21 files changed, 194 insertions, 320 deletions

diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index a415b1f44365..7c439fe4941b 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -593,7 +593,7 @@ void __init acpi_set_irq_model_ioapic(void)
 #ifdef CONFIG_ACPI_HOTPLUG_CPU
 #include <acpi/processor.h>
 
-static void __cpuinitdata acpi_map_cpu2node(acpi_handle handle, int cpu, int physid)
+static void __cpuinit acpi_map_cpu2node(acpi_handle handle, int cpu, int physid)
 {
 #ifdef CONFIG_ACPI_NUMA
 	int nid;
diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c
index 103b6ab368d3..146a49c763a4 100644
--- a/arch/x86/kernel/acpi/sleep.c
+++ b/arch/x86/kernel/acpi/sleep.c
@@ -24,6 +24,10 @@ unsigned long acpi_realmode_flags;
 static char temp_stack[4096];
 #endif
 
+asmlinkage void acpi_enter_s3(void)
+{
+	acpi_enter_sleep_state(3, wake_sleep_flags);
+}
 /**
  * acpi_suspend_lowlevel - save kernel state
  *
diff --git a/arch/x86/kernel/acpi/sleep.h b/arch/x86/kernel/acpi/sleep.h
index 416d4be13fef..d68677a2a010 100644
--- a/arch/x86/kernel/acpi/sleep.h
+++ b/arch/x86/kernel/acpi/sleep.h
@@ -3,12 +3,16 @@
  */
 
 #include <asm/trampoline.h>
+#include <linux/linkage.h>
 
 extern unsigned long saved_video_mode;
 extern long saved_magic;
 
 extern int wakeup_pmode_return;
 
+extern u8 wake_sleep_flags;
+extern asmlinkage void acpi_enter_s3(void);
+
 extern unsigned long acpi_copy_wakeup_routine(unsigned long);
 extern void wakeup_long64(void);
 
diff --git a/arch/x86/kernel/acpi/wakeup_32.S b/arch/x86/kernel/acpi/wakeup_32.S
index 13ab720573e3..72610839f03b 100644
--- a/arch/x86/kernel/acpi/wakeup_32.S
+++ b/arch/x86/kernel/acpi/wakeup_32.S
@@ -74,9 +74,7 @@ restore_registers:
 ENTRY(do_suspend_lowlevel)
 	call	save_processor_state
 	call	save_registers
-	pushl	$3
-	call	acpi_enter_sleep_state
-	addl	$4, %esp
+	call	acpi_enter_s3
 
 #	In case of S3 failure, we'll emerge here.  Jump
 # 	to ret_point to recover
diff --git a/arch/x86/kernel/acpi/wakeup_64.S b/arch/x86/kernel/acpi/wakeup_64.S
index 8ea5164cbd04..014d1d28c397 100644
--- a/arch/x86/kernel/acpi/wakeup_64.S
+++ b/arch/x86/kernel/acpi/wakeup_64.S
@@ -71,9 +71,7 @@ ENTRY(do_suspend_lowlevel)
 	movq	%rsi, saved_rsi
 
 	addq	$8, %rsp
-	movl	$3, %edi
-	xorl	%eax, %eax
-	call	acpi_enter_sleep_state
+	call	acpi_enter_s3
 	/* in case something went wrong, restore the machine status and go on */
 	jmp	resume_point
 
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 11544d8f1e97..3722179a49db 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -35,6 +35,7 @@
 #include <linux/smp.h>
 #include <linux/mm.h>
 
+#include <asm/irq_remapping.h>
 #include <asm/perf_event.h>
 #include <asm/x86_init.h>
 #include <asm/pgalloc.h>
@@ -1441,8 +1442,8 @@ void __init bsp_end_local_APIC_setup(void)
 	 * Now that local APIC setup is completed for BP, configure the fault
 	 * handling for interrupt remapping.
 	 */
-	if (intr_remapping_enabled)
-		enable_drhd_fault_handling();
+	if (irq_remapping_enabled)
+		irq_remap_enable_fault_handling();
 
 }
 
@@ -1517,7 +1518,7 @@ void enable_x2apic(void)
 int __init enable_IR(void)
 {
 #ifdef CONFIG_IRQ_REMAP
-	if (!intr_remapping_supported()) {
+	if (!irq_remapping_supported()) {
 		pr_debug("intr-remapping not supported\n");
 		return -1;
 	}
@@ -1528,7 +1529,7 @@ int __init enable_IR(void)
 		return -1;
 	}
 
-	return enable_intr_remapping();
+	return irq_remapping_enable();
 #endif
 	return -1;
 }
@@ -1537,10 +1538,13 @@ void __init enable_IR_x2apic(void)
 {
 	unsigned long flags;
 	int ret, x2apic_enabled = 0;
-	int dmar_table_init_ret;
+	int hardware_init_ret;
 
-	dmar_table_init_ret = dmar_table_init();
-	if (dmar_table_init_ret && !x2apic_supported())
+	/* Make sure irq_remap_ops are initialized */
+	setup_irq_remapping_ops();
+
+	hardware_init_ret = irq_remapping_prepare();
+	if (hardware_init_ret && !x2apic_supported())
 		return;
 
 	ret = save_ioapic_entries();
@@ -1556,7 +1560,7 @@ void __init enable_IR_x2apic(void)
 	if (x2apic_preenabled && nox2apic)
 		disable_x2apic();
 
-	if (dmar_table_init_ret)
+	if (hardware_init_ret)
 		ret = -1;
 	else
 		ret = enable_IR();
@@ -1637,9 +1641,11 @@ static int __init apic_verify(void)
 	mp_lapic_addr = APIC_DEFAULT_PHYS_BASE;
 
 	/* The BIOS may have set up the APIC at some other address */
-	rdmsr(MSR_IA32_APICBASE, l, h);
-	if (l & MSR_IA32_APICBASE_ENABLE)
-		mp_lapic_addr = l & MSR_IA32_APICBASE_BASE;
+	if (boot_cpu_data.x86 >= 6) {
+		rdmsr(MSR_IA32_APICBASE, l, h);
+		if (l & MSR_IA32_APICBASE_ENABLE)
+			mp_lapic_addr = l & MSR_IA32_APICBASE_BASE;
+	}
 
 	pr_info("Found and enabled local APIC!\n");
 	return 0;
@@ -1657,13 +1663,15 @@ int __init apic_force_enable(unsigned long addr)
 	 * MSR. This can only be done in software for Intel P6 or later
 	 * and AMD K7 (Model > 1) or later.
 	 */
-	rdmsr(MSR_IA32_APICBASE, l, h);
-	if (!(l & MSR_IA32_APICBASE_ENABLE)) {
-		pr_info("Local APIC disabled by BIOS -- reenabling.\n");
-		l &= ~MSR_IA32_APICBASE_BASE;
-		l |= MSR_IA32_APICBASE_ENABLE | addr;
-		wrmsr(MSR_IA32_APICBASE, l, h);
-		enabled_via_apicbase = 1;
+	if (boot_cpu_data.x86 >= 6) {
+		rdmsr(MSR_IA32_APICBASE, l, h);
+		if (!(l & MSR_IA32_APICBASE_ENABLE)) {
+			pr_info("Local APIC disabled by BIOS -- reenabling.\n");
+			l &= ~MSR_IA32_APICBASE_BASE;
+			l |= MSR_IA32_APICBASE_ENABLE | addr;
+			wrmsr(MSR_IA32_APICBASE, l, h);
+			enabled_via_apicbase = 1;
+		}
 	}
 	return apic_verify();
 }
@@ -2172,8 +2180,8 @@ static int lapic_suspend(void)
 	local_irq_save(flags);
 	disable_local_APIC();
 
-	if (intr_remapping_enabled)
-		disable_intr_remapping();
+	if (irq_remapping_enabled)
+		irq_remapping_disable();
 
 	local_irq_restore(flags);
 	return 0;
@@ -2189,7 +2197,7 @@ static void lapic_resume(void)
 		return;
 
 	local_irq_save(flags);
-	if (intr_remapping_enabled) {
+	if (irq_remapping_enabled) {
 		/*
 		 * IO-APIC and PIC have their own resume routines.
 		 * We just mask them here to make sure the interrupt
@@ -2209,10 +2217,12 @@ static void lapic_resume(void)
 		 * FIXME! This will be wrong if we ever support suspend on
 		 * SMP! We'll need to do this as part of the CPU restore!
 		 */
-		rdmsr(MSR_IA32_APICBASE, l, h);
-		l &= ~MSR_IA32_APICBASE_BASE;
-		l |= MSR_IA32_APICBASE_ENABLE | mp_lapic_addr;
-		wrmsr(MSR_IA32_APICBASE, l, h);
+		if (boot_cpu_data.x86 >= 6) {
+			rdmsr(MSR_IA32_APICBASE, l, h);
+			l &= ~MSR_IA32_APICBASE_BASE;
+			l |= MSR_IA32_APICBASE_ENABLE | mp_lapic_addr;
+			wrmsr(MSR_IA32_APICBASE, l, h);
+		}
 	}
 
 	maxlvt = lapic_get_maxlvt();
@@ -2239,8 +2249,8 @@ static void lapic_resume(void)
 	apic_write(APIC_ESR, 0);
 	apic_read(APIC_ESR);
 
-	if (intr_remapping_enabled)
-		reenable_intr_remapping(x2apic_mode);
+	if (irq_remapping_enabled)
+		irq_remapping_reenable(x2apic_mode);
 
 	local_irq_restore(flags);
 }
diff --git a/arch/x86/kernel/apic/apic_numachip.c b/arch/x86/kernel/apic/apic_numachip.c
index 899803e03214..23e75422e013 100644
--- a/arch/x86/kernel/apic/apic_numachip.c
+++ b/arch/x86/kernel/apic/apic_numachip.c
@@ -207,8 +207,11 @@ static void __init map_csrs(void)
 
 static void fixup_cpu_id(struct cpuinfo_x86 *c, int node)
 {
-	c->phys_proc_id = node;
-	per_cpu(cpu_llc_id, smp_processor_id()) = node;
+
+	if (c->phys_proc_id != node) {
+		c->phys_proc_id = node;
+		per_cpu(cpu_llc_id, smp_processor_id()) = node;
+	}
 }
 
 static int __init numachip_system_init(void)
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index e88300d8e80a..ef0648cd7084 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -86,6 +86,22 @@ void __init set_io_apic_ops(const struct io_apic_ops *ops)
 	io_apic_ops = *ops;
 }
 
+#ifdef CONFIG_IRQ_REMAP
+static void irq_remap_modify_chip_defaults(struct irq_chip *chip);
+static inline bool irq_remapped(struct irq_cfg *cfg)
+{
+	return cfg->irq_2_iommu.iommu != NULL;
+}
+#else
+static inline bool irq_remapped(struct irq_cfg *cfg)
+{
+	return false;
+}
+static inline void irq_remap_modify_chip_defaults(struct irq_chip *chip)
+{
+}
+#endif
+
 /*
  *      Is the SiS APIC rmw bug present ?
  *      -1 = don't know, 0 = no, 1 = yes
@@ -1361,77 +1377,13 @@ static void ioapic_register_intr(unsigned int irq, struct irq_cfg *cfg,
 				      fasteoi ? "fasteoi" : "edge");
 }
 
-
-static int setup_ir_ioapic_entry(int irq,
-			      struct IR_IO_APIC_route_entry *entry,
-			      unsigned int destination, int vector,
-			      struct io_apic_irq_attr *attr)
-{
-	int index;
-	struct irte irte;
-	int ioapic_id = mpc_ioapic_id(attr->ioapic);
-	struct intel_iommu *iommu = map_ioapic_to_ir(ioapic_id);
-
-	if (!iommu) {
-		pr_warn("No mapping iommu for ioapic %d\n", ioapic_id);
-		return -ENODEV;
-	}
-
-	index = alloc_irte(iommu, irq, 1);
-	if (index < 0) {
-		pr_warn("Failed to allocate IRTE for ioapic %d\n", ioapic_id);
-		return -ENOMEM;
-	}
-
-	prepare_irte(&irte, vector, destination);
-
-	/* Set source-id of interrupt request */
-	set_ioapic_sid(&irte, ioapic_id);
-
-	modify_irte(irq, &irte);
-
-	apic_printk(APIC_VERBOSE, KERN_DEBUG "IOAPIC[%d]: "
-		"Set IRTE entry (P:%d FPD:%d Dst_Mode:%d "
-		"Redir_hint:%d Trig_Mode:%d Dlvry_Mode:%X "
-		"Avail:%X Vector:%02X Dest:%08X "
-		"SID:%04X SQ:%X SVT:%X)\n",
-		attr->ioapic, irte.present, irte.fpd, irte.dst_mode,
-		irte.redir_hint, irte.trigger_mode, irte.dlvry_mode,
-		irte.avail, irte.vector, irte.dest_id,
-		irte.sid, irte.sq, irte.svt);
-
-	memset(entry, 0, sizeof(*entry));
-
-	entry->index2	= (index >> 15) & 0x1;
-	entry->zero	= 0;
-	entry->format	= 1;
-	entry->index	= (index & 0x7fff);
-	/*
-	 * IO-APIC RTE will be configured with virtual vector.
-	 * irq handler will do the explicit EOI to the io-apic.
-	 */
-	entry->vector	= attr->ioapic_pin;
-	entry->mask	= 0;			/* enable IRQ */
-	entry->trigger	= attr->trigger;
-	entry->polarity	= attr->polarity;
-
-	/* Mask level triggered irqs.
-	 * Use IRQ_DELAYED_DISABLE for edge triggered irqs.
-	 */
-	if (attr->trigger)
-		entry->mask = 1;
-
-	return 0;
-}
-
 static int setup_ioapic_entry(int irq, struct IO_APIC_route_entry *entry,
 			       unsigned int destination, int vector,
 			       struct io_apic_irq_attr *attr)
 {
-	if (intr_remapping_enabled)
-		return setup_ir_ioapic_entry(irq,
-			 (struct IR_IO_APIC_route_entry *)entry,
-			 destination, vector, attr);
+	if (irq_remapping_enabled)
+		return setup_ioapic_remapped_entry(irq, entry, destination,
+						   vector, attr);
 
 	memset(entry, 0, sizeof(*entry));
 
@@ -1588,7 +1540,7 @@ static void __init setup_timer_IRQ0_pin(unsigned int ioapic_idx,
 {
 	struct IO_APIC_route_entry entry;
 
-	if (intr_remapping_enabled)
+	if (irq_remapping_enabled)
 		return;
 
 	memset(&entry, 0, sizeof(entry));
@@ -1674,7 +1626,7 @@ __apicdebuginit(void) print_IO_APIC(int ioapic_idx)
 
 	printk(KERN_DEBUG ".... IRQ redirection table:\n");
 
-	if (intr_remapping_enabled) {
+	if (irq_remapping_enabled) {
 		printk(KERN_DEBUG " NR Indx Fmt Mask Trig IRR"
 			" Pol Stat Indx2 Zero Vect:\n");
 	} else {
@@ -1683,7 +1635,7 @@ __apicdebuginit(void) print_IO_APIC(int ioapic_idx)
 	}
 
 	for (i = 0; i <= reg_01.bits.entries; i++) {
-		if (intr_remapping_enabled) {
+		if (irq_remapping_enabled) {
 			struct IO_APIC_route_entry entry;
 			struct IR_IO_APIC_route_entry *ir_entry;
 
@@ -2050,7 +2002,7 @@ void disable_IO_APIC(void)
 	 * IOAPIC RTE as well as interrupt-remapping table entry).
 	 * As this gets called during crash dump, keep this simple for now.
 	 */
-	if (ioapic_i8259.pin != -1 && !intr_remapping_enabled) {
+	if (ioapic_i8259.pin != -1 && !irq_remapping_enabled) {
 		struct IO_APIC_route_entry entry;
 
 		memset(&entry, 0, sizeof(entry));
@@ -2074,7 +2026,7 @@ void disable_IO_APIC(void)
 	 * Use virtual wire A mode when interrupt remapping is enabled.
 	 */
 	if (cpu_has_apic || apic_from_smp_config())
-		disconnect_bsp_APIC(!intr_remapping_enabled &&
+		disconnect_bsp_APIC(!irq_remapping_enabled &&
 				ioapic_i8259.pin != -1);
 }
 
@@ -2390,71 +2342,6 @@ ioapic_set_affinity(struct irq_data *data, const struct cpumask *mask,
 	return ret;
 }
 
-#ifdef CONFIG_IRQ_REMAP
-
-/*
- * Migrate the IO-APIC irq in the presence of intr-remapping.
- *
- * For both level and 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 eliminate the io-apic RTE modification (with the
- * updated vector information), by using a virtual vector (io-apic pin number).
- * Real vector that is used for interrupting cpu will be coming from
- * the interrupt-remapping table entry.
- *
- * As the migration is a simple atomic update of IRTE, the same mechanism
- * is used to migrate MSI irq's in the presence of interrupt-remapping.
- */
-static int
-ir_ioapic_set_affinity(struct irq_data *data, const struct cpumask *mask,
-		       bool force)
-{
-	struct irq_cfg *cfg = data->chip_data;
-	unsigned int dest, irq = data->irq;
-	struct irte irte;
-
-	if (!cpumask_intersects(mask, cpu_online_mask))
-		return -EINVAL;
-
-	if (get_irte(irq, &irte))
-		return -EBUSY;
-
-	if (assign_irq_vector(irq, cfg, mask))
-		return -EBUSY;
-
-	dest = apic->cpu_mask_to_apicid_and(cfg->domain, mask);
-
-	irte.vector = cfg->vector;
-	irte.dest_id = IRTE_DEST(dest);
-
-	/*
-	 * Atomically updates the IRTE with the new destination, vector
-	 * and flushes the interrupt entry cache.
-	 */
-	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)
-		send_cleanup_vector(cfg);
-
-	cpumask_copy(data->affinity, mask);
-	return 0;
-}
-
-#else
-static inline int
-ir_ioapic_set_affinity(struct irq_data *data, const struct cpumask *mask,
-		       bool force)
-{
-	return 0;
-}
-#endif
-
 asmlinkage void smp_irq_move_cleanup_interrupt(void)
 {
 	unsigned vector, me;
@@ -2699,7 +2586,7 @@ static void irq_remap_modify_chip_defaults(struct irq_chip *chip)
 	chip->irq_eoi = ir_ack_apic_level;
 
 #ifdef CONFIG_SMP
-	chip->irq_set_affinity = ir_ioapic_set_affinity;
+	chip->irq_set_affinity = set_remapped_irq_affinity;
 #endif
 }
 #endif /* CONFIG_IRQ_REMAP */
@@ -2912,7 +2799,7 @@ static inline void __init check_timer(void)
 	 * 8259A.
 	 */
 	if (pin1 == -1) {
-		if (intr_remapping_enabled)
+		if (irq_remapping_enabled)
 			panic("BIOS bug: timer not connected to IO-APIC");
 		pin1 = pin2;
 		apic1 = apic2;
@@ -2945,7 +2832,7 @@ static inline void __init check_timer(void)
 				clear_IO_APIC_pin(0, pin1);
 			goto out;
 		}
-		if (intr_remapping_enabled)
+		if (irq_remapping_enabled)
 			panic("timer doesn't work through Interrupt-remapped IO-APIC");
 		local_irq_disable();
 		clear_IO_APIC_pin(apic1, pin1);
@@ -3169,7 +3056,7 @@ void destroy_irq(unsigned int irq)
 	irq_set_status_flags(irq, IRQ_NOREQUEST|IRQ_NOPROBE);
 
 	if (irq_remapped(cfg))
-		free_irte(irq);
+		free_remapped_irq(irq);
 	raw_spin_lock_irqsave(&vector_lock, flags);
 	__clear_irq_vector(irq, cfg);
 	raw_spin_unlock_irqrestore(&vector_lock, flags);
@@ -3198,54 +3085,34 @@ 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(cfg)) {
-		struct irte irte;
-		int ir_index;
-		u16 sub_handle;
-
-		ir_index = map_irq_to_irte_handle(irq, &sub_handle);
-		BUG_ON(ir_index == -1);
-
-		prepare_irte(&irte, cfg->vector, dest);
-
-		/* Set source-id of interrupt request */
-		if (pdev)
-			set_msi_sid(&irte, pdev);
-		else
-			set_hpet_sid(&irte, hpet_id);
-
-		modify_irte(irq, &irte);
+		compose_remapped_msi_msg(pdev, irq, dest, msg, hpet_id);
+		return err;
+	}
 
+	if (x2apic_enabled())
+		msg->address_hi = MSI_ADDR_BASE_HI |
+				  MSI_ADDR_EXT_DEST_ID(dest);
+	else
 		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 {
-		if (x2apic_enabled())
-			msg->address_hi = MSI_ADDR_BASE_HI |
-					  MSI_ADDR_EXT_DEST_ID(dest);
-		else
-			msg->address_hi = MSI_ADDR_BASE_HI;
 
-		msg->address_lo =
-			MSI_ADDR_BASE_LO |
-			((apic->irq_dest_mode == 0) ?
-				MSI_ADDR_DEST_MODE_PHYSICAL:
-				MSI_ADDR_DEST_MODE_LOGICAL) |
-			((apic->irq_delivery_mode != dest_LowestPrio) ?
-				MSI_ADDR_REDIRECTION_CPU:
-				MSI_ADDR_REDIRECTION_LOWPRI) |
-			MSI_ADDR_DEST_ID(dest);
+	msg->address_lo =
+		MSI_ADDR_BASE_LO |
+		((apic->irq_dest_mode == 0) ?
+			MSI_ADDR_DEST_MODE_PHYSICAL:
+			MSI_ADDR_DEST_MODE_LOGICAL) |
+		((apic->irq_delivery_mode != dest_LowestPrio) ?
+			MSI_ADDR_REDIRECTION_CPU:
+			MSI_ADDR_REDIRECTION_LOWPRI) |
+		MSI_ADDR_DEST_ID(dest);
+
+	msg->data =
+		MSI_DATA_TRIGGER_EDGE |
+		MSI_DATA_LEVEL_ASSERT |
+		((apic->irq_delivery_mode != dest_LowestPrio) ?
+			MSI_DATA_DELIVERY_FIXED:
+			MSI_DATA_DELIVERY_LOWPRI) |
+		MSI_DATA_VECTOR(cfg->vector);
 
-		msg->data =
-			MSI_DATA_TRIGGER_EDGE |
-			MSI_DATA_LEVEL_ASSERT |
-			((apic->irq_delivery_mode != dest_LowestPrio) ?
-				MSI_DATA_DELIVERY_FIXED:
-				MSI_DATA_DELIVERY_LOWPRI) |
-			MSI_DATA_VECTOR(cfg->vector);
-	}
 	return err;
 }
 
@@ -3288,33 +3155,6 @@ static struct irq_chip msi_chip = {
 	.irq_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;
-}
-
 static int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, int irq)
 {
 	struct irq_chip *chip = &msi_chip;
@@ -3345,7 +3185,6 @@ int native_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 	int node, ret, sub_handle, index = 0;
 	unsigned int irq, irq_want;
 	struct msi_desc *msidesc;
-	struct intel_iommu *iommu = NULL;
 
 	/* x86 doesn't support multiple MSI yet */
 	if (type == PCI_CAP_ID_MSI && nvec > 1)
@@ -3359,7 +3198,7 @@ int native_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 		if (irq == 0)
 			return -1;
 		irq_want = irq + 1;
-		if (!intr_remapping_enabled)
+		if (!irq_remapping_enabled)
 			goto no_ir;
 
 		if (!sub_handle) {
@@ -3367,23 +3206,16 @@ int native_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 			 * allocate the consecutive block of IRTE's
 			 * for 'nvec'
 			 */
-			index = msi_alloc_irte(dev, irq, nvec);
+			index = msi_alloc_remapped_irq(dev, irq, nvec);
 			if (index < 0) {
 				ret = index;
 				goto error;
 			}
 		} else {
-			iommu = map_dev_to_ir(dev);
-			if (!iommu) {
-				ret = -ENOENT;
+			ret = msi_setup_remapped_irq(dev, irq, index,
+						     sub_handle);
+			if (ret < 0)
 				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:
 		ret = setup_msi_irq(dev, msidesc, irq);
@@ -3501,15 +3333,8 @@ int arch_setup_hpet_msi(unsigned int irq, unsigned int id)
 	struct msi_msg msg;
 	int ret;
 
-	if (intr_remapping_enabled) {
-		struct intel_iommu *iommu = map_hpet_to_ir(id);
-		int index;
-
-		if (!iommu)
-			return -1;
-
-		index = alloc_irte(iommu, irq, 1);
-		if (index < 0)
+	if (irq_remapping_enabled) {
+		if (!setup_hpet_msi_remapped(irq, id))
 			return -1;
 	}
 
@@ -3888,8 +3713,8 @@ void __init setup_ioapic_dest(void)
 		else
 			mask = apic->target_cpus();
 
-		if (intr_remapping_enabled)
-			ir_ioapic_set_affinity(idata, mask, false);
+		if (irq_remapping_enabled)
+			set_remapped_irq_affinity(idata, mask, false);
 		else
 			ioapic_set_affinity(idata, mask, false);
 	}
diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c
index 8a778db45e3a..991e315f4227 100644
--- a/arch/x86/kernel/apic/x2apic_phys.c
+++ b/arch/x86/kernel/apic/x2apic_phys.c
@@ -24,6 +24,12 @@ static int x2apic_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
 {
 	if (x2apic_phys)
 		return x2apic_enabled();
+	else if ((acpi_gbl_FADT.header.revision >= FADT2_REVISION_ID) &&
+		(acpi_gbl_FADT.flags & ACPI_FADT_APIC_PHYSICAL) &&
+		x2apic_enabled()) {
+		printk(KERN_DEBUG "System requires x2apic physical mode\n");
+		return 1;
+	}
 	else
 		return 0;
 }
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 0a44b90602b0..146bb6218eec 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -26,7 +26,8 @@
  *	contact AMD for precise details and a CPU swap.
  *
  *	See	http://www.multimania.com/poulot/k6bug.html
- *		http://www.amd.com/K6/k6docs/revgd.html
+ *	and	section 2.6.2 of "AMD-K6 Processor Revision Guide - Model 6"
+ *		(Publication # 21266  Issue Date: August 1998)
  *
  *	The following test is erm.. interesting. AMD neglected to up
  *	the chip setting when fixing the bug but they also tweaked some
@@ -94,7 +95,6 @@ static void __cpuinit init_amd_k6(struct cpuinfo_x86 *c)
 				"system stability may be impaired when more than 32 MB are used.\n");
 		else
 			printk(KERN_CONT "probably OK (after B9730xxxx).\n");
-		printk(KERN_INFO "Please see http://membres.lycos.fr/poulot/k6bug.html\n");
 	}
 
 	/* K6 with old style WHCR */
@@ -353,10 +353,11 @@ static void __cpuinit srat_detect_node(struct cpuinfo_x86 *c)
 		node = per_cpu(cpu_llc_id, cpu);
 
 	/*
-	 * If core numbers are inconsistent, it's likely a multi-fabric platform,
-	 * so invoke platform-specific handler
+	 * On multi-fabric platform (e.g. Numascale NumaChip) a
+	 * platform-specific handler needs to be called to fixup some
+	 * IDs of the CPU.
 	 */
-	if (c->phys_proc_id != node)
+	if (x86_cpuinit.fixup_cpu_id)
 		x86_cpuinit.fixup_cpu_id(c, node);
 
 	if (!node_online(node)) {
@@ -579,6 +580,24 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c)
 		}
 	}
 
+	/* re-enable TopologyExtensions if switched off by BIOS */
+	if ((c->x86 == 0x15) &&
+	    (c->x86_model >= 0x10) && (c->x86_model <= 0x1f) &&
+	    !cpu_has(c, X86_FEATURE_TOPOEXT)) {
+		u64 val;
+
+		if (!rdmsrl_amd_safe(0xc0011005, &val)) {
+			val |= 1ULL << 54;
+			wrmsrl_amd_safe(0xc0011005, val);
+			rdmsrl(0xc0011005, val);
+			if (val & (1ULL << 54)) {
+				set_cpu_cap(c, X86_FEATURE_TOPOEXT);
+				printk(KERN_INFO FW_INFO "CPU: Re-enabling "
+				  "disabled Topology Extensions Support\n");
+			}
+		}
+	}
+
 	cpu_detect_cache_sizes(c);
 
 	/* Multi core CPU? */
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 67e258362a3d..cf79302198a6 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1163,15 +1163,6 @@ static void dbg_restore_debug_regs(void)
 #endif /* ! CONFIG_KGDB */
 
 /*
- * Prints an error where the NUMA and configured core-number mismatch and the
- * platform didn't override this to fix it up
- */
-void __cpuinit x86_default_fixup_cpu_id(struct cpuinfo_x86 *c, int node)
-{
-	pr_err("NUMA core number %d differs from configured core number %d\n", node, c->phys_proc_id);
-}
-
-/*
  * cpu_init() initializes state that is per-CPU. Some data is already
  * initialized (naturally) in the bootstrap process, such as the GDT
  * and IDT. We reload them nevertheless, this function acts as a
diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
index 73d08ed98a64..b8f3653dddbc 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -433,14 +433,14 @@ int amd_set_l3_disable_slot(struct amd_northbridge *nb, int cpu, unsigned slot,
 	/*  check if @slot is already used or the index is already disabled */
 	ret = amd_get_l3_disable_slot(nb, slot);
 	if (ret >= 0)
-		return -EINVAL;
+		return -EEXIST;
 
 	if (index > nb->l3_cache.indices)
 		return -EINVAL;
 
 	/* check whether the other slot has disabled the same index already */
 	if (index == amd_get_l3_disable_slot(nb, !slot))
-		return -EINVAL;
+		return -EEXIST;
 
 	amd_l3_disable_index(nb, cpu, slot, index);
 
@@ -468,8 +468,8 @@ static ssize_t store_cache_disable(struct _cpuid4_info *this_leaf,
 	err = amd_set_l3_disable_slot(this_leaf->base.nb, cpu, slot, val);
 	if (err) {
 		if (err == -EEXIST)
-			printk(KERN_WARNING "L3 disable slot %d in use!\n",
-					    slot);
+			pr_warning("L3 slot %d in use/index already disabled!\n",
+				   slot);
 		return err;
 	}
 	return count;
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index d086a09c087d..11c9166c3337 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -945,9 +945,10 @@ struct mce_info {
 	atomic_t		inuse;
 	struct task_struct	*t;
 	__u64			paddr;
+	int			restartable;
 } mce_info[MCE_INFO_MAX];
 
-static void mce_save_info(__u64 addr)
+static void mce_save_info(__u64 addr, int c)
 {
 	struct mce_info *mi;
 
@@ -955,6 +956,7 @@ static void mce_save_info(__u64 addr)
 		if (atomic_cmpxchg(&mi->inuse, 0, 1) == 0) {
 			mi->t = current;
 			mi->paddr = addr;
+			mi->restartable = c;
 			return;
 		}
 	}
@@ -1130,7 +1132,7 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 			mce_panic("Fatal machine check on current CPU", &m, msg);
 		if (worst == MCE_AR_SEVERITY) {
 			/* schedule action before return to userland */
-			mce_save_info(m.addr);
+			mce_save_info(m.addr, m.mcgstatus & MCG_STATUS_RIPV);
 			set_thread_flag(TIF_MCE_NOTIFY);
 		} else if (kill_it) {
 			force_sig(SIGBUS, current);
@@ -1179,7 +1181,13 @@ void mce_notify_process(void)
 
 	pr_err("Uncorrected hardware memory error in user-access at %llx",
 		 mi->paddr);
-	if (memory_failure(pfn, MCE_VECTOR, MF_ACTION_REQUIRED) < 0) {
+	/*
+	 * We must call memory_failure() here even if the current process is
+	 * doomed. We still need to mark the page as poisoned and alert any
+	 * other users of the page.
+	 */
+	if (memory_failure(pfn, MCE_VECTOR, MF_ACTION_REQUIRED) < 0 ||
+			   mi->restartable == 0) {
 		pr_err("Memory error not recovered");
 		force_sig(SIGBUS, current);
 	}
diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c
index 7734bcbb5a3a..2d6e6498c176 100644
--- a/arch/x86/kernel/i387.c
+++ b/arch/x86/kernel/i387.c
@@ -235,6 +235,7 @@ int init_fpu(struct task_struct *tsk)
 	if (tsk_used_math(tsk)) {
 		if (HAVE_HWFP && tsk == current)
 			unlazy_fpu(tsk);
+		tsk->thread.fpu.last_cpu = ~0;
 		return 0;
 	}
 
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index b8ba6e4a27e4..e554e5ad2fe8 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -79,7 +79,6 @@ struct kvm_task_sleep_node {
 	u32 token;
 	int cpu;
 	bool halted;
-	struct mm_struct *mm;
 };
 
 static struct kvm_task_sleep_head {
@@ -126,9 +125,7 @@ void kvm_async_pf_task_wait(u32 token)
 
 	n.token = token;
 	n.cpu = smp_processor_id();
-	n.mm = current->active_mm;
 	n.halted = idle || preempt_count() > 1;
-	atomic_inc(&n.mm->mm_count);
 	init_waitqueue_head(&n.wq);
 	hlist_add_head(&n.link, &b->list);
 	spin_unlock(&b->lock);
@@ -161,9 +158,6 @@ EXPORT_SYMBOL_GPL(kvm_async_pf_task_wait);
 static void apf_task_wake_one(struct kvm_task_sleep_node *n)
 {
 	hlist_del_init(&n->link);
-	if (!n->mm)
-		return;
-	mmdrop(n->mm);
 	if (n->halted)
 		smp_send_reschedule(n->cpu);
 	else if (waitqueue_active(&n->wq))
@@ -207,7 +201,7 @@ again:
 		 * async PF was not yet handled.
 		 * Add dummy entry for the token.
 		 */
-		n = kmalloc(sizeof(*n), GFP_ATOMIC);
+		n = kzalloc(sizeof(*n), GFP_ATOMIC);
 		if (!n) {
 			/*
 			 * Allocation failed! Busy wait while other cpu
@@ -219,7 +213,6 @@ again:
 		}
 		n->token = token;
 		n->cpu = smp_processor_id();
-		n->mm = NULL;
 		init_waitqueue_head(&n->wq);
 		hlist_add_head(&n->link, &b->list);
 	} else
diff --git a/arch/x86/kernel/microcode_amd.c b/arch/x86/kernel/microcode_amd.c
index 73465aab28f8..8a2ce8fd41c0 100644
--- a/arch/x86/kernel/microcode_amd.c
+++ b/arch/x86/kernel/microcode_amd.c
@@ -82,11 +82,6 @@ static int collect_cpu_info_amd(int cpu, struct cpu_signature *csig)
 {
 	struct cpuinfo_x86 *c = &cpu_data(cpu);
 
-	if (c->x86_vendor != X86_VENDOR_AMD || c->x86 < 0x10) {
-		pr_warning("CPU%d: family %d not supported\n", cpu, c->x86);
-		return -1;
-	}
-
 	csig->rev = c->microcode;
 	pr_info("CPU%d: patch_level=0x%08x\n", cpu, csig->rev);
 
@@ -380,6 +375,13 @@ static struct microcode_ops microcode_amd_ops = {
 
 struct microcode_ops * __init init_amd_microcode(void)
 {
+	struct cpuinfo_x86 *c = &cpu_data(0);
+
+	if (c->x86_vendor != X86_VENDOR_AMD || c->x86 < 0x10) {
+		pr_warning("AMD CPU family 0x%x not supported\n", c->x86);
+		return NULL;
+	}
+
 	patch = (void *)get_zeroed_page(GFP_KERNEL);
 	if (!patch)
 		return NULL;
diff --git a/arch/x86/kernel/microcode_core.c b/arch/x86/kernel/microcode_core.c
index 87a0f8688301..c9bda6d6035c 100644
--- a/arch/x86/kernel/microcode_core.c
+++ b/arch/x86/kernel/microcode_core.c
@@ -419,10 +419,8 @@ static int mc_device_add(struct device *dev, struct subsys_interface *sif)
 	if (err)
 		return err;
 
-	if (microcode_init_cpu(cpu) == UCODE_ERROR) {
-		sysfs_remove_group(&dev->kobj, &mc_attr_group);
+	if (microcode_init_cpu(cpu) == UCODE_ERROR)
 		return -EINVAL;
-	}
 
 	return err;
 }
@@ -528,11 +526,11 @@ static int __init microcode_init(void)
 		microcode_ops = init_intel_microcode();
 	else if (c->x86_vendor == X86_VENDOR_AMD)
 		microcode_ops = init_amd_microcode();
-
-	if (!microcode_ops) {
+	else
 		pr_err("no support for this CPU vendor\n");
+
+	if (!microcode_ops)
 		return -ENODEV;
-	}
 
 	microcode_pdev = platform_device_register_simple("microcode", -1,
 							 NULL, 0);
diff --git a/arch/x86/kernel/microcode_intel.c b/arch/x86/kernel/microcode_intel.c
index 3ca42d0e43a2..0327e2b3c408 100644
--- a/arch/x86/kernel/microcode_intel.c
+++ b/arch/x86/kernel/microcode_intel.c
@@ -147,12 +147,6 @@ static int collect_cpu_info(int cpu_num, struct cpu_signature *csig)
 
 	memset(csig, 0, sizeof(*csig));
 
-	if (c->x86_vendor != X86_VENDOR_INTEL || c->x86 < 6 ||
-	    cpu_has(c, X86_FEATURE_IA64)) {
-		pr_err("CPU%d not a capable Intel processor\n", cpu_num);
-		return -1;
-	}
-
 	csig->sig = cpuid_eax(0x00000001);
 
 	if ((c->x86_model >= 5) || (c->x86 > 6)) {
@@ -463,6 +457,14 @@ static struct microcode_ops microcode_intel_ops = {
 
 struct microcode_ops * __init init_intel_microcode(void)
 {
+	struct cpuinfo_x86 *c = &cpu_data(0);
+
+	if (c->x86_vendor != X86_VENDOR_INTEL || c->x86 < 6 ||
+	    cpu_has(c, X86_FEATURE_IA64)) {
+		pr_err("Intel CPU family 0x%x not supported\n", c->x86);
+		return NULL;
+	}
+
 	return &microcode_intel_ops;
 }
 
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 733ca39f367e..43d8b48b23e6 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -423,6 +423,7 @@ void set_personality_ia32(bool x32)
 		current_thread_info()->status |= TS_COMPAT;
 	}
 }
+EXPORT_SYMBOL_GPL(set_personality_ia32);
 
 unsigned long get_wchan(struct task_struct *p)
 {
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index 71f4727da373..5a98aa272184 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -185,10 +185,22 @@ void __init setup_per_cpu_areas(void)
 #endif
 	rc = -EINVAL;
 	if (pcpu_chosen_fc != PCPU_FC_PAGE) {
-		const size_t atom_size = cpu_has_pse ? PMD_SIZE : PAGE_SIZE;
 		const size_t dyn_size = PERCPU_MODULE_RESERVE +
 			PERCPU_DYNAMIC_RESERVE - PERCPU_FIRST_CHUNK_RESERVE;
+		size_t atom_size;
 
+		/*
+		 * On 64bit, use PMD_SIZE for atom_size so that embedded
+		 * percpu areas are aligned to PMD.  This, in the future,
+		 * can also allow using PMD mappings in vmalloc area.  Use
+		 * PAGE_SIZE on 32bit as vmalloc space is highly contended
+		 * and large vmalloc area allocs can easily fail.
+		 */
+#ifdef CONFIG_X86_64
+		atom_size = PMD_SIZE;
+#else
+		atom_size = PAGE_SIZE;
+#endif
 		rc = pcpu_embed_first_chunk(PERCPU_FIRST_CHUNK_RESERVE,
 					    dyn_size, atom_size,
 					    pcpu_cpu_distance,
diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c
index e9f265fd79ae..9cf71d0b2d37 100644
--- a/arch/x86/kernel/x86_init.c
+++ b/arch/x86/kernel/x86_init.c
@@ -93,7 +93,6 @@ struct x86_init_ops x86_init __initdata = {
 struct x86_cpuinit_ops x86_cpuinit __cpuinitdata = {
 	.early_percpu_clock_init	= x86_init_noop,
 	.setup_percpu_clockev		= setup_secondary_APIC_clock,
-	.fixup_cpu_id			= x86_default_fixup_cpu_id,
 };
 
 static void default_nmi_init(void) { };