Merge commit 'konrad/stable/xen-pcifront-0.8.2' into 2.6.36-rc8-initial-domain-v6

46 files changed, 851 insertions, 874 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index cea0cd9a316..74ea59d3407 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -59,6 +59,10 @@ config X86
 	select ANON_INODES
 	select HAVE_ARCH_KMEMCHECK
 	select HAVE_USER_RETURN_NOTIFIER
+	select HAVE_GENERIC_HARDIRQS
+	select HAVE_SPARSE_IRQ
+	select GENERIC_IRQ_PROBE
+	select GENERIC_PENDING_IRQ if SMP
 
 config INSTRUCTION_DECODER
 	def_bool (KPROBES || PERF_EVENTS)
@@ -200,20 +204,6 @@ config HAVE_INTEL_TXT
 	def_bool y
 	depends on EXPERIMENTAL && DMAR && ACPI
 
-# Use the generic interrupt handling code in kernel/irq/:
-config GENERIC_HARDIRQS
-	def_bool y
-
-config GENERIC_HARDIRQS_NO__DO_IRQ
-       def_bool y
-
-config GENERIC_IRQ_PROBE
-	def_bool y
-
-config GENERIC_PENDING_IRQ
-	def_bool y
-	depends on GENERIC_HARDIRQS && SMP
-
 config USE_GENERIC_SMP_HELPERS
 	def_bool y
 	depends on SMP
@@ -296,23 +286,6 @@ config X86_X2APIC
 
 	  If you don't know what to do here, say N.
 
-config SPARSE_IRQ
-	bool "Support sparse irq numbering"
-	depends on PCI_MSI || HT_IRQ
-	---help---
-	  This enables support for sparse irqs. This is useful for distro
-	  kernels that want to define a high CONFIG_NR_CPUS value but still
-	  want to have low kernel memory footprint on smaller machines.
-
-	  ( Sparse IRQs can also be beneficial on NUMA boxes, as they spread
-	    out the irq_desc[] array in a more NUMA-friendly way. )
-
-	  If you don't know what to do here, say N.
-
-config NUMA_IRQ_DESC
-	def_bool y
-	depends on SPARSE_IRQ && NUMA
-
 config X86_MPPARSE
 	bool "Enable MPS table" if ACPI
 	default y
@@ -1925,6 +1898,11 @@ config PCI_OLPC
 	def_bool y
 	depends on PCI && OLPC && (PCI_GOOLPC || PCI_GOANY)
 
+config PCI_XEN
+	def_bool y
+	depends on PCI && XEN
+	select SWIOTLB_XEN
+
 config PCI_DOMAINS
 	def_bool y
 	depends on PCI
diff --git a/arch/x86/include/asm/apb_timer.h b/arch/x86/include/asm/apb_timer.h
index a69b1ac9eaf..2fefa501d3b 100644
--- a/arch/x86/include/asm/apb_timer.h
+++ b/arch/x86/include/asm/apb_timer.h
@@ -54,7 +54,6 @@ extern struct clock_event_device *global_clock_event;
 extern unsigned long apbt_quick_calibrate(void);
 extern int arch_setup_apbt_irqs(int irq, int trigger, int mask, int cpu);
 extern void apbt_setup_secondary_clock(void);
-extern unsigned int boot_cpu_id;
 
 extern struct sfi_timer_table_entry *sfi_get_mtmr(int hint);
 extern void sfi_free_mtmr(struct sfi_timer_table_entry *mtmr);
diff --git a/arch/x86/include/asm/cpu.h b/arch/x86/include/asm/cpu.h
index b185091bf19..4fab24de26b 100644
--- a/arch/x86/include/asm/cpu.h
+++ b/arch/x86/include/asm/cpu.h
@@ -32,6 +32,5 @@ extern void arch_unregister_cpu(int);
 
 DECLARE_PER_CPU(int, cpu_state);
 
-extern unsigned int boot_cpu_id;
 
 #endif /* _ASM_X86_CPU_H */
diff --git a/arch/x86/include/asm/hpet.h b/arch/x86/include/asm/hpet.h
index 1d5c08a1bdf..2c392d663dc 100644
--- a/arch/x86/include/asm/hpet.h
+++ b/arch/x86/include/asm/hpet.h
@@ -74,10 +74,12 @@ extern void hpet_disable(void);
 extern unsigned int hpet_readl(unsigned int a);
 extern void force_hpet_resume(void);
 
-extern void hpet_msi_unmask(unsigned int irq);
-extern void hpet_msi_mask(unsigned int irq);
-extern void hpet_msi_write(unsigned int irq, struct msi_msg *msg);
-extern void hpet_msi_read(unsigned int irq, struct msi_msg *msg);
+struct irq_data;
+extern void hpet_msi_unmask(struct irq_data *data);
+extern void hpet_msi_mask(struct irq_data *data);
+struct hpet_dev;
+extern void hpet_msi_write(struct hpet_dev *hdev, struct msi_msg *msg);
+extern void hpet_msi_read(struct hpet_dev *hdev, struct msi_msg *msg);
 
 #ifdef CONFIG_PCI_MSI
 extern int arch_setup_hpet_msi(unsigned int irq, unsigned int id);
diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h
index 46c0fe05f23..d5905fd8ba4 100644
--- a/arch/x86/include/asm/hw_irq.h
+++ b/arch/x86/include/asm/hw_irq.h
@@ -78,6 +78,13 @@ static inline void set_io_apic_irq_attr(struct io_apic_irq_attr *irq_attr,
 	irq_attr->polarity	= polarity;
 }
 
+struct irq_2_iommu {
+	struct intel_iommu *iommu;
+	u16 irte_index;
+	u16 sub_handle;
+	u8  irte_mask;
+};
+
 /*
  * This is performance-critical, we want to do it O(1)
  *
@@ -89,15 +96,17 @@ struct irq_cfg {
 	cpumask_var_t		old_domain;
 	u8			vector;
 	u8			move_in_progress : 1;
+#ifdef CONFIG_INTR_REMAP
+	struct irq_2_iommu	irq_2_iommu;
+#endif
 };
 
-extern struct irq_cfg *irq_cfg(unsigned int);
 extern int assign_irq_vector(int, struct irq_cfg *, const struct cpumask *);
 extern void send_cleanup_vector(struct irq_cfg *);
 
-struct irq_desc;
-extern unsigned int set_desc_affinity(struct irq_desc *, const struct cpumask *,
-				      unsigned int *dest_id);
+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);
 
diff --git a/arch/x86/include/asm/i8259.h b/arch/x86/include/asm/i8259.h
index 1655147646a..a20365953bf 100644
--- a/arch/x86/include/asm/i8259.h
+++ b/arch/x86/include/asm/i8259.h
@@ -55,6 +55,8 @@ extern struct irq_chip i8259A_chip;
 struct legacy_pic {
 	int nr_legacy_irqs;
 	struct irq_chip *chip;
+	void (*mask)(unsigned int irq);
+	void (*unmask)(unsigned int irq);
 	void (*mask_all)(void);
 	void (*restore_mask)(void);
 	void (*init)(int auto_eoi);
diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h
index 30a3e977612..0ad29d40156 100644
--- a/arch/x86/include/asm/io.h
+++ b/arch/x86/include/asm/io.h
@@ -41,6 +41,8 @@
 #include <asm-generic/int-ll64.h>
 #include <asm/page.h>
 
+#include <xen/xen.h>
+
 #define build_mmio_read(name, size, type, reg, barrier) \
 static inline type name(const volatile void __iomem *addr) \
 { type ret; asm volatile("mov" size " %1,%0":reg (ret) \
@@ -349,6 +351,17 @@ extern void __iomem *early_memremap(resource_size_t phys_addr,
 extern void early_iounmap(void __iomem *addr, unsigned long size);
 extern void fixup_early_ioremap(void);
 
+#ifdef CONFIG_XEN
+struct bio_vec;
+
+extern bool xen_biovec_phys_mergeable(const struct bio_vec *vec1,
+				      const struct bio_vec *vec2);
+
+#define BIOVEC_PHYS_MERGEABLE(vec1, vec2)				\
+	(__BIOVEC_PHYS_MERGEABLE(vec1, vec2) &&				\
+	 (!xen_domain() || xen_biovec_phys_mergeable(vec1, vec2)))
+#endif	/* CONFIG_XEN */
+
 #define IO_SPACE_LIMIT 0xffff
 
 #endif /* _ASM_X86_IO_H */
diff --git a/arch/x86/include/asm/io_apic.h b/arch/x86/include/asm/io_apic.h
index 9cb2edb87c2..a6b28d017c2 100644
--- a/arch/x86/include/asm/io_apic.h
+++ b/arch/x86/include/asm/io_apic.h
@@ -169,13 +169,8 @@ extern void mask_IO_APIC_setup(struct IO_APIC_route_entry **ioapic_entries);
 extern int restore_IO_APIC_setup(struct IO_APIC_route_entry **ioapic_entries);
 
 extern void probe_nr_irqs_gsi(void);
+extern int get_nr_irqs_gsi(void);
 
-extern int setup_ioapic_entry(int apic, int irq,
-			      struct IO_APIC_route_entry *entry,
-			      unsigned int destination, int trigger,
-			      int polarity, int vector, int pin);
-extern void ioapic_write_entry(int apic, int pin,
-			       struct IO_APIC_route_entry e);
 extern void setup_ioapic_ids_from_mpc(void);
 
 struct mp_ioapic_gsi{
diff --git a/arch/x86/include/asm/irq_remapping.h b/arch/x86/include/asm/irq_remapping.h
index f275e224450..1c23360fb2d 100644
--- a/arch/x86/include/asm/irq_remapping.h
+++ b/arch/x86/include/asm/irq_remapping.h
@@ -3,4 +3,39 @@
 
 #define IRTE_DEST(dest) ((x2apic_mode) ? dest : dest << 8)
 
+#ifdef CONFIG_INTR_REMAP
+static inline void prepare_irte(struct irte *irte, int vector,
+			        unsigned int dest)
+{
+	memset(irte, 0, sizeof(*irte));
+
+	irte->present = 1;
+	irte->dst_mode = apic->irq_dest_mode;
+	/*
+	 * Trigger mode in the IRTE will always be edge, and for IO-APIC, the
+	 * actual level or edge trigger will be setup in the IO-APIC
+	 * RTE. This will help simplify level triggered irq migration.
+	 * For more details, see the comments (in io_apic.c) explainig IO-APIC
+	 * irq migration in the presence of interrupt-remapping.
+	*/
+	irte->trigger_mode = 0;
+	irte->dlvry_mode = apic->irq_delivery_mode;
+	irte->vector = vector;
+	irte->dest_id = IRTE_DEST(dest);
+	irte->redir_hint = 1;
+}
+static inline bool irq_remapped(struct irq_cfg *cfg)
+{
+	return cfg->irq_2_iommu.iommu != NULL;
+}
+#else
+static void prepare_irte(struct irte *irte, int vector, unsigned int dest)
+{
+}
+static inline bool irq_remapped(struct irq_cfg *cfg)
+{
+	return false;
+}
+#endif
+
 #endif	/* _ASM_X86_IRQ_REMAPPING_H */
diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h
index d395540ff89..ca0437c714b 100644
--- a/arch/x86/include/asm/pci.h
+++ b/arch/x86/include/asm/pci.h
@@ -7,6 +7,7 @@
 #include <linux/string.h>
 #include <asm/scatterlist.h>
 #include <asm/io.h>
+#include <asm/x86_init.h>
 
 #ifdef __KERNEL__
 
@@ -94,8 +95,36 @@ static inline void early_quirks(void) { }
 
 extern void pci_iommu_alloc(void);
 
-/* MSI arch hook */
-#define arch_setup_msi_irqs arch_setup_msi_irqs
+#ifdef CONFIG_PCI_MSI
+/* MSI arch specific hooks */
+static inline int x86_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
+{
+	return x86_msi.setup_msi_irqs(dev, nvec, type);
+}
+
+static inline void x86_teardown_msi_irqs(struct pci_dev *dev)
+{
+	x86_msi.teardown_msi_irqs(dev);
+}
+
+static inline void x86_teardown_msi_irq(unsigned int irq)
+{
+	x86_msi.teardown_msi_irq(irq);
+}
+#define arch_setup_msi_irqs x86_setup_msi_irqs
+#define arch_teardown_msi_irqs x86_teardown_msi_irqs
+#define arch_teardown_msi_irq x86_teardown_msi_irq
+/* implemented in arch/x86/kernel/apic/io_apic. */
+int native_setup_msi_irqs(struct pci_dev *dev, int nvec, int type);
+void native_teardown_msi_irq(unsigned int irq);
+/* default to the implementation in drivers/lib/msi.c */
+#define HAVE_DEFAULT_MSI_TEARDOWN_IRQS
+void default_teardown_msi_irqs(struct pci_dev *dev);
+#else
+#define native_setup_msi_irqs		NULL
+#define native_teardown_msi_irq		NULL
+#define default_teardown_msi_irqs	NULL
+#endif
 
 #define PCI_DMA_BUS_IS_PHYS (dma_ops->is_phys)
 
diff --git a/arch/x86/include/asm/pci_x86.h b/arch/x86/include/asm/pci_x86.h
index 49c7219826f..704526734be 100644
--- a/arch/x86/include/asm/pci_x86.h
+++ b/arch/x86/include/asm/pci_x86.h
@@ -47,6 +47,7 @@ enum pci_bf_sort_state {
 extern unsigned int pcibios_max_latency;
 
 void pcibios_resource_survey(void);
+void pcibios_set_cache_line_size(void);
 
 /* pci-pc.c */
 
diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h
index baa579c8e03..64642ad019f 100644
--- a/arch/x86/include/asm/x86_init.h
+++ b/arch/x86/include/asm/x86_init.h
@@ -154,9 +154,18 @@ struct x86_platform_ops {
 	int (*i8042_detect)(void);
 };
 
+struct pci_dev;
+
+struct x86_msi_ops {
+	int (*setup_msi_irqs)(struct pci_dev *dev, int nvec, int type);
+	void (*teardown_msi_irq)(unsigned int irq);
+	void (*teardown_msi_irqs)(struct pci_dev *dev);
+};
+
 extern struct x86_init_ops x86_init;
 extern struct x86_cpuinit_ops x86_cpuinit;
 extern struct x86_platform_ops x86_platform;
+extern struct x86_msi_ops x86_msi;
 
 extern void x86_init_noop(void);
 extern void x86_init_uint_noop(unsigned int unused);
diff --git a/arch/x86/include/asm/xen/pci.h b/arch/x86/include/asm/xen/pci.h
new file mode 100644
index 00000000000..449c82f7167
--- /dev/null
+++ b/arch/x86/include/asm/xen/pci.h
@@ -0,0 +1,53 @@
+#ifndef _ASM_X86_XEN_PCI_H
+#define _ASM_X86_XEN_PCI_H
+
+#if defined(CONFIG_PCI_XEN)
+extern int __init pci_xen_init(void);
+#define pci_xen 1
+#else
+#define pci_xen 0
+#define pci_xen_init (0)
+#endif
+
+#if defined(CONFIG_PCI_MSI)
+#if defined(CONFIG_PCI_XEN)
+/* The drivers/pci/xen-pcifront.c sets this structure to
+ * its own functions.
+ */
+struct xen_pci_frontend_ops {
+	int (*enable_msi)(struct pci_dev *dev, int **vectors);
+	void (*disable_msi)(struct pci_dev *dev);
+	int (*enable_msix)(struct pci_dev *dev, int **vectors, int nvec);
+	void (*disable_msix)(struct pci_dev *dev);
+};
+
+extern struct xen_pci_frontend_ops *xen_pci_frontend;
+
+static inline int xen_pci_frontend_enable_msi(struct pci_dev *dev,
+					      int **vectors)
+{
+	if (xen_pci_frontend && xen_pci_frontend->enable_msi)
+		return xen_pci_frontend->enable_msi(dev, vectors);
+	return -ENODEV;
+}
+static inline void xen_pci_frontend_disable_msi(struct pci_dev *dev)
+{
+	if (xen_pci_frontend && xen_pci_frontend->disable_msi)
+			xen_pci_frontend->disable_msi(dev);
+}
+static inline int xen_pci_frontend_enable_msix(struct pci_dev *dev,
+					       int **vectors, int nvec)
+{
+	if (xen_pci_frontend && xen_pci_frontend->enable_msix)
+		return xen_pci_frontend->enable_msix(dev, vectors, nvec);
+	return -ENODEV;
+}
+static inline void xen_pci_frontend_disable_msix(struct pci_dev *dev)
+{
+	if (xen_pci_frontend && xen_pci_frontend->disable_msix)
+			xen_pci_frontend->disable_msix(dev);
+}
+#endif /* CONFIG_PCI_XEN */
+#endif /* CONFIG_PCI_MSI */
+
+#endif	/* _ASM_X86_XEN_PCI_H */
diff --git a/arch/x86/kernel/apb_timer.c b/arch/x86/kernel/apb_timer.c
index 8dd77800ff5..42a70a2accc 100644
--- a/arch/x86/kernel/apb_timer.c
+++ b/arch/x86/kernel/apb_timer.c
@@ -231,34 +231,6 @@ static void apbt_restart_clocksource(struct clocksource *cs)
 	apbt_start_counter(phy_cs_timer_id);
 }
 
-/* Setup IRQ routing via IOAPIC */
-#ifdef CONFIG_SMP
-static void apbt_setup_irq(struct apbt_dev *adev)
-{
-	struct irq_chip *chip;
-	struct irq_desc *desc;
-
-	/* timer0 irq has been setup early */
-	if (adev->irq == 0)
-		return;
-	desc = irq_to_desc(adev->irq);
-	chip = get_irq_chip(adev->irq);
-	disable_irq(adev->irq);
-	desc->status |= IRQ_MOVE_PCNTXT;
-	irq_set_affinity(adev->irq, cpumask_of(adev->cpu));
-	/* APB timer irqs are set up as mp_irqs, timer is edge triggerred */
-	set_irq_chip_and_handler_name(adev->irq, chip, handle_edge_irq, "edge");
-	enable_irq(adev->irq);
-	if (system_state == SYSTEM_BOOTING)
-		if (request_irq(adev->irq, apbt_interrupt_handler,
-				IRQF_TIMER | IRQF_DISABLED | IRQF_NOBALANCING,
-				adev->name, adev)) {
-			printk(KERN_ERR "Failed request IRQ for APBT%d\n",
-			       adev->num);
-		}
-}
-#endif
-
 static void apbt_enable_int(int n)
 {
 	unsigned long ctrl = apbt_readl(n, APBTMR_N_CONTROL);
@@ -334,6 +306,27 @@ static int __init apbt_clockevent_register(void)
 }
 
 #ifdef CONFIG_SMP
+
+static void apbt_setup_irq(struct apbt_dev *adev)
+{
+	/* timer0 irq has been setup early */
+	if (adev->irq == 0)
+		return;
+
+	if (system_state == SYSTEM_BOOTING) {
+		irq_modify_status(adev->irq, 0, IRQ_MOVE_PCNTXT);
+		/* APB timer irqs are set up as mp_irqs, timer is edge type */
+		__set_irq_handler(adev->irq, handle_edge_irq, 0, "edge");
+		if (request_irq(adev->irq, apbt_interrupt_handler,
+				IRQF_TIMER | IRQF_DISABLED | IRQF_NOBALANCING,
+				adev->name, adev)) {
+			printk(KERN_ERR "Failed request IRQ for APBT%d\n",
+			       adev->num);
+		}
+	} else
+		enable_irq(adev->irq);
+}
+
 /* Should be called with per cpu */
 void apbt_setup_secondary_clock(void)
 {
@@ -343,7 +336,7 @@ void apbt_setup_secondary_clock(void)
 
 	/* Don't register boot CPU clockevent */
 	cpu = smp_processor_id();
-	if (cpu == boot_cpu_id)
+	if (!cpu)
 		return;
 	/*
 	 * We need to calculate the scaled math multiplication factor for
@@ -389,10 +382,11 @@ static int apbt_cpuhp_notify(struct notifier_block *n,
 
 	switch (action & 0xf) {
 	case CPU_DEAD:
+		disable_irq(adev->irq);
 		apbt_disable_int(cpu);
-		if (system_state == SYSTEM_RUNNING)
+		if (system_state == SYSTEM_RUNNING) {
 			pr_debug("skipping APBT CPU %lu offline\n", cpu);
-		else if (adev) {
+		} else if (adev) {
 			pr_debug("APBT clockevent for cpu %lu offline\n", cpu);
 			free_irq(adev->irq, adev);
 		}
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index e3b534cda49..8cf86fb3b4e 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -1665,10 +1665,7 @@ int __init APIC_init_uniprocessor(void)
 	}
 #endif
 
-#ifndef CONFIG_SMP
-	enable_IR_x2apic();
 	default_setup_apic_routing();
-#endif
 
 	verify_local_APIC();
 	connect_bsp_APIC();
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 5c5b8f3dddb..0885a412073 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -131,13 +131,9 @@ struct irq_pin_list {
 	struct irq_pin_list *next;
 };
 
-static struct irq_pin_list *get_one_free_irq_2_pin(int node)
+static struct irq_pin_list *alloc_irq_pin_list(int node)
 {
-	struct irq_pin_list *pin;
-
-	pin = kzalloc_node(sizeof(*pin), GFP_ATOMIC, node);
-
-	return pin;
+	return kzalloc_node(sizeof(struct irq_pin_list), GFP_KERNEL, node);
 }
 
 /* irq_cfg is indexed by the sum of all RTEs in all I/O APICs. */
@@ -150,10 +146,7 @@ static struct irq_cfg irq_cfgx[NR_IRQS];
 int __init arch_early_irq_init(void)
 {
 	struct irq_cfg *cfg;
-	struct irq_desc *desc;
-	int count;
-	int node;
-	int i;
+	int count, node, i;
 
 	if (!legacy_pic->nr_legacy_irqs) {
 		nr_irqs_gsi = 0;
@@ -162,13 +155,15 @@ int __init arch_early_irq_init(void)
 
 	cfg = irq_cfgx;
 	count = ARRAY_SIZE(irq_cfgx);
-	node= cpu_to_node(boot_cpu_id);
+	node = cpu_to_node(0);
+
+	/* Make sure the legacy interrupts are marked in the bitmap */
+	irq_reserve_irqs(0, legacy_pic->nr_legacy_irqs);
 
 	for (i = 0; i < count; i++) {
-		desc = irq_to_desc(i);
-		desc->chip_data = &cfg[i];
-		zalloc_cpumask_var_node(&cfg[i].domain, GFP_NOWAIT, node);
-		zalloc_cpumask_var_node(&cfg[i].old_domain, GFP_NOWAIT, node);
+		set_irq_chip_data(i, &cfg[i]);
+		zalloc_cpumask_var_node(&cfg[i].domain, GFP_KERNEL, node);
+		zalloc_cpumask_var_node(&cfg[i].old_domain, GFP_KERNEL, node);
 		/*
 		 * For legacy IRQ's, start with assigning irq0 to irq15 to
 		 * IRQ0_VECTOR to IRQ15_VECTOR on cpu 0.
@@ -183,170 +178,88 @@ int __init arch_early_irq_init(void)
 }
 
 #ifdef CONFIG_SPARSE_IRQ
-struct irq_cfg *irq_cfg(unsigned int irq)
+static struct irq_cfg *irq_cfg(unsigned int irq)
 {
-	struct irq_cfg *cfg = NULL;
-	struct irq_desc *desc;
-
-	desc = irq_to_desc(irq);
-	if (desc)
-		cfg = desc->chip_data;
-
-	return cfg;
+	return get_irq_chip_data(irq);
 }
 
-static struct irq_cfg *get_one_free_irq_cfg(int node)
+static struct irq_cfg *alloc_irq_cfg(unsigned int irq, int node)
 {
 	struct irq_cfg *cfg;
 
-	cfg = kzalloc_node(sizeof(*cfg), GFP_ATOMIC, node);
-	if (cfg) {
-		if (!zalloc_cpumask_var_node(&cfg->domain, GFP_ATOMIC, node)) {
-			kfree(cfg);
-			cfg = NULL;
-		} else if (!zalloc_cpumask_var_node(&cfg->old_domain,
-							  GFP_ATOMIC, node)) {
-			free_cpumask_var(cfg->domain);
-			kfree(cfg);
-			cfg = NULL;
-		}
-	}
-
+	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;
 }
 
-int arch_init_chip_data(struct irq_desc *desc, int node)
-{
-	struct irq_cfg *cfg;
-
-	cfg = desc->chip_data;
-	if (!cfg) {
-		desc->chip_data = get_one_free_irq_cfg(node);
-		if (!desc->chip_data) {
-			printk(KERN_ERR "can not alloc irq_cfg\n");
-			BUG_ON(1);
-		}
-	}
-
-	return 0;
-}
-
-/* for move_irq_desc */
-static void
-init_copy_irq_2_pin(struct irq_cfg *old_cfg, struct irq_cfg *cfg, int node)
+static void free_irq_cfg(unsigned int at, struct irq_cfg *cfg)
 {
-	struct irq_pin_list *old_entry, *head, *tail, *entry;
-
-	cfg->irq_2_pin = NULL;
-	old_entry = old_cfg->irq_2_pin;
-	if (!old_entry)
-		return;
-
-	entry = get_one_free_irq_2_pin(node);
-	if (!entry)
+	if (!cfg)
 		return;
+	set_irq_chip_data(at, NULL);
+	free_cpumask_var(cfg->domain);
+	free_cpumask_var(cfg->old_domain);
+	kfree(cfg);
+}
 
-	entry->apic	= old_entry->apic;
-	entry->pin	= old_entry->pin;
-	head		= entry;
-	tail		= entry;
-	old_entry	= old_entry->next;
-	while (old_entry) {
-		entry = get_one_free_irq_2_pin(node);
-		if (!entry) {
-			entry = head;
-			while (entry) {
-				head = entry->next;
-				kfree(entry);
-				entry = head;
-			}
-			/* still use the old one */
-			return;
-		}
-		entry->apic	= old_entry->apic;
-		entry->pin	= old_entry->pin;
-		tail->next	= entry;
-		tail		= entry;
-		old_entry	= old_entry->next;
-	}
+#else
 
-	tail->next = NULL;
-	cfg->irq_2_pin = head;
+struct irq_cfg *irq_cfg(unsigned int irq)
+{
+	return irq < nr_irqs ? irq_cfgx + irq : NULL;
 }
 
-static void free_irq_2_pin(struct irq_cfg *old_cfg, struct irq_cfg *cfg)
+static struct irq_cfg *alloc_irq_cfg(unsigned int irq, int node)
 {
-	struct irq_pin_list *entry, *next;
-
-	if (old_cfg->irq_2_pin == cfg->irq_2_pin)
-		return;
+	return irq_cfgx + irq;
+}
 
-	entry = old_cfg->irq_2_pin;
+static inline void free_irq_cfg(unsigned int at, struct irq_cfg *cfg) { }
 
-	while (entry) {
-		next = entry->next;
-		kfree(entry);
-		entry = next;
-	}
-	old_cfg->irq_2_pin = NULL;
-}
+#endif
 
-void arch_init_copy_chip_data(struct irq_desc *old_desc,
-				 struct irq_desc *desc, int node)
+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;
-	struct irq_cfg *old_cfg;
-
-	cfg = get_one_free_irq_cfg(node);
 
-	if (!cfg)
-		return;
-
-	desc->chip_data = cfg;
-
-	old_cfg = old_desc->chip_data;
-
-	cfg->vector = old_cfg->vector;
-	cfg->move_in_progress = old_cfg->move_in_progress;
-	cpumask_copy(cfg->domain, old_cfg->domain);
-	cpumask_copy(cfg->old_domain, old_cfg->old_domain);
-
-	init_copy_irq_2_pin(old_cfg, cfg, node);
-}
+	if (res < 0) {
+		if (res != -EEXIST)
+			return NULL;
+		cfg = get_irq_chip_data(at);
+		if (cfg)
+			return cfg;
+	}
 
-static void free_irq_cfg(struct irq_cfg *cfg)
-{
-	free_cpumask_var(cfg->domain);
-	free_cpumask_var(cfg->old_domain);
-	kfree(cfg);
+	cfg = alloc_irq_cfg(at, node);
+	if (cfg)
+		set_irq_chip_data(at, cfg);
+	else
+		irq_free_desc(at);
+	return cfg;
 }
 
-void arch_free_chip_data(struct irq_desc *old_desc, struct irq_desc *desc)
+static int alloc_irq_from(unsigned int from, int node)
 {
-	struct irq_cfg *old_cfg, *cfg;
-
-	old_cfg = old_desc->chip_data;
-	cfg = desc->chip_data;
-
-	if (old_cfg == cfg)
-		return;
-
-	if (old_cfg) {
-		free_irq_2_pin(old_cfg, cfg);
-		free_irq_cfg(old_cfg);
-		old_desc->chip_data = NULL;
-	}
+	return irq_alloc_desc_from(from, node);
 }
-/* end for move_irq_desc */
 
-#else
-struct irq_cfg *irq_cfg(unsigned int irq)
+static void free_irq_at(unsigned int at, struct irq_cfg *cfg)
 {
-	return irq < nr_irqs ? irq_cfgx + irq : NULL;
+	free_irq_cfg(at, cfg);
+	irq_free_desc(at);
 }
 
-#endif
-
 struct io_apic {
 	unsigned int index;
 	unsigned int unused[3];
@@ -451,7 +364,7 @@ __ioapic_write_entry(int apic, int pin, struct IO_APIC_route_entry e)
 	io_apic_write(apic, 0x10 + 2*pin, eu.w1);
 }
 
-void ioapic_write_entry(int apic, int pin, struct IO_APIC_route_entry e)
+static void ioapic_write_entry(int apic, int pin, struct IO_APIC_route_entry e)
 {
 	unsigned long flags;
 	raw_spin_lock_irqsave(&ioapic_lock, flags);
@@ -481,7 +394,7 @@ static void ioapic_mask_entry(int apic, int pin)
  * fast in the common case, and fast for shared ISA-space IRQs.
  */
 static int
-add_pin_to_irq_node_nopanic(struct irq_cfg *cfg, int node, int apic, int pin)
+__add_pin_to_irq_node(struct irq_cfg *cfg, int node, int apic, int pin)
 {
 	struct irq_pin_list **last, *entry;
 
@@ -493,7 +406,7 @@ add_pin_to_irq_node_nopanic(struct irq_cfg *cfg, int node, int apic, int pin)
 		last = &entry->next;
 	}
 
-	entry = get_one_free_irq_2_pin(node);
+	entry = alloc_irq_pin_list(node);
 	if (!entry) {
 		printk(KERN_ERR "can not alloc irq_pin_list (%d,%d,%d)\n",
 				node, apic, pin);
@@ -508,7 +421,7 @@ add_pin_to_irq_node_nopanic(struct irq_cfg *cfg, int node, int apic, int pin)
 
 static void add_pin_to_irq_node(struct irq_cfg *cfg, int node, int apic, int pin)
 {
-	if (add_pin_to_irq_node_nopanic(cfg, node, apic, pin))
+	if (__add_pin_to_irq_node(cfg, node, apic, pin))
 		panic("IO-APIC: failed to add irq-pin. Can not proceed\n");
 }
 
@@ -571,11 +484,6 @@ static void __unmask_and_level_IO_APIC_irq(struct irq_pin_list *entry)
 			     IO_APIC_REDIR_LEVEL_TRIGGER, NULL);
 }
 
-static void __unmask_IO_APIC_irq(struct irq_cfg *cfg)
-{
-	io_apic_modify_irq(cfg, ~IO_APIC_REDIR_MASKED, 0, NULL);
-}
-
 static void io_apic_sync(struct irq_pin_list *entry)
 {
 	/*
@@ -587,44 +495,37 @@ static void io_apic_sync(struct irq_pin_list *entry)
 	readl(&io_apic->data);
 }
 
-static void __mask_IO_APIC_irq(struct irq_cfg *cfg)
+static void mask_ioapic(struct irq_cfg *cfg)
 {
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&ioapic_lock, flags);
 	io_apic_modify_irq(cfg, ~0, IO_APIC_REDIR_MASKED, &io_apic_sync);
+	raw_spin_unlock_irqrestore(&ioapic_lock, flags);
 }
 
-static void mask_IO_APIC_irq_desc(struct irq_desc *desc)
+static void mask_ioapic_irq(struct irq_data *data)
 {
-	struct irq_cfg *cfg = desc->chip_data;
-	unsigned long flags;
-
-	BUG_ON(!cfg);
+	mask_ioapic(data->chip_data);
+}
 
-	raw_spin_lock_irqsave(&ioapic_lock, flags);
-	__mask_IO_APIC_irq(cfg);
-	raw_spin_unlock_irqrestore(&ioapic_lock, flags);
+static void __unmask_ioapic(struct irq_cfg *cfg)
+{
+	io_apic_modify_irq(cfg, ~IO_APIC_REDIR_MASKED, 0, NULL);
 }
 
-static void unmask_IO_APIC_irq_desc(struct irq_desc *desc)
+static void unmask_ioapic(struct irq_cfg *cfg)
 {
-	struct irq_cfg *cfg = desc->chip_data;
 	unsigned long flags;
 
 	raw_spin_lock_irqsave(&ioapic_lock, flags);
-	__unmask_IO_APIC_irq(cfg);
+	__unmask_ioapic(cfg);
 	raw_spin_unlock_irqrestore(&ioapic_lock, flags);
 }
 
-static void mask_IO_APIC_irq(unsigned int irq)
-{
-	struct irq_desc *desc = irq_to_desc(irq);
-
-	mask_IO_APIC_irq_desc(desc);
-}
-static void unmask_IO_APIC_irq(unsigned int irq)
+static void unmask_ioapic_irq(struct irq_data *data)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
-
-	unmask_IO_APIC_irq_desc(desc);
+	unmask_ioapic(data->chip_data);
 }
 
 static void clear_IO_APIC_pin(unsigned int apic, unsigned int pin)
@@ -694,14 +595,14 @@ struct IO_APIC_route_entry **alloc_ioapic_entries(void)
 	struct IO_APIC_route_entry **ioapic_entries;
 
 	ioapic_entries = kzalloc(sizeof(*ioapic_entries) * nr_ioapics,
-				GFP_ATOMIC);
+				GFP_KERNEL);
 	if (!ioapic_entries)
 		return 0;
 
 	for (apic = 0; apic < nr_ioapics; apic++) {
 		ioapic_entries[apic] =
 			kzalloc(sizeof(struct IO_APIC_route_entry) *
-				nr_ioapic_registers[apic], GFP_ATOMIC);
+				nr_ioapic_registers[apic], GFP_KERNEL);
 		if (!ioapic_entries[apic])
 			goto nomem;
 	}
@@ -1259,7 +1160,6 @@ void __setup_vector_irq(int cpu)
 	/* Initialize vector_irq on a new cpu */
 	int irq, vector;
 	struct irq_cfg *cfg;
-	struct irq_desc *desc;
 
 	/*
 	 * vector_lock will make sure that we don't run into irq vector
@@ -1268,9 +1168,10 @@ void __setup_vector_irq(int cpu)
 	 */
 	raw_spin_lock(&vector_lock);
 	/* Mark the inuse vectors */
-	for_each_irq_desc(irq, desc) {
-		cfg = desc->chip_data;
-
+	for_each_active_irq(irq) {
+		cfg = get_irq_chip_data(irq);
+		if (!cfg)
+			continue;
 		/*
 		 * If it is a legacy IRQ handled by the legacy PIC, this cpu
 		 * will be part of the irq_cfg's domain.
@@ -1327,17 +1228,17 @@ static inline int IO_APIC_irq_trigger(int irq)
 }
 #endif
 
-static void ioapic_register_intr(int irq, struct irq_desc *desc, unsigned long trigger)
+static void ioapic_register_intr(unsigned int irq, unsigned long trigger)
 {
 
 	if ((trigger == IOAPIC_AUTO && IO_APIC_irq_trigger(irq)) ||
 	    trigger == IOAPIC_LEVEL)
-		desc->status |= IRQ_LEVEL;
+		irq_set_status_flags(irq, IRQ_LEVEL);
 	else
-		desc->status &= ~IRQ_LEVEL;
+		irq_clear_status_flags(irq, IRQ_LEVEL);
 
-	if (irq_remapped(irq)) {
-		desc->status |= IRQ_MOVE_PCNTXT;
+	if (irq_remapped(get_irq_chip_data(irq))) {
+		irq_set_status_flags(irq, IRQ_MOVE_PCNTXT);
 		if (trigger)
 			set_irq_chip_and_handler_name(irq, &ir_ioapic_chip,
 						      handle_fasteoi_irq,
@@ -1358,10 +1259,10 @@ static void ioapic_register_intr(int irq, struct irq_desc *desc, unsigned long t
 					      handle_edge_irq, "edge");
 }
 
-int setup_ioapic_entry(int apic_id, int irq,
-		       struct IO_APIC_route_entry *entry,
-		       unsigned int destination, int trigger,
-		       int polarity, int vector, int pin)
+static int setup_ioapic_entry(int apic_id, int irq,
+			      struct IO_APIC_route_entry *entry,
+			      unsigned int destination, int trigger,
+			      int polarity, int vector, int pin)
 {
 	/*
 	 * add it to the IO-APIC irq-routing table:
@@ -1382,21 +1283,7 @@ int setup_ioapic_entry(int apic_id, int irq,
 		if (index < 0)
 			panic("Failed to allocate IRTE for ioapic %d\n", apic_id);
 
-		memset(&irte, 0, sizeof(irte));
-
-		irte.present = 1;
-		irte.dst_mode = apic->irq_dest_mode;
-		/*
-		 * Trigger mode in the IRTE will always be edge, and the
-		 * actual level or edge trigger will be setup in the IO-APIC
-		 * RTE. This will help simplify level triggered irq migration.
-		 * For more details, see the comments above explainig IO-APIC
-		 * irq migration in the presence of interrupt-remapping.
-		 */
-		irte.trigger_mode = 0;
-		irte.dlvry_mode = apic->irq_delivery_mode;
-		irte.vector = vector;
-		irte.dest_id = IRTE_DEST(destination);
+		prepare_irte(&irte, vector, destination);
 
 		/* Set source-id of interrupt request */
 		set_ioapic_sid(&irte, apic_id);
@@ -1431,18 +1318,14 @@ int setup_ioapic_entry(int apic_id, int irq,
 	return 0;
 }
 
-static void setup_IO_APIC_irq(int apic_id, int pin, unsigned int irq, struct irq_desc *desc,
-			      int trigger, int polarity)
+static void setup_ioapic_irq(int apic_id, int pin, unsigned int irq,
+			     struct irq_cfg *cfg, int trigger, int polarity)
 {
-	struct irq_cfg *cfg;
 	struct IO_APIC_route_entry entry;
 	unsigned int dest;
 
 	if (!IO_APIC_IRQ(irq))
 		return;
-
-	cfg = desc->chip_data;
-
 	/*
 	 * For legacy irqs, cfg->domain starts with cpu 0 for legacy
 	 * controllers like 8259. Now that IO-APIC can handle this irq, update
@@ -1471,9 +1354,9 @@ static void setup_IO_APIC_irq(int apic_id, int pin, unsigned int irq, struct irq
 		return;
 	}
 
-	ioapic_register_intr(irq, desc, trigger);
+	ioapic_register_intr(irq, trigger);
 	if (irq < legacy_pic->nr_legacy_irqs)
-		legacy_pic->chip->mask(irq);
+		legacy_pic->mask(irq);
 
 	ioapic_write_entry(apic_id, pin, entry);
 }
@@ -1484,11 +1367,9 @@ static struct {
 
 static void __init setup_IO_APIC_irqs(void)
 {
-	int apic_id, pin, idx, irq;
-	int notcon = 0;
-	struct irq_desc *desc;
+	int apic_id, pin, idx, irq, notcon = 0;
+	int node = cpu_to_node(0);
 	struct irq_cfg *cfg;
-	int node = cpu_to_node(boot_cpu_id);
 
 	apic_printk(APIC_VERBOSE, KERN_DEBUG "init IO_APIC IRQs\n");
 
@@ -1525,19 +1406,17 @@ static void __init setup_IO_APIC_irqs(void)
 				apic->multi_timer_check(apic_id, irq))
 			continue;
 
-		desc = irq_to_desc_alloc_node(irq, node);
-		if (!desc) {
-			printk(KERN_INFO "can not get irq_desc for %d\n", irq);
+		cfg = alloc_irq_and_cfg_at(irq, node);
+		if (!cfg)
 			continue;
-		}
-		cfg = desc->chip_data;
+
 		add_pin_to_irq_node(cfg, node, apic_id, pin);
 		/*
 		 * don't mark it in pin_programmed, so later acpi could
 		 * set it correctly when irq < 16
 		 */
-		setup_IO_APIC_irq(apic_id, pin, irq, desc,
-				irq_trigger(idx), irq_polarity(idx));
+		setup_ioapic_irq(apic_id, pin, irq, cfg, irq_trigger(idx),
+				  irq_polarity(idx));
 	}
 
 	if (notcon)
@@ -1552,9 +1431,7 @@ static void __init setup_IO_APIC_irqs(void)
  */
 void setup_IO_APIC_irq_extra(u32 gsi)
 {
-	int apic_id = 0, pin, idx, irq;
-	int node = cpu_to_node(boot_cpu_id);
-	struct irq_desc *desc;
+	int apic_id = 0, pin, idx, irq, node = cpu_to_node(0);
 	struct irq_cfg *cfg;
 
 	/*
@@ -1570,18 +1447,15 @@ void setup_IO_APIC_irq_extra(u32 gsi)
 		return;
 
 	irq = pin_2_irq(idx, apic_id, pin);
-#ifdef CONFIG_SPARSE_IRQ
-	desc = irq_to_desc(irq);
-	if (desc)
+
+	/* Only handle the non legacy irqs on secondary ioapics */
+	if (apic_id == 0 || irq < NR_IRQS_LEGACY)
 		return;
-#endif
-	desc = irq_to_desc_alloc_node(irq, node);
-	if (!desc) {
-		printk(KERN_INFO "can not get irq_desc for %d\n", irq);
+
+	cfg = alloc_irq_and_cfg_at(irq, node);
+	if (!cfg)
 		return;
-	}
 
-	cfg = desc->chip_data;
 	add_pin_to_irq_node(cfg, node, apic_id, pin);
 
 	if (test_bit(pin, mp_ioapic_routing[apic_id].pin_programmed)) {
@@ -1591,7 +1465,7 @@ void setup_IO_APIC_irq_extra(u32 gsi)
 	}
 	set_bit(pin, mp_ioapic_routing[apic_id].pin_programmed);
 
-	setup_IO_APIC_irq(apic_id, pin, irq, desc,
+	setup_ioapic_irq(apic_id, pin, irq, cfg,
 			irq_trigger(idx), irq_polarity(idx));
 }
 
@@ -1642,7 +1516,6 @@ __apicdebuginit(void) print_IO_APIC(void)
 	union IO_APIC_reg_03 reg_03;
 	unsigned long flags;
 	struct irq_cfg *cfg;
-	struct irq_desc *desc;
 	unsigned int irq;
 
 	printk(KERN_DEBUG "number of MP IRQ sources: %d.\n", mp_irq_entries);
@@ -1729,10 +1602,10 @@ __apicdebuginit(void) print_IO_APIC(void)
 	}
 	}
 	printk(KERN_DEBUG "IRQ to pin mappings:\n");
-	for_each_irq_desc(irq, desc) {
+	for_each_active_irq(irq) {
 		struct irq_pin_list *entry;
 
-		cfg = desc->chip_data;
+		cfg = get_irq_chip_data(irq);
 		if (!cfg)
 			continue;
 		entry = cfg->irq_2_pin;
@@ -2239,29 +2112,26 @@ static int __init timer_irq_works(void)
  * an edge even if it isn't on the 8259A...
  */
 
-static unsigned int startup_ioapic_irq(unsigned int irq)
+static unsigned int startup_ioapic_irq(struct irq_data *data)
 {
-	int was_pending = 0;
+	int was_pending = 0, irq = data->irq;
 	unsigned long flags;
-	struct irq_cfg *cfg;
 
 	raw_spin_lock_irqsave(&ioapic_lock, flags);
 	if (irq < legacy_pic->nr_legacy_irqs) {
-		legacy_pic->chip->mask(irq);
+		legacy_pic->mask(irq);
 		if (legacy_pic->irq_pending(irq))
 			was_pending = 1;
 	}
-	cfg = irq_cfg(irq);
-	__unmask_IO_APIC_irq(cfg);
+	__unmask_ioapic(data->chip_data);
 	raw_spin_unlock_irqrestore(&ioapic_lock, flags);
 
 	return was_pending;
 }
 
-static int ioapic_retrigger_irq(unsigned int irq)
+static int ioapic_retrigger_irq(struct irq_data *data)
 {
-
-	struct irq_cfg *cfg = irq_cfg(irq);
+	struct irq_cfg *cfg = data->chip_data;
 	unsigned long flags;
 
 	raw_spin_lock_irqsave(&vector_lock, flags);
@@ -2312,7 +2182,7 @@ static void __target_IO_APIC_irq(unsigned int irq, unsigned int dest, struct irq
 		 * With interrupt-remapping, destination information comes
 		 * from interrupt-remapping table entry.
 		 */
-		if (!irq_remapped(irq))
+		if (!irq_remapped(cfg))
 			io_apic_write(apic, 0x11 + pin*2, dest);
 		reg = io_apic_read(apic, 0x10 + pin*2);
 		reg &= ~IO_APIC_REDIR_VECTOR_MASK;
@@ -2322,65 +2192,46 @@ static void __target_IO_APIC_irq(unsigned int irq, unsigned int dest, struct irq
 }
 
 /*
- * Either sets desc->affinity to a valid value, and returns
+ * Either sets data->affinity to a valid value, and returns
  * ->cpu_mask_to_apicid of that in dest_id, or returns -1 and
- * leaves desc->affinity untouched.
+ * leaves data->affinity untouched.
  */
-unsigned int
-set_desc_affinity(struct irq_desc *desc, const struct cpumask *mask,
-		  unsigned int *dest_id)
+int __ioapic_set_affinity(struct irq_data *data, const struct cpumask *mask,
+			  unsigned int *dest_id)
 {
-	struct irq_cfg *cfg;
-	unsigned int irq;
+	struct irq_cfg *cfg = data->chip_data;
 
 	if (!cpumask_intersects(mask, cpu_online_mask))
 		return -1;
 
-	irq = desc->irq;
-	cfg = desc->chip_data;
-	if (assign_irq_vector(irq, cfg, mask))
+	if (assign_irq_vector(data->irq, data->chip_data, mask))
 		return -1;
 
-	cpumask_copy(desc->affinity, mask);
+	cpumask_copy(data->affinity, mask);
 
-	*dest_id = apic->cpu_mask_to_apicid_and(desc->affinity, cfg->domain);
+	*dest_id = apic->cpu_mask_to_apicid_and(mask, cfg->domain);
 	return 0;
 }
 
 static int
-set_ioapic_affinity_irq_desc(struct irq_desc *desc, const struct cpumask *mask)
+ioapic_set_affinity(struct irq_data *data, const struct cpumask *mask,
+		    bool force)
 {
-	struct irq_cfg *cfg;
+	unsigned int dest, irq = data->irq;
 	unsigned long flags;
-	unsigned int dest;
-	unsigned int irq;
-	int ret = -1;
-
-	irq = desc->irq;
-	cfg = desc->chip_data;
+	int ret;
 
 	raw_spin_lock_irqsave(&ioapic_lock, flags);
-	ret = set_desc_affinity(desc, mask, &dest);
+	ret = __ioapic_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, cfg);
+		__target_IO_APIC_irq(irq, dest, data->chip_data);
 	}
 	raw_spin_unlock_irqrestore(&ioapic_lock, flags);
-
 	return ret;
 }
 
-static int
-set_ioapic_affinity_irq(unsigned int irq, const struct cpumask *mask)
-{
-	struct irq_desc *desc;
-
-	desc = irq_to_desc(irq);
-
-	return set_ioapic_affinity_irq_desc(desc, mask);
-}
-
 #ifdef CONFIG_INTR_REMAP
 
 /*
@@ -2395,24 +2246,21 @@ set_ioapic_affinity_irq(unsigned int irq, const struct cpumask *mask)
  * the interrupt-remapping table entry.
  */
 static int
-migrate_ioapic_irq_desc(struct irq_desc *desc, const struct cpumask *mask)
+ir_ioapic_set_affinity(struct irq_data *data, const struct cpumask *mask,
+		       bool force)
 {
-	struct irq_cfg *cfg;
+	struct irq_cfg *cfg = data->chip_data;
+	unsigned int dest, irq = data->irq;
 	struct irte irte;
-	unsigned int dest;
-	unsigned int irq;
-	int ret = -1;
 
 	if (!cpumask_intersects(mask, cpu_online_mask))
-		return ret;
+		return -EINVAL;
 
-	irq = desc->irq;
 	if (get_irte(irq, &irte))
-		return ret;
+		return -EBUSY;
 
-	cfg = desc->chip_data;
 	if (assign_irq_vector(irq, cfg, mask))
-		return ret;
+		return -EBUSY;
 
 	dest = apic->cpu_mask_to_apicid_and(cfg->domain, mask);
 
@@ -2427,29 +2275,14 @@ migrate_ioapic_irq_desc(struct irq_desc *desc, const struct cpumask *mask)
 	if (cfg->move_in_progress)
 		send_cleanup_vector(cfg);
 
-	cpumask_copy(desc->affinity, mask);
-
+	cpumask_copy(data->affinity, mask);
 	return 0;
 }
 
-/*
- * Migrates the IRQ destination in the process context.
- */
-static int set_ir_ioapic_affinity_irq_desc(struct irq_desc *desc,
-					    const struct cpumask *mask)
-{
-	return migrate_ioapic_irq_desc(desc, mask);
-}
-static int set_ir_ioapic_affinity_irq(unsigned int irq,
-				       const struct cpumask *mask)
-{
-	struct irq_desc *desc = irq_to_desc(irq);
-
-	return set_ir_ioapic_affinity_irq_desc(desc, mask);
-}
 #else
-static inline int set_ir_ioapic_affinity_irq_desc(struct irq_desc *desc,
-						   const struct cpumask *mask)
+static inline int
+ir_ioapic_set_affinity(struct irq_data *data, const struct cpumask *mask,
+		       bool force)
 {
 	return 0;
 }
@@ -2511,10 +2344,8 @@ unlock:
 	irq_exit();
 }
 
-static void __irq_complete_move(struct irq_desc **descp, unsigned vector)
+static void __irq_complete_move(struct irq_cfg *cfg, unsigned vector)
 {
-	struct irq_desc *desc = *descp;
-	struct irq_cfg *cfg = desc->chip_data;
 	unsigned me;
 
 	if (likely(!cfg->move_in_progress))
@@ -2526,31 +2357,28 @@ static void __irq_complete_move(struct irq_desc **descp, unsigned vector)
 		send_cleanup_vector(cfg);
 }
 
-static void irq_complete_move(struct irq_desc **descp)
+static void irq_complete_move(struct irq_cfg *cfg)
 {
-	__irq_complete_move(descp, ~get_irq_regs()->orig_ax);
+	__irq_complete_move(cfg, ~get_irq_regs()->orig_ax);
 }
 
 void irq_force_complete_move(int irq)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
-	struct irq_cfg *cfg = desc->chip_data;
+	struct irq_cfg *cfg = get_irq_chip_data(irq);
 
 	if (!cfg)
 		return;
 
-	__irq_complete_move(&desc, cfg->vector);
+	__irq_complete_move(cfg, cfg->vector);
 }
 #else
-static inline void irq_complete_move(struct irq_desc **descp) {}
+static inline void irq_complete_move(struct irq_cfg *cfg) { }
 #endif
 
-static void ack_apic_edge(unsigned int irq)
+static void ack_apic_edge(struct irq_data *data)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
-
-	irq_complete_move(&desc);
-	move_native_irq(irq);
+	irq_complete_move(data->chip_data);
+	move_native_irq(data->irq);
 	ack_APIC_irq();
 }
 
@@ -2572,10 +2400,12 @@ atomic_t irq_mis_count;
  * Otherwise, we simulate the EOI message manually by changing the trigger
  * mode to edge and then back to level, with RTE being masked during this.
 */
-static void __eoi_ioapic_irq(unsigned int irq, struct irq_cfg *cfg)
+static void eoi_ioapic_irq(unsigned int irq, struct irq_cfg *cfg)
 {
 	struct irq_pin_list *entry;
+	unsigned long flags;
 
+	raw_spin_lock_irqsave(&ioapic_lock, flags);
 	for_each_irq_pin(entry, cfg->irq_2_pin) {
 		if (mp_ioapics[entry->apic].apicver >= 0x20) {
 			/*
@@ -2584,7 +2414,7 @@ static void __eoi_ioapic_irq(unsigned int irq, struct irq_cfg *cfg)
 			 * intr-remapping table entry. Hence for the io-apic
 			 * EOI we use the pin number.
 			 */
-			if (irq_remapped(irq))
+			if (irq_remapped(cfg))
 				io_apic_eoi(entry->apic, entry->pin);
 			else
 				io_apic_eoi(entry->apic, cfg->vector);
@@ -2593,36 +2423,22 @@ static void __eoi_ioapic_irq(unsigned int irq, struct irq_cfg *cfg)
 			__unmask_and_level_IO_APIC_irq(entry);
 		}
 	}
-}
-
-static void eoi_ioapic_irq(struct irq_desc *desc)
-{
-	struct irq_cfg *cfg;
-	unsigned long flags;
-	unsigned int irq;
-
-	irq = desc->irq;
-	cfg = desc->chip_data;
-
-	raw_spin_lock_irqsave(&ioapic_lock, flags);
-	__eoi_ioapic_irq(irq, cfg);
 	raw_spin_unlock_irqrestore(&ioapic_lock, flags);
 }
 
-static void ack_apic_level(unsigned int irq)
+static void ack_apic_level(struct irq_data *data)
 {
+	struct irq_cfg *cfg = data->chip_data;
+	int i, do_unmask_irq = 0, irq = data->irq;
 	struct irq_desc *desc = irq_to_desc(irq);
 	unsigned long v;
-	int i;
-	struct irq_cfg *cfg;
-	int do_unmask_irq = 0;
 
-	irq_complete_move(&desc);
+	irq_complete_move(cfg);
 #ifdef CONFIG_GENERIC_PENDING_IRQ
 	/* If we are moving the irq we need to mask it */
 	if (unlikely(desc->status & IRQ_MOVE_PENDING)) {
 		do_unmask_irq = 1;
-		mask_IO_APIC_irq_desc(desc);
+		mask_ioapic(cfg);
 	}
 #endif
 
@@ -2658,7 +2474,6 @@ static void ack_apic_level(unsigned int irq)
 	 * we use the above logic (mask+edge followed by unmask+level) from
 	 * Manfred Spraul to clear the remote IRR.
 	 */
-	cfg = desc->chip_data;
 	i = cfg->vector;
 	v = apic_read(APIC_TMR + ((i & ~0x1f) >> 1));
 
@@ -2678,7 +2493,7 @@ static void ack_apic_level(unsigned int irq)
 	if (!(v & (1 << (i & 0x1f)))) {
 		atomic_inc(&irq_mis_count);
 
-		eoi_ioapic_irq(desc);
+		eoi_ioapic_irq(irq, cfg);
 	}
 
 	/* Now we can move and renable the irq */
@@ -2709,61 +2524,57 @@ static void ack_apic_level(unsigned int irq)
 		 * accurate and is causing problems then it is a hardware bug
 		 * and you can go talk to the chipset vendor about it.
 		 */
-		cfg = desc->chip_data;
 		if (!io_apic_level_ack_pending(cfg))
 			move_masked_irq(irq);
-		unmask_IO_APIC_irq_desc(desc);
+		unmask_ioapic(cfg);
 	}
 }
 
 #ifdef CONFIG_INTR_REMAP
-static void ir_ack_apic_edge(unsigned int irq)
+static void ir_ack_apic_edge(struct irq_data *data)
 {
 	ack_APIC_irq();
 }
 
-static void ir_ack_apic_level(unsigned int irq)
+static void ir_ack_apic_level(struct irq_data *data)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
-
 	ack_APIC_irq();
-	eoi_ioapic_irq(desc);
+	eoi_ioapic_irq(data->irq, data->chip_data);
 }
 #endif /* CONFIG_INTR_REMAP */
 
 static struct irq_chip ioapic_chip __read_mostly = {
-	.name		= "IO-APIC",
-	.startup	= startup_ioapic_irq,
-	.mask		= mask_IO_APIC_irq,
-	.unmask		= unmask_IO_APIC_irq,
-	.ack		= ack_apic_edge,
-	.eoi		= ack_apic_level,
+	.name			= "IO-APIC",
+	.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,
 #ifdef CONFIG_SMP
-	.set_affinity	= set_ioapic_affinity_irq,
+	.irq_set_affinity	= ioapic_set_affinity,
 #endif
-	.retrigger	= ioapic_retrigger_irq,
+	.irq_retrigger		= ioapic_retrigger_irq,
 };
 
 static struct irq_chip ir_ioapic_chip __read_mostly = {
-	.name		= "IR-IO-APIC",
-	.startup	= startup_ioapic_irq,
-	.mask		= mask_IO_APIC_irq,
-	.unmask		= unmask_IO_APIC_irq,
+	.name			= "IR-IO-APIC",
+	.irq_startup		= startup_ioapic_irq,
+	.irq_mask		= mask_ioapic_irq,
+	.irq_unmask		= unmask_ioapic_irq,
 #ifdef CONFIG_INTR_REMAP
-	.ack		= ir_ack_apic_edge,
-	.eoi		= ir_ack_apic_level,
+	.irq_ack		= ir_ack_apic_edge,
+	.irq_eoi		= ir_ack_apic_level,
 #ifdef CONFIG_SMP
-	.set_affinity	= set_ir_ioapic_affinity_irq,
+	.irq_set_affinity	= ir_ioapic_set_affinity,
 #endif
 #endif
-	.retrigger	= ioapic_retrigger_irq,
+	.irq_retrigger		= ioapic_retrigger_irq,
 };
 
 static inline void init_IO_APIC_traps(void)
 {
-	int irq;
-	struct irq_desc *desc;
 	struct irq_cfg *cfg;
+	unsigned int irq;
 
 	/*
 	 * NOTE! The local APIC isn't very good at handling
@@ -2776,8 +2587,8 @@ static inline void init_IO_APIC_traps(void)
 	 * Also, we've got to be careful not to trash gate
 	 * 0x80, because int 0x80 is hm, kind of importantish. ;)
 	 */
-	for_each_irq_desc(irq, desc) {
-		cfg = desc->chip_data;
+	for_each_active_irq(irq) {
+		cfg = get_irq_chip_data(irq);
 		if (IO_APIC_IRQ(irq) && cfg && !cfg->vector) {
 			/*
 			 * Hmm.. We don't have an entry for this,
@@ -2788,7 +2599,7 @@ static inline void init_IO_APIC_traps(void)
 				legacy_pic->make_irq(irq);
 			else
 				/* Strange. Oh, well.. */
-				desc->chip = &no_irq_chip;
+				set_irq_chip(irq, &no_irq_chip);
 		}
 	}
 }
@@ -2797,7 +2608,7 @@ static inline void init_IO_APIC_traps(void)
  * The local APIC irq-chip implementation:
  */
 
-static void mask_lapic_irq(unsigned int irq)
+static void mask_lapic_irq(struct irq_data *data)
 {
 	unsigned long v;
 
@@ -2805,7 +2616,7 @@ static void mask_lapic_irq(unsigned int irq)
 	apic_write(APIC_LVT0, v | APIC_LVT_MASKED);
 }
 
-static void unmask_lapic_irq(unsigned int irq)
+static void unmask_lapic_irq(struct irq_data *data)
 {
 	unsigned long v;
 
@@ -2813,21 +2624,21 @@ static void unmask_lapic_irq(unsigned int irq)
 	apic_write(APIC_LVT0, v & ~APIC_LVT_MASKED);
 }
 
-static void ack_lapic_irq(unsigned int irq)
+static void ack_lapic_irq(struct irq_data *data)
 {
 	ack_APIC_irq();
 }
 
 static struct irq_chip lapic_chip __read_mostly = {
 	.name		= "local-APIC",
-	.mask		= mask_lapic_irq,
-	.unmask		= unmask_lapic_irq,
-	.ack		= ack_lapic_irq,
+	.irq_mask	= mask_lapic_irq,
+	.irq_unmask	= unmask_lapic_irq,
+	.irq_ack	= ack_lapic_irq,
 };
 
-static void lapic_register_intr(int irq, struct irq_desc *desc)
+static void lapic_register_intr(int irq)
 {
-	desc->status &= ~IRQ_LEVEL;
+	irq_clear_status_flags(irq, IRQ_LEVEL);
 	set_irq_chip_and_handler_name(irq, &lapic_chip, handle_edge_irq,
 				      "edge");
 }
@@ -2930,9 +2741,8 @@ int timer_through_8259 __initdata;
  */
 static inline void __init check_timer(void)
 {
-	struct irq_desc *desc = irq_to_desc(0);
-	struct irq_cfg *cfg = desc->chip_data;
-	int node = cpu_to_node(boot_cpu_id);
+	struct irq_cfg *cfg = get_irq_chip_data(0);
+	int node = cpu_to_node(0);
 	int apic1, pin1, apic2, pin2;
 	unsigned long flags;
 	int no_pin1 = 0;
@@ -2942,7 +2752,7 @@ static inline void __init check_timer(void)
 	/*
 	 * get/set the timer IRQ vector:
 	 */
-	legacy_pic->chip->mask(0);
+	legacy_pic->mask(0);
 	assign_irq_vector(0, cfg, apic->target_cpus());
 
 	/*
@@ -3001,7 +2811,7 @@ static inline void __init check_timer(void)
 			add_pin_to_irq_node(cfg, node, apic1, pin1);
 			setup_timer_IRQ0_pin(apic1, pin1, cfg->vector);
 		} else {
-			/* for edge trigger, setup_IO_APIC_irq already
+			/* for edge trigger, setup_ioapic_irq already
 			 * leave it unmasked.
 			 * so only need to unmask if it is level-trigger
 			 * do we really have level trigger timer?
@@ -3009,12 +2819,12 @@ static inline void __init check_timer(void)
 			int idx;
 			idx = find_irq_entry(apic1, pin1, mp_INT);
 			if (idx != -1 && irq_trigger(idx))
-				unmask_IO_APIC_irq_desc(desc);
+				unmask_ioapic(cfg);
 		}
 		if (timer_irq_works()) {
 			if (nmi_watchdog == NMI_IO_APIC) {
 				setup_nmi();
-				legacy_pic->chip->unmask(0);
+				legacy_pic->unmask(0);
 			}
 			if (disable_timer_pin_1 > 0)
 				clear_IO_APIC_pin(0, pin1);
@@ -3037,14 +2847,14 @@ static inline void __init check_timer(void)
 		 */
 		replace_pin_at_irq_node(cfg, node, apic1, pin1, apic2, pin2);
 		setup_timer_IRQ0_pin(apic2, pin2, cfg->vector);
-		legacy_pic->chip->unmask(0);
+		legacy_pic->unmask(0);
 		if (timer_irq_works()) {
 			apic_printk(APIC_QUIET, KERN_INFO "....... works.\n");
 			timer_through_8259 = 1;
 			if (nmi_watchdog == NMI_IO_APIC) {
-				legacy_pic->chip->mask(0);
+				legacy_pic->mask(0);
 				setup_nmi();
-				legacy_pic->chip->unmask(0);
+				legacy_pic->unmask(0);
 			}
 			goto out;
 		}
@@ -3052,7 +2862,7 @@ static inline void __init check_timer(void)
 		 * Cleanup, just in case ...
 		 */
 		local_irq_disable();
-		legacy_pic->chip->mask(0);
+		legacy_pic->mask(0);
 		clear_IO_APIC_pin(apic2, pin2);
 		apic_printk(APIC_QUIET, KERN_INFO "....... failed.\n");
 	}
@@ -3069,16 +2879,16 @@ static inline void __init check_timer(void)
 	apic_printk(APIC_QUIET, KERN_INFO
 		    "...trying to set up timer as Virtual Wire IRQ...\n");
 
-	lapic_register_intr(0, desc);
+	lapic_register_intr(0);
 	apic_write(APIC_LVT0, APIC_DM_FIXED | cfg->vector);	/* Fixed mode */
-	legacy_pic->chip->unmask(0);
+	legacy_pic->unmask(0);
 
 	if (timer_irq_works()) {
 		apic_printk(APIC_QUIET, KERN_INFO "..... works.\n");
 		goto out;
 	}
 	local_irq_disable();
-	legacy_pic->chip->mask(0);
+	legacy_pic->mask(0);
 	apic_write(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_FIXED | cfg->vector);
 	apic_printk(APIC_QUIET, KERN_INFO "..... failed.\n");
 
@@ -3244,49 +3054,42 @@ device_initcall(ioapic_init_sysfs);
 /*
  * Dynamic irq allocate and deallocation
  */
-unsigned int create_irq_nr(unsigned int irq_want, int node)
+unsigned int create_irq_nr(unsigned int from, int node)
 {
-	/* Allocate an unused irq */
-	unsigned int irq;
-	unsigned int new;
+	struct irq_cfg *cfg;
 	unsigned long flags;
-	struct irq_cfg *cfg_new = NULL;
-	struct irq_desc *desc_new = NULL;
-
-	irq = 0;
-	if (irq_want < nr_irqs_gsi)
-		irq_want = nr_irqs_gsi;
-
-	raw_spin_lock_irqsave(&vector_lock, flags);
-	for (new = irq_want; new < nr_irqs; new++) {
-		desc_new = irq_to_desc_alloc_node(new, node);
-		if (!desc_new) {
-			printk(KERN_INFO "can not get irq_desc for %d\n", new);
-			continue;
-		}
-		cfg_new = desc_new->chip_data;
-
-		if (cfg_new->vector != 0)
-			continue;
+	unsigned int ret = 0;
+	int irq;
 
-		desc_new = move_irq_desc(desc_new, node);
-		cfg_new = desc_new->chip_data;
+	if (from < nr_irqs_gsi)
+		from = nr_irqs_gsi;
 
-		if (__assign_irq_vector(new, cfg_new, apic->target_cpus()) == 0)
-			irq = new;
-		break;
+	irq = alloc_irq_from(from, node);
+	if (irq < 0)
+		return 0;
+	cfg = alloc_irq_cfg(irq, node);
+	if (!cfg) {
+		free_irq_at(irq, NULL);
+		return 0;
 	}
-	raw_spin_unlock_irqrestore(&vector_lock, flags);
 
-	if (irq > 0)
-		dynamic_irq_init_keep_chip_data(irq);
+	raw_spin_lock_irqsave(&vector_lock, flags);
+	if (!__assign_irq_vector(irq, cfg, apic->target_cpus()))
+		ret = irq;
+	raw_spin_unlock_irqrestore(&vector_lock, flags);
 
-	return irq;
+	if (ret) {
+		set_irq_chip_data(irq, cfg);
+		irq_clear_status_flags(irq, IRQ_NOREQUEST);
+	} else {
+		free_irq_at(irq, cfg);
+	}
+	return ret;
 }
 
 int create_irq(void)
 {
-	int node = cpu_to_node(boot_cpu_id);
+	int node = cpu_to_node(0);
 	unsigned int irq_want;
 	int irq;
 
@@ -3301,14 +3104,16 @@ int create_irq(void)
 
 void destroy_irq(unsigned int irq)
 {
+	struct irq_cfg *cfg = get_irq_chip_data(irq);
 	unsigned long flags;
 
-	dynamic_irq_cleanup_keep_chip_data(irq);
+	irq_set_status_flags(irq, IRQ_NOREQUEST|IRQ_NOPROBE);
 
 	free_irte(irq);
 	raw_spin_lock_irqsave(&vector_lock, flags);
-	__clear_irq_vector(irq, get_irq_chip_data(irq));
+	__clear_irq_vector(irq, cfg);
 	raw_spin_unlock_irqrestore(&vector_lock, flags);
+	free_irq_at(irq, cfg);
 }
 
 /*
@@ -3332,7 +3137,7 @@ static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq,
 
 	dest = apic->cpu_mask_to_apicid_and(cfg->domain, apic->target_cpus());
 
-	if (irq_remapped(irq)) {
+	if (irq_remapped(get_irq_chip_data(irq))) {
 		struct irte irte;
 		int ir_index;
 		u16 sub_handle;
@@ -3340,14 +3145,7 @@ static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq,
 		ir_index = map_irq_to_irte_handle(irq, &sub_handle);
 		BUG_ON(ir_index == -1);
 
-		memset (&irte, 0, sizeof(irte));
-
-		irte.present = 1;
-		irte.dst_mode = apic->irq_dest_mode;
-		irte.trigger_mode = 0; /* edge */
-		irte.dlvry_mode = apic->irq_delivery_mode;
-		irte.vector = cfg->vector;
-		irte.dest_id = IRTE_DEST(dest);
+		prepare_irte(&irte, cfg->vector, dest);
 
 		/* Set source-id of interrupt request */
 		if (pdev)
@@ -3392,26 +3190,24 @@ static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq,
 }
 
 #ifdef CONFIG_SMP
-static int set_msi_irq_affinity(unsigned int irq, const struct cpumask *mask)
+static int
+msi_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
-	struct irq_cfg *cfg;
+	struct irq_cfg *cfg = data->chip_data;
 	struct msi_msg msg;
 	unsigned int dest;
 
-	if (set_desc_affinity(desc, mask, &dest))
+	if (__ioapic_set_affinity(data, mask, &dest))
 		return -1;
 
-	cfg = desc->chip_data;
-
-	get_cached_msi_msg_desc(desc, &msg);
+	__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);
 
-	write_msi_msg_desc(desc, &msg);
+	__write_msi_msg(data->msi_desc, &msg);
 
 	return 0;
 }
@@ -3421,17 +3217,17 @@ static int set_msi_irq_affinity(unsigned int irq, const struct cpumask *mask)
  * done in the process context using interrupt-remapping hardware.
  */
 static int
-ir_set_msi_irq_affinity(unsigned int irq, const struct cpumask *mask)
+ir_msi_set_affinity(struct irq_data *data, const struct cpumask *mask,
+		    bool force)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
-	struct irq_cfg *cfg = desc->chip_data;
-	unsigned int dest;
+	struct irq_cfg *cfg = data->chip_data;
+	unsigned int dest, irq = data->irq;
 	struct irte irte;
 
 	if (get_irte(irq, &irte))
 		return -1;
 
-	if (set_desc_affinity(desc, mask, &dest))
+	if (__ioapic_set_affinity(data, mask, &dest))
 		return -1;
 
 	irte.vector = cfg->vector;
@@ -3461,27 +3257,27 @@ ir_set_msi_irq_affinity(unsigned int irq, const struct cpumask *mask)
  * which implement the MSI or MSI-X Capability Structure.
  */
 static struct irq_chip msi_chip = {
-	.name		= "PCI-MSI",
-	.unmask		= unmask_msi_irq,
-	.mask		= mask_msi_irq,
-	.ack		= ack_apic_edge,
+	.name			= "PCI-MSI",
+	.irq_unmask		= unmask_msi_irq,
+	.irq_mask		= mask_msi_irq,
+	.irq_ack		= ack_apic_edge,
 #ifdef CONFIG_SMP
-	.set_affinity	= set_msi_irq_affinity,
+	.irq_set_affinity	= msi_set_affinity,
 #endif
-	.retrigger	= ioapic_retrigger_irq,
+	.irq_retrigger		= ioapic_retrigger_irq,
 };
 
 static struct irq_chip msi_ir_chip = {
-	.name		= "IR-PCI-MSI",
-	.unmask		= unmask_msi_irq,
-	.mask		= mask_msi_irq,
+	.name			= "IR-PCI-MSI",
+	.irq_unmask		= unmask_msi_irq,
+	.irq_mask		= mask_msi_irq,
 #ifdef CONFIG_INTR_REMAP
-	.ack		= ir_ack_apic_edge,
+	.irq_ack		= ir_ack_apic_edge,
 #ifdef CONFIG_SMP
-	.set_affinity	= ir_set_msi_irq_affinity,
+	.irq_set_affinity	= ir_msi_set_affinity,
 #endif
 #endif
-	.retrigger	= ioapic_retrigger_irq,
+	.irq_retrigger		= ioapic_retrigger_irq,
 };
 
 /*
@@ -3513,8 +3309,8 @@ static int msi_alloc_irte(struct pci_dev *dev, int irq, int nvec)
 
 static int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, int irq)
 {
-	int ret;
 	struct msi_msg msg;
+	int ret;
 
 	ret = msi_compose_msg(dev, irq, &msg, -1);
 	if (ret < 0)
@@ -3523,12 +3319,8 @@ static int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, int irq)
 	set_irq_msi(irq, msidesc);
 	write_msi_msg(irq, &msg);
 
-	if (irq_remapped(irq)) {
-		struct irq_desc *desc = irq_to_desc(irq);
-		/*
-		 * irq migration in process context
-		 */
-		desc->status |= IRQ_MOVE_PCNTXT;
+	if (irq_remapped(get_irq_chip_data(irq))) {
+		irq_set_status_flags(irq, IRQ_MOVE_PCNTXT);
 		set_irq_chip_and_handler_name(irq, &msi_ir_chip, handle_edge_irq, "edge");
 	} else
 		set_irq_chip_and_handler_name(irq, &msi_chip, handle_edge_irq, "edge");
@@ -3538,15 +3330,12 @@ static int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, int irq)
 	return 0;
 }
 
-int arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
+int native_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 {
-	unsigned int irq;
-	int ret, sub_handle;
+	int node, ret, sub_handle, index = 0;
+	unsigned int irq, irq_want;
 	struct msi_desc *msidesc;
-	unsigned int irq_want;
 	struct intel_iommu *iommu = NULL;
-	int index = 0;
-	int node;
 
 	/* x86 doesn't support multiple MSI yet */
 	if (type == PCI_CAP_ID_MSI && nvec > 1)
@@ -3599,25 +3388,24 @@ error:
 	return ret;
 }
 
-void arch_teardown_msi_irq(unsigned int irq)
+void native_teardown_msi_irq(unsigned int irq)
 {
 	destroy_irq(irq);
 }
 
 #if defined (CONFIG_DMAR) || defined (CONFIG_INTR_REMAP)
 #ifdef CONFIG_SMP
-static int dmar_msi_set_affinity(unsigned int irq, const struct cpumask *mask)
+static int
+dmar_msi_set_affinity(struct irq_data *data, const struct cpumask *mask,
+		      bool force)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
-	struct irq_cfg *cfg;
+	struct irq_cfg *cfg = data->chip_data;
+	unsigned int dest, irq = data->irq;
 	struct msi_msg msg;
-	unsigned int dest;
 
-	if (set_desc_affinity(desc, mask, &dest))
+	if (__ioapic_set_affinity(data, mask, &dest))
 		return -1;
 
-	cfg = desc->chip_data;
-
 	dmar_msi_read(irq, &msg);
 
 	msg.data &= ~MSI_DATA_VECTOR_MASK;
@@ -3633,14 +3421,14 @@ static int dmar_msi_set_affinity(unsigned int irq, const struct cpumask *mask)
 #endif /* CONFIG_SMP */
 
 static struct irq_chip dmar_msi_type = {
-	.name = "DMAR_MSI",
-	.unmask = dmar_msi_unmask,
-	.mask = dmar_msi_mask,
-	.ack = ack_apic_edge,
+	.name			= "DMAR_MSI",
+	.irq_unmask		= dmar_msi_unmask,
+	.irq_mask		= dmar_msi_mask,
+	.irq_ack		= ack_apic_edge,
 #ifdef CONFIG_SMP
-	.set_affinity = dmar_msi_set_affinity,
+	.irq_set_affinity	= dmar_msi_set_affinity,
 #endif
-	.retrigger = ioapic_retrigger_irq,
+	.irq_retrigger		= ioapic_retrigger_irq,
 };
 
 int arch_setup_dmar_msi(unsigned int irq)
@@ -3661,26 +3449,24 @@ int arch_setup_dmar_msi(unsigned int irq)
 #ifdef CONFIG_HPET_TIMER
 
 #ifdef CONFIG_SMP
-static int hpet_msi_set_affinity(unsigned int irq, const struct cpumask *mask)
+static int hpet_msi_set_affinity(struct irq_data *data,
+				 const struct cpumask *mask, bool force)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
-	struct irq_cfg *cfg;
+	struct irq_cfg *cfg = data->chip_data;
 	struct msi_msg msg;
 	unsigned int dest;
 
-	if (set_desc_affinity(desc, mask, &dest))
+	if (__ioapic_set_affinity(data, mask, &dest))
 		return -1;
 
-	cfg = desc->chip_data;
-
-	hpet_msi_read(irq, &msg);
+	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(irq, &msg);
+	hpet_msi_write(data->handler_data, &msg);
 
 	return 0;
 }
@@ -3688,34 +3474,33 @@ static int hpet_msi_set_affinity(unsigned int irq, const struct cpumask *mask)
 #endif /* CONFIG_SMP */
 
 static struct irq_chip ir_hpet_msi_type = {
-	.name = "IR-HPET_MSI",
-	.unmask = hpet_msi_unmask,
-	.mask = hpet_msi_mask,
+	.name			= "IR-HPET_MSI",
+	.irq_unmask		= hpet_msi_unmask,
+	.irq_mask		= hpet_msi_mask,
 #ifdef CONFIG_INTR_REMAP
-	.ack = ir_ack_apic_edge,
+	.irq_ack		= ir_ack_apic_edge,
 #ifdef CONFIG_SMP
-	.set_affinity = ir_set_msi_irq_affinity,
+	.irq_set_affinity	= ir_msi_set_affinity,
 #endif
 #endif
-	.retrigger = ioapic_retrigger_irq,
+	.irq_retrigger		= ioapic_retrigger_irq,
 };
 
 static struct irq_chip hpet_msi_type = {
 	.name = "HPET_MSI",
-	.unmask = hpet_msi_unmask,
-	.mask = hpet_msi_mask,
-	.ack = ack_apic_edge,
+	.irq_unmask = hpet_msi_unmask,
+	.irq_mask = hpet_msi_mask,
+	.irq_ack = ack_apic_edge,
 #ifdef CONFIG_SMP
-	.set_affinity = hpet_msi_set_affinity,
+	.irq_set_affinity = hpet_msi_set_affinity,
 #endif
-	.retrigger = ioapic_retrigger_irq,
+	.irq_retrigger = ioapic_retrigger_irq,
 };
 
 int arch_setup_hpet_msi(unsigned int irq, unsigned int id)
 {
-	int ret;
 	struct msi_msg msg;
-	struct irq_desc *desc = irq_to_desc(irq);
+	int ret;
 
 	if (intr_remapping_enabled) {
 		struct intel_iommu *iommu = map_hpet_to_ir(id);
@@ -3733,9 +3518,9 @@ int arch_setup_hpet_msi(unsigned int irq, unsigned int id)
 	if (ret < 0)
 		return ret;
 
-	hpet_msi_write(irq, &msg);
-	desc->status |= IRQ_MOVE_PCNTXT;
-	if (irq_remapped(irq))
+	hpet_msi_write(get_irq_data(irq), &msg);
+	irq_set_status_flags(irq, IRQ_MOVE_PCNTXT);
+	if (irq_remapped(get_irq_chip_data(irq)))
 		set_irq_chip_and_handler_name(irq, &ir_hpet_msi_type,
 					      handle_edge_irq, "edge");
 	else
@@ -3768,33 +3553,30 @@ static void target_ht_irq(unsigned int irq, unsigned int dest, u8 vector)
 	write_ht_irq_msg(irq, &msg);
 }
 
-static int set_ht_irq_affinity(unsigned int irq, const struct cpumask *mask)
+static int
+ht_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
-	struct irq_cfg *cfg;
+	struct irq_cfg *cfg = data->chip_data;
 	unsigned int dest;
 
-	if (set_desc_affinity(desc, mask, &dest))
+	if (__ioapic_set_affinity(data, mask, &dest))
 		return -1;
 
-	cfg = desc->chip_data;
-
-	target_ht_irq(irq, dest, cfg->vector);
-
+	target_ht_irq(data->irq, dest, cfg->vector);
 	return 0;
 }
 
 #endif
 
 static struct irq_chip ht_irq_chip = {
-	.name		= "PCI-HT",
-	.mask		= mask_ht_irq,
-	.unmask		= unmask_ht_irq,
-	.ack		= ack_apic_edge,
+	.name			= "PCI-HT",
+	.irq_mask		= mask_ht_irq,
+	.irq_unmask		= unmask_ht_irq,
+	.irq_ack		= ack_apic_edge,
 #ifdef CONFIG_SMP
-	.set_affinity	= set_ht_irq_affinity,
+	.irq_set_affinity	= ht_set_affinity,
 #endif
-	.retrigger	= ioapic_retrigger_irq,
+	.irq_retrigger		= ioapic_retrigger_irq,
 };
 
 int arch_setup_ht_irq(unsigned int irq, struct pci_dev *dev)
@@ -3867,6 +3649,11 @@ void __init probe_nr_irqs_gsi(void)
 	printk(KERN_DEBUG "nr_irqs_gsi: %d\n", nr_irqs_gsi);
 }
 
+int get_nr_irqs_gsi(void)
+{
+	return nr_irqs_gsi;
+}
+
 #ifdef CONFIG_SPARSE_IRQ
 int __init arch_probe_nr_irqs(void)
 {
@@ -3885,14 +3672,13 @@ int __init arch_probe_nr_irqs(void)
 	if (nr < nr_irqs)
 		nr_irqs = nr;
 
-	return 0;
+	return NR_IRQS_LEGACY;
 }
 #endif
 
 static int __io_apic_set_pci_routing(struct device *dev, int irq,
 				struct io_apic_irq_attr *irq_attr)
 {
-	struct irq_desc *desc;
 	struct irq_cfg *cfg;
 	int node;
 	int ioapic, pin;
@@ -3908,13 +3694,11 @@ static int __io_apic_set_pci_routing(struct device *dev, int irq,
 	if (dev)
 		node = dev_to_node(dev);
 	else
-		node = cpu_to_node(boot_cpu_id);
+		node = cpu_to_node(0);
 
-	desc = irq_to_desc_alloc_node(irq, node);
-	if (!desc) {
-		printk(KERN_INFO "can not get irq_desc %d\n", irq);
+	cfg = alloc_irq_and_cfg_at(irq, node);
+	if (!cfg)
 		return 0;
-	}
 
 	pin = irq_attr->ioapic_pin;
 	trigger = irq_attr->trigger;
@@ -3924,15 +3708,14 @@ static int __io_apic_set_pci_routing(struct device *dev, int irq,
 	 * IRQs < 16 are already in the irq_2_pin[] map
 	 */
 	if (irq >= legacy_pic->nr_legacy_irqs) {
-		cfg = desc->chip_data;
-		if (add_pin_to_irq_node_nopanic(cfg, node, ioapic, pin)) {
+		if (__add_pin_to_irq_node(cfg, node, ioapic, pin)) {
 			printk(KERN_INFO "can not add pin %d for irq %d\n",
 				pin, irq);
 			return 0;
 		}
 	}
 
-	setup_IO_APIC_irq(ioapic, pin, irq, desc, trigger, polarity);
+	setup_ioapic_irq(ioapic, pin, irq, cfg, trigger, polarity);
 
 	return 0;
 }
@@ -4125,14 +3908,14 @@ void __init setup_ioapic_dest(void)
 		 */
 		if (desc->status &
 		    (IRQ_NO_BALANCING | IRQ_AFFINITY_SET))
-			mask = desc->affinity;
+			mask = desc->irq_data.affinity;
 		else
 			mask = apic->target_cpus();
 
 		if (intr_remapping_enabled)
-			set_ir_ioapic_affinity_irq_desc(desc, mask);
+			ir_ioapic_set_affinity(&desc->irq_data, mask, false);
 		else
-			set_ioapic_affinity_irq_desc(desc, mask);
+			ioapic_set_affinity(&desc->irq_data, mask, false);
 	}
 
 }
@@ -4316,19 +4099,18 @@ void __init mp_register_ioapic(int id, u32 address, u32 gsi_base)
 void __init pre_init_apic_IRQ0(void)
 {
 	struct irq_cfg *cfg;
-	struct irq_desc *desc;
 
 	printk(KERN_INFO "Early APIC setup for system timer0\n");
 #ifndef CONFIG_SMP
 	phys_cpu_present_map = physid_mask_of_physid(boot_cpu_physical_apicid);
 #endif
-	desc = irq_to_desc_alloc_node(0, 0);
+	/* Make sure the irq descriptor is set up */
+	cfg = alloc_irq_and_cfg_at(0, 0);
 
 	setup_local_APIC();
 
-	cfg = irq_cfg(0);
 	add_pin_to_irq_node(cfg, 0, 0, 0);
 	set_irq_chip_and_handler_name(0, &ioapic_chip, handle_edge_irq, "edge");
 
-	setup_IO_APIC_irq(0, 0, 0, desc, 0, 0);
+	setup_ioapic_irq(0, 0, 0, cfg, 0, 0);
 }
diff --git a/arch/x86/kernel/apic/nmi.c b/arch/x86/kernel/apic/nmi.c
index a43f71cb30f..c90041ccb74 100644
--- a/arch/x86/kernel/apic/nmi.c
+++ b/arch/x86/kernel/apic/nmi.c
@@ -178,7 +178,7 @@ int __init check_nmi_watchdog(void)
 error:
 	if (nmi_watchdog == NMI_IO_APIC) {
 		if (!timer_through_8259)
-			legacy_pic->chip->mask(0);
+			legacy_pic->mask(0);
 		on_each_cpu(__acpi_nmi_disable, NULL, 1);
 	}
 
diff --git a/arch/x86/kernel/apic/probe_64.c b/arch/x86/kernel/apic/probe_64.c
index 83e9be4778e..f9e4e6a5407 100644
--- a/arch/x86/kernel/apic/probe_64.c
+++ b/arch/x86/kernel/apic/probe_64.c
@@ -54,6 +54,9 @@ static int apicid_phys_pkg_id(int initial_apic_id, int index_msb)
  */
 void __init default_setup_apic_routing(void)
 {
+
+	enable_IR_x2apic();
+
 #ifdef CONFIG_X86_X2APIC
 	if (x2apic_mode
 #ifdef CONFIG_X86_UV
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index ba5f62f45f0..a8b4d91b839 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -148,7 +148,7 @@ static void __cpuinit amd_k7_smp_check(struct cpuinfo_x86 *c)
 {
 #ifdef CONFIG_SMP
 	/* calling is from identify_secondary_cpu() ? */
-	if (c->cpu_index == boot_cpu_id)
+	if (!c->cpu_index)
 		return;
 
 	/*
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index f2f9ac7da25..15c671385f5 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -665,7 +665,7 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
 		this_cpu->c_early_init(c);
 
 #ifdef CONFIG_SMP
-	c->cpu_index = boot_cpu_id;
+	c->cpu_index = 0;
 #endif
 	filter_cpuid_features(c, false);
 }
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index b4389441efb..695f17731e2 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -170,7 +170,7 @@ static void __cpuinit intel_smp_check(struct cpuinfo_x86 *c)
 {
 #ifdef CONFIG_SMP
 	/* calling is from identify_secondary_cpu() ? */
-	if (c->cpu_index == boot_cpu_id)
+	if (!c->cpu_index)
 		return;
 
 	/*
diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c
index ebdb85cf268..76b8cd953de 100644
--- a/arch/x86/kernel/early-quirks.c
+++ b/arch/x86/kernel/early-quirks.c
@@ -97,7 +97,6 @@ static void __init nvidia_bugs(int num, int slot, int func)
 }
 
 #if defined(CONFIG_ACPI) && defined(CONFIG_X86_IO_APIC)
-#if defined(CONFIG_ACPI) && defined(CONFIG_X86_IO_APIC)
 static u32 __init ati_ixp4x0_rev(int num, int slot, int func)
 {
 	u32 d;
@@ -115,7 +114,6 @@ static u32 __init ati_ixp4x0_rev(int num, int slot, int func)
 	d &= 0xff;
 	return d;
 }
-#endif
 
 static void __init ati_bugs(int num, int slot, int func)
 {
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index 7494999141b..efaf906daf9 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -440,9 +440,9 @@ static int hpet_legacy_next_event(unsigned long delta,
 static DEFINE_PER_CPU(struct hpet_dev *, cpu_hpet_dev);
 static struct hpet_dev	*hpet_devs;
 
-void hpet_msi_unmask(unsigned int irq)
+void hpet_msi_unmask(struct irq_data *data)
 {
-	struct hpet_dev *hdev = get_irq_data(irq);
+	struct hpet_dev *hdev = data->handler_data;
 	unsigned int cfg;
 
 	/* unmask it */
@@ -451,10 +451,10 @@ void hpet_msi_unmask(unsigned int irq)
 	hpet_writel(cfg, HPET_Tn_CFG(hdev->num));
 }
 
-void hpet_msi_mask(unsigned int irq)
+void hpet_msi_mask(struct irq_data *data)
 {
+	struct hpet_dev *hdev = data->handler_data;
 	unsigned int cfg;
-	struct hpet_dev *hdev = get_irq_data(irq);
 
 	/* mask it */
 	cfg = hpet_readl(HPET_Tn_CFG(hdev->num));
@@ -462,18 +462,14 @@ void hpet_msi_mask(unsigned int irq)
 	hpet_writel(cfg, HPET_Tn_CFG(hdev->num));
 }
 
-void hpet_msi_write(unsigned int irq, struct msi_msg *msg)
+void hpet_msi_write(struct hpet_dev *hdev, struct msi_msg *msg)
 {
-	struct hpet_dev *hdev = get_irq_data(irq);
-
 	hpet_writel(msg->data, HPET_Tn_ROUTE(hdev->num));
 	hpet_writel(msg->address_lo, HPET_Tn_ROUTE(hdev->num) + 4);
 }
 
-void hpet_msi_read(unsigned int irq, struct msi_msg *msg)
+void hpet_msi_read(struct hpet_dev *hdev, struct msi_msg *msg)
 {
-	struct hpet_dev *hdev = get_irq_data(irq);
-
 	msg->data = hpet_readl(HPET_Tn_ROUTE(hdev->num));
 	msg->address_lo = hpet_readl(HPET_Tn_ROUTE(hdev->num) + 4);
 	msg->address_hi = 0;
diff --git a/arch/x86/kernel/i8259.c b/arch/x86/kernel/i8259.c
index cafa7c80ac9..20757cb2efa 100644
--- a/arch/x86/kernel/i8259.c
+++ b/arch/x86/kernel/i8259.c
@@ -29,24 +29,10 @@
  * plus some generic x86 specific things if generic specifics makes
  * any sense at all.
  */
+static void init_8259A(int auto_eoi);
 
 static int i8259A_auto_eoi;
 DEFINE_RAW_SPINLOCK(i8259A_lock);
-static void mask_and_ack_8259A(unsigned int);
-static void mask_8259A(void);
-static void unmask_8259A(void);
-static void disable_8259A_irq(unsigned int irq);
-static void enable_8259A_irq(unsigned int irq);
-static void init_8259A(int auto_eoi);
-static int i8259A_irq_pending(unsigned int irq);
-
-struct irq_chip i8259A_chip = {
-	.name		= "XT-PIC",
-	.mask		= disable_8259A_irq,
-	.disable	= disable_8259A_irq,
-	.unmask		= enable_8259A_irq,
-	.mask_ack	= mask_and_ack_8259A,
-};
 
 /*
  * 8259A PIC functions to handle ISA devices:
@@ -68,7 +54,7 @@ unsigned int cached_irq_mask = 0xffff;
  */
 unsigned long io_apic_irqs;
 
-static void disable_8259A_irq(unsigned int irq)
+static void mask_8259A_irq(unsigned int irq)
 {
 	unsigned int mask = 1 << irq;
 	unsigned long flags;
@@ -82,7 +68,12 @@ static void disable_8259A_irq(unsigned int irq)
 	raw_spin_unlock_irqrestore(&i8259A_lock, flags);
 }
 
-static void enable_8259A_irq(unsigned int irq)
+static void disable_8259A_irq(struct irq_data *data)
+{
+	mask_8259A_irq(data->irq);
+}
+
+static void unmask_8259A_irq(unsigned int irq)
 {
 	unsigned int mask = ~(1 << irq);
 	unsigned long flags;
@@ -96,6 +87,11 @@ static void enable_8259A_irq(unsigned int irq)
 	raw_spin_unlock_irqrestore(&i8259A_lock, flags);
 }
 
+static void enable_8259A_irq(struct irq_data *data)
+{
+	unmask_8259A_irq(data->irq);
+}
+
 static int i8259A_irq_pending(unsigned int irq)
 {
 	unsigned int mask = 1<<irq;
@@ -117,7 +113,7 @@ static void make_8259A_irq(unsigned int irq)
 	disable_irq_nosync(irq);
 	io_apic_irqs &= ~(1<<irq);
 	set_irq_chip_and_handler_name(irq, &i8259A_chip, handle_level_irq,
-				      "XT");
+				      i8259A_chip.name);
 	enable_irq(irq);
 }
 
@@ -150,8 +146,9 @@ static inline int i8259A_irq_real(unsigned int irq)
  * first, _then_ send the EOI, and the order of EOI
  * to the two 8259s is important!
  */
-static void mask_and_ack_8259A(unsigned int irq)
+static void mask_and_ack_8259A(struct irq_data *data)
 {
+	unsigned int irq = data->irq;
 	unsigned int irqmask = 1 << irq;
 	unsigned long flags;
 
@@ -223,6 +220,14 @@ spurious_8259A_irq:
 	}
 }
 
+struct irq_chip i8259A_chip = {
+	.name		= "XT-PIC",
+	.irq_mask	= disable_8259A_irq,
+	.irq_disable	= disable_8259A_irq,
+	.irq_unmask	= enable_8259A_irq,
+	.irq_mask_ack	= mask_and_ack_8259A,
+};
+
 static char irq_trigger[2];
 /**
  * ELCR registers (0x4d0, 0x4d1) control edge/level of IRQ
@@ -342,9 +347,9 @@ static void init_8259A(int auto_eoi)
 		 * In AEOI mode we just have to mask the interrupt
 		 * when acking.
 		 */
-		i8259A_chip.mask_ack = disable_8259A_irq;
+		i8259A_chip.irq_mask_ack = disable_8259A_irq;
 	else
-		i8259A_chip.mask_ack = mask_and_ack_8259A;
+		i8259A_chip.irq_mask_ack = mask_and_ack_8259A;
 
 	udelay(100);		/* wait for 8259A to initialize */
 
@@ -363,14 +368,6 @@ static void init_8259A(int auto_eoi)
 static void legacy_pic_noop(void) { };
 static void legacy_pic_uint_noop(unsigned int unused) { };
 static void legacy_pic_int_noop(int unused) { };
-
-static struct irq_chip dummy_pic_chip  = {
-	.name = "dummy pic",
-	.mask = legacy_pic_uint_noop,
-	.unmask = legacy_pic_uint_noop,
-	.disable = legacy_pic_uint_noop,
-	.mask_ack = legacy_pic_uint_noop,
-};
 static int legacy_pic_irq_pending_noop(unsigned int irq)
 {
 	return 0;
@@ -378,7 +375,9 @@ static int legacy_pic_irq_pending_noop(unsigned int irq)
 
 struct legacy_pic null_legacy_pic = {
 	.nr_legacy_irqs = 0,
-	.chip = &dummy_pic_chip,
+	.chip = &dummy_irq_chip,
+	.mask = legacy_pic_uint_noop,
+	.unmask = legacy_pic_uint_noop,
 	.mask_all = legacy_pic_noop,
 	.restore_mask = legacy_pic_noop,
 	.init = legacy_pic_int_noop,
@@ -389,7 +388,9 @@ struct legacy_pic null_legacy_pic = {
 struct legacy_pic default_legacy_pic = {
 	.nr_legacy_irqs = NR_IRQS_LEGACY,
 	.chip  = &i8259A_chip,
-	.mask_all  = mask_8259A,
+	.mask = mask_8259A_irq,
+	.unmask = unmask_8259A_irq,
+	.mask_all = mask_8259A,
 	.restore_mask = unmask_8259A,
 	.init = init_8259A,
 	.irq_pending = i8259A_irq_pending,
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 91fd0c70a18..d765bdc4807 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -159,7 +159,7 @@ int show_interrupts(struct seq_file *p, void *v)
 	seq_printf(p, "%*d: ", prec, i);
 	for_each_online_cpu(j)
 		seq_printf(p, "%10u ", kstat_irqs_cpu(i, j));
-	seq_printf(p, " %8s", desc->chip->name);
+	seq_printf(p, " %8s", desc->irq_data.chip->name);
 	seq_printf(p, "-%-8s", desc->name);
 
 	if (action) {
@@ -282,6 +282,7 @@ void fixup_irqs(void)
 	unsigned int irq, vector;
 	static int warned;
 	struct irq_desc *desc;
+	struct irq_data *data;
 
 	for_each_irq_desc(irq, desc) {
 		int break_affinity = 0;
@@ -296,7 +297,8 @@ void fixup_irqs(void)
 		/* interrupt's are disabled at this point */
 		raw_spin_lock(&desc->lock);
 
-		affinity = desc->affinity;
+		data = &desc->irq_data;
+		affinity = data->affinity;
 		if (!irq_has_action(irq) ||
 		    cpumask_equal(affinity, cpu_online_mask)) {
 			raw_spin_unlock(&desc->lock);
@@ -315,16 +317,16 @@ void fixup_irqs(void)
 			affinity = cpu_all_mask;
 		}
 
-		if (!(desc->status & IRQ_MOVE_PCNTXT) && desc->chip->mask)
-			desc->chip->mask(irq);
+		if (!(desc->status & IRQ_MOVE_PCNTXT) && data->chip->irq_mask)
+			data->chip->irq_mask(data);
 
-		if (desc->chip->set_affinity)
-			desc->chip->set_affinity(irq, affinity);
+		if (data->chip->irq_set_affinity)
+			data->chip->irq_set_affinity(data, affinity, true);
 		else if (!(warned++))
 			set_affinity = 0;
 
-		if (!(desc->status & IRQ_MOVE_PCNTXT) && desc->chip->unmask)
-			desc->chip->unmask(irq);
+		if (!(desc->status & IRQ_MOVE_PCNTXT) && data->chip->irq_unmask)
+			data->chip->irq_unmask(data);
 
 		raw_spin_unlock(&desc->lock);
 
@@ -355,10 +357,10 @@ void fixup_irqs(void)
 		if (irr  & (1 << (vector % 32))) {
 			irq = __get_cpu_var(vector_irq)[vector];
 
-			desc = irq_to_desc(irq);
+			data = irq_get_irq_data(irq);
 			raw_spin_lock(&desc->lock);
-			if (desc->chip->retrigger)
-				desc->chip->retrigger(irq);
+			if (data->chip->irq_retrigger)
+				data->chip->irq_retrigger(data);
 			raw_spin_unlock(&desc->lock);
 		}
 	}
diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c
index 990ae7cfc57..a91ab503e24 100644
--- a/arch/x86/kernel/irqinit.c
+++ b/arch/x86/kernel/irqinit.c
@@ -100,6 +100,8 @@ int vector_used_by_percpu_irq(unsigned int vector)
 
 void __init init_ISA_irqs(void)
 {
+	struct irq_chip *chip = legacy_pic->chip;
+	const char *name = chip->name;
 	int i;
 
 #if defined(CONFIG_X86_64) || defined(CONFIG_X86_LOCAL_APIC)
@@ -107,19 +109,8 @@ void __init init_ISA_irqs(void)
 #endif
 	legacy_pic->init(0);
 
-	/*
-	 * 16 old-style INTA-cycle interrupts:
-	 */
-	for (i = 0; i < legacy_pic->nr_legacy_irqs; i++) {
-		struct irq_desc *desc = irq_to_desc(i);
-
-		desc->status = IRQ_DISABLED;
-		desc->action = NULL;
-		desc->depth = 1;
-
-		set_irq_chip_and_handler_name(i, &i8259A_chip,
-					      handle_level_irq, "XT");
-	}
+	for (i = 0; i < legacy_pic->nr_legacy_irqs; i++)
+		set_irq_chip_and_handler_name(i, chip, handle_level_irq, name);
 }
 
 void __init init_IRQ(void)
diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c
index 035c8c52918..b3ea9db39db 100644
--- a/arch/x86/kernel/machine_kexec_64.c
+++ b/arch/x86/kernel/machine_kexec_64.c
@@ -36,7 +36,7 @@ static int init_one_level2_page(struct kimage *image, pgd_t *pgd,
 		if (!page)
 			goto out;
 		pud = (pud_t *)page_address(page);
-		memset(pud, 0, PAGE_SIZE);
+		clear_page(pud);
 		set_pgd(pgd, __pgd(__pa(pud) | _KERNPG_TABLE));
 	}
 	pud = pud_offset(pgd, addr);
@@ -45,7 +45,7 @@ static int init_one_level2_page(struct kimage *image, pgd_t *pgd,
 		if (!page)
 			goto out;
 		pmd = (pmd_t *)page_address(page);
-		memset(pmd, 0, PAGE_SIZE);
+		clear_page(pmd);
 		set_pud(pud, __pud(__pa(pmd) | _KERNPG_TABLE));
 	}
 	pmd = pmd_offset(pud, addr);
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index e3af342fe83..7a4cf14223b 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -84,7 +84,7 @@ static int __init reboot_setup(char *str)
 			}
 				/* we will leave sorting out the final value
 				   when we are ready to reboot, since we might not
-				   have set up boot_cpu_id or smp_num_cpu */
+				   have detected BSP APIC ID or smp_num_cpu */
 			break;
 #endif /* CONFIG_SMP */
 
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index c3a4fbb2b99..7d5ee08c982 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -125,7 +125,6 @@ unsigned long max_pfn_mapped;
 RESERVE_BRK(dmi_alloc, 65536);
 #endif
 
-unsigned int boot_cpu_id __read_mostly;
 
 static __initdata unsigned long _brk_start = (unsigned long)__brk_base;
 unsigned long _brk_end = (unsigned long)__brk_base;
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index a60df9ae645..2335c15c93a 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -253,7 +253,7 @@ void __init setup_per_cpu_areas(void)
 		 * Up to this point, the boot CPU has been using .init.data
 		 * area.  Reload any changed state for the boot CPU.
 		 */
-		if (cpu == boot_cpu_id)
+		if (!cpu)
 			switch_to_new_gdt(cpu);
 	}
 
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 8b3bfc4dd70..864b386f6c0 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -324,9 +324,9 @@ notrace static void __cpuinit start_secondary(void *unused)
 	check_tsc_sync_target();
 
 	if (nmi_watchdog == NMI_IO_APIC) {
-		legacy_pic->chip->mask(0);
+		legacy_pic->mask(0);
 		enable_NMI_through_LVT0();
-		legacy_pic->chip->unmask(0);
+		legacy_pic->unmask(0);
 	}
 
 	/* This must be done before setting cpu_online_mask */
@@ -1109,8 +1109,6 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
 	}
 	set_cpu_sibling_map(0);
 
-	enable_IR_x2apic();
-	default_setup_apic_routing();
 
 	if (smp_sanity_check(max_cpus) < 0) {
 		printk(KERN_INFO "SMP disabled\n");
@@ -1118,6 +1116,8 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
 		goto out;
 	}
 
+	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)",
diff --git a/arch/x86/kernel/uv_irq.c b/arch/x86/kernel/uv_irq.c
index 1132129db79..7b24460917d 100644
--- a/arch/x86/kernel/uv_irq.c
+++ b/arch/x86/kernel/uv_irq.c
@@ -28,34 +28,21 @@ struct uv_irq_2_mmr_pnode{
 static spinlock_t		uv_irq_lock;
 static struct rb_root		uv_irq_root;
 
-static int uv_set_irq_affinity(unsigned int, const struct cpumask *);
+static int uv_set_irq_affinity(struct irq_data *, const struct cpumask *, bool);
 
-static void uv_noop(unsigned int irq)
-{
-}
-
-static unsigned int uv_noop_ret(unsigned int irq)
-{
-	return 0;
-}
+static void uv_noop(struct irq_data *data) { }
 
-static void uv_ack_apic(unsigned int irq)
+static void uv_ack_apic(struct irq_data *data)
 {
 	ack_APIC_irq();
 }
 
 static struct irq_chip uv_irq_chip = {
-	.name		= "UV-CORE",
-	.startup	= uv_noop_ret,
-	.shutdown	= uv_noop,
-	.enable		= uv_noop,
-	.disable	= uv_noop,
-	.ack		= uv_noop,
-	.mask		= uv_noop,
-	.unmask		= uv_noop,
-	.eoi		= uv_ack_apic,
-	.end		= uv_noop,
-	.set_affinity	= uv_set_irq_affinity,
+	.name			= "UV-CORE",
+	.irq_mask		= uv_noop,
+	.irq_unmask		= uv_noop,
+	.irq_eoi		= uv_ack_apic,
+	.irq_set_affinity	= uv_set_irq_affinity,
 };
 
 /*
@@ -144,26 +131,22 @@ 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_desc *desc = irq_to_desc(irq);
-	struct irq_cfg *cfg;
-	int mmr_pnode;
+	struct irq_cfg *cfg = get_irq_chip_data(irq);
 	unsigned long mmr_value;
 	struct uv_IO_APIC_route_entry *entry;
-	int err;
+	int mmr_pnode, err;
 
 	BUILD_BUG_ON(sizeof(struct uv_IO_APIC_route_entry) !=
 			sizeof(unsigned long));
 
-	cfg = irq_cfg(irq);
-
 	err = assign_irq_vector(irq, cfg, eligible_cpu);
 	if (err != 0)
 		return err;
 
 	if (limit == UV_AFFINITY_CPU)
-		desc->status |= IRQ_NO_BALANCING;
+		irq_set_status_flags(irq, IRQ_NO_BALANCING);
 	else
-		desc->status |= IRQ_MOVE_PCNTXT;
+		irq_set_status_flags(irq, IRQ_MOVE_PCNTXT);
 
 	set_irq_chip_and_handler_name(irq, &uv_irq_chip, handle_percpu_irq,
 				      irq_name);
@@ -206,17 +189,17 @@ static void arch_disable_uv_irq(int mmr_pnode, unsigned long mmr_offset)
 	uv_write_global_mmr64(mmr_pnode, mmr_offset, mmr_value);
 }
 
-static int uv_set_irq_affinity(unsigned int irq, const struct cpumask *mask)
+static int
+uv_set_irq_affinity(struct irq_data *data, const struct cpumask *mask,
+		    bool force)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
-	struct irq_cfg *cfg = desc->chip_data;
+	struct irq_cfg *cfg = data->chip_data;
 	unsigned int dest;
-	unsigned long mmr_value;
+	unsigned long mmr_value, mmr_offset;
 	struct uv_IO_APIC_route_entry *entry;
-	unsigned long mmr_offset;
 	int mmr_pnode;
 
-	if (set_desc_affinity(desc, mask, &dest))
+	if (__ioapic_set_affinity(data, mask, &dest))
 		return -1;
 
 	mmr_value = 0;
@@ -231,7 +214,7 @@ static int uv_set_irq_affinity(unsigned int irq, const struct cpumask *mask)
 	entry->dest		= dest;
 
 	/* Get previously stored MMR and pnode of hub sourcing interrupts */
-	if (uv_irq_2_mmr_info(irq, &mmr_offset, &mmr_pnode))
+	if (uv_irq_2_mmr_info(data->irq, &mmr_offset, &mmr_pnode))
 		return -1;
 
 	uv_write_global_mmr64(mmr_pnode, mmr_offset, mmr_value);
diff --git a/arch/x86/kernel/visws_quirks.c b/arch/x86/kernel/visws_quirks.c
index e680ea52db9..3371bd053b8 100644
--- a/arch/x86/kernel/visws_quirks.c
+++ b/arch/x86/kernel/visws_quirks.c
@@ -66,10 +66,7 @@ static void __init visws_time_init(void)
 }
 
 /* Replaces the default init_ISA_irqs in the generic setup */
-static void __init visws_pre_intr_init(void)
-{
-	init_VISWS_APIC_irqs();
-}
+static void __init visws_pre_intr_init(void);
 
 /* Quirk for machine specific memory setup. */
 
@@ -429,67 +426,34 @@ static int is_co_apic(unsigned int irq)
 /*
  * This is the SGI Cobalt (IO-)APIC:
  */
-
-static void enable_cobalt_irq(unsigned int irq)
+static void enable_cobalt_irq(struct irq_data *data)
 {
-	co_apic_set(is_co_apic(irq), irq);
+	co_apic_set(is_co_apic(data->irq), data->irq);
 }
 
-static void disable_cobalt_irq(unsigned int irq)
+static void disable_cobalt_irq(struct irq_data *data)
 {
-	int entry = is_co_apic(irq);
+	int entry = is_co_apic(data->irq);
 
 	co_apic_write(CO_APIC_LO(entry), CO_APIC_MASK);
 	co_apic_read(CO_APIC_LO(entry));
 }
 
-/*
- * "irq" really just serves to identify the device.  Here is where we
- * map this to the Cobalt APIC entry where it's physically wired.
- * This is called via request_irq -> setup_irq -> irq_desc->startup()
- */
-static unsigned int startup_cobalt_irq(unsigned int irq)
+static void ack_cobalt_irq(struct irq_data *data)
 {
 	unsigned long flags;
-	struct irq_desc *desc = irq_to_desc(irq);
 
 	spin_lock_irqsave(&cobalt_lock, flags);
-	if ((desc->status & (IRQ_DISABLED | IRQ_INPROGRESS | IRQ_WAITING)))
-		desc->status &= ~(IRQ_DISABLED | IRQ_INPROGRESS | IRQ_WAITING);
-	enable_cobalt_irq(irq);
-	spin_unlock_irqrestore(&cobalt_lock, flags);
-	return 0;
-}
-
-static void ack_cobalt_irq(unsigned int irq)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&cobalt_lock, flags);
-	disable_cobalt_irq(irq);
+	disable_cobalt_irq(data);
 	apic_write(APIC_EOI, APIC_EIO_ACK);
 	spin_unlock_irqrestore(&cobalt_lock, flags);
 }
 
-static void end_cobalt_irq(unsigned int irq)
-{
-	unsigned long flags;
-	struct irq_desc *desc = irq_to_desc(irq);
-
-	spin_lock_irqsave(&cobalt_lock, flags);
-	if (!(desc->status & (IRQ_DISABLED | IRQ_INPROGRESS)))
-		enable_cobalt_irq(irq);
-	spin_unlock_irqrestore(&cobalt_lock, flags);
-}
-
 static struct irq_chip cobalt_irq_type = {
-	.name =		"Cobalt-APIC",
-	.startup =	startup_cobalt_irq,
-	.shutdown =	disable_cobalt_irq,
-	.enable =	enable_cobalt_irq,
-	.disable =	disable_cobalt_irq,
-	.ack =		ack_cobalt_irq,
-	.end =		end_cobalt_irq,
+	.name		= "Cobalt-APIC",
+	.irq_enable	= enable_cobalt_irq,
+	.irq_disable	= disable_cobalt_irq,
+	.irq_ack	= ack_cobalt_irq,
 };
 
 
@@ -503,35 +467,34 @@ static struct irq_chip cobalt_irq_type = {
  * interrupt controller type, and through a special virtual interrupt-
  * controller. Device drivers only see the virtual interrupt sources.
  */
-static unsigned int startup_piix4_master_irq(unsigned int irq)
+static unsigned int startup_piix4_master_irq(struct irq_data *data)
 {
 	legacy_pic->init(0);
-
-	return startup_cobalt_irq(irq);
+	enable_cobalt_irq(data);
 }
 
-static void end_piix4_master_irq(unsigned int irq)
+static void end_piix4_master_irq(struct irq_data *data)
 {
 	unsigned long flags;
 
 	spin_lock_irqsave(&cobalt_lock, flags);
-	enable_cobalt_irq(irq);
+	enable_cobalt_irq(data);
 	spin_unlock_irqrestore(&cobalt_lock, flags);
 }
 
 static struct irq_chip piix4_master_irq_type = {
-	.name =		"PIIX4-master",
-	.startup =	startup_piix4_master_irq,
-	.ack =		ack_cobalt_irq,
-	.end =		end_piix4_master_irq,
+	.name		= "PIIX4-master",
+	.irq_startup	= startup_piix4_master_irq,
+	.irq_ack	= ack_cobalt_irq,
 };
 
+static void pii4_mask(struct irq_data *data) { }
 
 static struct irq_chip piix4_virtual_irq_type = {
-	.name =		"PIIX4-virtual",
+	.name		= "PIIX4-virtual",
+	.mask		= pii4_mask,
 };
 
-
 /*
  * PIIX4-8259 master/virtual functions to handle interrupt requests
  * from legacy devices: floppy, parallel, serial, rtc.
@@ -549,9 +512,8 @@ static struct irq_chip piix4_virtual_irq_type = {
  */
 static irqreturn_t piix4_master_intr(int irq, void *dev_id)
 {
-	int realirq;
-	struct irq_desc *desc;
 	unsigned long flags;
+	int realirq;
 
 	raw_spin_lock_irqsave(&i8259A_lock, flags);
 
@@ -592,18 +554,10 @@ static irqreturn_t piix4_master_intr(int irq, void *dev_id)
 
 	raw_spin_unlock_irqrestore(&i8259A_lock, flags);
 
-	desc = irq_to_desc(realirq);
-
 	/*
 	 * handle this 'virtual interrupt' as a Cobalt one now.
 	 */
-	kstat_incr_irqs_this_cpu(realirq, desc);
-
-	if (likely(desc->action != NULL))
-		handle_IRQ_event(realirq, desc->action);
-
-	if (!(desc->status & IRQ_DISABLED))
-		legacy_pic->chip->unmask(realirq);
+	generic_handle_irq(realirq);
 
 	return IRQ_HANDLED;
 
@@ -624,41 +578,35 @@ static struct irqaction cascade_action = {
 
 static inline void set_piix4_virtual_irq_type(void)
 {
-	piix4_virtual_irq_type.shutdown = i8259A_chip.mask;
 	piix4_virtual_irq_type.enable =	i8259A_chip.unmask;
 	piix4_virtual_irq_type.disable = i8259A_chip.mask;
+	piix4_virtual_irq_type.unmask =	i8259A_chip.unmask;
 }
 
-void init_VISWS_APIC_irqs(void)
+static void __init visws_pre_intr_init(void)
 {
 	int i;
 
-	for (i = 0; i < CO_IRQ_APIC0 + CO_APIC_LAST + 1; i++) {
-		struct irq_desc *desc = irq_to_desc(i);
-
-		desc->status = IRQ_DISABLED;
-		desc->action = 0;
-		desc->depth = 1;
+	set_piix4_virtual_irq_type();
 
-		if (i == 0) {
-			desc->chip = &cobalt_irq_type;
-		}
-		else if (i == CO_IRQ_IDE0) {
-			desc->chip = &cobalt_irq_type;
-		}
-		else if (i == CO_IRQ_IDE1) {
-			desc->chip = &cobalt_irq_type;
-		}
-		else if (i == CO_IRQ_8259) {
-			desc->chip = &piix4_master_irq_type;
-		}
-		else if (i < CO_IRQ_APIC0) {
-			set_piix4_virtual_irq_type();
-			desc->chip = &piix4_virtual_irq_type;
-		}
-		else if (IS_CO_APIC(i)) {
-			desc->chip = &cobalt_irq_type;
-		}
+	for (i = 0; i < CO_IRQ_APIC0 + CO_APIC_LAST + 1; i++) {
+		struct irq_chip *chip = NULL;
+
+		if (i == 0)
+			chip = &cobalt_irq_type;
+		else if (i == CO_IRQ_IDE0)
+			chip = &cobalt_irq_type;
+		else if (i == CO_IRQ_IDE1)
+			>chip = &cobalt_irq_type;
+		else if (i == CO_IRQ_8259)
+			chip = &piix4_master_irq_type;
+		else if (i < CO_IRQ_APIC0)
+			chip = &piix4_virtual_irq_type;
+		else if (IS_CO_APIC(i))
+			chip = &cobalt_irq_type;
+
+		if (chip)
+			set_irq_chip(i, chip);
 	}
 
 	setup_irq(CO_IRQ_8259, &master_action);
diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c
index cd6da6bf3ec..ceb2911aa43 100644
--- a/arch/x86/kernel/x86_init.c
+++ b/arch/x86/kernel/x86_init.c
@@ -6,10 +6,12 @@
 #include <linux/init.h>
 #include <linux/ioport.h>
 #include <linux/module.h>
+#include <linux/pci.h>
 
 #include <asm/bios_ebda.h>
 #include <asm/paravirt.h>
 #include <asm/pci_x86.h>
+#include <asm/pci.h>
 #include <asm/mpspec.h>
 #include <asm/setup.h>
 #include <asm/apic.h>
@@ -99,3 +101,8 @@ struct x86_platform_ops x86_platform = {
 };
 
 EXPORT_SYMBOL_GPL(x86_platform);
+struct x86_msi_ops x86_msi = {
+	.setup_msi_irqs = native_setup_msi_irqs,
+	.teardown_msi_irq = native_teardown_msi_irq,
+	.teardown_msi_irqs = default_teardown_msi_irqs,
+};
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 77d8c0f4817..22b06f7660f 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1056,14 +1056,13 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu)
 
 	vcpu->arch.apic = apic;
 
-	apic->regs_page = alloc_page(GFP_KERNEL);
+	apic->regs_page = alloc_page(GFP_KERNEL|__GFP_ZERO);
 	if (apic->regs_page == NULL) {
 		printk(KERN_ERR "malloc apic regs error for vcpu %x\n",
 		       vcpu->vcpu_id);
 		goto nomem_free_apic;
 	}
 	apic->regs = page_address(apic->regs_page);
-	memset(apic->regs, 0, PAGE_SIZE);
 	apic->vcpu = vcpu;
 
 	hrtimer_init(&apic->lapic_timer.timer, CLOCK_MONOTONIC,
diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c
index 9d5f5584845..73b1e1a1f48 100644
--- a/arch/x86/lguest/boot.c
+++ b/arch/x86/lguest/boot.c
@@ -791,22 +791,22 @@ static void lguest_flush_tlb_kernel(void)
  * simple as setting a bit.  We don't actually "ack" interrupts as such, we
  * just mask and unmask them.  I wonder if we should be cleverer?
  */
-static void disable_lguest_irq(unsigned int irq)
+static void disable_lguest_irq(struct irq_data *data)
 {
-	set_bit(irq, lguest_data.blocked_interrupts);
+	set_bit(data->irq, lguest_data.blocked_interrupts);
 }
 
-static void enable_lguest_irq(unsigned int irq)
+static void enable_lguest_irq(struct irq_data *data)
 {
-	clear_bit(irq, lguest_data.blocked_interrupts);
+	clear_bit(data->irq, lguest_data.blocked_interrupts);
 }
 
 /* This structure describes the lguest IRQ controller. */
 static struct irq_chip lguest_irq_controller = {
 	.name		= "lguest",
-	.mask		= disable_lguest_irq,
-	.mask_ack	= disable_lguest_irq,
-	.unmask		= enable_lguest_irq,
+	.irq_mask	= disable_lguest_irq,
+	.irq_mask_ack	= disable_lguest_irq,
+	.irq_unmask	= enable_lguest_irq,
 };
 
 /*
@@ -838,12 +838,12 @@ static void __init lguest_init_IRQ(void)
  * rather than set them in lguest_init_IRQ we are called here every time an
  * lguest device needs an interrupt.
  *
- * FIXME: irq_to_desc_alloc_node() can fail due to lack of memory, we should
+ * FIXME: irq_alloc_desc_at() can fail due to lack of memory, we should
  * pass that up!
  */
 void lguest_setup_irq(unsigned int irq)
 {
-	irq_to_desc_alloc_node(irq, 0);
+	irq_alloc_desc_at(irq, 0);
 	set_irq_chip_and_handler_name(irq, &lguest_irq_controller,
 				      handle_level_irq, "level");
 }
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index bca79091b9d..558f2d33207 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -67,7 +67,7 @@ static __init void *alloc_low_page(void)
 		panic("alloc_low_page: ran out of memory");
 
 	adr = __va(pfn * PAGE_SIZE);
-	memset(adr, 0, PAGE_SIZE);
+	clear_page(adr);
 	return adr;
 }
 
@@ -558,7 +558,7 @@ char swsusp_pg_dir[PAGE_SIZE]
 
 static inline void save_pg_dir(void)
 {
-	memcpy(swsusp_pg_dir, swapper_pg_dir, PAGE_SIZE);
+	copy_page(swsusp_pg_dir, swapper_pg_dir);
 }
 #else /* !CONFIG_ACPI_SLEEP */
 static inline void save_pg_dir(void)
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 9a6674689a2..7c48ad4faca 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -293,7 +293,7 @@ static __ref void *alloc_low_page(unsigned long *phys)
 		panic("alloc_low_page: ran out of memory");
 
 	adr = early_memremap(pfn * PAGE_SIZE, PAGE_SIZE);
-	memset(adr, 0, PAGE_SIZE);
+	clear_page(adr);
 	*phys  = pfn * PAGE_SIZE;
 	return adr;
 }
diff --git a/arch/x86/mm/k8topology_64.c b/arch/x86/mm/k8topology_64.c
index 970ed579d4e..240f86462a8 100644
--- a/arch/x86/mm/k8topology_64.c
+++ b/arch/x86/mm/k8topology_64.c
@@ -54,8 +54,8 @@ static __init int find_northbridge(void)
 static __init void early_get_boot_cpu_id(void)
 {
 	/*
-	 * need to get boot_cpu_id so can use that to create apicid_to_node
-	 * in k8_scan_nodes()
+	 * need to get the APIC ID of the BSP so can use that to
+	 * create apicid_to_node in k8_scan_nodes()
 	 */
 #ifdef CONFIG_X86_MPPARSE
 	/*
@@ -212,7 +212,7 @@ int __init k8_scan_nodes(void)
 	bits = boot_cpu_data.x86_coreid_bits;
 	cores = (1<<bits);
 	apicid_base = 0;
-	/* need to get boot_cpu_id early for system with apicid lifting */
+	/* get the APIC ID of the BSP early for systems with apicid lifting */
 	early_get_boot_cpu_id();
 	if (boot_cpu_physical_apicid > 0) {
 		pr_info("BSP APIC ID: %02x\n", boot_cpu_physical_apicid);
diff --git a/arch/x86/pci/Makefile b/arch/x86/pci/Makefile
index a0207a7fdf3..effd96e33f1 100644
--- a/arch/x86/pci/Makefile
+++ b/arch/x86/pci/Makefile
@@ -4,6 +4,7 @@ obj-$(CONFIG_PCI_BIOS)		+= pcbios.o
 obj-$(CONFIG_PCI_MMCONFIG)	+= mmconfig_$(BITS).o direct.o mmconfig-shared.o
 obj-$(CONFIG_PCI_DIRECT)	+= direct.o
 obj-$(CONFIG_PCI_OLPC)		+= olpc.o
+obj-$(CONFIG_PCI_XEN)		+= xen.o
 
 obj-y				+= fixup.o
 obj-$(CONFIG_ACPI)		+= acpi.o
diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c
index a0772af64ef..f7c8a399978 100644
--- a/arch/x86/pci/common.c
+++ b/arch/x86/pci/common.c
@@ -421,16 +421,10 @@ struct pci_bus * __devinit pcibios_scan_root(int busnum)
 
 	return bus;
 }
-
-int __init pcibios_init(void)
+void __init pcibios_set_cache_line_size(void)
 {
 	struct cpuinfo_x86 *c = &boot_cpu_data;
 
-	if (!raw_pci_ops) {
-		printk(KERN_WARNING "PCI: System does not support PCI\n");
-		return 0;
-	}
-
 	/*
 	 * Set PCI cacheline size to that of the CPU if the CPU has reported it.
 	 * (For older CPUs that don't support cpuid, we se it to 32 bytes
@@ -445,7 +439,16 @@ int __init pcibios_init(void)
  		pci_dfl_cache_line_size = 32 >> 2;
 		printk(KERN_DEBUG "PCI: Unknown cacheline size. Setting to 32 bytes\n");
 	}
+}
+
+int __init pcibios_init(void)
+{
+	if (!raw_pci_ops) {
+		printk(KERN_WARNING "PCI: System does not support PCI\n");
+		return 0;
+	}
 
+	pcibios_set_cache_line_size();
 	pcibios_resource_survey();
 
 	if (pci_bf_sort >= pci_force_bf)
diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c
index 55253095be8..8379c2c3d07 100644
--- a/arch/x86/pci/i386.c
+++ b/arch/x86/pci/i386.c
@@ -311,6 +311,8 @@ int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
 		 */
 		prot |= _PAGE_CACHE_UC_MINUS;
 
+	prot |= _PAGE_IOMAP;	/* creating a mapping for IO */
+
 	vma->vm_page_prot = __pgprot(prot);
 
 	if (io_remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff,
diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c
new file mode 100644
index 00000000000..4e371065ce4
--- /dev/null
+++ b/arch/x86/pci/xen.c
@@ -0,0 +1,142 @@
+/*
+ * Xen PCI Frontend Stub - puts some "dummy" functions in to the Linux
+ *			   x86 PCI core to support the Xen PCI Frontend
+ *
+ *   Author: Ryan Wilson <hap9@epoch.ncsc.mil>
+ */
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/pci.h>
+#include <linux/acpi.h>
+
+#include <linux/io.h>
+#include <asm/pci_x86.h>
+
+#include <asm/xen/hypervisor.h>
+
+#include <xen/events.h>
+#include <asm/xen/pci.h>
+
+#if defined(CONFIG_PCI_MSI)
+#include <linux/msi.h>
+
+struct xen_pci_frontend_ops *xen_pci_frontend;
+EXPORT_SYMBOL_GPL(xen_pci_frontend);
+
+/*
+ * For MSI interrupts we have to use drivers/xen/event.s functions to
+ * allocate an irq_desc and setup the right */
+
+
+static int xen_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
+{
+	int irq, ret, i;
+	struct msi_desc *msidesc;
+	int *v;
+
+	v = kzalloc(sizeof(int) * max(1, nvec), GFP_KERNEL);
+	if (!v)
+		return -ENOMEM;
+
+	if (!xen_initial_domain()) {
+		if (type == PCI_CAP_ID_MSIX)
+			ret = xen_pci_frontend_enable_msix(dev, &v, nvec);
+		else
+			ret = xen_pci_frontend_enable_msi(dev, &v);
+		if (ret)
+			goto error;
+	}
+	i = 0;
+	list_for_each_entry(msidesc, &dev->msi_list, list) {
+		irq = xen_allocate_pirq(v[i], 0, /* not sharable */
+			(type == PCI_CAP_ID_MSIX) ?
+			"pcifront-msi-x" : "pcifront-msi");
+		if (irq < 0)
+			return -1;
+
+		ret = set_irq_msi(irq, msidesc);
+		if (ret)
+			goto error_while;
+		i++;
+	}
+	kfree(v);
+	return 0;
+
+error_while:
+	unbind_from_irqhandler(irq, NULL);
+error:
+	if (ret == -ENODEV)
+		dev_err(&dev->dev, "Xen PCI frontend has not registered" \
+			" MSI/MSI-X support!\n");
+
+	kfree(v);
+	return ret;
+}
+
+static void xen_teardown_msi_irqs(struct pci_dev *dev)
+{
+	/* Only do this when were are in non-privileged mode.*/
+	if (!xen_initial_domain()) {
+		struct msi_desc *msidesc;
+
+		msidesc = list_entry(dev->msi_list.next, struct msi_desc, list);
+		if (msidesc->msi_attrib.is_msix)
+			xen_pci_frontend_disable_msix(dev);
+		else
+			xen_pci_frontend_disable_msi(dev);
+	}
+
+}
+
+static void xen_teardown_msi_irq(unsigned int irq)
+{
+	xen_destroy_irq(irq);
+}
+#endif
+
+static int xen_pcifront_enable_irq(struct pci_dev *dev)
+{
+	int rc;
+	int share = 1;
+
+	dev_info(&dev->dev, "Xen PCI enabling IRQ: %d\n", dev->irq);
+
+	if (dev->irq < 0)
+		return -EINVAL;
+
+	if (dev->irq < NR_IRQS_LEGACY)
+		share = 0;
+
+	rc = xen_allocate_pirq(dev->irq, share, "pcifront");
+	if (rc < 0) {
+		dev_warn(&dev->dev, "Xen PCI IRQ: %d, failed to register:%d\n",
+			 dev->irq, rc);
+		return rc;
+	}
+	return 0;
+}
+
+int __init pci_xen_init(void)
+{
+	if (!xen_pv_domain() || xen_initial_domain())
+		return -ENODEV;
+
+	printk(KERN_INFO "PCI: setting up Xen PCI frontend stub\n");
+
+	pcibios_set_cache_line_size();
+
+	pcibios_enable_irq = xen_pcifront_enable_irq;
+	pcibios_disable_irq = NULL;
+
+#ifdef CONFIG_ACPI
+	/* Keep ACPI out of the picture */
+	acpi_noirq = 1;
+#endif
+
+#ifdef CONFIG_PCI_MSI
+	x86_msi.setup_msi_irqs = xen_setup_msi_irqs;
+	x86_msi.teardown_msi_irq = xen_teardown_msi_irq;
+	x86_msi.teardown_msi_irqs = xen_teardown_msi_irqs;
+#endif
+	return 0;
+}
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 7d46c844141..1ccfa1bf0f8 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -45,6 +45,7 @@
 #include <asm/paravirt.h>
 #include <asm/apic.h>
 #include <asm/page.h>
+#include <asm/xen/pci.h>
 #include <asm/xen/hypercall.h>
 #include <asm/xen/hypervisor.h>
 #include <asm/fixmap.h>
@@ -1220,6 +1221,8 @@ asmlinkage void __init xen_start_kernel(void)
 		add_preferred_console("xenboot", 0, NULL);
 		add_preferred_console("tty", 0, NULL);
 		add_preferred_console("hvc", 0, NULL);
+		if (pci_xen)
+			x86_init.pci.arch_init = pci_xen_init;
 	} else {
 		/* Make sure ACS will be enabled */
 		pci_request_acs();
diff --git a/arch/x86/xen/pci-swiotlb-xen.c b/arch/x86/xen/pci-swiotlb-xen.c
index a013ec9d0c5..be4d80a6fae 100644
--- a/arch/x86/xen/pci-swiotlb-xen.c
+++ b/arch/x86/xen/pci-swiotlb-xen.c
@@ -1,6 +1,7 @@
 /* Glue code to lib/swiotlb-xen.c */
 
 #include <linux/dma-mapping.h>
+#include <linux/pci.h>
 #include <xen/swiotlb-xen.h>
 
 #include <asm/xen/hypervisor.h>
@@ -54,5 +55,8 @@ void __init pci_xen_swiotlb_init(void)
 	if (xen_swiotlb) {
 		xen_swiotlb_init(1);
 		dma_ops = &xen_swiotlb_dma_ops;
+
+		/* Make sure ACS will be enabled */
+		pci_request_acs();
 	}
 }
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index 328b0030542..c413132702f 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -260,7 +260,5 @@ void __init xen_arch_setup(void)
 
 	pm_idle = xen_idle;
 
-	paravirt_disable_iospace();
-
 	fiddle_vdso();
 }