Merge branch 'irq-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'irq-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (96 commits)
  apic, x86: Use BIOS settings for IBS and MCE threshold interrupt LVT offsets
  apic, x86: Check if EILVT APIC registers are available (AMD only)
  x86: ioapic: Call free_irte only if interrupt remapping enabled
  arm: Use ARCH_IRQ_INIT_FLAGS
  genirq, ARM: Fix boot on ARM platforms
  genirq: Fix CONFIG_GENIRQ_NO_DEPRECATED=y build
  x86: Switch sparse_irq allocations to GFP_KERNEL
  genirq: Switch sparse_irq allocator to GFP_KERNEL
  genirq: Make sparse_lock a mutex
  x86: lguest: Use new irq allocator
  genirq: Remove the now unused sparse irq leftovers
  genirq: Sanitize dynamic irq handling
  genirq: Remove arch_init_chip_data()
  x86: xen: Sanitise sparse_irq handling
  x86: Use sane enumeration
  x86: uv: Clean up the direct access to irq_desc
  x86: Make io_apic.c local functions static
  genirq: Remove irq_2_iommu
  x86: Speed up the irq_remapped check in hot pathes
  intr_remap: Simplify the code further
  ...

Fix up trivial conflicts in arch/x86/Kconfig

22 files changed, 733 insertions, 852 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 8c9e609a175..7ab9db88ab6 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -63,6 +63,10 @@ config X86
 	select HAVE_USER_RETURN_NOTIFIER
 	select HAVE_ARCH_JUMP_LABEL
 	select HAVE_TEXT_POKE_SMP
+	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)
@@ -204,20 +208,6 @@ 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
@@ -300,23 +290,6 @@ 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
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index 1fa03e04ae4..286de34b0ed 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -252,9 +252,7 @@ static inline int apic_is_clustered_box(void)
 }
 #endif
 
-extern u8 setup_APIC_eilvt_mce(u8 vector, u8 msg_type, u8 mask);
-extern u8 setup_APIC_eilvt_ibs(u8 vector, u8 msg_type, u8 mask);
-
+extern int setup_APIC_eilvt(u8 lvt_off, u8 vector, u8 msg_type, u8 mask);
 
 #else /* !CONFIG_X86_LOCAL_APIC */
 static inline void lapic_shutdown(void) { }
diff --git a/arch/x86/include/asm/apicdef.h b/arch/x86/include/asm/apicdef.h
index 7fe3b3060f0..a859ca461fb 100644
--- a/arch/x86/include/asm/apicdef.h
+++ b/arch/x86/include/asm/apicdef.h
@@ -131,6 +131,7 @@
 #define APIC_EILVTn(n)	(0x500 + 0x10 * n)
 #define		APIC_EILVT_NR_AMD_K8	1	/* # of extended interrupts */
 #define		APIC_EILVT_NR_AMD_10H	4
+#define		APIC_EILVT_NR_MAX	APIC_EILVT_NR_AMD_10H
 #define		APIC_EILVT_LVTOFF(x)	(((x) >> 4) & 0xF)
 #define		APIC_EILVT_MSG_FIX	0x0
 #define		APIC_EILVT_MSG_SMI	0x2
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 3a54a1ca1a0..0274ec5a7e6 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_apic.h b/arch/x86/include/asm/io_apic.h
index 9cb2edb87c2..c8be4566c3d 100644
--- a/arch/x86/include/asm/io_apic.h
+++ b/arch/x86/include/asm/io_apic.h
@@ -170,12 +170,6 @@ extern int restore_IO_APIC_setup(struct IO_APIC_route_entry **ioapic_entries);
 
 extern void probe_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 8d841505344..1c23360fb2d 100644
--- a/arch/x86/include/asm/irq_remapping.h
+++ b/arch/x86/include/asm/irq_remapping.h
@@ -24,10 +24,18 @@ static inline void prepare_irte(struct irte *irte, int 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/kernel/apb_timer.c b/arch/x86/kernel/apb_timer.c
index 6fe2b5cb4f3..92543c73cf8 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)
 {
@@ -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 8cf86fb3b4e..850657d1b0e 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -52,6 +52,7 @@
 #include <asm/mce.h>
 #include <asm/kvm_para.h>
 #include <asm/tsc.h>
+#include <asm/atomic.h>
 
 unsigned int num_processors;
 
@@ -370,38 +371,87 @@ static void __setup_APIC_LVTT(unsigned int clocks, int oneshot, int irqen)
 }
 
 /*
- * Setup extended LVT, AMD specific (K8, family 10h)
+ * Setup extended LVT, AMD specific
  *
- * Vector mappings are hard coded. On K8 only offset 0 (APIC500) and
- * MCE interrupts are supported. Thus MCE offset must be set to 0.
+ * Software should use the LVT offsets the BIOS provides.  The offsets
+ * are determined by the subsystems using it like those for MCE
+ * threshold or IBS.  On K8 only offset 0 (APIC500) and MCE interrupts
+ * are supported. Beginning with family 10h at least 4 offsets are
+ * available.
  *
- * If mask=1, the LVT entry does not generate interrupts while mask=0
- * enables the vector. See also the BKDGs.
+ * Since the offsets must be consistent for all cores, we keep track
+ * of the LVT offsets in software and reserve the offset for the same
+ * vector also to be used on other cores. An offset is freed by
+ * setting the entry to APIC_EILVT_MASKED.
+ *
+ * If the BIOS is right, there should be no conflicts. Otherwise a
+ * "[Firmware Bug]: ..." error message is generated. However, if
+ * software does not properly determines the offsets, it is not
+ * necessarily a BIOS bug.
  */
 
-#define APIC_EILVT_LVTOFF_MCE 0
-#define APIC_EILVT_LVTOFF_IBS 1
+static atomic_t eilvt_offsets[APIC_EILVT_NR_MAX];
 
-static void setup_APIC_eilvt(u8 lvt_off, u8 vector, u8 msg_type, u8 mask)
+static inline int eilvt_entry_is_changeable(unsigned int old, unsigned int new)
 {
-	unsigned long reg = (lvt_off << 4) + APIC_EILVTn(0);
-	unsigned int  v   = (mask << 16) | (msg_type << 8) | vector;
-
-	apic_write(reg, v);
+	return (old & APIC_EILVT_MASKED)
+		|| (new == APIC_EILVT_MASKED)
+		|| ((new & ~APIC_EILVT_MASKED) == old);
 }
 
-u8 setup_APIC_eilvt_mce(u8 vector, u8 msg_type, u8 mask)
+static unsigned int reserve_eilvt_offset(int offset, unsigned int new)
 {
-	setup_APIC_eilvt(APIC_EILVT_LVTOFF_MCE, vector, msg_type, mask);
-	return APIC_EILVT_LVTOFF_MCE;
+	unsigned int rsvd;			/* 0: uninitialized */
+
+	if (offset >= APIC_EILVT_NR_MAX)
+		return ~0;
+
+	rsvd = atomic_read(&eilvt_offsets[offset]) & ~APIC_EILVT_MASKED;
+	do {
+		if (rsvd &&
+		    !eilvt_entry_is_changeable(rsvd, new))
+			/* may not change if vectors are different */
+			return rsvd;
+		rsvd = atomic_cmpxchg(&eilvt_offsets[offset], rsvd, new);
+	} while (rsvd != new);
+
+	return new;
 }
 
-u8 setup_APIC_eilvt_ibs(u8 vector, u8 msg_type, u8 mask)
+/*
+ * If mask=1, the LVT entry does not generate interrupts while mask=0
+ * enables the vector. See also the BKDGs.
+ */
+
+int setup_APIC_eilvt(u8 offset, u8 vector, u8 msg_type, u8 mask)
 {
-	setup_APIC_eilvt(APIC_EILVT_LVTOFF_IBS, vector, msg_type, mask);
-	return APIC_EILVT_LVTOFF_IBS;
+	unsigned long reg = APIC_EILVTn(offset);
+	unsigned int new, old, reserved;
+
+	new = (mask << 16) | (msg_type << 8) | vector;
+	old = apic_read(reg);
+	reserved = reserve_eilvt_offset(offset, new);
+
+	if (reserved != new) {
+		pr_err(FW_BUG "cpu %d, try to setup vector 0x%x, but "
+		       "vector 0x%x was already reserved by another core, "
+		       "APIC%lX=0x%x\n",
+		       smp_processor_id(), new, reserved, reg, old);
+		return -EINVAL;
+	}
+
+	if (!eilvt_entry_is_changeable(old, new)) {
+		pr_err(FW_BUG "cpu %d, try to setup vector 0x%x but "
+		       "register already in use, APIC%lX=0x%x\n",
+		       smp_processor_id(), new, reg, old);
+		return -EBUSY;
+	}
+
+	apic_write(reg, new);
+
+	return 0;
 }
-EXPORT_SYMBOL_GPL(setup_APIC_eilvt_ibs);
+EXPORT_SYMBOL_GPL(setup_APIC_eilvt);
 
 /*
  * Program the next event, relative to now
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 9508811e844..8ae808d110f 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;
@@ -164,11 +157,13 @@ int __init arch_early_irq_init(void)
 	count = ARRAY_SIZE(irq_cfgx);
 	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)
+static void unmask_ioapic_irq(struct irq_data *data)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
-
-	mask_IO_APIC_irq_desc(desc);
-}
-static void unmask_IO_APIC_irq(unsigned int irq)
-{
-	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:
@@ -1417,18 +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
@@ -1457,9 +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);
 }
@@ -1470,11 +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;
-	struct irq_cfg *cfg;
+	int apic_id, pin, idx, irq, notcon = 0;
 	int node = cpu_to_node(0);
+	struct irq_cfg *cfg;
 
 	apic_printk(APIC_VERBOSE, KERN_DEBUG "init IO_APIC IRQs\n");
 
@@ -1511,19 +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)
@@ -1538,9 +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(0);
-	struct irq_desc *desc;
+	int apic_id = 0, pin, idx, irq, node = cpu_to_node(0);
 	struct irq_cfg *cfg;
 
 	/*
@@ -1556,18 +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)) {
@@ -1577,7 +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));
 }
 
@@ -1628,7 +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);
@@ -1715,10 +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;
@@ -2225,29 +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);
@@ -2298,7 +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;
@@ -2308,65 +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
 
 /*
@@ -2381,24 +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);
 
@@ -2413,29 +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;
 }
@@ -2497,10 +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))
@@ -2512,31 +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();
 }
 
@@ -2558,10 +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) {
 			/*
@@ -2570,7 +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);
@@ -2579,36 +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
 
@@ -2644,7 +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));
 
@@ -2664,7 +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 */
@@ -2695,61 +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
@@ -2762,8 +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,
@@ -2774,7 +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);
 		}
 	}
 }
@@ -2783,7 +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;
 
@@ -2791,7 +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;
 
@@ -2799,21 +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");
 }
@@ -2916,8 +2741,7 @@ 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;
+	struct irq_cfg *cfg = get_irq_chip_data(0);
 	int node = cpu_to_node(0);
 	int apic1, pin1, apic2, pin2;
 	unsigned long flags;
@@ -2928,7 +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());
 
 	/*
@@ -2987,7 +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?
@@ -2995,12 +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);
@@ -3023,14 +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;
 		}
@@ -3038,7 +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");
 	}
@@ -3055,16 +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");
 
@@ -3230,44 +3054,37 @@ 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)
@@ -3287,14 +3104,17 @@ 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);
+	if (intr_remapping_enabled)
+		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);
 }
 
 /*
@@ -3318,7 +3138,7 @@ 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;
@@ -3371,26 +3191,24 @@ 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;
 }
@@ -3400,17 +3218,17 @@ 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;
@@ -3440,27 +3258,27 @@ 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,
 };
 
 /*
@@ -3492,8 +3310,8 @@ 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)
@@ -3502,12 +3320,8 @@ 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");
@@ -3519,13 +3333,10 @@ static int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, int irq)
 
 int arch_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)
@@ -3585,18 +3396,17 @@ void arch_teardown_msi_irq(unsigned int 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;
@@ -3612,14 +3422,14 @@ 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)
@@ -3640,26 +3450,24 @@ 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;
 }
@@ -3667,34 +3475,33 @@ 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);
@@ -3712,9 +3519,9 @@ 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
@@ -3747,33 +3554,30 @@ 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)
@@ -3864,14 +3668,13 @@ 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;
@@ -3889,11 +3692,9 @@ static int __io_apic_set_pci_routing(struct device *dev, int irq,
 	else
 		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;
@@ -3903,15 +3704,14 @@ 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;
 }
@@ -4104,14 +3904,14 @@ 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);
 	}
 
 }
@@ -4295,19 +4095,18 @@ 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/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index 39aaee5c1ab..80c482382d5 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -131,7 +131,8 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c)
 	u32 low = 0, high = 0, address = 0;
 	unsigned int bank, block;
 	struct thresh_restart tr;
-	u8 lvt_off;
+	int lvt_off = -1;
+	u8 offset;
 
 	for (bank = 0; bank < NR_BANKS; ++bank) {
 		for (block = 0; block < NR_BLOCKS; ++block) {
@@ -162,8 +163,28 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c)
 			if (shared_bank[bank] && c->cpu_core_id)
 				break;
 #endif
-			lvt_off = setup_APIC_eilvt_mce(THRESHOLD_APIC_VECTOR,
-						       APIC_EILVT_MSG_FIX, 0);
+			offset = (high & MASK_LVTOFF_HI) >> 20;
+			if (lvt_off < 0) {
+				if (setup_APIC_eilvt(offset,
+						     THRESHOLD_APIC_VECTOR,
+						     APIC_EILVT_MSG_FIX, 0)) {
+					pr_err(FW_BUG "cpu %d, failed to "
+					       "setup threshold interrupt "
+					       "for bank %d, block %d "
+					       "(MSR%08X=0x%x%08x)",
+					       smp_processor_id(), bank, block,
+					       address, high, low);
+					continue;
+				}
+				lvt_off = offset;
+			} else if (lvt_off != offset) {
+				pr_err(FW_BUG "cpu %d, invalid threshold "
+				       "interrupt offset %d for bank %d,"
+				       "block %d (MSR%08X=0x%x%08x)",
+				       smp_processor_id(), lvt_off, bank,
+				       block, address, high, low);
+				continue;
+			}
 
 			high &= ~MASK_LVTOFF_HI;
 			high |= lvt_off << 20;
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 44edb03fc9e..83ec0175f98 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 713969b9266..c752e973958 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/smpboot.c b/arch/x86/kernel/smpboot.c
index 2ced73ba048..dfb50890b5b 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -323,9 +323,9 @@ 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 */
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/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/oprofile/op_model_amd.c b/arch/x86/oprofile/op_model_amd.c
index b67a6b5aa8d..42fb46f8388 100644
--- a/arch/x86/oprofile/op_model_amd.c
+++ b/arch/x86/oprofile/op_model_amd.c
@@ -64,15 +64,22 @@ static u64 ibs_op_ctl;
  * IBS cpuid feature detection
  */
 
-#define IBS_CPUID_FEATURES      0x8000001b
+#define IBS_CPUID_FEATURES		0x8000001b
 
 /*
  * Same bit mask as for IBS cpuid feature flags (Fn8000_001B_EAX), but
  * bit 0 is used to indicate the existence of IBS.
  */
-#define IBS_CAPS_AVAIL			(1LL<<0)
-#define IBS_CAPS_RDWROPCNT		(1LL<<3)
-#define IBS_CAPS_OPCNT			(1LL<<4)
+#define IBS_CAPS_AVAIL			(1U<<0)
+#define IBS_CAPS_RDWROPCNT		(1U<<3)
+#define IBS_CAPS_OPCNT			(1U<<4)
+
+/*
+ * IBS APIC setup
+ */
+#define IBSCTL				0x1cc
+#define IBSCTL_LVT_OFFSET_VALID		(1ULL<<8)
+#define IBSCTL_LVT_OFFSET_MASK		0x0F
 
 /*
  * IBS randomization macros
@@ -266,6 +273,74 @@ static void op_amd_stop_ibs(void)
 		wrmsrl(MSR_AMD64_IBSOPCTL, 0);
 }
 
+static inline int eilvt_is_available(int offset)
+{
+	/* check if we may assign a vector */
+	return !setup_APIC_eilvt(offset, 0, APIC_EILVT_MSG_NMI, 1);
+}
+
+static inline int ibs_eilvt_valid(void)
+{
+	u64 val;
+	int offset;
+
+	rdmsrl(MSR_AMD64_IBSCTL, val);
+	if (!(val & IBSCTL_LVT_OFFSET_VALID)) {
+		pr_err(FW_BUG "cpu %d, invalid IBS "
+		       "interrupt offset %d (MSR%08X=0x%016llx)",
+		       smp_processor_id(), offset,
+		       MSR_AMD64_IBSCTL, val);
+		return 0;
+	}
+
+	offset = val & IBSCTL_LVT_OFFSET_MASK;
+
+	if (eilvt_is_available(offset))
+		return !0;
+
+	pr_err(FW_BUG "cpu %d, IBS interrupt offset %d "
+	       "not available (MSR%08X=0x%016llx)",
+	       smp_processor_id(), offset,
+	       MSR_AMD64_IBSCTL, val);
+
+	return 0;
+}
+
+static inline int get_ibs_offset(void)
+{
+	u64 val;
+
+	rdmsrl(MSR_AMD64_IBSCTL, val);
+	if (!(val & IBSCTL_LVT_OFFSET_VALID))
+		return -EINVAL;
+
+	return val & IBSCTL_LVT_OFFSET_MASK;
+}
+
+static void setup_APIC_ibs(void)
+{
+	int offset;
+
+	offset = get_ibs_offset();
+	if (offset < 0)
+		goto failed;
+
+	if (!setup_APIC_eilvt(offset, 0, APIC_EILVT_MSG_NMI, 0))
+		return;
+failed:
+	pr_warn("oprofile: IBS APIC setup failed on cpu #%d\n",
+		smp_processor_id());
+}
+
+static void clear_APIC_ibs(void)
+{
+	int offset;
+
+	offset = get_ibs_offset();
+	if (offset >= 0)
+		setup_APIC_eilvt(offset, 0, APIC_EILVT_MSG_FIX, 1);
+}
+
 #ifdef CONFIG_OPROFILE_EVENT_MULTIPLEX
 
 static void op_mux_switch_ctrl(struct op_x86_model_spec const *model,
@@ -376,13 +451,13 @@ static void op_amd_setup_ctrs(struct op_x86_model_spec const *model,
 	}
 
 	if (ibs_caps)
-		setup_APIC_eilvt_ibs(0, APIC_EILVT_MSG_NMI, 0);
+		setup_APIC_ibs();
 }
 
 static void op_amd_cpu_shutdown(void)
 {
 	if (ibs_caps)
-		setup_APIC_eilvt_ibs(0, APIC_EILVT_MSG_FIX, 1);
+		clear_APIC_ibs();
 }
 
 static int op_amd_check_ctrs(struct pt_regs * const regs,
@@ -445,16 +520,11 @@ static void op_amd_stop(struct op_msrs const * const msrs)
 	op_amd_stop_ibs();
 }
 
-static int __init_ibs_nmi(void)
+static int setup_ibs_ctl(int ibs_eilvt_off)
 {
-#define IBSCTL_LVTOFFSETVAL		(1 << 8)
-#define IBSCTL				0x1cc
 	struct pci_dev *cpu_cfg;
 	int nodes;
 	u32 value = 0;
-	u8 ibs_eilvt_off;
-
-	ibs_eilvt_off = setup_APIC_eilvt_ibs(0, APIC_EILVT_MSG_FIX, 1);
 
 	nodes = 0;
 	cpu_cfg = NULL;
@@ -466,21 +536,60 @@ static int __init_ibs_nmi(void)
 			break;
 		++nodes;
 		pci_write_config_dword(cpu_cfg, IBSCTL, ibs_eilvt_off
-				       | IBSCTL_LVTOFFSETVAL);
+				       | IBSCTL_LVT_OFFSET_VALID);
 		pci_read_config_dword(cpu_cfg, IBSCTL, &value);
-		if (value != (ibs_eilvt_off | IBSCTL_LVTOFFSETVAL)) {
+		if (value != (ibs_eilvt_off | IBSCTL_LVT_OFFSET_VALID)) {
 			pci_dev_put(cpu_cfg);
 			printk(KERN_DEBUG "Failed to setup IBS LVT offset, "
-				"IBSCTL = 0x%08x", value);
-			return 1;
+			       "IBSCTL = 0x%08x\n", value);
+			return -EINVAL;
 		}
 	} while (1);
 
 	if (!nodes) {
-		printk(KERN_DEBUG "No CPU node configured for IBS");
-		return 1;
+		printk(KERN_DEBUG "No CPU node configured for IBS\n");
+		return -ENODEV;
+	}
+
+	return 0;
+}
+
+static int force_ibs_eilvt_setup(void)
+{
+	int i;
+	int ret;
+
+	/* find the next free available EILVT entry */
+	for (i = 1; i < 4; i++) {
+		if (!eilvt_is_available(i))
+			continue;
+		ret = setup_ibs_ctl(i);
+		if (ret)
+			return ret;
+		return 0;
 	}
 
+	printk(KERN_DEBUG "No EILVT entry available\n");
+
+	return -EBUSY;
+}
+
+static int __init_ibs_nmi(void)
+{
+	int ret;
+
+	if (ibs_eilvt_valid())
+		return 0;
+
+	ret = force_ibs_eilvt_setup();
+	if (ret)
+		return ret;
+
+	if (!ibs_eilvt_valid())
+		return -EFAULT;
+
+	pr_err(FW_BUG "workaround enabled for IBS LVT offset\n");
+
 	return 0;
 }