Merge branch 'irq/core' into x86/apic

Pick up the dependencies for the vector management rework series.

arch/x86/include/asm/irqdomain.h

@@ -41,8 +41,8 @@ extern int mp_irqdomain_alloc(struct irq_domain *domain, unsigned int virq,
 			      unsigned int nr_irqs, void *arg);
 extern void mp_irqdomain_free(struct irq_domain *domain, unsigned int virq,
 			      unsigned int nr_irqs);
-extern void mp_irqdomain_activate(struct irq_domain *domain,
+extern int mp_irqdomain_activate(struct irq_domain *domain,
-				  struct irq_data *irq_data);
+				 struct irq_data *irq_data, bool early);
 extern void mp_irqdomain_deactivate(struct irq_domain *domain,
 				    struct irq_data *irq_data);
 extern int mp_irqdomain_ioapic_idx(struct irq_domain *domain);

arch/x86/kernel/apic/htirq.c

@@ -112,8 +112,8 @@ static void htirq_domain_free(struct irq_domain *domain, unsigned int virq,
 	irq_domain_free_irqs_top(domain, virq, nr_irqs);
 }
 
-static void htirq_domain_activate(struct irq_domain *domain,
+static int htirq_domain_activate(struct irq_domain *domain,
-				  struct irq_data *irq_data)
+				 struct irq_data *irq_data, bool early)
 {
 	struct ht_irq_msg msg;
 	struct irq_cfg *cfg = irqd_cfg(irq_data);
@@ -132,6 +132,7 @@ static void htirq_domain_activate(struct irq_domain *domain,
 			HT_IRQ_LOW_MT_ARBITRATED) |
 		HT_IRQ_LOW_IRQ_MASKED;
 	write_ht_irq_msg(irq_data->irq, &msg);
+	return 0;
 }
 
 static void htirq_domain_deactivate(struct irq_domain *domain,

arch/x86/kernel/apic/io_apic.c

@@ -2137,7 +2137,7 @@ static inline void __init check_timer(void)
 				unmask_ioapic_irq(irq_get_irq_data(0));
 		}
 		irq_domain_deactivate_irq(irq_data);
-		irq_domain_activate_irq(irq_data);
+		irq_domain_activate_irq(irq_data, false);
 		if (timer_irq_works()) {
 			if (disable_timer_pin_1 > 0)
 				clear_IO_APIC_pin(0, pin1);
@@ -2159,7 +2159,7 @@ static inline void __init check_timer(void)
 		 */
 		replace_pin_at_irq_node(data, node, apic1, pin1, apic2, pin2);
 		irq_domain_deactivate_irq(irq_data);
-		irq_domain_activate_irq(irq_data);
+		irq_domain_activate_irq(irq_data, false);
 		legacy_pic->unmask(0);
 		if (timer_irq_works()) {
 			apic_printk(APIC_QUIET, KERN_INFO "....... works.\n");
@@ -3018,8 +3018,8 @@ void mp_irqdomain_free(struct irq_domain *domain, unsigned int virq,
 	irq_domain_free_irqs_top(domain, virq, nr_irqs);
 }
 
-void mp_irqdomain_activate(struct irq_domain *domain,
+int mp_irqdomain_activate(struct irq_domain *domain,
-			   struct irq_data *irq_data)
+			  struct irq_data *irq_data, bool early)
 {
 	unsigned long flags;
 	struct irq_pin_list *entry;
@@ -3029,6 +3029,7 @@ void mp_irqdomain_activate(struct irq_domain *domain,
 	for_each_irq_pin(entry, data->irq_2_pin)
 		__ioapic_write_entry(entry->apic, entry->pin, data->entry);
 	raw_spin_unlock_irqrestore(&ioapic_lock, flags);
+	return 0;
 }
 
 void mp_irqdomain_deactivate(struct irq_domain *domain,

arch/x86/platform/uv/uv_irq.c

@@ -127,10 +127,11 @@ static void uv_domain_free(struct irq_domain *domain, unsigned int virq,
  * Re-target the irq to the specified CPU and enable the specified MMR located
  * on the specified blade to allow the sending of MSIs to the specified CPU.
  */
-static void uv_domain_activate(struct irq_domain *domain,
+static int uv_domain_activate(struct irq_domain *domain,
-			       struct irq_data *irq_data)
+			      struct irq_data *irq_data, bool early)
 {
 	uv_program_mmr(irqd_cfg(irq_data), irq_data->chip_data);
+	return 0;
 }
 
 /*

drivers/gpio/gpio-xgene-sb.c

@@ -140,8 +140,9 @@ static int xgene_gpio_sb_to_irq(struct gpio_chip *gc, u32 gpio)
 	return irq_create_fwspec_mapping(&fwspec);
 }
 
-static void xgene_gpio_sb_domain_activate(struct irq_domain *d,
+static int xgene_gpio_sb_domain_activate(struct irq_domain *d,
-		struct irq_data *irq_data)
+					 struct irq_data *irq_data,
+					 bool early)
 {
 	struct xgene_gpio_sb *priv = d->host_data;
 	u32 gpio = HWIRQ_TO_GPIO(priv, irq_data->hwirq);
@@ -150,11 +151,12 @@ static void xgene_gpio_sb_domain_activate(struct irq_domain *d,
 		dev_err(priv->gc.parent,
 		"Unable to configure XGene GPIO standby pin %d as IRQ\n",
 				gpio);
-		return;
+		return -ENOSPC;
 	}
 
 	xgene_gpio_set_bit(&priv->gc, priv->regs + MPA_GPIO_SEL_LO,
 			gpio * 2, 1);
+	return 0;
 }
 
 static void xgene_gpio_sb_domain_deactivate(struct irq_domain *d,

drivers/iommu/amd_iommu.c

@@ -4170,8 +4170,8 @@ static void irq_remapping_free(struct irq_domain *domain, unsigned int virq,
 	irq_domain_free_irqs_common(domain, virq, nr_irqs);
 }
 
-static void irq_remapping_activate(struct irq_domain *domain,
+static int irq_remapping_activate(struct irq_domain *domain,
-				   struct irq_data *irq_data)
+				  struct irq_data *irq_data, bool early)
 {
 	struct amd_ir_data *data = irq_data->chip_data;
 	struct irq_2_irte *irte_info = &data->irq_2_irte;
@@ -4180,6 +4180,7 @@ static void irq_remapping_activate(struct irq_domain *domain,
 	if (iommu)
 		iommu->irte_ops->activate(data->entry, irte_info->devid,
 					  irte_info->index);
+	return 0;
 }
 
 static void irq_remapping_deactivate(struct irq_domain *domain,

drivers/iommu/intel_irq_remapping.c

@@ -1389,12 +1389,13 @@ static void intel_irq_remapping_free(struct irq_domain *domain,
 	irq_domain_free_irqs_common(domain, virq, nr_irqs);
 }
 
-static void intel_irq_remapping_activate(struct irq_domain *domain,
+static int intel_irq_remapping_activate(struct irq_domain *domain,
-					 struct irq_data *irq_data)
+					struct irq_data *irq_data, bool early)
 {
 	struct intel_ir_data *data = irq_data->chip_data;
 
 	modify_irte(&data->irq_2_iommu, &data->irte_entry);
+	return 0;
 }
 
 static void intel_irq_remapping_deactivate(struct irq_domain *domain,

drivers/irqchip/irq-gic-v3-its.c

@@ -2186,8 +2186,8 @@ static int its_irq_domain_alloc(struct irq_domain *domain, unsigned int virq,
 	return 0;
 }
 
-static void its_irq_domain_activate(struct irq_domain *domain,
+static int its_irq_domain_activate(struct irq_domain *domain,
-				    struct irq_data *d)
+				   struct irq_data *d, bool early)
 {
 	struct its_device *its_dev = irq_data_get_irq_chip_data(d);
 	u32 event = its_get_event_id(d);
@@ -2205,6 +2205,7 @@ static void its_irq_domain_activate(struct irq_domain *domain,
 
 	/* Map the GIC IRQ and event to the device */
 	its_send_mapti(its_dev, d->hwirq, event);
+	return 0;
 }
 
 static void its_irq_domain_deactivate(struct irq_domain *domain,
@@ -2678,8 +2679,8 @@ static int its_vpe_irq_domain_alloc(struct irq_domain *domain, unsigned int virq
 	return err;
 }
 
-static void its_vpe_irq_domain_activate(struct irq_domain *domain,
+static int its_vpe_irq_domain_activate(struct irq_domain *domain,
-					struct irq_data *d)
+				       struct irq_data *d, bool early)
 {
 	struct its_vpe *vpe = irq_data_get_irq_chip_data(d);
 
@@ -2687,6 +2688,7 @@ static void its_vpe_irq_domain_activate(struct irq_domain *domain,
 	vpe->col_idx = cpumask_first(cpu_online_mask);
 	its_send_vmapp(vpe, true);
 	its_send_vinvall(vpe);
+	return 0;
 }
 
 static void its_vpe_irq_domain_deactivate(struct irq_domain *domain,

drivers/pinctrl/stm32/pinctrl-stm32.c

@@ -289,13 +289,14 @@ static int stm32_gpio_domain_translate(struct irq_domain *d,
 	return 0;
 }
 
-static void stm32_gpio_domain_activate(struct irq_domain *d,
+static int stm32_gpio_domain_activate(struct irq_domain *d,
-				       struct irq_data *irq_data)
+				      struct irq_data *irq_data, bool early)
 {
 	struct stm32_gpio_bank *bank = d->host_data;
 	struct stm32_pinctrl *pctl = dev_get_drvdata(bank->gpio_chip.parent);
 
 	regmap_field_write(pctl->irqmux[irq_data->hwirq], bank->bank_nr);
+	return 0;
 }
 
 static int stm32_gpio_domain_alloc(struct irq_domain *d,

include/linux/irq.h

@@ -1113,6 +1113,28 @@ static inline u32 irq_reg_readl(struct irq_chip_generic *gc,
 		return readl(gc->reg_base + reg_offset);
 }
 
+struct irq_matrix;
+struct irq_matrix *irq_alloc_matrix(unsigned int matrix_bits,
+				    unsigned int alloc_start,
+				    unsigned int alloc_end);
+void irq_matrix_online(struct irq_matrix *m);
+void irq_matrix_offline(struct irq_matrix *m);
+void irq_matrix_assign_system(struct irq_matrix *m, unsigned int bit, bool replace);
+int irq_matrix_reserve_managed(struct irq_matrix *m, const struct cpumask *msk);
+void irq_matrix_remove_managed(struct irq_matrix *m, const struct cpumask *msk);
+int irq_matrix_alloc_managed(struct irq_matrix *m, unsigned int cpu);
+void irq_matrix_reserve(struct irq_matrix *m);
+void irq_matrix_remove_reserved(struct irq_matrix *m);
+int irq_matrix_alloc(struct irq_matrix *m, const struct cpumask *msk,
+		     bool reserved, unsigned int *mapped_cpu);
+void irq_matrix_free(struct irq_matrix *m, unsigned int cpu,
+		     unsigned int bit, bool managed);
+void irq_matrix_assign(struct irq_matrix *m, unsigned int bit);
+unsigned int irq_matrix_available(struct irq_matrix *m, bool cpudown);
+unsigned int irq_matrix_allocated(struct irq_matrix *m);
+unsigned int irq_matrix_reserved(struct irq_matrix *m);
+void irq_matrix_debug_show(struct seq_file *sf, struct irq_matrix *m, int ind);
+
 /* Contrary to Linux irqs, for hardware irqs the irq number 0 is valid */
 #define INVALID_HWIRQ	(~0UL)
 irq_hw_number_t ipi_get_hwirq(unsigned int irq, unsigned int cpu);

include/linux/irqdesc.h

@@ -93,6 +93,7 @@ struct irq_desc {
 #endif
 #ifdef CONFIG_GENERIC_IRQ_DEBUGFS
 	struct dentry		*debugfs_file;
+	const char		*dev_name;
 #endif
 #ifdef CONFIG_SPARSE_IRQ
 	struct rcu_head		rcu;

include/linux/irqdomain.h

@@ -40,6 +40,7 @@ struct of_device_id;
 struct irq_chip;
 struct irq_data;
 struct cpumask;
+struct seq_file;
 
 /* Number of irqs reserved for a legacy isa controller */
 #define NUM_ISA_INTERRUPTS	16
@@ -104,18 +105,21 @@ struct irq_domain_ops {
 	int (*xlate)(struct irq_domain *d, struct device_node *node,
 		     const u32 *intspec, unsigned int intsize,
 		     unsigned long *out_hwirq, unsigned int *out_type);
-
 #ifdef	CONFIG_IRQ_DOMAIN_HIERARCHY
 	/* extended V2 interfaces to support hierarchy irq_domains */
 	int (*alloc)(struct irq_domain *d, unsigned int virq,
 		     unsigned int nr_irqs, void *arg);
 	void (*free)(struct irq_domain *d, unsigned int virq,
 		     unsigned int nr_irqs);
-	void (*activate)(struct irq_domain *d, struct irq_data *irq_data);
+	int (*activate)(struct irq_domain *d, struct irq_data *irqd, bool early);
 	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);
 #endif
+#ifdef CONFIG_GENERIC_IRQ_DEBUGFS
+	void (*debug_show)(struct seq_file *m, struct irq_domain *d,
+			   struct irq_data *irqd, int ind);
+#endif
 };
 
 extern struct irq_domain_ops irq_generic_chip_ops;
@@ -437,7 +441,7 @@ extern int __irq_domain_alloc_irqs(struct irq_domain *domain, int irq_base,
 				   unsigned int nr_irqs, int node, void *arg,
 				   bool realloc, const struct cpumask *affinity);
 extern void irq_domain_free_irqs(unsigned int virq, unsigned int nr_irqs);
-extern void irq_domain_activate_irq(struct irq_data *irq_data);
+extern int irq_domain_activate_irq(struct irq_data *irq_data, bool early);
 extern void irq_domain_deactivate_irq(struct irq_data *irq_data);
 
 static inline int irq_domain_alloc_irqs(struct irq_domain *domain,
@@ -507,8 +511,6 @@ static inline bool irq_domain_is_msi_remap(struct irq_domain *domain)
 extern bool irq_domain_hierarchical_is_msi_remap(struct irq_domain *domain);
 
 #else	/* CONFIG_IRQ_DOMAIN_HIERARCHY */
-static inline void irq_domain_activate_irq(struct irq_data *data) { }
-static inline void irq_domain_deactivate_irq(struct irq_data *data) { }
 static inline int irq_domain_alloc_irqs(struct irq_domain *domain,
 			unsigned int nr_irqs, int node, void *arg)
 {
@@ -557,8 +559,6 @@ irq_domain_hierarchical_is_msi_remap(struct irq_domain *domain)
 
 #else /* CONFIG_IRQ_DOMAIN */
 static inline void irq_dispose_mapping(unsigned int virq) { }
-static inline void irq_domain_activate_irq(struct irq_data *data) { }
-static inline void irq_domain_deactivate_irq(struct irq_data *data) { }
 static inline struct irq_domain *irq_find_matching_fwnode(
 	struct fwnode_handle *fwnode, enum irq_domain_bus_token bus_token)
 {

include/linux/msi.h

@@ -283,6 +283,11 @@ enum {
 	MSI_FLAG_PCI_MSIX		= (1 << 3),
 	/* Needs early activate, required for PCI */
 	MSI_FLAG_ACTIVATE_EARLY		= (1 << 4),
+	/*
+	 * Must reactivate when irq is started even when
+	 * MSI_FLAG_ACTIVATE_EARLY has been set.
+	 */
+	MSI_FLAG_MUST_REACTIVATE	= (1 << 5),
 };
 
 int msi_domain_set_affinity(struct irq_data *data, const struct cpumask *mask,

include/trace/events/irq_matrix.h

@@ -0,0 +1,201 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM irq_matrix
+
+#if !defined(_TRACE_IRQ_MATRIX_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_IRQ_MATRIX_H
+
+#include <linux/tracepoint.h>
+
+struct irq_matrix;
+struct cpumap;
+
+DECLARE_EVENT_CLASS(irq_matrix_global,
+
+	TP_PROTO(struct irq_matrix *matrix),
+
+	TP_ARGS(matrix),
+
+	TP_STRUCT__entry(
+		__field(	unsigned int,	online_maps		)
+		__field(	unsigned int,	global_available	)
+		__field(	unsigned int,	global_reserved		)
+		__field(	unsigned int,	total_allocated		)
+	),
+
+	TP_fast_assign(
+		__entry->online_maps		= matrix->online_maps;
+		__entry->global_available	= matrix->global_available;
+		__entry->global_reserved	= matrix->global_reserved;
+		__entry->total_allocated	= matrix->total_allocated;
+	),
+
+	TP_printk("online_maps=%d global_avl=%u, global_rsvd=%u, total_alloc=%u",
+		  __entry->online_maps, __entry->global_available,
+		  __entry->global_reserved, __entry->total_allocated)
+);
+
+DECLARE_EVENT_CLASS(irq_matrix_global_update,
+
+	TP_PROTO(int bit, struct irq_matrix *matrix),
+
+	TP_ARGS(bit, matrix),
+
+	TP_STRUCT__entry(
+		__field(	int,		bit			)
+		__field(	unsigned int,	online_maps		)
+		__field(	unsigned int,	global_available	)
+		__field(	unsigned int,	global_reserved		)
+		__field(	unsigned int,	total_allocated		)
+	),
+
+	TP_fast_assign(
+		__entry->bit			= bit;
+		__entry->online_maps		= matrix->online_maps;
+		__entry->global_available	= matrix->global_available;
+		__entry->global_reserved	= matrix->global_reserved;
+		__entry->total_allocated	= matrix->total_allocated;
+	),
+
+	TP_printk("bit=%d online_maps=%d global_avl=%u, global_rsvd=%u, total_alloc=%u",
+		  __entry->bit, __entry->online_maps,
+		  __entry->global_available, __entry->global_reserved,
+		  __entry->total_allocated)
+);
+
+DECLARE_EVENT_CLASS(irq_matrix_cpu,
+
+	TP_PROTO(int bit, unsigned int cpu, struct irq_matrix *matrix,
+		 struct cpumap *cmap),
+
+	TP_ARGS(bit, cpu, matrix, cmap),
+
+	TP_STRUCT__entry(
+		__field(	int,		bit			)
+		__field(	unsigned int,	cpu			)
+		__field(	bool,		online			)
+		__field(	unsigned int,	available		)
+		__field(	unsigned int,	allocated		)
+		__field(	unsigned int,	managed			)
+		__field(	unsigned int,	online_maps		)
+		__field(	unsigned int,	global_available	)
+		__field(	unsigned int,	global_reserved		)
+		__field(	unsigned int,	total_allocated		)
+	),
+
+	TP_fast_assign(
+		__entry->bit			= bit;
+		__entry->cpu			= cpu;
+		__entry->online			= cmap->online;
+		__entry->available		= cmap->available;
+		__entry->allocated		= cmap->allocated;
+		__entry->managed		= cmap->managed;
+		__entry->online_maps		= matrix->online_maps;
+		__entry->global_available	= matrix->global_available;
+		__entry->global_reserved	= matrix->global_reserved;
+		__entry->total_allocated	= matrix->total_allocated;
+	),
+
+	TP_printk("bit=%d cpu=%u online=%d avl=%u alloc=%u managed=%u online_maps=%u global_avl=%u, global_rsvd=%u, total_alloc=%u",
+		  __entry->bit, __entry->cpu, __entry->online,
+		  __entry->available, __entry->allocated,
+		  __entry->managed, __entry->online_maps,
+		  __entry->global_available, __entry->global_reserved,
+		  __entry->total_allocated)
+);
+
+DEFINE_EVENT(irq_matrix_global, irq_matrix_online,
+
+	TP_PROTO(struct irq_matrix *matrix),
+
+	TP_ARGS(matrix)
+);
+
+DEFINE_EVENT(irq_matrix_global, irq_matrix_offline,
+
+	TP_PROTO(struct irq_matrix *matrix),
+
+	TP_ARGS(matrix)
+);
+
+DEFINE_EVENT(irq_matrix_global, irq_matrix_reserve,
+
+	TP_PROTO(struct irq_matrix *matrix),
+
+	TP_ARGS(matrix)
+);
+
+DEFINE_EVENT(irq_matrix_global, irq_matrix_remove_reserved,
+
+	TP_PROTO(struct irq_matrix *matrix),
+
+	TP_ARGS(matrix)
+);
+
+DEFINE_EVENT(irq_matrix_global_update, irq_matrix_assign_system,
+
+	TP_PROTO(int bit, struct irq_matrix *matrix),
+
+	TP_ARGS(bit, matrix)
+);
+
+DEFINE_EVENT(irq_matrix_cpu, irq_matrix_alloc_reserved,
+
+	TP_PROTO(int bit, unsigned int cpu,
+		 struct irq_matrix *matrix, struct cpumap *cmap),
+
+	TP_ARGS(bit, cpu, matrix, cmap)
+);
+
+DEFINE_EVENT(irq_matrix_cpu, irq_matrix_reserve_managed,
+
+	TP_PROTO(int bit, unsigned int cpu,
+		 struct irq_matrix *matrix, struct cpumap *cmap),
+
+	TP_ARGS(bit, cpu, matrix, cmap)
+);
+
+DEFINE_EVENT(irq_matrix_cpu, irq_matrix_remove_managed,
+
+	TP_PROTO(int bit, unsigned int cpu,
+		 struct irq_matrix *matrix, struct cpumap *cmap),
+
+	TP_ARGS(bit, cpu, matrix, cmap)
+);
+
+DEFINE_EVENT(irq_matrix_cpu, irq_matrix_alloc_managed,
+
+	TP_PROTO(int bit, unsigned int cpu,
+		 struct irq_matrix *matrix, struct cpumap *cmap),
+
+	TP_ARGS(bit, cpu, matrix, cmap)
+);
+
+DEFINE_EVENT(irq_matrix_cpu, irq_matrix_assign,
+
+	TP_PROTO(int bit, unsigned int cpu,
+		 struct irq_matrix *matrix, struct cpumap *cmap),
+
+	TP_ARGS(bit, cpu, matrix, cmap)
+);
+
+DEFINE_EVENT(irq_matrix_cpu, irq_matrix_alloc,
+
+	TP_PROTO(int bit, unsigned int cpu,
+		 struct irq_matrix *matrix, struct cpumap *cmap),
+
+	TP_ARGS(bit, cpu, matrix, cmap)
+);
+
+DEFINE_EVENT(irq_matrix_cpu, irq_matrix_free,
+
+	TP_PROTO(int bit, unsigned int cpu,
+		 struct irq_matrix *matrix, struct cpumap *cmap),
+
+	TP_ARGS(bit, cpu, matrix, cmap)
+);
+
+
+#endif /*  _TRACE_IRQ_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>

kernel/irq/Kconfig

@@ -97,6 +97,9 @@ config HANDLE_DOMAIN_IRQ
 config IRQ_TIMINGS
 	bool
 
+config GENERIC_IRQ_MATRIX_ALLOCATOR
+	bool
+
 config IRQ_DOMAIN_DEBUG
 	bool "Expose hardware/virtual IRQ mapping via debugfs"
 	depends on IRQ_DOMAIN && DEBUG_FS

kernel/irq/Makefile

@@ -13,3 +13,4 @@ obj-$(CONFIG_GENERIC_MSI_IRQ) += msi.o
 obj-$(CONFIG_GENERIC_IRQ_IPI) += ipi.o
 obj-$(CONFIG_SMP) += affinity.o
 obj-$(CONFIG_GENERIC_IRQ_DEBUGFS) += debugfs.o
+obj-$(CONFIG_GENERIC_IRQ_MATRIX_ALLOCATOR) += matrix.o

kernel/irq/autoprobe.c

@@ -53,7 +53,7 @@ unsigned long probe_irq_on(void)
 			if (desc->irq_data.chip->irq_set_type)
 				desc->irq_data.chip->irq_set_type(&desc->irq_data,
 							 IRQ_TYPE_PROBE);
-			irq_startup(desc, IRQ_NORESEND, IRQ_START_FORCE);
+			irq_activate_and_startup(desc, IRQ_NORESEND);
 		}
 		raw_spin_unlock_irq(&desc->lock);
 	}

kernel/irq/chip.c

@@ -207,20 +207,24 @@ __irq_startup_managed(struct irq_desc *desc, struct cpumask *aff, bool force)
 		 * Catch code which fiddles with enable_irq() on a managed
 		 * and potentially shutdown IRQ. Chained interrupt
 		 * installment or irq auto probing should not happen on
-		 * managed irqs either. Emit a warning, break the affinity
+		 * managed irqs either.
-		 * and start it up as a normal interrupt.
 		 */
 		if (WARN_ON_ONCE(force))
-			return IRQ_STARTUP_NORMAL;
+			return IRQ_STARTUP_ABORT;
 		/*
 		 * The interrupt was requested, but there is no online CPU
 		 * in it's affinity mask. Put it into managed shutdown
 		 * state and let the cpu hotplug mechanism start it up once
 		 * a CPU in the mask becomes available.
 		 */
-		irqd_set_managed_shutdown(d);
 		return IRQ_STARTUP_ABORT;
 	}
+	/*
+	 * Managed interrupts have reserved resources, so this should not
+	 * happen.
+	 */
+	if (WARN_ON(irq_domain_activate_irq(d, false)))
+		return IRQ_STARTUP_ABORT;
 	return IRQ_STARTUP_MANAGED;
 }
 #else
@@ -236,7 +240,9 @@ static int __irq_startup(struct irq_desc *desc)
 	struct irq_data *d = irq_desc_get_irq_data(desc);
 	int ret = 0;
 
-	irq_domain_activate_irq(d);
+	/* Warn if this interrupt is not activated but try nevertheless */
+	WARN_ON_ONCE(!irqd_is_activated(d));
+
 	if (d->chip->irq_startup) {
 		ret = d->chip->irq_startup(d);
 		irq_state_clr_disabled(desc);
@@ -269,6 +275,7 @@ int irq_startup(struct irq_desc *desc, bool resend, bool force)
 			irq_set_affinity_locked(d, aff, false);
 			break;
 		case IRQ_STARTUP_ABORT:
+			irqd_set_managed_shutdown(d);
 			return 0;
 		}
 	}
@@ -278,6 +285,22 @@ int irq_startup(struct irq_desc *desc, bool resend, bool force)
 	return ret;
 }
 
+int irq_activate(struct irq_desc *desc)
+{
+	struct irq_data *d = irq_desc_get_irq_data(desc);
+
+	if (!irqd_affinity_is_managed(d))
+		return irq_domain_activate_irq(d, false);
+	return 0;
+}
+
+void irq_activate_and_startup(struct irq_desc *desc, bool resend)
+{
+	if (WARN_ON(irq_activate(desc)))
+		return;
+	irq_startup(desc, resend, IRQ_START_FORCE);
+}
+
 static void __irq_disable(struct irq_desc *desc, bool mask);
 
 void irq_shutdown(struct irq_desc *desc)
@@ -953,7 +976,7 @@ __irq_do_set_handler(struct irq_desc *desc, irq_flow_handler_t handle,
 		irq_settings_set_norequest(desc);
 		irq_settings_set_nothread(desc);
 		desc->action = &chained_action;
-		irq_startup(desc, IRQ_RESEND, IRQ_START_FORCE);
+		irq_activate_and_startup(desc, IRQ_RESEND);
 	}
 }
 

kernel/irq/debugfs.c

@@ -81,6 +81,8 @@ irq_debug_show_data(struct seq_file *m, struct irq_data *data, int ind)
 		   data->domain ? data->domain->name : "");
 	seq_printf(m, "%*shwirq:   0x%lx\n", ind + 1, "", data->hwirq);
 	irq_debug_show_chip(m, data, ind + 1);
+	if (data->domain && data->domain->ops && data->domain->ops->debug_show)
+		data->domain->ops->debug_show(m, NULL, data, ind + 1);
 #ifdef	CONFIG_IRQ_DOMAIN_HIERARCHY
 	if (!data->parent_data)
 		return;
@@ -149,6 +151,7 @@ static int irq_debug_show(struct seq_file *m, void *p)
 	raw_spin_lock_irq(&desc->lock);
 	data = irq_desc_get_irq_data(desc);
 	seq_printf(m, "handler:  %pf\n", desc->handle_irq);
+	seq_printf(m, "device:   %s\n", desc->dev_name);
 	seq_printf(m, "status:   0x%08x\n", desc->status_use_accessors);
 	irq_debug_show_bits(m, 0, desc->status_use_accessors, irqdesc_states,
 			    ARRAY_SIZE(irqdesc_states));
@@ -226,6 +229,15 @@ static const struct file_operations dfs_irq_ops = {
 	.release	= single_release,
 };
 
+void irq_debugfs_copy_devname(int irq, struct device *dev)
+{
+	struct irq_desc *desc = irq_to_desc(irq);
+	const char *name = dev_name(dev);
+
+	if (name)
+		desc->dev_name = kstrdup(name, GFP_KERNEL);
+}
+
 void irq_add_debugfs_entry(unsigned int irq, struct irq_desc *desc)
 {
 	char name [10];

kernel/irq/internals.h

@@ -74,6 +74,8 @@ extern void __enable_irq(struct irq_desc *desc);
 #define IRQ_START_FORCE	true
 #define IRQ_START_COND	false
 
+extern int irq_activate(struct irq_desc *desc);
+extern void irq_activate_and_startup(struct irq_desc *desc, bool resend);
 extern int irq_startup(struct irq_desc *desc, bool resend, bool force);
 
 extern void irq_shutdown(struct irq_desc *desc);
@@ -436,6 +438,18 @@ static inline bool irq_fixup_move_pending(struct irq_desc *desc, bool fclear)
 }
 #endif /* !CONFIG_GENERIC_PENDING_IRQ */
 
+#if !defined(CONFIG_IRQ_DOMAIN) || !defined(CONFIG_IRQ_DOMAIN_HIERARCHY)
+static inline int irq_domain_activate_irq(struct irq_data *data, bool early)
+{
+	irqd_set_activated(data);
+	return 0;
+}
+static inline void irq_domain_deactivate_irq(struct irq_data *data)
+{
+	irqd_clr_activated(data);
+}
+#endif
+
 #ifdef CONFIG_GENERIC_IRQ_DEBUGFS
 #include <linux/debugfs.h>
 
@@ -443,7 +457,9 @@ void irq_add_debugfs_entry(unsigned int irq, struct irq_desc *desc);
 static inline void irq_remove_debugfs_entry(struct irq_desc *desc)
 {
 	debugfs_remove(desc->debugfs_file);
+	kfree(desc->dev_name);
 }
+void irq_debugfs_copy_devname(int irq, struct device *dev);
 # ifdef CONFIG_IRQ_DOMAIN
 void irq_domain_debugfs_init(struct dentry *root);
 # else
@@ -458,4 +474,7 @@ static inline void irq_add_debugfs_entry(unsigned int irq, struct irq_desc *d)
 static inline void irq_remove_debugfs_entry(struct irq_desc *d)
 {
 }
+static inline void irq_debugfs_copy_devname(int irq, struct device *dev)
+{
+}
 #endif /* CONFIG_GENERIC_IRQ_DEBUGFS */

kernel/irq/irqdesc.c

@@ -448,7 +448,7 @@ static int alloc_descs(unsigned int start, unsigned int cnt, int node,
 		}
 	}
 
-	flags = affinity ? IRQD_AFFINITY_MANAGED : 0;
+	flags = affinity ? IRQD_AFFINITY_MANAGED | IRQD_MANAGED_SHUTDOWN : 0;
 	mask = NULL;
 
 	for (i = 0; i < cnt; i++) {
@@ -462,6 +462,7 @@ static int alloc_descs(unsigned int start, unsigned int cnt, int node,
 			goto err;
 		irq_insert_desc(start + i, desc);
 		irq_sysfs_add(start + i, desc);
+		irq_add_debugfs_entry(start + i, desc);
 	}
 	bitmap_set(allocated_irqs, start, cnt);
 	return start;

kernel/irq/irqdomain.c

@@ -1682,18 +1682,6 @@ void irq_domain_free_irqs_parent(struct irq_domain *domain,
 }
 EXPORT_SYMBOL_GPL(irq_domain_free_irqs_parent);
 
-static void __irq_domain_activate_irq(struct irq_data *irq_data)
-{
-	if (irq_data && irq_data->domain) {
-		struct irq_domain *domain = irq_data->domain;
-
-		if (irq_data->parent_data)
-			__irq_domain_activate_irq(irq_data->parent_data);
-		if (domain->ops->activate)
-			domain->ops->activate(domain, irq_data);
-	}
-}
-
 static void __irq_domain_deactivate_irq(struct irq_data *irq_data)
 {
 	if (irq_data && irq_data->domain) {
@@ -1706,6 +1694,26 @@ static void __irq_domain_deactivate_irq(struct irq_data *irq_data)
 	}
 }
 
+static int __irq_domain_activate_irq(struct irq_data *irqd, bool early)
+{
+	int ret = 0;
+
+	if (irqd && irqd->domain) {
+		struct irq_domain *domain = irqd->domain;
+
+		if (irqd->parent_data)
+			ret = __irq_domain_activate_irq(irqd->parent_data,
+							early);
+		if (!ret && domain->ops->activate) {
+			ret = domain->ops->activate(domain, irqd, early);
+			/* Rollback in case of error */
+			if (ret && irqd->parent_data)
+				__irq_domain_deactivate_irq(irqd->parent_data);
+		}
+	}
+	return ret;
+}
+
 /**
  * irq_domain_activate_irq - Call domain_ops->activate recursively to activate
  *			     interrupt
@@ -1714,12 +1722,15 @@ static void __irq_domain_deactivate_irq(struct irq_data *irq_data)
  * This is the second step to call domain_ops->activate to program interrupt
  * controllers, so the interrupt could actually get delivered.
  */
-void irq_domain_activate_irq(struct irq_data *irq_data)
+int irq_domain_activate_irq(struct irq_data *irq_data, bool early)
 {
-	if (!irqd_is_activated(irq_data)) {
+	int ret = 0;
-		__irq_domain_activate_irq(irq_data);
+
+	if (!irqd_is_activated(irq_data))
+		ret = __irq_domain_activate_irq(irq_data, early);
+	if (!ret)
 		irqd_set_activated(irq_data);
-	}
+	return ret;
 }
 
 /**
@@ -1810,6 +1821,8 @@ irq_domain_debug_show_one(struct seq_file *m, struct irq_domain *d, int ind)
 		   d->revmap_size + d->revmap_direct_max_irq);
 	seq_printf(m, "%*smapped: %u\n", ind + 1, "", d->mapcount);
 	seq_printf(m, "%*sflags:  0x%08x\n", ind +1 , "", d->flags);
+	if (d->ops && d->ops->debug_show)
+		d->ops->debug_show(m, d, NULL, ind + 1);
 #ifdef	CONFIG_IRQ_DOMAIN_HIERARCHY
 	if (!d->parent)
 		return;

kernel/irq/manage.c

@@ -519,7 +519,7 @@ void __enable_irq(struct irq_desc *desc)
 		 * time. If it was already started up, then irq_startup()
 		 * will invoke irq_enable() under the hood.
 		 */
-		irq_startup(desc, IRQ_RESEND, IRQ_START_COND);
+		irq_startup(desc, IRQ_RESEND, IRQ_START_FORCE);
 		break;
 	}
 	default:
@@ -1325,6 +1325,21 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 				goto out_unlock;
 		}
 
+		/*
+		 * Activate the interrupt. That activation must happen
+		 * independently of IRQ_NOAUTOEN. request_irq() can fail
+		 * and the callers are supposed to handle
+		 * that. enable_irq() of an interrupt requested with
+		 * IRQ_NOAUTOEN is not supposed to fail. The activation
+		 * keeps it in shutdown mode, it merily associates
+		 * resources if necessary and if that's not possible it
+		 * fails. Interrupts which are in managed shutdown mode
+		 * will simply ignore that activation request.
+		 */
+		ret = irq_activate(desc);
+		if (ret)
+			goto out_unlock;
+
 		desc->istate &= ~(IRQS_AUTODETECT | IRQS_SPURIOUS_DISABLED | \
 				  IRQS_ONESHOT | IRQS_WAITING);
 		irqd_clear(&desc->irq_data, IRQD_IRQ_INPROGRESS);
@@ -1400,7 +1415,6 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 		wake_up_process(new->secondary->thread);
 
 	register_irq_proc(irq, desc);
-	irq_add_debugfs_entry(irq, desc);
 	new->dir = NULL;
 	register_handler_proc(irq, new);
 	return 0;
@@ -1643,6 +1657,10 @@ const void *free_irq(unsigned int irq, void *dev_id)
 #endif
 
 	action = __free_irq(irq, dev_id);
+
+	if (!action)
+		return NULL;
+
 	devname = action->name;
 	kfree(action);
 	return devname;

kernel/irq/matrix.c

@@ -0,0 +1,443 @@
+/*
+ * Copyright (C) 2017 Thomas Gleixner <tglx@linutronix.de>
+ *
+ * SPDX-License-Identifier: GPL-2.0
+ */
+#include <linux/spinlock.h>
+#include <linux/seq_file.h>
+#include <linux/bitmap.h>
+#include <linux/percpu.h>
+#include <linux/cpu.h>
+#include <linux/irq.h>
+
+#define IRQ_MATRIX_SIZE	(BITS_TO_LONGS(IRQ_MATRIX_BITS) * sizeof(unsigned long))
+
+struct cpumap {
+	unsigned int		available;
+	unsigned int		allocated;
+	unsigned int		managed;
+	bool			online;
+	unsigned long		alloc_map[IRQ_MATRIX_SIZE];
+	unsigned long		managed_map[IRQ_MATRIX_SIZE];
+};
+
+struct irq_matrix {
+	unsigned int		matrix_bits;
+	unsigned int		alloc_start;
+	unsigned int		alloc_end;
+	unsigned int		alloc_size;
+	unsigned int		global_available;
+	unsigned int		global_reserved;
+	unsigned int		systembits_inalloc;
+	unsigned int		total_allocated;
+	unsigned int		online_maps;
+	struct cpumap __percpu	*maps;
+	unsigned long		scratch_map[IRQ_MATRIX_SIZE];
+	unsigned long		system_map[IRQ_MATRIX_SIZE];
+};
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/irq_matrix.h>
+
+/**
+ * irq_alloc_matrix - Allocate a irq_matrix structure and initialize it
+ * @matrix_bits:	Number of matrix bits must be <= IRQ_MATRIX_BITS
+ * @alloc_start:	From which bit the allocation search starts
+ * @alloc_end:		At which bit the allocation search ends, i.e first
+ *			invalid bit
+ */
+__init struct irq_matrix *irq_alloc_matrix(unsigned int matrix_bits,
+					   unsigned int alloc_start,
+					   unsigned int alloc_end)
+{
+	struct irq_matrix *m;
+
+	if (matrix_bits > IRQ_MATRIX_BITS)
+		return NULL;
+
+	m = kzalloc(sizeof(*m), GFP_KERNEL);
+	if (!m)
+		return NULL;
+
+	m->matrix_bits = matrix_bits;
+	m->alloc_start = alloc_start;
+	m->alloc_end = alloc_end;
+	m->alloc_size = alloc_end - alloc_start;
+	m->maps = alloc_percpu(*m->maps);
+	if (!m->maps) {
+		kfree(m);
+		return NULL;
+	}
+	return m;
+}
+
+/**
+ * irq_matrix_online - Bring the local CPU matrix online
+ * @m:		Matrix pointer
+ */
+void irq_matrix_online(struct irq_matrix *m)
+{
+	struct cpumap *cm = this_cpu_ptr(m->maps);
+
+	BUG_ON(cm->online);
+
+	bitmap_zero(cm->alloc_map, m->matrix_bits);
+	cm->available = m->alloc_size - (cm->managed + m->systembits_inalloc);
+	cm->allocated = 0;
+	m->global_available += cm->available;
+	cm->online = true;
+	m->online_maps++;
+	trace_irq_matrix_online(m);
+}
+
+/**
+ * irq_matrix_offline - Bring the local CPU matrix offline
+ * @m:		Matrix pointer
+ */
+void irq_matrix_offline(struct irq_matrix *m)
+{
+	struct cpumap *cm = this_cpu_ptr(m->maps);
+
+	/* Update the global available size */
+	m->global_available -= cm->available;
+	cm->online = false;
+	m->online_maps--;
+	trace_irq_matrix_offline(m);
+}
+
+static unsigned int matrix_alloc_area(struct irq_matrix *m, struct cpumap *cm,
+				      unsigned int num, bool managed)
+{
+	unsigned int area, start = m->alloc_start;
+	unsigned int end = m->alloc_end;
+
+	bitmap_or(m->scratch_map, cm->managed_map, m->system_map, end);
+	bitmap_or(m->scratch_map, m->scratch_map, cm->alloc_map, end);
+	area = bitmap_find_next_zero_area(m->scratch_map, end, start, num, 0);
+	if (area >= end)
+		return area;
+	if (managed)
+		bitmap_set(cm->managed_map, area, num);
+	else
+		bitmap_set(cm->alloc_map, area, num);
+	return area;
+}
+
+/**
+ * irq_matrix_assign_system - Assign system wide entry in the matrix
+ * @m:		Matrix pointer
+ * @bit:	Which bit to reserve
+ * @replace:	Replace an already allocated vector with a system
+ *		vector at the same bit position.
+ *
+ * The BUG_ON()s below are on purpose. If this goes wrong in the
+ * early boot process, then the chance to survive is about zero.
+ * If this happens when the system is life, it's not much better.
+ */
+void irq_matrix_assign_system(struct irq_matrix *m, unsigned int bit,
+			      bool replace)
+{
+	struct cpumap *cm = this_cpu_ptr(m->maps);
+
+	BUG_ON(bit > m->matrix_bits);
+	BUG_ON(m->online_maps > 1 || (m->online_maps && !replace));
+
+	set_bit(bit, m->system_map);
+	if (replace) {
+		BUG_ON(!test_and_clear_bit(bit, cm->alloc_map));
+		cm->allocated--;
+		m->total_allocated--;
+	}
+	if (bit >= m->alloc_start && bit < m->alloc_end)
+		m->systembits_inalloc++;
+
+	trace_irq_matrix_assign_system(bit, m);
+}
+
+/**
+ * irq_matrix_reserve_managed - Reserve a managed interrupt in a CPU map
+ * @m:		Matrix pointer
+ * @msk:	On which CPUs the bits should be reserved.
+ *
+ * Can be called for offline CPUs. Note, this will only reserve one bit
+ * on all CPUs in @msk, but it's not guaranteed that the bits are at the
+ * same offset on all CPUs
+ */
+int irq_matrix_reserve_managed(struct irq_matrix *m, const struct cpumask *msk)
+{
+	unsigned int cpu, failed_cpu;
+
+	for_each_cpu(cpu, msk) {
+		struct cpumap *cm = per_cpu_ptr(m->maps, cpu);
+		unsigned int bit;
+
+		bit = matrix_alloc_area(m, cm, 1, true);
+		if (bit >= m->alloc_end)
+			goto cleanup;
+		cm->managed++;
+		if (cm->online) {
+			cm->available--;
+			m->global_available--;
+		}
+		trace_irq_matrix_reserve_managed(bit, cpu, m, cm);
+	}
+	return 0;
+cleanup:
+	failed_cpu = cpu;
+	for_each_cpu(cpu, msk) {
+		if (cpu == failed_cpu)
+			break;
+		irq_matrix_remove_managed(m, cpumask_of(cpu));
+	}
+	return -ENOSPC;
+}
+
+/**
+ * irq_matrix_remove_managed - Remove managed interrupts in a CPU map
+ * @m:		Matrix pointer
+ * @msk:	On which CPUs the bits should be removed
+ *
+ * Can be called for offline CPUs
+ *
+ * This removes not allocated managed interrupts from the map. It does
+ * not matter which one because the managed interrupts free their
+ * allocation when they shut down. If not, the accounting is screwed,
+ * but all what can be done at this point is warn about it.
+ */
+void irq_matrix_remove_managed(struct irq_matrix *m, const struct cpumask *msk)
+{
+	unsigned int cpu;
+
+	for_each_cpu(cpu, msk) {
+		struct cpumap *cm = per_cpu_ptr(m->maps, cpu);
+		unsigned int bit, end = m->alloc_end;
+
+		if (WARN_ON_ONCE(!cm->managed))
+			continue;
+
+		/* Get managed bit which are not allocated */
+		bitmap_andnot(m->scratch_map, cm->managed_map, cm->alloc_map, end);
+
+		bit = find_first_bit(m->scratch_map, end);
+		if (WARN_ON_ONCE(bit >= end))
+			continue;
+
+		clear_bit(bit, cm->managed_map);
+
+		cm->managed--;
+		if (cm->online) {
+			cm->available++;
+			m->global_available++;
+		}
+		trace_irq_matrix_remove_managed(bit, cpu, m, cm);
+	}
+}
+
+/**
+ * irq_matrix_alloc_managed - Allocate a managed interrupt in a CPU map
+ * @m:		Matrix pointer
+ * @cpu:	On which CPU the interrupt should be allocated
+ */
+int irq_matrix_alloc_managed(struct irq_matrix *m, unsigned int cpu)
+{
+	struct cpumap *cm = per_cpu_ptr(m->maps, cpu);
+	unsigned int bit, end = m->alloc_end;
+
+	/* Get managed bit which are not allocated */
+	bitmap_andnot(m->scratch_map, cm->managed_map, cm->alloc_map, end);
+	bit = find_first_bit(m->scratch_map, end);
+	if (bit >= end)
+		return -ENOSPC;
+	set_bit(bit, cm->alloc_map);
+	cm->allocated++;
+	m->total_allocated++;
+	trace_irq_matrix_alloc_managed(bit, cpu, m, cm);
+	return bit;
+}
+
+/**
+ * irq_matrix_assign - Assign a preallocated interrupt in the local CPU map
+ * @m:		Matrix pointer
+ * @bit:	Which bit to mark
+ *
+ * This should only be used to mark preallocated vectors
+ */
+void irq_matrix_assign(struct irq_matrix *m, unsigned int bit)
+{
+	struct cpumap *cm = this_cpu_ptr(m->maps);
+
+	if (WARN_ON_ONCE(bit < m->alloc_start || bit >= m->alloc_end))
+		return;
+	if (WARN_ON_ONCE(test_and_set_bit(bit, cm->alloc_map)))
+		return;
+	cm->allocated++;
+	m->total_allocated++;
+	cm->available--;
+	m->global_available--;
+	trace_irq_matrix_assign(bit, smp_processor_id(), m, cm);
+}
+
+/**
+ * irq_matrix_reserve - Reserve interrupts
+ * @m:		Matrix pointer
+ *
+ * This is merily a book keeping call. It increments the number of globally
+ * reserved interrupt bits w/o actually allocating them. This allows to
+ * setup interrupt descriptors w/o assigning low level resources to it.
+ * The actual allocation happens when the interrupt gets activated.
+ */
+void irq_matrix_reserve(struct irq_matrix *m)
+{
+	if (m->global_reserved <= m->global_available &&
+	    m->global_reserved + 1 > m->global_available)
+		pr_warn("Interrupt reservation exceeds available resources\n");
+
+	m->global_reserved++;
+	trace_irq_matrix_reserve(m);
+}
+
+/**
+ * irq_matrix_remove_reserved - Remove interrupt reservation
+ * @m:		Matrix pointer
+ *
+ * This is merily a book keeping call. It decrements the number of globally
+ * reserved interrupt bits. This is used to undo irq_matrix_reserve() when the
+ * interrupt was never in use and a real vector allocated, which undid the
+ * reservation.
+ */
+void irq_matrix_remove_reserved(struct irq_matrix *m)
+{
+	m->global_reserved--;
+	trace_irq_matrix_remove_reserved(m);
+}
+
+/**
+ * irq_matrix_alloc - Allocate a regular interrupt in a CPU map
+ * @m:		Matrix pointer
+ * @msk:	Which CPUs to search in
+ * @reserved:	Allocate previously reserved interrupts
+ * @mapped_cpu: Pointer to store the CPU for which the irq was allocated
+ */
+int irq_matrix_alloc(struct irq_matrix *m, const struct cpumask *msk,
+		     bool reserved, unsigned int *mapped_cpu)
+{
+	unsigned int cpu;
+
+	for_each_cpu(cpu, msk) {
+		struct cpumap *cm = per_cpu_ptr(m->maps, cpu);
+		unsigned int bit;
+
+		if (!cm->online)
+			continue;
+
+		bit = matrix_alloc_area(m, cm, 1, false);
+		if (bit < m->alloc_end) {
+			cm->allocated++;
+			cm->available--;
+			m->total_allocated++;
+			m->global_available--;
+			if (reserved)
+				m->global_reserved--;
+			*mapped_cpu = cpu;
+			trace_irq_matrix_alloc(bit, cpu, m, cm);
+			return bit;
+		}
+	}
+	return -ENOSPC;
+}
+
+/**
+ * irq_matrix_free - Free allocated interrupt in the matrix
+ * @m:		Matrix pointer
+ * @cpu:	Which CPU map needs be updated
+ * @bit:	The bit to remove
+ * @managed:	If true, the interrupt is managed and not accounted
+ *		as available.
+ */
+void irq_matrix_free(struct irq_matrix *m, unsigned int cpu,
+		     unsigned int bit, bool managed)
+{
+	struct cpumap *cm = per_cpu_ptr(m->maps, cpu);
+
+	if (WARN_ON_ONCE(bit < m->alloc_start || bit >= m->alloc_end))
+		return;
+
+	if (cm->online) {
+		clear_bit(bit, cm->alloc_map);
+		cm->allocated--;
+		m->total_allocated--;
+		if (!managed) {
+			cm->available++;
+			m->global_available++;
+		}
+	}
+	trace_irq_matrix_free(bit, cpu, m, cm);
+}
+
+/**
+ * irq_matrix_available - Get the number of globally available irqs
+ * @m:		Pointer to the matrix to query
+ * @cpudown:	If true, the local CPU is about to go down, adjust
+ *		the number of available irqs accordingly
+ */
+unsigned int irq_matrix_available(struct irq_matrix *m, bool cpudown)
+{
+	struct cpumap *cm = this_cpu_ptr(m->maps);
+
+	return m->global_available - cpudown ? cm->available : 0;
+}
+
+/**
+ * irq_matrix_reserved - Get the number of globally reserved irqs
+ * @m:		Pointer to the matrix to query
+ */
+unsigned int irq_matrix_reserved(struct irq_matrix *m)
+{
+	return m->global_reserved;
+}
+
+/**
+ * irq_matrix_allocated - Get the number of allocated irqs on the local cpu
+ * @m:		Pointer to the matrix to search
+ *
+ * This returns number of allocated irqs
+ */
+unsigned int irq_matrix_allocated(struct irq_matrix *m)
+{
+	struct cpumap *cm = this_cpu_ptr(m->maps);
+
+	return cm->allocated;
+}
+
+#ifdef CONFIG_GENERIC_IRQ_DEBUGFS
+/**
+ * irq_matrix_debug_show - Show detailed allocation information
+ * @sf:		Pointer to the seq_file to print to
+ * @m:		Pointer to the matrix allocator
+ * @ind:	Indentation for the print format
+ *
+ * Note, this is a lockless snapshot.
+ */
+void irq_matrix_debug_show(struct seq_file *sf, struct irq_matrix *m, int ind)
+{
+	unsigned int nsys = bitmap_weight(m->system_map, m->matrix_bits);
+	int cpu;
+
+	seq_printf(sf, "Online bitmaps:   %6u\n", m->online_maps);
+	seq_printf(sf, "Global available: %6u\n", m->global_available);
+	seq_printf(sf, "Global reserved:  %6u\n", m->global_reserved);
+	seq_printf(sf, "Total allocated:  %6u\n", m->total_allocated);
+	seq_printf(sf, "System: %u: %*pbl\n", nsys, m->matrix_bits,
+		   m->system_map);
+	seq_printf(sf, "%*s| CPU | avl | man | act | vectors\n", ind, " ");
+	cpus_read_lock();
+	for_each_online_cpu(cpu) {
+		struct cpumap *cm = per_cpu_ptr(m->maps, cpu);
+
+		seq_printf(sf, "%*s %4d  %4u  %4u  %4u  %*pbl\n", ind, " ",
+			   cpu, cm->available, cm->managed, cm->allocated,
+			   m->matrix_bits, cm->alloc_map);
+	}
+	cpus_read_unlock();
+}
+#endif

kernel/irq/msi.c

@@ -16,6 +16,8 @@
 #include <linux/msi.h>
 #include <linux/slab.h>
 
+#include "internals.h"
+
 /**
  * alloc_msi_entry - Allocate an initialize msi_entry
  * @dev:	Pointer to the device for which this is allocated
@@ -100,13 +102,14 @@ int msi_domain_set_affinity(struct irq_data *irq_data,
 	return ret;
 }
 
-static void msi_domain_activate(struct irq_domain *domain,
+static int msi_domain_activate(struct irq_domain *domain,
-				struct irq_data *irq_data)
+			       struct irq_data *irq_data, bool early)
 {
 	struct msi_msg msg;
 
 	BUG_ON(irq_chip_compose_msi_msg(irq_data, &msg));
 	irq_chip_write_msi_msg(irq_data, &msg);
+	return 0;
 }
 
 static void msi_domain_deactivate(struct irq_domain *domain,
@@ -373,8 +376,10 @@ int msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev,
 			return ret;
 		}
 
-		for (i = 0; i < desc->nvec_used; i++)
+		for (i = 0; i < desc->nvec_used; i++) {
 			irq_set_msi_desc_off(virq, i, desc);
+			irq_debugfs_copy_devname(virq + i, dev);
+		}
 	}
 
 	if (ops->msi_finish)
@@ -396,11 +401,28 @@ int msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev,
 			struct irq_data *irq_data;
 
 			irq_data = irq_domain_get_irq_data(domain, desc->irq);
-			irq_domain_activate_irq(irq_data);
+			ret = irq_domain_activate_irq(irq_data, true);
+			if (ret)
+				goto cleanup;
+			if (info->flags & MSI_FLAG_MUST_REACTIVATE)
+				irqd_clr_activated(irq_data);
 		}
 	}
-
 	return 0;
+
+cleanup:
+	for_each_msi_entry(desc, dev) {
+		struct irq_data *irqd;
+
+		if (desc->irq == virq)
+			break;
+
+		irqd = irq_domain_get_irq_data(domain, desc->irq);
+		if (irqd_is_activated(irqd))
+			irq_domain_deactivate_irq(irqd);
+	}
+	msi_domain_free_irqs(domain, dev);
+	return ret;
 }
 
 /**