Merge branch 'x86-apic-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 apic updates from Thomas Gleixner: "After stopping the full x86/apic branch, I took some time to go through the first block of patches again, which are mostly cleanups and preparatory work for the irqdomain conversion and ioapic hotplug support. Unfortunaly one of the real problematic commits was right at the beginning, so I rebased this portion of the pending patches without the offenders. It would be great to get this into 3.19. That makes reworking the problematic parts simpler. The usual tip testing did not unearth any issues and it is fully bisectible now. I'm pretty confident that this wont affect the calmness of the xmas season. Changes: - Split the convoluted io_apic.c code into domain specific parts (vector, ioapic, msi, htirq) - Introduce proper helper functions to retrieve irq specific data instead of open coded dereferencing of pointers - Preparatory work for ioapic hotplug and irqdomain conversion - Removal of the non functional pci-ioapic driver - Removal of unused irq entry stubs - Make native_smp_prepare_cpus() preemtible to avoid GFP_ATOMIC allocations for everything which is called from there. - Small cleanups and fixes" * 'x86-apic-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (36 commits) iommu/amd: Use helpers to access irq_cfg data structure associated with IRQ iommu/vt-d: Use helpers to access irq_cfg data structure associated with IRQ x86: irq_remapping: Use helpers to access irq_cfg data structure associated with IRQ x86, irq: Use helpers to access irq_cfg data structure associated with IRQ x86, irq: Make MSI and HT_IRQ indepenent of X86_IO_APIC x86, irq: Move IRQ initialization routines from io_apic.c into vector.c x86, irq: Move IOAPIC related declarations from hw_irq.h into io_apic.h x86, irq: Move HT IRQ related code from io_apic.c into htirq.c x86, irq: Move PCI MSI related code from io_apic.c into msi.c x86, irq: Replace printk(KERN_LVL) with pr_lvl() utilities x86, irq: Make UP version of irq_complete_move() an inline stub x86, irq: Move local APIC related code from io_apic.c into vector.c x86, irq: Introduce helpers to access struct irq_cfg x86, irq: Protect __clear_irq_vector() with vector_lock x86, irq: Rename local APIC related functions in io_apic.c as apic_xxx() x86, irq: Refine hw_irq.h to prepare for irqdomain support x86, irq: Convert irq_2_pin list to generic list x86, irq: Kill useless parameter 'irq_attr' of IO_APIC_get_PCI_irq_vector() x86, irq, acpi: Get rid of special handling of GSI for ACPI SCI x86, irq: Introduce helper to check whether an IOAPIC has been registered ...
author: Linus Torvalds <torvalds@linux-foundation.org> 2014-12-19 14:02:02 -0800
committer: Linus Torvalds <torvalds@linux-foundation.org> 2014-12-19 14:02:02 -0800
commit: e589c9e13aeb0c5539bf1314b3a78442ea8fc0c2 (patch)
tree: 87aaebb0ef7c4cc7ee6cffc152a9264b24659b7e /arch
parent: Merge branch 'timers-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip (diff)
parent: iommu/amd: Use helpers to access irq_cfg data structure associated with IRQ (diff)
download: linux-dev-e589c9e13aeb0c5539bf1314b3a78442ea8fc0c2.tar.xz
linux-dev-e589c9e13aeb0c5539bf1314b3a78442ea8fc0c2.zip
25 files changed, 1573 insertions, 1254 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 2995788bcb1d..ba397bde7948 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -883,11 +883,11 @@ config X86_UP_IOAPIC
 config X86_LOCAL_APIC
 	def_bool y
 	depends on X86_64 || SMP || X86_32_NON_STANDARD || X86_UP_APIC || PCI_MSI
+	select GENERIC_IRQ_LEGACY_ALLOC_HWIRQ
 
 config X86_IO_APIC
-	def_bool y
-	depends on X86_64 || SMP || X86_32_NON_STANDARD || X86_UP_IOAPIC || PCI_MSI
-	select GENERIC_IRQ_LEGACY_ALLOC_HWIRQ
+	def_bool X86_64 || SMP || X86_32_NON_STANDARD || X86_UP_IOAPIC
+	depends on X86_LOCAL_APIC
 	select IRQ_DOMAIN
 
 config X86_REROUTE_FOR_BROKEN_BOOT_IRQS
diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h
index 4615906d83df..9662290e0b20 100644
--- a/arch/x86/include/asm/hw_irq.h
+++ b/arch/x86/include/asm/hw_irq.h
@@ -94,30 +94,7 @@ extern void trace_call_function_single_interrupt(void);
 #define trace_kvm_posted_intr_ipi kvm_posted_intr_ipi
 #endif /* CONFIG_TRACING */
 
-/* IOAPIC */
-#define IO_APIC_IRQ(x) (((x) >= NR_IRQS_LEGACY) || ((1<<(x)) & io_apic_irqs))
-extern unsigned long io_apic_irqs;
-
-extern void setup_IO_APIC(void);
-extern void disable_IO_APIC(void);
-
-struct io_apic_irq_attr {
-	int ioapic;
-	int ioapic_pin;
-	int trigger;
-	int polarity;
-};
-
-static inline void set_io_apic_irq_attr(struct io_apic_irq_attr *irq_attr,
-					int ioapic, int ioapic_pin,
-					int trigger, int polarity)
-{
-	irq_attr->ioapic	= ioapic;
-	irq_attr->ioapic_pin	= ioapic_pin;
-	irq_attr->trigger	= trigger;
-	irq_attr->polarity	= polarity;
-}
-
+#ifdef CONFIG_IRQ_REMAP
 /* Intel specific interrupt remapping information */
 struct irq_2_iommu {
 	struct intel_iommu *iommu;
@@ -131,14 +108,12 @@ struct irq_2_irte {
 	u16 devid; /* Device ID for IRTE table */
 	u16 index; /* Index into IRTE table*/
 };
+#endif	/* CONFIG_IRQ_REMAP */
+
+#ifdef	CONFIG_X86_LOCAL_APIC
+struct irq_data;
 
-/*
- * This is performance-critical, we want to do it O(1)
- *
- * Most irqs are mapped 1:1 with pins.
- */
 struct irq_cfg {
-	struct irq_pin_list	*irq_2_pin;
 	cpumask_var_t		domain;
 	cpumask_var_t		old_domain;
 	u8			vector;
@@ -150,18 +125,39 @@ struct irq_cfg {
 		struct irq_2_irte  irq_2_irte;
 	};
 #endif
+	union {
+#ifdef CONFIG_X86_IO_APIC
+		struct {
+			struct list_head	irq_2_pin;
+		};
+#endif
+	};
 };
 
+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);
+extern void lock_vector_lock(void);
+extern void unlock_vector_lock(void);
 extern int assign_irq_vector(int, struct irq_cfg *, const struct cpumask *);
+extern void clear_irq_vector(int irq, struct irq_cfg *cfg);
+extern void setup_vector_irq(int cpu);
+#ifdef CONFIG_SMP
 extern void send_cleanup_vector(struct irq_cfg *);
+extern void irq_complete_move(struct irq_cfg *cfg);
+#else
+static inline void send_cleanup_vector(struct irq_cfg *c) { }
+static inline void irq_complete_move(struct irq_cfg *c) { }
+#endif
 
-struct irq_data;
-int __ioapic_set_affinity(struct irq_data *, const struct cpumask *,
-			  unsigned int *dest_id);
-extern int IO_APIC_get_PCI_irq_vector(int bus, int devfn, int pin, struct io_apic_irq_attr *irq_attr);
-extern void setup_ioapic_dest(void);
-
-extern void enable_IO_APIC(void);
+extern int apic_retrigger_irq(struct irq_data *data);
+extern void apic_ack_edge(struct irq_data *data);
+extern int apic_set_affinity(struct irq_data *data, const struct cpumask *mask,
+			     unsigned int *dest_id);
+#else	/*  CONFIG_X86_LOCAL_APIC */
+static inline void lock_vector_lock(void) {}
+static inline void unlock_vector_lock(void) {}
+#endif	/* CONFIG_X86_LOCAL_APIC */
 
 /* Statistics */
 extern atomic_t irq_err_count;
@@ -185,7 +181,8 @@ extern __visible void smp_call_function_single_interrupt(struct pt_regs *);
 extern __visible void smp_invalidate_interrupt(struct pt_regs *);
 #endif
 
-extern void (*__initconst interrupt[NR_VECTORS-FIRST_EXTERNAL_VECTOR])(void);
+extern void (*__initconst interrupt[FIRST_SYSTEM_VECTOR
+				    - FIRST_EXTERNAL_VECTOR])(void);
 #ifdef CONFIG_TRACING
 #define trace_interrupt interrupt
 #endif
@@ -195,17 +192,6 @@ extern void (*__initconst interrupt[NR_VECTORS-FIRST_EXTERNAL_VECTOR])(void);
 
 typedef int vector_irq_t[NR_VECTORS];
 DECLARE_PER_CPU(vector_irq_t, vector_irq);
-extern void setup_vector_irq(int cpu);
-
-#ifdef CONFIG_X86_IO_APIC
-extern void lock_vector_lock(void);
-extern void unlock_vector_lock(void);
-extern void __setup_vector_irq(int cpu);
-#else
-static inline void lock_vector_lock(void) {}
-static inline void unlock_vector_lock(void) {}
-static inline void __setup_vector_irq(int cpu) {}
-#endif
 
 #endif /* !ASSEMBLY_ */
 
diff --git a/arch/x86/include/asm/io_apic.h b/arch/x86/include/asm/io_apic.h
index 1733ab49ac5e..bf006cce9418 100644
--- a/arch/x86/include/asm/io_apic.h
+++ b/arch/x86/include/asm/io_apic.h
@@ -132,6 +132,10 @@ extern int noioapicquirk;
 /* -1 if "noapic" boot option passed */
 extern int noioapicreroute;
 
+extern unsigned long io_apic_irqs;
+
+#define IO_APIC_IRQ(x) (((x) >= NR_IRQS_LEGACY) || ((1 << (x)) & io_apic_irqs))
+
 /*
  * If we use the IO-APIC for IRQ routing, disable automatic
  * assignment of PCI IRQ's.
@@ -139,18 +143,15 @@ extern int noioapicreroute;
 #define io_apic_assign_pci_irqs \
 	(mp_irq_entries && !skip_ioapic_setup && io_apic_irqs)
 
-struct io_apic_irq_attr;
 struct irq_cfg;
 extern void ioapic_insert_resources(void);
+extern int arch_early_ioapic_init(void);
 
 extern int native_setup_ioapic_entry(int, struct IO_APIC_route_entry *,
 				     unsigned int, int,
 				     struct io_apic_irq_attr *);
 extern void eoi_ioapic_irq(unsigned int irq, struct irq_cfg *cfg);
 
-extern void native_compose_msi_msg(struct pci_dev *pdev,
-				   unsigned int irq, unsigned int dest,
-				   struct msi_msg *msg, u8 hpet_id);
 extern void native_eoi_ioapic_pin(int apic, int pin, int vector);
 
 extern int save_ioapic_entries(void);
@@ -160,6 +161,13 @@ extern int restore_ioapic_entries(void);
 extern void setup_ioapic_ids_from_mpc(void);
 extern void setup_ioapic_ids_from_mpc_nocheck(void);
 
+struct io_apic_irq_attr {
+	int ioapic;
+	int ioapic_pin;
+	int trigger;
+	int polarity;
+};
+
 enum ioapic_domain_type {
 	IOAPIC_DOMAIN_INVALID,
 	IOAPIC_DOMAIN_LEGACY,
@@ -188,8 +196,10 @@ extern int mp_find_ioapic_pin(int ioapic, u32 gsi);
 extern u32 mp_pin_to_gsi(int ioapic, int pin);
 extern int mp_map_gsi_to_irq(u32 gsi, unsigned int flags);
 extern void mp_unmap_irq(int irq);
-extern void __init mp_register_ioapic(int id, u32 address, u32 gsi_base,
-				      struct ioapic_domain_cfg *cfg);
+extern int mp_register_ioapic(int id, u32 address, u32 gsi_base,
+			      struct ioapic_domain_cfg *cfg);
+extern int mp_unregister_ioapic(u32 gsi_base);
+extern int mp_ioapic_registered(u32 gsi_base);
 extern int mp_irqdomain_map(struct irq_domain *domain, unsigned int virq,
 			    irq_hw_number_t hwirq);
 extern void mp_irqdomain_unmap(struct irq_domain *domain, unsigned int virq);
@@ -227,19 +237,25 @@ static inline void io_apic_modify(unsigned int apic, unsigned int reg, unsigned
 
 extern void io_apic_eoi(unsigned int apic, unsigned int vector);
 
-extern bool mp_should_keep_irq(struct device *dev);
-
+extern void setup_IO_APIC(void);
+extern void enable_IO_APIC(void);
+extern void disable_IO_APIC(void);
+extern void setup_ioapic_dest(void);
+extern int IO_APIC_get_PCI_irq_vector(int bus, int devfn, int pin);
+extern void print_IO_APICs(void);
 #else  /* !CONFIG_X86_IO_APIC */
 
+#define IO_APIC_IRQ(x)		0
 #define io_apic_assign_pci_irqs 0
 #define setup_ioapic_ids_from_mpc x86_init_noop
 static inline void ioapic_insert_resources(void) { }
+static inline int arch_early_ioapic_init(void) { return 0; }
+static inline void print_IO_APICs(void) {}
 #define gsi_top (NR_IRQS_LEGACY)
 static inline int mp_find_ioapic(u32 gsi) { return 0; }
 static inline u32 mp_pin_to_gsi(int ioapic, int pin) { return UINT_MAX; }
 static inline int mp_map_gsi_to_irq(u32 gsi, unsigned int flags) { return gsi; }
 static inline void mp_unmap_irq(int irq) { }
-static inline bool mp_should_keep_irq(struct device *dev) { return 1; }
 
 static inline int save_ioapic_entries(void)
 {
@@ -262,7 +278,6 @@ static inline void disable_ioapic_support(void) { }
 #define native_io_apic_print_entries	NULL
 #define native_ioapic_set_affinity	NULL
 #define native_setup_ioapic_entry	NULL
-#define native_compose_msi_msg		NULL
 #define native_eoi_ioapic_pin		NULL
 #endif
 
diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h
index 5702d7e3111d..666c89ec4bd7 100644
--- a/arch/x86/include/asm/irq_vectors.h
+++ b/arch/x86/include/asm/irq_vectors.h
@@ -126,6 +126,12 @@
 
 #define NR_VECTORS			 256
 
+#ifdef CONFIG_X86_LOCAL_APIC
+#define FIRST_SYSTEM_VECTOR		LOCAL_TIMER_VECTOR
+#else
+#define FIRST_SYSTEM_VECTOR		NR_VECTORS
+#endif
+
 #define FPU_IRQ				  13
 
 #define	FIRST_VM86_IRQ			   3
diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h
index 0892ea0e683f..4e370a5d8117 100644
--- a/arch/x86/include/asm/pci.h
+++ b/arch/x86/include/asm/pci.h
@@ -96,12 +96,15 @@ extern void pci_iommu_alloc(void);
 #ifdef CONFIG_PCI_MSI
 /* implemented in arch/x86/kernel/apic/io_apic. */
 struct msi_desc;
+void native_compose_msi_msg(struct pci_dev *pdev, unsigned int irq,
+			    unsigned int dest, struct msi_msg *msg, u8 hpet_id);
 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);
 int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc,
 		  unsigned int irq_base, unsigned int irq_offset);
 #else
+#define native_compose_msi_msg		NULL
 #define native_setup_msi_irqs		NULL
 #define native_teardown_msi_irq		NULL
 #endif
diff --git a/arch/x86/include/asm/pci_x86.h b/arch/x86/include/asm/pci_x86.h
index fa1195dae425..164e3f8d3c3d 100644
--- a/arch/x86/include/asm/pci_x86.h
+++ b/arch/x86/include/asm/pci_x86.h
@@ -93,6 +93,8 @@ extern raw_spinlock_t pci_config_lock;
 extern int (*pcibios_enable_irq)(struct pci_dev *dev);
 extern void (*pcibios_disable_irq)(struct pci_dev *dev);
 
+extern bool mp_should_keep_irq(struct device *dev);
+
 struct pci_raw_ops {
 	int (*read)(unsigned int domain, unsigned int bus, unsigned int devfn,
 						int reg, int len, u32 *val);
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index a142e77693e1..4433a4be8171 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -76,6 +76,19 @@ int acpi_fix_pin2_polarity __initdata;
 static u64 acpi_lapic_addr __initdata = APIC_DEFAULT_PHYS_BASE;
 #endif
 
+/*
+ * Locks related to IOAPIC hotplug
+ * Hotplug side:
+ *	->device_hotplug_lock
+ *		->acpi_ioapic_lock
+ *			->ioapic_lock
+ * Interrupt mapping side:
+ *	->acpi_ioapic_lock
+ *		->ioapic_mutex
+ *			->ioapic_lock
+ */
+static DEFINE_MUTEX(acpi_ioapic_lock);
+
 /* --------------------------------------------------------------------------
                               Boot-time Configuration
    -------------------------------------------------------------------------- */
@@ -395,10 +408,6 @@ static int mp_register_gsi(struct device *dev, u32 gsi, int trigger,
 	if (acpi_irq_model != ACPI_IRQ_MODEL_IOAPIC)
 		return gsi;
 
-	/* Don't set up the ACPI SCI because it's already set up */
-	if (acpi_gbl_FADT.sci_interrupt == gsi)
-		return mp_map_gsi_to_irq(gsi, IOAPIC_MAP_ALLOC);
-
 	trigger = trigger == ACPI_EDGE_SENSITIVE ? 0 : 1;
 	polarity = polarity == ACPI_ACTIVE_HIGH ? 0 : 1;
 	node = dev ? dev_to_node(dev) : NUMA_NO_NODE;
@@ -411,7 +420,8 @@ static int mp_register_gsi(struct device *dev, u32 gsi, int trigger,
 	if (irq < 0)
 		return irq;
 
-	if (enable_update_mptable)
+	/* Don't set up the ACPI SCI because it's already set up */
+	if (enable_update_mptable && acpi_gbl_FADT.sci_interrupt != gsi)
 		mp_config_acpi_gsi(dev, gsi, trigger, polarity);
 
 	return irq;
@@ -424,9 +434,6 @@ static void mp_unregister_gsi(u32 gsi)
 	if (acpi_irq_model != ACPI_IRQ_MODEL_IOAPIC)
 		return;
 
-	if (acpi_gbl_FADT.sci_interrupt == gsi)
-		return;
-
 	irq = mp_map_gsi_to_irq(gsi, 0);
 	if (irq > 0)
 		mp_unmap_irq(irq);
@@ -609,8 +616,10 @@ int acpi_gsi_to_irq(u32 gsi, unsigned int *irqp)
 	if (acpi_irq_model == ACPI_IRQ_MODEL_PIC) {
 		*irqp = gsi;
 	} else {
+		mutex_lock(&acpi_ioapic_lock);
 		irq = mp_map_gsi_to_irq(gsi,
 					IOAPIC_MAP_ALLOC | IOAPIC_MAP_CHECK);
+		mutex_unlock(&acpi_ioapic_lock);
 		if (irq < 0)
 			return -1;
 		*irqp = irq;
@@ -650,7 +659,9 @@ static int acpi_register_gsi_ioapic(struct device *dev, u32 gsi,
 	int irq = gsi;
 
 #ifdef CONFIG_X86_IO_APIC
+	mutex_lock(&acpi_ioapic_lock);
 	irq = mp_register_gsi(dev, gsi, trigger, polarity);
+	mutex_unlock(&acpi_ioapic_lock);
 #endif
 
 	return irq;
@@ -659,7 +670,9 @@ static int acpi_register_gsi_ioapic(struct device *dev, u32 gsi,
 static void acpi_unregister_gsi_ioapic(u32 gsi)
 {
 #ifdef CONFIG_X86_IO_APIC
+	mutex_lock(&acpi_ioapic_lock);
 	mp_unregister_gsi(gsi);
+	mutex_unlock(&acpi_ioapic_lock);
 #endif
 }
 
@@ -690,6 +703,7 @@ void acpi_unregister_gsi(u32 gsi)
 }
 EXPORT_SYMBOL_GPL(acpi_unregister_gsi);
 
+#ifdef CONFIG_X86_LOCAL_APIC
 static void __init acpi_set_irq_model_ioapic(void)
 {
 	acpi_irq_model = ACPI_IRQ_MODEL_IOAPIC;
@@ -697,6 +711,7 @@ static void __init acpi_set_irq_model_ioapic(void)
 	__acpi_unregister_gsi = acpi_unregister_gsi_ioapic;
 	acpi_ioapic = 1;
 }
+#endif
 
 /*
  *  ACPI based hotplug support for CPU
@@ -759,20 +774,74 @@ EXPORT_SYMBOL(acpi_unmap_lsapic);
 
 int acpi_register_ioapic(acpi_handle handle, u64 phys_addr, u32 gsi_base)
 {
-	/* TBD */
-	return -EINVAL;
-}
+	int ret = -ENOSYS;
+#ifdef CONFIG_ACPI_HOTPLUG_IOAPIC
+	int ioapic_id;
+	u64 addr;
+	struct ioapic_domain_cfg cfg = {
+		.type = IOAPIC_DOMAIN_DYNAMIC,
+		.ops = &acpi_irqdomain_ops,
+	};
+
+	ioapic_id = acpi_get_ioapic_id(handle, gsi_base, &addr);
+	if (ioapic_id < 0) {
+		unsigned long long uid;
+		acpi_status status;
 
+		status = acpi_evaluate_integer(handle, METHOD_NAME__UID,
+					       NULL, &uid);
+		if (ACPI_FAILURE(status)) {
+			acpi_handle_warn(handle, "failed to get IOAPIC ID.\n");
+			return -EINVAL;
+		}
+		ioapic_id = (int)uid;
+	}
+
+	mutex_lock(&acpi_ioapic_lock);
+	ret  = mp_register_ioapic(ioapic_id, phys_addr, gsi_base, &cfg);
+	mutex_unlock(&acpi_ioapic_lock);
+#endif
+
+	return ret;
+}
 EXPORT_SYMBOL(acpi_register_ioapic);
 
 int acpi_unregister_ioapic(acpi_handle handle, u32 gsi_base)
 {
-	/* TBD */
-	return -EINVAL;
-}
+	int ret = -ENOSYS;
 
+#ifdef CONFIG_ACPI_HOTPLUG_IOAPIC
+	mutex_lock(&acpi_ioapic_lock);
+	ret  = mp_unregister_ioapic(gsi_base);
+	mutex_unlock(&acpi_ioapic_lock);
+#endif
+
+	return ret;
+}
 EXPORT_SYMBOL(acpi_unregister_ioapic);
 
+/**
+ * acpi_ioapic_registered - Check whether IOAPIC assoicatied with @gsi_base
+ *			    has been registered
+ * @handle:	ACPI handle of the IOAPIC deivce
+ * @gsi_base:	GSI base associated with the IOAPIC
+ *
+ * Assume caller holds some type of lock to serialize acpi_ioapic_registered()
+ * with acpi_register_ioapic()/acpi_unregister_ioapic().
+ */
+int acpi_ioapic_registered(acpi_handle handle, u32 gsi_base)
+{
+	int ret = 0;
+
+#ifdef CONFIG_ACPI_HOTPLUG_IOAPIC
+	mutex_lock(&acpi_ioapic_lock);
+	ret  = mp_ioapic_registered(gsi_base);
+	mutex_unlock(&acpi_ioapic_lock);
+#endif
+
+	return ret;
+}
+
 static int __init acpi_parse_sbf(struct acpi_table_header *table)
 {
 	struct acpi_table_boot *sb;
@@ -1185,7 +1254,9 @@ static void __init acpi_process_madt(void)
 			/*
 			 * Parse MADT IO-APIC entries
 			 */
+			mutex_lock(&acpi_ioapic_lock);
 			error = acpi_parse_madt_ioapic_entries();
+			mutex_unlock(&acpi_ioapic_lock);
 			if (!error) {
 				acpi_set_irq_model_ioapic();
 
diff --git a/arch/x86/kernel/apic/Makefile b/arch/x86/kernel/apic/Makefile
index dcb5b15401ce..8bb12ddc5db8 100644
--- a/arch/x86/kernel/apic/Makefile
+++ b/arch/x86/kernel/apic/Makefile
@@ -2,10 +2,12 @@
 # Makefile for local APIC drivers and for the IO-APIC code
 #
 
-obj-$(CONFIG_X86_LOCAL_APIC)	+= apic.o apic_noop.o ipi.o
+obj-$(CONFIG_X86_LOCAL_APIC)	+= apic.o apic_noop.o ipi.o vector.o
 obj-y				+= hw_nmi.o
 
 obj-$(CONFIG_X86_IO_APIC)	+= io_apic.o
+obj-$(CONFIG_PCI_MSI)		+= msi.o
+obj-$(CONFIG_HT_IRQ)		+= htirq.o
 obj-$(CONFIG_SMP)		+= ipi.o
 
 ifeq ($(CONFIG_X86_64),y)
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index ba6cc041edb1..29b5b18afa27 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -196,7 +196,7 @@ static int disable_apic_timer __initdata;
 int local_apic_timer_c2_ok;
 EXPORT_SYMBOL_GPL(local_apic_timer_c2_ok);
 
-int first_system_vector = 0xfe;
+int first_system_vector = FIRST_SYSTEM_VECTOR;
 
 /*
  * Debug level, exported for io_apic.c
@@ -1930,7 +1930,7 @@ int __init APIC_init_uniprocessor(void)
 /*
  * This interrupt should _never_ happen with our APIC/SMP architecture
  */
-static inline void __smp_spurious_interrupt(void)
+static inline void __smp_spurious_interrupt(u8 vector)
 {
 	u32 v;
 
@@ -1939,30 +1939,32 @@ static inline void __smp_spurious_interrupt(void)
 	 * if it is a vectored one.  Just in case...
 	 * Spurious interrupts should not be ACKed.
 	 */
-	v = apic_read(APIC_ISR + ((SPURIOUS_APIC_VECTOR & ~0x1f) >> 1));
-	if (v & (1 << (SPURIOUS_APIC_VECTOR & 0x1f)))
+	v = apic_read(APIC_ISR + ((vector & ~0x1f) >> 1));
+	if (v & (1 << (vector & 0x1f)))
 		ack_APIC_irq();
 
 	inc_irq_stat(irq_spurious_count);
 
 	/* see sw-dev-man vol 3, chapter 7.4.13.5 */
-	pr_info("spurious APIC interrupt on CPU#%d, "
-		"should never happen.\n", smp_processor_id());
+	pr_info("spurious APIC interrupt through vector %02x on CPU#%d, "
+		"should never happen.\n", vector, smp_processor_id());
 }
 
 __visible void smp_spurious_interrupt(struct pt_regs *regs)
 {
 	entering_irq();
-	__smp_spurious_interrupt();
+	__smp_spurious_interrupt(~regs->orig_ax);
 	exiting_irq();
 }
 
 __visible void smp_trace_spurious_interrupt(struct pt_regs *regs)
 {
+	u8 vector = ~regs->orig_ax;
+
 	entering_irq();
-	trace_spurious_apic_entry(SPURIOUS_APIC_VECTOR);
-	__smp_spurious_interrupt();
-	trace_spurious_apic_exit(SPURIOUS_APIC_VECTOR);
+	trace_spurious_apic_entry(vector);
+	__smp_spurious_interrupt(vector);
+	trace_spurious_apic_exit(vector);
 	exiting_irq();
 }
 
diff --git a/arch/x86/kernel/apic/htirq.c b/arch/x86/kernel/apic/htirq.c
new file mode 100644
index 000000000000..816f36e979ad
--- /dev/null
+++ b/arch/x86/kernel/apic/htirq.c
@@ -0,0 +1,107 @@
+/*
+ * Support Hypertransport IRQ
+ *
+ * Copyright (C) 1997, 1998, 1999, 2000, 2009 Ingo Molnar, Hajnalka Szabo
+ *	Moved from arch/x86/kernel/apic/io_apic.c.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/mm.h>
+#include <linux/interrupt.h>
+#include <linux/init.h>
+#include <linux/device.h>
+#include <linux/pci.h>
+#include <linux/htirq.h>
+#include <asm/hw_irq.h>
+#include <asm/apic.h>
+#include <asm/hypertransport.h>
+
+/*
+ * Hypertransport interrupt support
+ */
+static void target_ht_irq(unsigned int irq, unsigned int dest, u8 vector)
+{
+	struct ht_irq_msg msg;
+
+	fetch_ht_irq_msg(irq, &msg);
+
+	msg.address_lo &= ~(HT_IRQ_LOW_VECTOR_MASK | HT_IRQ_LOW_DEST_ID_MASK);
+	msg.address_hi &= ~(HT_IRQ_HIGH_DEST_ID_MASK);
+
+	msg.address_lo |= HT_IRQ_LOW_VECTOR(vector) | HT_IRQ_LOW_DEST_ID(dest);
+	msg.address_hi |= HT_IRQ_HIGH_DEST_ID(dest);
+
+	write_ht_irq_msg(irq, &msg);
+}
+
+static int
+ht_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force)
+{
+	struct irq_cfg *cfg = irqd_cfg(data);
+	unsigned int dest;
+	int ret;
+
+	ret = apic_set_affinity(data, mask, &dest);
+	if (ret)
+		return ret;
+
+	target_ht_irq(data->irq, dest, cfg->vector);
+	return IRQ_SET_MASK_OK_NOCOPY;
+}
+
+static struct irq_chip ht_irq_chip = {
+	.name			= "PCI-HT",
+	.irq_mask		= mask_ht_irq,
+	.irq_unmask		= unmask_ht_irq,
+	.irq_ack		= apic_ack_edge,
+	.irq_set_affinity	= ht_set_affinity,
+	.irq_retrigger		= apic_retrigger_irq,
+	.flags			= IRQCHIP_SKIP_SET_WAKE,
+};
+
+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_lo =
+		HT_IRQ_LOW_BASE |
+		HT_IRQ_LOW_DEST_ID(dest) |
+		HT_IRQ_LOW_VECTOR(cfg->vector) |
+		((apic->irq_dest_mode == 0) ?
+			HT_IRQ_LOW_DM_PHYSICAL :
+			HT_IRQ_LOW_DM_LOGICAL) |
+		HT_IRQ_LOW_RQEOI_EDGE |
+		((apic->irq_delivery_mode != dest_LowestPrio) ?
+			HT_IRQ_LOW_MT_FIXED :
+			HT_IRQ_LOW_MT_ARBITRATED) |
+		HT_IRQ_LOW_IRQ_MASKED;
+
+	write_ht_irq_msg(irq, &msg);
+
+	irq_set_chip_and_handler_name(irq, &ht_irq_chip,
+				      handle_edge_irq, "edge");
+
+	dev_dbg(&dev->dev, "irq %d for HT\n", irq);
+
+	return 0;
+}
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index a6745e756729..3f5f60406ab1 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -32,15 +32,11 @@
 #include <linux/module.h>
 #include <linux/syscore_ops.h>
 #include <linux/irqdomain.h>
-#include <linux/msi.h>
-#include <linux/htirq.h>
 #include <linux/freezer.h>
 #include <linux/kthread.h>
 #include <linux/jiffies.h>	/* time_after() */
 #include <linux/slab.h>
 #include <linux/bootmem.h>
-#include <linux/dmar.h>
-#include <linux/hpet.h>
 
 #include <asm/idle.h>
 #include <asm/io.h>
@@ -52,17 +48,12 @@
 #include <asm/dma.h>
 #include <asm/timer.h>
 #include <asm/i8259.h>
-#include <asm/msidef.h>
-#include <asm/hypertransport.h>
 #include <asm/setup.h>
 #include <asm/irq_remapping.h>
-#include <asm/hpet.h>
 #include <asm/hw_irq.h>
 
 #include <asm/apic.h>
 
-#define __apicdebuginit(type) static type __init
-
 #define	for_each_ioapic(idx)		\
 	for ((idx) = 0; (idx) < nr_ioapics; (idx)++)
 #define	for_each_ioapic_reverse(idx)	\
@@ -74,7 +65,7 @@
 		for_each_pin((idx), (pin))
 
 #define for_each_irq_pin(entry, head) \
-	for (entry = head; entry; entry = entry->next)
+	list_for_each_entry(entry, &head, list)
 
 /*
  *      Is the SiS APIC rmw bug present ?
@@ -83,7 +74,6 @@
 int sis_apic_bug = -1;
 
 static DEFINE_RAW_SPINLOCK(ioapic_lock);
-static DEFINE_RAW_SPINLOCK(vector_lock);
 static DEFINE_MUTEX(ioapic_mutex);
 static unsigned int ioapic_dynirq_base;
 static int ioapic_initialized;
@@ -112,6 +102,7 @@ static struct ioapic {
 	struct ioapic_domain_cfg irqdomain_cfg;
 	struct irq_domain *irqdomain;
 	struct mp_pin_info *pin_info;
+	struct resource *iomem_res;
 } ioapics[MAX_IO_APICS];
 
 #define mpc_ioapic_ver(ioapic_idx)	ioapics[ioapic_idx].mp_config.apicver
@@ -205,8 +196,6 @@ static int __init parse_noapic(char *str)
 }
 early_param("noapic", parse_noapic);
 
-static struct irq_cfg *alloc_irq_and_cfg_at(unsigned int at, int node);
-
 /* Will be called in mpparse/acpi/sfi codes for saving IRQ info */
 void mp_save_irq(struct mpc_intsrc *m)
 {
@@ -228,8 +217,8 @@ void mp_save_irq(struct mpc_intsrc *m)
 }
 
 struct irq_pin_list {
+	struct list_head list;
 	int apic, pin;
-	struct irq_pin_list *next;
 };
 
 static struct irq_pin_list *alloc_irq_pin_list(int node)
@@ -237,7 +226,26 @@ static struct irq_pin_list *alloc_irq_pin_list(int node)
 	return kzalloc_node(sizeof(struct irq_pin_list), GFP_KERNEL, node);
 }
 
-int __init arch_early_irq_init(void)
+static void alloc_ioapic_saved_registers(int idx)
+{
+	size_t size;
+
+	if (ioapics[idx].saved_registers)
+		return;
+
+	size = sizeof(struct IO_APIC_route_entry) * ioapics[idx].nr_registers;
+	ioapics[idx].saved_registers = kzalloc(size, GFP_KERNEL);
+	if (!ioapics[idx].saved_registers)
+		pr_err("IOAPIC %d: suspend/resume impossible!\n", idx);
+}
+
+static void free_ioapic_saved_registers(int idx)
+{
+	kfree(ioapics[idx].saved_registers);
+	ioapics[idx].saved_registers = NULL;
+}
+
+int __init arch_early_ioapic_init(void)
 {
 	struct irq_cfg *cfg;
 	int i, node = cpu_to_node(0);
@@ -245,13 +253,8 @@ int __init arch_early_irq_init(void)
 	if (!nr_legacy_irqs())
 		io_apic_irqs = ~0UL;
 
-	for_each_ioapic(i) {
-		ioapics[i].saved_registers =
-			kzalloc(sizeof(struct IO_APIC_route_entry) *
-				ioapics[i].nr_registers, GFP_KERNEL);
-		if (!ioapics[i].saved_registers)
-			pr_err("IOAPIC %d: suspend/resume impossible!\n", i);
-	}
+	for_each_ioapic(i)
+		alloc_ioapic_saved_registers(i);
 
 	/*
 	 * For legacy IRQ's, start with assigning irq0 to irq15 to
@@ -266,61 +269,6 @@ int __init arch_early_irq_init(void)
 	return 0;
 }
 
-static inline struct irq_cfg *irq_cfg(unsigned int irq)
-{
-	return irq_get_chip_data(irq);
-}
-
-static struct irq_cfg *alloc_irq_cfg(unsigned int irq, int node)
-{
-	struct irq_cfg *cfg;
-
-	cfg = kzalloc_node(sizeof(*cfg), GFP_KERNEL, node);
-	if (!cfg)
-		return NULL;
-	if (!zalloc_cpumask_var_node(&cfg->domain, GFP_KERNEL, node))
-		goto out_cfg;
-	if (!zalloc_cpumask_var_node(&cfg->old_domain, GFP_KERNEL, node))
-		goto out_domain;
-	return cfg;
-out_domain:
-	free_cpumask_var(cfg->domain);
-out_cfg:
-	kfree(cfg);
-	return NULL;
-}
-
-static void free_irq_cfg(unsigned int at, struct irq_cfg *cfg)
-{
-	if (!cfg)
-		return;
-	irq_set_chip_data(at, NULL);
-	free_cpumask_var(cfg->domain);
-	free_cpumask_var(cfg->old_domain);
-	kfree(cfg);
-}
-
-static struct irq_cfg *alloc_irq_and_cfg_at(unsigned int at, int node)
-{
-	int res = irq_alloc_desc_at(at, node);
-	struct irq_cfg *cfg;
-
-	if (res < 0) {
-		if (res != -EEXIST)
-			return NULL;
-		cfg = irq_cfg(at);
-		if (cfg)
-			return cfg;
-	}
-
-	cfg = alloc_irq_cfg(at, node);
-	if (cfg)
-		irq_set_chip_data(at, cfg);
-	else
-		irq_free_desc(at);
-	return cfg;
-}
-
 struct io_apic {
 	unsigned int index;
 	unsigned int unused[3];
@@ -445,15 +393,12 @@ static void ioapic_mask_entry(int apic, int pin)
  */
 static int __add_pin_to_irq_node(struct irq_cfg *cfg, int node, int apic, int pin)
 {
-	struct irq_pin_list **last, *entry;
+	struct irq_pin_list *entry;
 
 	/* don't allow duplicates */
-	last = &cfg->irq_2_pin;
-	for_each_irq_pin(entry, cfg->irq_2_pin) {
+	for_each_irq_pin(entry, cfg->irq_2_pin)
 		if (entry->apic == apic && entry->pin == pin)
 			return 0;
-		last = &entry->next;
-	}
 
 	entry = alloc_irq_pin_list(node);
 	if (!entry) {
@@ -464,22 +409,19 @@ static int __add_pin_to_irq_node(struct irq_cfg *cfg, int node, int apic, int pi
 	entry->apic = apic;
 	entry->pin = pin;
 
-	*last = entry;
+	list_add_tail(&entry->list, &cfg->irq_2_pin);
 	return 0;
 }
 
 static void __remove_pin_from_irq(struct irq_cfg *cfg, int apic, int pin)
 {
-	struct irq_pin_list **last, *entry;
+	struct irq_pin_list *tmp, *entry;
 
-	last = &cfg->irq_2_pin;
-	for_each_irq_pin(entry, cfg->irq_2_pin)
+	list_for_each_entry_safe(entry, tmp, &cfg->irq_2_pin, list)
 		if (entry->apic == apic && entry->pin == pin) {
-			*last = entry->next;
+			list_del(&entry->list);
 			kfree(entry);
 			return;
-		} else {
-			last = &entry->next;
 		}
 }
 
@@ -559,7 +501,7 @@ static void mask_ioapic(struct irq_cfg *cfg)
 
 static void mask_ioapic_irq(struct irq_data *data)
 {
-	mask_ioapic(data->chip_data);
+	mask_ioapic(irqd_cfg(data));
 }
 
 static void __unmask_ioapic(struct irq_cfg *cfg)
@@ -578,7 +520,7 @@ static void unmask_ioapic(struct irq_cfg *cfg)
 
 static void unmask_ioapic_irq(struct irq_data *data)
 {
-	unmask_ioapic(data->chip_data);
+	unmask_ioapic(irqd_cfg(data));
 }
 
 /*
@@ -1164,8 +1106,7 @@ void mp_unmap_irq(int irq)
  * Find a specific PCI IRQ entry.
  * Not an __init, possibly needed by modules
  */
-int IO_APIC_get_PCI_irq_vector(int bus, int slot, int pin,
-				struct io_apic_irq_attr *irq_attr)
+int IO_APIC_get_PCI_irq_vector(int bus, int slot, int pin)
 {
 	int irq, i, best_ioapic = -1, best_idx = -1;
 
@@ -1219,195 +1160,11 @@ int IO_APIC_get_PCI_irq_vector(int bus, int slot, int pin,
 		return -1;
 
 out:
-	irq = pin_2_irq(best_idx, best_ioapic, mp_irqs[best_idx].dstirq,
-			IOAPIC_MAP_ALLOC);
-	if (irq > 0)
-		set_io_apic_irq_attr(irq_attr, best_ioapic,
-				     mp_irqs[best_idx].dstirq,
-				     irq_trigger(best_idx),
-				     irq_polarity(best_idx));
-	return irq;
+	return pin_2_irq(best_idx, best_ioapic, mp_irqs[best_idx].dstirq,
+			 IOAPIC_MAP_ALLOC);
 }
 EXPORT_SYMBOL(IO_APIC_get_PCI_irq_vector);
 
-void lock_vector_lock(void)
-{
-	/* Used to the online set of cpus does not change
-	 * during assign_irq_vector.
-	 */
-	raw_spin_lock(&vector_lock);
-}
-
-void unlock_vector_lock(void)
-{
-	raw_spin_unlock(&vector_lock);
-}
-
-static int
-__assign_irq_vector(int irq, struct irq_cfg *cfg, const struct cpumask *mask)
-{
-	/*
-	 * NOTE! The local APIC isn't very good at handling
-	 * multiple interrupts at the same interrupt level.
-	 * As the interrupt level is determined by taking the
-	 * vector number and shifting that right by 4, we
-	 * want to spread these out a bit so that they don't
-	 * all fall in the same interrupt level.
-	 *
-	 * Also, we've got to be careful not to trash gate
-	 * 0x80, because int 0x80 is hm, kind of importantish. ;)
-	 */
-	static int current_vector = FIRST_EXTERNAL_VECTOR + VECTOR_OFFSET_START;
-	static int current_offset = VECTOR_OFFSET_START % 16;
-	int cpu, err;
-	cpumask_var_t tmp_mask;
-
-	if (cfg->move_in_progress)
-		return -EBUSY;
-
-	if (!alloc_cpumask_var(&tmp_mask, GFP_ATOMIC))
-		return -ENOMEM;
-
-	/* Only try and allocate irqs on cpus that are present */
-	err = -ENOSPC;
-	cpumask_clear(cfg->old_domain);
-	cpu = cpumask_first_and(mask, cpu_online_mask);
-	while (cpu < nr_cpu_ids) {
-		int new_cpu, vector, offset;
-
-		apic->vector_allocation_domain(cpu, tmp_mask, mask);
-
-		if (cpumask_subset(tmp_mask, cfg->domain)) {
-			err = 0;
-			if (cpumask_equal(tmp_mask, cfg->domain))
-				break;
-			/*
-			 * New cpumask using the vector is a proper subset of
-			 * the current in use mask. So cleanup the vector
-			 * allocation for the members that are not used anymore.
-			 */
-			cpumask_andnot(cfg->old_domain, cfg->domain, tmp_mask);
-			cfg->move_in_progress =
-			   cpumask_intersects(cfg->old_domain, cpu_online_mask);
-			cpumask_and(cfg->domain, cfg->domain, tmp_mask);
-			break;
-		}
-
-		vector = current_vector;
-		offset = current_offset;
-next:
-		vector += 16;
-		if (vector >= first_system_vector) {
-			offset = (offset + 1) % 16;
-			vector = FIRST_EXTERNAL_VECTOR + offset;
-		}
-
-		if (unlikely(current_vector == vector)) {
-			cpumask_or(cfg->old_domain, cfg->old_domain, tmp_mask);
-			cpumask_andnot(tmp_mask, mask, cfg->old_domain);
-			cpu = cpumask_first_and(tmp_mask, cpu_online_mask);
-			continue;
-		}
-
-		if (test_bit(vector, used_vectors))
-			goto next;
-
-		for_each_cpu_and(new_cpu, tmp_mask, cpu_online_mask) {
-			if (per_cpu(vector_irq, new_cpu)[vector] > VECTOR_UNDEFINED)
-				goto next;
-		}
-		/* Found one! */
-		current_vector = vector;
-		current_offset = offset;
-		if (cfg->vector) {
-			cpumask_copy(cfg->old_domain, cfg->domain);
-			cfg->move_in_progress =
-			   cpumask_intersects(cfg->old_domain, cpu_online_mask);
-		}
-		for_each_cpu_and(new_cpu, tmp_mask, cpu_online_mask)
-			per_cpu(vector_irq, new_cpu)[vector] = irq;
-		cfg->vector = vector;
-		cpumask_copy(cfg->domain, tmp_mask);
-		err = 0;
-		break;
-	}
-	free_cpumask_var(tmp_mask);
-	return err;
-}
-
-int assign_irq_vector(int irq, struct irq_cfg *cfg, const struct cpumask *mask)
-{
-	int err;
-	unsigned long flags;
-
-	raw_spin_lock_irqsave(&vector_lock, flags);
-	err = __assign_irq_vector(irq, cfg, mask);
-	raw_spin_unlock_irqrestore(&vector_lock, flags);
-	return err;
-}
-
-static void __clear_irq_vector(int irq, struct irq_cfg *cfg)
-{
-	int cpu, vector;
-
-	BUG_ON(!cfg->vector);
-
-	vector = cfg->vector;
-	for_each_cpu_and(cpu, cfg->domain, cpu_online_mask)
-		per_cpu(vector_irq, cpu)[vector] = VECTOR_UNDEFINED;
-
-	cfg->vector = 0;
-	cpumask_clear(cfg->domain);
-
-	if (likely(!cfg->move_in_progress))
-		return;
-	for_each_cpu_and(cpu, cfg->old_domain, cpu_online_mask) {
-		for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) {
-			if (per_cpu(vector_irq, cpu)[vector] != irq)
-				continue;
-			per_cpu(vector_irq, cpu)[vector] = VECTOR_UNDEFINED;
-			break;
-		}
-	}
-	cfg->move_in_progress = 0;
-}
-
-void __setup_vector_irq(int cpu)
-{
-	/* Initialize vector_irq on a new cpu */
-	int irq, vector;
-	struct irq_cfg *cfg;
-
-	/*
-	 * vector_lock will make sure that we don't run into irq vector
-	 * assignments that might be happening on another cpu in parallel,
-	 * while we setup our initial vector to irq mappings.
-	 */
-	raw_spin_lock(&vector_lock);
-	/* Mark the inuse vectors */
-	for_each_active_irq(irq) {
-		cfg = irq_cfg(irq);
-		if (!cfg)
-			continue;
-
-		if (!cpumask_test_cpu(cpu, cfg->domain))
-			continue;
-		vector = cfg->vector;
-		per_cpu(vector_irq, cpu)[vector] = irq;
-	}
-	/* Mark the free vectors */
-	for (vector = 0; vector < NR_VECTORS; ++vector) {
-		irq = per_cpu(vector_irq, cpu)[vector];
-		if (irq <= VECTOR_UNDEFINED)
-			continue;
-
-		cfg = irq_cfg(irq);
-		if (!cpumask_test_cpu(cpu, cfg->domain))
-			per_cpu(vector_irq, cpu)[vector] = VECTOR_UNDEFINED;
-	}
-	raw_spin_unlock(&vector_lock);
-}
-
 static struct irq_chip ioapic_chip;
 
 #ifdef CONFIG_X86_32
@@ -1496,7 +1253,7 @@ static void setup_ioapic_irq(unsigned int irq, struct irq_cfg *cfg,
 					 &dest)) {
 		pr_warn("Failed to obtain apicid for ioapic %d, pin %d\n",
 			mpc_ioapic_id(attr->ioapic), attr->ioapic_pin);
-		__clear_irq_vector(irq, cfg);
+		clear_irq_vector(irq, cfg);
 
 		return;
 	}
@@ -1510,7 +1267,7 @@ static void setup_ioapic_irq(unsigned int irq, struct irq_cfg *cfg,
 	if (x86_io_apic_ops.setup_entry(irq, &entry, dest, cfg->vector, attr)) {
 		pr_warn("Failed to setup ioapic entry for ioapic  %d, pin %d\n",
 			mpc_ioapic_id(attr->ioapic), attr->ioapic_pin);
-		__clear_irq_vector(irq, cfg);
+		clear_irq_vector(irq, cfg);
 
 		return;
 	}
@@ -1641,7 +1398,7 @@ void ioapic_zap_locks(void)
 	raw_spin_lock_init(&ioapic_lock);
 }
 
-__apicdebuginit(void) print_IO_APIC(int ioapic_idx)
+static void __init print_IO_APIC(int ioapic_idx)
 {
 	union IO_APIC_reg_00 reg_00;
 	union IO_APIC_reg_01 reg_01;
@@ -1698,7 +1455,7 @@ __apicdebuginit(void) print_IO_APIC(int ioapic_idx)
 	x86_io_apic_ops.print_entries(ioapic_idx, reg_01.bits.entries);
 }
 
-__apicdebuginit(void) print_IO_APICs(void)
+void __init print_IO_APICs(void)
 {
 	int ioapic_idx;
 	struct irq_cfg *cfg;
@@ -1731,8 +1488,7 @@ __apicdebuginit(void) print_IO_APICs(void)
 		cfg = irq_cfg(irq);
 		if (!cfg)
 			continue;
-		entry = cfg->irq_2_pin;
-		if (!entry)
+		if (list_empty(&cfg->irq_2_pin))
 			continue;
 		printk(KERN_DEBUG "IRQ%d ", irq);
 		for_each_irq_pin(entry, cfg->irq_2_pin)
@@ -1743,205 +1499,6 @@ __apicdebuginit(void) print_IO_APICs(void)
 	printk(KERN_INFO ".................................... done.\n");
 }
 
-__apicdebuginit(void) print_APIC_field(int base)
-{
-	int i;
-
-	printk(KERN_DEBUG);
-
-	for (i = 0; i < 8; i++)
-		pr_cont("%08x", apic_read(base + i*0x10));
-
-	pr_cont("\n");
-}
-
-__apicdebuginit(void) print_local_APIC(void *dummy)
-{
-	unsigned int i, v, ver, maxlvt;
-	u64 icr;
-
-	printk(KERN_DEBUG "printing local APIC contents on CPU#%d/%d:\n",
-		smp_processor_id(), hard_smp_processor_id());
-	v = apic_read(APIC_ID);
-	printk(KERN_INFO "... APIC ID:      %08x (%01x)\n", v, read_apic_id());
-	v = apic_read(APIC_LVR);
-	printk(KERN_INFO "... APIC VERSION: %08x\n", v);
-	ver = GET_APIC_VERSION(v);
-	maxlvt = lapic_get_maxlvt();
-
-	v = apic_read(APIC_TASKPRI);
-	printk(KERN_DEBUG "... APIC TASKPRI: %08x (%02x)\n", v, v & APIC_TPRI_MASK);
-
-	if (APIC_INTEGRATED(ver)) {                     /* !82489DX */
-		if (!APIC_XAPIC(ver)) {
-			v = apic_read(APIC_ARBPRI);
-			printk(KERN_DEBUG "... APIC ARBPRI: %08x (%02x)\n", v,
-			       v & APIC_ARBPRI_MASK);
-		}
-		v = apic_read(APIC_PROCPRI);
-		printk(KERN_DEBUG "... APIC PROCPRI: %08x\n", v);
-	}
-
-	/*
-	 * Remote read supported only in the 82489DX and local APIC for
-	 * Pentium processors.
-	 */
-	if (!APIC_INTEGRATED(ver) || maxlvt == 3) {
-		v = apic_read(APIC_RRR);
-		printk(KERN_DEBUG "... APIC RRR: %08x\n", v);
-	}
-
-	v = apic_read(APIC_LDR);
-	printk(KERN_DEBUG "... APIC LDR: %08x\n", v);
-	if (!x2apic_enabled()) {
-		v = apic_read(APIC_DFR);
-		printk(KERN_DEBUG "... APIC DFR: %08x\n", v);
-	}
-	v = apic_read(APIC_SPIV);
-	printk(KERN_DEBUG "... APIC SPIV: %08x\n", v);
-
-	printk(KERN_DEBUG "... APIC ISR field:\n");
-	print_APIC_field(APIC_ISR);
-	printk(KERN_DEBUG "... APIC TMR field:\n");
-	print_APIC_field(APIC_TMR);
-	printk(KERN_DEBUG "... APIC IRR field:\n");
-	print_APIC_field(APIC_IRR);
-
-	if (APIC_INTEGRATED(ver)) {             /* !82489DX */
-		if (maxlvt > 3)         /* Due to the Pentium erratum 3AP. */
-			apic_write(APIC_ESR, 0);
-
-		v = apic_read(APIC_ESR);
-		printk(KERN_DEBUG "... APIC ESR: %08x\n", v);
-	}
-
-	icr = apic_icr_read();
-	printk(KERN_DEBUG "... APIC ICR: %08x\n", (u32)icr);
-	printk(KERN_DEBUG "... APIC ICR2: %08x\n", (u32)(icr >> 32));
-
-	v = apic_read(APIC_LVTT);
-	printk(KERN_DEBUG "... APIC LVTT: %08x\n", v);
-
-	if (maxlvt > 3) {                       /* PC is LVT#4. */
-		v = apic_read(APIC_LVTPC);
-		printk(KERN_DEBUG "... APIC LVTPC: %08x\n", v);
-	}
-	v = apic_read(APIC_LVT0);
-	printk(KERN_DEBUG "... APIC LVT0: %08x\n", v);
-	v = apic_read(APIC_LVT1);
-	printk(KERN_DEBUG "... APIC LVT1: %08x\n", v);
-
-	if (maxlvt > 2) {			/* ERR is LVT#3. */
-		v = apic_read(APIC_LVTERR);
-		printk(KERN_DEBUG "... APIC LVTERR: %08x\n", v);
-	}
-
-	v = apic_read(APIC_TMICT);
-	printk(KERN_DEBUG "... APIC TMICT: %08x\n", v);
-	v = apic_read(APIC_TMCCT);
-	printk(KERN_DEBUG "... APIC TMCCT: %08x\n", v);
-	v = apic_read(APIC_TDCR);
-	printk(KERN_DEBUG "... APIC TDCR: %08x\n", v);
-
-	if (boot_cpu_has(X86_FEATURE_EXTAPIC)) {
-		v = apic_read(APIC_EFEAT);
-		maxlvt = (v >> 16) & 0xff;
-		printk(KERN_DEBUG "... APIC EFEAT: %08x\n", v);
-		v = apic_read(APIC_ECTRL);
-		printk(KERN_DEBUG "... APIC ECTRL: %08x\n", v);
-		for (i = 0; i < maxlvt; i++) {
-			v = apic_read(APIC_EILVTn(i));
-			printk(KERN_DEBUG "... APIC EILVT%d: %08x\n", i, v);
-		}
-	}
-	pr_cont("\n");
-}
-
-__apicdebuginit(void) print_local_APICs(int maxcpu)
-{
-	int cpu;
-
-	if (!maxcpu)
-		return;
-
-	preempt_disable();
-	for_each_online_cpu(cpu) {
-		if (cpu >= maxcpu)
-			break;
-		smp_call_function_single(cpu, print_local_APIC, NULL, 1);
-	}
-	preempt_enable();
-}
-
-__apicdebuginit(void) print_PIC(void)
-{
-	unsigned int v;
-	unsigned long flags;
-
-	if (!nr_legacy_irqs())
-		return;
-
-	printk(KERN_DEBUG "\nprinting PIC contents\n");
-
-	raw_spin_lock_irqsave(&i8259A_lock, flags);
-
-	v = inb(0xa1) << 8 | inb(0x21);
-	printk(KERN_DEBUG "... PIC  IMR: %04x\n", v);
-
-	v = inb(0xa0) << 8 | inb(0x20);
-	printk(KERN_DEBUG "... PIC  IRR: %04x\n", v);
-
-	outb(0x0b,0xa0);
-	outb(0x0b,0x20);
-	v = inb(0xa0) << 8 | inb(0x20);
-	outb(0x0a,0xa0);
-	outb(0x0a,0x20);
-
-	raw_spin_unlock_irqrestore(&i8259A_lock, flags);
-
-	printk(KERN_DEBUG "... PIC  ISR: %04x\n", v);
-
-	v = inb(0x4d1) << 8 | inb(0x4d0);
-	printk(KERN_DEBUG "... PIC ELCR: %04x\n", v);
-}
-
-static int __initdata show_lapic = 1;
-static __init int setup_show_lapic(char *arg)
-{
-	int num = -1;
-
-	if (strcmp(arg, "all") == 0) {
-		show_lapic = CONFIG_NR_CPUS;
-	} else {
-		get_option(&arg, &num);
-		if (num >= 0)
-			show_lapic = num;
-	}
-
-	return 1;
-}
-__setup("show_lapic=", setup_show_lapic);
-
-__apicdebuginit(int) print_ICs(void)
-{
-	if (apic_verbosity == APIC_QUIET)
-		return 0;
-
-	print_PIC();
-
-	/* don't print out if apic is not there */
-	if (!cpu_has_apic && !apic_from_smp_config())
-		return 0;
-
-	print_local_APICs(show_lapic);
-	print_IO_APICs();
-
-	return 0;
-}
-
-late_initcall(print_ICs);
-
-
 /* Where if anywhere is the i8259 connect in external int mode */
 static struct { int pin, apic; } ioapic_i8259 = { -1, -1 };
 
@@ -2244,26 +1801,12 @@ static unsigned int startup_ioapic_irq(struct irq_data *data)
 		if (legacy_pic->irq_pending(irq))
 			was_pending = 1;
 	}
-	__unmask_ioapic(data->chip_data);
+	__unmask_ioapic(irqd_cfg(data));
 	raw_spin_unlock_irqrestore(&ioapic_lock, flags);
 
 	return was_pending;
 }
 
-static int ioapic_retrigger_irq(struct irq_data *data)
-{
-	struct irq_cfg *cfg = data->chip_data;
-	unsigned long flags;
-	int cpu;
-
-	raw_spin_lock_irqsave(&vector_lock, flags);
-	cpu = cpumask_first_and(cfg->domain, cpu_online_mask);
-	apic->send_IPI_mask(cpumask_of(cpu), cfg->vector);
-	raw_spin_unlock_irqrestore(&vector_lock, flags);
-
-	return 1;
-}
-
 /*
  * Level and edge triggered IO-APIC interrupts need different handling,
  * so we use two separate IRQ descriptors. Edge triggered IRQs can be
@@ -2273,113 +1816,6 @@ static int ioapic_retrigger_irq(struct irq_data *data)
  * races.
  */
 
-#ifdef CONFIG_SMP
-void send_cleanup_vector(struct irq_cfg *cfg)
-{
-	cpumask_var_t cleanup_mask;
-
-	if (unlikely(!alloc_cpumask_var(&cleanup_mask, GFP_ATOMIC))) {
-		unsigned int i;
-		for_each_cpu_and(i, cfg->old_domain, cpu_online_mask)
-			apic->send_IPI_mask(cpumask_of(i), IRQ_MOVE_CLEANUP_VECTOR);
-	} else {
-		cpumask_and(cleanup_mask, cfg->old_domain, cpu_online_mask);
-		apic->send_IPI_mask(cleanup_mask, IRQ_MOVE_CLEANUP_VECTOR);
-		free_cpumask_var(cleanup_mask);
-	}
-	cfg->move_in_progress = 0;
-}
-
-asmlinkage __visible void smp_irq_move_cleanup_interrupt(void)
-{
-	unsigned vector, me;
-
-	ack_APIC_irq();
-	irq_enter();
-	exit_idle();
-
-	me = smp_processor_id();
-	for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) {
-		int irq;
-		unsigned int irr;
-		struct irq_desc *desc;
-		struct irq_cfg *cfg;
-		irq = __this_cpu_read(vector_irq[vector]);
-
-		if (irq <= VECTOR_UNDEFINED)
-			continue;
-
-		desc = irq_to_desc(irq);
-		if (!desc)
-			continue;
-
-		cfg = irq_cfg(irq);
-		if (!cfg)
-			continue;
-
-		raw_spin_lock(&desc->lock);
-
-		/*
-		 * Check if the irq migration is in progress. If so, we
-		 * haven't received the cleanup request yet for this irq.
-		 */
-		if (cfg->move_in_progress)
-			goto unlock;
-
-		if (vector == cfg->vector && cpumask_test_cpu(me, cfg->domain))
-			goto unlock;
-
-		irr = apic_read(APIC_IRR + (vector / 32 * 0x10));
-		/*
-		 * Check if the vector that needs to be cleanedup is
-		 * registered at the cpu's IRR. If so, then this is not
-		 * the best time to clean it up. Lets clean it up in the
-		 * next attempt by sending another IRQ_MOVE_CLEANUP_VECTOR
-		 * to myself.
-		 */
-		if (irr  & (1 << (vector % 32))) {
-			apic->send_IPI_self(IRQ_MOVE_CLEANUP_VECTOR);
-			goto unlock;
-		}
-		__this_cpu_write(vector_irq[vector], VECTOR_UNDEFINED);
-unlock:
-		raw_spin_unlock(&desc->lock);
-	}
-
-	irq_exit();
-}
-
-static void __irq_complete_move(struct irq_cfg *cfg, unsigned vector)
-{
-	unsigned me;
-
-	if (likely(!cfg->move_in_progress))
-		return;
-
-	me = smp_processor_id();
-
-	if (vector == cfg->vector && cpumask_test_cpu(me, cfg->domain))
-		send_cleanup_vector(cfg);
-}
-
-static void irq_complete_move(struct irq_cfg *cfg)
-{
-	__irq_complete_move(cfg, ~get_irq_regs()->orig_ax);
-}
-
-void irq_force_complete_move(int irq)
-{
-	struct irq_cfg *cfg = irq_cfg(irq);
-
-	if (!cfg)
-		return;
-
-	__irq_complete_move(cfg, cfg->vector);
-}
-#else
-static inline void irq_complete_move(struct irq_cfg *cfg) { }
-#endif
-
 static void __target_IO_APIC_irq(unsigned int irq, unsigned int dest, struct irq_cfg *cfg)
 {
 	int apic, pin;
@@ -2400,41 +1836,6 @@ static void __target_IO_APIC_irq(unsigned int irq, unsigned int dest, struct irq
 	}
 }
 
-/*
- * Either sets data->affinity to a valid value, and returns
- * ->cpu_mask_to_apicid of that in dest_id, or returns -1 and
- * leaves data->affinity untouched.
- */
-int __ioapic_set_affinity(struct irq_data *data, const struct cpumask *mask,
-			  unsigned int *dest_id)
-{
-	struct irq_cfg *cfg = data->chip_data;
-	unsigned int irq = data->irq;
-	int err;
-
-	if (!config_enabled(CONFIG_SMP))
-		return -EPERM;
-
-	if (!cpumask_intersects(mask, cpu_online_mask))
-		return -EINVAL;
-
-	err = assign_irq_vector(irq, cfg, mask);
-	if (err)
-		return err;
-
-	err = apic->cpu_mask_to_apicid_and(mask, cfg->domain, dest_id);
-	if (err) {
-		if (assign_irq_vector(irq, cfg, data->affinity))
-			pr_err("Failed to recover vector for irq %d\n", irq);
-		return err;
-	}
-
-	cpumask_copy(data->affinity, mask);
-
-	return 0;
-}
-
-
 int native_ioapic_set_affinity(struct irq_data *data,
 			       const struct cpumask *mask,
 			       bool force)
@@ -2447,24 +1848,17 @@ int native_ioapic_set_affinity(struct irq_data *data,
 		return -EPERM;
 
 	raw_spin_lock_irqsave(&ioapic_lock, flags);
-	ret = __ioapic_set_affinity(data, mask, &dest);
+	ret = apic_set_affinity(data, mask, &dest);
 	if (!ret) {
 		/* Only the high 8 bits are valid. */
 		dest = SET_APIC_LOGICAL_ID(dest);
-		__target_IO_APIC_irq(irq, dest, data->chip_data);
+		__target_IO_APIC_irq(irq, dest, irqd_cfg(data));
 		ret = IRQ_SET_MASK_OK_NOCOPY;
 	}
 	raw_spin_unlock_irqrestore(&ioapic_lock, flags);
 	return ret;
 }
 
-static void ack_apic_edge(struct irq_data *data)
-{
-	irq_complete_move(data->chip_data);
-	irq_move_irq(data);
-	ack_APIC_irq();
-}
-
 atomic_t irq_mis_count;
 
 #ifdef CONFIG_GENERIC_PENDING_IRQ
@@ -2547,9 +1941,9 @@ static inline void ioapic_irqd_unmask(struct irq_data *data,
 }
 #endif
 
-static void ack_apic_level(struct irq_data *data)
+static void ack_ioapic_level(struct irq_data *data)
 {
-	struct irq_cfg *cfg = data->chip_data;
+	struct irq_cfg *cfg = irqd_cfg(data);
 	int i, irq = data->irq;
 	unsigned long v;
 	bool masked;
@@ -2619,10 +2013,10 @@ static struct irq_chip ioapic_chip __read_mostly = {
 	.irq_startup		= startup_ioapic_irq,
 	.irq_mask		= mask_ioapic_irq,
 	.irq_unmask		= unmask_ioapic_irq,
-	.irq_ack		= ack_apic_edge,
-	.irq_eoi		= ack_apic_level,
+	.irq_ack		= apic_ack_edge,
+	.irq_eoi		= ack_ioapic_level,
 	.irq_set_affinity	= native_ioapic_set_affinity,
-	.irq_retrigger		= ioapic_retrigger_irq,
+	.irq_retrigger		= apic_retrigger_irq,
 	.flags			= IRQCHIP_SKIP_SET_WAKE,
 };
 
@@ -2965,6 +2359,16 @@ static int mp_irqdomain_create(int ioapic)
 	return 0;
 }
 
+static void ioapic_destroy_irqdomain(int idx)
+{
+	if (ioapics[idx].irqdomain) {
+		irq_domain_remove(ioapics[idx].irqdomain);
+		ioapics[idx].irqdomain = NULL;
+	}
+	kfree(ioapics[idx].pin_info);
+	ioapics[idx].pin_info = NULL;
+}
+
 void __init setup_IO_APIC(void)
 {
 	int ioapic;
@@ -3044,399 +2448,6 @@ static int __init ioapic_init_ops(void)
 
 device_initcall(ioapic_init_ops);
 
-/*
- * Dynamic irq allocate and deallocation. Should be replaced by irq domains!
- */
-int arch_setup_hwirq(unsigned int irq, int node)
-{
-	struct irq_cfg *cfg;
-	unsigned long flags;
-	int ret;
-
-	cfg = alloc_irq_cfg(irq, node);
-	if (!cfg)
-		return -ENOMEM;
-
-	raw_spin_lock_irqsave(&vector_lock, flags);
-	ret = __assign_irq_vector(irq, cfg, apic->target_cpus());
-	raw_spin_unlock_irqrestore(&vector_lock, flags);
-
-	if (!ret)
-		irq_set_chip_data(irq, cfg);
-	else
-		free_irq_cfg(irq, cfg);
-	return ret;
-}
-
-void arch_teardown_hwirq(unsigned int irq)
-{
-	struct irq_cfg *cfg = irq_cfg(irq);
-	unsigned long flags;
-
-	free_remapped_irq(irq);
-	raw_spin_lock_irqsave(&vector_lock, flags);
-	__clear_irq_vector(irq, cfg);
-	raw_spin_unlock_irqrestore(&vector_lock, flags);
-	free_irq_cfg(irq, cfg);
-}
-
-/*
- * MSI message composition
- */
-void native_compose_msi_msg(struct pci_dev *pdev,
-			    unsigned int irq, unsigned int dest,
-			    struct msi_msg *msg, u8 hpet_id)
-{
-	struct irq_cfg *cfg = irq_cfg(irq);
-
-	msg->address_hi = MSI_ADDR_BASE_HI;
-
-	if (x2apic_enabled())
-		msg->address_hi |= MSI_ADDR_EXT_DEST_ID(dest);
-
-	msg->address_lo =
-		MSI_ADDR_BASE_LO |
-		((apic->irq_dest_mode == 0) ?
-			MSI_ADDR_DEST_MODE_PHYSICAL:
-			MSI_ADDR_DEST_MODE_LOGICAL) |
-		((apic->irq_delivery_mode != dest_LowestPrio) ?
-			MSI_ADDR_REDIRECTION_CPU:
-			MSI_ADDR_REDIRECTION_LOWPRI) |
-		MSI_ADDR_DEST_ID(dest);
-
-	msg->data =
-		MSI_DATA_TRIGGER_EDGE |
-		MSI_DATA_LEVEL_ASSERT |
-		((apic->irq_delivery_mode != dest_LowestPrio) ?
-			MSI_DATA_DELIVERY_FIXED:
-			MSI_DATA_DELIVERY_LOWPRI) |
-		MSI_DATA_VECTOR(cfg->vector);
-}
-
-#ifdef CONFIG_PCI_MSI
-static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq,
-			   struct msi_msg *msg, u8 hpet_id)
-{
-	struct irq_cfg *cfg;
-	int err;
-	unsigned dest;
-
-	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;
-
-	x86_msi.compose_msi_msg(pdev, irq, dest, msg, hpet_id);
-
-	return 0;
-}
-
-static int
-msi_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force)
-{
-	struct irq_cfg *cfg = data->chip_data;
-	struct msi_msg msg;
-	unsigned int dest;
-	int ret;
-
-	ret = __ioapic_set_affinity(data, mask, &dest);
-	if (ret)
-		return ret;
-
-	__get_cached_msi_msg(data->msi_desc, &msg);
-
-	msg.data &= ~MSI_DATA_VECTOR_MASK;
-	msg.data |= MSI_DATA_VECTOR(cfg->vector);
-	msg.address_lo &= ~MSI_ADDR_DEST_ID_MASK;
-	msg.address_lo |= MSI_ADDR_DEST_ID(dest);
-
-	__pci_write_msi_msg(data->msi_desc, &msg);
-
-	return IRQ_SET_MASK_OK_NOCOPY;
-}
-
-/*
- * IRQ Chip for MSI PCI/PCI-X/PCI-Express Devices,
- * which implement the MSI or MSI-X Capability Structure.
- */
-static struct irq_chip msi_chip = {
-	.name			= "PCI-MSI",
-	.irq_unmask		= pci_msi_unmask_irq,
-	.irq_mask		= pci_msi_mask_irq,
-	.irq_ack		= ack_apic_edge,
-	.irq_set_affinity	= msi_set_affinity,
-	.irq_retrigger		= ioapic_retrigger_irq,
-	.flags			= IRQCHIP_SKIP_SET_WAKE,
-};
-
-int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc,
-		  unsigned int irq_base, unsigned int irq_offset)
-{
-	struct irq_chip *chip = &msi_chip;
-	struct msi_msg msg;
-	unsigned int irq = irq_base + irq_offset;
-	int ret;
-
-	ret = msi_compose_msg(dev, irq, &msg, -1);
-	if (ret < 0)
-		return ret;
-
-	irq_set_msi_desc_off(irq_base, irq_offset, msidesc);
-
-	/*
-	 * MSI-X message is written per-IRQ, the offset is always 0.
-	 * MSI message denotes a contiguous group of IRQs, written for 0th IRQ.
-	 */
-	if (!irq_offset)
-		pci_write_msi_msg(irq, &msg);
-
-	setup_remapped_irq(irq, irq_cfg(irq), chip);
-
-	irq_set_chip_and_handler_name(irq, chip, handle_edge_irq, "edge");
-
-	dev_printk(KERN_DEBUG, &dev->dev, "irq %d for MSI/MSI-X\n", irq);
-
-	return 0;
-}
-
-int native_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
-{
-	struct msi_desc *msidesc;
-	unsigned int irq;
-	int node, 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)
-			return -ENOSPC;
-
-		ret = setup_msi_irq(dev, msidesc, irq, 0);
-		if (ret < 0) {
-			irq_free_hwirq(irq);
-			return ret;
-		}
-
-	}
-	return 0;
-}
-
-void native_teardown_msi_irq(unsigned int irq)
-{
-	irq_free_hwirq(irq);
-}
-
-#ifdef CONFIG_DMAR_TABLE
-static int
-dmar_msi_set_affinity(struct irq_data *data, const struct cpumask *mask,
-		      bool force)
-{
-	struct irq_cfg *cfg = data->chip_data;
-	unsigned int dest, irq = data->irq;
-	struct msi_msg msg;
-	int ret;
-
-	ret = __ioapic_set_affinity(data, mask, &dest);
-	if (ret)
-		return ret;
-
-	dmar_msi_read(irq, &msg);
-
-	msg.data &= ~MSI_DATA_VECTOR_MASK;
-	msg.data |= MSI_DATA_VECTOR(cfg->vector);
-	msg.address_lo &= ~MSI_ADDR_DEST_ID_MASK;
-	msg.address_lo |= MSI_ADDR_DEST_ID(dest);
-	msg.address_hi = MSI_ADDR_BASE_HI | MSI_ADDR_EXT_DEST_ID(dest);
-
-	dmar_msi_write(irq, &msg);
-
-	return IRQ_SET_MASK_OK_NOCOPY;
-}
-
-static struct irq_chip dmar_msi_type = {
-	.name			= "DMAR_MSI",
-	.irq_unmask		= dmar_msi_unmask,
-	.irq_mask		= dmar_msi_mask,
-	.irq_ack		= ack_apic_edge,
-	.irq_set_affinity	= dmar_msi_set_affinity,
-	.irq_retrigger		= ioapic_retrigger_irq,
-	.flags			= IRQCHIP_SKIP_SET_WAKE,
-};
-
-int arch_setup_dmar_msi(unsigned int irq)
-{
-	int ret;
-	struct msi_msg msg;
-
-	ret = msi_compose_msg(NULL, irq, &msg, -1);
-	if (ret < 0)
-		return ret;
-	dmar_msi_write(irq, &msg);
-	irq_set_chip_and_handler_name(irq, &dmar_msi_type, handle_edge_irq,
-				      "edge");
-	return 0;
-}
-#endif
-
-#ifdef CONFIG_HPET_TIMER
-
-static int hpet_msi_set_affinity(struct irq_data *data,
-				 const struct cpumask *mask, bool force)
-{
-	struct irq_cfg *cfg = data->chip_data;
-	struct msi_msg msg;
-	unsigned int dest;
-	int ret;
-
-	ret = __ioapic_set_affinity(data, mask, &dest);
-	if (ret)
-		return ret;
-
-	hpet_msi_read(data->handler_data, &msg);
-
-	msg.data &= ~MSI_DATA_VECTOR_MASK;
-	msg.data |= MSI_DATA_VECTOR(cfg->vector);
-	msg.address_lo &= ~MSI_ADDR_DEST_ID_MASK;
-	msg.address_lo |= MSI_ADDR_DEST_ID(dest);
-
-	hpet_msi_write(data->handler_data, &msg);
-
-	return IRQ_SET_MASK_OK_NOCOPY;
-}
-
-static struct irq_chip hpet_msi_type = {
-	.name = "HPET_MSI",
-	.irq_unmask = hpet_msi_unmask,
-	.irq_mask = hpet_msi_mask,
-	.irq_ack = ack_apic_edge,
-	.irq_set_affinity = hpet_msi_set_affinity,
-	.irq_retrigger = ioapic_retrigger_irq,
-	.flags = IRQCHIP_SKIP_SET_WAKE,
-};
-
-int default_setup_hpet_msi(unsigned int irq, unsigned int id)
-{
-	struct irq_chip *chip = &hpet_msi_type;
-	struct msi_msg msg;
-	int ret;
-
-	ret = msi_compose_msg(NULL, irq, &msg, id);
-	if (ret < 0)
-		return ret;
-
-	hpet_msi_write(irq_get_handler_data(irq), &msg);
-	irq_set_status_flags(irq, IRQ_MOVE_PCNTXT);
-	setup_remapped_irq(irq, irq_cfg(irq), chip);
-
-	irq_set_chip_and_handler_name(irq, chip, handle_edge_irq, "edge");
-	return 0;
-}
-#endif
-
-#endif /* CONFIG_PCI_MSI */
-/*
- * Hypertransport interrupt support
- */
-#ifdef CONFIG_HT_IRQ
-
-static void target_ht_irq(unsigned int irq, unsigned int dest, u8 vector)
-{
-	struct ht_irq_msg msg;
-	fetch_ht_irq_msg(irq, &msg);
-
-	msg.address_lo &= ~(HT_IRQ_LOW_VECTOR_MASK | HT_IRQ_LOW_DEST_ID_MASK);
-	msg.address_hi &= ~(HT_IRQ_HIGH_DEST_ID_MASK);
-
-	msg.address_lo |= HT_IRQ_LOW_VECTOR(vector) | HT_IRQ_LOW_DEST_ID(dest);
-	msg.address_hi |= HT_IRQ_HIGH_DEST_ID(dest);
-
-	write_ht_irq_msg(irq, &msg);
-}
-
-static int
-ht_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force)
-{
-	struct irq_cfg *cfg = data->chip_data;
-	unsigned int dest;
-	int ret;
-
-	ret = __ioapic_set_affinity(data, mask, &dest);
-	if (ret)
-		return ret;
-
-	target_ht_irq(data->irq, dest, cfg->vector);
-	return IRQ_SET_MASK_OK_NOCOPY;
-}
-
-static struct irq_chip ht_irq_chip = {
-	.name			= "PCI-HT",
-	.irq_mask		= mask_ht_irq,
-	.irq_unmask		= unmask_ht_irq,
-	.irq_ack		= ack_apic_edge,
-	.irq_set_affinity	= ht_set_affinity,
-	.irq_retrigger		= ioapic_retrigger_irq,
-	.flags			= IRQCHIP_SKIP_SET_WAKE,
-};
-
-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_lo =
-		HT_IRQ_LOW_BASE |
-		HT_IRQ_LOW_DEST_ID(dest) |
-		HT_IRQ_LOW_VECTOR(cfg->vector) |
-		((apic->irq_dest_mode == 0) ?
-			HT_IRQ_LOW_DM_PHYSICAL :
-			HT_IRQ_LOW_DM_LOGICAL) |
-		HT_IRQ_LOW_RQEOI_EDGE |
-		((apic->irq_delivery_mode != dest_LowestPrio) ?
-			HT_IRQ_LOW_MT_FIXED :
-			HT_IRQ_LOW_MT_ARBITRATED) |
-		HT_IRQ_LOW_IRQ_MASKED;
-
-	write_ht_irq_msg(irq, &msg);
-
-	irq_set_chip_and_handler_name(irq, &ht_irq_chip,
-				      handle_edge_irq, "edge");
-
-	dev_printk(KERN_DEBUG, &dev->dev, "irq %d for HT\n", irq);
-
-	return 0;
-}
-#endif /* CONFIG_HT_IRQ */
-
 static int
 io_apic_setup_irq_pin(unsigned int irq, int node, struct io_apic_irq_attr *attr)
 {
@@ -3451,7 +2462,7 @@ io_apic_setup_irq_pin(unsigned int irq, int node, struct io_apic_irq_attr *attr)
 	return ret;
 }
 
-static int __init io_apic_get_redir_entries(int ioapic)
+static int io_apic_get_redir_entries(int ioapic)
 {
 	union IO_APIC_reg_01	reg_01;
 	unsigned long flags;
@@ -3476,28 +2487,8 @@ unsigned int arch_dynirq_lower_bound(unsigned int from)
 	return ioapic_initialized ? ioapic_dynirq_base : gsi_top;
 }
 
-int __init arch_probe_nr_irqs(void)
-{
-	int nr;
-
-	if (nr_irqs > (NR_VECTORS * nr_cpu_ids))
-		nr_irqs = NR_VECTORS * nr_cpu_ids;
-
-	nr = (gsi_top + nr_legacy_irqs()) + 8 * nr_cpu_ids;
-#if defined(CONFIG_PCI_MSI) || defined(CONFIG_HT_IRQ)
-	/*
-	 * for MSI and HT dyn irq
-	 */
-	nr += gsi_top * 16;
-#endif
-	if (nr < nr_irqs)
-		nr_irqs = nr;
-
-	return 0;
-}
-
 #ifdef CONFIG_X86_32
-static int __init io_apic_get_unique_id(int ioapic, int apic_id)
+static int io_apic_get_unique_id(int ioapic, int apic_id)
 {
 	union IO_APIC_reg_00 reg_00;
 	static physid_mask_t apic_id_map = PHYSID_MASK_NONE;
@@ -3572,30 +2563,63 @@ static int __init io_apic_get_unique_id(int ioapic, int apic_id)
 	return apic_id;
 }
 
-static u8 __init io_apic_unique_id(u8 id)
+static u8 io_apic_unique_id(int idx, u8 id)
 {
 	if ((boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) &&
 	    !APIC_XAPIC(apic_version[boot_cpu_physical_apicid]))
-		return io_apic_get_unique_id(nr_ioapics, id);
+		return io_apic_get_unique_id(idx, id);
 	else
 		return id;
 }
 #else
-static u8 __init io_apic_unique_id(u8 id)
+static u8 io_apic_unique_id(int idx, u8 id)
 {
-	int i;
+	union IO_APIC_reg_00 reg_00;
 	DECLARE_BITMAP(used, 256);
+	unsigned long flags;
+	u8 new_id;
+	int i;
 
 	bitmap_zero(used, 256);
 	for_each_ioapic(i)
 		__set_bit(mpc_ioapic_id(i), used);
+
+	/* Hand out the requested id if available */
 	if (!test_bit(id, used))
 		return id;
-	return find_first_zero_bit(used, 256);
+
+	/*
+	 * Read the current id from the ioapic and keep it if
+	 * available.
+	 */
+	raw_spin_lock_irqsave(&ioapic_lock, flags);
+	reg_00.raw = io_apic_read(idx, 0);
+	raw_spin_unlock_irqrestore(&ioapic_lock, flags);
+	new_id = reg_00.bits.ID;
+	if (!test_bit(new_id, used)) {
+		apic_printk(APIC_VERBOSE, KERN_INFO
+			"IOAPIC[%d]: Using reg apic_id %d instead of %d\n",
+			 idx, new_id, id);
+		return new_id;
+	}
+
+	/*
+	 * Get the next free id and write it to the ioapic.
+	 */
+	new_id = find_first_zero_bit(used, 256);
+	reg_00.bits.ID = new_id;
+	raw_spin_lock_irqsave(&ioapic_lock, flags);
+	io_apic_write(idx, 0, reg_00.raw);
+	reg_00.raw = io_apic_read(idx, 0);
+	raw_spin_unlock_irqrestore(&ioapic_lock, flags);
+	/* Sanity check */
+	BUG_ON(reg_00.bits.ID != new_id);
+
+	return new_id;
 }
 #endif
 
-static int __init io_apic_get_version(int ioapic)
+static int io_apic_get_version(int ioapic)
 {
 	union IO_APIC_reg_01	reg_01;
 	unsigned long flags;
@@ -3702,6 +2726,7 @@ static struct resource * __init ioapic_setup_resources(void)
 		snprintf(mem, IOAPIC_RESOURCE_NAME_SIZE, "IOAPIC %u", i);
 		mem += IOAPIC_RESOURCE_NAME_SIZE;
 		num++;
+		ioapics[i].iomem_res = res;
 	}
 
 	ioapic_resources = res;
@@ -3799,21 +2824,7 @@ int mp_find_ioapic_pin(int ioapic, u32 gsi)
 	return gsi - gsi_cfg->gsi_base;
 }
 
-static __init int bad_ioapic(unsigned long address)
-{
-	if (nr_ioapics >= MAX_IO_APICS) {
-		pr_warn("WARNING: Max # of I/O APICs (%d) exceeded (found %d), skipping\n",
-			MAX_IO_APICS, nr_ioapics);
-		return 1;
-	}
-	if (!address) {
-		pr_warn("WARNING: Bogus (zero) I/O APIC address found in table, skipping!\n");
-		return 1;
-	}
-	return 0;
-}
-
-static __init int bad_ioapic_register(int idx)
+static int bad_ioapic_register(int idx)
 {
 	union IO_APIC_reg_00 reg_00;
 	union IO_APIC_reg_01 reg_01;
@@ -3832,32 +2843,61 @@ static __init int bad_ioapic_register(int idx)
 	return 0;
 }
 
-void __init mp_register_ioapic(int id, u32 address, u32 gsi_base,
-			       struct ioapic_domain_cfg *cfg)
+static int find_free_ioapic_entry(void)
 {
-	int idx = 0;
-	int entries;
+	int idx;
+
+	for (idx = 0; idx < MAX_IO_APICS; idx++)
+		if (ioapics[idx].nr_registers == 0)
+			return idx;
+
+	return MAX_IO_APICS;
+}
+
+/**
+ * mp_register_ioapic - Register an IOAPIC device
+ * @id:		hardware IOAPIC ID
+ * @address:	physical address of IOAPIC register area
+ * @gsi_base:	base of GSI associated with the IOAPIC
+ * @cfg:	configuration information for the IOAPIC
+ */
+int mp_register_ioapic(int id, u32 address, u32 gsi_base,
+		       struct ioapic_domain_cfg *cfg)
+{
+	bool hotplug = !!ioapic_initialized;
 	struct mp_ioapic_gsi *gsi_cfg;
+	int idx, ioapic, entries;
+	u32 gsi_end;
 
-	if (bad_ioapic(address))
-		return;
+	if (!address) {
+		pr_warn("Bogus (zero) I/O APIC address found, skipping!\n");
+		return -EINVAL;
+	}
+	for_each_ioapic(ioapic)
+		if (ioapics[ioapic].mp_config.apicaddr == address) {
+			pr_warn("address 0x%x conflicts with IOAPIC%d\n",
+				address, ioapic);
+			return -EEXIST;
+		}
 
-	idx = nr_ioapics;
+	idx = find_free_ioapic_entry();
+	if (idx >= MAX_IO_APICS) {
+		pr_warn("Max # of I/O APICs (%d) exceeded (found %d), skipping\n",
+			MAX_IO_APICS, idx);
+		return -ENOSPC;
+	}
 
 	ioapics[idx].mp_config.type = MP_IOAPIC;
 	ioapics[idx].mp_config.flags = MPC_APIC_USABLE;
 	ioapics[idx].mp_config.apicaddr = address;
-	ioapics[idx].irqdomain = NULL;
-	ioapics[idx].irqdomain_cfg = *cfg;
 
 	set_fixmap_nocache(FIX_IO_APIC_BASE_0 + idx, address);
-
 	if (bad_ioapic_register(idx)) {
 		clear_fixmap(FIX_IO_APIC_BASE_0 + idx);
-		return;
+		return -ENODEV;
 	}
 
-	ioapics[idx].mp_config.apicid = io_apic_unique_id(id);
+	ioapics[idx].mp_config.apicid = io_apic_unique_id(idx, id);
 	ioapics[idx].mp_config.apicver = io_apic_get_version(idx);
 
 	/*
@@ -3865,24 +2905,112 @@ void __init mp_register_ioapic(int id, u32 address, u32 gsi_base,
 	 * and to prevent reprogramming of IOAPIC pins (PCI GSIs).
 	 */
 	entries = io_apic_get_redir_entries(idx);
+	gsi_end = gsi_base + entries - 1;
+	for_each_ioapic(ioapic) {
+		gsi_cfg = mp_ioapic_gsi_routing(ioapic);
+		if ((gsi_base >= gsi_cfg->gsi_base &&
+		     gsi_base <= gsi_cfg->gsi_end) ||
+		    (gsi_end >= gsi_cfg->gsi_base &&
+		     gsi_end <= gsi_cfg->gsi_end)) {
+			pr_warn("GSI range [%u-%u] for new IOAPIC conflicts with GSI[%u-%u]\n",
+				gsi_base, gsi_end,
+				gsi_cfg->gsi_base, gsi_cfg->gsi_end);
+			clear_fixmap(FIX_IO_APIC_BASE_0 + idx);
+			return -ENOSPC;
+		}
+	}
 	gsi_cfg = mp_ioapic_gsi_routing(idx);
 	gsi_cfg->gsi_base = gsi_base;
-	gsi_cfg->gsi_end = gsi_base + entries - 1;
+	gsi_cfg->gsi_end = gsi_end;
+
+	ioapics[idx].irqdomain = NULL;
+	ioapics[idx].irqdomain_cfg = *cfg;
 
 	/*
-	 * The number of IO-APIC IRQ registers (== #pins):
+	 * If mp_register_ioapic() is called during early boot stage when
+	 * walking ACPI/SFI/DT tables, it's too early to create irqdomain,
+	 * we are still using bootmem allocator. So delay it to setup_IO_APIC().
 	 */
-	ioapics[idx].nr_registers = entries;
+	if (hotplug) {
+		if (mp_irqdomain_create(idx)) {
+			clear_fixmap(FIX_IO_APIC_BASE_0 + idx);
+			return -ENOMEM;
+		}
+		alloc_ioapic_saved_registers(idx);
+	}
 
 	if (gsi_cfg->gsi_end >= gsi_top)
 		gsi_top = gsi_cfg->gsi_end + 1;
+	if (nr_ioapics <= idx)
+		nr_ioapics = idx + 1;
+
+	/* Set nr_registers to mark entry present */
+	ioapics[idx].nr_registers = entries;
 
 	pr_info("IOAPIC[%d]: apic_id %d, version %d, address 0x%x, GSI %d-%d\n",
 		idx, mpc_ioapic_id(idx),
 		mpc_ioapic_ver(idx), mpc_ioapic_addr(idx),
 		gsi_cfg->gsi_base, gsi_cfg->gsi_end);
 
-	nr_ioapics++;
+	return 0;
+}
+
+int mp_unregister_ioapic(u32 gsi_base)
+{
+	int ioapic, pin;
+	int found = 0;
+	struct mp_pin_info *pin_info;
+
+	for_each_ioapic(ioapic)
+		if (ioapics[ioapic].gsi_config.gsi_base == gsi_base) {
+			found = 1;
+			break;
+		}
+	if (!found) {
+		pr_warn("can't find IOAPIC for GSI %d\n", gsi_base);
+		return -ENODEV;
+	}
+
+	for_each_pin(ioapic, pin) {
+		pin_info = mp_pin_info(ioapic, pin);
+		if (pin_info->count) {
+			pr_warn("pin%d on IOAPIC%d is still in use.\n",
+				pin, ioapic);
+			return -EBUSY;
+		}
+	}
+
+	/* Mark entry not present */
+	ioapics[ioapic].nr_registers  = 0;
+	ioapic_destroy_irqdomain(ioapic);
+	free_ioapic_saved_registers(ioapic);
+	if (ioapics[ioapic].iomem_res)
+		release_resource(ioapics[ioapic].iomem_res);
+	clear_fixmap(FIX_IO_APIC_BASE_0 + ioapic);
+	memset(&ioapics[ioapic], 0, sizeof(ioapics[ioapic]));
+
+	return 0;
+}
+
+int mp_ioapic_registered(u32 gsi_base)
+{
+	int ioapic;
+
+	for_each_ioapic(ioapic)
+		if (ioapics[ioapic].gsi_config.gsi_base == gsi_base)
+			return 1;
+
+	return 0;
+}
+
+static inline void set_io_apic_irq_attr(struct io_apic_irq_attr *irq_attr,
+					int ioapic, int ioapic_pin,
+					int trigger, int polarity)
+{
+	irq_attr->ioapic	= ioapic;
+	irq_attr->ioapic_pin	= ioapic_pin;
+	irq_attr->trigger	= trigger;
+	irq_attr->polarity	= polarity;
 }
 
 int mp_irqdomain_map(struct irq_domain *domain, unsigned int virq,
@@ -3931,7 +3059,7 @@ void mp_irqdomain_unmap(struct irq_domain *domain, unsigned int virq)
 
 	ioapic_mask_entry(ioapic, pin);
 	__remove_pin_from_irq(cfg, ioapic, pin);
-	WARN_ON(cfg->irq_2_pin != NULL);
+	WARN_ON(!list_empty(&cfg->irq_2_pin));
 	arch_teardown_hwirq(virq);
 }
 
@@ -3964,18 +3092,6 @@ int mp_set_gsi_attr(u32 gsi, int trigger, int polarity, int node)
 	return ret;
 }
 
-bool mp_should_keep_irq(struct device *dev)
-{
-	if (dev->power.is_prepared)
-		return true;
-#ifdef	CONFIG_PM
-	if (dev->power.runtime_status == RPM_SUSPENDING)
-		return true;
-#endif
-
-	return false;
-}
-
 /* Enable IOAPIC early just for system timer */
 void __init pre_init_apic_IRQ0(void)
 {
diff --git a/arch/x86/kernel/apic/msi.c b/arch/x86/kernel/apic/msi.c
new file mode 100644
index 000000000000..d6ba2d660dc5
--- /dev/null
+++ b/arch/x86/kernel/apic/msi.c
@@ -0,0 +1,286 @@
+/*
+ * Support of MSI, HPET and DMAR interrupts.
+ *
+ * Copyright (C) 1997, 1998, 1999, 2000, 2009 Ingo Molnar, Hajnalka Szabo
+ *	Moved from arch/x86/kernel/apic/io_apic.c.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/mm.h>
+#include <linux/interrupt.h>
+#include <linux/pci.h>
+#include <linux/dmar.h>
+#include <linux/hpet.h>
+#include <linux/msi.h>
+#include <asm/msidef.h>
+#include <asm/hpet.h>
+#include <asm/hw_irq.h>
+#include <asm/apic.h>
+#include <asm/irq_remapping.h>
+
+void native_compose_msi_msg(struct pci_dev *pdev,
+			    unsigned int irq, unsigned int dest,
+			    struct msi_msg *msg, u8 hpet_id)
+{
+	struct irq_cfg *cfg = irq_cfg(irq);
+
+	msg->address_hi = MSI_ADDR_BASE_HI;
+
+	if (x2apic_enabled())
+		msg->address_hi |= MSI_ADDR_EXT_DEST_ID(dest);
+
+	msg->address_lo =
+		MSI_ADDR_BASE_LO |
+		((apic->irq_dest_mode == 0) ?
+			MSI_ADDR_DEST_MODE_PHYSICAL :
+			MSI_ADDR_DEST_MODE_LOGICAL) |
+		((apic->irq_delivery_mode != dest_LowestPrio) ?
+			MSI_ADDR_REDIRECTION_CPU :
+			MSI_ADDR_REDIRECTION_LOWPRI) |
+		MSI_ADDR_DEST_ID(dest);
+
+	msg->data =
+		MSI_DATA_TRIGGER_EDGE |
+		MSI_DATA_LEVEL_ASSERT |
+		((apic->irq_delivery_mode != dest_LowestPrio) ?
+			MSI_DATA_DELIVERY_FIXED :
+			MSI_DATA_DELIVERY_LOWPRI) |
+		MSI_DATA_VECTOR(cfg->vector);
+}
+
+static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq,
+			   struct msi_msg *msg, u8 hpet_id)
+{
+	struct irq_cfg *cfg;
+	int err;
+	unsigned dest;
+
+	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;
+
+	x86_msi.compose_msi_msg(pdev, irq, dest, msg, hpet_id);
+
+	return 0;
+}
+
+static int
+msi_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force)
+{
+	struct irq_cfg *cfg = irqd_cfg(data);
+	struct msi_msg msg;
+	unsigned int dest;
+	int ret;
+
+	ret = apic_set_affinity(data, mask, &dest);
+	if (ret)
+		return ret;
+
+	__get_cached_msi_msg(data->msi_desc, &msg);
+
+	msg.data &= ~MSI_DATA_VECTOR_MASK;
+	msg.data |= MSI_DATA_VECTOR(cfg->vector);
+	msg.address_lo &= ~MSI_ADDR_DEST_ID_MASK;
+	msg.address_lo |= MSI_ADDR_DEST_ID(dest);
+
+	__pci_write_msi_msg(data->msi_desc, &msg);
+
+	return IRQ_SET_MASK_OK_NOCOPY;
+}
+
+/*
+ * IRQ Chip for MSI PCI/PCI-X/PCI-Express Devices,
+ * which implement the MSI or MSI-X Capability Structure.
+ */
+static struct irq_chip msi_chip = {
+	.name			= "PCI-MSI",
+	.irq_unmask		= pci_msi_unmask_irq,
+	.irq_mask		= pci_msi_mask_irq,
+	.irq_ack		= apic_ack_edge,
+	.irq_set_affinity	= msi_set_affinity,
+	.irq_retrigger		= apic_retrigger_irq,
+	.flags			= IRQCHIP_SKIP_SET_WAKE,
+};
+
+int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc,
+		  unsigned int irq_base, unsigned int irq_offset)
+{
+	struct irq_chip *chip = &msi_chip;
+	struct msi_msg msg;
+	unsigned int irq = irq_base + irq_offset;
+	int ret;
+
+	ret = msi_compose_msg(dev, irq, &msg, -1);
+	if (ret < 0)
+		return ret;
+
+	irq_set_msi_desc_off(irq_base, irq_offset, msidesc);
+
+	/*
+	 * MSI-X message is written per-IRQ, the offset is always 0.
+	 * MSI message denotes a contiguous group of IRQs, written for 0th IRQ.
+	 */
+	if (!irq_offset)
+		pci_write_msi_msg(irq, &msg);
+
+	setup_remapped_irq(irq, irq_cfg(irq), chip);
+
+	irq_set_chip_and_handler_name(irq, chip, handle_edge_irq, "edge");
+
+	dev_dbg(&dev->dev, "irq %d for MSI/MSI-X\n", irq);
+
+	return 0;
+}
+
+int native_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
+{
+	struct msi_desc *msidesc;
+	unsigned int irq;
+	int node, 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)
+			return -ENOSPC;
+
+		ret = setup_msi_irq(dev, msidesc, irq, 0);
+		if (ret < 0) {
+			irq_free_hwirq(irq);
+			return ret;
+		}
+
+	}
+	return 0;
+}
+
+void native_teardown_msi_irq(unsigned int irq)
+{
+	irq_free_hwirq(irq);
+}
+
+#ifdef CONFIG_DMAR_TABLE
+static int
+dmar_msi_set_affinity(struct irq_data *data, const struct cpumask *mask,
+		      bool force)
+{
+	struct irq_cfg *cfg = irqd_cfg(data);
+	unsigned int dest, irq = data->irq;
+	struct msi_msg msg;
+	int ret;
+
+	ret = apic_set_affinity(data, mask, &dest);
+	if (ret)
+		return ret;
+
+	dmar_msi_read(irq, &msg);
+
+	msg.data &= ~MSI_DATA_VECTOR_MASK;
+	msg.data |= MSI_DATA_VECTOR(cfg->vector);
+	msg.address_lo &= ~MSI_ADDR_DEST_ID_MASK;
+	msg.address_lo |= MSI_ADDR_DEST_ID(dest);
+	msg.address_hi = MSI_ADDR_BASE_HI | MSI_ADDR_EXT_DEST_ID(dest);
+
+	dmar_msi_write(irq, &msg);
+
+	return IRQ_SET_MASK_OK_NOCOPY;
+}
+
+static struct irq_chip dmar_msi_type = {
+	.name			= "DMAR_MSI",
+	.irq_unmask		= dmar_msi_unmask,
+	.irq_mask		= dmar_msi_mask,
+	.irq_ack		= apic_ack_edge,
+	.irq_set_affinity	= dmar_msi_set_affinity,
+	.irq_retrigger		= apic_retrigger_irq,
+	.flags			= IRQCHIP_SKIP_SET_WAKE,
+};
+
+int arch_setup_dmar_msi(unsigned int irq)
+{
+	int ret;
+	struct msi_msg msg;
+
+	ret = msi_compose_msg(NULL, irq, &msg, -1);
+	if (ret < 0)
+		return ret;
+	dmar_msi_write(irq, &msg);
+	irq_set_chip_and_handler_name(irq, &dmar_msi_type, handle_edge_irq,
+				      "edge");
+	return 0;
+}
+#endif
+
+/*
+ * MSI message composition
+ */
+#ifdef CONFIG_HPET_TIMER
+
+static int hpet_msi_set_affinity(struct irq_data *data,
+				 const struct cpumask *mask, bool force)
+{
+	struct irq_cfg *cfg = irqd_cfg(data);
+	struct msi_msg msg;
+	unsigned int dest;
+	int ret;
+
+	ret = apic_set_affinity(data, mask, &dest);
+	if (ret)
+		return ret;
+
+	hpet_msi_read(data->handler_data, &msg);
+
+	msg.data &= ~MSI_DATA_VECTOR_MASK;
+	msg.data |= MSI_DATA_VECTOR(cfg->vector);
+	msg.address_lo &= ~MSI_ADDR_DEST_ID_MASK;
+	msg.address_lo |= MSI_ADDR_DEST_ID(dest);
+
+	hpet_msi_write(data->handler_data, &msg);
+
+	return IRQ_SET_MASK_OK_NOCOPY;
+}
+
+static struct irq_chip hpet_msi_type = {
+	.name = "HPET_MSI",
+	.irq_unmask = hpet_msi_unmask,
+	.irq_mask = hpet_msi_mask,
+	.irq_ack = apic_ack_edge,
+	.irq_set_affinity = hpet_msi_set_affinity,
+	.irq_retrigger = apic_retrigger_irq,
+	.flags = IRQCHIP_SKIP_SET_WAKE,
+};
+
+int default_setup_hpet_msi(unsigned int irq, unsigned int id)
+{
+	struct irq_chip *chip = &hpet_msi_type;
+	struct msi_msg msg;
+	int ret;
+
+	ret = msi_compose_msg(NULL, irq, &msg, id);
+	if (ret < 0)
+		return ret;
+
+	hpet_msi_write(irq_get_handler_data(irq), &msg);
+	irq_set_status_flags(irq, IRQ_MOVE_PCNTXT);
+	setup_remapped_irq(irq, irq_cfg(irq), chip);
+
+	irq_set_chip_and_handler_name(irq, chip, handle_edge_irq, "edge");
+	return 0;
+}
+#endif
diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c
new file mode 100644
index 000000000000..6cedd7914581
--- /dev/null
+++ b/arch/x86/kernel/apic/vector.c
@@ -0,0 +1,719 @@
+/*
+ * Local APIC related interfaces to support IOAPIC, MSI, HT_IRQ etc.
+ *
+ * Copyright (C) 1997, 1998, 1999, 2000, 2009 Ingo Molnar, Hajnalka Szabo
+ *	Moved from arch/x86/kernel/apic/io_apic.c.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/interrupt.h>
+#include <linux/init.h>
+#include <linux/compiler.h>
+#include <linux/irqdomain.h>
+#include <linux/slab.h>
+#include <asm/hw_irq.h>
+#include <asm/apic.h>
+#include <asm/i8259.h>
+#include <asm/desc.h>
+#include <asm/irq_remapping.h>
+
+static DEFINE_RAW_SPINLOCK(vector_lock);
+
+void lock_vector_lock(void)
+{
+	/* Used to the online set of cpus does not change
+	 * during assign_irq_vector.
+	 */
+	raw_spin_lock(&vector_lock);
+}
+
+void unlock_vector_lock(void)
+{
+	raw_spin_unlock(&vector_lock);
+}
+
+struct irq_cfg *irq_cfg(unsigned int irq)
+{
+	return irq_get_chip_data(irq);
+}
+
+struct irq_cfg *irqd_cfg(struct irq_data *irq_data)
+{
+	return irq_data->chip_data;
+}
+
+static struct irq_cfg *alloc_irq_cfg(unsigned int irq, int node)
+{
+	struct irq_cfg *cfg;
+
+	cfg = kzalloc_node(sizeof(*cfg), GFP_KERNEL, node);
+	if (!cfg)
+		return NULL;
+	if (!zalloc_cpumask_var_node(&cfg->domain, GFP_KERNEL, node))
+		goto out_cfg;
+	if (!zalloc_cpumask_var_node(&cfg->old_domain, GFP_KERNEL, node))
+		goto out_domain;
+#ifdef	CONFIG_X86_IO_APIC
+	INIT_LIST_HEAD(&cfg->irq_2_pin);
+#endif
+	return cfg;
+out_domain:
+	free_cpumask_var(cfg->domain);
+out_cfg:
+	kfree(cfg);
+	return NULL;
+}
+
+struct irq_cfg *alloc_irq_and_cfg_at(unsigned int at, int node)
+{
+	int res = irq_alloc_desc_at(at, node);
+	struct irq_cfg *cfg;
+
+	if (res < 0) {
+		if (res != -EEXIST)
+			return NULL;
+		cfg = irq_cfg(at);
+		if (cfg)
+			return cfg;
+	}
+
+	cfg = alloc_irq_cfg(at, node);
+	if (cfg)
+		irq_set_chip_data(at, cfg);
+	else
+		irq_free_desc(at);
+	return cfg;
+}
+
+static void free_irq_cfg(unsigned int at, struct irq_cfg *cfg)
+{
+	if (!cfg)
+		return;
+	irq_set_chip_data(at, NULL);
+	free_cpumask_var(cfg->domain);
+	free_cpumask_var(cfg->old_domain);
+	kfree(cfg);
+}
+
+static int
+__assign_irq_vector(int irq, struct irq_cfg *cfg, const struct cpumask *mask)
+{
+	/*
+	 * NOTE! The local APIC isn't very good at handling
+	 * multiple interrupts at the same interrupt level.
+	 * As the interrupt level is determined by taking the
+	 * vector number and shifting that right by 4, we
+	 * want to spread these out a bit so that they don't
+	 * all fall in the same interrupt level.
+	 *
+	 * Also, we've got to be careful not to trash gate
+	 * 0x80, because int 0x80 is hm, kind of importantish. ;)
+	 */
+	static int current_vector = FIRST_EXTERNAL_VECTOR + VECTOR_OFFSET_START;
+	static int current_offset = VECTOR_OFFSET_START % 16;
+	int cpu, err;
+	cpumask_var_t tmp_mask;
+
+	if (cfg->move_in_progress)
+		return -EBUSY;
+
+	if (!alloc_cpumask_var(&tmp_mask, GFP_ATOMIC))
+		return -ENOMEM;
+
+	/* Only try and allocate irqs on cpus that are present */
+	err = -ENOSPC;
+	cpumask_clear(cfg->old_domain);
+	cpu = cpumask_first_and(mask, cpu_online_mask);
+	while (cpu < nr_cpu_ids) {
+		int new_cpu, vector, offset;
+
+		apic->vector_allocation_domain(cpu, tmp_mask, mask);
+
+		if (cpumask_subset(tmp_mask, cfg->domain)) {
+			err = 0;
+			if (cpumask_equal(tmp_mask, cfg->domain))
+				break;
+			/*
+			 * New cpumask using the vector is a proper subset of
+			 * the current in use mask. So cleanup the vector
+			 * allocation for the members that are not used anymore.
+			 */
+			cpumask_andnot(cfg->old_domain, cfg->domain, tmp_mask);
+			cfg->move_in_progress =
+			   cpumask_intersects(cfg->old_domain, cpu_online_mask);
+			cpumask_and(cfg->domain, cfg->domain, tmp_mask);
+			break;
+		}
+
+		vector = current_vector;
+		offset = current_offset;
+next:
+		vector += 16;
+		if (vector >= first_system_vector) {
+			offset = (offset + 1) % 16;
+			vector = FIRST_EXTERNAL_VECTOR + offset;
+		}
+
+		if (unlikely(current_vector == vector)) {
+			cpumask_or(cfg->old_domain, cfg->old_domain, tmp_mask);
+			cpumask_andnot(tmp_mask, mask, cfg->old_domain);
+			cpu = cpumask_first_and(tmp_mask, cpu_online_mask);
+			continue;
+		}
+
+		if (test_bit(vector, used_vectors))
+			goto next;
+
+		for_each_cpu_and(new_cpu, tmp_mask, cpu_online_mask) {
+			if (per_cpu(vector_irq, new_cpu)[vector] >
+			    VECTOR_UNDEFINED)
+				goto next;
+		}
+		/* Found one! */
+		current_vector = vector;
+		current_offset = offset;
+		if (cfg->vector) {
+			cpumask_copy(cfg->old_domain, cfg->domain);
+			cfg->move_in_progress =
+			   cpumask_intersects(cfg->old_domain, cpu_online_mask);
+		}
+		for_each_cpu_and(new_cpu, tmp_mask, cpu_online_mask)
+			per_cpu(vector_irq, new_cpu)[vector] = irq;
+		cfg->vector = vector;
+		cpumask_copy(cfg->domain, tmp_mask);
+		err = 0;
+		break;
+	}
+	free_cpumask_var(tmp_mask);
+
+	return err;
+}
+
+int assign_irq_vector(int irq, struct irq_cfg *cfg, const struct cpumask *mask)
+{
+	int err;
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&vector_lock, flags);
+	err = __assign_irq_vector(irq, cfg, mask);
+	raw_spin_unlock_irqrestore(&vector_lock, flags);
+	return err;
+}
+
+void clear_irq_vector(int irq, struct irq_cfg *cfg)
+{
+	int cpu, vector;
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&vector_lock, flags);
+	BUG_ON(!cfg->vector);
+
+	vector = cfg->vector;
+	for_each_cpu_and(cpu, cfg->domain, cpu_online_mask)
+		per_cpu(vector_irq, cpu)[vector] = VECTOR_UNDEFINED;
+
+	cfg->vector = 0;
+	cpumask_clear(cfg->domain);
+
+	if (likely(!cfg->move_in_progress)) {
+		raw_spin_unlock_irqrestore(&vector_lock, flags);
+		return;
+	}
+
+	for_each_cpu_and(cpu, cfg->old_domain, cpu_online_mask) {
+		for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS;
+		     vector++) {
+			if (per_cpu(vector_irq, cpu)[vector] != irq)
+				continue;
+			per_cpu(vector_irq, cpu)[vector] = VECTOR_UNDEFINED;
+			break;
+		}
+	}
+	cfg->move_in_progress = 0;
+	raw_spin_unlock_irqrestore(&vector_lock, flags);
+}
+
+int __init arch_probe_nr_irqs(void)
+{
+	int nr;
+
+	if (nr_irqs > (NR_VECTORS * nr_cpu_ids))
+		nr_irqs = NR_VECTORS * nr_cpu_ids;
+
+	nr = (gsi_top + nr_legacy_irqs()) + 8 * nr_cpu_ids;
+#if defined(CONFIG_PCI_MSI) || defined(CONFIG_HT_IRQ)
+	/*
+	 * for MSI and HT dyn irq
+	 */
+	if (gsi_top <= NR_IRQS_LEGACY)
+		nr +=  8 * nr_cpu_ids;
+	else
+		nr += gsi_top * 16;
+#endif
+	if (nr < nr_irqs)
+		nr_irqs = nr;
+
+	return nr_legacy_irqs();
+}
+
+int __init arch_early_irq_init(void)
+{
+	return arch_early_ioapic_init();
+}
+
+static void __setup_vector_irq(int cpu)
+{
+	/* Initialize vector_irq on a new cpu */
+	int irq, vector;
+	struct irq_cfg *cfg;
+
+	/*
+	 * vector_lock will make sure that we don't run into irq vector
+	 * assignments that might be happening on another cpu in parallel,
+	 * while we setup our initial vector to irq mappings.
+	 */
+	raw_spin_lock(&vector_lock);
+	/* Mark the inuse vectors */
+	for_each_active_irq(irq) {
+		cfg = irq_cfg(irq);
+		if (!cfg)
+			continue;
+
+		if (!cpumask_test_cpu(cpu, cfg->domain))
+			continue;
+		vector = cfg->vector;
+		per_cpu(vector_irq, cpu)[vector] = irq;
+	}
+	/* Mark the free vectors */
+	for (vector = 0; vector < NR_VECTORS; ++vector) {
+		irq = per_cpu(vector_irq, cpu)[vector];
+		if (irq <= VECTOR_UNDEFINED)
+			continue;
+
+		cfg = irq_cfg(irq);
+		if (!cpumask_test_cpu(cpu, cfg->domain))
+			per_cpu(vector_irq, cpu)[vector] = VECTOR_UNDEFINED;
+	}
+	raw_spin_unlock(&vector_lock);
+}
+
+/*
+ * Setup the vector to irq mappings.
+ */
+void setup_vector_irq(int cpu)
+{
+	int irq;
+
+	/*
+	 * On most of the platforms, legacy PIC delivers the interrupts on the
+	 * boot cpu. But there are certain platforms where PIC interrupts are
+	 * delivered to multiple cpu's. If the legacy IRQ is handled by the
+	 * legacy PIC, for the new cpu that is coming online, setup the static
+	 * legacy vector to irq mapping:
+	 */
+	for (irq = 0; irq < nr_legacy_irqs(); irq++)
+		per_cpu(vector_irq, cpu)[IRQ0_VECTOR + irq] = irq;
+
+	__setup_vector_irq(cpu);
+}
+
+int apic_retrigger_irq(struct irq_data *data)
+{
+	struct irq_cfg *cfg = irqd_cfg(data);
+	unsigned long flags;
+	int cpu;
+
+	raw_spin_lock_irqsave(&vector_lock, flags);
+	cpu = cpumask_first_and(cfg->domain, cpu_online_mask);
+	apic->send_IPI_mask(cpumask_of(cpu), cfg->vector);
+	raw_spin_unlock_irqrestore(&vector_lock, flags);
+
+	return 1;
+}
+
+void apic_ack_edge(struct irq_data *data)
+{
+	irq_complete_move(irqd_cfg(data));
+	irq_move_irq(data);
+	ack_APIC_irq();
+}
+
+/*
+ * Either sets data->affinity to a valid value, and returns
+ * ->cpu_mask_to_apicid of that in dest_id, or returns -1 and
+ * leaves data->affinity untouched.
+ */
+int apic_set_affinity(struct irq_data *data, const struct cpumask *mask,
+		      unsigned int *dest_id)
+{
+	struct irq_cfg *cfg = irqd_cfg(data);
+	unsigned int irq = data->irq;
+	int err;
+
+	if (!config_enabled(CONFIG_SMP))
+		return -EPERM;
+
+	if (!cpumask_intersects(mask, cpu_online_mask))
+		return -EINVAL;
+
+	err = assign_irq_vector(irq, cfg, mask);
+	if (err)
+		return err;
+
+	err = apic->cpu_mask_to_apicid_and(mask, cfg->domain, dest_id);
+	if (err) {
+		if (assign_irq_vector(irq, cfg, data->affinity))
+			pr_err("Failed to recover vector for irq %d\n", irq);
+		return err;
+	}
+
+	cpumask_copy(data->affinity, mask);
+
+	return 0;
+}
+
+#ifdef CONFIG_SMP
+void send_cleanup_vector(struct irq_cfg *cfg)
+{
+	cpumask_var_t cleanup_mask;
+
+	if (unlikely(!alloc_cpumask_var(&cleanup_mask, GFP_ATOMIC))) {
+		unsigned int i;
+
+		for_each_cpu_and(i, cfg->old_domain, cpu_online_mask)
+			apic->send_IPI_mask(cpumask_of(i),
+					    IRQ_MOVE_CLEANUP_VECTOR);
+	} else {
+		cpumask_and(cleanup_mask, cfg->old_domain, cpu_online_mask);
+		apic->send_IPI_mask(cleanup_mask, IRQ_MOVE_CLEANUP_VECTOR);
+		free_cpumask_var(cleanup_mask);
+	}
+	cfg->move_in_progress = 0;
+}
+
+asmlinkage __visible void smp_irq_move_cleanup_interrupt(void)
+{
+	unsigned vector, me;
+
+	ack_APIC_irq();
+	irq_enter();
+	exit_idle();
+
+	me = smp_processor_id();
+	for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) {
+		int irq;
+		unsigned int irr;
+		struct irq_desc *desc;
+		struct irq_cfg *cfg;
+
+		irq = __this_cpu_read(vector_irq[vector]);
+
+		if (irq <= VECTOR_UNDEFINED)
+			continue;
+
+		desc = irq_to_desc(irq);
+		if (!desc)
+			continue;
+
+		cfg = irq_cfg(irq);
+		if (!cfg)
+			continue;
+
+		raw_spin_lock(&desc->lock);
+
+		/*
+		 * Check if the irq migration is in progress. If so, we
+		 * haven't received the cleanup request yet for this irq.
+		 */
+		if (cfg->move_in_progress)
+			goto unlock;
+
+		if (vector == cfg->vector && cpumask_test_cpu(me, cfg->domain))
+			goto unlock;
+
+		irr = apic_read(APIC_IRR + (vector / 32 * 0x10));
+		/*
+		 * Check if the vector that needs to be cleanedup is
+		 * registered at the cpu's IRR. If so, then this is not
+		 * the best time to clean it up. Lets clean it up in the
+		 * next attempt by sending another IRQ_MOVE_CLEANUP_VECTOR
+		 * to myself.
+		 */
+		if (irr  & (1 << (vector % 32))) {
+			apic->send_IPI_self(IRQ_MOVE_CLEANUP_VECTOR);
+			goto unlock;
+		}
+		__this_cpu_write(vector_irq[vector], VECTOR_UNDEFINED);
+unlock:
+		raw_spin_unlock(&desc->lock);
+	}
+
+	irq_exit();
+}
+
+static void __irq_complete_move(struct irq_cfg *cfg, unsigned vector)
+{
+	unsigned me;
+
+	if (likely(!cfg->move_in_progress))
+		return;
+
+	me = smp_processor_id();
+
+	if (vector == cfg->vector && cpumask_test_cpu(me, cfg->domain))
+		send_cleanup_vector(cfg);
+}
+
+void irq_complete_move(struct irq_cfg *cfg)
+{
+	__irq_complete_move(cfg, ~get_irq_regs()->orig_ax);
+}
+
+void irq_force_complete_move(int irq)
+{
+	struct irq_cfg *cfg = irq_cfg(irq);
+
+	if (!cfg)
+		return;
+
+	__irq_complete_move(cfg, cfg->vector);
+}
+#endif
+
+/*
+ * Dynamic irq allocate and deallocation. Should be replaced by irq domains!
+ */
+int arch_setup_hwirq(unsigned int irq, int node)
+{
+	struct irq_cfg *cfg;
+	unsigned long flags;
+	int ret;
+
+	cfg = alloc_irq_cfg(irq, node);
+	if (!cfg)
+		return -ENOMEM;
+
+	raw_spin_lock_irqsave(&vector_lock, flags);
+	ret = __assign_irq_vector(irq, cfg, apic->target_cpus());
+	raw_spin_unlock_irqrestore(&vector_lock, flags);
+
+	if (!ret)
+		irq_set_chip_data(irq, cfg);
+	else
+		free_irq_cfg(irq, cfg);
+	return ret;
+}
+
+void arch_teardown_hwirq(unsigned int irq)
+{
+	struct irq_cfg *cfg = irq_cfg(irq);
+
+	free_remapped_irq(irq);
+	clear_irq_vector(irq, cfg);
+	free_irq_cfg(irq, cfg);
+}
+
+static void __init print_APIC_field(int base)
+{
+	int i;
+
+	printk(KERN_DEBUG);
+
+	for (i = 0; i < 8; i++)
+		pr_cont("%08x", apic_read(base + i*0x10));
+
+	pr_cont("\n");
+}
+
+static void __init print_local_APIC(void *dummy)
+{
+	unsigned int i, v, ver, maxlvt;
+	u64 icr;
+
+	pr_debug("printing local APIC contents on CPU#%d/%d:\n",
+		 smp_processor_id(), hard_smp_processor_id());
+	v = apic_read(APIC_ID);
+	pr_info("... APIC ID:      %08x (%01x)\n", v, read_apic_id());
+	v = apic_read(APIC_LVR);
+	pr_info("... APIC VERSION: %08x\n", v);
+	ver = GET_APIC_VERSION(v);
+	maxlvt = lapic_get_maxlvt();
+
+	v = apic_read(APIC_TASKPRI);
+	pr_debug("... APIC TASKPRI: %08x (%02x)\n", v, v & APIC_TPRI_MASK);
+
+	/* !82489DX */
+	if (APIC_INTEGRATED(ver)) {
+		if (!APIC_XAPIC(ver)) {
+			v = apic_read(APIC_ARBPRI);
+			pr_debug("... APIC ARBPRI: %08x (%02x)\n",
+				 v, v & APIC_ARBPRI_MASK);
+		}
+		v = apic_read(APIC_PROCPRI);
+		pr_debug("... APIC PROCPRI: %08x\n", v);
+	}
+
+	/*
+	 * Remote read supported only in the 82489DX and local APIC for
+	 * Pentium processors.
+	 */
+	if (!APIC_INTEGRATED(ver) || maxlvt == 3) {
+		v = apic_read(APIC_RRR);
+		pr_debug("... APIC RRR: %08x\n", v);
+	}
+
+	v = apic_read(APIC_LDR);
+	pr_debug("... APIC LDR: %08x\n", v);
+	if (!x2apic_enabled()) {
+		v = apic_read(APIC_DFR);
+		pr_debug("... APIC DFR: %08x\n", v);
+	}
+	v = apic_read(APIC_SPIV);
+	pr_debug("... APIC SPIV: %08x\n", v);
+
+	pr_debug("... APIC ISR field:\n");
+	print_APIC_field(APIC_ISR);
+	pr_debug("... APIC TMR field:\n");
+	print_APIC_field(APIC_TMR);
+	pr_debug("... APIC IRR field:\n");
+	print_APIC_field(APIC_IRR);
+
+	/* !82489DX */
+	if (APIC_INTEGRATED(ver)) {
+		/* Due to the Pentium erratum 3AP. */
+		if (maxlvt > 3)
+			apic_write(APIC_ESR, 0);
+
+		v = apic_read(APIC_ESR);
+		pr_debug("... APIC ESR: %08x\n", v);
+	}
+
+	icr = apic_icr_read();
+	pr_debug("... APIC ICR: %08x\n", (u32)icr);
+	pr_debug("... APIC ICR2: %08x\n", (u32)(icr >> 32));
+
+	v = apic_read(APIC_LVTT);
+	pr_debug("... APIC LVTT: %08x\n", v);
+
+	if (maxlvt > 3) {
+		/* PC is LVT#4. */
+		v = apic_read(APIC_LVTPC);
+		pr_debug("... APIC LVTPC: %08x\n", v);
+	}
+	v = apic_read(APIC_LVT0);
+	pr_debug("... APIC LVT0: %08x\n", v);
+	v = apic_read(APIC_LVT1);
+	pr_debug("... APIC LVT1: %08x\n", v);
+
+	if (maxlvt > 2) {
+		/* ERR is LVT#3. */
+		v = apic_read(APIC_LVTERR);
+		pr_debug("... APIC LVTERR: %08x\n", v);
+	}
+
+	v = apic_read(APIC_TMICT);
+	pr_debug("... APIC TMICT: %08x\n", v);
+	v = apic_read(APIC_TMCCT);
+	pr_debug("... APIC TMCCT: %08x\n", v);
+	v = apic_read(APIC_TDCR);
+	pr_debug("... APIC TDCR: %08x\n", v);
+
+	if (boot_cpu_has(X86_FEATURE_EXTAPIC)) {
+		v = apic_read(APIC_EFEAT);
+		maxlvt = (v >> 16) & 0xff;
+		pr_debug("... APIC EFEAT: %08x\n", v);
+		v = apic_read(APIC_ECTRL);
+		pr_debug("... APIC ECTRL: %08x\n", v);
+		for (i = 0; i < maxlvt; i++) {
+			v = apic_read(APIC_EILVTn(i));
+			pr_debug("... APIC EILVT%d: %08x\n", i, v);
+		}
+	}
+	pr_cont("\n");
+}
+
+static void __init print_local_APICs(int maxcpu)
+{
+	int cpu;
+
+	if (!maxcpu)
+		return;
+
+	preempt_disable();
+	for_each_online_cpu(cpu) {
+		if (cpu >= maxcpu)
+			break;
+		smp_call_function_single(cpu, print_local_APIC, NULL, 1);
+	}
+	preempt_enable();
+}
+
+static void __init print_PIC(void)
+{
+	unsigned int v;
+	unsigned long flags;
+
+	if (!nr_legacy_irqs())
+		return;
+
+	pr_debug("\nprinting PIC contents\n");
+
+	raw_spin_lock_irqsave(&i8259A_lock, flags);
+
+	v = inb(0xa1) << 8 | inb(0x21);
+	pr_debug("... PIC  IMR: %04x\n", v);
+
+	v = inb(0xa0) << 8 | inb(0x20);
+	pr_debug("... PIC  IRR: %04x\n", v);
+
+	outb(0x0b, 0xa0);
+	outb(0x0b, 0x20);
+	v = inb(0xa0) << 8 | inb(0x20);
+	outb(0x0a, 0xa0);
+	outb(0x0a, 0x20);
+
+	raw_spin_unlock_irqrestore(&i8259A_lock, flags);
+
+	pr_debug("... PIC  ISR: %04x\n", v);
+
+	v = inb(0x4d1) << 8 | inb(0x4d0);
+	pr_debug("... PIC ELCR: %04x\n", v);
+}
+
+static int show_lapic __initdata = 1;
+static __init int setup_show_lapic(char *arg)
+{
+	int num = -1;
+
+	if (strcmp(arg, "all") == 0) {
+		show_lapic = CONFIG_NR_CPUS;
+	} else {
+		get_option(&arg, &num);
+		if (num >= 0)
+			show_lapic = num;
+	}
+
+	return 1;
+}
+__setup("show_lapic=", setup_show_lapic);
+
+static int __init print_ICs(void)
+{
+	if (apic_verbosity == APIC_QUIET)
+		return 0;
+
+	print_PIC();
+
+	/* don't print out if apic is not there */
+	if (!cpu_has_apic && !apic_from_smp_config())
+		return 0;
+
+	print_local_APICs(show_lapic);
+	print_IO_APICs();
+
+	return 0;
+}
+
+late_initcall(print_ICs);
diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c
index f5ab56d14287..aceb2f90c716 100644
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -28,6 +28,7 @@
 #include <asm/nmi.h>
 #include <asm/hw_irq.h>
 #include <asm/apic.h>
+#include <asm/io_apic.h>
 #include <asm/hpet.h>
 #include <linux/kdebug.h>
 #include <asm/cpu.h>
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index 1cf7c97ff175..000d4199b03e 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -732,10 +732,10 @@ ENTRY(interrupt)
 ENTRY(irq_entries_start)
 	RING0_INT_FRAME
 vector=FIRST_EXTERNAL_VECTOR
-.rept (NR_VECTORS-FIRST_EXTERNAL_VECTOR+6)/7
+.rept (FIRST_SYSTEM_VECTOR-FIRST_EXTERNAL_VECTOR+6)/7
 	.balign 32
   .rept	7
-    .if vector < NR_VECTORS
+    .if vector < FIRST_SYSTEM_VECTOR
       .if vector <> FIRST_EXTERNAL_VECTOR
 	CFI_ADJUST_CFA_OFFSET -4
       .endif
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 90878aa38dbd..9ebaf63ba182 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -740,10 +740,10 @@ ENTRY(interrupt)
 ENTRY(irq_entries_start)
 	INTR_FRAME
 vector=FIRST_EXTERNAL_VECTOR
-.rept (NR_VECTORS-FIRST_EXTERNAL_VECTOR+6)/7
+.rept (FIRST_SYSTEM_VECTOR-FIRST_EXTERNAL_VECTOR+6)/7
 	.balign 32
   .rept	7
-    .if vector < NR_VECTORS
+    .if vector < FIRST_SYSTEM_VECTOR
       .if vector <> FIRST_EXTERNAL_VECTOR
 	CFI_ADJUST_CFA_OFFSET -8
       .endif
diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c
index 4de73ee78361..70e181ea1eac 100644
--- a/arch/x86/kernel/irqinit.c
+++ b/arch/x86/kernel/irqinit.c
@@ -99,32 +99,9 @@ void __init init_IRQ(void)
 	x86_init.irqs.intr_init();
 }
 
-/*
- * Setup the vector to irq mappings.
- */
-void setup_vector_irq(int cpu)
-{
-#ifndef CONFIG_X86_IO_APIC
-	int irq;
-
-	/*
-	 * On most of the platforms, legacy PIC delivers the interrupts on the
-	 * boot cpu. But there are certain platforms where PIC interrupts are
-	 * delivered to multiple cpu's. If the legacy IRQ is handled by the
-	 * legacy PIC, for the new cpu that is coming online, setup the static
-	 * legacy vector to irq mapping:
-	 */
-	for (irq = 0; irq < nr_legacy_irqs(); irq++)
-		per_cpu(vector_irq, cpu)[IRQ0_VECTOR + irq] = irq;
-#endif
-
-	__setup_vector_irq(cpu);
-}
-
 static void __init smp_intr_init(void)
 {
 #ifdef CONFIG_SMP
-#if defined(CONFIG_X86_64) || defined(CONFIG_X86_LOCAL_APIC)
 	/*
 	 * The reschedule interrupt is a CPU-to-CPU reschedule-helper
 	 * IPI, driven by wakeup.
@@ -144,7 +121,6 @@ static void __init smp_intr_init(void)
 
 	/* IPI used for rebooting/stopping */
 	alloc_intr_gate(REBOOT_VECTOR, reboot_interrupt);
-#endif
 #endif /* CONFIG_SMP */
 }
 
@@ -159,7 +135,7 @@ static void __init apic_intr_init(void)
 	alloc_intr_gate(THRESHOLD_APIC_VECTOR, threshold_interrupt);
 #endif
 
-#if defined(CONFIG_X86_64) || defined(CONFIG_X86_LOCAL_APIC)
+#ifdef CONFIG_X86_LOCAL_APIC
 	/* self generated IPI for local APIC timer */
 	alloc_intr_gate(LOCAL_TIMER_VECTOR, apic_timer_interrupt);
 
@@ -197,10 +173,17 @@ void __init native_init_IRQ(void)
 	 * 'special' SMP interrupts)
 	 */
 	i = FIRST_EXTERNAL_VECTOR;
-	for_each_clear_bit_from(i, used_vectors, NR_VECTORS) {
+#ifndef CONFIG_X86_LOCAL_APIC
+#define first_system_vector NR_VECTORS
+#endif
+	for_each_clear_bit_from(i, used_vectors, first_system_vector) {
 		/* IA32_SYSCALL_VECTOR could be used in trap_init already. */
 		set_intr_gate(i, interrupt[i - FIRST_EXTERNAL_VECTOR]);
 	}
+#ifdef CONFIG_X86_LOCAL_APIC
+	for_each_clear_bit_from(i, used_vectors, NR_VECTORS)
+		set_intr_gate(i, spurious_interrupt);
+#endif
 
 	if (!acpi_ioapic && !of_ioapic && nr_legacy_irqs())
 		setup_irq(2, &irq2);
diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c
index 72e8e310258d..469b23d6acc2 100644
--- a/arch/x86/kernel/machine_kexec_32.c
+++ b/arch/x86/kernel/machine_kexec_32.c
@@ -20,6 +20,7 @@
 #include <asm/tlbflush.h>
 #include <asm/mmu_context.h>
 #include <asm/apic.h>
+#include <asm/io_apic.h>
 #include <asm/cpufeature.h>
 #include <asm/desc.h>
 #include <asm/cacheflush.h>
diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c
index 485981059a40..415480d3ea84 100644
--- a/arch/x86/kernel/machine_kexec_64.c
+++ b/arch/x86/kernel/machine_kexec_64.c
@@ -22,6 +22,7 @@
 #include <asm/pgtable.h>
 #include <asm/tlbflush.h>
 #include <asm/mmu_context.h>
+#include <asm/io_apic.h>
 #include <asm/debugreg.h>
 #include <asm/kexec-bzimage64.h>
 
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 17962e667a91..bae6c609888e 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -12,6 +12,7 @@
 #include <acpi/reboot.h>
 #include <asm/io.h>
 #include <asm/apic.h>
+#include <asm/io_apic.h>
 #include <asm/desc.h>
 #include <asm/hpet.h>
 #include <asm/pgtable.h>
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 7a8f5845e8eb..6d7022c683e3 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -1084,7 +1084,6 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
 {
 	unsigned int i;
 
-	preempt_disable();
 	smp_cpu_index_default();
 
 	/*
@@ -1102,22 +1101,19 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
 	}
 	set_cpu_sibling_map(0);
 
-
 	if (smp_sanity_check(max_cpus) < 0) {
 		pr_info("SMP disabled\n");
 		disable_smp();
-		goto out;
+		return;
 	}
 
 	default_setup_apic_routing();
 
-	preempt_disable();
 	if (read_apic_id() != boot_cpu_physical_apicid) {
 		panic("Boot APIC ID in local APIC unexpected (%d vs %d)",
 		     read_apic_id(), boot_cpu_physical_apicid);
 		/* Or can we switch back to PIC here? */
 	}
-	preempt_enable();
 
 	connect_bsp_APIC();
 
@@ -1151,8 +1147,6 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
 		uv_system_init();
 
 	set_mtrr_aps_delayed_init();
-out:
-	preempt_enable();
 }
 
 void arch_enable_nonboot_cpus_begin(void)
diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c
index aae94132bc24..c1c1544b8485 100644
--- a/arch/x86/lguest/boot.c
+++ b/arch/x86/lguest/boot.c
@@ -841,7 +841,7 @@ static void __init lguest_init_IRQ(void)
 {
 	unsigned int i;
 
-	for (i = FIRST_EXTERNAL_VECTOR; i < NR_VECTORS; i++) {
+	for (i = FIRST_EXTERNAL_VECTOR; i < FIRST_SYSTEM_VECTOR; i++) {
 		/* Some systems map "vectors" to interrupts weirdly.  Not us! */
 		__this_cpu_write(vector_irq[i], i - FIRST_EXTERNAL_VECTOR);
 		if (i != SYSCALL_VECTOR)
diff --git a/arch/x86/pci/intel_mid_pci.c b/arch/x86/pci/intel_mid_pci.c
index b9958c364075..44b9271580b5 100644
--- a/arch/x86/pci/intel_mid_pci.c
+++ b/arch/x86/pci/intel_mid_pci.c
@@ -210,6 +210,9 @@ static int intel_mid_pci_irq_enable(struct pci_dev *dev)
 {
 	int polarity;
 
+	if (dev->irq_managed && dev->irq > 0)
+		return 0;
+
 	if (intel_mid_identify_cpu() == INTEL_MID_CPU_CHIP_TANGIER)
 		polarity = 0; /* active high */
 	else
@@ -224,13 +227,18 @@ static int intel_mid_pci_irq_enable(struct pci_dev *dev)
 	if (mp_map_gsi_to_irq(dev->irq, IOAPIC_MAP_ALLOC) < 0)
 		return -EBUSY;
 
+	dev->irq_managed = 1;
+
 	return 0;
 }
 
 static void intel_mid_pci_irq_disable(struct pci_dev *dev)
 {
-	if (!mp_should_keep_irq(&dev->dev) && dev->irq > 0)
+	if (!mp_should_keep_irq(&dev->dev) && dev->irq_managed &&
+	    dev->irq > 0) {
 		mp_unmap_irq(dev->irq);
+		dev->irq_managed = 0;
+	}
 }
 
 struct pci_ops intel_mid_pci_ops = {
diff --git a/arch/x86/pci/irq.c b/arch/x86/pci/irq.c
index eb500c2592ad..5dc6ca5e1741 100644
--- a/arch/x86/pci/irq.c
+++ b/arch/x86/pci/irq.c
@@ -1200,11 +1200,12 @@ static int pirq_enable_irq(struct pci_dev *dev)
 #ifdef CONFIG_X86_IO_APIC
 			struct pci_dev *temp_dev;
 			int irq;
-			struct io_apic_irq_attr irq_attr;
+
+			if (dev->irq_managed && dev->irq > 0)
+				return 0;
 
 			irq = IO_APIC_get_PCI_irq_vector(dev->bus->number,
-						PCI_SLOT(dev->devfn),
-						pin - 1, &irq_attr);
+						PCI_SLOT(dev->devfn), pin - 1);
 			/*
 			 * Busses behind bridges are typically not listed in the MP-table.
 			 * In this case we have to look up the IRQ based on the parent bus,
@@ -1218,7 +1219,7 @@ static int pirq_enable_irq(struct pci_dev *dev)
 				pin = pci_swizzle_interrupt_pin(dev, pin);
 				irq = IO_APIC_get_PCI_irq_vector(bridge->bus->number,
 						PCI_SLOT(bridge->devfn),
-						pin - 1, &irq_attr);
+						pin - 1);
 				if (irq >= 0)
 					dev_warn(&dev->dev, "using bridge %s "
 						 "INT %c to get IRQ %d\n",
@@ -1228,6 +1229,7 @@ static int pirq_enable_irq(struct pci_dev *dev)
 			}
 			dev = temp_dev;
 			if (irq >= 0) {
+				dev->irq_managed = 1;
 				dev->irq = irq;
 				dev_info(&dev->dev, "PCI->APIC IRQ transform: "
 					 "INT %c -> IRQ %d\n", 'A' + pin - 1, irq);
@@ -1254,11 +1256,24 @@ static int pirq_enable_irq(struct pci_dev *dev)
 	return 0;
 }
 
+bool mp_should_keep_irq(struct device *dev)
+{
+	if (dev->power.is_prepared)
+		return true;
+#ifdef CONFIG_PM
+	if (dev->power.runtime_status == RPM_SUSPENDING)
+		return true;
+#endif
+
+	return false;
+}
+
 static void pirq_disable_irq(struct pci_dev *dev)
 {
 	if (io_apic_assign_pci_irqs && !mp_should_keep_irq(&dev->dev) &&
-	    dev->irq) {
+	    dev->irq_managed && dev->irq) {
 		mp_unmap_irq(dev->irq);
 		dev->irq = 0;
+		dev->irq_managed = 0;
 	}
 }
diff --git a/arch/x86/platform/uv/uv_irq.c b/arch/x86/platform/uv/uv_irq.c
index b233681af4de..0ce673645432 100644
--- a/arch/x86/platform/uv/uv_irq.c
+++ b/arch/x86/platform/uv/uv_irq.c
@@ -131,7 +131,7 @@ 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_get_chip_data(irq);
+	struct irq_cfg *cfg = irq_cfg(irq);
 	unsigned long mmr_value;
 	struct uv_IO_APIC_route_entry *entry;
 	int mmr_pnode, err;
@@ -198,13 +198,13 @@ static int
 uv_set_irq_affinity(struct irq_data *data, const struct cpumask *mask,
 		    bool force)
 {
-	struct irq_cfg *cfg = data->chip_data;
+	struct irq_cfg *cfg = irqd_cfg(data);
 	unsigned int dest;
 	unsigned long mmr_value, mmr_offset;
 	struct uv_IO_APIC_route_entry *entry;
 	int mmr_pnode;
 
-	if (__ioapic_set_affinity(data, mask, &dest))
+	if (apic_set_affinity(data, mask, &dest))
 		return -1;
 
 	mmr_value = 0;
author	Linus Torvalds <torvalds@linux-foundation.org>	2014-12-19 14:02:02 -0800
committer	Linus Torvalds <torvalds@linux-foundation.org>	2014-12-19 14:02:02 -0800
commit	e589c9e13aeb0c5539bf1314b3a78442ea8fc0c2 (patch)
tree	87aaebb0ef7c4cc7ee6cffc152a9264b24659b7e /arch
parent	Merge branch 'timers-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip (diff)
parent	iommu/amd: Use helpers to access irq_cfg data structure associated with IRQ (diff)
download	linux-dev-e589c9e13aeb0c5539bf1314b3a78442ea8fc0c2.tar.xz linux-dev-e589c9e13aeb0c5539bf1314b3a78442ea8fc0c2.zip