Merge tag 'x86-irq-2020-10-12' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 irq updates from Thomas Gleixner:
 "Surgery of the MSI interrupt handling to prepare the support of
  upcoming devices which require non-PCI based MSI handling:

   - Cleanup historical leftovers all over the place

   - Rework the code to utilize more core functionality

   - Wrap XEN PCI/MSI interrupts into an irqdomain to make irqdomain
     assignment to PCI devices possible.

   - Assign irqdomains to PCI devices at initialization time which
     allows to utilize the full functionality of hierarchical
     irqdomains.

   - Remove arch_.*_msi_irq() functions from X86 and utilize the
     irqdomain which is assigned to the device for interrupt management.

   - Make the arch_.*_msi_irq() support conditional on a config switch
     and let the last few users select it"

* tag 'x86-irq-2020-10-12' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (40 commits)
  PCI: MSI: Fix Kconfig dependencies for PCI_MSI_ARCH_FALLBACKS
  x86/apic/msi: Unbreak DMAR and HPET MSI
  iommu/amd: Remove domain search for PCI/MSI
  iommu/vt-d: Remove domain search for PCI/MSI[X]
  x86/irq: Make most MSI ops XEN private
  x86/irq: Cleanup the arch_*_msi_irqs() leftovers
  PCI/MSI: Make arch_.*_msi_irq[s] fallbacks selectable
  x86/pci: Set default irq domain in pcibios_add_device()
  iommm/amd: Store irq domain in struct device
  iommm/vt-d: Store irq domain in struct device
  x86/xen: Wrap XEN MSI management into irqdomain
  irqdomain/msi: Allow to override msi_domain_alloc/free_irqs()
  x86/xen: Consolidate XEN-MSI init
  x86/xen: Rework MSI teardown
  x86/xen: Make xen_msi_init() static and rename it to xen_hvm_msi_init()
  PCI/MSI: Provide pci_dev_has_special_msi_domain() helper
  PCI_vmd_Mark_VMD_irqdomain_with_DOMAIN_BUS_VMD_MSI
  irqdomain/msi: Provide DOMAIN_BUS_VMD_MSI
  x86/irq: Initialize PCI/MSI domain at PCI init time
  x86/pci: Reducde #ifdeffery in PCI init code
  ...

22 files changed, 300 insertions, 307 deletions

diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index 2cc44e957c31..1c129abb7f09 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -519,6 +519,14 @@ static inline bool apic_id_is_primary_thread(unsigned int id) { return false; }
 static inline void apic_smt_update(void) { }
 #endif
 
+struct msi_msg;
+
+#ifdef CONFIG_PCI_MSI
+void x86_vector_msi_compose_msg(struct irq_data *data, struct msi_msg *msg);
+#else
+# define x86_vector_msi_compose_msg NULL
+#endif
+
 extern void ioapic_zap_locks(void);
 
 #endif /* _ASM_X86_APIC_H */
diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h
index 74c12437401e..a4aeeaace040 100644
--- a/arch/x86/include/asm/hw_irq.h
+++ b/arch/x86/include/asm/hw_irq.h
@@ -36,61 +36,56 @@ 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,
+	X86_IRQ_ALLOC_TYPE_PCI_MSI,
+	X86_IRQ_ALLOC_TYPE_PCI_MSIX,
 	X86_IRQ_ALLOC_TYPE_DMAR,
 	X86_IRQ_ALLOC_TYPE_UV,
+	X86_IRQ_ALLOC_TYPE_IOAPIC_GET_PARENT,
+	X86_IRQ_ALLOC_TYPE_HPET_GET_PARENT,
 };
 
+struct ioapic_alloc_info {
+	int				pin;
+	int				node;
+	u32				trigger : 1;
+	u32				polarity : 1;
+	u32				valid : 1;
+	struct IO_APIC_route_entry	*entry;
+};
+
+struct uv_alloc_info {
+	int		limit;
+	int		blade;
+	unsigned long	offset;
+	char		*name;
+
+};
+
+/**
+ * irq_alloc_info - X86 specific interrupt allocation info
+ * @type:	X86 specific allocation type
+ * @flags:	Flags for allocation tweaks
+ * @devid:	Device ID for allocations
+ * @hwirq:	Associated hw interrupt number in the domain
+ * @mask:	CPU mask for vector allocation
+ * @desc:	Pointer to msi descriptor
+ * @data:	Allocation specific data
+ *
+ * @ioapic:	IOAPIC specific allocation data
+ * @uv:		UV specific allocation data
+*/
 struct irq_alloc_info {
 	enum irq_alloc_type	type;
 	u32			flags;
-	const struct cpumask	*mask;	/* CPU mask for vector allocation */
+	u32			devid;
+	irq_hw_number_t		hwirq;
+	const struct cpumask	*mask;
+	struct msi_desc		*desc;
+	void			*data;
+
 	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
-#ifdef	CONFIG_DMAR_TABLE
-		struct {
-			int		dmar_id;
-			void		*dmar_data;
-		};
-#endif
-#ifdef	CONFIG_X86_UV
-		struct {
-			int		uv_limit;
-			int		uv_blade;
-			unsigned long	uv_offset;
-			char		*uv_name;
-		};
-#endif
-#if IS_ENABLED(CONFIG_VMD)
-		struct {
-			struct msi_desc *desc;
-		};
-#endif
+		struct ioapic_alloc_info	ioapic;
+		struct uv_alloc_info		uv;
 	};
 };
 
diff --git a/arch/x86/include/asm/irq_remapping.h b/arch/x86/include/asm/irq_remapping.h
index 4bc985f1e2e4..af4a151d70b3 100644
--- a/arch/x86/include/asm/irq_remapping.h
+++ b/arch/x86/include/asm/irq_remapping.h
@@ -45,8 +45,6 @@ extern int irq_remap_enable_fault_handling(void);
 extern void panic_if_irq_remap(const char *msg);
 
 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);
 
 /* Create PCI MSI/MSIx irqdomain, use @parent as the parent irqdomain. */
@@ -74,12 +72,6 @@ static inline void panic_if_irq_remap(const char *msg)
 }
 
 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;
diff --git a/arch/x86/include/asm/irqdomain.h b/arch/x86/include/asm/irqdomain.h
index c066ffae222b..cd684d45cb5f 100644
--- a/arch/x86/include/asm/irqdomain.h
+++ b/arch/x86/include/asm/irqdomain.h
@@ -51,9 +51,13 @@ extern int mp_irqdomain_ioapic_idx(struct irq_domain *domain);
 #endif /* CONFIG_X86_IO_APIC */
 
 #ifdef CONFIG_PCI_MSI
-extern void arch_init_msi_domain(struct irq_domain *domain);
+void x86_create_pci_msi_domain(void);
+struct irq_domain *native_create_pci_msi_domain(void);
+extern struct irq_domain *x86_pci_msi_default_domain;
 #else
-static inline void arch_init_msi_domain(struct irq_domain *domain) { }
+static inline void x86_create_pci_msi_domain(void) { }
+#define native_create_pci_msi_domain	NULL
+#define x86_pci_msi_default_domain	NULL
 #endif
 
 #endif
diff --git a/arch/x86/include/asm/mpspec.h b/arch/x86/include/asm/mpspec.h
index 606cbaebd336..e90ac7e9ae2c 100644
--- a/arch/x86/include/asm/mpspec.h
+++ b/arch/x86/include/asm/mpspec.h
@@ -67,21 +67,11 @@ static inline void find_smp_config(void)
 #ifdef CONFIG_X86_MPPARSE
 extern void e820__memblock_alloc_reserved_mpc_new(void);
 extern int enable_update_mptable;
-extern int default_mpc_apic_id(struct mpc_cpu *m);
-extern void default_smp_read_mpc_oem(struct mpc_table *mpc);
-# ifdef CONFIG_X86_IO_APIC
-extern void default_mpc_oem_bus_info(struct mpc_bus *m, char *str);
-# else
-#  define default_mpc_oem_bus_info NULL
-# endif
 extern void default_find_smp_config(void);
 extern void default_get_smp_config(unsigned int early);
 #else
 static inline void e820__memblock_alloc_reserved_mpc_new(void) { }
 #define enable_update_mptable 0
-#define default_mpc_apic_id NULL
-#define default_smp_read_mpc_oem NULL
-#define default_mpc_oem_bus_info NULL
 #define default_find_smp_config x86_init_noop
 #define default_get_smp_config x86_init_uint_noop
 #endif
diff --git a/arch/x86/include/asm/msi.h b/arch/x86/include/asm/msi.h
index 25ddd0916bb2..cd30013d15d3 100644
--- a/arch/x86/include/asm/msi.h
+++ b/arch/x86/include/asm/msi.h
@@ -9,6 +9,4 @@ typedef struct irq_alloc_info msi_alloc_info_t;
 int pci_msi_prepare(struct irq_domain *domain, struct device *dev, int nvec,
 		    msi_alloc_info_t *arg);
 
-void pci_msi_set_desc(msi_alloc_info_t *arg, struct msi_desc *desc);
-
 #endif /* _ASM_X86_MSI_H */
diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h
index 7ccb338507e3..d2c76c8d8cfd 100644
--- a/arch/x86/include/asm/pci.h
+++ b/arch/x86/include/asm/pci.h
@@ -105,17 +105,6 @@ static inline void early_quirks(void) { }
 
 extern void pci_iommu_alloc(void);
 
-#ifdef CONFIG_PCI_MSI
-/* implemented in arch/x86/kernel/apic/io_apic. */
-struct msi_desc;
-int native_setup_msi_irqs(struct pci_dev *dev, int nvec, int type);
-void native_teardown_msi_irq(unsigned int irq);
-void native_restore_msi_irqs(struct pci_dev *dev);
-#else
-#define native_setup_msi_irqs		NULL
-#define native_teardown_msi_irq		NULL
-#endif
-
 /* generic pci stuff */
 #include <asm-generic/pci.h>
 
diff --git a/arch/x86/include/asm/pci_x86.h b/arch/x86/include/asm/pci_x86.h
index 73bb404f4d2a..490411dba438 100644
--- a/arch/x86/include/asm/pci_x86.h
+++ b/arch/x86/include/asm/pci_x86.h
@@ -114,9 +114,20 @@ extern const struct pci_raw_ops pci_direct_conf1;
 extern bool port_cf9_safe;
 
 /* arch_initcall level */
+#ifdef CONFIG_PCI_DIRECT
 extern int pci_direct_probe(void);
 extern void pci_direct_init(int type);
+#else
+static inline int pci_direct_probe(void) { return -1; }
+static inline  void pci_direct_init(int type) { }
+#endif
+
+#ifdef CONFIG_PCI_BIOS
 extern void pci_pcbios_init(void);
+#else
+static inline void pci_pcbios_init(void) { }
+#endif
+
 extern void __init dmi_check_pciprobe(void);
 extern void __init dmi_check_skip_isa_align(void);
 
diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h
index 6807153c0410..397196fae24d 100644
--- a/arch/x86/include/asm/x86_init.h
+++ b/arch/x86/include/asm/x86_init.h
@@ -8,25 +8,16 @@ struct mpc_bus;
 struct mpc_cpu;
 struct mpc_table;
 struct cpuinfo_x86;
+struct irq_domain;
 
 /**
  * struct x86_init_mpparse - platform specific mpparse ops
- * @mpc_record:			platform specific mpc record accounting
  * @setup_ioapic_ids:		platform specific ioapic id override
- * @mpc_apic_id:		platform specific mpc apic id assignment
- * @smp_read_mpc_oem:		platform specific oem mpc table setup
- * @mpc_oem_pci_bus:		platform specific pci bus setup (default NULL)
- * @mpc_oem_bus_info:		platform specific mpc bus info
  * @find_smp_config:		find the smp configuration
  * @get_smp_config:		get the smp configuration
  */
 struct x86_init_mpparse {
-	void (*mpc_record)(unsigned int mode);
 	void (*setup_ioapic_ids)(void);
-	int (*mpc_apic_id)(struct mpc_cpu *m);
-	void (*smp_read_mpc_oem)(struct mpc_table *mpc);
-	void (*mpc_oem_pci_bus)(struct mpc_bus *m);
-	void (*mpc_oem_bus_info)(struct mpc_bus *m, char *name);
 	void (*find_smp_config)(void);
 	void (*get_smp_config)(unsigned int early);
 };
@@ -52,12 +43,14 @@ struct x86_init_resources {
  * @intr_init:			interrupt init code
  * @intr_mode_select:		interrupt delivery mode selection
  * @intr_mode_init:		interrupt delivery mode setup
+ * @create_pci_msi_domain:	Create the PCI/MSI interrupt domain
  */
 struct x86_init_irqs {
 	void (*pre_vector_init)(void);
 	void (*intr_init)(void);
 	void (*intr_mode_select)(void);
 	void (*intr_mode_init)(void);
+	struct irq_domain *(*create_pci_msi_domain)(void);
 };
 
 /**
@@ -283,9 +276,6 @@ struct x86_platform_ops {
 struct pci_dev;
 
 struct x86_msi_ops {
-	int (*setup_msi_irqs)(struct pci_dev *dev, int nvec, int type);
-	void (*teardown_msi_irq)(unsigned int irq);
-	void (*teardown_msi_irqs)(struct pci_dev *dev);
 	void (*restore_msi_irqs)(struct pci_dev *dev);
 };
 
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 5f943b938167..b3eef1d5c903 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -1429,6 +1429,9 @@ void __init apic_intr_mode_init(void)
 		break;
 	}
 
+	if (x86_platform.apic_post_init)
+		x86_platform.apic_post_init();
+
 	apic_bsp_setup(upmode);
 }
 
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 21f9c7f11779..7b3c7e0d4a09 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -860,10 +860,10 @@ void ioapic_set_alloc_attr(struct irq_alloc_info *info, int node,
 {
 	init_irq_alloc_info(info, NULL);
 	info->type = X86_IRQ_ALLOC_TYPE_IOAPIC;
-	info->ioapic_node = node;
-	info->ioapic_trigger = trigger;
-	info->ioapic_polarity = polarity;
-	info->ioapic_valid = 1;
+	info->ioapic.node = node;
+	info->ioapic.trigger = trigger;
+	info->ioapic.polarity = polarity;
+	info->ioapic.valid = 1;
 }
 
 #ifndef CONFIG_ACPI
@@ -878,32 +878,32 @@ static void ioapic_copy_alloc_attr(struct irq_alloc_info *dst,
 
 	copy_irq_alloc_info(dst, src);
 	dst->type = X86_IRQ_ALLOC_TYPE_IOAPIC;
-	dst->ioapic_id = mpc_ioapic_id(ioapic_idx);
-	dst->ioapic_pin = pin;
-	dst->ioapic_valid = 1;
-	if (src && src->ioapic_valid) {
-		dst->ioapic_node = src->ioapic_node;
-		dst->ioapic_trigger = src->ioapic_trigger;
-		dst->ioapic_polarity = src->ioapic_polarity;
+	dst->devid = mpc_ioapic_id(ioapic_idx);
+	dst->ioapic.pin = pin;
+	dst->ioapic.valid = 1;
+	if (src && src->ioapic.valid) {
+		dst->ioapic.node = src->ioapic.node;
+		dst->ioapic.trigger = src->ioapic.trigger;
+		dst->ioapic.polarity = src->ioapic.polarity;
 	} else {
-		dst->ioapic_node = NUMA_NO_NODE;
+		dst->ioapic.node = NUMA_NO_NODE;
 		if (acpi_get_override_irq(gsi, &trigger, &polarity) >= 0) {
-			dst->ioapic_trigger = trigger;
-			dst->ioapic_polarity = polarity;
+			dst->ioapic.trigger = trigger;
+			dst->ioapic.polarity = polarity;
 		} else {
 			/*
 			 * PCI interrupts are always active low level
 			 * triggered.
 			 */
-			dst->ioapic_trigger = IOAPIC_LEVEL;
-			dst->ioapic_polarity = IOAPIC_POL_LOW;
+			dst->ioapic.trigger = IOAPIC_LEVEL;
+			dst->ioapic.polarity = IOAPIC_POL_LOW;
 		}
 	}
 }
 
 static int ioapic_alloc_attr_node(struct irq_alloc_info *info)
 {
-	return (info && info->ioapic_valid) ? info->ioapic_node : NUMA_NO_NODE;
+	return (info && info->ioapic.valid) ? info->ioapic.node : NUMA_NO_NODE;
 }
 
 static void mp_register_handler(unsigned int irq, unsigned long trigger)
@@ -933,14 +933,14 @@ static bool mp_check_pin_attr(int irq, struct irq_alloc_info *info)
 	 * pin with real trigger and polarity attributes.
 	 */
 	if (irq < nr_legacy_irqs() && data->count == 1) {
-		if (info->ioapic_trigger != data->trigger)
-			mp_register_handler(irq, info->ioapic_trigger);
-		data->entry.trigger = data->trigger = info->ioapic_trigger;
-		data->entry.polarity = data->polarity = info->ioapic_polarity;
+		if (info->ioapic.trigger != data->trigger)
+			mp_register_handler(irq, info->ioapic.trigger);
+		data->entry.trigger = data->trigger = info->ioapic.trigger;
+		data->entry.polarity = data->polarity = info->ioapic.polarity;
 	}
 
-	return data->trigger == info->ioapic_trigger &&
-	       data->polarity == info->ioapic_polarity;
+	return data->trigger == info->ioapic.trigger &&
+	       data->polarity == info->ioapic.polarity;
 }
 
 static int alloc_irq_from_domain(struct irq_domain *domain, int ioapic, u32 gsi,
@@ -1002,7 +1002,7 @@ static int alloc_isa_irq_from_domain(struct irq_domain *domain,
 		if (!mp_check_pin_attr(irq, info))
 			return -EBUSY;
 		if (__add_pin_to_irq_node(irq_data->chip_data, node, ioapic,
-					  info->ioapic_pin))
+					  info->ioapic.pin))
 			return -ENOMEM;
 	} else {
 		info->flags |= X86_IRQ_ALLOC_LEGACY;
@@ -2092,8 +2092,8 @@ static int mp_alloc_timer_irq(int ioapic, int pin)
 		struct irq_alloc_info info;
 
 		ioapic_set_alloc_attr(&info, NUMA_NO_NODE, 0, 0);
-		info.ioapic_id = mpc_ioapic_id(ioapic);
-		info.ioapic_pin = pin;
+		info.devid = mpc_ioapic_id(ioapic);
+		info.ioapic.pin = pin;
 		mutex_lock(&ioapic_mutex);
 		irq = alloc_isa_irq_from_domain(domain, 0, ioapic, pin, &info);
 		mutex_unlock(&ioapic_mutex);
@@ -2297,9 +2297,9 @@ static int mp_irqdomain_create(int ioapic)
 		return 0;
 
 	init_irq_alloc_info(&info, NULL);
-	info.type = X86_IRQ_ALLOC_TYPE_IOAPIC;
-	info.ioapic_id = mpc_ioapic_id(ioapic);
-	parent = irq_remapping_get_ir_irq_domain(&info);
+	info.type = X86_IRQ_ALLOC_TYPE_IOAPIC_GET_PARENT;
+	info.devid = mpc_ioapic_id(ioapic);
+	parent = irq_remapping_get_irq_domain(&info);
 	if (!parent)
 		parent = x86_vector_domain;
 	else
@@ -2933,9 +2933,9 @@ int mp_ioapic_registered(u32 gsi_base)
 static void mp_irqdomain_get_attr(u32 gsi, struct mp_chip_data *data,
 				  struct irq_alloc_info *info)
 {
-	if (info && info->ioapic_valid) {
-		data->trigger = info->ioapic_trigger;
-		data->polarity = info->ioapic_polarity;
+	if (info && info->ioapic.valid) {
+		data->trigger = info->ioapic.trigger;
+		data->polarity = info->ioapic.polarity;
 	} else if (acpi_get_override_irq(gsi, &data->trigger,
 					 &data->polarity) < 0) {
 		/* PCI interrupts are always active low level triggered. */
@@ -2981,7 +2981,7 @@ int mp_irqdomain_alloc(struct irq_domain *domain, unsigned int virq,
 		return -EINVAL;
 
 	ioapic = mp_irqdomain_ioapic_idx(domain);
-	pin = info->ioapic_pin;
+	pin = info->ioapic.pin;
 	if (irq_find_mapping(domain, (irq_hw_number_t)pin) > 0)
 		return -EEXIST;
 
@@ -2989,7 +2989,7 @@ int mp_irqdomain_alloc(struct irq_domain *domain, unsigned int virq,
 	if (!data)
 		return -ENOMEM;
 
-	info->ioapic_entry = &data->entry;
+	info->ioapic.entry = &data->entry;
 	ret = irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, info);
 	if (ret < 0) {
 		kfree(data);
@@ -2997,7 +2997,7 @@ int mp_irqdomain_alloc(struct irq_domain *domain, unsigned int virq,
 	}
 
 	INIT_LIST_HEAD(&data->irq_2_pin);
-	irq_data->hwirq = info->ioapic_pin;
+	irq_data->hwirq = info->ioapic.pin;
 	irq_data->chip = (domain->parent == x86_vector_domain) ?
 			  &ioapic_chip : &ioapic_ir_chip;
 	irq_data->chip_data = data;
@@ -3007,8 +3007,8 @@ int mp_irqdomain_alloc(struct irq_domain *domain, unsigned int virq,
 	add_pin_to_irq_node(data, ioapic_alloc_attr_node(info), ioapic, pin);
 
 	local_irq_save(flags);
-	if (info->ioapic_entry)
-		mp_setup_entry(cfg, data, info->ioapic_entry);
+	if (info->ioapic.entry)
+		mp_setup_entry(cfg, data, info->ioapic.entry);
 	mp_register_handler(virq, data->trigger);
 	if (virq < nr_legacy_irqs())
 		legacy_pic->mask(virq);
diff --git a/arch/x86/kernel/apic/msi.c b/arch/x86/kernel/apic/msi.c
index c2b2911feeef..6313f0a05db7 100644
--- a/arch/x86/kernel/apic/msi.c
+++ b/arch/x86/kernel/apic/msi.c
@@ -21,7 +21,7 @@
 #include <asm/apic.h>
 #include <asm/irq_remapping.h>
 
-static struct irq_domain *msi_default_domain;
+struct irq_domain *x86_pci_msi_default_domain __ro_after_init;
 
 static void __irq_msi_compose_msg(struct irq_cfg *cfg, struct msi_msg *msg)
 {
@@ -45,7 +45,7 @@ static void __irq_msi_compose_msg(struct irq_cfg *cfg, struct msi_msg *msg)
 		MSI_DATA_VECTOR(cfg->vector);
 }
 
-static void irq_msi_compose_msg(struct irq_data *data, struct msi_msg *msg)
+void x86_vector_msi_compose_msg(struct irq_data *data, struct msi_msg *msg)
 {
 	__irq_msi_compose_msg(irqd_cfg(data), msg);
 }
@@ -177,40 +177,10 @@ static struct irq_chip pci_msi_controller = {
 	.irq_mask		= pci_msi_mask_irq,
 	.irq_ack		= irq_chip_ack_parent,
 	.irq_retrigger		= irq_chip_retrigger_hierarchy,
-	.irq_compose_msi_msg	= irq_msi_compose_msg,
 	.irq_set_affinity	= msi_set_affinity,
 	.flags			= IRQCHIP_SKIP_SET_WAKE,
 };
 
-int native_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
-{
-	struct irq_domain *domain;
-	struct irq_alloc_info info;
-
-	init_irq_alloc_info(&info, NULL);
-	info.type = X86_IRQ_ALLOC_TYPE_MSI;
-	info.msi_dev = dev;
-
-	domain = irq_remapping_get_irq_domain(&info);
-	if (domain == NULL)
-		domain = msi_default_domain;
-	if (domain == NULL)
-		return -ENOSYS;
-
-	return msi_domain_alloc_irqs(domain, &dev->dev, nvec);
-}
-
-void native_teardown_msi_irq(unsigned int irq)
-{
-	irq_domain_free_irqs(irq, 1);
-}
-
-static irq_hw_number_t pci_msi_get_hwirq(struct msi_domain_info *info,
-					 msi_alloc_info_t *arg)
-{
-	return arg->msi_hwirq;
-}
-
 int pci_msi_prepare(struct irq_domain *domain, struct device *dev, int nvec,
 		    msi_alloc_info_t *arg)
 {
@@ -218,11 +188,10 @@ int pci_msi_prepare(struct irq_domain *domain, struct device *dev, int nvec,
 	struct msi_desc *desc = first_pci_msi_entry(pdev);
 
 	init_irq_alloc_info(arg, NULL);
-	arg->msi_dev = pdev;
 	if (desc->msi_attrib.is_msix) {
-		arg->type = X86_IRQ_ALLOC_TYPE_MSIX;
+		arg->type = X86_IRQ_ALLOC_TYPE_PCI_MSIX;
 	} else {
-		arg->type = X86_IRQ_ALLOC_TYPE_MSI;
+		arg->type = X86_IRQ_ALLOC_TYPE_PCI_MSI;
 		arg->flags |= X86_IRQ_ALLOC_CONTIGUOUS_VECTORS;
 	}
 
@@ -230,16 +199,8 @@ int pci_msi_prepare(struct irq_domain *domain, struct device *dev, int nvec,
 }
 EXPORT_SYMBOL_GPL(pci_msi_prepare);
 
-void pci_msi_set_desc(msi_alloc_info_t *arg, struct msi_desc *desc)
-{
-	arg->msi_hwirq = pci_msi_domain_calc_hwirq(arg->msi_dev, desc);
-}
-EXPORT_SYMBOL_GPL(pci_msi_set_desc);
-
 static struct msi_domain_ops pci_msi_domain_ops = {
-	.get_hwirq	= pci_msi_get_hwirq,
 	.msi_prepare	= pci_msi_prepare,
-	.set_desc	= pci_msi_set_desc,
 };
 
 static struct msi_domain_info pci_msi_domain_info = {
@@ -251,25 +212,32 @@ static struct msi_domain_info pci_msi_domain_info = {
 	.handler_name	= "edge",
 };
 
-void __init arch_init_msi_domain(struct irq_domain *parent)
+struct irq_domain * __init native_create_pci_msi_domain(void)
 {
 	struct fwnode_handle *fn;
+	struct irq_domain *d;
 
 	if (disable_apic)
-		return;
+		return NULL;
 
 	fn = irq_domain_alloc_named_fwnode("PCI-MSI");
-	if (fn) {
-		msi_default_domain =
-			pci_msi_create_irq_domain(fn, &pci_msi_domain_info,
-						  parent);
-	}
-	if (!msi_default_domain) {
+	if (!fn)
+		return NULL;
+
+	d = pci_msi_create_irq_domain(fn, &pci_msi_domain_info,
+				      x86_vector_domain);
+	if (!d) {
 		irq_domain_free_fwnode(fn);
-		pr_warn("failed to initialize irqdomain for MSI/MSI-x.\n");
+		pr_warn("Failed to initialize PCI-MSI irqdomain.\n");
 	} else {
-		msi_default_domain->flags |= IRQ_DOMAIN_MSI_NOMASK_QUIRK;
+		d->flags |= IRQ_DOMAIN_MSI_NOMASK_QUIRK;
 	}
+	return d;
+}
+
+void __init x86_create_pci_msi_domain(void)
+{
+	x86_pci_msi_default_domain = x86_init.irqs.create_pci_msi_domain();
 }
 
 #ifdef CONFIG_IRQ_REMAP
@@ -279,7 +247,6 @@ static struct irq_chip pci_msi_ir_controller = {
 	.irq_mask		= pci_msi_mask_irq,
 	.irq_ack		= irq_chip_ack_parent,
 	.irq_retrigger		= irq_chip_retrigger_hierarchy,
-	.irq_set_vcpu_affinity	= irq_chip_set_vcpu_affinity_parent,
 	.flags			= IRQCHIP_SKIP_SET_WAKE,
 };
 
@@ -321,35 +288,28 @@ static struct irq_chip dmar_msi_controller = {
 	.irq_ack		= irq_chip_ack_parent,
 	.irq_set_affinity	= msi_domain_set_affinity,
 	.irq_retrigger		= irq_chip_retrigger_hierarchy,
-	.irq_compose_msi_msg	= irq_msi_compose_msg,
 	.irq_write_msi_msg	= dmar_msi_write_msg,
 	.flags			= IRQCHIP_SKIP_SET_WAKE,
 };
 
-static irq_hw_number_t dmar_msi_get_hwirq(struct msi_domain_info *info,
-					  msi_alloc_info_t *arg)
-{
-	return arg->dmar_id;
-}
-
 static int dmar_msi_init(struct irq_domain *domain,
 			 struct msi_domain_info *info, unsigned int virq,
 			 irq_hw_number_t hwirq, msi_alloc_info_t *arg)
 {
-	irq_domain_set_info(domain, virq, arg->dmar_id, info->chip, NULL,
-			    handle_edge_irq, arg->dmar_data, "edge");
+	irq_domain_set_info(domain, virq, arg->devid, info->chip, NULL,
+			    handle_edge_irq, arg->data, "edge");
 
 	return 0;
 }
 
 static struct msi_domain_ops dmar_msi_domain_ops = {
-	.get_hwirq	= dmar_msi_get_hwirq,
 	.msi_init	= dmar_msi_init,
 };
 
 static struct msi_domain_info dmar_msi_domain_info = {
 	.ops		= &dmar_msi_domain_ops,
 	.chip		= &dmar_msi_controller,
+	.flags		= MSI_FLAG_USE_DEF_DOM_OPS,
 };
 
 static struct irq_domain *dmar_get_irq_domain(void)
@@ -384,8 +344,9 @@ int dmar_alloc_hwirq(int id, int node, void *arg)
 
 	init_irq_alloc_info(&info, NULL);
 	info.type = X86_IRQ_ALLOC_TYPE_DMAR;
-	info.dmar_id = id;
-	info.dmar_data = arg;
+	info.devid = id;
+	info.hwirq = id;
+	info.data = arg;
 
 	return irq_domain_alloc_irqs(domain, 1, node, &info);
 }
@@ -419,24 +380,17 @@ static struct irq_chip hpet_msi_controller __ro_after_init = {
 	.irq_ack = irq_chip_ack_parent,
 	.irq_set_affinity = msi_domain_set_affinity,
 	.irq_retrigger = irq_chip_retrigger_hierarchy,
-	.irq_compose_msi_msg = irq_msi_compose_msg,
 	.irq_write_msi_msg = hpet_msi_write_msg,
 	.flags = IRQCHIP_SKIP_SET_WAKE,
 };
 
-static irq_hw_number_t hpet_msi_get_hwirq(struct msi_domain_info *info,
-					  msi_alloc_info_t *arg)
-{
-	return arg->hpet_index;
-}
-
 static int hpet_msi_init(struct irq_domain *domain,
 			 struct msi_domain_info *info, unsigned int virq,
 			 irq_hw_number_t hwirq, msi_alloc_info_t *arg)
 {
 	irq_set_status_flags(virq, IRQ_MOVE_PCNTXT);
-	irq_domain_set_info(domain, virq, arg->hpet_index, info->chip, NULL,
-			    handle_edge_irq, arg->hpet_data, "edge");
+	irq_domain_set_info(domain, virq, arg->hwirq, info->chip, NULL,
+			    handle_edge_irq, arg->data, "edge");
 
 	return 0;
 }
@@ -448,7 +402,6 @@ static void hpet_msi_free(struct irq_domain *domain,
 }
 
 static struct msi_domain_ops hpet_msi_domain_ops = {
-	.get_hwirq	= hpet_msi_get_hwirq,
 	.msi_init	= hpet_msi_init,
 	.msi_free	= hpet_msi_free,
 };
@@ -456,6 +409,7 @@ static struct msi_domain_ops hpet_msi_domain_ops = {
 static struct msi_domain_info hpet_msi_domain_info = {
 	.ops		= &hpet_msi_domain_ops,
 	.chip		= &hpet_msi_controller,
+	.flags		= MSI_FLAG_USE_DEF_DOM_OPS,
 };
 
 struct irq_domain *hpet_create_irq_domain(int hpet_id)
@@ -476,9 +430,9 @@ struct irq_domain *hpet_create_irq_domain(int hpet_id)
 	domain_info->data = (void *)(long)hpet_id;
 
 	init_irq_alloc_info(&info, NULL);
-	info.type = X86_IRQ_ALLOC_TYPE_HPET;
-	info.hpet_id = hpet_id;
-	parent = irq_remapping_get_ir_irq_domain(&info);
+	info.type = X86_IRQ_ALLOC_TYPE_HPET_GET_PARENT;
+	info.devid = hpet_id;
+	parent = irq_remapping_get_irq_domain(&info);
 	if (parent == NULL)
 		parent = x86_vector_domain;
 	else
@@ -506,9 +460,9 @@ int hpet_assign_irq(struct irq_domain *domain, struct hpet_channel *hc,
 
 	init_irq_alloc_info(&info, NULL);
 	info.type = X86_IRQ_ALLOC_TYPE_HPET;
-	info.hpet_data = hc;
-	info.hpet_id = hpet_dev_id(domain);
-	info.hpet_index = dev_num;
+	info.data = hc;
+	info.devid = hpet_dev_id(domain);
+	info.hwirq = dev_num;
 
 	return irq_domain_alloc_irqs(domain, 1, NUMA_NO_NODE, &info);
 }
diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c
index 99ee61c9ba54..67b6f7c049ec 100644
--- a/arch/x86/kernel/apic/probe_32.c
+++ b/arch/x86/kernel/apic/probe_32.c
@@ -170,9 +170,6 @@ void __init default_setup_apic_routing(void)
 
 	if (apic->setup_apic_routing)
 		apic->setup_apic_routing();
-
-	if (x86_platform.apic_post_init)
-		x86_platform.apic_post_init();
 }
 
 void __init generic_apic_probe(void)
diff --git a/arch/x86/kernel/apic/probe_64.c b/arch/x86/kernel/apic/probe_64.c
index bd3835d6b535..c46720f185c0 100644
--- a/arch/x86/kernel/apic/probe_64.c
+++ b/arch/x86/kernel/apic/probe_64.c
@@ -32,9 +32,6 @@ void __init default_setup_apic_routing(void)
 			break;
 		}
 	}
-
-	if (x86_platform.apic_post_init)
-		x86_platform.apic_post_init();
 }
 
 int __init default_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c
index f8a56b5dc29f..1eac53632786 100644
--- a/arch/x86/kernel/apic/vector.c
+++ b/arch/x86/kernel/apic/vector.c
@@ -714,8 +714,6 @@ int __init arch_early_irq_init(void)
 	BUG_ON(x86_vector_domain == NULL);
 	irq_set_default_host(x86_vector_domain);
 
-	arch_init_msi_domain(x86_vector_domain);
-
 	BUG_ON(!alloc_cpumask_var(&vector_searchmask, GFP_KERNEL));
 
 	/*
@@ -824,6 +822,7 @@ static struct irq_chip lapic_controller = {
 	.name			= "APIC",
 	.irq_ack		= apic_ack_edge,
 	.irq_set_affinity	= apic_set_affinity,
+	.irq_compose_msi_msg	= x86_vector_msi_compose_msg,
 	.irq_retrigger		= apic_retrigger_irq,
 };
 
diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c
index a0e8fc7d85f1..ddffd80f5c52 100644
--- a/arch/x86/kernel/devicetree.c
+++ b/arch/x86/kernel/devicetree.c
@@ -229,8 +229,8 @@ static int dt_irqdomain_alloc(struct irq_domain *domain, unsigned int virq,
 
 	it = &of_ioapic_type[type_index];
 	ioapic_set_alloc_attr(&tmp, NUMA_NO_NODE, it->trigger, it->polarity);
-	tmp.ioapic_id = mpc_ioapic_id(mp_irqdomain_ioapic_idx(domain));
-	tmp.ioapic_pin = fwspec->param[0];
+	tmp.devid = mpc_ioapic_id(mp_irqdomain_ioapic_idx(domain));
+	tmp.ioapic.pin = fwspec->param[0];
 
 	return mp_irqdomain_alloc(domain, virq, nr_irqs, &tmp);
 }
diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c
index 5c358ccf6649..8f06449aab27 100644
--- a/arch/x86/kernel/mpparse.c
+++ b/arch/x86/kernel/mpparse.c
@@ -45,11 +45,6 @@ static int __init mpf_checksum(unsigned char *mp, int len)
 	return sum & 0xFF;
 }
 
-int __init default_mpc_apic_id(struct mpc_cpu *m)
-{
-	return m->apicid;
-}
-
 static void __init MP_processor_info(struct mpc_cpu *m)
 {
 	int apicid;
@@ -60,7 +55,7 @@ static void __init MP_processor_info(struct mpc_cpu *m)
 		return;
 	}
 
-	apicid = x86_init.mpparse.mpc_apic_id(m);
+	apicid = m->apicid;
 
 	if (m->cpuflag & CPU_BOOTPROCESSOR) {
 		bootup_cpu = " (Bootup-CPU)";
@@ -72,7 +67,7 @@ static void __init MP_processor_info(struct mpc_cpu *m)
 }
 
 #ifdef CONFIG_X86_IO_APIC
-void __init default_mpc_oem_bus_info(struct mpc_bus *m, char *str)
+static void __init mpc_oem_bus_info(struct mpc_bus *m, char *str)
 {
 	memcpy(str, m->bustype, 6);
 	str[6] = 0;
@@ -83,7 +78,7 @@ static void __init MP_bus_info(struct mpc_bus *m)
 {
 	char str[7];
 
-	x86_init.mpparse.mpc_oem_bus_info(m, str);
+	mpc_oem_bus_info(m, str);
 
 #if MAX_MP_BUSSES < 256
 	if (m->busid >= MAX_MP_BUSSES) {
@@ -99,9 +94,6 @@ static void __init MP_bus_info(struct mpc_bus *m)
 		mp_bus_id_to_type[m->busid] = MP_BUS_ISA;
 #endif
 	} else if (strncmp(str, BUSTYPE_PCI, sizeof(BUSTYPE_PCI) - 1) == 0) {
-		if (x86_init.mpparse.mpc_oem_pci_bus)
-			x86_init.mpparse.mpc_oem_pci_bus(m);
-
 		clear_bit(m->busid, mp_bus_not_pci);
 #ifdef CONFIG_EISA
 		mp_bus_id_to_type[m->busid] = MP_BUS_PCI;
@@ -197,8 +189,6 @@ static void __init smp_dump_mptable(struct mpc_table *mpc, unsigned char *mpt)
 			1, mpc, mpc->length, 1);
 }
 
-void __init default_smp_read_mpc_oem(struct mpc_table *mpc) { }
-
 static int __init smp_read_mpc(struct mpc_table *mpc, unsigned early)
 {
 	char str[16];
@@ -217,14 +207,7 @@ static int __init smp_read_mpc(struct mpc_table *mpc, unsigned early)
 	if (early)
 		return 1;
 
-	if (mpc->oemptr)
-		x86_init.mpparse.smp_read_mpc_oem(mpc);
-
-	/*
-	 *      Now process the configuration blocks.
-	 */
-	x86_init.mpparse.mpc_record(0);
-
+	/* Now process the configuration blocks. */
 	while (count < mpc->length) {
 		switch (*mpt) {
 		case MP_PROCESSOR:
@@ -255,7 +238,6 @@ static int __init smp_read_mpc(struct mpc_table *mpc, unsigned early)
 			count = mpc->length;
 			break;
 		}
-		x86_init.mpparse.mpc_record(1);
 	}
 
 	if (!num_processors)
diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c
index 123f1c1f1788..a3038d8deb6a 100644
--- a/arch/x86/kernel/x86_init.c
+++ b/arch/x86/kernel/x86_init.c
@@ -24,6 +24,7 @@
 #include <asm/tsc.h>
 #include <asm/iommu.h>
 #include <asm/mach_traps.h>
+#include <asm/irqdomain.h>
 
 void x86_init_noop(void) { }
 void __init x86_init_uint_noop(unsigned int unused) { }
@@ -67,11 +68,7 @@ struct x86_init_ops x86_init __initdata = {
 	},
 
 	.mpparse = {
-		.mpc_record		= x86_init_uint_noop,
 		.setup_ioapic_ids	= x86_init_noop,
-		.mpc_apic_id		= default_mpc_apic_id,
-		.smp_read_mpc_oem	= default_smp_read_mpc_oem,
-		.mpc_oem_bus_info	= default_mpc_oem_bus_info,
 		.find_smp_config	= default_find_smp_config,
 		.get_smp_config		= default_get_smp_config,
 	},
@@ -80,7 +77,8 @@ struct x86_init_ops x86_init __initdata = {
 		.pre_vector_init	= init_ISA_irqs,
 		.intr_init		= native_init_IRQ,
 		.intr_mode_select	= apic_intr_mode_select,
-		.intr_mode_init		= apic_intr_mode_init
+		.intr_mode_init		= apic_intr_mode_init,
+		.create_pci_msi_domain	= native_create_pci_msi_domain,
 	},
 
 	.oem = {
@@ -148,28 +146,10 @@ EXPORT_SYMBOL_GPL(x86_platform);
 
 #if defined(CONFIG_PCI_MSI)
 struct x86_msi_ops x86_msi __ro_after_init = {
-	.setup_msi_irqs		= native_setup_msi_irqs,
-	.teardown_msi_irq	= native_teardown_msi_irq,
-	.teardown_msi_irqs	= default_teardown_msi_irqs,
 	.restore_msi_irqs	= default_restore_msi_irqs,
 };
 
 /* MSI arch specific hooks */
-int arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
-{
-	return x86_msi.setup_msi_irqs(dev, nvec, type);
-}
-
-void arch_teardown_msi_irqs(struct pci_dev *dev)
-{
-	x86_msi.teardown_msi_irqs(dev);
-}
-
-void arch_teardown_msi_irq(unsigned int irq)
-{
-	x86_msi.teardown_msi_irq(irq);
-}
-
 void arch_restore_msi_irqs(struct pci_dev *dev)
 {
 	x86_msi.restore_msi_irqs(dev);
diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c
index df1d95913d4e..3507f456fcd0 100644
--- a/arch/x86/pci/common.c
+++ b/arch/x86/pci/common.c
@@ -19,6 +19,7 @@
 #include <asm/smp.h>
 #include <asm/pci_x86.h>
 #include <asm/setup.h>
+#include <asm/irqdomain.h>
 
 unsigned int pci_probe = PCI_PROBE_BIOS | PCI_PROBE_CONF1 | PCI_PROBE_CONF2 |
 				PCI_PROBE_MMCONF;
@@ -633,8 +634,9 @@ static void set_dev_domain_options(struct pci_dev *pdev)
 
 int pcibios_add_device(struct pci_dev *dev)
 {
-	struct setup_data *data;
 	struct pci_setup_rom *rom;
+	struct irq_domain *msidom;
+	struct setup_data *data;
 	u64 pa_data;
 
 	pa_data = boot_params.hdr.setup_data;
@@ -661,6 +663,20 @@ int pcibios_add_device(struct pci_dev *dev)
 		memunmap(data);
 	}
 	set_dev_domain_options(dev);
+
+	/*
+	 * Setup the initial MSI domain of the device. If the underlying
+	 * bus has a PCI/MSI irqdomain associated use the bus domain,
+	 * otherwise set the default domain. This ensures that special irq
+	 * domains e.g. VMD are preserved. The default ensures initial
+	 * operation if irq remapping is not active. If irq remapping is
+	 * active it will overwrite the domain pointer when the device is
+	 * associated to a remapping domain.
+	 */
+	msidom = dev_get_msi_domain(&dev->bus->dev);
+	if (!msidom)
+		msidom = x86_pci_msi_default_domain;
+	dev_set_msi_domain(&dev->dev, msidom);
 	return 0;
 }
 
diff --git a/arch/x86/pci/init.c b/arch/x86/pci/init.c
index 5fc617edf108..00bfa1ebad6c 100644
--- a/arch/x86/pci/init.c
+++ b/arch/x86/pci/init.c
@@ -3,16 +3,17 @@
 #include <linux/init.h>
 #include <asm/pci_x86.h>
 #include <asm/x86_init.h>
+#include <asm/irqdomain.h>
 
 /* arch_initcall has too random ordering, so call the initializers
    in the right sequence from here. */
 static __init int pci_arch_init(void)
 {
-#ifdef CONFIG_PCI_DIRECT
-	int type = 0;
+	int type;
+
+	x86_create_pci_msi_domain();
 
 	type = pci_direct_probe();
-#endif
 
 	if (!(pci_probe & PCI_PROBE_NOEARLY))
 		pci_mmcfg_early_init();
@@ -20,18 +21,16 @@ static __init int pci_arch_init(void)
 	if (x86_init.pci.arch_init && !x86_init.pci.arch_init())
 		return 0;
 
-#ifdef CONFIG_PCI_BIOS
 	pci_pcbios_init();
-#endif
+
 	/*
 	 * don't check for raw_pci_ops here because we want pcbios as last
 	 * fallback, yet it's needed to run first to set pcibios_last_bus
 	 * in case legacy PCI probing is used. otherwise detecting peer busses
 	 * fails.
 	 */
-#ifdef CONFIG_PCI_DIRECT
 	pci_direct_init(type);
-#endif
+
 	if (!raw_pci_ops && !raw_pci_ext_ops)
 		printk(KERN_ERR
 		"PCI: Fatal: No config space access function found\n");
diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c
index 89395a5049bb..c552cd2d0632 100644
--- a/arch/x86/pci/xen.c
+++ b/arch/x86/pci/xen.c
@@ -157,6 +157,13 @@ static int acpi_register_gsi_xen(struct device *dev, u32 gsi,
 struct xen_pci_frontend_ops *xen_pci_frontend;
 EXPORT_SYMBOL_GPL(xen_pci_frontend);
 
+struct xen_msi_ops {
+	int (*setup_msi_irqs)(struct pci_dev *dev, int nvec, int type);
+	void (*teardown_msi_irqs)(struct pci_dev *dev);
+};
+
+static struct xen_msi_ops xen_msi_ops __ro_after_init;
+
 static int xen_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 {
 	int irq, ret, i;
@@ -372,28 +379,122 @@ static void xen_initdom_restore_msi_irqs(struct pci_dev *dev)
 		WARN(ret && ret != -ENOSYS, "restore_msi -> %d\n", ret);
 	}
 }
-#endif
+#else /* CONFIG_XEN_DOM0 */
+#define xen_initdom_setup_msi_irqs	NULL
+#define xen_initdom_restore_msi_irqs	NULL
+#endif /* !CONFIG_XEN_DOM0 */
 
 static void xen_teardown_msi_irqs(struct pci_dev *dev)
 {
 	struct msi_desc *msidesc;
+	int i;
+
+	for_each_pci_msi_entry(msidesc, dev) {
+		if (msidesc->irq) {
+			for (i = 0; i < msidesc->nvec_used; i++)
+				xen_destroy_irq(msidesc->irq + i);
+		}
+	}
+}
+
+static void xen_pv_teardown_msi_irqs(struct pci_dev *dev)
+{
+	struct msi_desc *msidesc = first_pci_msi_entry(dev);
 
-	msidesc = first_pci_msi_entry(dev);
 	if (msidesc->msi_attrib.is_msix)
 		xen_pci_frontend_disable_msix(dev);
 	else
 		xen_pci_frontend_disable_msi(dev);
 
-	/* Free the IRQ's and the msidesc using the generic code. */
-	default_teardown_msi_irqs(dev);
+	xen_teardown_msi_irqs(dev);
 }
 
-static void xen_teardown_msi_irq(unsigned int irq)
+static int xen_msi_domain_alloc_irqs(struct irq_domain *domain,
+				     struct device *dev,  int nvec)
 {
-	xen_destroy_irq(irq);
+	int type;
+
+	if (WARN_ON_ONCE(!dev_is_pci(dev)))
+		return -EINVAL;
+
+	if (first_msi_entry(dev)->msi_attrib.is_msix)
+		type = PCI_CAP_ID_MSIX;
+	else
+		type = PCI_CAP_ID_MSI;
+
+	return xen_msi_ops.setup_msi_irqs(to_pci_dev(dev), nvec, type);
 }
 
-#endif
+static void xen_msi_domain_free_irqs(struct irq_domain *domain,
+				     struct device *dev)
+{
+	if (WARN_ON_ONCE(!dev_is_pci(dev)))
+		return;
+
+	xen_msi_ops.teardown_msi_irqs(to_pci_dev(dev));
+}
+
+static struct msi_domain_ops xen_pci_msi_domain_ops = {
+	.domain_alloc_irqs	= xen_msi_domain_alloc_irqs,
+	.domain_free_irqs	= xen_msi_domain_free_irqs,
+};
+
+static struct msi_domain_info xen_pci_msi_domain_info = {
+	.ops			= &xen_pci_msi_domain_ops,
+};
+
+/*
+ * This irq domain is a blatant violation of the irq domain design, but
+ * distangling XEN into real irq domains is not a job for mere mortals with
+ * limited XENology. But it's the least dangerous way for a mere mortal to
+ * get rid of the arch_*_msi_irqs() hackery in order to store the irq
+ * domain pointer in struct device. This irq domain wrappery allows to do
+ * that without breaking XEN terminally.
+ */
+static __init struct irq_domain *xen_create_pci_msi_domain(void)
+{
+	struct irq_domain *d = NULL;
+	struct fwnode_handle *fn;
+
+	fn = irq_domain_alloc_named_fwnode("XEN-MSI");
+	if (fn)
+		d = msi_create_irq_domain(fn, &xen_pci_msi_domain_info, NULL);
+
+	/* FIXME: No idea how to survive if this fails */
+	BUG_ON(!d);
+
+	return d;
+}
+
+static __init void xen_setup_pci_msi(void)
+{
+	if (xen_pv_domain()) {
+		if (xen_initial_domain()) {
+			xen_msi_ops.setup_msi_irqs = xen_initdom_setup_msi_irqs;
+			x86_msi.restore_msi_irqs = xen_initdom_restore_msi_irqs;
+		} else {
+			xen_msi_ops.setup_msi_irqs = xen_setup_msi_irqs;
+		}
+		xen_msi_ops.teardown_msi_irqs = xen_pv_teardown_msi_irqs;
+		pci_msi_ignore_mask = 1;
+	} else if (xen_hvm_domain()) {
+		xen_msi_ops.setup_msi_irqs = xen_hvm_setup_msi_irqs;
+		xen_msi_ops.teardown_msi_irqs = xen_teardown_msi_irqs;
+	} else {
+		WARN_ON_ONCE(1);
+		return;
+	}
+
+	/*
+	 * Override the PCI/MSI irq domain init function. No point
+	 * in allocating the native domain and never use it.
+	 */
+	x86_init.irqs.create_pci_msi_domain = xen_create_pci_msi_domain;
+}
+
+#else /* CONFIG_PCI_MSI */
+static inline void xen_setup_pci_msi(void) { }
+#endif /* CONFIG_PCI_MSI */
 
 int __init pci_xen_init(void)
 {
@@ -410,17 +511,12 @@ int __init pci_xen_init(void)
 	/* Keep ACPI out of the picture */
 	acpi_noirq_set();
 
-#ifdef CONFIG_PCI_MSI
-	x86_msi.setup_msi_irqs = xen_setup_msi_irqs;
-	x86_msi.teardown_msi_irq = xen_teardown_msi_irq;
-	x86_msi.teardown_msi_irqs = xen_teardown_msi_irqs;
-	pci_msi_ignore_mask = 1;
-#endif
+	xen_setup_pci_msi();
 	return 0;
 }
 
 #ifdef CONFIG_PCI_MSI
-void __init xen_msi_init(void)
+static void __init xen_hvm_msi_init(void)
 {
 	if (!disable_apic) {
 		/*
@@ -435,9 +531,7 @@ void __init xen_msi_init(void)
 		    ((eax & XEN_HVM_CPUID_APIC_ACCESS_VIRT) && boot_cpu_has(X86_FEATURE_APIC)))
 			return;
 	}
-
-	x86_msi.setup_msi_irqs = xen_hvm_setup_msi_irqs;
-	x86_msi.teardown_msi_irq = xen_teardown_msi_irq;
+	xen_setup_pci_msi();
 }
 #endif
 
@@ -460,7 +554,7 @@ int __init pci_xen_hvm_init(void)
 	 * We need to wait until after x2apic is initialized
 	 * before we can set MSI IRQ ops.
 	 */
-	x86_platform.apic_post_init = xen_msi_init;
+	x86_platform.apic_post_init = xen_hvm_msi_init;
 #endif
 	return 0;
 }
@@ -470,12 +564,7 @@ int __init pci_xen_initial_domain(void)
 {
 	int irq;
 
-#ifdef CONFIG_PCI_MSI
-	x86_msi.setup_msi_irqs = xen_initdom_setup_msi_irqs;
-	x86_msi.teardown_msi_irq = xen_teardown_msi_irq;
-	x86_msi.restore_msi_irqs = xen_initdom_restore_msi_irqs;
-	pci_msi_ignore_mask = 1;
-#endif
+	xen_setup_pci_msi();
 	__acpi_register_gsi = acpi_register_gsi_xen;
 	__acpi_unregister_gsi = NULL;
 	/*
diff --git a/arch/x86/platform/uv/uv_irq.c b/arch/x86/platform/uv/uv_irq.c
index abb6075397f0..18ca2261cc9a 100644
--- a/arch/x86/platform/uv/uv_irq.c
+++ b/arch/x86/platform/uv/uv_irq.c
@@ -90,15 +90,15 @@ static int uv_domain_alloc(struct irq_domain *domain, unsigned int virq,
 
 	ret = irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, arg);
 	if (ret >= 0) {
-		if (info->uv_limit == UV_AFFINITY_CPU)
+		if (info->uv.limit == UV_AFFINITY_CPU)
 			irq_set_status_flags(virq, IRQ_NO_BALANCING);
 		else
 			irq_set_status_flags(virq, IRQ_MOVE_PCNTXT);
 
-		chip_data->pnode = uv_blade_to_pnode(info->uv_blade);
-		chip_data->offset = info->uv_offset;
+		chip_data->pnode = uv_blade_to_pnode(info->uv.blade);
+		chip_data->offset = info->uv.offset;
 		irq_domain_set_info(domain, virq, virq, &uv_irq_chip, chip_data,
-				    handle_percpu_irq, NULL, info->uv_name);
+				    handle_percpu_irq, NULL, info->uv.name);
 	} else {
 		kfree(chip_data);
 	}
@@ -193,10 +193,10 @@ int uv_setup_irq(char *irq_name, int cpu, int mmr_blade,
 
 	init_irq_alloc_info(&info, cpumask_of(cpu));
 	info.type = X86_IRQ_ALLOC_TYPE_UV;
-	info.uv_limit = limit;
-	info.uv_blade = mmr_blade;
-	info.uv_offset = mmr_offset;
-	info.uv_name = irq_name;
+	info.uv.limit = limit;
+	info.uv.blade = mmr_blade;
+	info.uv.offset = mmr_offset;
+	info.uv.name = irq_name;
 
 	return irq_domain_alloc_irqs(domain, 1,
 				     uv_blade_to_memory_nid(mmr_blade), &info);