Convert x86 to hierarchy irqdomain and stacked irqchip

index 9662290e0b20..b988ddf7434b 100644
@@ -116,6 +116,7 @@ struct irq_data;
 struct irq_cfg {
 	cpumask_var_t		domain;
 	cpumask_var_t		old_domain;
+	unsigned int		dest_apicid;
 	u8			vector;
 	u8			move_in_progress : 1;
 #ifdef CONFIG_IRQ_REMAP

index 6cedd7914581..c724ef6b218c 100644
@@ -188,6 +188,12 @@ next:
 	}
 	free_cpumask_var(tmp_mask);
 
+	if (!err) {
+		/* cache destination APIC IDs into cfg->dest_apicid */
+		err = apic->cpu_mask_to_apicid_and(mask, cfg->domain,
+						   &cfg->dest_apicid);
+	}
+
 	return err;
 }
 

index b988ddf7434b..eb7692c9ab93 100644
@@ -112,6 +112,17 @@ struct irq_2_irte {
 
 #ifdef	CONFIG_X86_LOCAL_APIC
 struct irq_data;
+struct irq_domain;
+
+struct irq_alloc_info {
+	u32			flags;
+	const struct cpumask	*mask;	/* CPU mask for vector allocation */
+};
+
+enum {
+	/* Allocate contigious CPU vectors */
+	X86_IRQ_ALLOC_CONTIGOUS_VECTORS		= 0x1,
+};
 
 struct irq_cfg {
 	cpumask_var_t		domain;

@@ -135,6 +146,12 @@ struct irq_cfg {
 	};
 };
 
+extern struct irq_domain *x86_vector_domain;
+
+extern void init_irq_alloc_info(struct irq_alloc_info *info,
+				const struct cpumask *mask);
+extern void copy_irq_alloc_info(struct irq_alloc_info *dst,
+				struct irq_alloc_info *src);
 extern struct irq_cfg *irq_cfg(unsigned int irq);
 extern struct irq_cfg *irqd_cfg(struct irq_data *irq_data);
 extern struct irq_cfg *alloc_irq_and_cfg_at(unsigned int at, int node);

index f4dc2462a1ac..56d532106ef3 100644
@@ -2356,9 +2356,6 @@ static int mp_irqdomain_create(int ioapic)
 		ioapic_dynirq_base = max(ioapic_dynirq_base,
 					 gsi_cfg->gsi_end + 1);
 
-	if (gsi_cfg->gsi_base == 0)
-		irq_set_default_host(ip->irqdomain);
-
 	return 0;
 }
 

231 lines not on this page · raw message

index 3acbff4716b0..ae29554f57ea 100644
@@ -11,6 +11,7 @@
 #include <linux/cpu.h>
 #include <linux/pm.h>
 #include <linux/io.h>
+#include <linux/irqdomain.h>
 
 #include <asm/fixmap.h>
 #include <asm/hpet.h>

@@ -476,7 +477,7 @@ static int hpet_msi_next_event(unsigned long delta,
 static int hpet_setup_msi_irq(unsigned int irq)
 {
 	if (x86_msi.setup_hpet_msi(irq, hpet_blockid)) {
-		irq_free_hwirq(irq);
+		irq_domain_free_irqs(irq, 1);
 		return -EINVAL;
 	}
 	return 0;

@@ -484,9 +485,10 @@ static int hpet_setup_msi_irq(unsigned int irq)
 
 static int hpet_assign_irq(struct hpet_dev *dev)
 {
-	unsigned int irq = irq_alloc_hwirq(-1);
+	int irq;
 
-	if (!irq)
+	irq = irq_domain_alloc_irqs(NULL, 1, NUMA_NO_NODE, NULL);
+	if (irq <= 0)
 		return -EINVAL;
 
 	irq_set_handler_data(irq, dev);

index d6ba2d660dc5..76cc2c902176 100644
@@ -14,6 +14,7 @@
 #include <linux/dmar.h>
 #include <linux/hpet.h>
 #include <linux/msi.h>
+#include <linux/irqdomain.h>
 #include <asm/msidef.h>
 #include <asm/hpet.h>
 #include <asm/hw_irq.h>

@@ -146,23 +147,20 @@ int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc,
 int native_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 {
 	struct msi_desc *msidesc;
-	unsigned int irq;
-	int node, ret;
+	int irq, ret;
 
 	/* Multiple MSI vectors only supported with interrupt remapping */
 	if (type == PCI_CAP_ID_MSI && nvec > 1)
 		return 1;
 
-	node = dev_to_node(&dev->dev);
-
 	list_for_each_entry(msidesc, &dev->msi_list, list) {
-		irq = irq_alloc_hwirq(node);
-		if (!irq)
+		irq = irq_domain_alloc_irqs(NULL, 1, NUMA_NO_NODE, NULL);
+		if (irq <= 0)
 			return -ENOSPC;
 
 		ret = setup_msi_irq(dev, msidesc, irq, 0);
 		if (ret < 0) {
-			irq_free_hwirq(irq);
+			irq_domain_free_irqs(irq, 1);
 			return ret;
 		}
 

@@ -172,7 +170,7 @@ int native_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 
 void native_teardown_msi_irq(unsigned int irq)
 {
-	irq_free_hwirq(irq);
+	irq_domain_free_irqs(irq, 1);
 }
 
 #ifdef CONFIG_DMAR_TABLE

index 0ce673645432..474912d03f40 100644
@@ -12,6 +12,7 @@
 #include <linux/rbtree.h>
 #include <linux/slab.h>
 #include <linux/irq.h>
+#include <linux/irqdomain.h>
 
 #include <asm/apic.h>
 #include <asm/uv/uv_irq.h>

@@ -130,24 +131,14 @@ static int
 arch_enable_uv_irq(char *irq_name, unsigned int irq, int cpu, int mmr_blade,
 		       unsigned long mmr_offset, int limit)
 {
-	const struct cpumask *eligible_cpu = cpumask_of(cpu);
 	struct irq_cfg *cfg = irq_cfg(irq);
 	unsigned long mmr_value;
 	struct uv_IO_APIC_route_entry *entry;
-	int mmr_pnode, err;
-	unsigned int dest;
+	int mmr_pnode;
 
 	BUILD_BUG_ON(sizeof(struct uv_IO_APIC_route_entry) !=
 			sizeof(unsigned long));
 
-	err = assign_irq_vector(irq, cfg, eligible_cpu);
-	if (err != 0)
-		return err;
-
-	err = apic->cpu_mask_to_apicid_and(eligible_cpu, eligible_cpu, &dest);
-	if (err != 0)
-		return err;
-
 	if (limit == UV_AFFINITY_CPU)
 		irq_set_status_flags(irq, IRQ_NO_BALANCING);
 	else

@@ -164,7 +155,7 @@ arch_enable_uv_irq(char *irq_name, unsigned int irq, int cpu, int mmr_blade,
 	entry->polarity		= 0;
 	entry->trigger		= 0;
 	entry->mask		= 0;
-	entry->dest		= dest;
+	entry->dest		= cfg->dest_apicid;
 
 	mmr_pnode = uv_blade_to_pnode(mmr_blade);
 	uv_write_global_mmr64(mmr_pnode, mmr_offset, mmr_value);

@@ -238,9 +229,13 @@ uv_set_irq_affinity(struct irq_data *data, const struct cpumask *mask,
 int uv_setup_irq(char *irq_name, int cpu, int mmr_blade,
 		 unsigned long mmr_offset, int limit)
 {
-	int ret, irq = irq_alloc_hwirq(uv_blade_to_memory_nid(mmr_blade));
+	int ret, irq;
+	struct irq_alloc_info info;
 
-	if (!irq)
+	init_irq_alloc_info(&info, cpumask_of(cpu));
+	irq = irq_domain_alloc_irqs(NULL, 1, uv_blade_to_memory_nid(mmr_blade),
+				    &info);
+	if (irq <= 0)
 		return -EBUSY;
 
 	ret = arch_enable_uv_irq(irq_name, irq, cpu, mmr_blade, mmr_offset,

@@ -248,7 +243,7 @@ int uv_setup_irq(char *irq_name, int cpu, int mmr_blade,
 	if (ret == irq)
 		uv_set_irq_2_mmr_info(irq, mmr_offset, mmr_blade);
 	else
-		irq_free_hwirq(irq);
+		irq_domain_free_irqs(irq, 1);
 
 	return ret;
 }

@@ -283,6 +278,6 @@ void uv_teardown_irq(unsigned int irq)
 			n = n->rb_right;
 	}
 	spin_unlock_irqrestore(&uv_irq_lock, irqflags);
-	irq_free_hwirq(irq);
+	irq_domain_free_irqs(irq, 1);
 }
 EXPORT_SYMBOL_GPL(uv_teardown_irq);

index 816f36e979ad..b307ee7a7148 100644
@@ -14,6 +14,7 @@
 #include <linux/device.h>
 #include <linux/pci.h>
 #include <linux/htirq.h>
+#include <linux/irqdomain.h>
 #include <asm/hw_irq.h>
 #include <asm/apic.h>
 #include <asm/hypertransport.h>

@@ -61,31 +62,30 @@ static struct irq_chip ht_irq_chip = {
 	.flags			= IRQCHIP_SKIP_SET_WAKE,
 };
 
+int arch_alloc_ht_irq(struct pci_dev *dev)
+{
+	return irq_domain_alloc_irqs(NULL, 1, dev_to_node(&dev->dev), NULL);
+}
+
+void arch_free_ht_irq(int irq)
+{
+	irq_domain_free_irqs(irq, 1);
+}
+
 int arch_setup_ht_irq(unsigned int irq, struct pci_dev *dev)
 {
 	struct irq_cfg *cfg;
 	struct ht_irq_msg msg;
-	unsigned dest;
-	int err;
 
 	if (disable_apic)
 		return -ENXIO;
 
 	cfg = irq_cfg(irq);
-	err = assign_irq_vector(irq, cfg, apic->target_cpus());
-	if (err)
-		return err;
-
-	err = apic->cpu_mask_to_apicid_and(cfg->domain,
-					   apic->target_cpus(), &dest);
-	if (err)
-		return err;
-
-	msg.address_hi = HT_IRQ_HIGH_DEST_ID(dest);
+	msg.address_hi = HT_IRQ_HIGH_DEST_ID(cfg->dest_apicid);
 
 	msg.address_lo =
 		HT_IRQ_LOW_BASE |
-		HT_IRQ_LOW_DEST_ID(dest) |
+		HT_IRQ_LOW_DEST_ID(cfg->dest_apicid) |
 		HT_IRQ_LOW_VECTOR(cfg->vector) |
 		((apic->irq_dest_mode == 0) ?
 			HT_IRQ_LOW_DM_PHYSICAL :

index a94dd2c4183a..ceb0ebeb7b5f 100644
@@ -117,8 +117,8 @@ int __ht_create_irq(struct pci_dev *dev, int idx, ht_irq_update_t *update)
 	cfg->msg.address_lo = 0xffffffff;
 	cfg->msg.address_hi = 0xffffffff;
 
-	irq = irq_alloc_hwirq(dev_to_node(&dev->dev));
-	if (!irq) {
+	irq = arch_alloc_ht_irq(dev);
+	if (irq <= 0) {
 		kfree(cfg);
 		return -EBUSY;
 	}

@@ -163,8 +163,7 @@ void ht_destroy_irq(unsigned int irq)
 	cfg = irq_get_handler_data(irq);
 	irq_set_chip(irq, NULL);
 	irq_set_handler_data(irq, NULL);
-	irq_free_hwirq(irq);
-
+	arch_free_ht_irq(irq);
 	kfree(cfg);
 }
 EXPORT_SYMBOL(ht_destroy_irq);

index 70a1dbbf2093..5caa51b7b95c 100644
@@ -15,6 +15,8 @@ void unmask_ht_irq(struct irq_data *data);
 
 /* The arch hook for getting things started */
 int arch_setup_ht_irq(unsigned int irq, struct pci_dev *dev);
+int arch_alloc_ht_irq(struct pci_dev *dev);
+void arch_free_ht_irq(int irq);
 
 /* For drivers of buggy hardware */
 typedef void (ht_irq_update_t)(struct pci_dev *dev, int irq,

index 6224d316c405..86d897bc15dd 100644
@@ -99,7 +99,7 @@ static inline bool setup_remapped_irq(int irq,
 }
 #endif /* CONFIG_IRQ_REMAP */
 
-#define dmar_alloc_hwirq()	irq_alloc_hwirq(-1)
-#define dmar_free_hwirq		irq_free_hwirq
+extern int dmar_alloc_hwirq(void);
+extern void dmar_free_hwirq(int irq);
 
 #endif /* __X86_IRQ_REMAPPING_H */

index 76cc2c902176..9be7d6d8a579 100644
@@ -223,6 +223,16 @@ int arch_setup_dmar_msi(unsigned int irq)
 				      "edge");
 	return 0;
 }
+
+int dmar_alloc_hwirq(void)
+{
+	return irq_domain_alloc_irqs(NULL, 1, NUMA_NO_NODE, NULL);
+}
+
+void dmar_free_hwirq(int irq)
+{
+	irq_domain_free_irqs(irq, 1);
+}
 #endif
 
 /*

index 390079ee1350..5617150fd8fb 100644
@@ -6,6 +6,7 @@
 #include <linux/msi.h>
 #include <linux/irq.h>
 #include <linux/pci.h>
+#include <linux/irqdomain.h>
 
 #include <asm/hw_irq.h>
 #include <asm/irq_remapping.h>

@@ -49,6 +50,18 @@ static void irq_remapping_disable_io_apic(void)
 		disconnect_bsp_APIC(0);
 }
 
+#ifndef CONFIG_GENERIC_IRQ_LEGACY_ALLOC_HWIRQ
+static unsigned int irq_alloc_hwirqs(int cnt, int node)
+{
+	return irq_domain_alloc_irqs(NULL, -1, cnt, node, NULL);
+}
+
+static void irq_free_hwirqs(unsigned int from, int cnt)
+{
+	irq_domain_free_irqs(from, cnt);
+}
+#endif
+
 static int do_setup_msi_irqs(struct pci_dev *dev, int nvec)
 {
 	int ret, sub_handle, nvec_pow2, index = 0;

@@ -104,7 +117,7 @@ static int do_setup_msix_irqs(struct pci_dev *dev, int nvec)
 
 	list_for_each_entry(msidesc, &dev->msi_list, list) {
 
-		irq = irq_alloc_hwirq(node);
+		irq = irq_alloc_hwirqs(1, node);
 		if (irq == 0)
 			return -1;
 

@@ -127,7 +140,7 @@ static int do_setup_msix_irqs(struct pci_dev *dev, int nvec)
 	return 0;
 
 error:
-	irq_free_hwirq(irq);
+	irq_free_hwirqs(irq, 1);
 	return ret;
 }
 

index eb7692c9ab93..bd7881c5a57a 100644
@@ -113,10 +113,47 @@ struct irq_2_irte {
 #ifdef	CONFIG_X86_LOCAL_APIC
 struct irq_data;
 struct irq_domain;
+struct pci_dev;
+struct msi_desc;
+
+enum irq_alloc_type {
+	X86_IRQ_ALLOC_TYPE_IOAPIC = 1,
+	X86_IRQ_ALLOC_TYPE_HPET,
+	X86_IRQ_ALLOC_TYPE_MSI,
+	X86_IRQ_ALLOC_TYPE_MSIX,
+};
 
 struct irq_alloc_info {
+	enum irq_alloc_type	type;
 	u32			flags;
 	const struct cpumask	*mask;	/* CPU mask for vector allocation */
+	union {
+		int		unused;
+#ifdef	CONFIG_HPET_TIMER
+		struct {
+			int		hpet_id;
+			int		hpet_index;
+			void		*hpet_data;
+		};
+#endif
+#ifdef	CONFIG_PCI_MSI
+		struct {
+			struct pci_dev	*msi_dev;
+			irq_hw_number_t	msi_hwirq;
+		};
+#endif
+#ifdef	CONFIG_X86_IO_APIC
+		struct {
+			int		ioapic_id;
+			int		ioapic_pin;
+			int		ioapic_node;
+			u32		ioapic_trigger : 1;
+			u32		ioapic_polarity : 1;
+			u32		ioapic_valid : 1;
+			struct IO_APIC_route_entry *ioapic_entry;
+		};
+#endif
+	};
 };
 
 enum {

index 86d897bc15dd..0cd6195cc375 100644
@@ -22,6 +22,8 @@
 #ifndef __X86_IRQ_REMAPPING_H
 #define __X86_IRQ_REMAPPING_H
 
+#include <linux/irqdomain.h>
+#include <asm/hw_irq.h>
 #include <asm/io_apic.h>
 
 struct IO_APIC_route_entry;

@@ -30,6 +32,7 @@ struct irq_chip;
 struct msi_msg;
 struct pci_dev;
 struct irq_cfg;
+struct irq_alloc_info;
 
 #ifdef CONFIG_IRQ_REMAP
 

@@ -56,6 +59,25 @@ extern bool setup_remapped_irq(int irq,
 
 void irq_remap_modify_chip_defaults(struct irq_chip *chip);
 
+extern struct irq_domain *
+irq_remapping_get_ir_irq_domain(struct irq_alloc_info *info);
+extern struct irq_domain *
+irq_remapping_get_irq_domain(struct irq_alloc_info *info);
+extern void irq_remapping_print_chip(struct irq_data *data, struct seq_file *p);
+
+/* Create PCI MSI/MSIx irqdomain, use @parent as the parent irqdomain. */
+static inline struct irq_domain *
+arch_create_msi_irq_domain(struct irq_domain *parent)
+{
+	return NULL;
+}
+
+/* Get parent irqdomain for interrupt remapping irqdomain */
+static inline struct irq_domain *arch_get_ir_parent_domain(void)
+{
+	return x86_vector_domain;
+}
+
 #else  /* CONFIG_IRQ_REMAP */
 
 static inline void set_irq_remapping_broken(void) { }

@@ -97,6 +119,20 @@ static inline bool setup_remapped_irq(int irq,
 {
 	return false;
 }
+
+static inline struct irq_domain *
+irq_remapping_get_ir_irq_domain(struct irq_alloc_info *info)
+{
+	return NULL;
+}
+
+static inline struct irq_domain *
+irq_remapping_get_irq_domain(struct irq_alloc_info *info)
+{
+	return NULL;
+}
+
+#define	irq_remapping_print_chip	NULL
 #endif /* CONFIG_IRQ_REMAP */
 
 extern int dmar_alloc_hwirq(void);

65 lines not on this page · raw message

index 7c70cc29ffe6..3e109b1ea688 100644
@@ -30,6 +30,8 @@ struct irq_data;
 struct cpumask;
 struct pci_dev;
 struct msi_msg;
+struct irq_domain;
+struct irq_alloc_info;
 
 extern int irq_remap_broken;
 extern int disable_sourceid_checking;

@@ -77,11 +79,19 @@ struct irq_remap_ops {
 
 	/* Setup interrupt remapping for an HPET MSI */
 	int (*alloc_hpet_msi)(unsigned int, unsigned int);
+
+	/* Get the irqdomain associated the IOMMU device */
+	struct irq_domain *(*get_ir_irq_domain)(struct irq_alloc_info *);
+
+	/* Get the MSI irqdomain associated with the IOMMU device */
+	struct irq_domain *(*get_irq_domain)(struct irq_alloc_info *);
 };
 
 extern struct irq_remap_ops intel_irq_remap_ops;
 extern struct irq_remap_ops amd_iommu_irq_ops;
 
+extern void ir_ack_apic_edge(struct irq_data *data);
+
 #else  /* CONFIG_IRQ_REMAP */
 
 #define irq_remapping_enabled 0

index 14de1ab223c8..d3adaf32b3ec 100644
@@ -82,10 +82,10 @@ static int get_irte(int irq, struct irte *entry)
 	return 0;
 }
 
-static int alloc_irte(struct intel_iommu *iommu, int irq, u16 count)
+static int alloc_irte(struct intel_iommu *iommu, int irq,
+		      struct irq_2_iommu *irq_iommu, u16 count)
 {
 	struct ir_table *table = iommu->ir_table;
-	struct irq_2_iommu *irq_iommu = irq_2_iommu(irq);
 	struct irq_cfg *cfg = irq_cfg(irq);
 	unsigned int mask = 0;
 	unsigned long flags;

@@ -173,9 +173,9 @@ static int set_irte_irq(int irq, struct intel_iommu *iommu, u16 index, u16 subha
 	return 0;
 }
 
-static int modify_irte(int irq, struct irte *irte_modified)
+static int modify_irte(struct irq_2_iommu *irq_iommu,
+		       struct irte *irte_modified)
 {
-	struct irq_2_iommu *irq_iommu = irq_2_iommu(irq);
 	struct intel_iommu *iommu;
 	unsigned long flags;
 	struct irte *irte;

@@ -242,7 +242,7 @@ static int clear_entries(struct irq_2_iommu *irq_iommu)
 		return 0;
 
 	iommu = irq_iommu->iommu;
-	index = irq_iommu->irte_index + irq_iommu->sub_handle;
+	index = irq_iommu->irte_index;
 
 	start = iommu->ir_table->base + index;
 	end = start + (1 << irq_iommu->irte_mask);

@@ -986,7 +986,7 @@ static int intel_setup_ioapic_entry(int irq,
 		pr_warn("No mapping iommu for ioapic %d\n", ioapic_id);
 		index = -ENODEV;
 	} else {
-		index = alloc_irte(iommu, irq, 1);
+		index = alloc_irte(iommu, irq, irq_2_iommu(irq), 1);
 		if (index < 0) {
 			pr_warn("Failed to allocate IRTE for ioapic %d\n",
 				ioapic_id);

@@ -1002,7 +1002,7 @@ static int intel_setup_ioapic_entry(int irq,
 	/* Set source-id of interrupt request */
 	set_ioapic_sid(&irte, ioapic_id);
 
-	modify_irte(irq, &irte);
+	modify_irte(irq_2_iommu(irq), &irte);
 
 	apic_printk(APIC_VERBOSE, KERN_DEBUG "IOAPIC[%d]: "
 		"Set IRTE entry (P:%d FPD:%d Dst_Mode:%d "

@@ -1089,7 +1089,7 @@ intel_ioapic_set_affinity(struct irq_data *data, const struct cpumask *mask,
 	 * Atomically updates the IRTE with the new destination, vector
 	 * and flushes the interrupt entry cache.
 	 */
-	modify_irte(irq, &irte);
+	modify_irte(irq_2_iommu(irq), &irte);
 
 	/*
 	 * After this point, all the interrupts will start arriving

@@ -1125,7 +1125,7 @@ static void intel_compose_msi_msg(struct pci_dev *pdev,
 	else
 		set_hpet_sid(&irte, hpet_id);
 
-	modify_irte(irq, &irte);
+	modify_irte(irq_2_iommu(irq), &irte);
 
 	msg->address_hi = MSI_ADDR_BASE_HI;
 	msg->data = sub_handle;

@@ -1152,7 +1152,7 @@ static int intel_msi_alloc_irq(struct pci_dev *dev, int irq, int nvec)
 		       "Unable to map PCI %s to iommu\n", pci_name(dev));
 		index = -ENOENT;
 	} else {
-		index = alloc_irte(iommu, irq, nvec);
+		index = alloc_irte(iommu, irq, irq_2_iommu(irq), nvec);
 		if (index < 0) {
 			printk(KERN_ERR
 			       "Unable to allocate %d IRTE for PCI %s\n",

@@ -1196,7 +1196,7 @@ static int intel_alloc_hpet_msi(unsigned int irq, unsigned int id)
 	down_read(&dmar_global_lock);
 	iommu = map_hpet_to_ir(id);
 	if (iommu) {
-		index = alloc_irte(iommu, irq, 1);
+		index = alloc_irte(iommu, irq, irq_2_iommu(irq), 1);
 		if (index >= 0)
 			ret = 0;
 	}

index d3adaf32b3ec..f2dbb0d54d17 100644
@@ -8,6 +8,7 @@
 #include <linux/irq.h>
 #include <linux/intel-iommu.h>
 #include <linux/acpi.h>
+#include <linux/irqdomain.h>
 #include <asm/io_apic.h>
 #include <asm/smp.h>
 #include <asm/cpu.h>

@@ -31,6 +32,14 @@ struct hpet_scope {
 	unsigned int devfn;
 };
 
+struct intel_ir_data {
+	struct irq_2_iommu			irq_2_iommu;
+	struct irte				irte_entry;
+	union {
+		struct msi_msg			msi_entry;
+	};
+};
+
 #define IR_X2APIC_MODE(mode) (mode ? (1 << 11) : 0)
 #define IRTE_DEST(dest) ((eim_mode) ? dest : dest << 8)
 

@@ -50,6 +59,7 @@ static struct hpet_scope ir_hpet[MAX_HPET_TBS];
  * the dmar_global_lock.
  */
 static DEFINE_RAW_SPINLOCK(irq_2_ir_lock);
+static struct irq_domain_ops intel_ir_domain_ops;
 
 static int __init parse_ioapics_under_ir(void);
 

@@ -263,7 +273,7 @@ static int free_irte(int irq)
 	unsigned long flags;
 	int rc;
 
-	if (!irq_iommu)
+	if (!irq_iommu || irq_iommu->iommu == NULL)
 		return -1;
 
 	raw_spin_lock_irqsave(&irq_2_ir_lock, flags);

@@ -488,7 +498,6 @@ static int intel_setup_irq_remapping(struct intel_iommu *iommu)
 
 	pages = alloc_pages_node(iommu->node, GFP_KERNEL | __GFP_ZERO,
 				 INTR_REMAP_PAGE_ORDER);
-
 	if (!pages) {
 		pr_err("IR%d: failed to allocate pages of order %d\n",
 		       iommu->seq_id, INTR_REMAP_PAGE_ORDER);

@@ -502,11 +511,23 @@ static int intel_setup_irq_remapping(struct intel_iommu *iommu)
 		goto out_free_pages;
 	}
 
+	iommu->ir_domain = irq_domain_add_hierarchy(arch_get_ir_parent_domain(),
+						    0, INTR_REMAP_TABLE_ENTRIES,
+						    NULL, &intel_ir_domain_ops,
+						    iommu);
+	if (!iommu->ir_domain) {
+		pr_err("IR%d: failed to allocate irqdomain\n", iommu->seq_id);
+		goto out_free_bitmap;
+	}
+	iommu->ir_msi_domain = arch_create_msi_irq_domain(iommu->ir_domain);
+
 	ir_table->base = page_address(pages);
 	ir_table->bitmap = bitmap;
 	iommu->ir_table = ir_table;
 	return 0;
 
+out_free_bitmap:
+	kfree(bitmap);
 out_free_pages:
 	__free_pages(pages, INTR_REMAP_PAGE_ORDER);
 out_free_table:

@@ -517,6 +538,14 @@ out_free_table:
 static void intel_teardown_irq_remapping(struct intel_iommu *iommu)
 {
 	if (iommu && iommu->ir_table) {
+		if (iommu->ir_msi_domain) {
+			irq_domain_remove(iommu->ir_msi_domain);
+			iommu->ir_msi_domain = NULL;
+		}
+		if (iommu->ir_domain) {
+			irq_domain_remove(iommu->ir_domain);
+			iommu->ir_domain = NULL;
+		}
 		free_pages((unsigned long)iommu->ir_table->base,
 			   INTR_REMAP_PAGE_ORDER);
 		kfree(iommu->ir_table->bitmap);

@@ -1062,12 +1091,6 @@ intel_ioapic_set_affinity(struct irq_data *data, const struct cpumask *mask,
 	struct irte irte;
 	int err;
 
-	if (!config_enabled(CONFIG_SMP))
-		return -EINVAL;
-
-	if (!cpumask_intersects(mask, cpu_online_mask))
-		return -EINVAL;
-
 	if (get_irte(irq, &irte))
 		return -EBUSY;
 

@@ -1100,6 +1123,7 @@ intel_ioapic_set_affinity(struct irq_data *data, const struct cpumask *mask,
 		send_cleanup_vector(cfg);
 
 	cpumask_copy(data->affinity, mask);
+
 	return 0;
 }
 

@@ -1205,6 +1229,53 @@ static int intel_alloc_hpet_msi(unsigned int irq, unsigned int id)
 	return ret;
 }
 
+static struct irq_domain *intel_get_ir_irq_domain(struct irq_alloc_info *info)
+{
+	struct intel_iommu *iommu = NULL;
+
+	if (!info)
+		return NULL;
+
+	switch (info->type) {
+	case X86_IRQ_ALLOC_TYPE_IOAPIC:
+		iommu = map_ioapic_to_ir(info->ioapic_id);
+		break;
+	case X86_IRQ_ALLOC_TYPE_HPET:
+		iommu = map_hpet_to_ir(info->hpet_id);
+		break;
+	case X86_IRQ_ALLOC_TYPE_MSI:
+	case X86_IRQ_ALLOC_TYPE_MSIX:
+		iommu = map_dev_to_ir(info->msi_dev);
+		break;
+	default:
+		BUG_ON(1);
+		break;
+	}
+
+	return iommu ? iommu->ir_domain : NULL;
+}
+
+static struct irq_domain *intel_get_irq_domain(struct irq_alloc_info *info)
+{
+	struct intel_iommu *iommu;
+
+	if (!info)
+		return NULL;
+
+	switch (info->type) {
+	case X86_IRQ_ALLOC_TYPE_MSI:
+	case X86_IRQ_ALLOC_TYPE_MSIX:
+		iommu = map_dev_to_ir(info->msi_dev);
+		if (iommu)
+			return iommu->ir_msi_domain;
+		break;
+	default:
+		break;
+	}
+
+	return NULL;
+}
+
 struct irq_remap_ops intel_irq_remap_ops = {
 	.prepare		= intel_prepare_irq_remapping,
 	.enable			= intel_enable_irq_remapping,

@@ -1218,6 +1289,256 @@ struct irq_remap_ops intel_irq_remap_ops = {
 	.msi_alloc_irq		= intel_msi_alloc_irq,
 	.msi_setup_irq		= intel_msi_setup_irq,
 	.alloc_hpet_msi		= intel_alloc_hpet_msi,
+	.get_ir_irq_domain	= intel_get_ir_irq_domain,
+	.get_irq_domain		= intel_get_irq_domain,
+};
+
+/*
+ * Migrate the IO-APIC irq in the presence of intr-remapping.
+ *
+ * For both level and edge triggered, irq migration is a simple atomic
+ * update(of vector and cpu destination) of IRTE and flush the hardware cache.
+ *
+ * For level triggered, we eliminate the io-apic RTE modification (with the
+ * updated vector information), by using a virtual vector (io-apic pin number).
+ * Real vector that is used for interrupting cpu will be coming from
+ * the interrupt-remapping table entry.
+ *
+ * As the migration is a simple atomic update of IRTE, the same mechanism
+ * is used to migrate MSI irq's in the presence of interrupt-remapping.
+ */
+static int
+intel_ir_set_affinity(struct irq_data *data, const struct cpumask *mask,
+		      bool force)
+{
+	struct intel_ir_data *ir_data = data->chip_data;
+	struct irte *irte = &ir_data->irte_entry;
+	struct irq_cfg *cfg = irqd_cfg(data);
+	struct irq_data *parent = data->parent_data;
+	int ret;
+
+	ret = parent->chip->irq_set_affinity(parent, mask, force);
+	if (ret < 0 || ret == IRQ_SET_MASK_OK_DONE)
+		return ret;
+
+	/*
+	 * Atomically updates the IRTE with the new destination, vector
+	 * and flushes the interrupt entry cache.
+	 */
+	irte->vector = cfg->vector;
+	irte->dest_id = IRTE_DEST(cfg->dest_apicid);
+	modify_irte(&ir_data->irq_2_iommu, irte);
+
+	/*
+	 * After this point, all the interrupts will start arriving
+	 * at the new destination. So, time to cleanup the previous
+	 * vector allocation.
+	 */
+	if (cfg->move_in_progress)
+		send_cleanup_vector(cfg);
+
+	return IRQ_SET_MASK_OK_DONE;
+}
+
+static void intel_ir_compose_msi_msg(struct irq_data *irq_data,
+				     struct msi_msg *msg)
+{
+	struct intel_ir_data *ir_data = irq_data->chip_data;
+
+	*msg = ir_data->msi_entry;
+}
+
+static struct irq_chip intel_ir_chip = {
+	.irq_ack = ir_ack_apic_edge,
+	.irq_set_affinity = intel_ir_set_affinity,
+	.irq_compose_msi_msg = intel_ir_compose_msi_msg,
+};
+
+static void intel_irq_remapping_prepare_irte(struct intel_ir_data *data,
+					     struct irq_cfg *irq_cfg,
+					     struct irq_alloc_info *info,
+					     int index, int sub_handle)
+{
+	struct IR_IO_APIC_route_entry *entry;
+	struct irte *irte = &data->irte_entry;
+	struct msi_msg *msg = &data->msi_entry;
+
+	prepare_irte(irte, irq_cfg->vector, irq_cfg->dest_apicid);
+	switch (info->type) {
+	case X86_IRQ_ALLOC_TYPE_IOAPIC:
+		/* Set source-id of interrupt request */
+		set_ioapic_sid(irte, info->ioapic_id);
+		apic_printk(APIC_VERBOSE, KERN_DEBUG "IOAPIC[%d]: Set IRTE entry (P:%d FPD:%d Dst_Mode:%d Redir_hint:%d Trig_Mode:%d Dlvry_Mode:%X Avail:%X Vector:%02X Dest:%08X SID:%04X SQ:%X SVT:%X)\n",
+			info->ioapic_id, irte->present, irte->fpd,
+			irte->dst_mode, irte->redir_hint,
+			irte->trigger_mode, irte->dlvry_mode,
+			irte->avail, irte->vector, irte->dest_id,
+			irte->sid, irte->sq, irte->svt);
+
+		entry = (struct IR_IO_APIC_route_entry *)info->ioapic_entry;
+		info->ioapic_entry = NULL;
+		memset(entry, 0, sizeof(*entry));
+		entry->index2	= (index >> 15) & 0x1;
+		entry->zero	= 0;
+		entry->format	= 1;
+		entry->index	= (index & 0x7fff);
+		/*
+		 * IO-APIC RTE will be configured with virtual vector.
+		 * irq handler will do the explicit EOI to the io-apic.
+		 */
+		entry->vector	= info->ioapic_pin;
+		entry->mask	= 0;			/* enable IRQ */
+		entry->trigger	= info->ioapic_trigger;
+		entry->polarity	= info->ioapic_polarity;
+		if (info->ioapic_trigger)
+			entry->mask = 1; /* Mask level triggered irqs. */
+		break;
+
+	case X86_IRQ_ALLOC_TYPE_HPET:
+	case X86_IRQ_ALLOC_TYPE_MSI:
+	case X86_IRQ_ALLOC_TYPE_MSIX:
+		if (info->type == X86_IRQ_ALLOC_TYPE_HPET)
+			set_hpet_sid(irte, info->hpet_id);
+		else
+			set_msi_sid(irte, info->msi_dev);
+
+		msg->address_hi = MSI_ADDR_BASE_HI;
+		msg->data = sub_handle;
+		msg->address_lo = MSI_ADDR_BASE_LO | MSI_ADDR_IR_EXT_INT |
+				  MSI_ADDR_IR_SHV |
+				  MSI_ADDR_IR_INDEX1(index) |
+				  MSI_ADDR_IR_INDEX2(index);
+		break;
+
+	default:
+		BUG_ON(1);
+		break;
+	}
+}
+
+static void intel_free_irq_resources(struct irq_domain *domain,
+				     unsigned int virq, unsigned int nr_irqs)
+{
+	struct irq_data *irq_data;
+	struct intel_ir_data *data;
+	struct irq_2_iommu *irq_iommu;
+	unsigned long flags;
+	int i;
+
+	for (i = 0; i < nr_irqs; i++) {
+		irq_data = irq_domain_get_irq_data(domain, virq  + i);
+		if (irq_data && irq_data->chip_data) {
+			data = irq_data->chip_data;
+			irq_iommu = &data->irq_2_iommu;
+			raw_spin_lock_irqsave(&irq_2_ir_lock, flags);
+			clear_entries(irq_iommu);
+			raw_spin_unlock_irqrestore(&irq_2_ir_lock, flags);
+			irq_domain_reset_irq_data(irq_data);
+			kfree(data);
+		}
+	}
+}
+
+static int intel_irq_remapping_alloc(struct irq_domain *domain,
+				     unsigned int virq, unsigned int nr_irqs,
+				     void *arg)
+{
+	struct intel_iommu *iommu = domain->host_data;
+	struct irq_alloc_info *info = arg;
+	struct intel_ir_data *data;
+	struct irq_data *irq_data;
+	struct irq_cfg *irq_cfg;
+	int i, ret, index;
+
+	if (!info || !iommu)
+		return -EINVAL;
+	if (nr_irqs > 1 && info->type != X86_IRQ_ALLOC_TYPE_MSI &&
+	    info->type != X86_IRQ_ALLOC_TYPE_MSIX)
+		return -EINVAL;
+
+	/*
+	 * With IRQ remapping enabled, don't need contigious CPU vectors
+	 * to support multiple MSI interrupts.
+	 */
+	if (info->type == X86_IRQ_ALLOC_TYPE_MSI)
+		info->flags &= ~X86_IRQ_ALLOC_CONTIGOUS_VECTORS;
+
+	ret = irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, arg);
+	if (ret < 0)
+		return ret;
+
+	ret = -ENOMEM;
+	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	if (!data)
+		goto out_free_parent;
+
+	down_read(&dmar_global_lock);
+	index = alloc_irte(iommu, virq, &data->irq_2_iommu, nr_irqs);
+	up_read(&dmar_global_lock);
+	if (index < 0) {
+		pr_warn("Failed to allocate IRTE\n");
+		kfree(data);
+		goto out_free_parent;
+	}
+
+	for (i = 0; i < nr_irqs; i++) {
+		irq_data = irq_domain_get_irq_data(domain, virq + i);
+		irq_cfg = irqd_cfg(irq_data);
+		if (!irq_data || !irq_cfg) {
+			ret = -EINVAL;
+			goto out_free_data;
+		}
+
+		if (i > 0) {
+			data = kzalloc(sizeof(*data), GFP_KERNEL);
+			if (!data)
+				goto out_free_data;
+		}
+		irq_data->hwirq = (index << 16) + i;
+		irq_data->chip_data = data;
+		irq_data->chip = &intel_ir_chip;
+		intel_irq_remapping_prepare_irte(data, irq_cfg, info, index, i);
+		irq_set_status_flags(virq + i, IRQ_MOVE_PCNTXT);
+	}
+	return 0;
+
+out_free_data:
+	intel_free_irq_resources(domain, virq, i);
+out_free_parent:
+	irq_domain_free_irqs_common(domain, virq, nr_irqs);
+	return ret;
+}
+
+static void intel_irq_remapping_free(struct irq_domain *domain,
+				     unsigned int virq, unsigned int nr_irqs)
+{
+	intel_free_irq_resources(domain, virq, nr_irqs);
+	irq_domain_free_irqs_common(domain, virq, nr_irqs);
+}
+
+static void intel_irq_remapping_activate(struct irq_domain *domain,
+					 struct irq_data *irq_data)
+{
+	struct intel_ir_data *data = irq_data->chip_data;
+
+	modify_irte(&data->irq_2_iommu, &data->irte_entry);
+}
+
+static void intel_irq_remapping_deactivate(struct irq_domain *domain,
+					   struct irq_data *irq_data)
+{
+	struct intel_ir_data *data = irq_data->chip_data;
+	struct irte entry;
+
+	memset(&entry, 0, sizeof(entry));
+	modify_irte(&data->irq_2_iommu, &entry);
+}
+
+static struct irq_domain_ops intel_ir_domain_ops = {
+	.alloc = intel_irq_remapping_alloc,
+	.free = intel_irq_remapping_free,
+	.activate = intel_irq_remapping_activate,
+	.deactivate = intel_irq_remapping_deactivate,
 };
 
 /*

index a65208a8fe18..ecaf3a937845 100644
@@ -286,6 +286,8 @@ struct q_inval {
 
 #define INTR_REMAP_TABLE_ENTRIES	65536
 
+struct irq_domain;
+
 struct ir_table {
 	struct irte *base;
 	unsigned long *bitmap;

@@ -335,6 +337,8 @@ struct intel_iommu {
 
 #ifdef CONFIG_IRQ_REMAP
 	struct ir_table *ir_table;	/* Interrupt remapping info */
+	struct irq_domain *ir_domain;
+	struct irq_domain *ir_msi_domain;
 #endif
 	struct device	*iommu_dev; /* IOMMU-sysfs device */
 	int		node;

index 48882c126245..db974bd348a1 100644
@@ -33,6 +33,7 @@
 #include <linux/export.h>
 #include <linux/irq.h>
 #include <linux/msi.h>
+#include <linux/irqdomain.h>
 #include <asm/irq_remapping.h>
 #include <asm/io_apic.h>
 #include <asm/apic.h>

@@ -3857,6 +3858,16 @@ union irte {
 	} fields;
 };
 
+struct amd_ir_data {
+	struct irq_2_irte			irq_2_irte;
+	union irte				irte_entry;
+	union {
+		struct msi_msg			msi_entry;
+	};
+};
+
+static struct irq_chip amd_ir_chip;
+
 #define DTE_IRQ_PHYS_ADDR_MASK	(((1ULL << 45)-1) << 6)
 #define DTE_IRQ_REMAP_INTCTL    (2ULL << 60)
 #define DTE_IRQ_TABLE_LEN       (8ULL << 1)

@@ -3950,7 +3961,8 @@ out_unlock:
 	return table;
 }
 
-static int alloc_irq_index(struct irq_cfg *cfg, u16 devid, int count)
+static int alloc_irq_index(struct irq_cfg *cfg, struct irq_2_irte *irte_info,
+			   u16 devid, int count)
 {
 	struct irq_remap_table *table;
 	unsigned long flags;

@@ -3972,15 +3984,12 @@ static int alloc_irq_index(struct irq_cfg *cfg, u16 devid, int count)
 			c = 0;
 
 		if (c == count)	{
-			struct irq_2_irte *irte_info;
-
 			for (; c != 0; --c)
 				table->table[index - c + 1] = IRTE_ALLOCATED;
 
 			index -= count - 1;
 
 			cfg->remapped	      = 1;
-			irte_info             = &cfg->irq_2_irte;
 			irte_info->devid      = devid;
 			irte_info->index      = index;
 

@@ -4225,7 +4234,7 @@ static int msi_alloc_irq(struct pci_dev *pdev, int irq, int nvec)
 		return -EINVAL;
 
 	devid = get_device_id(&pdev->dev);
-	index = alloc_irq_index(cfg, devid, nvec);
+	index = alloc_irq_index(cfg, &cfg->irq_2_irte, devid, nvec);
 
 	return index < 0 ? MAX_IRQS_PER_TABLE : index;
 }

@@ -4272,7 +4281,7 @@ static int alloc_hpet_msi(unsigned int irq, unsigned int id)
 	if (devid < 0)
 		return devid;
 
-	index = alloc_irq_index(cfg, devid, 1);
+	index = alloc_irq_index(cfg, &cfg->irq_2_irte, devid, 1);
 	if (index < 0)
 		return index;
 

@@ -4283,6 +4292,72 @@ static int alloc_hpet_msi(unsigned int irq, unsigned int id)
 	return 0;
 }
 
+static int get_devid(struct irq_alloc_info *info)
+{
+	int devid = -1;
+
+	switch (info->type) {
+	case X86_IRQ_ALLOC_TYPE_IOAPIC:
+		devid     = get_ioapic_devid(info->ioapic_id);
+		break;
+	case X86_IRQ_ALLOC_TYPE_HPET:
+		devid     = get_hpet_devid(info->hpet_id);
+		break;
+	case X86_IRQ_ALLOC_TYPE_MSI:
+	case X86_IRQ_ALLOC_TYPE_MSIX:
+		devid = get_device_id(&info->msi_dev->dev);
+		break;
+	default:
+		BUG_ON(1);
+		break;
+	}
+
+	return devid;
+}
+
+static struct irq_domain *get_ir_irq_domain(struct irq_alloc_info *info)
+{
+	int devid;
+	struct amd_iommu *iommu;
+
+	if (!info)
+		return NULL;
+
+	devid = get_devid(info);
+	if (devid >= 0) {
+		iommu = amd_iommu_rlookup_table[devid];
+		if (iommu)
+			return iommu->ir_domain;
+	}
+
+	return NULL;
+}
+
+static struct irq_domain *get_irq_domain(struct irq_alloc_info *info)
+{
+	int devid;
+	struct amd_iommu *iommu;
+
+	if (!info)
+		return NULL;
+
+	switch (info->type) {
+	case X86_IRQ_ALLOC_TYPE_MSI:
+	case X86_IRQ_ALLOC_TYPE_MSIX:
+		devid = get_device_id(&info->msi_dev->dev);
+		if (devid >= 0) {
+			iommu = amd_iommu_rlookup_table[devid];
+			if (iommu)
+				return iommu->msi_domain;
+		}
+		break;
+	default:
+		break;
+	}
+
+	return NULL;
+}
+
 struct irq_remap_ops amd_iommu_irq_ops = {
 	.prepare		= amd_iommu_prepare,
 	.enable			= amd_iommu_enable,

@@ -4296,5 +4371,247 @@ struct irq_remap_ops amd_iommu_irq_ops = {
 	.msi_alloc_irq		= msi_alloc_irq,
 	.msi_setup_irq		= msi_setup_irq,
 	.alloc_hpet_msi		= alloc_hpet_msi,
+	.get_ir_irq_domain	= get_ir_irq_domain,
+	.get_irq_domain		= get_irq_domain,
+};
+
+static void irq_remapping_prepare_irte(struct amd_ir_data *data,
+				       struct irq_cfg *irq_cfg,
+				       struct irq_alloc_info *info,
+				       int devid, int index, int sub_handle)
+{
+	union irte *irte = &data->irte_entry;
+	struct irq_2_irte *irte_info = &data->irq_2_irte;
+	struct msi_msg *msg = &data->msi_entry;
+	struct IO_APIC_route_entry *entry;
+
+	irq_cfg->remapped = 1;
+	data->irq_2_irte.devid = devid;
+	data->irq_2_irte.index = index + sub_handle;
+
+	/* Setup IRTE for IOMMU */
+	irte->val = 0;
+	irte->fields.vector      = irq_cfg->vector;
+	irte->fields.int_type    = apic->irq_delivery_mode;
+	irte->fields.destination = irq_cfg->dest_apicid;
+	irte->fields.dm          = apic->irq_dest_mode;
+	irte->fields.valid       = 1;
+
+	switch (info->type) {
+	case X86_IRQ_ALLOC_TYPE_IOAPIC:
+		/* Setup IOAPIC entry */
+		entry = info->ioapic_entry;
+		info->ioapic_entry = NULL;
+		memset(entry, 0, sizeof(*entry));
+		entry->vector        = index;
+		entry->mask          = 0;
+		entry->trigger       = info->ioapic_trigger;
+		entry->polarity      = info->ioapic_polarity;
+		/* Mask level triggered irqs. */
+		if (info->ioapic_trigger)
+			entry->mask = 1;
+		break;
+
+	case X86_IRQ_ALLOC_TYPE_HPET:
+	case X86_IRQ_ALLOC_TYPE_MSI:
+	case X86_IRQ_ALLOC_TYPE_MSIX:
+		msg->address_hi = MSI_ADDR_BASE_HI;
+		msg->address_lo = MSI_ADDR_BASE_LO;
+		msg->data = irte_info->index;
+		break;
+
+	default:
+		BUG_ON(1);
+		break;
+	}
+}
+
+static int irq_remapping_alloc(struct irq_domain *domain, unsigned int virq,
+			       unsigned int nr_irqs, void *arg)
+{
+	struct irq_alloc_info *info = arg;
+	struct amd_ir_data *data;
+	struct irq_data *irq_data;
+	struct irq_cfg *cfg;
+	int i, ret, devid;
+	int index = -1;
+
+	if (!info)
+		return -EINVAL;
+	if (nr_irqs > 1 && info->type != X86_IRQ_ALLOC_TYPE_MSI &&
+	    info->type != X86_IRQ_ALLOC_TYPE_MSIX)
+		return -EINVAL;
+
+	/*
+	 * With IRQ remapping enabled, don't need contigious CPU vectors
+	 * to support multiple MSI interrupts.
+	 */
+	if (info->type == X86_IRQ_ALLOC_TYPE_MSI)
+		info->flags &= ~X86_IRQ_ALLOC_CONTIGOUS_VECTORS;
+
+	devid = get_devid(info);
+	if (devid < 0)
+		return -EINVAL;
+
+	ret = irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, arg);
+	if (ret < 0)
+		return ret;
+
+	ret = -ENOMEM;
+	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	if (!data)
+		goto out_free_parent;
+
+	if (info->type == X86_IRQ_ALLOC_TYPE_IOAPIC) {
+		if (get_irq_table(devid, true))
+			index = info->ioapic_pin;
+		else
+			ret = -ENOMEM;
+	} else {
+		cfg = irq_cfg(virq);
+		index = alloc_irq_index(cfg, &data->irq_2_irte, devid, nr_irqs);
+	}
+	if (index < 0) {
+		pr_warn("Failed to allocate IRTE\n");
+		kfree(data);
+		goto out_free_parent;
+	}
+
+	for (i = 0; i < nr_irqs; i++) {
+		irq_data = irq_domain_get_irq_data(domain, virq + i);
+		cfg = irqd_cfg(irq_data);
+		if (!irq_data || !cfg) {
+			ret = -EINVAL;
+			goto out_free_data;
+		}
+
+		if (i > 0) {
+			data = kzalloc(sizeof(*data), GFP_KERNEL);
+			if (!data)
+				goto out_free_data;
+		}
+		irq_data->hwirq = (devid << 16) + i;
+		irq_data->chip_data = data;
+		irq_data->chip = &amd_ir_chip;
+		irq_remapping_prepare_irte(data, cfg, info, devid, index, i);
+		irq_set_status_flags(virq + i, IRQ_MOVE_PCNTXT);
+	}
+	return 0;
+
+out_free_data:
+	for (i--; i >= 0; i--) {
+		irq_data = irq_domain_get_irq_data(domain, virq + i);
+		if (irq_data)
+			kfree(irq_data->chip_data);
+	}
+	for (i = 0; i < nr_irqs; i++)
+		free_irte(devid, index + i);
+out_free_parent:
+	irq_domain_free_irqs_common(domain, virq, nr_irqs);
+	return ret;
+}
+
+static void irq_remapping_free(struct irq_domain *domain, unsigned int virq,
+			       unsigned int nr_irqs)
+{
+	struct irq_data *irq_data;
+	struct amd_ir_data *data;
+	struct irq_2_irte *irte_info;
+	int i;
+
+	for (i = 0; i < nr_irqs; i++) {
+		irq_data = irq_domain_get_irq_data(domain, virq  + i);
+		if (irq_data && irq_data->chip_data) {
+			data = irq_data->chip_data;
+			irte_info = &data->irq_2_irte;
+			free_irte(irte_info->devid, irte_info->index);
+			kfree(data);
+		}
+	}
+	irq_domain_free_irqs_common(domain, virq, nr_irqs);
+}
+
+static void irq_remapping_activate(struct irq_domain *domain,
+				   struct irq_data *irq_data)
+{
+	struct amd_ir_data *data = irq_data->chip_data;
+	struct irq_2_irte *irte_info = &data->irq_2_irte;
+
+	modify_irte(irte_info->devid, irte_info->index, data->irte_entry);
+}
+
+static void irq_remapping_deactivate(struct irq_domain *domain,
+				     struct irq_data *irq_data)
+{
+	struct amd_ir_data *data = irq_data->chip_data;
+	struct irq_2_irte *irte_info = &data->irq_2_irte;
+	union irte entry;
+
+	entry.val = 0;
+	modify_irte(irte_info->devid, irte_info->index, data->irte_entry);
+}
+
+static struct irq_domain_ops amd_ir_domain_ops = {
+	.alloc = irq_remapping_alloc,
+	.free = irq_remapping_free,
+	.activate = irq_remapping_activate,
+	.deactivate = irq_remapping_deactivate,
 };
+
+static int amd_ir_set_affinity(struct irq_data *data,
+			       const struct cpumask *mask, bool force)
+{
+	struct amd_ir_data *ir_data = data->chip_data;
+	struct irq_2_irte *irte_info = &ir_data->irq_2_irte;
+	struct irq_cfg *cfg = irqd_cfg(data);
+	struct irq_data *parent = data->parent_data;
+	int ret;
+
+	ret = parent->chip->irq_set_affinity(parent, mask, force);
+	if (ret < 0 || ret == IRQ_SET_MASK_OK_DONE)
+		return ret;
+
+	/*
+	 * Atomically updates the IRTE with the new destination, vector
+	 * and flushes the interrupt entry cache.
+	 */
+	ir_data->irte_entry.fields.vector = cfg->vector;
+	ir_data->irte_entry.fields.destination = cfg->dest_apicid;
+	modify_irte(irte_info->devid, irte_info->index, ir_data->irte_entry);
+
+	/*
+	 * After this point, all the interrupts will start arriving
+	 * at the new destination. So, time to cleanup the previous
+	 * vector allocation.
+	 */
+	if (cfg->move_in_progress)
+		send_cleanup_vector(cfg);
+
+	return IRQ_SET_MASK_OK_DONE;
+}
+
+static void ir_compose_msi_msg(struct irq_data *irq_data, struct msi_msg *msg)
+{
+	struct amd_ir_data *ir_data = irq_data->chip_data;
+
+	*msg = ir_data->msi_entry;
+}
+
+static struct irq_chip amd_ir_chip = {
+	.irq_ack = ir_ack_apic_edge,
+	.irq_set_affinity = amd_ir_set_affinity,
+	.irq_compose_msi_msg = ir_compose_msi_msg,
+};
+
+int amd_iommu_create_irq_domain(struct amd_iommu *iommu)
+{
+	iommu->ir_domain = irq_domain_add_tree(NULL, &amd_ir_domain_ops, iommu);
+	if (!iommu->ir_domain)
+		return -ENOMEM;
+
+	iommu->ir_domain->parent = arch_get_ir_parent_domain();
+	iommu->msi_domain = arch_create_msi_irq_domain(iommu->ir_domain);
+
+	return 0;
+}
 #endif

index 450ef5001a65..c17df04d7a7f 100644
@@ -1124,6 +1124,10 @@ static int __init init_iommu_one(struct amd_iommu *iommu, struct ivhd_header *h)
 	if (ret)
 		return ret;
 
+	ret = amd_iommu_create_irq_domain(iommu);
+	if (ret)
+		return ret;
+
 	/*
 	 * Make sure IOMMU is not considered to translate itself. The IVRS
 	 * table tells us so, but this is a lie!

index 72b0fd455e24..0a21142d3639 100644
@@ -62,6 +62,15 @@ extern u8 amd_iommu_pc_get_max_counters(u16 devid);
 extern int amd_iommu_pc_get_set_reg_val(u16 devid, u8 bank, u8 cntr, u8 fxn,
 				    u64 *value, bool is_write);
 
+#ifdef CONFIG_IRQ_REMAP
+extern int amd_iommu_create_irq_domain(struct amd_iommu *iommu);
+#else
+static inline int amd_iommu_create_irq_domain(struct amd_iommu *iommu)
+{
+	return 0;
+}
+#endif
+
 #define PPR_SUCCESS			0x0
 #define PPR_INVALID			0x1
 #define PPR_FAILURE			0xf

index c4fffb710c58..e2972a38c1ea 100644
@@ -392,6 +392,7 @@ struct amd_iommu_fault {
 
 
 struct iommu_domain;
+struct irq_domain;
 
 /*
  * This structure contains generic data for  IOMMU protection domains

@@ -574,6 +575,10 @@ struct amd_iommu {
 	/* The maximum PC banks and counters/bank (PCSup=1) */
 	u8 max_banks;
 	u8 max_counters;
+#ifdef CONFIG_IRQ_REMAP
+	struct irq_domain *ir_domain;
+	struct irq_domain *msi_domain;
+#endif
 };
 
 struct devid_map {