(d, dist_prio_nmi);
 

@@ -686,15 +653,8 @@ static void gic_irq_nmi_teardown(struct irq_data *d)
 		return;
 
 	/* desc lock should already be held */
-	if (gic_irq_in_rdist(d)) {
-		u32 idx = gic_get_rdist_index(d);
-
-		/* Tearing down NMI, only switch handler for last NMI */
-		if (refcount_dec_and_test(&rdist_nmi_refs[idx]))
-			desc->handle_irq = handle_percpu_devid_irq;
-	} else {
+	if (!gic_irq_in_rdist(d))
 		desc->handle_irq = handle_fasteoi_irq;
-	}
 
 	gic_irq_set_prio(d, dist_prio_irq);
 }

@@ -2080,19 +2040,9 @@ static const struct gic_quirk gic_quirks[] = {
 
 static void gic_enable_nmi_support(void)
 {
-	int i;
-
 	if (!gic_prio_masking_enabled() || nmi_support_forbidden)
 		return;
 
-	rdist_nmi_refs = kcalloc(gic_data.ppi_nr + SGI_NR,
-				 sizeof(*rdist_nmi_refs), GFP_KERNEL);
-	if (!rdist_nmi_refs)
-		return;
-
-	for (i = 0; i < gic_data.ppi_nr + SGI_NR; i++)
-		refcount_set(&rdist_nmi_refs[i], 0);
-
 	pr_info("Pseudo-NMIs enabled using %s ICC_PMR_EL1 synchronisation\n",
 		gic_has_relaxed_pmr_sync() ? "relaxed" : "forced");
 

index c67e76fbcc077..b728c18f6ded7 100644
@@ -655,7 +655,6 @@ extern void handle_bad_irq(struct irq_desc *desc);
 extern void handle_nested_irq(unsigned int irq);
 
 extern void handle_fasteoi_nmi(struct irq_desc *desc);
-extern void handle_percpu_devid_fasteoi_nmi(struct irq_desc *desc);
 
 extern int irq_chip_compose_msi_msg(struct irq_data *data, struct msi_msg *msg);
 extern int irq_chip_pm_get(struct irq_data *data);

index 3ffa0d80ddd19..633e1f67bb6f4 100644
@@ -929,31 +929,6 @@ void handle_percpu_devid_irq(struct irq_desc *desc)
 		chip->irq_eoi(&desc->irq_data);
 }
 
-/**
- * handle_percpu_devid_fasteoi_nmi - Per CPU local NMI handler with per cpu
- *				     dev ids
- * @desc:	the interrupt description structure for this irq
- *
- * Similar to handle_fasteoi_nmi, but handling the dev_id cookie
- * as a percpu pointer.
- */
-void handle_percpu_devid_fasteoi_nmi(struct irq_desc *desc)
-{
-	struct irq_chip *chip = irq_desc_get_chip(desc);
-	struct irqaction *action = desc->action;
-	unsigned int irq = irq_desc_get_irq(desc);
-	irqreturn_t res;
-
-	__kstat_incr_irqs_this_cpu(desc);
-
-	trace_irq_handler_entry(irq, action);
-	res = action->handler(irq, raw_cpu_ptr(action->percpu_dev_id));
-	trace_irq_handler_exit(irq, action, res);
-
-	if (chip->irq_eoi)
-		chip->irq_eoi(&desc->irq_data);
-}
-
 static void
 __irq_do_set_handler(struct irq_desc *desc, irq_flow_handler_t handle,
 		     int is_chained, const char *name)

index 51b6484c04934..0ec1a71ab4e84 100644
@@ -121,8 +121,10 @@ typedef irqreturn_t (*irq_handler_t)(int, void *);
  */
 struct irqaction {
 	irq_handler_t		handler;
-	void			*dev_id;
-	void __percpu		*percpu_dev_id;
+	union {
+		void		*dev_id;
+		void __percpu	*percpu_dev_id;
+	};
 	struct irqaction	*next;
 	irq_handler_t		thread_fn;
 	struct task_struct	*thread;

index c94837382037e..d9ddc30678b5d 100644
@@ -2442,6 +2442,24 @@ int setup_percpu_irq(unsigned int irq, struct irqaction *act)
 	return retval;
 }
 
+static
+struct irqaction *create_percpu_irqaction(irq_handler_t handler, unsigned long flags,
+					  const char *devname, void __percpu *dev_id)
+{
+	struct irqaction *action;
+
+	action = kzalloc(sizeof(struct irqaction), GFP_KERNEL);
+	if (!action)
+		return NULL;
+
+	action->handler = handler;
+	action->flags = flags | IRQF_PERCPU | IRQF_NO_SUSPEND;
+	action->name = devname;
+	action->percpu_dev_id = dev_id;
+
+	return action;
+}
+
 /**
  * __request_percpu_irq - allocate a percpu interrupt line
  * @irq:	Interrupt line to allocate

@@ -2450,9 +2468,9 @@ int setup_percpu_irq(unsigned int irq, struct irqaction *act)
  * @devname:	An ascii name for the claiming device
  * @dev_id:	A percpu cookie passed back to the handler function
  *
- * This call allocates interrupt resources and enables the interrupt on the
- * local CPU. If the interrupt is supposed to be enabled on other CPUs, it
- * has to be done on each CPU using enable_percpu_irq().
+ * This call allocates interrupt resources, but doesn't enable the interrupt
+ * on any CPU, as all percpu-devid interrupts are flagged with IRQ_NOAUTOEN.
+ * It has to be done on each CPU using enable_percpu_irq().
  *
  * @dev_id must be globally unique. It is a per-cpu variable, and
  * the handler gets called with the interrupted CPU's instance of

@@ -2477,15 +2495,10 @@ int __request_percpu_irq(unsigned int irq, irq_handler_t handler,
 	if (flags && flags != IRQF_TIMER)
 		return -EINVAL;
 
-	action = kzalloc(sizeof(struct irqaction), GFP_KERNEL);
+	action = create_percpu_irqaction(handler, flags, devname, dev_id);
 	if (!action)
 		return -ENOMEM;
 
-	action->handler = handler;
-	action->flags = flags | IRQF_PERCPU | IRQF_NO_SUSPEND;
-	action->name = devname;
-	action->percpu_dev_id = dev_id;
-
 	retval = irq_chip_pm_get(&desc->irq_data);
 	if (retval < 0) {
 		kfree(action);

@@ -2546,16 +2559,11 @@ int request_percpu_nmi(unsigned int irq, irq_handler_t handler,
 	if (irq_is_nmi(desc))
 		return -EINVAL;
 
-	action = kzalloc(sizeof(struct irqaction), GFP_KERNEL);
+	action = create_percpu_irqaction(handler, IRQF_NO_THREAD | IRQF_NOBALANCING,
+					 name, dev_id);
 	if (!action)
 		return -ENOMEM;
 
-	action->handler = handler;
-	action->flags = IRQF_PERCPU | IRQF_NO_SUSPEND | IRQF_NO_THREAD
-		| IRQF_NOBALANCING;
-	action->name = name;
-	action->percpu_dev_id = dev_id;
-
 	retval = irq_chip_pm_get(&desc->irq_data);
 	if (retval < 0)
 		goto err_out;

index 0ec1a71ab4e84..52147d5f432b3 100644
@@ -125,6 +125,7 @@ struct irqaction {
 		void		*dev_id;
 		void __percpu	*percpu_dev_id;
 	};
+	const struct cpumask	*affinity;
 	struct irqaction	*next;
 	irq_handler_t		thread_fn;
 	struct task_struct	*thread;

@@ -181,7 +182,7 @@ request_any_context_irq(unsigned int irq, irq_handler_t handler,
 extern int __must_check
 __request_percpu_irq(unsigned int irq, irq_handler_t handler,
 		     unsigned long flags, const char *devname,
-		     void __percpu *percpu_dev_id);
+		     const cpumask_t *affinity, void __percpu *percpu_dev_id);
 
 extern int __must_check
 request_nmi(unsigned int irq, irq_handler_t handler, unsigned long flags,

@@ -192,7 +193,7 @@ request_percpu_irq(unsigned int irq, irq_handler_t handler,
 		   const char *devname, void __percpu *percpu_dev_id)
 {
 	return __request_percpu_irq(irq, handler, 0,
-				    devname, percpu_dev_id);
+				    devname, NULL, percpu_dev_id);
 }
 
 extern int __must_check

index d9ddc30678b5d..5f4c651677436 100644
@@ -2444,10 +2444,14 @@ int setup_percpu_irq(unsigned int irq, struct irqaction *act)
 
 static
 struct irqaction *create_percpu_irqaction(irq_handler_t handler, unsigned long flags,
-					  const char *devname, void __percpu *dev_id)
+					  const char *devname, const cpumask_t *affinity,
+					  void __percpu *dev_id)
 {
 	struct irqaction *action;
 
+	if (!affinity)
+		affinity = cpu_possible_mask;
+
 	action = kzalloc(sizeof(struct irqaction), GFP_KERNEL);
 	if (!action)
 		return NULL;

@@ -2456,6 +2460,7 @@ struct irqaction *create_percpu_irqaction(irq_handler_t handler, unsigned long f
 	action->flags = flags | IRQF_PERCPU | IRQF_NO_SUSPEND;
 	action->name = devname;
 	action->percpu_dev_id = dev_id;
+	action->affinity = affinity;
 
 	return action;
 }

@@ -2466,6 +2471,7 @@ struct irqaction *create_percpu_irqaction(irq_handler_t handler, unsigned long f
  * @handler:	Function to be called when the IRQ occurs.
  * @flags:	Interrupt type flags (IRQF_TIMER only)
  * @devname:	An ascii name for the claiming device
+ * @affinity:	A cpumask describing the target CPUs for this interrupt
  * @dev_id:	A percpu cookie passed back to the handler function
  *
  * This call allocates interrupt resources, but doesn't enable the interrupt

@@ -2478,7 +2484,7 @@ struct irqaction *create_percpu_irqaction(irq_handler_t handler, unsigned long f
  */
 int __request_percpu_irq(unsigned int irq, irq_handler_t handler,
 			 unsigned long flags, const char *devname,
-			 void __percpu *dev_id)
+			 const cpumask_t *affinity, void __percpu *dev_id)
 {
 	struct irqaction *action;
 	struct irq_desc *desc;

@@ -2495,7 +2501,7 @@ int __request_percpu_irq(unsigned int irq, irq_handler_t handler,
 	if (flags && flags != IRQF_TIMER)
 		return -EINVAL;
 
-	action = create_percpu_irqaction(handler, flags, devname, dev_id);
+	action = create_percpu_irqaction(handler, flags, devname, affinity, dev_id);
 	if (!action)
 		return -ENOMEM;
 

@@ -2560,7 +2566,7 @@ int request_percpu_nmi(unsigned int irq, irq_handler_t handler,
 		return -EINVAL;
 
 	action = create_percpu_irqaction(handler, IRQF_NO_THREAD | IRQF_NOBALANCING,
-					 name, dev_id);
+					 name, NULL, dev_id);
 	if (!action)
 		return -ENOMEM;
 

index 68cea3a4a35ca..6fb838eee2e7d 100644
@@ -1094,7 +1094,7 @@ static void ipi_setup_sgi(int ipi)
 	irq = ipi_irq_base + ipi;
 
 	if (ipi_should_be_nmi(ipi)) {
-		err = request_percpu_nmi(irq, ipi_handler, "IPI", &irq_stat);
+		err = request_percpu_nmi(irq, ipi_handler, "IPI", NULL, &irq_stat);
 		WARN(err, "Could not request IRQ %d as NMI, err=%d\n", irq, err);
 	} else {
 		err = request_percpu_irq(irq, ipi_handler, "IPI", &irq_stat);

index 5c310e803dd78..22c601b46c858 100644
@@ -659,7 +659,7 @@ int armpmu_request_irq(int irq, int cpu)
 			irq_ops = &pmunmi_ops;
 		}
 	} else if (armpmu_count_irq_users(irq) == 0) {
-		err = request_percpu_nmi(irq, handler, "arm-pmu", &cpu_armpmu);
+		err = request_percpu_nmi(irq, handler, "arm-pmu", NULL, &cpu_armpmu);
 
 		/* If cannot get an NMI, get a normal interrupt */
 		if (err) {

index 52147d5f432b3..81506ab759b81 100644
@@ -197,8 +197,8 @@ request_percpu_irq(unsigned int irq, irq_handler_t handler,
 }
 
 extern int __must_check
-request_percpu_nmi(unsigned int irq, irq_handler_t handler,
-		   const char *devname, void __percpu *dev);
+request_percpu_nmi(unsigned int irq, irq_handler_t handler, const char *name,
+		   const struct cpumask *affinity, void __percpu *dev_id);
 
 extern const void *free_irq(unsigned int, void *);
 extern void free_percpu_irq(unsigned int, void __percpu *);

index 5f4c651677436..b1a3140e5f3c9 100644
@@ -2527,6 +2527,7 @@ EXPORT_SYMBOL_GPL(__request_percpu_irq);
  * @irq:	Interrupt line to allocate
  * @handler:	Function to be called when the IRQ occurs.
  * @name:	An ascii name for the claiming device
+ * @affinity:	A cpumask describing the target CPUs for this interrupt
  * @dev_id:	A percpu cookie passed back to the handler function
  *
  * This call allocates interrupt resources for a per CPU NMI. Per CPU NMIs

@@ -2543,8 +2544,8 @@ EXPORT_SYMBOL_GPL(__request_percpu_irq);
  * If the interrupt line cannot be used to deliver NMIs, function
  * will fail returning a negative value.
  */
-int request_percpu_nmi(unsigned int irq, irq_handler_t handler,
-		       const char *name, void __percpu *dev_id)
+int request_percpu_nmi(unsigned int irq, irq_handler_t handler, const char *name,
+		       const struct cpumask *affinity, void __percpu *dev_id)
 {
 	struct irqaction *action;
 	struct irq_desc *desc;

@@ -2561,12 +2562,13 @@ int request_percpu_nmi(unsigned int irq, irq_handler_t handler,
 	    !irq_supports_nmi(desc))
 		return -EINVAL;
 
-	/* The line cannot already be NMI */
-	if (irq_is_nmi(desc))
+	/* The line cannot be NMI already if the new request covers all CPUs */
+	if (irq_is_nmi(desc) &&
+	    (!affinity || cpumask_equal(affinity, cpu_possible_mask)))
 		return -EINVAL;
 
 	action = create_percpu_irqaction(handler, IRQF_NO_THREAD | IRQF_NOBALANCING,
-					 name, NULL, dev_id);
+					 name, affinity, dev_id);
 	if (!action)
 		return -ENOMEM;
 

index 633e1f67bb6f4..19e0a87a2663e 100644
@@ -897,8 +897,9 @@ void handle_percpu_irq(struct irq_desc *desc)
 void handle_percpu_devid_irq(struct irq_desc *desc)
 {
 	struct irq_chip *chip = irq_desc_get_chip(desc);
-	struct irqaction *action = desc->action;
 	unsigned int irq = irq_desc_get_irq(desc);
+	unsigned int cpu = smp_processor_id();
+	struct irqaction *action;
 	irqreturn_t res;
 
 	/*

@@ -910,12 +911,15 @@ void handle_percpu_devid_irq(struct irq_desc *desc)
 	if (chip->irq_ack)
 		chip->irq_ack(&desc->irq_data);
 
+	for (action = desc->action; action; action = action->next)
+		if (cpumask_test_cpu(cpu, action->affinity))
+			break;
+
 	if (likely(action)) {
 		trace_irq_handler_entry(irq, action);
 		res = action->handler(irq, raw_cpu_ptr(action->percpu_dev_id));
 		trace_irq_handler_exit(irq, action, res);
 	} else {
-		unsigned int cpu = smp_processor_id();
 		bool enabled = cpumask_test_cpu(cpu, desc->percpu_enabled);
 
 		if (enabled)

127 lines not on this page · raw message

index 0bb29316b4362..8b1b4c8a4f54c 100644
@@ -2470,6 +2470,9 @@ int setup_percpu_irq(unsigned int irq, struct irqaction *act)
 	if (retval < 0)
 		return retval;
 
+	if (!act->affinity)
+		act->affinity = cpu_online_mask;
+
 	retval = __setup_irq(irq, desc, act);
 
 	if (retval)

index 81506ab759b81..fa62ab556ee32 100644
@@ -196,6 +196,15 @@ request_percpu_irq(unsigned int irq, irq_handler_t handler,
 				    devname, NULL, percpu_dev_id);
 }
 
+static inline int __must_check
+request_percpu_irq_affinity(unsigned int irq, irq_handler_t handler,
+			    const char *devname, const cpumask_t *affinity,
+			    void __percpu *percpu_dev_id)
+{
+	return __request_percpu_irq(irq, handler, 0,
+				    devname, affinity, percpu_dev_id);
+}
+
 extern int __must_check
 request_percpu_nmi(unsigned int irq, irq_handler_t handler, const char *name,
 		   const struct cpumask *affinity, void __percpu *dev_id);

index 22c601b46c858..959ceb3d1f556 100644
@@ -26,7 +26,8 @@
 
 #include <asm/irq_regs.h>
 
-static int armpmu_count_irq_users(const int irq);
+static int armpmu_count_irq_users(const struct cpumask *affinity,
+				  const int irq);
 
 struct pmu_irq_ops {
 	void (*enable_pmuirq)(unsigned int irq);

@@ -64,7 +65,9 @@ static void armpmu_enable_percpu_pmuirq(unsigned int irq)
 static void armpmu_free_percpu_pmuirq(unsigned int irq, int cpu,
 				   void __percpu *devid)
 {
-	if (armpmu_count_irq_users(irq) == 1)
+	struct arm_pmu *armpmu = *per_cpu_ptr((void * __percpu *)devid, cpu);
+
+	if (armpmu_count_irq_users(&armpmu->supported_cpus, irq) == 1)
 		free_percpu_irq(irq, devid);
 }
 

@@ -89,7 +92,9 @@ static void armpmu_disable_percpu_pmunmi(unsigned int irq)
 static void armpmu_free_percpu_pmunmi(unsigned int irq, int cpu,
 				      void __percpu *devid)
 {
-	if (armpmu_count_irq_users(irq) == 1)
+	struct arm_pmu *armpmu = *per_cpu_ptr((void * __percpu *)devid, cpu);
+
+	if (armpmu_count_irq_users(&armpmu->supported_cpus, irq) == 1)
 		free_percpu_nmi(irq, devid);
 }
 

@@ -580,11 +585,11 @@ static const struct attribute_group armpmu_common_attr_group = {
 	.attrs = armpmu_common_attrs,
 };
 
-static int armpmu_count_irq_users(const int irq)
+static int armpmu_count_irq_users(const struct cpumask *affinity, const int irq)
 {
 	int cpu, count = 0;
 
-	for_each_possible_cpu(cpu) {
+	for_each_cpu(cpu, affinity) {
 		if (per_cpu(cpu_irq, cpu) == irq)
 			count++;
 	}

@@ -592,12 +597,13 @@ static int armpmu_count_irq_users(const int irq)
 	return count;
 }
 
-static const struct pmu_irq_ops *armpmu_find_irq_ops(int irq)
+static const struct pmu_irq_ops *
+armpmu_find_irq_ops(const struct cpumask *affinity, int irq)
 {
 	const struct pmu_irq_ops *ops = NULL;
 	int cpu;
 
-	for_each_possible_cpu(cpu) {
+	for_each_cpu(cpu, affinity) {
 		if (per_cpu(cpu_irq, cpu) != irq)
 			continue;
 

@@ -609,22 +615,25 @@ static const struct pmu_irq_ops *armpmu_find_irq_ops(int irq)
 	return ops;
 }
 
-void armpmu_free_irq(int irq, int cpu)
+void armpmu_free_irq(struct arm_pmu * __percpu *armpmu, int irq, int cpu)
 {
 	if (per_cpu(cpu_irq, cpu) == 0)
 		return;
 	if (WARN_ON(irq != per_cpu(cpu_irq, cpu)))
 		return;
 
-	per_cpu(cpu_irq_ops, cpu)->free_pmuirq(irq, cpu, &cpu_armpmu);
+	per_cpu(cpu_irq_ops, cpu)->free_pmuirq(irq, cpu, armpmu);
 
 	per_cpu(cpu_irq, cpu) = 0;
 	per_cpu(cpu_irq_ops, cpu) = NULL;
 }
 
-int armpmu_request_irq(int irq, int cpu)
+int armpmu_request_irq(struct arm_pmu * __percpu *pcpu_armpmu, int irq, int cpu)
 {
 	int err = 0;
+	struct arm_pmu **armpmu = per_cpu_ptr(pcpu_armpmu, cpu);
+	const struct cpumask *affinity = *armpmu ? &(*armpmu)->supported_cpus :
+						   cpu_possible_mask; /* ACPI */
 	const irq_handler_t handler = armpmu_dispatch_irq;
 	const struct pmu_irq_ops *irq_ops;
 

@@ -646,25 +655,24 @@ int armpmu_request_irq(int irq, int cpu)
 			    IRQF_NOBALANCING | IRQF_NO_AUTOEN |
 			    IRQF_NO_THREAD;
 
-		err = request_nmi(irq, handler, irq_flags, "arm-pmu",
-				  per_cpu_ptr(&cpu_armpmu, cpu));
+		err = request_nmi(irq, handler, irq_flags, "arm-pmu", armpmu);
 
 		/* If cannot get an NMI, get a normal interrupt */
 		if (err) {
 			err = request_irq(irq, handler, irq_flags, "arm-pmu",
-					  per_cpu_ptr(&cpu_armpmu, cpu));
+					  armpmu);
 			irq_ops = &pmuirq_ops;
 		} else {
 			has_nmi = true;
 			irq_ops = &pmunmi_ops;
 		}
-	} else if (armpmu_count_irq_users(irq) == 0) {
-		err = request_percpu_nmi(irq, handler, "arm-pmu", NULL, &cpu_armpmu);
+	} else if (armpmu_count_irq_users(affinity, irq) == 0) {
+		err = request_percpu_nmi(irq, handler, "arm-pmu", affinity, pcpu_armpmu);
 
 		/* If cannot get an NMI, get a normal interrupt */
 		if (err) {
-			err = request_percpu_irq(irq, handler, "arm-pmu",
-						 &cpu_armpmu);
+			err = request_percpu_irq_affinity(irq, handler, "arm-pmu",
+							  affinity, pcpu_armpmu);
 			irq_ops = &percpu_pmuirq_ops;
 		} else {
 			has_nmi = true;

@@ -672,7 +680,7 @@ int armpmu_request_irq(int irq, int cpu)
 		}
 	} else {
 		/* Per cpudevid irq was already requested by another CPU */
-		irq_ops = armpmu_find_irq_ops(irq);
+		irq_ops = armpmu_find_irq_ops(affinity, irq);
 
 		if (WARN_ON(!irq_ops))
 			err = -EINVAL;

index 05dda19c5359a..e80f76d95e68b 100644
@@ -218,7 +218,7 @@ static int arm_pmu_acpi_parse_irqs(void)
 		 * them with their PMUs.
 		 */
 		per_cpu(pmu_irqs, cpu) = irq;
-		err = armpmu_request_irq(irq, cpu);
+		err = armpmu_request_irq(&probed_pmus, irq, cpu);
 		if (err)
 			goto out_err;
 	}

index 9c0494d8a867a..1c9e50a132015 100644
@@ -165,7 +165,7 @@ static int armpmu_request_irqs(struct arm_pmu *armpmu)
 		if (!irq)
 			continue;
 
-		err = armpmu_request_irq(irq, cpu);
+		err = armpmu_request_irq(&hw_events->percpu_pmu, irq, cpu);
 		if (err)
 			break;
 	}

@@ -181,7 +181,7 @@ static void armpmu_free_irqs(struct arm_pmu *armpmu)
 	for_each_cpu(cpu, &armpmu->supported_cpus) {
 		int irq = per_cpu(hw_events->irq, cpu);
 
-		armpmu_free_irq(irq, cpu);
+		armpmu_free_irq(&hw_events->percpu_pmu, irq, cpu);
 	}
 }
 

index 93c9a26492fcf..6690bd77aa4ee 100644
@@ -190,8 +190,8 @@ bool arm_pmu_irq_is_nmi(void);
 struct arm_pmu *armpmu_alloc(void);
 void armpmu_free(struct arm_pmu *pmu);
 int armpmu_register(struct arm_pmu *pmu);
-int armpmu_request_irq(int irq, int cpu);
-void armpmu_free_irq(int irq, int cpu);
+int armpmu_request_irq(struct arm_pmu * __percpu *armpmu, int irq, int cpu);
+void armpmu_free_irq(struct arm_pmu * __percpu *armpmu, int irq, int cpu);
 
 #define ARMV8_PMU_PDEV_NAME "armv8-pmu"