Patches contributed by Eötvös Lorand University


commit 4588c1f0354ac96a358b3f9e8e4331c51cf3336f
Author: Ingo Molnar <mingo@elte.hu>
Date:   Sat Sep 6 14:19:17 2008 +0200

    x86: HPET_MSI Basic HPET_MSI setup code, cleanups
    
    small style cleanups.
    
    Signed-off-by: Ingo Molnar <mingo@elte.hu>

diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index 3f10d16a8348..03d3655734b4 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -1,39 +1,39 @@
 #include <linux/clocksource.h>
 #include <linux/clockchips.h>
+#include <linux/interrupt.h>
+#include <linux/sysdev.h>
 #include <linux/delay.h>
 #include <linux/errno.h>
 #include <linux/hpet.h>
 #include <linux/init.h>
-#include <linux/sysdev.h>
-#include <linux/pm.h>
-#include <linux/interrupt.h>
 #include <linux/cpu.h>
+#include <linux/pm.h>
+#include <linux/io.h>
 
 #include <asm/fixmap.h>
-#include <asm/hpet.h>
 #include <asm/i8253.h>
-#include <asm/io.h>
+#include <asm/hpet.h>
 
-#define HPET_MASK	CLOCKSOURCE_MASK(32)
-#define HPET_SHIFT	22
+#define HPET_MASK			CLOCKSOURCE_MASK(32)
+#define HPET_SHIFT			22
 
 /* FSEC = 10^-15
    NSEC = 10^-9 */
-#define FSEC_PER_NSEC	1000000L
+#define FSEC_PER_NSEC			1000000L
 
 /*
  * HPET address is set in acpi/boot.c, when an ACPI entry exists
  */
-unsigned long hpet_address;
-static void __iomem *hpet_virt_address;
+unsigned long				hpet_address;
+static void __iomem			*hpet_virt_address;
 
 struct hpet_dev {
-	struct clock_event_device evt;
-	unsigned int num;
-	int cpu;
-	unsigned int irq;
-	unsigned int flags;
-	char name[10];
+	struct clock_event_device	evt;
+	unsigned int			num;
+	int				cpu;
+	unsigned int			irq;
+	unsigned int			flags;
+	char				name[10];
 };
 
 unsigned long hpet_readl(unsigned long a)
@@ -70,7 +70,7 @@ static inline void hpet_clear_mapping(void)
 static int boot_hpet_disable;
 int hpet_force_user;
 
-static int __init hpet_setup(char* str)
+static int __init hpet_setup(char *str)
 {
 	if (str) {
 		if (!strncmp("disable", str, 7))
@@ -91,7 +91,7 @@ __setup("nohpet", disable_hpet);
 
 static inline int is_hpet_capable(void)
 {
-	return (!boot_hpet_disable && hpet_address);
+	return !boot_hpet_disable && hpet_address;
 }
 
 /*
@@ -122,10 +122,10 @@ static void hpet_reserve_platform_timers(unsigned long id)
 
 	nrtimers = ((id & HPET_ID_NUMBER) >> HPET_ID_NUMBER_SHIFT) + 1;
 
-	memset(&hd, 0, sizeof (hd));
-	hd.hd_phys_address = hpet_address;
-	hd.hd_address = hpet;
-	hd.hd_nirqs = nrtimers;
+	memset(&hd, 0, sizeof(hd));
+	hd.hd_phys_address	= hpet_address;
+	hd.hd_address		= hpet;
+	hd.hd_nirqs		= nrtimers;
 	hpet_reserve_timer(&hd, 0);
 
 #ifdef CONFIG_HPET_EMULATE_RTC
@@ -141,8 +141,8 @@ static void hpet_reserve_platform_timers(unsigned long id)
 	hd.hd_irq[1] = HPET_LEGACY_RTC;
 
 	for (i = 2; i < nrtimers; timer++, i++) {
-		hd.hd_irq[i] = (readl(&timer->hpet_config) & Tn_INT_ROUTE_CNF_MASK) >>
-			Tn_INT_ROUTE_CNF_SHIFT;
+		hd.hd_irq[i] = (readl(&timer->hpet_config) &
+			Tn_INT_ROUTE_CNF_MASK) >> Tn_INT_ROUTE_CNF_SHIFT;
 	}
 
 	hpet_alloc(&hd);
@@ -244,7 +244,7 @@ static void hpet_set_mode(enum clock_event_mode mode,
 	unsigned long cfg, cmp, now;
 	uint64_t delta;
 
-	switch(mode) {
+	switch (mode) {
 	case CLOCK_EVT_MODE_PERIODIC:
 		delta = ((uint64_t)(NSEC_PER_SEC/HZ)) * evt->mult;
 		delta >>= evt->shift;

commit c59d85a7b7822b83fc9783314543eea0ca860480
Author: Ingo Molnar <mingo@elte.hu>
Date:   Thu Aug 28 08:56:33 2008 +0200

    sparseirq: export nr_irqs on m68k/sparc/s390
    
    Stephen Rothwell reported such build failures on m68k/sparc/s390:
    
    > ERROR: "nr_irqs" [drivers/net/hamradio/baycom_ser_fdx.ko] undefined!
    > ERROR: "nr_irqs" [drivers/net/3c59x.ko] undefined!
    
    export nr_irqs on these architectures too.
    
    Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
    Signed-off-by: Ingo Molnar <mingo@elte.hu>

diff --git a/arch/m68k/kernel/ints.c b/arch/m68k/kernel/ints.c
index 74453d15692e..44169e4cd91d 100644
--- a/arch/m68k/kernel/ints.c
+++ b/arch/m68k/kernel/ints.c
@@ -47,6 +47,7 @@
 #endif
 
 int nr_irqs = NR_IRQS;
+EXPORT_SYMBOL(nr_irqs);
 
 extern u32 auto_irqhandler_fixup[];
 extern u32 user_irqhandler_fixup[];
diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c
index 14eb5496c8a8..3624c4a0037a 100644
--- a/arch/s390/kernel/irq.c
+++ b/arch/s390/kernel/irq.c
@@ -18,6 +18,7 @@
 #include <linux/profile.h>
 
 int nr_irqs = NR_IRQS;
+EXPORT_SYMBOL(nr_irqs);
 
 /*
  * show_interrupts is needed by /proc/interrupts.
diff --git a/arch/sparc/kernel/irq.c b/arch/sparc/kernel/irq.c
index 059598b7e0f0..4b99e3ce3916 100644
--- a/arch/sparc/kernel/irq.c
+++ b/arch/sparc/kernel/irq.c
@@ -57,6 +57,7 @@
 #endif /* SMP */
 
 int nr_irqs = NR_IRQS;
+EXPORT_SYMBOL(nr_irqs);
 
 unsigned long __raw_local_irq_save(void)
 {

commit 0c425cec64eb0c0d0dd7037c21a25585cbe3636c
Author: Ingo Molnar <mingo@elte.hu>
Date:   Mon Aug 18 13:04:26 2008 +0200

    warning: fix arch x86 kernel io_apic c
    
    fix warning:
    
      arch/x86/kernel/io_apic.c: In function ‘print_local_APIC’:
      arch/x86/kernel/io_apic.c:1786: warning: format ‘%08x’ expects type ‘unsigned int’, but argument 2 has type ‘u64’
      arch/x86/kernel/io_apic.c:1787: warning: format ‘%08x’ expects type ‘unsigned int’, but argument 2 has type ‘u64’
    
    By creating uniform behavior on 32-bit and 64-bit and printing out the ICR
    value in two 32-bit words.
    
    Code has changed:
    
       text    data     bss     dec     hex filename
      22901   19650   17040   59591    e8c7 io_apic.o.before
      22899   19650   17040   59589    e8c5 io_apic.o.after
    
    Due to the 32-bit cast narrowing the printed out value on 64-bit.
    
    Signed-off-by: Ingo Molnar <mingo@elte.hu>

diff --git a/arch/x86/kernel/io_apic.c b/arch/x86/kernel/io_apic.c
index f7e80262cbbb..34c74cf5c244 100644
--- a/arch/x86/kernel/io_apic.c
+++ b/arch/x86/kernel/io_apic.c
@@ -1774,8 +1774,8 @@ __apicdebuginit(void) print_local_APIC(void *dummy)
 	}
 
 	icr = apic_icr_read();
-	printk(KERN_DEBUG "... APIC ICR: %08x\n", icr);
-	printk(KERN_DEBUG "... APIC ICR2: %08x\n", icr >> 32);
+	printk(KERN_DEBUG "... APIC ICR: %08x\n", (u32)icr);
+	printk(KERN_DEBUG "... APIC ICR2: %08x\n", (u32)(icr >> 32));
 
 	v = apic_read(APIC_LVTT);
 	printk(KERN_DEBUG "... APIC LVTT: %08x\n", v);

commit 54168ed7f2a4f3fc2780e645124ae952598da601
Author: Ingo Molnar <mingo@elte.hu>
Date:   Wed Aug 20 09:07:45 2008 +0200

    x86: make io_apic_32.c the same as io_apic_64.c
    
    Signed-off-by: Ingo Molnar <mingo@elte.hu>

diff --git a/arch/x86/kernel/io_apic_32.c b/arch/x86/kernel/io_apic_32.c
index 3ed36041c81e..fba6d6ee3480 100644
--- a/arch/x86/kernel/io_apic_32.c
+++ b/arch/x86/kernel/io_apic_32.c
@@ -35,7 +35,7 @@
 #include <linux/htirq.h>
 #include <linux/freezer.h>
 #include <linux/kthread.h>
-#include <linux/jiffies.h>      /* time_after() */
+#include <linux/jiffies.h>	/* time_after() */
 #ifdef CONFIG_ACPI
 #include <acpi/acpi_bus.h>
 #endif
@@ -64,8 +64,8 @@
 #define __apicdebuginit(type) static type __init
 
 /*
- *	Is the SiS APIC rmw bug present ?
- *	-1 = don't know, 0 = no, 1 = yes
+ *      Is the SiS APIC rmw bug present ?
+ *      -1 = don't know, 0 = no, 1 = yes
  */
 int sis_apic_bug = -1;
 
@@ -102,7 +102,7 @@ DECLARE_BITMAP(mp_bus_not_pci, MAX_MP_BUSSES);
 
 int skip_ioapic_setup;
 
-static int __init parse_noapic(char *arg)
+static int __init parse_noapic(char *str)
 {
 	/* disable IO-APIC */
 	disable_ioapic_setup();
@@ -188,7 +188,7 @@ static void __init init_work(void *data)
 	irq_cfgx[legacy_count - 1].next = NULL;
 }
 
-#define for_each_irq_cfg(cfg)           \
+#define for_each_irq_cfg(cfg)		\
 	for (cfg = irq_cfgx; cfg; cfg = cfg->next)
 
 DEFINE_DYN_ARRAY(irq_cfgx, sizeof(struct irq_cfg), nr_irq_cfg, PAGE_SIZE, init_work);
@@ -262,7 +262,6 @@ static struct irq_cfg *irq_cfg_alloc(unsigned int irq)
 		irq_cfgx = cfg;
 	cfg->irq = irq;
 	printk(KERN_DEBUG "found new irq_cfg for irq %d\n", cfg->irq);
-
 #ifdef CONFIG_HAVE_SPARSE_IRQ_DEBUG
 	{
 		/* dump the results */
@@ -384,9 +383,9 @@ static inline void io_apic_write(unsigned int apic, unsigned int reg, unsigned i
  */
 static inline void io_apic_modify(unsigned int apic, unsigned int reg, unsigned int value)
 {
-	volatile struct io_apic __iomem *io_apic = io_apic_base(apic);
-	if (sis_apic_bug)
-		writel(reg, &io_apic->index);
+	struct io_apic __iomem *io_apic = io_apic_base(apic);
+        if (sis_apic_bug)
+                writel(reg, &io_apic->index);
 	writel(value, &io_apic->data);
 }
 
@@ -494,11 +493,20 @@ static void __target_IO_APIC_irq(unsigned int irq, unsigned int dest, u8 vector)
 
 		apic = entry->apic;
 		pin = entry->pin;
+#ifdef CONFIG_INTR_REMAP
+		/*
+		 * With interrupt-remapping, destination information comes
+		 * from interrupt-remapping table entry.
+		 */
+		if (!irq_remapped(irq))
+			io_apic_write(apic, 0x11 + pin*2, dest);
+#else
 		io_apic_write(apic, 0x11 + pin*2, dest);
+#endif
 		reg = io_apic_read(apic, 0x10 + pin*2);
 		reg &= ~IO_APIC_REDIR_VECTOR_MASK;
 		reg |= vector;
-		io_apic_modify(apic, 0x10 + pin *2, reg);
+		io_apic_modify(apic, 0x10 + pin*2, reg);
 		if (!entry->next)
 			break;
 		entry = entry->next;
@@ -513,6 +521,7 @@ static void set_ioapic_affinity_irq(unsigned int irq, cpumask_t mask)
 	unsigned long flags;
 	unsigned int dest;
 	cpumask_t tmp;
+	struct irq_desc *desc;
 
 	cpus_and(tmp, mask, cpu_online_map);
 	if (cpus_empty(tmp))
@@ -529,12 +538,12 @@ static void set_ioapic_affinity_irq(unsigned int irq, cpumask_t mask)
 	 */
 	dest = SET_APIC_LOGICAL_ID(dest);
 
+	desc = irq_to_desc(irq);
 	spin_lock_irqsave(&ioapic_lock, flags);
 	__target_IO_APIC_irq(irq, dest, cfg->vector);
-	irq_to_desc(irq)->affinity = mask;
+	desc->affinity = mask;
 	spin_unlock_irqrestore(&ioapic_lock, flags);
 }
-
 #endif /* CONFIG_SMP */
 
 /*
@@ -699,7 +708,7 @@ static void __unmask_and_level_IO_APIC_irq(unsigned int irq)
 
 #endif
 
-static void mask_IO_APIC_irq(unsigned int irq)
+static void mask_IO_APIC_irq (unsigned int irq)
 {
 	unsigned long flags;
 
@@ -708,7 +717,7 @@ static void mask_IO_APIC_irq(unsigned int irq)
 	spin_unlock_irqrestore(&ioapic_lock, flags);
 }
 
-static void unmask_IO_APIC_irq(unsigned int irq)
+static void unmask_IO_APIC_irq (unsigned int irq)
 {
 	unsigned long flags;
 
@@ -725,14 +734,13 @@ static void clear_IO_APIC_pin(unsigned int apic, unsigned int pin)
 	entry = ioapic_read_entry(apic, pin);
 	if (entry.delivery_mode == dest_SMI)
 		return;
-
 	/*
 	 * Disable it in the IO-APIC irq-routing table:
 	 */
 	ioapic_mask_entry(apic, pin);
 }
 
-static void clear_IO_APIC(void)
+static void clear_IO_APIC (void)
 {
 	int apic, pin;
 
@@ -741,7 +749,7 @@ static void clear_IO_APIC(void)
 			clear_IO_APIC_pin(apic, pin);
 }
 
-#ifndef CONFIG_SMP
+#if !defined(CONFIG_SMP) && defined(CONFIG_X86_32)
 void send_IPI_self(int vector)
 {
 	unsigned int cfg;
@@ -756,9 +764,9 @@ void send_IPI_self(int vector)
 	 */
 	apic_write(APIC_ICR, cfg);
 }
-#endif /* !CONFIG_SMP */
-
+#endif /* !CONFIG_SMP && CONFIG_X86_32*/
 
+#ifdef CONFIG_X86_32
 /*
  * support for broken MP BIOSs, enables hand-redirection of PIRQ0-7 to
  * specific CPU-side IRQs.
@@ -797,6 +805,75 @@ static int __init ioapic_pirq_setup(char *str)
 }
 
 __setup("pirq=", ioapic_pirq_setup);
+#endif /* CONFIG_X86_32 */
+
+#ifdef CONFIG_INTR_REMAP
+/* I/O APIC RTE contents at the OS boot up */
+static struct IO_APIC_route_entry *early_ioapic_entries[MAX_IO_APICS];
+
+/*
+ * Saves and masks all the unmasked IO-APIC RTE's
+ */
+int save_mask_IO_APIC_setup(void)
+{
+	union IO_APIC_reg_01 reg_01;
+	unsigned long flags;
+	int apic, pin;
+
+	/*
+	 * The number of IO-APIC IRQ registers (== #pins):
+	 */
+	for (apic = 0; apic < nr_ioapics; apic++) {
+		spin_lock_irqsave(&ioapic_lock, flags);
+		reg_01.raw = io_apic_read(apic, 1);
+		spin_unlock_irqrestore(&ioapic_lock, flags);
+		nr_ioapic_registers[apic] = reg_01.bits.entries+1;
+	}
+
+	for (apic = 0; apic < nr_ioapics; apic++) {
+		early_ioapic_entries[apic] =
+			kzalloc(sizeof(struct IO_APIC_route_entry) *
+				nr_ioapic_registers[apic], GFP_KERNEL);
+		if (!early_ioapic_entries[apic])
+			return -ENOMEM;
+	}
+
+	for (apic = 0; apic < nr_ioapics; apic++)
+		for (pin = 0; pin < nr_ioapic_registers[apic]; pin++) {
+			struct IO_APIC_route_entry entry;
+
+			entry = early_ioapic_entries[apic][pin] =
+				ioapic_read_entry(apic, pin);
+			if (!entry.mask) {
+				entry.mask = 1;
+				ioapic_write_entry(apic, pin, entry);
+			}
+		}
+	return 0;
+}
+
+void restore_IO_APIC_setup(void)
+{
+	int apic, pin;
+
+	for (apic = 0; apic < nr_ioapics; apic++)
+		for (pin = 0; pin < nr_ioapic_registers[apic]; pin++)
+			ioapic_write_entry(apic, pin,
+					   early_ioapic_entries[apic][pin]);
+}
+
+void reinit_intr_remapped_IO_APIC(int intr_remapping)
+{
+	/*
+	 * for now plain restore of previous settings.
+	 * TBD: In the case of OS enabling interrupt-remapping,
+	 * IO-APIC RTE's need to be setup to point to interrupt-remapping
+	 * table entries. for now, do a plain restore, and wait for
+	 * the setup_IO_APIC_irqs() to do proper initialization.
+	 */
+	restore_IO_APIC_setup();
+}
+#endif
 
 /*
  * Find the IRQ entry number of a certain pin.
@@ -848,7 +925,7 @@ static int __init find_isa_irq_apic(int irq, int type)
 	}
 	if (i < mp_irq_entries) {
 		int apic;
-		for (apic = 0; apic < nr_ioapics; apic++) {
+		for(apic = 0; apic < nr_ioapics; apic++) {
 			if (mp_ioapics[apic].mp_apicid == mp_irqs[i].mp_dstapic)
 				return apic;
 		}
@@ -867,10 +944,10 @@ int IO_APIC_get_PCI_irq_vector(int bus, int slot, int pin)
 {
 	int apic, i, best_guess = -1;
 
-	apic_printk(APIC_DEBUG, "querying PCI -> IRQ mapping bus:%d, "
-		"slot:%d, pin:%d.\n", bus, slot, pin);
+	apic_printk(APIC_DEBUG, "querying PCI -> IRQ mapping bus:%d, slot:%d, pin:%d.\n",
+		bus, slot, pin);
 	if (test_bit(bus, mp_bus_not_pci)) {
-		printk(KERN_WARNING "PCI BIOS passed nonexistent PCI bus %d!\n", bus);
+		apic_printk(APIC_VERBOSE, "PCI BIOS passed nonexistent PCI bus %d!\n", bus);
 		return -1;
 	}
 	for (i = 0; i < mp_irq_entries; i++) {
@@ -885,7 +962,7 @@ int IO_APIC_get_PCI_irq_vector(int bus, int slot, int pin)
 		    !mp_irqs[i].mp_irqtype &&
 		    (bus == lbus) &&
 		    (slot == ((mp_irqs[i].mp_srcbusirq >> 2) & 0x1f))) {
-			int irq = pin_2_irq(i, apic, mp_irqs[i].mp_dstirq);
+			int irq = pin_2_irq(i,apic,mp_irqs[i].mp_dstirq);
 
 			if (!(apic || IO_APIC_IRQ(irq)))
 				continue;
@@ -902,6 +979,7 @@ int IO_APIC_get_PCI_irq_vector(int bus, int slot, int pin)
 	}
 	return best_guess;
 }
+
 EXPORT_SYMBOL(IO_APIC_get_PCI_irq_vector);
 
 #if defined(CONFIG_EISA) || defined(CONFIG_MCA)
@@ -918,6 +996,7 @@ static int EISA_ELCR(unsigned int irq)
 			"Broken MPtable reports ISA irq %d\n", irq);
 	return 0;
 }
+
 #endif
 
 /* ISA interrupts are always polarity zero edge triggered,
@@ -954,36 +1033,36 @@ static int MPBIOS_polarity(int idx)
 	/*
 	 * Determine IRQ line polarity (high active or low active):
 	 */
-	switch (mp_irqs[idx].mp_irqflag & 3) {
-	case 0: /* conforms, ie. bus-type dependent polarity */
-	{
-		polarity = test_bit(bus, mp_bus_not_pci)?
-			default_ISA_polarity(idx):
-			default_PCI_polarity(idx);
-		break;
-	}
-	case 1: /* high active */
-	{
-		polarity = 0;
-		break;
-	}
-	case 2: /* reserved */
-	{
-		printk(KERN_WARNING "broken BIOS!!\n");
-		polarity = 1;
-		break;
-	}
-	case 3: /* low active */
-	{
-		polarity = 1;
-		break;
-	}
-	default: /* invalid */
+	switch (mp_irqs[idx].mp_irqflag & 3)
 	{
-		printk(KERN_WARNING "broken BIOS!!\n");
-		polarity = 1;
-		break;
-	}
+		case 0: /* conforms, ie. bus-type dependent polarity */
+			if (test_bit(bus, mp_bus_not_pci))
+				polarity = default_ISA_polarity(idx);
+			else
+				polarity = default_PCI_polarity(idx);
+			break;
+		case 1: /* high active */
+		{
+			polarity = 0;
+			break;
+		}
+		case 2: /* reserved */
+		{
+			printk(KERN_WARNING "broken BIOS!!\n");
+			polarity = 1;
+			break;
+		}
+		case 3: /* low active */
+		{
+			polarity = 1;
+			break;
+		}
+		default: /* invalid */
+		{
+			printk(KERN_WARNING "broken BIOS!!\n");
+			polarity = 1;
+			break;
+		}
 	}
 	return polarity;
 }
@@ -996,67 +1075,67 @@ static int MPBIOS_trigger(int idx)
 	/*
 	 * Determine IRQ trigger mode (edge or level sensitive):
 	 */
-	switch ((mp_irqs[idx].mp_irqflag>>2) & 3) {
-	case 0: /* conforms, ie. bus-type dependent */
+	switch ((mp_irqs[idx].mp_irqflag>>2) & 3)
 	{
-		trigger = test_bit(bus, mp_bus_not_pci)?
-				default_ISA_trigger(idx):
-				default_PCI_trigger(idx);
+		case 0: /* conforms, ie. bus-type dependent */
+			if (test_bit(bus, mp_bus_not_pci))
+				trigger = default_ISA_trigger(idx);
+			else
+				trigger = default_PCI_trigger(idx);
 #if defined(CONFIG_EISA) || defined(CONFIG_MCA)
-		switch (mp_bus_id_to_type[bus]) {
-		case MP_BUS_ISA: /* ISA pin */
-		{
-			/* set before the switch */
+			switch (mp_bus_id_to_type[bus]) {
+				case MP_BUS_ISA: /* ISA pin */
+				{
+					/* set before the switch */
+					break;
+				}
+				case MP_BUS_EISA: /* EISA pin */
+				{
+					trigger = default_EISA_trigger(idx);
+					break;
+				}
+				case MP_BUS_PCI: /* PCI pin */
+				{
+					/* set before the switch */
+					break;
+				}
+				case MP_BUS_MCA: /* MCA pin */
+				{
+					trigger = default_MCA_trigger(idx);
+					break;
+				}
+				default:
+				{
+					printk(KERN_WARNING "broken BIOS!!\n");
+					trigger = 1;
+					break;
+				}
+			}
+#endif
 			break;
-		}
-		case MP_BUS_EISA: /* EISA pin */
+		case 1: /* edge */
 		{
-			trigger = default_EISA_trigger(idx);
+			trigger = 0;
 			break;
 		}
-		case MP_BUS_PCI: /* PCI pin */
+		case 2: /* reserved */
 		{
-			/* set before the switch */
+			printk(KERN_WARNING "broken BIOS!!\n");
+			trigger = 1;
 			break;
 		}
-		case MP_BUS_MCA: /* MCA pin */
+		case 3: /* level */
 		{
-			trigger = default_MCA_trigger(idx);
+			trigger = 1;
 			break;
 		}
-		default:
+		default: /* invalid */
 		{
 			printk(KERN_WARNING "broken BIOS!!\n");
-			trigger = 1;
+			trigger = 0;
 			break;
 		}
 	}
-#endif
-		break;
-	}
-	case 1: /* edge */
-	{
-		trigger = 0;
-		break;
-	}
-	case 2: /* reserved */
-	{
-		printk(KERN_WARNING "broken BIOS!!\n");
-		trigger = 1;
-		break;
-	}
-	case 3: /* level */
-	{
-		trigger = 1;
-		break;
-	}
-	default: /* invalid */
-	{
-		printk(KERN_WARNING "broken BIOS!!\n");
-		trigger = 0;
-		break;
-	}
-	}
 	return trigger;
 }
 
@@ -1082,9 +1161,9 @@ static int pin_2_irq(int idx, int apic, int pin)
 	if (mp_irqs[idx].mp_dstirq != pin)
 		printk(KERN_ERR "broken BIOS or MPTABLE parser, ayiee!!\n");
 
-	if (test_bit(bus, mp_bus_not_pci))
+	if (test_bit(bus, mp_bus_not_pci)) {
 		irq = mp_irqs[idx].mp_srcbusirq;
-	else {
+	} else {
 		/*
 		 * PCI IRQs are mapped in order
 		 */
@@ -1092,14 +1171,14 @@ static int pin_2_irq(int idx, int apic, int pin)
 		while (i < apic)
 			irq += nr_ioapic_registers[i++];
 		irq += pin;
-
-		/*
-		 * For MPS mode, so far only needed by ES7000 platform
-		 */
-		if (ioapic_renumber_irq)
-			irq = ioapic_renumber_irq(apic, irq);
+                /*
+                 * For MPS mode, so far only needed by ES7000 platform
+                 */
+                if (ioapic_renumber_irq)
+                        irq = ioapic_renumber_irq(apic, irq);
 	}
 
+#ifdef CONFIG_X86_32
 	/*
 	 * PCI IRQ command line redirection. Yes, limits are hardcoded.
 	 */
@@ -1116,6 +1195,8 @@ static int pin_2_irq(int idx, int apic, int pin)
 			}
 		}
 	}
+#endif
+
 	return irq;
 }
 
@@ -1145,74 +1226,70 @@ static int __assign_irq_vector(int irq, cpumask_t mask)
 	 * Also, we've got to be careful not to trash gate
 	 * 0x80, because int 0x80 is hm, kind of importantish. ;)
 	 */
-        static int current_vector = FIRST_DEVICE_VECTOR, current_offset = 0;
-        unsigned int old_vector;
-        int cpu;
-        struct irq_cfg *cfg;
+	static int current_vector = FIRST_DEVICE_VECTOR, current_offset = 0;
+	unsigned int old_vector;
+	int cpu;
+	struct irq_cfg *cfg;
 
-        cfg = irq_cfg(irq);
+	cfg = irq_cfg(irq);
 
-        /* Only try and allocate irqs on cpus that are present */
-        cpus_and(mask, mask, cpu_online_map);
+	/* Only try and allocate irqs on cpus that are present */
+	cpus_and(mask, mask, cpu_online_map);
 
-        if ((cfg->move_in_progress) || cfg->move_cleanup_count)
-                return -EBUSY;
+	if ((cfg->move_in_progress) || cfg->move_cleanup_count)
+		return -EBUSY;
 
-        old_vector = cfg->vector;
-        if (old_vector) {
-                cpumask_t tmp;
-                cpus_and(tmp, cfg->domain, mask);
-                if (!cpus_empty(tmp))
-                        return 0;
-        }
+	old_vector = cfg->vector;
+	if (old_vector) {
+		cpumask_t tmp;
+		cpus_and(tmp, cfg->domain, mask);
+		if (!cpus_empty(tmp))
+			return 0;
+	}
 
-        for_each_cpu_mask_nr(cpu, mask) {
-                cpumask_t domain, new_mask;
-                int new_cpu;
-                int vector, offset;
+	for_each_cpu_mask_nr(cpu, mask) {
+		cpumask_t domain, new_mask;
+		int new_cpu;
+		int vector, offset;
 
-                domain = vector_allocation_domain(cpu);
-                cpus_and(new_mask, domain, cpu_online_map);
+		domain = vector_allocation_domain(cpu);
+		cpus_and(new_mask, domain, cpu_online_map);
 
-                vector = current_vector;
-                offset = current_offset;
+		vector = current_vector;
+		offset = current_offset;
 next:
-                vector += 8;
-                if (vector >= first_system_vector) {
-                        /* If we run out of vectors on large boxen, must share them. */
-                        offset = (offset + 1) % 8;
-                        vector = FIRST_DEVICE_VECTOR + offset;
-                }
-                if (unlikely(current_vector == vector))
-                        continue;
+		vector += 8;
+		if (vector >= first_system_vector) {
+			/* If we run out of vectors on large boxen, must share them. */
+			offset = (offset + 1) % 8;
+			vector = FIRST_DEVICE_VECTOR + offset;
+		}
+		if (unlikely(current_vector == vector))
+			continue;
 #ifdef CONFIG_X86_64
-                if (vector == IA32_SYSCALL_VECTOR)
-                        goto next;
+		if (vector == IA32_SYSCALL_VECTOR)
+			goto next;
 #else
-                if (vector == SYSCALL_VECTOR)
-                        goto next;
+		if (vector == SYSCALL_VECTOR)
+			goto next;
 #endif
-                for_each_cpu_mask_nr(new_cpu, new_mask)
-                        if (per_cpu(vector_irq, new_cpu)[vector] != -1)
-                                goto next;
-                /* Found one! */
-                current_vector = vector;
-                current_offset = offset;
-                if (old_vector) {
-                        cfg->move_in_progress = 1;
-                        cfg->old_domain = cfg->domain;
-                }
-		printk(KERN_DEBUG "assign_irq_vector: irq %d vector %#x cpu ", irq, vector);
-		for_each_cpu_mask_nr(new_cpu, new_mask) {
-			per_cpu(vector_irq, new_cpu)[vector] = irq;
-			printk(KERN_CONT " %d ", new_cpu);
+		for_each_cpu_mask_nr(new_cpu, new_mask)
+			if (per_cpu(vector_irq, new_cpu)[vector] != -1)
+				goto next;
+		/* Found one! */
+		current_vector = vector;
+		current_offset = offset;
+		if (old_vector) {
+			cfg->move_in_progress = 1;
+			cfg->old_domain = cfg->domain;
 		}
-		printk(KERN_CONT "\n");
-                cfg->vector = vector;
-                cfg->domain = domain;
-                return 0;
-        }
-        return -ENOSPC;
+		for_each_cpu_mask_nr(new_cpu, new_mask)
+			per_cpu(vector_irq, new_cpu)[vector] = irq;
+		cfg->vector = vector;
+		cfg->domain = domain;
+		return 0;
+	}
+	return -ENOSPC;
 }
 
 static int assign_irq_vector(int irq, cpumask_t mask)
@@ -1223,7 +1300,6 @@ static int assign_irq_vector(int irq, cpumask_t mask)
 	spin_lock_irqsave(&vector_lock, flags);
 	err = __assign_irq_vector(irq, mask);
 	spin_unlock_irqrestore(&vector_lock, flags);
-
 	return err;
 }
 
@@ -1269,36 +1345,39 @@ void __setup_vector_irq(int cpu)
 		cfg = irq_cfg(irq);
 		if (!cpu_isset(cpu, cfg->domain))
 			per_cpu(vector_irq, cpu)[vector] = -1;
-        }
+	}
 }
 
 static struct irq_chip ioapic_chip;
+#ifdef CONFIG_INTR_REMAP
+static struct irq_chip ir_ioapic_chip;
+#endif
 
-#define IOAPIC_AUTO	-1
-#define IOAPIC_EDGE	0
-#define IOAPIC_LEVEL	1
+#define IOAPIC_AUTO     -1
+#define IOAPIC_EDGE     0
+#define IOAPIC_LEVEL    1
 
 #ifdef CONFIG_X86_32
 static inline int IO_APIC_irq_trigger(int irq)
 {
-	int apic, idx, pin;
+        int apic, idx, pin;
 
-	for (apic = 0; apic < nr_ioapics; apic++) {
-		for (pin = 0; pin < nr_ioapic_registers[apic]; pin++) {
-			idx = find_irq_entry(apic, pin, mp_INT);
-			if ((idx != -1) && (irq == pin_2_irq(idx, apic, pin)))
-				return irq_trigger(idx);
-		}
-	}
-	/*
-	 * nonexistent IRQs are edge default
-	 */
-	return 0;
+        for (apic = 0; apic < nr_ioapics; apic++) {
+                for (pin = 0; pin < nr_ioapic_registers[apic]; pin++) {
+                        idx = find_irq_entry(apic, pin, mp_INT);
+                        if ((idx != -1) && (irq == pin_2_irq(idx, apic, pin)))
+                                return irq_trigger(idx);
+                }
+        }
+        /*
+         * nonexistent IRQs are edge default
+         */
+        return 0;
 }
 #else
 static inline int IO_APIC_irq_trigger(int irq)
 {
-        return 1;
+	return 1;
 }
 #endif
 
@@ -1318,13 +1397,27 @@ static void ioapic_register_intr(int irq, unsigned long trigger)
 	else
 		desc->status &= ~IRQ_LEVEL;
 
+#ifdef CONFIG_INTR_REMAP
+	if (irq_remapped(irq)) {
+		desc->status |= IRQ_MOVE_PCNTXT;
+		if (trigger)
+			set_irq_chip_and_handler_name(irq, &ir_ioapic_chip,
+						      handle_fasteoi_irq,
+						     "fasteoi");
+		else
+			set_irq_chip_and_handler_name(irq, &ir_ioapic_chip,
+						      handle_edge_irq, "edge");
+		return;
+	}
+#endif
 	if ((trigger == IOAPIC_AUTO && IO_APIC_irq_trigger(irq)) ||
 	    trigger == IOAPIC_LEVEL)
 		set_irq_chip_and_handler_name(irq, &ioapic_chip,
-					 handle_fasteoi_irq, "fasteoi");
+					      handle_fasteoi_irq,
+					      "fasteoi");
 	else
 		set_irq_chip_and_handler_name(irq, &ioapic_chip,
-					 handle_edge_irq, "edge");
+					      handle_edge_irq, "edge");
 }
 
 static int setup_ioapic_entry(int apic, int irq,
@@ -1337,11 +1430,45 @@ static int setup_ioapic_entry(int apic, int irq,
 	 */
 	memset(entry,0,sizeof(*entry));
 
-	entry->delivery_mode = INT_DELIVERY_MODE;
-	entry->dest_mode = INT_DEST_MODE;
-	entry->dest = destination;
+#ifdef CONFIG_INTR_REMAP
+	if (intr_remapping_enabled) {
+		struct intel_iommu *iommu = map_ioapic_to_ir(apic);
+		struct irte irte;
+		struct IR_IO_APIC_route_entry *ir_entry =
+			(struct IR_IO_APIC_route_entry *) entry;
+		int index;
+
+		if (!iommu)
+			panic("No mapping iommu for ioapic %d\n", apic);
+
+		index = alloc_irte(iommu, irq, 1);
+		if (index < 0)
+			panic("Failed to allocate IRTE for ioapic %d\n", apic);
+
+		memset(&irte, 0, sizeof(irte));
+
+		irte.present = 1;
+		irte.dst_mode = INT_DEST_MODE;
+		irte.trigger_mode = trigger;
+		irte.dlvry_mode = INT_DELIVERY_MODE;
+		irte.vector = vector;
+		irte.dest_id = IRTE_DEST(destination);
+
+		modify_irte(irq, &irte);
+
+		ir_entry->index2 = (index >> 15) & 0x1;
+		ir_entry->zero = 0;
+		ir_entry->format = 1;
+		ir_entry->index = (index & 0x7fff);
+	} else
+#endif
+	{
+		entry->delivery_mode = INT_DELIVERY_MODE;
+		entry->dest_mode = INT_DEST_MODE;
+		entry->dest = destination;
+	}
 
-	entry->mask = 0;                                /* enable IRQ */
+	entry->mask = 0;				/* enable IRQ */
 	entry->trigger = trigger;
 	entry->polarity = polarity;
 	entry->vector = vector;
@@ -1351,12 +1478,11 @@ static int setup_ioapic_entry(int apic, int irq,
 	 */
 	if (trigger)
 		entry->mask = 1;
-
 	return 0;
 }
 
 static void setup_IO_APIC_irq(int apic, int pin, unsigned int irq,
-                              int trigger, int polarity)
+			      int trigger, int polarity)
 {
 	struct irq_cfg *cfg;
 	struct IO_APIC_route_entry entry;
@@ -1420,10 +1546,10 @@ static void __init setup_IO_APIC_irqs(void)
 		}
 
 		irq = pin_2_irq(idx, apic, pin);
-
+#ifdef CONFIG_X86_32
                 if (multi_timer_check(apic, irq))
                         continue;
-
+#endif
 		add_pin_to_irq(irq, apic, pin);
 
 		setup_IO_APIC_irq(apic, pin, irq,
@@ -1443,6 +1569,11 @@ static void __init setup_timer_IRQ0_pin(unsigned int apic, unsigned int pin,
 {
 	struct IO_APIC_route_entry entry;
 
+#ifdef CONFIG_INTR_REMAP
+	if (intr_remapping_enabled)
+		return;
+#endif
+
 	memset(&entry, 0, sizeof(entry));
 
 	/*
@@ -1461,7 +1592,7 @@ static void __init setup_timer_IRQ0_pin(unsigned int apic, unsigned int pin,
 	 * The timer IRQ doesn't have to know that behind the
 	 * scene we may have a 8259A-master in AEOI mode ...
 	 */
-	ioapic_register_intr(0, IOAPIC_EDGE);
+	set_irq_chip_and_handler_name(0, &ioapic_chip, handle_edge_irq, "edge");
 
 	/*
 	 * Add it to the IO-APIC irq-routing table:
@@ -1501,17 +1632,18 @@ __apicdebuginit(void) print_IO_APIC(void)
 	reg_01.raw = io_apic_read(apic, 1);
 	if (reg_01.bits.version >= 0x10)
 		reg_02.raw = io_apic_read(apic, 2);
-	if (reg_01.bits.version >= 0x20)
-		reg_03.raw = io_apic_read(apic, 3);
+        if (reg_01.bits.version >= 0x20)
+                reg_03.raw = io_apic_read(apic, 3);
 	spin_unlock_irqrestore(&ioapic_lock, flags);
 
+	printk("\n");
 	printk(KERN_DEBUG "IO APIC #%d......\n", mp_ioapics[apic].mp_apicid);
 	printk(KERN_DEBUG ".... register #00: %08X\n", reg_00.raw);
 	printk(KERN_DEBUG ".......    : physical APIC id: %02X\n", reg_00.bits.ID);
 	printk(KERN_DEBUG ".......    : Delivery Type: %X\n", reg_00.bits.delivery_type);
 	printk(KERN_DEBUG ".......    : LTS          : %X\n", reg_00.bits.LTS);
 
-	printk(KERN_DEBUG ".... register #01: %08X\n", reg_01.raw);
+	printk(KERN_DEBUG ".... register #01: %08X\n", *(int *)&reg_01);
 	printk(KERN_DEBUG ".......     : max redirection entries: %04X\n", reg_01.bits.entries);
 
 	printk(KERN_DEBUG ".......     : PRQ implemented: %X\n", reg_01.bits.PRQ);
@@ -1548,7 +1680,10 @@ __apicdebuginit(void) print_IO_APIC(void)
 
 		entry = ioapic_read_entry(apic, i);
 
-		printk(KERN_DEBUG " %02x %02X  ", i, entry.dest);
+		printk(KERN_DEBUG " %02x %03X ",
+			i,
+			entry.dest
+		);
 
 		printk("%1d    %1d    %1d   %1d   %1d    %1d    %1d    %02X\n",
 			entry.mask,
@@ -1567,7 +1702,7 @@ __apicdebuginit(void) print_IO_APIC(void)
 		struct irq_pin_list *entry = cfg->irq_2_pin;
 		if (!entry)
 			continue;
-		printk(KERN_DEBUG "IRQ%d ", i);
+		printk(KERN_DEBUG "IRQ%d ", cfg->irq);
 		for (;;) {
 			printk("-> %d:%d", entry->apic, entry->pin);
 			if (!entry->next)
@@ -1614,8 +1749,7 @@ __apicdebuginit(void) print_local_APIC(void *dummy)
 	printk("\n" KERN_DEBUG "printing local APIC contents on CPU#%d/%d:\n",
 		smp_processor_id(), hard_smp_processor_id());
 	v = apic_read(APIC_ID);
-	printk(KERN_INFO "... APIC ID:      %08x (%01x)\n", v,
-			GET_APIC_ID(v));
+	printk(KERN_INFO "... APIC ID:      %08x (%01x)\n", v, read_apic_id());
 	v = apic_read(APIC_LVR);
 	printk(KERN_INFO "... APIC VERSION: %08x\n", v);
 	ver = GET_APIC_VERSION(v);
@@ -1624,7 +1758,7 @@ __apicdebuginit(void) print_local_APIC(void *dummy)
 	v = apic_read(APIC_TASKPRI);
 	printk(KERN_DEBUG "... APIC TASKPRI: %08x (%02x)\n", v, v & APIC_TPRI_MASK);
 
-	if (APIC_INTEGRATED(ver)) {			/* !82489DX */
+	if (APIC_INTEGRATED(ver)) {                     /* !82489DX */
 		v = apic_read(APIC_ARBPRI);
 		printk(KERN_DEBUG "... APIC ARBPRI: %08x (%02x)\n", v,
 			v & APIC_ARBPRI_MASK);
@@ -1650,9 +1784,10 @@ __apicdebuginit(void) print_local_APIC(void *dummy)
 	printk(KERN_DEBUG "... APIC IRR field:\n");
 	print_APIC_bitfield(APIC_IRR);
 
-	if (APIC_INTEGRATED(ver)) {		/* !82489DX */
-		if (maxlvt > 3)		/* Due to the Pentium erratum 3AP. */
+	if (APIC_INTEGRATED(ver)) {             /* !82489DX */
+		if (maxlvt > 3)         /* Due to the Pentium erratum 3AP. */
 			apic_write(APIC_ESR, 0);
+
 		v = apic_read(APIC_ESR);
 		printk(KERN_DEBUG "... APIC ESR: %08x\n", v);
 	}
@@ -1710,11 +1845,11 @@ __apicdebuginit(void) print_PIC(void)
 	v = inb(0xa0) << 8 | inb(0x20);
 	printk(KERN_DEBUG "... PIC  IRR: %04x\n", v);
 
-	outb(0x0b, 0xa0);
-	outb(0x0b, 0x20);
+	outb(0x0b,0xa0);
+	outb(0x0b,0x20);
 	v = inb(0xa0) << 8 | inb(0x20);
-	outb(0x0a, 0xa0);
-	outb(0x0a, 0x20);
+	outb(0x0a,0xa0);
+	outb(0x0a,0x20);
 
 	spin_unlock_irqrestore(&i8259A_lock, flags);
 
@@ -1739,16 +1874,19 @@ fs_initcall(print_all_ICs);
 /* Where if anywhere is the i8259 connect in external int mode */
 static struct { int pin, apic; } ioapic_i8259 = { -1, -1 };
 
-static void __init enable_IO_APIC(void)
+void __init enable_IO_APIC(void)
 {
 	union IO_APIC_reg_01 reg_01;
 	int i8259_apic, i8259_pin;
-	int i, apic;
+	int apic;
 	unsigned long flags;
 
+#ifdef CONFIG_X86_32
+	int i;
 	if (!pirqs_enabled)
 		for (i = 0; i < MAX_PIRQS; i++)
 			pirq_entries[i] = -1;
+#endif
 
 	/*
 	 * The number of IO-APIC IRQ registers (== #pins):
@@ -1759,7 +1897,7 @@ static void __init enable_IO_APIC(void)
 		spin_unlock_irqrestore(&ioapic_lock, flags);
 		nr_ioapic_registers[apic] = reg_01.bits.entries+1;
 	}
-	for (apic = 0; apic < nr_ioapics; apic++) {
+	for(apic = 0; apic < nr_ioapics; apic++) {
 		int pin;
 		/* See if any of the pins is in ExtINT mode */
 		for (pin = 0; pin < nr_ioapic_registers[apic]; pin++) {
@@ -1830,16 +1968,18 @@ void disable_IO_APIC(void)
 		entry.dest_mode       = 0; /* Physical */
 		entry.delivery_mode   = dest_ExtINT; /* ExtInt */
 		entry.vector          = 0;
-		entry.dest	      = read_apic_id();
+		entry.dest            = read_apic_id();
 
 		/*
 		 * Add it to the IO-APIC irq-routing table:
 		 */
 		ioapic_write_entry(ioapic_i8259.apic, ioapic_i8259.pin, entry);
 	}
+
 	disconnect_bsp_APIC(ioapic_i8259.pin != -1);
 }
 
+#ifdef CONFIG_X86_32
 /*
  * function to set the IO-APIC physical IDs based on the
  * values stored in the MPC table.
@@ -1940,8 +2080,6 @@ static void __init setup_ioapic_ids_from_mpc(void)
 
 		reg_00.bits.ID = mp_ioapics[apic].mp_apicid;
 		spin_lock_irqsave(&ioapic_lock, flags);
-		io_apic_write(apic, 0, reg_00.raw);
-		spin_unlock_irqrestore(&ioapic_lock, flags);
 
 		/*
 		 * Sanity check
@@ -1955,6 +2093,7 @@ static void __init setup_ioapic_ids_from_mpc(void)
 			apic_printk(APIC_VERBOSE, " ok.\n");
 	}
 }
+#endif
 
 int no_timer_check __initdata;
 
@@ -1994,9 +2133,10 @@ static int __init timer_irq_works(void)
 	 * might have cached one ExtINT interrupt.  Finally, at
 	 * least one tick may be lost due to delays.
 	 */
+
+	/* jiffies wrap? */
 	if (time_after(jiffies, t1 + 4))
 		return 1;
-
 	return 0;
 }
 
@@ -2014,8 +2154,6 @@ static int __init timer_irq_works(void)
  */
 
 /*
- * Startup quirk:
- *
  * Starting up a edge-triggered IO-APIC interrupt is
  * nasty - we need to make sure that we get the edge.
  * If it is already asserted for some reason, we need
@@ -2023,9 +2161,8 @@ static int __init timer_irq_works(void)
  *
  * This is not complete - we should be able to fake
  * an edge even if it isn't on the 8259A...
- *
- * (We do this for level-triggered IRQs too - it cannot hurt.)
  */
+
 static unsigned int startup_ioapic_irq(unsigned int irq)
 {
 	int was_pending = 0;
@@ -2043,70 +2180,254 @@ static unsigned int startup_ioapic_irq(unsigned int irq)
 	return was_pending;
 }
 
+#ifdef CONFIG_X86_64
 static int ioapic_retrigger_irq(unsigned int irq)
 {
-	send_IPI_self(irq_cfg(irq)->vector);
+
+	struct irq_cfg *cfg = irq_cfg(irq);
+	unsigned long flags;
+
+	spin_lock_irqsave(&vector_lock, flags);
+	send_IPI_mask(cpumask_of_cpu(first_cpu(cfg->domain)), cfg->vector);
+	spin_unlock_irqrestore(&vector_lock, flags);
 
 	return 1;
 }
-
-#ifdef CONFIG_SMP
-asmlinkage void smp_irq_move_cleanup_interrupt(void)
+#else
+static int ioapic_retrigger_irq(unsigned int irq)
 {
-	unsigned vector, me;
-	ack_APIC_irq();
-	irq_enter();
-
-	me = smp_processor_id();
-	for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) {
-		unsigned int irq;
-		struct irq_desc *desc;
-		struct irq_cfg *cfg;
-		irq = __get_cpu_var(vector_irq)[vector];
+        send_IPI_self(irq_cfg(irq)->vector);
 
-		desc = irq_to_desc(irq);
-		if (!desc)
-			continue;
+        return 1;
+}
+#endif
 
-		cfg = irq_cfg(irq);
-		spin_lock(&desc->lock);
-		if (!cfg->move_cleanup_count)
-			goto unlock;
+/*
+ * Level and edge triggered IO-APIC interrupts need different handling,
+ * so we use two separate IRQ descriptors. Edge triggered IRQs can be
+ * handled with the level-triggered descriptor, but that one has slightly
+ * more overhead. Level-triggered interrupts cannot be handled with the
+ * edge-triggered handler, without risking IRQ storms and other ugly
+ * races.
+ */
 
-		if ((vector == cfg->vector) && cpu_isset(me, cfg->domain))
-			goto unlock;
+#ifdef CONFIG_SMP
 
-		__get_cpu_var(vector_irq)[vector] = -1;
-		cfg->move_cleanup_count--;
-unlock:
-		spin_unlock(&desc->lock);
-	}
+#ifdef CONFIG_INTR_REMAP
+static void ir_irq_migration(struct work_struct *work);
 
-	irq_exit();
-}
+static DECLARE_DELAYED_WORK(ir_migration_work, ir_irq_migration);
 
-static void irq_complete_move(unsigned int irq)
+/*
+ * Migrate the IO-APIC irq in the presence of intr-remapping.
+ *
+ * For edge triggered, irq migration is a simple atomic update(of vector
+ * and cpu destination) of IRTE and flush the hardware cache.
+ *
+ * For level triggered, we need to modify the io-apic RTE aswell with the update
+ * vector information, along with modifying IRTE with vector and destination.
+ * So irq migration for level triggered is little  bit more complex compared to
+ * edge triggered migration. But the good news is, we use the same algorithm
+ * for level triggered migration as we have today, only difference being,
+ * we now initiate the irq migration from process context instead of the
+ * interrupt context.
+ *
+ * In future, when we do a directed EOI (combined with cpu EOI broadcast
+ * suppression) to the IO-APIC, level triggered irq migration will also be
+ * as simple as edge triggered migration and we can do the irq migration
+ * with a simple atomic update to IO-APIC RTE.
+ */
+static void migrate_ioapic_irq(int irq, cpumask_t mask)
 {
-	struct irq_cfg *cfg = irq_cfg(irq);
-	unsigned vector, me;
+	struct irq_cfg *cfg;
+	struct irq_desc *desc;
+	cpumask_t tmp, cleanup_mask;
+	struct irte irte;
+	int modify_ioapic_rte;
+	unsigned int dest;
+	unsigned long flags;
 
-	if (likely(!cfg->move_in_progress))
+	cpus_and(tmp, mask, cpu_online_map);
+	if (cpus_empty(tmp))
 		return;
 
-	vector = ~get_irq_regs()->orig_ax;
-	me = smp_processor_id();
-	if ((vector == cfg->vector) && cpu_isset(me, cfg->domain)) {
-		cpumask_t cleanup_mask;
+	if (get_irte(irq, &irte))
+		return;
 
-		cpus_and(cleanup_mask, cfg->old_domain, cpu_online_map);
-		cfg->move_cleanup_count = cpus_weight(cleanup_mask);
-		send_IPI_mask(cleanup_mask, IRQ_MOVE_CLEANUP_VECTOR);
+	if (assign_irq_vector(irq, mask))
+		return;
+
+	cfg = irq_cfg(irq);
+	cpus_and(tmp, cfg->domain, mask);
+	dest = cpu_mask_to_apicid(tmp);
+
+	desc = irq_to_desc(irq);
+	modify_ioapic_rte = desc->status & IRQ_LEVEL;
+	if (modify_ioapic_rte) {
+		spin_lock_irqsave(&ioapic_lock, flags);
+		__target_IO_APIC_irq(irq, dest, cfg->vector);
+		spin_unlock_irqrestore(&ioapic_lock, flags);
+	}
+
+	irte.vector = cfg->vector;
+	irte.dest_id = IRTE_DEST(dest);
+
+	/*
+	 * Modified the IRTE and flushes the Interrupt entry cache.
+	 */
+	modify_irte(irq, &irte);
+
+	if (cfg->move_in_progress) {
+		cpus_and(cleanup_mask, cfg->old_domain, cpu_online_map);
+		cfg->move_cleanup_count = cpus_weight(cleanup_mask);
+		send_IPI_mask(cleanup_mask, IRQ_MOVE_CLEANUP_VECTOR);
+		cfg->move_in_progress = 0;
+	}
+
+	desc->affinity = mask;
+}
+
+static int migrate_irq_remapped_level(int irq)
+{
+	int ret = -1;
+	struct irq_desc *desc = irq_to_desc(irq);
+
+	mask_IO_APIC_irq(irq);
+
+	if (io_apic_level_ack_pending(irq)) {
+		/*
+	 	 * Interrupt in progress. Migrating irq now will change the
+		 * vector information in the IO-APIC RTE and that will confuse
+		 * the EOI broadcast performed by cpu.
+		 * So, delay the irq migration to the next instance.
+		 */
+		schedule_delayed_work(&ir_migration_work, 1);
+		goto unmask;
+	}
+
+	/* everthing is clear. we have right of way */
+	migrate_ioapic_irq(irq, desc->pending_mask);
+
+	ret = 0;
+	desc->status &= ~IRQ_MOVE_PENDING;
+	cpus_clear(desc->pending_mask);
+
+unmask:
+	unmask_IO_APIC_irq(irq);
+	return ret;
+}
+
+static void ir_irq_migration(struct work_struct *work)
+{
+	unsigned int irq;
+	struct irq_desc *desc;
+
+	for_each_irq_desc(irq, desc) {
+		if (desc->status & IRQ_MOVE_PENDING) {
+			unsigned long flags;
+
+			spin_lock_irqsave(&desc->lock, flags);
+			if (!desc->chip->set_affinity ||
+			    !(desc->status & IRQ_MOVE_PENDING)) {
+				desc->status &= ~IRQ_MOVE_PENDING;
+				spin_unlock_irqrestore(&desc->lock, flags);
+				continue;
+			}
+
+			desc->chip->set_affinity(irq, desc->pending_mask);
+			spin_unlock_irqrestore(&desc->lock, flags);
+		}
+	}
+}
+
+/*
+ * Migrates the IRQ destination in the process context.
+ */
+static void set_ir_ioapic_affinity_irq(unsigned int irq, cpumask_t mask)
+{
+	struct irq_desc *desc = irq_to_desc(irq);
+
+	if (desc->status & IRQ_LEVEL) {
+		desc->status |= IRQ_MOVE_PENDING;
+		desc->pending_mask = mask;
+		migrate_irq_remapped_level(irq);
+		return;
+	}
+
+	migrate_ioapic_irq(irq, mask);
+}
+#endif
+
+asmlinkage void smp_irq_move_cleanup_interrupt(void)
+{
+	unsigned vector, me;
+	ack_APIC_irq();
+#ifdef CONFIG_X86_64
+	exit_idle();
+#endif
+	irq_enter();
+
+	me = smp_processor_id();
+	for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) {
+		unsigned int irq;
+		struct irq_desc *desc;
+		struct irq_cfg *cfg;
+		irq = __get_cpu_var(vector_irq)[vector];
+
+		desc = irq_to_desc(irq);
+		if (!desc)
+			continue;
+
+		cfg = irq_cfg(irq);
+		spin_lock(&desc->lock);
+		if (!cfg->move_cleanup_count)
+			goto unlock;
+
+		if ((vector == cfg->vector) && cpu_isset(me, cfg->domain))
+			goto unlock;
+
+		__get_cpu_var(vector_irq)[vector] = -1;
+		cfg->move_cleanup_count--;
+unlock:
+		spin_unlock(&desc->lock);
+	}
+
+	irq_exit();
+}
+
+static void irq_complete_move(unsigned int irq)
+{
+	struct irq_cfg *cfg = irq_cfg(irq);
+	unsigned vector, me;
+
+	if (likely(!cfg->move_in_progress))
+		return;
+
+	vector = ~get_irq_regs()->orig_ax;
+	me = smp_processor_id();
+	if ((vector == cfg->vector) && cpu_isset(me, cfg->domain)) {
+		cpumask_t cleanup_mask;
+
+		cpus_and(cleanup_mask, cfg->old_domain, cpu_online_map);
+		cfg->move_cleanup_count = cpus_weight(cleanup_mask);
+		send_IPI_mask(cleanup_mask, IRQ_MOVE_CLEANUP_VECTOR);
 		cfg->move_in_progress = 0;
 	}
 }
 #else
 static inline void irq_complete_move(unsigned int irq) {}
 #endif
+#ifdef CONFIG_INTR_REMAP
+static void ack_x2apic_level(unsigned int irq)
+{
+	ack_x2APIC_irq();
+}
+
+static void ack_x2apic_edge(unsigned int irq)
+{
+	ack_x2APIC_irq();
+}
+#endif
 
 static void ack_apic_edge(unsigned int irq)
 {
@@ -2118,55 +2439,55 @@ static void ack_apic_edge(unsigned int irq)
 #ifdef CONFIG_X86_64
 static void ack_apic_level(unsigned int irq)
 {
-        int do_unmask_irq = 0;
+	int do_unmask_irq = 0;
 
-        irq_complete_move(irq);
+	irq_complete_move(irq);
 #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(irq);
-        }
+	/* If we are moving the irq we need to mask it */
+	if (unlikely(irq_to_desc(irq)->status & IRQ_MOVE_PENDING)) {
+		do_unmask_irq = 1;
+		mask_IO_APIC_irq(irq);
+	}
 #endif
 
-        /*
-         * We must acknowledge the irq before we move it or the acknowledge will
-         * not propagate properly.
-         */
-        ack_APIC_irq();
-
-        /* Now we can move and renable the irq */
-        if (unlikely(do_unmask_irq)) {
-                /* Only migrate the irq if the ack has been received.
-                 *
-                 * On rare occasions the broadcast level triggered ack gets
-                 * delayed going to ioapics, and if we reprogram the
-                 * vector while Remote IRR is still set the irq will never
-                 * fire again.
-                 *
-                 * To prevent this scenario we read the Remote IRR bit
-                 * of the ioapic.  This has two effects.
-                 * - On any sane system the read of the ioapic will
-                 *   flush writes (and acks) going to the ioapic from
-                 *   this cpu.
-                 * - We get to see if the ACK has actually been delivered.
-                 *
-                 * Based on failed experiments of reprogramming the
-                 * ioapic entry from outside of irq context starting
-                 * with masking the ioapic entry and then polling until
-                 * Remote IRR was clear before reprogramming the
-                 * ioapic I don't trust the Remote IRR bit to be
-                 * completey accurate.
-                 *
-                 * However there appears to be no other way to plug
-                 * this race, so if the Remote IRR bit is not
-                 * accurate and is causing problems then it is a hardware bug
-                 * and you can go talk to the chipset vendor about it.
-                 */
-                if (!io_apic_level_ack_pending(irq))
-                        move_masked_irq(irq, desc);
-                unmask_IO_APIC_irq(irq);
-        }
+	/*
+	 * We must acknowledge the irq before we move it or the acknowledge will
+	 * not propagate properly.
+	 */
+	ack_APIC_irq();
+
+	/* Now we can move and renable the irq */
+	if (unlikely(do_unmask_irq)) {
+		/* Only migrate the irq if the ack has been received.
+		 *
+		 * On rare occasions the broadcast level triggered ack gets
+		 * delayed going to ioapics, and if we reprogram the
+		 * vector while Remote IRR is still set the irq will never
+		 * fire again.
+		 *
+		 * To prevent this scenario we read the Remote IRR bit
+		 * of the ioapic.  This has two effects.
+		 * - On any sane system the read of the ioapic will
+		 *   flush writes (and acks) going to the ioapic from
+		 *   this cpu.
+		 * - We get to see if the ACK has actually been delivered.
+		 *
+		 * Based on failed experiments of reprogramming the
+		 * ioapic entry from outside of irq context starting
+		 * with masking the ioapic entry and then polling until
+		 * Remote IRR was clear before reprogramming the
+		 * ioapic I don't trust the Remote IRR bit to be
+		 * completey accurate.
+		 *
+		 * However there appears to be no other way to plug
+		 * this race, so if the Remote IRR bit is not
+		 * accurate and is causing problems then it is a hardware bug
+		 * and you can go talk to the chipset vendor about it.
+		 */
+		if (!io_apic_level_ack_pending(irq))
+			move_masked_irq(irq);
+		unmask_IO_APIC_irq(irq);
+	}
 }
 #else
 atomic_t irq_mis_count;
@@ -2177,25 +2498,25 @@ static void ack_apic_level(unsigned int irq)
 
 	irq_complete_move(irq);
 	move_native_irq(irq);
-/*
- * It appears there is an erratum which affects at least version 0x11
- * of I/O APIC (that's the 82093AA and cores integrated into various
- * chipsets).  Under certain conditions a level-triggered interrupt is
- * erroneously delivered as edge-triggered one but the respective IRR
- * bit gets set nevertheless.  As a result the I/O unit expects an EOI
- * message but it will never arrive and further interrupts are blocked
- * from the source.  The exact reason is so far unknown, but the
- * phenomenon was observed when two consecutive interrupt requests
- * from a given source get delivered to the same CPU and the source is
- * temporarily disabled in between.
- *
- * A workaround is to simulate an EOI message manually.  We achieve it
- * by setting the trigger mode to edge and then to level when the edge
- * trigger mode gets detected in the TMR of a local APIC for a
- * level-triggered interrupt.  We mask the source for the time of the
- * operation to prevent an edge-triggered interrupt escaping meanwhile.
- * The idea is from Manfred Spraul.  --macro
- */
+	/*
+	* It appears there is an erratum which affects at least version 0x11
+	* of I/O APIC (that's the 82093AA and cores integrated into various
+	* chipsets).  Under certain conditions a level-triggered interrupt is
+	* erroneously delivered as edge-triggered one but the respective IRR
+	* bit gets set nevertheless.  As a result the I/O unit expects an EOI
+	* message but it will never arrive and further interrupts are blocked
+	* from the source.  The exact reason is so far unknown, but the
+	* phenomenon was observed when two consecutive interrupt requests
+	* from a given source get delivered to the same CPU and the source is
+	* temporarily disabled in between.
+	*
+	* A workaround is to simulate an EOI message manually.  We achieve it
+	* by setting the trigger mode to edge and then to level when the edge
+	* trigger mode gets detected in the TMR of a local APIC for a
+	* level-triggered interrupt.  We mask the source for the time of the
+	* operation to prevent an edge-triggered interrupt escaping meanwhile.
+	* The idea is from Manfred Spraul.  --macro
+	*/
 	i = irq_cfg(irq)->vector;
 
 	v = apic_read(APIC_TMR + ((i & ~0x1f) >> 1));
@@ -2225,6 +2546,20 @@ static struct irq_chip ioapic_chip __read_mostly = {
 	.retrigger	= ioapic_retrigger_irq,
 };
 
+#ifdef CONFIG_INTR_REMAP
+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,
+	.ack 		= ack_x2apic_edge,
+	.eoi 		= ack_x2apic_level,
+#ifdef CONFIG_SMP
+	.set_affinity 	= set_ir_ioapic_affinity_irq,
+#endif
+	.retrigger	= ioapic_retrigger_irq,
+};
+#endif
 
 static inline void init_IO_APIC_traps(void)
 {
@@ -2282,7 +2617,7 @@ 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 (unsigned int irq)
 {
 	ack_APIC_irq();
 }
@@ -2383,12 +2718,12 @@ static inline void __init unlock_ExtINT_logic(void)
 
 static int disable_timer_pin_1 __initdata;
 /* Actually the next is obsolete, but keep it for paranoid reasons -AK */
-static int __init parse_disable_timer_pin_1(char *arg)
+static int __init disable_timer_pin_setup(char *arg)
 {
 	disable_timer_pin_1 = 1;
 	return 0;
 }
-early_param("disable_timer_pin_1", parse_disable_timer_pin_1);
+early_param("disable_timer_pin_1", disable_timer_pin_setup);
 
 int timer_through_8259 __initdata;
 
@@ -2397,6 +2732,8 @@ int timer_through_8259 __initdata;
  * a wide range of boards and BIOS bugs.  Fortunately only the timer IRQ
  * is so screwy.  Thanks to Brian Perkins for testing/hacking this beast
  * fanatically on his truly buggy board.
+ *
+ * FIXME: really need to revamp this for all platforms.
  */
 static inline void __init check_timer(void)
 {
@@ -2408,8 +2745,8 @@ static inline void __init check_timer(void)
 
 	local_irq_save(flags);
 
-	ver = apic_read(APIC_LVR);
-	ver = GET_APIC_VERSION(ver);
+        ver = apic_read(APIC_LVR);
+        ver = GET_APIC_VERSION(ver);
 
 	/*
 	 * get/set the timer IRQ vector:
@@ -2428,7 +2765,9 @@ static inline void __init check_timer(void)
 	 */
 	apic_write(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_EXTINT);
 	init_8259A(1);
+#ifdef CONFIG_X86_32
 	timer_ack = (nmi_watchdog == NMI_IO_APIC && !APIC_INTEGRATED(ver));
+#endif
 
 	pin1  = find_isa_irq_pin(0, mp_INT);
 	apic1 = find_isa_irq_apic(0, mp_INT);
@@ -2447,6 +2786,10 @@ static inline void __init check_timer(void)
 	 * 8259A.
 	 */
 	if (pin1 == -1) {
+#ifdef CONFIG_INTR_REMAP
+		if (intr_remapping_enabled)
+			panic("BIOS bug: timer not connected to IO-APIC");
+#endif
 		pin1 = pin2;
 		apic1 = apic2;
 		no_pin1 = 1;
@@ -2473,6 +2816,10 @@ static inline void __init check_timer(void)
 				clear_IO_APIC_pin(0, pin1);
 			goto out;
 		}
+#ifdef CONFIG_INTR_REMAP
+		if (intr_remapping_enabled)
+			panic("timer doesn't work through Interrupt-remapped IO-APIC");
+#endif
 		clear_IO_APIC_pin(apic1, pin1);
 		if (!no_pin1)
 			apic_printk(APIC_QUIET, KERN_ERR "..MP-BIOS bug: "
@@ -2512,7 +2859,9 @@ static inline void __init check_timer(void)
 			    "through the IO-APIC - disabling NMI Watchdog!\n");
 		nmi_watchdog = NMI_NONE;
 	}
+#ifdef CONFIG_X86_32
 	timer_ack = 0;
+#endif
 
 	apic_printk(APIC_QUIET, KERN_INFO
 		    "...trying to set up timer as Virtual Wire IRQ...\n");
@@ -2570,17 +2919,25 @@ static inline void __init check_timer(void)
 
 void __init setup_IO_APIC(void)
 {
+
+#ifdef CONFIG_X86_32
 	enable_IO_APIC();
+#else
+	/*
+	 * calling enable_IO_APIC() is moved to setup_local_APIC for BP
+	 */
+#endif
 
 	io_apic_irqs = ~PIC_IRQS;
 
-	printk("ENABLING IO-APIC IRQs\n");
-
-	/*
-	 * Set up IO-APIC IRQ routing.
-	 */
-	if (!acpi_ioapic)
-		setup_ioapic_ids_from_mpc();
+	apic_printk(APIC_VERBOSE, "ENABLING IO-APIC IRQs\n");
+        /*
+         * Set up IO-APIC IRQ routing.
+         */
+#ifdef CONFIG_X86_32
+        if (!acpi_ioapic)
+                setup_ioapic_ids_from_mpc();
+#endif
 	sync_Arb_IDs();
 	setup_IO_APIC_irqs();
 	init_IO_APIC_traps();
@@ -2588,15 +2945,15 @@ void __init setup_IO_APIC(void)
 }
 
 /*
- *	Called after all the initialization is done. If we didnt find any
- *	APIC bugs then we can allow the modify fast path
+ *      Called after all the initialization is done. If we didnt find any
+ *      APIC bugs then we can allow the modify fast path
  */
 
 static int __init io_apic_bug_finalize(void)
 {
-	if (sis_apic_bug == -1)
-		sis_apic_bug = 0;
-	return 0;
+        if (sis_apic_bug == -1)
+                sis_apic_bug = 0;
+        return 0;
 }
 
 late_initcall(io_apic_bug_finalize);
@@ -2605,7 +2962,7 @@ struct sysfs_ioapic_data {
 	struct sys_device dev;
 	struct IO_APIC_route_entry entry[0];
 };
-static struct sysfs_ioapic_data *mp_ioapic_data[MAX_IO_APICS];
+static struct sysfs_ioapic_data * mp_ioapic_data[MAX_IO_APICS];
 
 static int ioapic_suspend(struct sys_device *dev, pm_message_t state)
 {
@@ -2615,8 +2972,8 @@ static int ioapic_suspend(struct sys_device *dev, pm_message_t state)
 
 	data = container_of(dev, struct sysfs_ioapic_data, dev);
 	entry = data->entry;
-	for (i = 0; i < nr_ioapic_registers[dev->id]; i++)
-		entry[i] = ioapic_read_entry(dev->id, i);
+	for (i = 0; i < nr_ioapic_registers[dev->id]; i ++, entry ++ )
+		*entry = ioapic_read_entry(dev->id, i);
 
 	return 0;
 }
@@ -2653,14 +3010,14 @@ static struct sysdev_class ioapic_sysdev_class = {
 
 static int __init ioapic_init_sysfs(void)
 {
-	struct sys_device *dev;
-	int i, size, error = 0;
+	struct sys_device * dev;
+	int i, size, error;
 
 	error = sysdev_class_register(&ioapic_sysdev_class);
 	if (error)
 		return error;
 
-	for (i = 0; i < nr_ioapics; i++) {
+	for (i = 0; i < nr_ioapics; i++ ) {
 		size = sizeof(struct sys_device) + nr_ioapic_registers[i]
 			* sizeof(struct IO_APIC_route_entry);
 		mp_ioapic_data[i] = kzalloc(size, GFP_KERNEL);
@@ -2691,18 +3048,18 @@ device_initcall(ioapic_init_sysfs);
 unsigned int create_irq_nr(unsigned int irq_want)
 {
 	/* Allocate an unused irq */
-	unsigned int irq, new;
+	unsigned int irq;
+	unsigned int new;
 	unsigned long flags;
 	struct irq_cfg *cfg_new;
 
 #ifndef CONFIG_HAVE_SPARSE_IRQ
-	/* only can use bus/dev/fn.. when per_cpu vector is used */
 	irq_want = nr_irqs - 1;
 #endif
 
 	irq = 0;
 	spin_lock_irqsave(&vector_lock, flags);
-	for (new = (nr_irqs - 1); new > 0; new--) {
+	for (new = irq_want; new > 0; new--) {
 		if (platform_legacy_irq(new))
 			continue;
 		cfg_new = irq_cfg(new);
@@ -2725,7 +3082,14 @@ unsigned int create_irq_nr(unsigned int irq_want)
 
 int create_irq(void)
 {
-	return create_irq_nr(nr_irqs - 1);
+	int irq;
+
+	irq = create_irq_nr(nr_irqs - 1);
+
+	if (irq == 0)
+		irq = -1;
+
+	return irq;
 }
 
 void destroy_irq(unsigned int irq)
@@ -2734,6 +3098,9 @@ void destroy_irq(unsigned int irq)
 
 	dynamic_irq_cleanup(irq);
 
+#ifdef CONFIG_INTR_REMAP
+	free_irte(irq);
+#endif
 	spin_lock_irqsave(&vector_lock, flags);
 	__clear_irq_vector(irq);
 	spin_unlock_irqrestore(&vector_lock, flags);
@@ -2759,25 +3126,54 @@ static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq, struct msi_ms
 	cpus_and(tmp, cfg->domain, tmp);
 	dest = cpu_mask_to_apicid(tmp);
 
-	msg->address_hi = MSI_ADDR_BASE_HI;
-	msg->address_lo =
-		MSI_ADDR_BASE_LO |
-		((INT_DEST_MODE == 0) ?
-			MSI_ADDR_DEST_MODE_PHYSICAL:
-			MSI_ADDR_DEST_MODE_LOGICAL) |
-		((INT_DELIVERY_MODE != dest_LowestPrio) ?
-			MSI_ADDR_REDIRECTION_CPU:
-			MSI_ADDR_REDIRECTION_LOWPRI) |
-		MSI_ADDR_DEST_ID(dest);
-
-	msg->data =
-		MSI_DATA_TRIGGER_EDGE |
-		MSI_DATA_LEVEL_ASSERT |
-		((INT_DELIVERY_MODE != dest_LowestPrio) ?
-			MSI_DATA_DELIVERY_FIXED:
-			MSI_DATA_DELIVERY_LOWPRI) |
-		MSI_DATA_VECTOR(cfg->vector);
+#ifdef CONFIG_INTR_REMAP
+	if (irq_remapped(irq)) {
+		struct irte irte;
+		int ir_index;
+		u16 sub_handle;
+
+		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 = INT_DEST_MODE;
+		irte.trigger_mode = 0; /* edge */
+		irte.dlvry_mode = INT_DELIVERY_MODE;
+		irte.vector = cfg->vector;
+		irte.dest_id = IRTE_DEST(dest);
+
+		modify_irte(irq, &irte);
+
+		msg->address_hi = MSI_ADDR_BASE_HI;
+		msg->data = sub_handle;
+		msg->address_lo = MSI_ADDR_BASE_LO | MSI_ADDR_IR_EXT_INT |
+				  MSI_ADDR_IR_SHV |
+				  MSI_ADDR_IR_INDEX1(ir_index) |
+				  MSI_ADDR_IR_INDEX2(ir_index);
+	} else
+#endif
+	{
+		msg->address_hi = MSI_ADDR_BASE_HI;
+		msg->address_lo =
+			MSI_ADDR_BASE_LO |
+			((INT_DEST_MODE == 0) ?
+				MSI_ADDR_DEST_MODE_PHYSICAL:
+				MSI_ADDR_DEST_MODE_LOGICAL) |
+			((INT_DELIVERY_MODE != dest_LowestPrio) ?
+				MSI_ADDR_REDIRECTION_CPU:
+				MSI_ADDR_REDIRECTION_LOWPRI) |
+			MSI_ADDR_DEST_ID(dest);
 
+		msg->data =
+			MSI_DATA_TRIGGER_EDGE |
+			MSI_DATA_LEVEL_ASSERT |
+			((INT_DELIVERY_MODE != dest_LowestPrio) ?
+				MSI_DATA_DELIVERY_FIXED:
+				MSI_DATA_DELIVERY_LOWPRI) |
+			MSI_DATA_VECTOR(cfg->vector);
+	}
 	return err;
 }
 
@@ -2788,6 +3184,7 @@ static void set_msi_irq_affinity(unsigned int irq, cpumask_t mask)
 	struct msi_msg msg;
 	unsigned int dest;
 	cpumask_t tmp;
+	struct irq_desc *desc;
 
 	cpus_and(tmp, mask, cpu_online_map);
 	if (cpus_empty(tmp))
@@ -2808,8 +3205,61 @@ static void set_msi_irq_affinity(unsigned int irq, cpumask_t mask)
 	msg.address_lo |= MSI_ADDR_DEST_ID(dest);
 
 	write_msi_msg(irq, &msg);
-	irq_to_desc(irq)->affinity = mask;
+	desc = irq_to_desc(irq);
+	desc->affinity = mask;
 }
+
+#ifdef CONFIG_INTR_REMAP
+/*
+ * Migrate the MSI irq to another cpumask. This migration is
+ * done in the process context using interrupt-remapping hardware.
+ */
+static void ir_set_msi_irq_affinity(unsigned int irq, cpumask_t mask)
+{
+	struct irq_cfg *cfg;
+	unsigned int dest;
+	cpumask_t tmp, cleanup_mask;
+	struct irte irte;
+	struct irq_desc *desc;
+
+	cpus_and(tmp, mask, cpu_online_map);
+	if (cpus_empty(tmp))
+		return;
+
+	if (get_irte(irq, &irte))
+		return;
+
+	if (assign_irq_vector(irq, mask))
+		return;
+
+	cfg = irq_cfg(irq);
+	cpus_and(tmp, cfg->domain, mask);
+	dest = cpu_mask_to_apicid(tmp);
+
+	irte.vector = cfg->vector;
+	irte.dest_id = IRTE_DEST(dest);
+
+	/*
+	 * atomically update the IRTE with the new destination and vector.
+	 */
+	modify_irte(irq, &irte);
+
+	/*
+	 * After this point, all the interrupts will start arriving
+	 * at the new destination. So, time to cleanup the previous
+	 * vector allocation.
+	 */
+	if (cfg->move_in_progress) {
+		cpus_and(cleanup_mask, cfg->old_domain, cpu_online_map);
+		cfg->move_cleanup_count = cpus_weight(cleanup_mask);
+		send_IPI_mask(cleanup_mask, IRQ_MOVE_CLEANUP_VECTOR);
+		cfg->move_in_progress = 0;
+	}
+
+	desc = irq_to_desc(irq);
+	desc->affinity = mask;
+}
+#endif
 #endif /* CONFIG_SMP */
 
 /*
@@ -2827,6 +3277,45 @@ static struct irq_chip msi_chip = {
 	.retrigger	= ioapic_retrigger_irq,
 };
 
+#ifdef CONFIG_INTR_REMAP
+static struct irq_chip msi_ir_chip = {
+	.name		= "IR-PCI-MSI",
+	.unmask		= unmask_msi_irq,
+	.mask		= mask_msi_irq,
+	.ack		= ack_x2apic_edge,
+#ifdef CONFIG_SMP
+	.set_affinity	= ir_set_msi_irq_affinity,
+#endif
+	.retrigger	= ioapic_retrigger_irq,
+};
+
+/*
+ * Map the PCI dev to the corresponding remapping hardware unit
+ * and allocate 'nvec' consecutive interrupt-remapping table entries
+ * in it.
+ */
+static int msi_alloc_irte(struct pci_dev *dev, int irq, int nvec)
+{
+	struct intel_iommu *iommu;
+	int index;
+
+	iommu = map_dev_to_ir(dev);
+	if (!iommu) {
+		printk(KERN_ERR
+		       "Unable to map PCI %s to iommu\n", pci_name(dev));
+		return -ENOENT;
+	}
+
+	index = alloc_irte(iommu, irq, nvec);
+	if (index < 0) {
+		printk(KERN_ERR
+		       "Unable to allocate %d IRTE for PCI %s\n", nvec,
+		        pci_name(dev));
+		return -ENOSPC;
+	}
+	return index;
+}
+#endif
 
 static int setup_msi_irq(struct pci_dev *dev, struct msi_desc *desc, int irq)
 {
@@ -2840,7 +3329,17 @@ static int setup_msi_irq(struct pci_dev *dev, struct msi_desc *desc, int irq)
 	set_irq_msi(irq, desc);
 	write_msi_msg(irq, &msg);
 
-	set_irq_chip_and_handler_name(irq, &msi_chip, handle_edge_irq, "edge");
+#ifdef CONFIG_INTR_REMAP
+	if (irq_remapped(irq)) {
+		struct irq_desc *desc = irq_to_desc(irq);
+		/*
+		 * irq migration in process context
+		 */
+		desc->status |= IRQ_MOVE_PCNTXT;
+		set_irq_chip_and_handler_name(irq, &msi_ir_chip, handle_edge_irq, "edge");
+	} else
+#endif
+		set_irq_chip_and_handler_name(irq, &msi_chip, handle_edge_irq, "edge");
 
 	return 0;
 }
@@ -2859,59 +3358,164 @@ static unsigned int build_irq_for_pci_dev(struct pci_dev *dev)
 
 int arch_setup_msi_irq(struct pci_dev *dev, struct msi_desc *desc)
 {
-	int irq, ret;
-
+	unsigned int irq;
+	int ret;
 	unsigned int irq_want;
 
 	irq_want = build_irq_for_pci_dev(dev) + 0x100;
 
 	irq = create_irq_nr(irq_want);
-
 	if (irq == 0)
 		return -1;
 
+#ifdef CONFIG_INTR_REMAP
+	if (!intr_remapping_enabled)
+		goto no_ir;
+
+	ret = msi_alloc_irte(dev, irq, 1);
+	if (ret < 0)
+		goto error;
+no_ir:
+#endif
 	ret = setup_msi_irq(dev, desc, irq);
 	if (ret < 0) {
 		destroy_irq(irq);
 		return ret;
-        }
-
+	}
 	return 0;
+
+#ifdef CONFIG_INTR_REMAP
+error:
+	destroy_irq(irq);
+	return ret;
+#endif
 }
 
 int arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 {
-        unsigned int irq;
-        int ret, sub_handle;
-        struct msi_desc *desc;
-        unsigned int irq_want;
-
-        irq_want = build_irq_for_pci_dev(dev) + 0x100;
-        sub_handle = 0;
-        list_for_each_entry(desc, &dev->msi_list, list) {
-                irq = create_irq_nr(irq_want--);
-                if (irq == 0)
-                        return -1;
-                ret = setup_msi_irq(dev, desc, irq);
-                if (ret < 0)
-                        goto error;
-                sub_handle++;
-        }
-        return 0;
+	unsigned int irq;
+	int ret, sub_handle;
+	struct msi_desc *desc;
+	unsigned int irq_want;
+
+#ifdef CONFIG_INTR_REMAP
+	struct intel_iommu *iommu = 0;
+	int index = 0;
+#endif
+
+	irq_want = build_irq_for_pci_dev(dev) + 0x100;
+	sub_handle = 0;
+	list_for_each_entry(desc, &dev->msi_list, list) {
+		irq = create_irq_nr(irq_want--);
+		if (irq == 0)
+			return -1;
+#ifdef CONFIG_INTR_REMAP
+		if (!intr_remapping_enabled)
+			goto no_ir;
+
+		if (!sub_handle) {
+			/*
+			 * allocate the consecutive block of IRTE's
+			 * for 'nvec'
+			 */
+			index = msi_alloc_irte(dev, irq, nvec);
+			if (index < 0) {
+				ret = index;
+				goto error;
+			}
+		} else {
+			iommu = map_dev_to_ir(dev);
+			if (!iommu) {
+				ret = -ENOENT;
+				goto error;
+			}
+			/*
+			 * setup the mapping between the irq and the IRTE
+			 * base index, the sub_handle pointing to the
+			 * appropriate interrupt remap table entry.
+			 */
+			set_irte_irq(irq, iommu, index, sub_handle);
+		}
+no_ir:
+#endif
+		ret = setup_msi_irq(dev, desc, irq);
+		if (ret < 0)
+			goto error;
+		sub_handle++;
+	}
+	return 0;
 
 error:
-        destroy_irq(irq);
-        return ret;
+	destroy_irq(irq);
+	return ret;
 }
 
-
 void arch_teardown_msi_irq(unsigned int irq)
 {
 	destroy_irq(irq);
 }
 
-#endif /* CONFIG_PCI_MSI */
+#ifdef CONFIG_DMAR
+#ifdef CONFIG_SMP
+static void dmar_msi_set_affinity(unsigned int irq, cpumask_t mask)
+{
+	struct irq_cfg *cfg;
+	struct msi_msg msg;
+	unsigned int dest;
+	cpumask_t tmp;
+	struct irq_desc *desc;
+
+	cpus_and(tmp, mask, cpu_online_map);
+	if (cpus_empty(tmp))
+		return;
+
+	if (assign_irq_vector(irq, mask))
+		return;
+
+	cfg = irq_cfg(irq);
+	cpus_and(tmp, cfg->domain, mask);
+	dest = cpu_mask_to_apicid(tmp);
+
+	dmar_msi_read(irq, &msg);
+
+	msg.data &= ~MSI_DATA_VECTOR_MASK;
+	msg.data |= MSI_DATA_VECTOR(cfg->vector);
+	msg.address_lo &= ~MSI_ADDR_DEST_ID_MASK;
+	msg.address_lo |= MSI_ADDR_DEST_ID(dest);
+
+	dmar_msi_write(irq, &msg);
+	desc = irq_to_desc(irq);
+	desc->affinity = mask;
+}
+#endif /* CONFIG_SMP */
+
+struct irq_chip dmar_msi_type = {
+	.name = "DMAR_MSI",
+	.unmask = dmar_msi_unmask,
+	.mask = dmar_msi_mask,
+	.ack = ack_apic_edge,
+#ifdef CONFIG_SMP
+	.set_affinity = dmar_msi_set_affinity,
+#endif
+	.retrigger = ioapic_retrigger_irq,
+};
+
+int arch_setup_dmar_msi(unsigned int irq)
+{
+	int ret;
+	struct msi_msg msg;
 
+	ret = msi_compose_msg(NULL, irq, &msg);
+	if (ret < 0)
+		return ret;
+	dmar_msi_write(irq, &msg);
+	set_irq_chip_and_handler_name(irq, &dmar_msi_type, handle_edge_irq,
+		"edge");
+	return 0;
+}
+#endif
+
+#endif /* CONFIG_PCI_MSI */
 /*
  * Hypertransport interrupt support
  */
@@ -2938,6 +3542,7 @@ static void set_ht_irq_affinity(unsigned int irq, cpumask_t mask)
 	struct irq_cfg *cfg;
 	unsigned int dest;
 	cpumask_t tmp;
+	struct irq_desc *desc;
 
 	cpus_and(tmp, mask, cpu_online_map);
 	if (cpus_empty(tmp))
@@ -2951,7 +3556,8 @@ static void set_ht_irq_affinity(unsigned int irq, cpumask_t mask)
 	dest = cpu_mask_to_apicid(tmp);
 
 	target_ht_irq(irq, dest, cfg->vector);
-	irq_to_desc(irq)->affinity = mask;
+	desc = irq_to_desc(irq);
+	desc->affinity = mask;
 }
 #endif
 
@@ -2974,7 +3580,7 @@ int arch_setup_ht_irq(unsigned int irq, struct pci_dev *dev)
 
 	tmp = TARGET_CPUS;
 	err = assign_irq_vector(irq, tmp);
-	if ( !err) {
+	if (!err) {
 		struct ht_irq_msg msg;
 		unsigned dest;
 
@@ -3007,11 +3613,12 @@ int arch_setup_ht_irq(unsigned int irq, struct pci_dev *dev)
 #endif /* CONFIG_HT_IRQ */
 
 /* --------------------------------------------------------------------------
-			ACPI-based IOAPIC Configuration
+                          ACPI-based IOAPIC Configuration
    -------------------------------------------------------------------------- */
 
 #ifdef CONFIG_ACPI
 
+#ifdef CONFIG_X86_32
 int __init io_apic_get_unique_id(int ioapic, int apic_id)
 {
 	union IO_APIC_reg_00 reg_00;
@@ -3086,7 +3693,6 @@ int __init io_apic_get_unique_id(int ioapic, int apic_id)
 	return apic_id;
 }
 
-
 int __init io_apic_get_version(int ioapic)
 {
 	union IO_APIC_reg_01	reg_01;
@@ -3098,9 +3704,9 @@ int __init io_apic_get_version(int ioapic)
 
 	return reg_01.bits.version;
 }
+#endif
 
-
-int __init io_apic_get_redir_entries(int ioapic)
+int __init io_apic_get_redir_entries (int ioapic)
 {
 	union IO_APIC_reg_01	reg_01;
 	unsigned long flags;
@@ -3113,10 +3719,10 @@ int __init io_apic_get_redir_entries(int ioapic)
 }
 
 
-int io_apic_set_pci_routing(int ioapic, int pin, int irq, int triggering, int polarity)
+int io_apic_set_pci_routing (int ioapic, int pin, int irq, int triggering, int polarity)
 {
 	if (!IO_APIC_IRQ(irq)) {
-		printk(KERN_ERR "IOAPIC[%d]: Invalid reference to IRQ 0\n",
+		apic_printk(APIC_QUIET,KERN_ERR "IOAPIC[%d]: Invalid reference to IRQ 0\n",
 			ioapic);
 		return -EINVAL;
 	}
@@ -3132,6 +3738,7 @@ int io_apic_set_pci_routing(int ioapic, int pin, int irq, int triggering, int po
 	return 0;
 }
 
+
 int acpi_get_override_irq(int bus_irq, int *trigger, int *polarity)
 {
 	int i;
@@ -3163,7 +3770,6 @@ void __init setup_ioapic_dest(void)
 {
 	int pin, ioapic, irq, irq_entry;
 	struct irq_cfg *cfg;
-	struct irq_desc *desc;
 
 	if (skip_ioapic_setup == 1)
 		return;
@@ -3184,43 +3790,124 @@ void __init setup_ioapic_dest(void)
 				setup_IO_APIC_irq(ioapic, pin, irq,
 						  irq_trigger(irq_entry),
 						  irq_polarity(irq_entry));
-			else {
-				desc = irq_to_desc(irq);
+#ifdef CONFIG_INTR_REMAP
+			else if (intr_remapping_enabled)
+				set_ir_ioapic_affinity_irq(irq, TARGET_CPUS);
+#endif
+			else
 				set_ioapic_affinity_irq(irq, TARGET_CPUS);
-			}
 		}
 
 	}
 }
 #endif
 
+#ifdef CONFIG_X86_64
+#define IOAPIC_RESOURCE_NAME_SIZE 11
+
+static struct resource *ioapic_resources;
+
+static struct resource * __init ioapic_setup_resources(void)
+{
+	unsigned long n;
+	struct resource *res;
+	char *mem;
+	int i;
+
+	if (nr_ioapics <= 0)
+		return NULL;
+
+	n = IOAPIC_RESOURCE_NAME_SIZE + sizeof(struct resource);
+	n *= nr_ioapics;
+
+	mem = alloc_bootmem(n);
+	res = (void *)mem;
+
+	if (mem != NULL) {
+		mem += sizeof(struct resource) * nr_ioapics;
+
+		for (i = 0; i < nr_ioapics; i++) {
+			res[i].name = mem;
+			res[i].flags = IORESOURCE_MEM | IORESOURCE_BUSY;
+			sprintf(mem,  "IOAPIC %u", i);
+			mem += IOAPIC_RESOURCE_NAME_SIZE;
+		}
+	}
+
+	ioapic_resources = res;
+
+	return res;
+}
+#endif
+
 void __init ioapic_init_mappings(void)
 {
 	unsigned long ioapic_phys, idx = FIX_IO_APIC_BASE_0;
 	int i;
+#ifdef CONFIG_X86_64
+	struct resource *ioapic_res;
 
+	ioapic_res = ioapic_setup_resources();
+#endif
 	for (i = 0; i < nr_ioapics; i++) {
 		if (smp_found_config) {
 			ioapic_phys = mp_ioapics[i].mp_apicaddr;
-			if (!ioapic_phys) {
-				printk(KERN_ERR
-				       "WARNING: bogus zero IO-APIC "
-				       "address found in MPTABLE, "
-				       "disabling IO/APIC support!\n");
-				smp_found_config = 0;
-				skip_ioapic_setup = 1;
-				goto fake_ioapic_page;
-			}
+#ifdef CONFIG_X86_32
+                        if (!ioapic_phys) {
+                                printk(KERN_ERR
+                                       "WARNING: bogus zero IO-APIC "
+                                       "address found in MPTABLE, "
+                                       "disabling IO/APIC support!\n");
+                                smp_found_config = 0;
+                                skip_ioapic_setup = 1;
+                                goto fake_ioapic_page;
+                        }
+#endif
 		} else {
+#ifdef CONFIG_X86_32
 fake_ioapic_page:
+#endif
 			ioapic_phys = (unsigned long)
-				      alloc_bootmem_pages(PAGE_SIZE);
+				alloc_bootmem_pages(PAGE_SIZE);
 			ioapic_phys = __pa(ioapic_phys);
 		}
 		set_fixmap_nocache(idx, ioapic_phys);
-		printk(KERN_DEBUG "mapped IOAPIC to %08lx (%08lx)\n",
-		       __fix_to_virt(idx), ioapic_phys);
+		apic_printk(APIC_VERBOSE,
+			    "mapped IOAPIC to %08lx (%08lx)\n",
+			    __fix_to_virt(idx), ioapic_phys);
 		idx++;
+
+#ifdef CONFIG_X86_64
+		if (ioapic_res != NULL) {
+			ioapic_res->start = ioapic_phys;
+			ioapic_res->end = ioapic_phys + (4 * 1024) - 1;
+			ioapic_res++;
+		}
+#endif
 	}
 }
 
+#ifdef CONFIG_X86_64
+static int __init ioapic_insert_resources(void)
+{
+	int i;
+	struct resource *r = ioapic_resources;
+
+	if (!r) {
+		printk(KERN_ERR
+		       "IO APIC resources could be not be allocated.\n");
+		return -1;
+	}
+
+	for (i = 0; i < nr_ioapics; i++) {
+		insert_resource(&iomem_resource, r);
+		r++;
+	}
+
+	return 0;
+}
+
+/* Insert the IO APIC resources after PCI initialization has occured to handle
+ * IO APICS that are mapped in on a BAR in PCI space. */
+late_initcall(ioapic_insert_resources);
+#endif

commit e955b5398b660a204854bdff059d050b44090879
Author: Ingo Molnar <mingo@elte.hu>
Date:   Tue Aug 19 20:50:37 2008 -0700

    sparseirq: fix lockdep
    
    -tip testing found this lockdep splat:
    
    [    0.000000] Initializing CPU#0
    [    0.000000] found new irq_desc for irq 0
    [    0.000000] INFO: trying to register non-static key.
    [    0.000000] the code is fine but needs lockdep annotation.
    [    0.000000] turning off the locking correctness validator.
    [    0.000000] Pid: 0, comm: swapper Not tainted 2.6.27-rc3-tip-00191-g98ccb89-dirty #1
    [    0.000000]  [<c0153c22>] register_lock_class+0x3d2/0x400
    [    0.000000]  [<c0104d87>] ? mcount_call+0x5/0xa
    [    0.000000]  [<c0154f3a>] __lock_acquire+0x22a/0x5d0
    [    0.000000]  [<c0104d87>] ? mcount_call+0x5/0xa
    [    0.000000]  [<c0155351>] lock_acquire+0x71/0xa0
    [    0.000000]  [<c016d61f>] ? set_irq_chip+0x3f/0x90
    [    0.000000]  [<c070f148>] _spin_lock_irqsave+0x58/0x90
    [    0.000000]  [<c016d61f>] ? set_irq_chip+0x3f/0x90
    [    0.000000]  [<c016d61f>] set_irq_chip+0x3f/0x90
    [    0.000000]  [<c016d7e0>] ? handle_level_irq+0x0/0xe0
    [    0.000000]  [<c016da1a>] set_irq_chip_and_handler_name+0x1a/0x40
    [    0.000000]  [<c0a396c1>] init_ISA_irqs+0x51/0xa0
    [    0.000000]  [<c0a4a365>] pre_intr_init_hook+0x25/0x30
    [    0.000000]  [<c0a39723>] native_init_IRQ+0x13/0x370
    [    0.000000]  [<c015569c>] ? lock_release+0xcc/0x1d0
    [    0.000000]  [<c0104d87>] ? mcount_call+0x5/0xa
    [    0.000000]  [<c070dc22>] ? __mutex_unlock_slowpath+0x92/0x110
    [    0.000000]  [<c070dcad>] ? mutex_unlock+0xd/0x10
    [    0.000000]  [<c0135f62>] ? cpu_maps_update_done+0x12/0x20
    [    0.000000]  [<c06c6743>] ? register_cpu_notifier+0x23/0x30
    [    0.000000]  [<c011e8ae>] init_IRQ+0xe/0x10
    [    0.000000]  [<c0a357a5>] start_kernel+0x1c5/0x340
    [    0.000000]  [<c0a35280>] ? unknown_bootoption+0x0/0x210
    [    0.000000]  [<c0a3506b>] i386_start_kernel+0x6b/0x80
    [    0.000000]  =======================
    [    0.000000] found new irq_desc for irq 1
    [    0.000000] found new irq_desc for irq 2
    [    0.000000] found new irq_desc for irq 3
    
    this:
    
     static void init_one_irq_desc(struct irq_desc *desc)
     {
             memcpy(desc, &irq_desc_init, sizeof(struct irq_desc));
     #ifdef CONFIG_TRACE_IRQFLAGS
             lockdep_set_class(&desc->lock, &irq_desc_lock_class);
     #endif
     }
    
    should be unconditional.
    
    Signed-off-by: Ingo Molnar <mingo@elte.hu>

diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index 6d174390f3a0..24c83a3cee4d 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -18,13 +18,10 @@
 
 #include "internals.h"
 
-#ifdef CONFIG_TRACE_IRQFLAGS
-
 /*
  * lockdep: we want to handle all irq_desc locks as a single lock-class:
  */
 static struct lock_class_key irq_desc_lock_class;
-#endif
 
 /**
  * handle_bad_irq - handle spurious and unhandled irqs
@@ -75,9 +72,7 @@ static struct irq_desc irq_desc_init = {
 static void init_one_irq_desc(struct irq_desc *desc)
 {
 	memcpy(desc, &irq_desc_init, sizeof(struct irq_desc));
-#ifdef CONFIG_TRACE_IRQFLAGS
 	lockdep_set_class(&desc->lock, &irq_desc_lock_class);
-#endif
 }
 
 extern int after_bootmem;

commit 3bf52a4df3ccd25d4154797977c556a2a8b3bc1e
Author: Ingo Molnar <mingo@elte.hu>
Date:   Tue Aug 19 20:50:29 2008 -0700

    irq: sparse irqs, fix IRQ auto-probe crash
    
    fix:
    
    [   10.631533] calling  yenta_socket_init+0x0/0x20
    [   10.631533] Yenta: CardBus bridge found at 0000:15:00.0 [17aa:2012]
    [   10.631533] Yenta: Using INTVAL to route CSC interrupts to PCI
    [   10.631533] Yenta: Routing CardBus interrupts to PCI
    [   10.631533] Yenta TI: socket 0000:15:00.0, mfunc 0x01d01002, devctl 0x64
    [   10.731599] BUG: unable to handle kernel NULL pointer dereference at 00000040
    [   10.731838] IP: [<c0c95b5f>] _spin_lock_irq+0xf/0x20
    [   10.732221] *pde = 00000000
    [   10.732741] Oops: 0002 [#1] SMP
    [   10.733453]
    [   10.734253] Pid: 1, comm: swapper Tainted: G        W (2.6.27-rc3-tip-00173-gd7eaa4f-dirty #1)
    [   10.735188] EIP: 0060:[<c0c95b5f>] EFLAGS: 00010002 CPU: 0
    [   10.735523] EIP is at _spin_lock_irq+0xf/0x20
    [   10.735523] EAX: 00000040 EBX: 00000000 ECX: f6e04c90 EDX: 00000100
    [   10.735523] ESI: 000000df EDI: f6e04c90 EBP: f7867df0 ESP: f7867df0
    [   10.735523]  DS: 007b ES: 007b FS: 00d8 GS: 0000 SS: 0068
    [   10.735523] Process swapper (pid: 1, ti=f7867000 task=f7870000 task.ti=f7867000)
    [   10.735523] Stack: f7867e04 c0155fbd 00000000 00000000 f6e04c90 f7867e5c c0c6e319 c0f6a074
    [   10.735523]        f6e04c90 000017aa 00002012 c112b648 f791f240 c112b5e0 f7867e44 c010440b
    [   10.735523]        f791f240 f791f29c c112b8ec f791f240 00000000 f7867e5c c048f893 03c0b648
    [   10.735523] Call Trace:
    [   10.735523]  [<c0155fbd>] ? probe_irq_on+0x3d/0x140
    [   10.735523]  [<c0c6e319>] ? yenta_probe+0x529/0x640
    [   10.735523]  [<c010440b>] ? mcount_call+0x5/0xa
    [   10.735523]  [<c048f893>] ? pci_match_device+0xa3/0xb0
    [   10.735523]  [<c048fc1e>] ? pci_device_probe+0x5e/0x80
    [   10.735523]  [<c0515423>] ? driver_probe_device+0x83/0x180
    [   10.735523]  [<c0515594>] ? __driver_attach+0x74/0x80
    [   10.735523]  [<c0514b69>] ? bus_for_each_dev+0x49/0x70
    [   10.735523]  [<c051528e>] ? driver_attach+0x1e/0x20
    [   10.735523]  [<c0515520>] ? __driver_attach+0x0/0x80
    [   10.735523]  [<c05150d3>] ? bus_add_driver+0x1a3/0x220
    [   10.735523]  [<c048fb60>] ? pci_device_remove+0x0/0x40
    [   10.735523]  [<c05157f4>] ? driver_register+0x54/0x130
    [   10.735523]  [<c048fe2f>] ? __pci_register_driver+0x4f/0x90
    [   10.735523]  [<c11e9419>] ? yenta_socket_init+0x19/0x20
    [   10.735523]  [<c0101125>] ? do_one_initcall+0x35/0x160
    [   10.735523]  [<c11e9400>] ? yenta_socket_init+0x0/0x20
    [   10.735523]  [<c01391a6>] ? __queue_work+0x36/0x50
    [   10.735523]  [<c013922d>] ? queue_work_on+0x3d/0x50
    [   10.735523]  [<c11a2758>] ? kernel_init+0x148/0x210
    [   10.735523]  [<c11a2610>] ? kernel_init+0x0/0x210
    [   10.735523]  [<c01043f3>] ? kernel_thread_helper+0x7/0x10
    [   10.735523]  =======================
    [   10.735523] Code: 10 38 f2 74 06 f3 90 8a 10 eb f6 5d 89 c8 c3 8d b6 00 00 00 00 8d bc 27 00 00 00 00 55 89 e5 e8 a4 e8 46 ff fa ba 00 01 00 00 90 <66> 0f c1 10 38 f2 74 06 f3 90 8a 10 eb f6 5d c3 90 55 89 e5 53
    
    as auto-probing wants to iterate over existing irqs.
    
    Signed-off-by: Ingo Molnar <mingo@elte.hu>

diff --git a/kernel/irq/autoprobe.c b/kernel/irq/autoprobe.c
index c45ab718cf07..b3a5549ea81e 100644
--- a/kernel/irq/autoprobe.c
+++ b/kernel/irq/autoprobe.c
@@ -40,6 +40,8 @@ unsigned long probe_irq_on(void)
 	 */
 	for (i = nr_irqs-1; i > 0; i--) {
 		desc = irq_to_desc(i);
+		if (!desc)
+			continue;
 
 		spin_lock_irq(&desc->lock);
 		if (!desc->action && !(desc->status & IRQ_NOPROBE)) {
@@ -70,6 +72,8 @@ unsigned long probe_irq_on(void)
 	 */
 	for (i = nr_irqs-1; i > 0; i--) {
 		desc = irq_to_desc(i);
+		if (!desc)
+			continue;
 
 		spin_lock_irq(&desc->lock);
 		if (!desc->action && !(desc->status & IRQ_NOPROBE)) {
@@ -93,6 +97,8 @@ unsigned long probe_irq_on(void)
 		unsigned int status;
 
 		desc = irq_to_desc(i);
+		if (!desc)
+			continue;
 		spin_lock_irq(&desc->lock);
 		status = desc->status;
 
@@ -134,6 +140,8 @@ unsigned int probe_irq_mask(unsigned long val)
 		struct irq_desc *desc = irq_to_desc(i);
 		unsigned int status;
 
+		if (!desc)
+			continue;
 		spin_lock_irq(&desc->lock);
 		status = desc->status;
 
@@ -177,6 +185,8 @@ int probe_irq_off(unsigned long val)
 		struct irq_desc *desc = irq_to_desc(i);
 		unsigned int status;
 
+		if (!desc)
+			continue;
 		spin_lock_irq(&desc->lock);
 		status = desc->status;
 

commit a84488c213a8cfc29200344a6fb6357d48c8ed85
Author: Ingo Molnar <mingo@elte.hu>
Date:   Tue Aug 19 20:50:31 2008 -0700

    irq: sparse irqs, fix #3
    
    fix non-APIC UP build:
    
     arch/x86/kernel/built-in.o: In function `setup_arch':
     : undefined reference to `pin_map_size'
     arch/x86/kernel/built-in.o: In function `setup_arch':
     : undefined reference to `first_free_entry'
    
    Signed-off-by: Ingo Molnar <mingo@elte.hu>

diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 558ec26b08e2..02e3a6697977 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -1074,8 +1074,10 @@ void __init setup_arch(char **cmdline_p)
 		nr_irqs = 32 * nr_cpu_ids + 224;
 	init_cpu_to_node();
 #endif
+#ifdef CONFIG_X86_IO_APIC
 	pin_map_size = nr_irqs * 2;
 	first_free_entry = nr_irqs;
+#endif
 
 	init_apic_mappings();
 	ioapic_init_mappings();

commit fa42d10dd5e1ff373061c0526f272106512301f9
Author: Ingo Molnar <mingo@elte.hu>
Date:   Tue Aug 19 20:50:30 2008 -0700

    irq: sparse irqs, export nr_irqs
    
    fix:
    
      Building modules, stage 2.
      MODPOST 458 modules
      ERROR: "nr_irqs" [drivers/serial/8250.ko] undefined!
    
    Signed-off-by: Ingo Molnar <mingo@elte.hu>

diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index e94eeca09ea9..6ce3bcc2b8f7 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -48,6 +48,7 @@ handle_bad_irq(unsigned int irq, struct irq_desc *desc)
  * Controller mappings for all interrupt sources:
  */
 int nr_irqs = NR_IRQS;
+EXPORT_SYMBOL_GPL(nr_irqs);
 
 #ifdef CONFIG_HAVE_DYN_ARRAY
 static struct irq_desc irq_desc_init __initdata = {

commit 5fef06e8c8c52aa7170dbbb068aa996d83738d38
Merge: 0c5d1eb77a8b 278429cff880
Author: Ingo Molnar <mingo@elte.hu>
Date:   Thu Oct 16 16:51:32 2008 +0200

    Merge branch 'linus' into genirq

commit b2aaf8f74cdc84a9182f6cabf198b7763bcb9d40
Merge: 4f962d4d6592 278429cff880
Author: Ingo Molnar <mingo@elte.hu>
Date:   Wed Oct 15 13:46:29 2008 +0200

    Merge branch 'linus' into stackprotector
    
    Conflicts:
            arch/x86/kernel/Makefile
            include/asm-x86/pda.h

diff --cc arch/x86/kernel/Makefile
index d001739d8b06,0d41f0343dc0..50632e16d01c
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@@ -13,21 -20,21 +20,22 @@@ endi
  nostackp := $(call cc-option, -fno-stack-protector)
  CFLAGS_vsyscall_64.o	:= $(PROFILING) -g0 $(nostackp)
  CFLAGS_hpet.o		:= $(nostackp)
- CFLAGS_tsc_64.o		:= $(nostackp)
+ CFLAGS_tsc.o		:= $(nostackp)
 +CFLAGS_paravirt.o	:= $(nostackp)
  
  obj-y			:= process_$(BITS).o signal_$(BITS).o entry_$(BITS).o
- obj-y			+= traps_$(BITS).o irq_$(BITS).o
+ obj-y			+= traps.o irq_$(BITS).o dumpstack_$(BITS).o
  obj-y			+= time_$(BITS).o ioport.o ldt.o
- obj-y			+= setup_$(BITS).o i8259_$(BITS).o setup.o
+ obj-y			+= setup.o i8259.o irqinit_$(BITS).o setup_percpu.o
+ obj-$(CONFIG_X86_VISWS)	+= visws_quirks.o
+ obj-$(CONFIG_X86_32)	+= probe_roms_32.o
  obj-$(CONFIG_X86_32)	+= sys_i386_32.o i386_ksyms_32.o
  obj-$(CONFIG_X86_64)	+= sys_x86_64.o x8664_ksyms_64.o
- obj-$(CONFIG_X86_64)	+= syscall_64.o vsyscall_64.o setup64.o
- obj-y			+= bootflag.o e820_$(BITS).o
+ obj-$(CONFIG_X86_64)	+= syscall_64.o vsyscall_64.o
+ obj-y			+= bootflag.o e820.o
  obj-y			+= pci-dma.o quirks.o i8237.o topology.o kdebugfs.o
  obj-y			+= alternative.o i8253.o pci-nommu.o
- obj-$(CONFIG_X86_64)	+= bugs_64.o
- obj-y			+= tsc_$(BITS).o io_delay.o rtc.o
+ obj-y			+= tsc.o io_delay.o rtc.o
  
  obj-$(CONFIG_X86_TRAMPOLINE)	+= trampoline.o
  obj-y				+= process.o
diff --cc arch/x86/kernel/process_64.c
index f73cfbc2c281,cd8c0ed02b7e..749d5f888d4d
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@@ -147,27 -102,13 +103,24 @@@ static inline void play_dead(void
  void cpu_idle(void)
  {
  	current_thread_info()->status |= TS_POLLING;
 +
 +	/*
 +	 * If we're the non-boot CPU, nothing set the PDA stack
 +	 * canary up for us - and if we are the boot CPU we have
 +	 * a 0 stack canary. This is a good place for updating
 +	 * it, as we wont ever return from this function (so the
 +	 * invalid canaries already on the stack wont ever
 +	 * trigger):
 +	 */
 +	boot_init_stack_canary();
 +
  	/* endless idle loop with no priority at all */
  	while (1) {
- 		tick_nohz_stop_sched_tick();
+ 		tick_nohz_stop_sched_tick(1);
  		while (!need_resched()) {
- 			void (*idle)(void);
  
  			rmb();
- 			idle = pm_idle;
- 			if (!idle)
- 				idle = default_idle;
+ 
  			if (cpu_is_offline(smp_processor_id()))
  				play_dead();
  			/*
@@@ -648,11 -634,13 +646,12 @@@ __switch_to(struct task_struct *prev_p
  	 */
  	prev->usersp = read_pda(oldrsp);
  	write_pda(oldrsp, next->usersp);
- 	write_pda(pcurrent, next_p); 
+ 	write_pda(pcurrent, next_p);
  
  	write_pda(kernelstack,
- 	(unsigned long)task_stack_page(next_p) + THREAD_SIZE - PDA_STACKOFFSET);
+ 		  (unsigned long)task_stack_page(next_p) +
+ 		  THREAD_SIZE - PDA_STACKOFFSET);
  #ifdef CONFIG_CC_STACKPROTECTOR
 -	write_pda(stack_canary, next_p->stack_canary);
  	/*
  	 * Build time only check to make sure the stack_canary is at
  	 * offset 40 in the pda; this is a gcc ABI requirement
diff --cc include/asm-x86/pda.h
index a5ff5bb76299,80860afffbdb..45fd2aee8d6a
--- a/include/asm-x86/pda.h
+++ b/include/asm-x86/pda.h
@@@ -19,7 -19,11 +19,9 @@@ struct x8664_pda 
  	unsigned long stack_canary;	/* 40 stack canary value */
  					/* gcc-ABI: this canary MUST be at
  					   offset 40!!! */
 -#endif
  	char *irqstackptr;
+ 	short nodenumber;		/* number of current node (32k max) */
+ 	short in_bootmem;		/* pda lives in bootmem */
  	unsigned int __softirq_pending;
  	unsigned int __nmi_count;	/* number of NMI on this CPUs */
  	short mmu_state;
@@@ -131,5 -134,4 +132,6 @@@ do {									
  
  #define PDA_STACKOFFSET (5*8)
  
 +#define refresh_stack_canary() write_pda(stack_canary, current->stack_canary)
- #endif
++
+ #endif /* ASM_X86__PDA_H */
diff --cc include/linux/sched.h
index f0132f9ef4dd,c226c7b82946..1a7e8461db5a
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@@ -1968,21 -1965,15 +1964,28 @@@ static inline unsigned long *end_of_sta
  
  #endif
  
+ static inline int object_is_on_stack(void *obj)
+ {
+ 	void *stack = task_stack_page(current);
+ 
+ 	return (obj >= stack) && (obj < (stack + THREAD_SIZE));
+ }
+ 
  extern void thread_info_cache_init(void);
  
 +#ifdef CONFIG_DEBUG_STACK_USAGE
 +static inline unsigned long stack_not_used(struct task_struct *p)
 +{
 +	unsigned long *n = end_of_stack(p);
 +
 +	do { 	/* Skip over canary */
 +		n++;
 +	} while (!*n);
 +
 +	return (unsigned long)n - (unsigned long)end_of_stack(p);
 +}
 +#endif
 +
  /* set thread flags in other task's structures
   * - see asm/thread_info.h for TIF_xxxx flags available
   */