arm/arm64: Turning IPIs into normal interrupts

index 8d5bc2c237d7..726f94d8b8cc 100644
@@ -621,6 +621,7 @@ static inline int irq_set_parent(int irq, int parent_irq)
  */
 extern void handle_level_irq(struct irq_desc *desc);
 extern void handle_fasteoi_irq(struct irq_desc *desc);
+extern void handle_percpu_devid_fasteoi_ipi(struct irq_desc *desc);
 extern void handle_edge_irq(struct irq_desc *desc);
 extern void handle_edge_eoi_irq(struct irq_desc *desc);
 extern void handle_simple_irq(struct irq_desc *desc);

index 41e7e37a0928..b9c49a61f8bb 100644
@@ -955,6 +955,33 @@ void handle_percpu_devid_irq(struct irq_desc *desc)
 		chip->irq_eoi(&desc->irq_data);
 }
 
+/**
+ * handle_percpu_devid_fasteoi_ipi - Per CPU local IPI handler with per cpu
+ *				     dev ids
+ * @desc:	the interrupt description structure for this irq
+ *
+ * The biggest difference with the IRQ version is that the interrupt is
+ * EOIed early, as the IPI could result in a context switch, and we need to
+ * make sure the IPI can fire again. We also assume that the arch code has
+ * registered an action. If not, we are positively doomed.
+ */
+void handle_percpu_devid_fasteoi_ipi(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);
+
+	if (chip->irq_eoi)
+		chip->irq_eoi(&desc->irq_data);
+
+	trace_irq_handler_entry(irq, action);
+	res = action->handler(irq, raw_cpu_ptr(action->percpu_dev_id));
+	trace_irq_handler_exit(irq, action, res);
+}
+
 /**
  * handle_percpu_devid_fasteoi_nmi - Per CPU local NMI handler with per cpu
  *				     dev ids

index 726f94d8b8cc..48f23533aec8 100644
@@ -71,6 +71,7 @@ enum irqchip_irq_state;
  *				  it from the spurious interrupt detection
  *				  mechanism and from core side polling.
  * IRQ_DISABLE_UNLAZY		- Disable lazy irq disable
+ * IRQ_HIDDEN			- Don't show up in /proc/interrupts
  */
 enum {
 	IRQ_TYPE_NONE		= 0x00000000,

@@ -97,13 +98,14 @@ enum {
 	IRQ_PER_CPU_DEVID	= (1 << 17),
 	IRQ_IS_POLLED		= (1 << 18),
 	IRQ_DISABLE_UNLAZY	= (1 << 19),
+	IRQ_HIDDEN		= (1 << 20),
 };
 
 #define IRQF_MODIFY_MASK	\
 	(IRQ_TYPE_SENSE_MASK | IRQ_NOPROBE | IRQ_NOREQUEST | \
 	 IRQ_NOAUTOEN | IRQ_MOVE_PCNTXT | IRQ_LEVEL | IRQ_NO_BALANCING | \
 	 IRQ_PER_CPU | IRQ_NESTED_THREAD | IRQ_NOTHREAD | IRQ_PER_CPU_DEVID | \
-	 IRQ_IS_POLLED | IRQ_DISABLE_UNLAZY)
+	 IRQ_IS_POLLED | IRQ_DISABLE_UNLAZY | IRQ_HIDDEN)
 
 #define IRQ_NO_BALANCING_MASK	(IRQ_PER_CPU | IRQ_NO_BALANCING)
 

index 4f9f844074db..ce93626470c3 100644
@@ -131,6 +131,7 @@ static const struct irq_bit_descr irqdesc_states[] = {
 	BIT_MASK_DESCR(_IRQ_PER_CPU_DEVID),
 	BIT_MASK_DESCR(_IRQ_IS_POLLED),
 	BIT_MASK_DESCR(_IRQ_DISABLE_UNLAZY),
+	BIT_MASK_DESCR(_IRQ_HIDDEN),
 };
 
 static const struct irq_bit_descr irqdesc_istates[] = {

index 32c071d7bc03..72513ed2a5fc 100644
@@ -485,7 +485,7 @@ int show_interrupts(struct seq_file *p, void *v)
 
 	rcu_read_lock();
 	desc = irq_to_desc(i);
-	if (!desc)
+	if (!desc || irq_settings_is_hidden(desc))
 		goto outsparse;
 
 	if (desc->kstat_irqs)

index e43795cd2ccf..403378b9947b 100644
@@ -17,6 +17,7 @@ enum {
 	_IRQ_PER_CPU_DEVID	= IRQ_PER_CPU_DEVID,
 	_IRQ_IS_POLLED		= IRQ_IS_POLLED,
 	_IRQ_DISABLE_UNLAZY	= IRQ_DISABLE_UNLAZY,
+	_IRQ_HIDDEN		= IRQ_HIDDEN,
 	_IRQF_MODIFY_MASK	= IRQF_MODIFY_MASK,
 };
 

@@ -31,6 +32,7 @@ enum {
 #define IRQ_PER_CPU_DEVID	GOT_YOU_MORON
 #define IRQ_IS_POLLED		GOT_YOU_MORON
 #define IRQ_DISABLE_UNLAZY	GOT_YOU_MORON
+#define IRQ_HIDDEN		GOT_YOU_MORON
 #undef IRQF_MODIFY_MASK
 #define IRQF_MODIFY_MASK	GOT_YOU_MORON
 

@@ -167,3 +169,8 @@ static inline void irq_settings_clr_disable_unlazy(struct irq_desc *desc)
 {
 	desc->status_use_accessors &= ~_IRQ_DISABLE_UNLAZY;
 }
+
+static inline bool irq_settings_is_hidden(struct irq_desc *desc)
+{
+	return desc->status_use_accessors & _IRQ_HIDDEN;
+}

index ea268d88b6f7..4537a4620e3d 100644
@@ -74,6 +74,11 @@ extern void set_smp_cross_call(void (*)(const struct cpumask *, unsigned int));
 
 extern void (*__smp_cross_call)(const struct cpumask *, unsigned int);
 
+/*
+ * Register IPI interrupts with the arch SMP code
+ */
+extern void set_smp_ipi_range(int ipi_base, int nr_ipi);
+
 /*
  * Called from the secondary holding pen, this is the secondary CPU entry point.
  */

154 lines not on this page · raw message

index a91f21e3c5b5..0e29730295ca 100644
@@ -45,6 +45,11 @@ extern void smp_init_cpus(void);
  */
 extern void set_smp_cross_call(void (*)(const struct cpumask *, unsigned int));
 
+/*
+ * Register IPI interrupts with the arch SMP code
+ */
+extern void set_smp_ipi_range(int ipi_base, int nr_ipi);
+
 /*
  * Called from platform specific assembly code, this is the
  * secondary CPU entry point.

177 lines not on this page · raw message

index cc46bc2d634b..19b294ed48ba 100644
@@ -112,6 +112,7 @@ static DEFINE_PER_CPU(bool, has_rss);
 #define DEFAULT_PMR_VALUE	0xf0
 
 enum gic_intid_range {
+	SGI_RANGE,
 	PPI_RANGE,
 	SPI_RANGE,
 	EPPI_RANGE,

@@ -123,6 +124,8 @@ enum gic_intid_range {
 static enum gic_intid_range __get_intid_range(irq_hw_number_t hwirq)
 {
 	switch (hwirq) {
+	case 0 ... 15:
+		return SGI_RANGE;
 	case 16 ... 31:
 		return PPI_RANGE;
 	case 32 ... 1019:

@@ -148,15 +151,22 @@ static inline unsigned int gic_irq(struct irq_data *d)
 	return d->hwirq;
 }
 
-static inline int gic_irq_in_rdist(struct irq_data *d)
+static inline bool gic_irq_in_rdist(struct irq_data *d)
 {
-	enum gic_intid_range range = get_intid_range(d);
-	return range == PPI_RANGE || range == EPPI_RANGE;
+	switch (get_intid_range(d)) {
+	case SGI_RANGE:
+	case PPI_RANGE:
+	case EPPI_RANGE:
+		return true;
+	default:
+		return false;
+	}
 }
 
 static inline void __iomem *gic_dist_base(struct irq_data *d)
 {
 	switch (get_intid_range(d)) {
+	case SGI_RANGE:
 	case PPI_RANGE:
 	case EPPI_RANGE:
 		/* SGI+PPI -> SGI_base for this CPU */

@@ -253,6 +263,7 @@ static void gic_enable_redist(bool enable)
 static u32 convert_offset_index(struct irq_data *d, u32 offset, u32 *index)
 {
 	switch (get_intid_range(d)) {
+	case SGI_RANGE:
 	case PPI_RANGE:
 	case SPI_RANGE:
 		*index = d->hwirq;

@@ -1277,6 +1288,7 @@ static int gic_irq_domain_map(struct irq_domain *d, unsigned int irq,
 		chip = &gic_eoimode1_chip;
 
 	switch (__get_intid_range(hw)) {
+	case SGI_RANGE:
 	case PPI_RANGE:
 	case EPPI_RANGE:
 		irq_set_percpu_devid(irq);

index 19b294ed48ba..d275e9b9533d 100644
@@ -36,6 +36,8 @@
 #define FLAGS_WORKAROUND_GICR_WAKER_MSM8996	(1ULL << 0)
 #define FLAGS_WORKAROUND_CAVIUM_ERRATUM_38539	(1ULL << 1)
 
+#define GIC_IRQ_TYPE_PARTITION	(GIC_IRQ_TYPE_LPI + 1)
+
 struct redist_region {
 	void __iomem		*redist_base;
 	phys_addr_t		phys_base;

@@ -657,38 +659,14 @@ static asmlinkage void __exception_irq_entry gic_handle_irq(struct pt_regs *regs
 	if ((irqnr >= 1020 && irqnr <= 1023))
 		return;
 
-	/* Treat anything but SGIs in a uniform way */
-	if (likely(irqnr > 15)) {
-		int err;
-
-		if (static_branch_likely(&supports_deactivate_key))
-			gic_write_eoir(irqnr);
-		else
-			isb();
-
-		err = handle_domain_irq(gic_data.domain, irqnr, regs);
-		if (err) {
-			WARN_ONCE(true, "Unexpected interrupt received!\n");
-			gic_deactivate_unhandled(irqnr);
-		}
-		return;
-	}
-	if (irqnr < 16) {
+	if (static_branch_likely(&supports_deactivate_key))
 		gic_write_eoir(irqnr);
-		if (static_branch_likely(&supports_deactivate_key))
-			gic_write_dir(irqnr);
-#ifdef CONFIG_SMP
-		/*
-		 * Unlike GICv2, we don't need an smp_rmb() here.
-		 * The control dependency from gic_read_iar to
-		 * the ISB in gic_write_eoir is enough to ensure
-		 * that any shared data read by handle_IPI will
-		 * be read after the ACK.
-		 */
-		handle_IPI(irqnr, regs);
-#else
-		WARN_ONCE(true, "Unexpected SGI received!\n");
-#endif
+	else
+		isb();
+
+	if (handle_domain_irq(gic_data.domain, irqnr, regs)) {
+		WARN_ONCE(true, "Unexpected interrupt received!\n");
+		gic_deactivate_unhandled(irqnr);
 	}
 }
 

@@ -1136,11 +1114,11 @@ static void gic_send_sgi(u64 cluster_id, u16 tlist, unsigned int irq)
 	gic_write_sgi1r(val);
 }
 
-static void gic_raise_softirq(const struct cpumask *mask, unsigned int irq)
+static void gic_ipi_send_mask(struct irq_data *d, const struct cpumask *mask)
 {
 	int cpu;
 
-	if (WARN_ON(irq >= 16))
+	if (WARN_ON(d->hwirq >= 16))
 		return;
 
 	/*

@@ -1154,7 +1132,7 @@ static void gic_raise_softirq(const struct cpumask *mask, unsigned int irq)
 		u16 tlist;
 
 		tlist = gic_compute_target_list(&cpu, mask, cluster_id);
-		gic_send_sgi(cluster_id, tlist, irq);
+		gic_send_sgi(cluster_id, tlist, d->hwirq);
 	}
 
 	/* Force the above writes to ICC_SGI1R_EL1 to be executed */

@@ -1163,10 +1141,24 @@ static void gic_raise_softirq(const struct cpumask *mask, unsigned int irq)
 
 static void __init gic_smp_init(void)
 {
-	set_smp_cross_call(gic_raise_softirq);
+	struct irq_fwspec sgi_fwspec = {
+		.fwnode		= gic_data.fwnode,
+		.param_count	= 1,
+	};
+	int base_sgi;
+
 	cpuhp_setup_state_nocalls(CPUHP_AP_IRQ_GIC_STARTING,
 				  "irqchip/arm/gicv3:starting",
 				  gic_starting_cpu, NULL);
+
+	/* Register all 8 non-secure SGIs */
+	base_sgi = __irq_domain_alloc_irqs(gic_data.domain, -1, 8,
+					   NUMA_NO_NODE, &sgi_fwspec,
+					   false, NULL);
+	if (WARN_ON(base_sgi <= 0))
+		return;
+
+	set_smp_ipi_range(base_sgi, 8);
 }
 
 static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val,

@@ -1215,6 +1207,7 @@ static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val,
 }
 #else
 #define gic_set_affinity	NULL
+#define gic_ipi_send_mask	NULL
 #define gic_smp_init()		do { } while(0)
 #endif
 

@@ -1257,6 +1250,7 @@ static struct irq_chip gic_chip = {
 	.irq_set_irqchip_state	= gic_irq_set_irqchip_state,
 	.irq_nmi_setup		= gic_irq_nmi_setup,
 	.irq_nmi_teardown	= gic_irq_nmi_teardown,
+	.ipi_send_mask		= gic_ipi_send_mask,
 	.flags			= IRQCHIP_SET_TYPE_MASKED |
 				  IRQCHIP_SKIP_SET_WAKE |
 				  IRQCHIP_MASK_ON_SUSPEND,

@@ -1274,6 +1268,7 @@ static struct irq_chip gic_eoimode1_chip = {
 	.irq_set_vcpu_affinity	= gic_irq_set_vcpu_affinity,
 	.irq_nmi_setup		= gic_irq_nmi_setup,
 	.irq_nmi_teardown	= gic_irq_nmi_teardown,
+	.ipi_send_mask		= gic_ipi_send_mask,
 	.flags			= IRQCHIP_SET_TYPE_MASKED |
 				  IRQCHIP_SKIP_SET_WAKE |
 				  IRQCHIP_MASK_ON_SUSPEND,

@@ -1289,6 +1284,12 @@ static int gic_irq_domain_map(struct irq_domain *d, unsigned int irq,
 
 	switch (__get_intid_range(hw)) {
 	case SGI_RANGE:
+		irq_set_percpu_devid(irq);
+		irq_domain_set_info(d, irq, hw, chip, d->host_data,
+				    handle_percpu_devid_fasteoi_ipi,
+				    NULL, NULL);
+		break;
+
 	case PPI_RANGE:
 	case EPPI_RANGE:
 		irq_set_percpu_devid(irq);

@@ -1318,13 +1319,17 @@ static int gic_irq_domain_map(struct irq_domain *d, unsigned int irq,
 	return 0;
 }
 
-#define GIC_IRQ_TYPE_PARTITION	(GIC_IRQ_TYPE_LPI + 1)
-
 static int gic_irq_domain_translate(struct irq_domain *d,
 				    struct irq_fwspec *fwspec,
 				    unsigned long *hwirq,
 				    unsigned int *type)
 {
+	if (fwspec->param_count == 1 && fwspec->param[0] < 16) {
+		*hwirq = fwspec->param[0];
+		*type = IRQ_TYPE_EDGE_RISING;
+		return 0;
+	}
+
 	if (is_of_node(fwspec->fwnode)) {
 		if (fwspec->param_count < 3)
 			return -EINVAL;

@@ -1656,9 +1661,9 @@ static int __init gic_init_bases(void __iomem *dist_base,
 
 	gic_update_rdist_properties();
 
-	gic_smp_init();
 	gic_dist_init();
 	gic_cpu_init();
+	gic_smp_init();
 	gic_cpu_pm_init();
 
 	if (gic_dist_supports_lpis()) {

index 00de05abd3c3..c17fabd6741e 100644
@@ -329,10 +329,8 @@ static int gic_irq_set_vcpu_affinity(struct irq_data *d, void *vcpu)
 static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val,
 			    bool force)
 {
-	void __iomem *reg = gic_dist_base(d) + GIC_DIST_TARGET + (gic_irq(d) & ~3);
-	unsigned int cpu, shift = (gic_irq(d) % 4) * 8;
-	u32 val, mask, bit;
-	unsigned long flags;
+	void __iomem *reg = gic_dist_base(d) + GIC_DIST_TARGET + gic_irq(d);
+	unsigned int cpu;
 
 	if (!force)
 		cpu = cpumask_any_and(mask_val, cpu_online_mask);

@@ -342,13 +340,7 @@ static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val,
 	if (cpu >= NR_GIC_CPU_IF || cpu >= nr_cpu_ids)
 		return -EINVAL;
 
-	gic_lock_irqsave(flags);
-	mask = 0xff << shift;
-	bit = gic_cpu_map[cpu] << shift;
-	val = readl_relaxed(reg) & ~mask;
-	writel_relaxed(val | bit, reg);
-	gic_unlock_irqrestore(flags);
-
+	writeb_relaxed(gic_cpu_map[cpu], reg);
 	irq_data_update_effective_affinity(d, cpumask_of(cpu));
 
 	return IRQ_SET_MASK_OK_DONE;

index d329ec3d64d8..dca40a974b7a 100644
@@ -107,6 +107,8 @@ static DEFINE_RAW_SPINLOCK(cpu_map_lock);
 
 #endif
 
+static DEFINE_STATIC_KEY_FALSE(needs_rmw_access);
+
 /*
  * The GIC mapping of CPU interfaces does not necessarily match
  * the logical CPU numbering.  Let's use a mapping as returned

@@ -774,6 +776,25 @@ static int gic_pm_init(struct gic_chip_data *gic)
 #endif
 
 #ifdef CONFIG_SMP
+static void rmw_writeb(u8 bval, void __iomem *addr)
+{
+	static DEFINE_RAW_SPINLOCK(rmw_lock);
+	unsigned long offset = (unsigned long)addr & ~3UL;
+	unsigned long shift = offset * 8;
+	unsigned long flags;
+	u32 val;
+
+	raw_spin_lock_irqsave(&rmw_lock, flags);
+
+	addr -= offset;
+	val = readl_relaxed(addr);
+	val &= ~(0xffUL << shift);
+	val |= (u32)bval << shift;
+	writel_relaxed(val, addr);
+
+	raw_spin_unlock_irqrestore(&rmw_lock, flags);
+}
+
 static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val,
 			    bool force)
 {

@@ -788,7 +809,10 @@ static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val,
 	if (cpu >= NR_GIC_CPU_IF || cpu >= nr_cpu_ids)
 		return -EINVAL;
 
-	writeb_relaxed(gic_cpu_map[cpu], reg);
+	if (static_branch_unlikely(&needs_rmw_access))
+		rmw_writeb(gic_cpu_map[cpu], reg);
+	else
+		writeb_relaxed(gic_cpu_map[cpu], reg);
 	irq_data_update_effective_affinity(d, cpumask_of(cpu));
 
 	return IRQ_SET_MASK_OK_DONE;

@@ -1375,6 +1399,29 @@ static bool gic_check_eoimode(struct device_node *node, void __iomem **base)
 	return true;
 }
 
+static bool gic_enable_rmw_access(void *data)
+{
+	/*
+	 * The EMEV2 class of machines has a broken interconnect, and
+	 * locks up on accesses that are less than 32bit. So far, only
+	 * the affinity setting requires it.
+	 */
+	if (of_machine_is_compatible("renesas,emev2")) {
+		static_branch_enable(&needs_rmw_access);
+		return true;
+	}
+
+	return false;
+}
+
+static const struct gic_quirk gic_quirks[] = {
+	{
+		.desc		= "Implementation with broken byte access",
+		.compatible	= "arm,pl390",
+		.init		= gic_enable_rmw_access,
+	},
+};
+
 static int gic_of_setup(struct gic_chip_data *gic, struct device_node *node)
 {
 	if (!gic || !node)

@@ -1391,6 +1438,8 @@ static int gic_of_setup(struct gic_chip_data *gic, struct device_node *node)
 	if (of_property_read_u32(node, "cpu-offset", &gic->percpu_offset))
 		gic->percpu_offset = 0;
 
+	gic_enable_of_quirks(node, gic_quirks, gic);
+
 	return 0;
 
 error:

index c17fabd6741e..801a5a5004d6 100644
@@ -325,28 +325,6 @@ static int gic_irq_set_vcpu_affinity(struct irq_data *d, void *vcpu)
 	return 0;
 }
 
-#ifdef CONFIG_SMP
-static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val,
-			    bool force)
-{
-	void __iomem *reg = gic_dist_base(d) + GIC_DIST_TARGET + gic_irq(d);
-	unsigned int cpu;
-
-	if (!force)
-		cpu = cpumask_any_and(mask_val, cpu_online_mask);
-	else
-		cpu = cpumask_first(mask_val);
-
-	if (cpu >= NR_GIC_CPU_IF || cpu >= nr_cpu_ids)
-		return -EINVAL;
-
-	writeb_relaxed(gic_cpu_map[cpu], reg);
-	irq_data_update_effective_affinity(d, cpumask_of(cpu));
-
-	return IRQ_SET_MASK_OK_DONE;
-}
-#endif
-
 static void __exception_irq_entry gic_handle_irq(struct pt_regs *regs)
 {
 	u32 irqstat, irqnr;

@@ -795,6 +773,26 @@ static int gic_pm_init(struct gic_chip_data *gic)
 #endif
 
 #ifdef CONFIG_SMP
+static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val,
+			    bool force)
+{
+	void __iomem *reg = gic_dist_base(d) + GIC_DIST_TARGET + gic_irq(d);
+	unsigned int cpu;
+
+	if (!force)
+		cpu = cpumask_any_and(mask_val, cpu_online_mask);
+	else
+		cpu = cpumask_first(mask_val);
+
+	if (cpu >= NR_GIC_CPU_IF || cpu >= nr_cpu_ids)
+		return -EINVAL;
+
+	writeb_relaxed(gic_cpu_map[cpu], reg);
+	irq_data_update_effective_affinity(d, cpumask_of(cpu));
+
+	return IRQ_SET_MASK_OK_DONE;
+}
+
 static void gic_raise_softirq(const struct cpumask *mask, unsigned int irq)
 {
 	int cpu;

@@ -824,6 +822,23 @@ static void gic_raise_softirq(const struct cpumask *mask, unsigned int irq)
 
 	gic_unlock_irqrestore(flags);
 }
+
+static int gic_starting_cpu(unsigned int cpu)
+{
+	gic_cpu_init(&gic_data[0]);
+	return 0;
+}
+
+static __init void gic_smp_init(void)
+{
+	set_smp_cross_call(gic_raise_softirq);
+	cpuhp_setup_state_nocalls(CPUHP_AP_IRQ_GIC_STARTING,
+				  "irqchip/arm/gic:starting",
+				  gic_starting_cpu, NULL);
+}
+#else
+#define gic_smp_init()		do { } while(0)
+#define gic_set_affinity	NULL
 #endif
 
 #ifdef CONFIG_BL_SWITCHER

@@ -1027,12 +1042,6 @@ static int gic_irq_domain_translate(struct irq_domain *d,
 	return -EINVAL;
 }
 
-static int gic_starting_cpu(unsigned int cpu)
-{
-	gic_cpu_init(&gic_data[0]);
-	return 0;
-}
-
 static int gic_irq_domain_alloc(struct irq_domain *domain, unsigned int virq,
 				unsigned int nr_irqs, void *arg)
 {

@@ -1079,10 +1088,8 @@ static void gic_init_chip(struct gic_chip_data *gic, struct device *dev,
 		gic->chip.irq_set_vcpu_affinity = gic_irq_set_vcpu_affinity;
 	}
 
-#ifdef CONFIG_SMP
 	if (gic == &gic_data[0])
 		gic->chip.irq_set_affinity = gic_set_affinity;
-#endif
 }
 
 static int gic_init_bases(struct gic_chip_data *gic,

@@ -1199,12 +1206,7 @@ static int __init __gic_init_bases(struct gic_chip_data *gic,
 		 */
 		for (i = 0; i < NR_GIC_CPU_IF; i++)
 			gic_cpu_map[i] = 0xff;
-#ifdef CONFIG_SMP
-		set_smp_cross_call(gic_raise_softirq);
-#endif
-		cpuhp_setup_state_nocalls(CPUHP_AP_IRQ_GIC_STARTING,
-					  "irqchip/arm/gic:starting",
-					  gic_starting_cpu, NULL);
+
 		set_handle_irq(gic_handle_irq);
 		if (static_branch_likely(&supports_deactivate_key))
 			pr_info("GIC: Using split EOI/Deactivate mode\n");

@@ -1221,6 +1223,8 @@ static int __init __gic_init_bases(struct gic_chip_data *gic,
 	ret = gic_init_bases(gic, handle);
 	if (ret)
 		kfree(name);
+	else if (gic == &gic_data[0])
+		gic_smp_init();
 
 	return ret;
 }

index 801a5a5004d6..86699761e19f 100644
@@ -335,31 +335,22 @@ static void __exception_irq_entry gic_handle_irq(struct pt_regs *regs)
 		irqstat = readl_relaxed(cpu_base + GIC_CPU_INTACK);
 		irqnr = irqstat & GICC_IAR_INT_ID_MASK;
 
-		if (likely(irqnr > 15 && irqnr < 1020)) {
-			if (static_branch_likely(&supports_deactivate_key))
-				writel_relaxed(irqstat, cpu_base + GIC_CPU_EOI);
-			isb();
-			handle_domain_irq(gic->domain, irqnr, regs);
-			continue;
-		}
-		if (irqnr < 16) {
+		if (unlikely(irqnr >= 1020))
+			break;
+
+		if (static_branch_likely(&supports_deactivate_key))
 			writel_relaxed(irqstat, cpu_base + GIC_CPU_EOI);
-			if (static_branch_likely(&supports_deactivate_key))
-				writel_relaxed(irqstat, cpu_base + GIC_CPU_DEACTIVATE);
-#ifdef CONFIG_SMP
-			/*
-			 * Ensure any shared data written by the CPU sending
-			 * the IPI is read after we've read the ACK register
-			 * on the GIC.
-			 *
-			 * Pairs with the write barrier in gic_raise_softirq
-			 */
+		isb();
+
+		/*
+		 * Ensure any shared data written by the CPU sending the IPI
+		 * is read after we've read the ACK register on the GIC.
+		 *
+		 * Pairs with the write barrier in gic_ipi_send_mask
+		 */
+		if (irqnr <= 15)
 			smp_rmb();
-			handle_IPI(irqnr, regs);
-#endif
-			continue;
-		}
-		break;
+		handle_domain_irq(gic->domain, irqnr, regs);
 	} while (1);
 }
 

@@ -793,14 +784,14 @@ static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val,
 	return IRQ_SET_MASK_OK_DONE;
 }
 
-static void gic_raise_softirq(const struct cpumask *mask, unsigned int irq)
+static void gic_ipi_send_mask(struct irq_data *d, const struct cpumask *mask)
 {
 	int cpu;
 	unsigned long flags, map = 0;
 
 	if (unlikely(nr_cpu_ids == 1)) {
 		/* Only one CPU? let's do a self-IPI... */
-		writel_relaxed(2 << 24 | irq,
+		writel_relaxed(2 << 24 | d->hwirq,
 			       gic_data_dist_base(&gic_data[0]) + GIC_DIST_SOFTINT);
 		return;
 	}

@@ -818,7 +809,7 @@ static void gic_raise_softirq(const struct cpumask *mask, unsigned int irq)
 	dmb(ishst);
 
 	/* this always happens on GIC0 */
-	writel_relaxed(map << 16 | irq, gic_data_dist_base(&gic_data[0]) + GIC_DIST_SOFTINT);
+	writel_relaxed(map << 16 | d->hwirq, gic_data_dist_base(&gic_data[0]) + GIC_DIST_SOFTINT);
 
 	gic_unlock_irqrestore(flags);
 }

@@ -831,14 +822,28 @@ static int gic_starting_cpu(unsigned int cpu)
 
 static __init void gic_smp_init(void)
 {
-	set_smp_cross_call(gic_raise_softirq);
+	struct irq_fwspec sgi_fwspec = {
+		.fwnode		= gic_data[0].domain->fwnode,
+		.param_count	= 1,
+	};
+	int base_sgi;
+
 	cpuhp_setup_state_nocalls(CPUHP_AP_IRQ_GIC_STARTING,
 				  "irqchip/arm/gic:starting",
 				  gic_starting_cpu, NULL);
+
+	base_sgi = __irq_domain_alloc_irqs(gic_data[0].domain, -1, 8,
+					   NUMA_NO_NODE, &sgi_fwspec,
+					   false, NULL);
+	if (WARN_ON(base_sgi <= 0))
+		return;
+
+	set_smp_ipi_range(base_sgi, 8);
 }
 #else
 #define gic_smp_init()		do { } while(0)
 #define gic_set_affinity	NULL
+#define gic_ipi_send_mask	NULL
 #endif
 
 #ifdef CONFIG_BL_SWITCHER

@@ -985,15 +990,24 @@ static int gic_irq_domain_map(struct irq_domain *d, unsigned int irq,
 {
 	struct gic_chip_data *gic = d->host_data;
 
-	if (hw < 32) {
+	switch (hw) {
+	case 0 ... 15:
+		irq_set_percpu_devid(irq);
+		irq_domain_set_info(d, irq, hw, &gic->chip, d->host_data,
+				    handle_percpu_devid_fasteoi_ipi,
+				    NULL, NULL);
+		break;
+	case 16 ... 31:
 		irq_set_percpu_devid(irq);
 		irq_domain_set_info(d, irq, hw, &gic->chip, d->host_data,
 				    handle_percpu_devid_irq, NULL, NULL);
-	} else {
+		break;
+	default:
 		irq_domain_set_info(d, irq, hw, &gic->chip, d->host_data,
 				    handle_fasteoi_irq, NULL, NULL);
 		irq_set_probe(irq);
 		irqd_set_single_target(irq_desc_get_irq_data(irq_to_desc(irq)));
+		break;
 	}
 	return 0;
 }

@@ -1007,19 +1021,26 @@ static int gic_irq_domain_translate(struct irq_domain *d,
 				    unsigned long *hwirq,
 				    unsigned int *type)
 {
+	if (fwspec->param_count == 1 && fwspec->param[0] < 16) {
+		*hwirq = fwspec->param[0];
+		*type = IRQ_TYPE_EDGE_RISING;
+		return 0;
+	}
+
 	if (is_of_node(fwspec->fwnode)) {
 		if (fwspec->param_count < 3)
 			return -EINVAL;
 
-		/* Get the interrupt number and add 16 to skip over SGIs */
-		*hwirq = fwspec->param[1] + 16;
-
-		/*
-		 * For SPIs, we need to add 16 more to get the GIC irq
-		 * ID number
-		 */
-		if (!fwspec->param[0])
-			*hwirq += 16;
+		switch (fwspec->param[0]) {
+		case 0:			/* SPI */
+			*hwirq = fwspec->param[1] + 32;
+			break;
+		case 1:			/* PPI */
+			*hwirq = fwspec->param[1] + 16;
+			break;
+		default:
+			return -EINVAL;
+		}
 
 		*type = fwspec->param[2] & IRQ_TYPE_SENSE_MASK;
 

@@ -1088,8 +1109,10 @@ static void gic_init_chip(struct gic_chip_data *gic, struct device *dev,
 		gic->chip.irq_set_vcpu_affinity = gic_irq_set_vcpu_affinity;
 	}
 
-	if (gic == &gic_data[0])
+	if (gic == &gic_data[0]) {
 		gic->chip.irq_set_affinity = gic_set_affinity;
+		gic->chip.ipi_send_mask = gic_ipi_send_mask;
+	}
 }
 
 static int gic_init_bases(struct gic_chip_data *gic,

index 82520006195d..f47b41dfd023 100644
@@ -152,9 +152,6 @@ void gic_cpu_config(void __iomem *base, int nr, void (*sync_access)(void))
 		writel_relaxed(GICD_INT_DEF_PRI_X4,
 					base + GIC_DIST_PRI + i * 4 / 4);
 
-	/* Ensure all SGI interrupts are now enabled */
-	writel_relaxed(GICD_INT_EN_SET_SGI, base + GIC_DIST_ENABLE_SET);
-
 	if (sync_access)
 		sync_access();
 }

index 2038693f074c..85df6ddad9be 100644
@@ -10,6 +10,7 @@
 #include <linux/of_irq.h>
 #include <linux/irqchip.h>
 #include <linux/irqdomain.h>
+#include <linux/irqchip/chained_irq.h>
 #include <linux/irqchip/irq-bcm2836.h>
 
 #include <asm/exception.h>

@@ -89,12 +90,24 @@ static struct irq_chip bcm2836_arm_irqchip_gpu = {
 	.irq_unmask	= bcm2836_arm_irqchip_unmask_gpu_irq,
 };
 
+static void bcm2836_arm_irqchip_dummy_op(struct irq_data *d)
+{
+}
+
+static struct irq_chip bcm2836_arm_irqchip_dummy = {
+	.name		= "bcm2836-dummy",
+	.irq_eoi	= bcm2836_arm_irqchip_dummy_op,
+};
+
 static int bcm2836_map(struct irq_domain *d, unsigned int irq,
 		       irq_hw_number_t hw)
 {
 	struct irq_chip *chip;
 
 	switch (hw) {
+	case LOCAL_IRQ_MAILBOX0:
+		chip = &bcm2836_arm_irqchip_dummy;
+		break;
 	case LOCAL_IRQ_CNTPSIRQ:
 	case LOCAL_IRQ_CNTPNSIRQ:
 	case LOCAL_IRQ_CNTHPIRQ:

@@ -127,17 +140,7 @@ __exception_irq_entry bcm2836_arm_irqchip_handle_irq(struct pt_regs *regs)
 	u32 stat;
 
 	stat = readl_relaxed(intc.base + LOCAL_IRQ_PENDING0 + 4 * cpu);
-	if (stat & BIT(LOCAL_IRQ_MAILBOX0)) {
-#ifdef CONFIG_SMP
-		void __iomem *mailbox0 = (intc.base +
-					  LOCAL_MAILBOX0_CLR0 + 16 * cpu);
-		u32 mbox_val = readl(mailbox0);
-		u32 ipi = ffs(mbox_val) - 1;
-
-		writel(1 << ipi, mailbox0);
-		handle_IPI(ipi, regs);
-#endif
-	} else if (stat) {
+	if (stat) {
 		u32 hwirq = ffs(stat) - 1;
 
 		handle_domain_irq(intc.domain, hwirq, regs);

@@ -145,8 +148,35 @@ __exception_irq_entry bcm2836_arm_irqchip_handle_irq(struct pt_regs *regs)
 }
 
 #ifdef CONFIG_SMP
-static void bcm2836_arm_irqchip_send_ipi(const struct cpumask *mask,
-					 unsigned int ipi)
+static struct irq_domain *ipi_domain;
+
+static void bcm2836_arm_irqchip_handle_ipi(struct irq_desc *desc)
+{
+	struct irq_chip *chip = irq_desc_get_chip(desc);
+	int cpu = smp_processor_id();
+	u32 mbox_val;
+
+	chained_irq_enter(chip, desc);
+
+	mbox_val = readl_relaxed(intc.base + LOCAL_MAILBOX0_CLR0 + 16 * cpu);
+	if (mbox_val) {
+		int hwirq = ffs(mbox_val) - 1;
+		generic_handle_irq(irq_find_mapping(ipi_domain, hwirq));
+	}
+
+	chained_irq_exit(chip, desc);
+}
+
+static void bcm2836_arm_irqchip_ipi_eoi(struct irq_data *d)
+{
+	int cpu = smp_processor_id();
+
+	writel_relaxed(BIT(d->hwirq),
+		       intc.base + LOCAL_MAILBOX0_CLR0 + 16 * cpu);
+}
+
+static void bcm2836_arm_irqchip_ipi_send_mask(struct irq_data *d,
+					      const struct cpumask *mask)
 {
 	int cpu;
 	void __iomem *mailbox0_base = intc.base + LOCAL_MAILBOX0_SET0;

@@ -157,11 +187,45 @@ static void bcm2836_arm_irqchip_send_ipi(const struct cpumask *mask,
 	 */
 	smp_wmb();
 
-	for_each_cpu(cpu, mask)	{
-		writel(1 << ipi, mailbox0_base + 16 * cpu);
+	for_each_cpu(cpu, mask)
+		writel_relaxed(BIT(d->hwirq), mailbox0_base + 16 * cpu);
+}
+
+static struct irq_chip bcm2836_arm_irqchip_ipi = {
+	.name		= "IPI",
+	.irq_eoi	= bcm2836_arm_irqchip_ipi_eoi,
+	.ipi_send_mask	= bcm2836_arm_irqchip_ipi_send_mask,
+};
+
+static int bcm2836_arm_irqchip_ipi_alloc(struct irq_domain *d,
+					 unsigned int virq,
+					 unsigned int nr_irqs, void *args)
+{
+	int i;
+
+	for (i = 0; i < nr_irqs; i++) {
+		irq_set_percpu_devid(virq + i);
+		irq_domain_set_info(d, virq + i, i, &bcm2836_arm_irqchip_ipi,
+				    d->host_data,
+				    handle_percpu_devid_fasteoi_ipi,
+				    NULL, NULL);
 	}
+
+	return 0;
 }
 
+static void bcm2836_arm_irqchip_ipi_free(struct irq_domain *d,
+					 unsigned int virq,
+					 unsigned int nr_irqs)
+{
+	/* Not freeing IPIs */
+}
+
+static const struct irq_domain_ops ipi_domain_ops = {
+	.alloc	= bcm2836_arm_irqchip_ipi_alloc,
+	.free	= bcm2836_arm_irqchip_ipi_free,
+};
+
 static int bcm2836_cpu_starting(unsigned int cpu)
 {
 	bcm2836_arm_irqchip_unmask_per_cpu_irq(LOCAL_MAILBOX_INT_CONTROL0, 0,

@@ -175,25 +239,58 @@ static int bcm2836_cpu_dying(unsigned int cpu)
 					     cpu);
 	return 0;
 }
-#endif
 
-static const struct irq_domain_ops bcm2836_arm_irqchip_intc_ops = {
-	.xlate = irq_domain_xlate_onetwocell,
-	.map = bcm2836_map,
-};
+#define BITS_PER_MBOX	32
 
-static void
-bcm2836_arm_irqchip_smp_init(void)
+static void bcm2836_arm_irqchip_smp_init(void)
 {
-#ifdef CONFIG_SMP
+	struct irq_fwspec ipi_fwspec = {
+		.fwnode		= intc.domain->fwnode,
+		.param_count	= 1,
+		.param		= {
+			[0]	= LOCAL_IRQ_MAILBOX0,
+		},
+	};
+	int base_ipi, mux_irq;
+
+	mux_irq = irq_create_fwspec_mapping(&ipi_fwspec);
+	if (WARN_ON(mux_irq <= 0))
+		return;
+
+	ipi_domain = irq_domain_create_linear(intc.domain->fwnode,
+					      BITS_PER_MBOX, &ipi_domain_ops,
+					      NULL);
+	if (WARN_ON(!ipi_domain))
+		return;
+
+	ipi_domain->flags |= IRQ_DOMAIN_FLAG_IPI_SINGLE;
+	irq_domain_update_bus_token(ipi_domain, DOMAIN_BUS_IPI);
+
+	base_ipi = __irq_domain_alloc_irqs(ipi_domain, -1, BITS_PER_MBOX,
+					   NUMA_NO_NODE, NULL,
+					   false, NULL);
+
+	if (WARN_ON(!base_ipi))
+		return;
+
+	set_smp_ipi_range(base_ipi, BITS_PER_MBOX);
+
+	irq_set_chained_handler_and_data(mux_irq,
+					 bcm2836_arm_irqchip_handle_ipi, NULL);
+
 	/* Unmask IPIs to the boot CPU. */
 	cpuhp_setup_state(CPUHP_AP_IRQ_BCM2836_STARTING,
 			  "irqchip/bcm2836:starting", bcm2836_cpu_starting,
 			  bcm2836_cpu_dying);
-
-	set_smp_cross_call(bcm2836_arm_irqchip_send_ipi);
-#endif
 }
+#else
+#define bcm2836_arm_irqchip_smp_init()	do { } while(0)
+#endif
+
+static const struct irq_domain_ops bcm2836_arm_irqchip_intc_ops = {
+	.xlate = irq_domain_xlate_onetwocell,
+	.map = bcm2836_map,
+};
 
 /*
  * The LOCAL_IRQ_CNT* timer firings are based off of the external

@@ -232,6 +329,8 @@ static int __init bcm2836_arm_irqchip_l1_intc_of_init(struct device_node *node,
 	if (!intc.domain)
 		panic("%pOF: unable to create IRQ domain\n", node);
 
+	irq_domain_update_bus_token(intc.domain, DOMAIN_BUS_WIRED);
+
 	bcm2836_arm_irqchip_smp_init();
 
 	set_handle_irq(bcm2836_arm_irqchip_handle_irq);

index 130caa1c9d93..9b73dcfaf48d 100644
@@ -171,6 +171,29 @@ static int hip04_irq_set_affinity(struct irq_data *d,
 
 	return IRQ_SET_MASK_OK;
 }
+
+static void hip04_ipi_send_mask(struct irq_data *d, const struct cpumask *mask)
+{
+	int cpu;
+	unsigned long flags, map = 0;
+
+	raw_spin_lock_irqsave(&irq_controller_lock, flags);
+
+	/* Convert our logical CPU mask into a physical one. */
+	for_each_cpu(cpu, mask)
+		map |= hip04_cpu_map[cpu];
+
+	/*
+	 * Ensure that stores to Normal memory are visible to the
+	 * other CPUs before they observe us issuing the IPI.
+	 */
+	dmb(ishst);
+
+	/* this always happens on GIC0 */
+	writel_relaxed(map << 8 | d->hwirq, hip04_data.dist_base + GIC_DIST_SOFTINT);
+
+	raw_spin_unlock_irqrestore(&irq_controller_lock, flags);
+}
 #endif
 
 static void __exception_irq_entry hip04_handle_irq(struct pt_regs *regs)

@@ -182,19 +205,9 @@ static void __exception_irq_entry hip04_handle_irq(struct pt_regs *regs)
 		irqstat = readl_relaxed(cpu_base + GIC_CPU_INTACK);
 		irqnr = irqstat & GICC_IAR_INT_ID_MASK;
 
-		if (likely(irqnr > 15 && irqnr <= HIP04_MAX_IRQS)) {
+		if (irqnr <= HIP04_MAX_IRQS)
 			handle_domain_irq(hip04_data.domain, irqnr, regs);
-			continue;
-		}
-		if (irqnr < 16) {
-			writel_relaxed(irqstat, cpu_base + GIC_CPU_EOI);
-#ifdef CONFIG_SMP
-			handle_IPI(irqnr, regs);
-#endif
-			continue;
-		}
-		break;
-	} while (1);
+	} while (irqnr > HIP04_MAX_IRQS);
 }
 
 static struct irq_chip hip04_irq_chip = {

@@ -205,6 +218,7 @@ static struct irq_chip hip04_irq_chip = {
 	.irq_set_type		= hip04_irq_set_type,
 #ifdef CONFIG_SMP
 	.irq_set_affinity	= hip04_irq_set_affinity,
+	.ipi_send_mask		= hip04_ipi_send_mask,
 #endif
 	.flags			= IRQCHIP_SET_TYPE_MASKED |
 				  IRQCHIP_SKIP_SET_WAKE |

@@ -279,39 +293,17 @@ static void hip04_irq_cpu_init(struct hip04_irq_data *intc)
 	writel_relaxed(1, base + GIC_CPU_CTRL);
 }
 
-#ifdef CONFIG_SMP
-static void hip04_raise_softirq(const struct cpumask *mask, unsigned int irq)
-{
-	int cpu;
-	unsigned long flags, map = 0;
-
-	raw_spin_lock_irqsave(&irq_controller_lock, flags);
-
-	/* Convert our logical CPU mask into a physical one. */
-	for_each_cpu(cpu, mask)
-		map |= hip04_cpu_map[cpu];
-
-	/*
-	 * Ensure that stores to Normal memory are visible to the
-	 * other CPUs before they observe us issuing the IPI.
-	 */
-	dmb(ishst);
-
-	/* this always happens on GIC0 */
-	writel_relaxed(map << 8 | irq, hip04_data.dist_base + GIC_DIST_SOFTINT);
-
-	raw_spin_unlock_irqrestore(&irq_controller_lock, flags);
-}
-#endif
-
 static int hip04_irq_domain_map(struct irq_domain *d, unsigned int irq,
 				irq_hw_number_t hw)
 {
-	if (hw < 32) {
+	if (hw < 16) {
+		irq_set_percpu_devid(irq);
+		irq_set_chip_and_handler(irq, &hip04_irq_chip,
+					 handle_percpu_devid_fasteoi_ipi);
+	} else if (hw < 32) {
 		irq_set_percpu_devid(irq);
 		irq_set_chip_and_handler(irq, &hip04_irq_chip,
 					 handle_percpu_devid_irq);
-		irq_set_status_flags(irq, IRQ_NOAUTOEN);
 	} else {
 		irq_set_chip_and_handler(irq, &hip04_irq_chip,
 					 handle_fasteoi_irq);

@@ -328,10 +320,13 @@ static int hip04_irq_domain_xlate(struct irq_domain *d,
 				  unsigned long *out_hwirq,
 				  unsigned int *out_type)
 {
-	unsigned long ret = 0;
-
 	if (irq_domain_get_of_node(d) != controller)
 		return -EINVAL;
+	if (intsize == 1 && intspec[0] < 16) {
+		*out_hwirq = intspec[0];
+		*out_type = IRQ_TYPE_EDGE_RISING;
+		return 0;
+	}
 	if (intsize < 3)
 		return -EINVAL;
 

@@ -344,7 +339,7 @@ static int hip04_irq_domain_xlate(struct irq_domain *d,
 
 	*out_type = intspec[2] & IRQ_TYPE_SENSE_MASK;
 
-	return ret;
+	return 0;
 }
 
 static int hip04_irq_starting_cpu(unsigned int cpu)

@@ -361,7 +356,6 @@ static const struct irq_domain_ops hip04_irq_domain_ops = {
 static int __init
 hip04_of_init(struct device_node *node, struct device_node *parent)
 {
-	irq_hw_number_t hwirq_base = 16;
 	int nr_irqs, irq_base, i;
 
 	if (WARN_ON(!node))

@@ -390,24 +384,21 @@ hip04_of_init(struct device_node *node, struct device_node *parent)
 		nr_irqs = HIP04_MAX_IRQS;
 	hip04_data.nr_irqs = nr_irqs;
 
-	nr_irqs -= hwirq_base; /* calculate # of irqs to allocate */
-
-	irq_base = irq_alloc_descs(-1, hwirq_base, nr_irqs, numa_node_id());
+	irq_base = irq_alloc_descs(-1, 0, nr_irqs, numa_node_id());
 	if (irq_base < 0) {
 		pr_err("failed to allocate IRQ numbers\n");
 		return -EINVAL;
 	}
 
 	hip04_data.domain = irq_domain_add_legacy(node, nr_irqs, irq_base,
-						  hwirq_base,
+						  0,
 						  &hip04_irq_domain_ops,
 						  &hip04_data);
-
 	if (WARN_ON(!hip04_data.domain))
 		return -EINVAL;
 
 #ifdef CONFIG_SMP
-	set_smp_cross_call(hip04_raise_softirq);
+	set_smp_ipi_range(irq_base, 16);
 #endif
 	set_handle_irq(hip04_handle_irq);
 

index c9bdc5221b82..d7eb2e93db8f 100644
@@ -310,7 +310,134 @@ static inline int armada_370_xp_msi_init(struct device_node *node,
 }
 #endif
 
+static void armada_xp_mpic_perf_init(void)
+{
+	unsigned long cpuid = cpu_logical_map(smp_processor_id());
+
+	/* Enable Performance Counter Overflow interrupts */
+	writel(ARMADA_370_XP_INT_CAUSE_PERF(cpuid),
+	       per_cpu_int_base + ARMADA_370_XP_INT_FABRIC_MASK_OFFS);
+}
+
 #ifdef CONFIG_SMP
+static struct irq_domain *ipi_domain;
+
+static void armada_370_xp_ipi_mask(struct irq_data *d)
+{
+	u32 reg;
+	reg = readl(per_cpu_int_base + ARMADA_370_XP_IN_DRBEL_MSK_OFFS);
+	reg &= ~BIT(d->hwirq);
+	writel(reg, per_cpu_int_base + ARMADA_370_XP_IN_DRBEL_MSK_OFFS);
+}
+
+static void armada_370_xp_ipi_unmask(struct irq_data *d)
+{
+	u32 reg;
+	reg = readl(per_cpu_int_base + ARMADA_370_XP_IN_DRBEL_MSK_OFFS);
+	reg |= BIT(d->hwirq);
+	writel(reg, per_cpu_int_base + ARMADA_370_XP_IN_DRBEL_MSK_OFFS);
+}
+
+static void armada_370_xp_ipi_send_mask(struct irq_data *d,
+					const struct cpumask *mask)
+{
+	unsigned long map = 0;
+	int cpu;
+
+	/* Convert our logical CPU mask into a physical one. */
+	for_each_cpu(cpu, mask)
+		map |= 1 << cpu_logical_map(cpu);
+
+	/*
+	 * Ensure that stores to Normal memory are visible to the
+	 * other CPUs before issuing the IPI.
+	 */
+	dsb();
+
+	/* submit softirq */
+	writel((map << 8) | d->hwirq, main_int_base +
+		ARMADA_370_XP_SW_TRIG_INT_OFFS);
+}
+
+static void armada_370_xp_ipi_eoi(struct irq_data *d)
+{
+	writel(~BIT(d->hwirq), per_cpu_int_base + ARMADA_370_XP_IN_DRBEL_CAUSE_OFFS);
+}
+
+static struct irq_chip ipi_irqchip = {
+	.name		= "IPI",
+	.irq_mask	= armada_370_xp_ipi_mask,
+	.irq_unmask	= armada_370_xp_ipi_unmask,
+	.irq_eoi	= armada_370_xp_ipi_eoi,
+	.ipi_send_mask	= armada_370_xp_ipi_send_mask,
+};
+
+static int armada_370_xp_ipi_alloc(struct irq_domain *d,
+					 unsigned int virq,
+					 unsigned int nr_irqs, void *args)
+{
+	int i;
+
+	for (i = 0; i < nr_irqs; i++) {
+		irq_set_percpu_devid(virq + i);
+		irq_domain_set_info(d, virq + i, i, &ipi_irqchip,
+				    d->host_data,
+				    handle_percpu_devid_fasteoi_ipi,
+				    NULL, NULL);
+	}
+
+	return 0;
+}
+
+static void armada_370_xp_ipi_free(struct irq_domain *d,
+					 unsigned int virq,
+					 unsigned int nr_irqs)
+{
+	/* Not freeing IPIs */
+}
+
+static const struct irq_domain_ops ipi_domain_ops = {
+	.alloc	= armada_370_xp_ipi_alloc,
+	.free	= armada_370_xp_ipi_free,
+};
+
+static void ipi_resume(void)
+{
+	int i;
+
+	for (i = 0; i < IPI_DOORBELL_END; i++) {
+		int irq;
+
+		irq = irq_find_mapping(ipi_domain, i);
+		if (irq <= 0)
+			continue;
+		if (irq_percpu_is_enabled(irq)) {
+			struct irq_data *d;
+			d = irq_domain_get_irq_data(ipi_domain, irq);
+			armada_370_xp_ipi_unmask(d);
+		}
+	}
+}
+
+static __init void armada_xp_ipi_init(struct device_node *node)
+{
+	int base_ipi;
+
+	ipi_domain = irq_domain_create_linear(of_node_to_fwnode(node),
+					      IPI_DOORBELL_END,
+					      &ipi_domain_ops, NULL);
+	if (WARN_ON(!ipi_domain))
+		return;
+
+	irq_domain_update_bus_token(ipi_domain, DOMAIN_BUS_IPI);
+	base_ipi = __irq_domain_alloc_irqs(ipi_domain, -1, IPI_DOORBELL_END,
+					   NUMA_NO_NODE, NULL, false, NULL);
+	if (WARN_ON(!base_ipi))
+		return;
+
+	set_smp_ipi_range(base_ipi, IPI_DOORBELL_END);
+}
+
 static DEFINE_RAW_SPINLOCK(irq_controller_lock);
 
 static int armada_xp_set_affinity(struct irq_data *d,

@@ -334,43 +461,6 @@ static int armada_xp_set_affinity(struct irq_data *d,
 
 	return IRQ_SET_MASK_OK;
 }
-#endif
-
-static struct irq_chip armada_370_xp_irq_chip = {
-	.name		= "MPIC",
-	.irq_mask       = armada_370_xp_irq_mask,
-	.irq_mask_ack   = armada_370_xp_irq_mask,
-	.irq_unmask     = armada_370_xp_irq_unmask,
-#ifdef CONFIG_SMP
-	.irq_set_affinity = armada_xp_set_affinity,
-#endif
-	.flags		= IRQCHIP_SKIP_SET_WAKE | IRQCHIP_MASK_ON_SUSPEND,
-};
-
-static int armada_370_xp_mpic_irq_map(struct irq_domain *h,
-				      unsigned int virq, irq_hw_number_t hw)
-{
-	armada_370_xp_irq_mask(irq_get_irq_data(virq));
-	if (!is_percpu_irq(hw))
-		writel(hw, per_cpu_int_base +
-			ARMADA_370_XP_INT_CLEAR_MASK_OFFS);
-	else
-		writel(hw, main_int_base + ARMADA_370_XP_INT_SET_ENABLE_OFFS);
-	irq_set_status_flags(virq, IRQ_LEVEL);
-
-	if (is_percpu_irq(hw)) {
-		irq_set_percpu_devid(virq);
-		irq_set_chip_and_handler(virq, &armada_370_xp_irq_chip,
-					handle_percpu_devid_irq);
-	} else {
-		irq_set_chip_and_handler(virq, &armada_370_xp_irq_chip,
-					handle_level_irq);
-		irqd_set_single_target(irq_desc_get_irq_data(irq_to_desc(virq)));
-	}
-	irq_set_probe(virq);
-
-	return 0;
-}
 
 static void armada_xp_mpic_smp_cpu_init(void)
 {

@@ -383,48 +473,16 @@ static void armada_xp_mpic_smp_cpu_init(void)
 	for (i = 0; i < nr_irqs; i++)
 		writel(i, per_cpu_int_base + ARMADA_370_XP_INT_SET_MASK_OFFS);
 
+	/* Disable all IPIs */
+	writel(0, per_cpu_int_base + ARMADA_370_XP_IN_DRBEL_MSK_OFFS);
+
 	/* Clear pending IPIs */
 	writel(0, per_cpu_int_base + ARMADA_370_XP_IN_DRBEL_CAUSE_OFFS);
 
-	/* Enable first 8 IPIs */
-	writel(IPI_DOORBELL_MASK, per_cpu_int_base +
-		ARMADA_370_XP_IN_DRBEL_MSK_OFFS);
-
 	/* Unmask IPI interrupt */
 	writel(0, per_cpu_int_base + ARMADA_370_XP_INT_CLEAR_MASK_OFFS);
 }
 
-static void armada_xp_mpic_perf_init(void)
-{
-	unsigned long cpuid = cpu_logical_map(smp_processor_id());
-
-	/* Enable Performance Counter Overflow interrupts */
-	writel(ARMADA_370_XP_INT_CAUSE_PERF(cpuid),
-	       per_cpu_int_base + ARMADA_370_XP_INT_FABRIC_MASK_OFFS);
-}
-
-#ifdef CONFIG_SMP
-static void armada_mpic_send_doorbell(const struct cpumask *mask,
-				      unsigned int irq)
-{
-	int cpu;
-	unsigned long map = 0;
-
-	/* Convert our logical CPU mask into a physical one. */
-	for_each_cpu(cpu, mask)
-		map |= 1 << cpu_logical_map(cpu);
-
-	/*
-	 * Ensure that stores to Normal memory are visible to the
-	 * other CPUs before issuing the IPI.
-	 */
-	dsb();
-
-	/* submit softirq */
-	writel((map << 8) | irq, main_int_base +
-		ARMADA_370_XP_SW_TRIG_INT_OFFS);
-}
-
 static void armada_xp_mpic_reenable_percpu(void)
 {
 	unsigned int irq;

@@ -445,6 +503,8 @@ static void armada_xp_mpic_reenable_percpu(void)
 
 		armada_370_xp_irq_unmask(data);
 	}
+
+	ipi_resume();
 }
 
 static int armada_xp_mpic_starting_cpu(unsigned int cpu)

@@ -462,7 +522,46 @@ static int mpic_cascaded_starting_cpu(unsigned int cpu)
 	enable_percpu_irq(parent_irq, IRQ_TYPE_NONE);
 	return 0;
 }
+#else
+static void armada_xp_mpic_smp_cpu_init(void) {}
+static void ipi_resume(void) {}
+#endif
+
+static struct irq_chip armada_370_xp_irq_chip = {
+	.name		= "MPIC",
+	.irq_mask       = armada_370_xp_irq_mask,
+	.irq_mask_ack   = armada_370_xp_irq_mask,
+	.irq_unmask     = armada_370_xp_irq_unmask,
+#ifdef CONFIG_SMP
+	.irq_set_affinity = armada_xp_set_affinity,
 #endif
+	.flags		= IRQCHIP_SKIP_SET_WAKE | IRQCHIP_MASK_ON_SUSPEND,
+};
+
+static int armada_370_xp_mpic_irq_map(struct irq_domain *h,
+				      unsigned int virq, irq_hw_number_t hw)
+{
+	armada_370_xp_irq_mask(irq_get_irq_data(virq));
+	if (!is_percpu_irq(hw))
+		writel(hw, per_cpu_int_base +
+			ARMADA_370_XP_INT_CLEAR_MASK_OFFS);
+	else
+		writel(hw, main_int_base + ARMADA_370_XP_INT_SET_ENABLE_OFFS);
+	irq_set_status_flags(virq, IRQ_LEVEL);
+
+	if (is_percpu_irq(hw)) {
+		irq_set_percpu_devid(virq);
+		irq_set_chip_and_handler(virq, &armada_370_xp_irq_chip,
+					handle_percpu_devid_irq);
+	} else {
+		irq_set_chip_and_handler(virq, &armada_370_xp_irq_chip,
+					handle_level_irq);
+		irqd_set_single_target(irq_desc_get_irq_data(irq_to_desc(virq)));
+	}
+	irq_set_probe(virq);
+
+	return 0;
+}
 
 static const struct irq_domain_ops armada_370_xp_mpic_irq_ops = {
 	.map = armada_370_xp_mpic_irq_map,

@@ -562,22 +661,15 @@ armada_370_xp_handle_irq(struct pt_regs *regs)
 #ifdef CONFIG_SMP
 		/* IPI Handling */
 		if (irqnr == 0) {
-			u32 ipimask, ipinr;
+			unsigned long ipimask;
+			int ipi;
 
 			ipimask = readl_relaxed(per_cpu_int_base +
 						ARMADA_370_XP_IN_DRBEL_CAUSE_OFFS)
 				& IPI_DOORBELL_MASK;
 
-			writel(~ipimask, per_cpu_int_base +
-				ARMADA_370_XP_IN_DRBEL_CAUSE_OFFS);
-
-			/* Handle all pending doorbells */
-			for (ipinr = IPI_DOORBELL_START;
-			     ipinr < IPI_DOORBELL_END; ipinr++) {
-				if (ipimask & (0x1 << ipinr))
-					handle_IPI(ipinr, regs);
-			}
-			continue;
+			for_each_set_bit(ipi, &ipimask, IPI_DOORBELL_END)
+				handle_domain_irq(ipi_domain, ipi, regs);
 		}
 #endif
 

@@ -636,6 +728,8 @@ static void armada_370_xp_mpic_resume(void)
 		writel(0, per_cpu_int_base + ARMADA_370_XP_INT_CLEAR_MASK_OFFS);
 	if (doorbell_mask_reg & PCI_MSI_DOORBELL_MASK)
 		writel(1, per_cpu_int_base + ARMADA_370_XP_INT_CLEAR_MASK_OFFS);
+
+	ipi_resume();
 }
 
 static struct syscore_ops armada_370_xp_mpic_syscore_ops = {

@@ -691,7 +785,7 @@ static int __init armada_370_xp_mpic_of_init(struct device_node *node,
 		irq_set_default_host(armada_370_xp_mpic_domain);
 		set_handle_irq(armada_370_xp_handle_irq);
 #ifdef CONFIG_SMP
-		set_smp_cross_call(armada_mpic_send_doorbell);
+		armada_xp_ipi_init(node);
 		cpuhp_setup_state_nocalls(CPUHP_AP_IRQ_ARMADA_XP_STARTING,
 					  "irqchip/armada/ipi:starting",
 					  armada_xp_mpic_starting_cpu, NULL);

index 8a1ef1907760..a1020285ea75 100644
@@ -2,11 +2,9 @@
 #ifndef __ASM_IRQ_WORK_H
 #define __ASM_IRQ_WORK_H
 
-#include <asm/smp.h>
-
 static inline bool arch_irq_work_has_interrupt(void)
 {
-	return !!__smp_cross_call;
+	return true;
 }
 
 #endif /* __ASM_IRQ_WORK_H */

index 4537a4620e3d..dd3f68ed9ac9 100644
@@ -67,13 +67,6 @@ extern void handle_IPI(int ipinr, struct pt_regs *regs);
  */
 extern void smp_init_cpus(void);
 
-/*
- * Provide a function to raise an IPI cross call on CPUs in callmap.
- */
-extern void set_smp_cross_call(void (*)(const struct cpumask *, unsigned int));
-
-extern void (*__smp_cross_call)(const struct cpumask *, unsigned int);
-
 /*
  * Register IPI interrupts with the arch SMP code
  */

index c08950cc09cc..ed8a8184e3b6 100644
@@ -783,13 +783,6 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
 	}
 }
 
-void (*__smp_cross_call)(const struct cpumask *, unsigned int);
-
-void __init set_smp_cross_call(void (*fn)(const struct cpumask *, unsigned int))
-{
-	__smp_cross_call = fn;
-}
-
 static const char *ipi_types[NR_IPI] __tracepoint_string = {
 #define S(x,s)	[x] = s
 	S(IPI_RESCHEDULE, "Rescheduling interrupts"),

@@ -801,11 +794,7 @@ static const char *ipi_types[NR_IPI] __tracepoint_string = {
 	S(IPI_WAKEUP, "CPU wake-up interrupts"),
 };
 
-static void smp_cross_call(const struct cpumask *target, unsigned int ipinr)
-{
-	trace_ipi_raise(target, ipi_types[ipinr]);
-	__smp_cross_call(target, ipinr);
-}
+static void smp_cross_call(const struct cpumask *target, unsigned int ipinr);
 
 void show_ipi_list(struct seq_file *p, int prec)
 {

@@ -852,8 +841,7 @@ void arch_send_wakeup_ipi_mask(const struct cpumask *mask)
 #ifdef CONFIG_IRQ_WORK
 void arch_irq_work_raise(void)
 {
-	if (__smp_cross_call)
-		smp_cross_call(cpumask_of(smp_processor_id()), IPI_IRQ_WORK);
+	smp_cross_call(cpumask_of(smp_processor_id()), IPI_IRQ_WORK);
 }
 #endif
 

@@ -960,27 +948,16 @@ static void do_handle_IPI(int ipinr)
 		trace_ipi_exit_rcuidle(ipi_types[ipinr]);
 }
 
-/* Legacy version, should go away once all irqchips have been converted */
-void handle_IPI(int ipinr, struct pt_regs *regs)
-{
-	struct pt_regs *old_regs = set_irq_regs(regs);
-
-	irq_enter();
-	do_handle_IPI(ipinr);
-	irq_exit();
-
-	set_irq_regs(old_regs);
-}
-
 static irqreturn_t ipi_handler(int irq, void *data)
 {
 	do_handle_IPI(irq - ipi_irq_base);
 	return IRQ_HANDLED;
 }
 
-static void ipi_send(const struct cpumask *target, unsigned int ipi)
+static void smp_cross_call(const struct cpumask *target, unsigned int ipinr)
 {
-	__ipi_send_mask(ipi_desc[ipi], target);
+	trace_ipi_raise(target, ipi_types[ipinr]);
+	__ipi_send_mask(ipi_desc[ipinr], target);
 }
 
 static void ipi_setup(int cpu)

@@ -1022,7 +999,6 @@ void __init set_smp_ipi_range(int ipi_base, int n)
 	}
 
 	ipi_irq_base = ipi_base;
-	__smp_cross_call = ipi_send;
 
 	/* Setup the boot CPU immediately */
 	ipi_setup(smp_processor_id());

index 985493af704b..5ffa4bacdad3 100644
@@ -13,21 +13,12 @@
 #include <asm/kvm_arm.h>
 #include <asm/sysreg.h>
 
-#define NR_IPI	7
-
 typedef struct {
 	unsigned int __softirq_pending;
-	unsigned int ipi_irqs[NR_IPI];
 } ____cacheline_aligned irq_cpustat_t;
 
 #include <linux/irq_cpustat.h>	/* Standard mappings for irq_cpustat_t above */
 
-#define __inc_irq_stat(cpu, member)	__IRQ_STAT(cpu, member)++
-#define __get_irq_stat(cpu, member)	__IRQ_STAT(cpu, member)
-
-u64 smp_irq_stat_cpu(unsigned int cpu);
-#define arch_irq_stat_cpu	smp_irq_stat_cpu
-
 #define __ARCH_IRQ_EXIT_IRQS_DISABLED	1
 
 struct nmi_ctx {

index ed8a8184e3b6..8b903ceef2be 100644
@@ -73,7 +73,8 @@ enum ipi_msg_type {
 	IPI_CPU_CRASH_STOP,
 	IPI_TIMER,
 	IPI_IRQ_WORK,
-	IPI_WAKEUP
+	IPI_WAKEUP,
+	NR_IPI
 };
 
 static int ipi_irq_base;

@@ -801,26 +802,15 @@ void show_ipi_list(struct seq_file *p, int prec)
 	unsigned int cpu, i;
 
 	for (i = 0; i < NR_IPI; i++) {
+		unsigned int irq = irq_desc_get_irq(ipi_desc[i]);
 		seq_printf(p, "%*s%u:%s", prec - 1, "IPI", i,
 			   prec >= 4 ? " " : "");
 		for_each_online_cpu(cpu)
-			seq_printf(p, "%10u ",
-				   __get_irq_stat(cpu, ipi_irqs[i]));
+			seq_printf(p, "%10u ", kstat_irqs_cpu(irq, cpu));
 		seq_printf(p, "      %s\n", ipi_types[i]);
 	}
 }
 
-u64 smp_irq_stat_cpu(unsigned int cpu)
-{
-	u64 sum = 0;
-	int i;
-
-	for (i = 0; i < NR_IPI; i++)
-		sum += __get_irq_stat(cpu, ipi_irqs[i]);
-
-	return sum;
-}
-
 void arch_send_call_function_ipi_mask(const struct cpumask *mask)
 {
 	smp_cross_call(mask, IPI_CALL_FUNC);

@@ -893,10 +883,8 @@ static void do_handle_IPI(int ipinr)
 {
 	unsigned int cpu = smp_processor_id();
 
-	if ((unsigned)ipinr < NR_IPI) {
+	if ((unsigned)ipinr < NR_IPI)
 		trace_ipi_entry_rcuidle(ipi_types[ipinr]);
-		__inc_irq_stat(cpu, ipi_irqs[ipinr]);
-	}
 
 	switch (ipinr) {
 	case IPI_RESCHEDULE:

@@ -991,7 +979,7 @@ void __init set_smp_ipi_range(int ipi_base, int n)
 		int err;
 
 		err = request_percpu_irq(ipi_base + i, ipi_handler,
-					 "IPI", &irq_stat);
+					 "IPI", &cpu_number);
 		WARN_ON(err);
 
 		ipi_desc[i] = irq_to_desc(ipi_base + i);

index 0e29730295ca..0ca55a607d0a 100644
@@ -39,12 +39,6 @@ void handle_IPI(int ipinr, struct pt_regs *regs);
  */
 extern void smp_init_cpus(void);
 
-
-/*
- * Provide a function to raise an IPI cross call on CPUs in callmap.
- */
-extern void set_smp_cross_call(void (*)(const struct cpumask *, unsigned int));
-
 /*
  * Register IPI interrupts with the arch SMP code
  */

index 269639b14259..285980c2a437 100644
@@ -514,14 +514,6 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
 	}
 }
 
-static void (*__smp_cross_call)(const struct cpumask *, unsigned int);
-
-void __init set_smp_cross_call(void (*fn)(const struct cpumask *, unsigned int))
-{
-	if (!__smp_cross_call)
-		__smp_cross_call = fn;
-}
-
 static const char *ipi_types[NR_IPI] __tracepoint_string = {
 #define S(x,s)	[x] = s
 	S(IPI_WAKEUP, "CPU wakeup interrupts"),

@@ -533,11 +525,7 @@ static const char *ipi_types[NR_IPI] __tracepoint_string = {
 	S(IPI_COMPLETION, "completion interrupts"),
 };
 
-static void smp_cross_call(const struct cpumask *target, unsigned int ipinr)
-{
-	trace_ipi_raise_rcuidle(target, ipi_types[ipinr]);
-	__smp_cross_call(target, ipinr);
-}
+static void smp_cross_call(const struct cpumask *target, unsigned int ipinr);
 
 void show_ipi_list(struct seq_file *p, int prec)
 {

@@ -716,9 +704,10 @@ static irqreturn_t ipi_handler(int irq, void *data)
 	return IRQ_HANDLED;
 }
 
-static void ipi_send(const struct cpumask *target, unsigned int ipi)
+static void smp_cross_call(const struct cpumask *target, unsigned int ipinr)
 {
-	__ipi_send_mask(ipi_desc[ipi], target);
+	trace_ipi_raise_rcuidle(target, ipi_types[ipinr]);
+	__ipi_send_mask(ipi_desc[ipinr], target);
 }
 
 static void ipi_setup(int cpu)

@@ -760,7 +749,6 @@ void __init set_smp_ipi_range(int ipi_base, int n)
 	}
 
 	ipi_irq_base = ipi_base;
-	set_smp_cross_call(ipi_send);
 
 	/* Setup the boot CPU immediately */
 	ipi_setup(smp_processor_id());

@@ -873,7 +861,7 @@ core_initcall(register_cpufreq_notifier);
 
 static void raise_nmi(cpumask_t *mask)
 {
-	__smp_cross_call(mask, IPI_CPU_BACKTRACE);
+	__ipi_send_mask(ipi_desc[IPI_CPU_BACKTRACE], mask);
 }
 
 void arch_trigger_cpumask_backtrace(const cpumask_t *mask, bool exclude_self)

index 7a88f160b1fb..b95848ed2bc7 100644
@@ -6,29 +6,12 @@
 #include <linux/threads.h>
 #include <asm/irq.h>
 
-/* number of IPIS _not_ including IPI_CPU_BACKTRACE */
-#define NR_IPI	7
-
 typedef struct {
 	unsigned int __softirq_pending;
-#ifdef CONFIG_SMP
-	unsigned int ipi_irqs[NR_IPI];
-#endif
 } ____cacheline_aligned irq_cpustat_t;
 
 #include <linux/irq_cpustat.h>	/* Standard mappings for irq_cpustat_t above */
 
-#define __inc_irq_stat(cpu, member)	__IRQ_STAT(cpu, member)++
-#define __get_irq_stat(cpu, member)	__IRQ_STAT(cpu, member)
-
-#ifdef CONFIG_SMP
-u64 smp_irq_stat_cpu(unsigned int cpu);
-#else
-#define smp_irq_stat_cpu(cpu)	0
-#endif
-
-#define arch_irq_stat_cpu	smp_irq_stat_cpu
-
 #define __ARCH_IRQ_EXIT_IRQS_DISABLED	1
 
 #endif /* __ASM_HARDIRQ_H */

index 285980c2a437..249fac8b0a8e 100644
@@ -66,6 +66,7 @@ enum ipi_msg_type {
 	IPI_CPU_STOP,
 	IPI_IRQ_WORK,
 	IPI_COMPLETION,
+	NR_IPI,
 	/*
 	 * CPU_BACKTRACE is special and not included in NR_IPI
 	 * or tracable with trace_ipi_*

@@ -532,27 +533,16 @@ void show_ipi_list(struct seq_file *p, int prec)
 	unsigned int cpu, i;
 
 	for (i = 0; i < NR_IPI; i++) {
+		unsigned int irq = irq_desc_get_irq(ipi_desc[i]);
 		seq_printf(p, "%*s%u: ", prec - 1, "IPI", i);
 
 		for_each_online_cpu(cpu)
-			seq_printf(p, "%10u ",
-				   __get_irq_stat(cpu, ipi_irqs[i]));
+			seq_printf(p, "%10u ", kstat_irqs_cpu(irq, cpu));
 
 		seq_printf(p, " %s\n", ipi_types[i]);
 	}
 }
 
-u64 smp_irq_stat_cpu(unsigned int cpu)
-{
-	u64 sum = 0;
-	int i;
-
-	for (i = 0; i < NR_IPI; i++)
-		sum += __get_irq_stat(cpu, ipi_irqs[i]);
-
-	return sum;
-}
-
 void arch_send_call_function_ipi_mask(const struct cpumask *mask)
 {
 	smp_cross_call(mask, IPI_CALL_FUNC);