Merge branch 'tip/perf/core' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-2.6-trace into perf/urgent

26 files changed, 648 insertions, 714 deletions

diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 1e994754d323..34244b2cd880 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -85,7 +85,6 @@ obj-$(CONFIG_DOUBLEFAULT) 	+= doublefault_32.o
 obj-$(CONFIG_KGDB)		+= kgdb.o
 obj-$(CONFIG_VM86)		+= vm86_32.o
 obj-$(CONFIG_EARLY_PRINTK)	+= early_printk.o
-obj-$(CONFIG_EARLY_PRINTK_MRST)	+= early_printk_mrst.o
 
 obj-$(CONFIG_HPET_TIMER) 	+= hpet.o
 obj-$(CONFIG_APB_TIMER)		+= apb_timer.o
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 71232b941b6c..17c8090fabd4 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -198,6 +198,11 @@ static void __cpuinit acpi_register_lapic(int id, u8 enabled)
 {
 	unsigned int ver = 0;
 
+	if (id >= (MAX_LOCAL_APIC-1)) {
+		printk(KERN_INFO PREFIX "skipped apicid that is too big\n");
+		return;
+	}
+
 	if (!enabled) {
 		++disabled_cpus;
 		return;
@@ -910,13 +915,13 @@ static int __init acpi_parse_madt_lapic_entries(void)
 	acpi_register_lapic_address(acpi_lapic_addr);
 
 	count = acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_SAPIC,
-				      acpi_parse_sapic, MAX_APICS);
+				      acpi_parse_sapic, MAX_LOCAL_APIC);
 
 	if (!count) {
 		x2count = acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_X2APIC,
-						acpi_parse_x2apic, MAX_APICS);
+					acpi_parse_x2apic, MAX_LOCAL_APIC);
 		count = acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_APIC,
-					      acpi_parse_lapic, MAX_APICS);
+					acpi_parse_lapic, MAX_LOCAL_APIC);
 	}
 	if (!count && !x2count) {
 		printk(KERN_ERR PREFIX "No LAPIC entries present\n");
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 553d0b0d639b..123608531c8f 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -353,6 +353,7 @@ void __init_or_module alternatives_smp_module_del(struct module *mod)
 	mutex_unlock(&smp_alt);
 }
 
+bool skip_smp_alternatives;
 void alternatives_smp_switch(int smp)
 {
 	struct smp_alt_module *mod;
@@ -368,7 +369,7 @@ void alternatives_smp_switch(int smp)
 	printk("lockdep: fixing up alternatives.\n");
 #endif
 
-	if (noreplace_smp || smp_alt_once)
+	if (noreplace_smp || smp_alt_once || skip_smp_alternatives)
 		return;
 	BUG_ON(!smp && (num_online_cpus() > 1));
 
diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c
index 8f6463d8ed0d..affacb5e0065 100644
--- a/arch/x86/kernel/amd_nb.c
+++ b/arch/x86/kernel/amd_nb.c
@@ -12,95 +12,116 @@
 
 static u32 *flush_words;
 
-struct pci_device_id k8_nb_ids[] = {
+struct pci_device_id amd_nb_misc_ids[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_K8_NB_MISC) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_10H_NB_MISC) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_MISC) },
 	{}
 };
-EXPORT_SYMBOL(k8_nb_ids);
+EXPORT_SYMBOL(amd_nb_misc_ids);
 
-struct k8_northbridge_info k8_northbridges;
-EXPORT_SYMBOL(k8_northbridges);
+struct amd_northbridge_info amd_northbridges;
+EXPORT_SYMBOL(amd_northbridges);
 
-static struct pci_dev *next_k8_northbridge(struct pci_dev *dev)
+static struct pci_dev *next_northbridge(struct pci_dev *dev,
+					struct pci_device_id *ids)
 {
 	do {
 		dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev);
 		if (!dev)
 			break;
-	} while (!pci_match_id(&k8_nb_ids[0], dev));
+	} while (!pci_match_id(ids, dev));
 	return dev;
 }
 
-int cache_k8_northbridges(void)
+int amd_cache_northbridges(void)
 {
-	int i;
-	struct pci_dev *dev;
+	int i = 0;
+	struct amd_northbridge *nb;
+	struct pci_dev *misc;
 
-	if (k8_northbridges.num)
+	if (amd_nb_num())
 		return 0;
 
-	dev = NULL;
-	while ((dev = next_k8_northbridge(dev)) != NULL)
-		k8_northbridges.num++;
+	misc = NULL;
+	while ((misc = next_northbridge(misc, amd_nb_misc_ids)) != NULL)
+		i++;
 
-	/* some CPU families (e.g. family 0x11) do not support GART */
-	if (boot_cpu_data.x86 == 0xf || boot_cpu_data.x86 == 0x10 ||
-	    boot_cpu_data.x86 == 0x15)
-		k8_northbridges.gart_supported = 1;
+	if (i == 0)
+		return 0;
 
-	k8_northbridges.nb_misc = kmalloc((k8_northbridges.num + 1) *
-					  sizeof(void *), GFP_KERNEL);
-	if (!k8_northbridges.nb_misc)
+	nb = kzalloc(i * sizeof(struct amd_northbridge), GFP_KERNEL);
+	if (!nb)
 		return -ENOMEM;
 
-	if (!k8_northbridges.num) {
-		k8_northbridges.nb_misc[0] = NULL;
-		return 0;
-	}
+	amd_northbridges.nb = nb;
+	amd_northbridges.num = i;
 
-	if (k8_northbridges.gart_supported) {
-		flush_words = kmalloc(k8_northbridges.num * sizeof(u32),
-				      GFP_KERNEL);
-		if (!flush_words) {
-			kfree(k8_northbridges.nb_misc);
-			return -ENOMEM;
-		}
-	}
+	misc = NULL;
+	for (i = 0; i != amd_nb_num(); i++) {
+		node_to_amd_nb(i)->misc = misc =
+			next_northbridge(misc, amd_nb_misc_ids);
+        }
+
+	/* some CPU families (e.g. family 0x11) do not support GART */
+	if (boot_cpu_data.x86 == 0xf || boot_cpu_data.x86 == 0x10 ||
+	    boot_cpu_data.x86 == 0x15)
+		amd_northbridges.flags |= AMD_NB_GART;
+
+	/*
+	 * Some CPU families support L3 Cache Index Disable. There are some
+	 * limitations because of E382 and E388 on family 0x10.
+	 */
+	if (boot_cpu_data.x86 == 0x10 &&
+	    boot_cpu_data.x86_model >= 0x8 &&
+	    (boot_cpu_data.x86_model > 0x9 ||
+	     boot_cpu_data.x86_mask >= 0x1))
+		amd_northbridges.flags |= AMD_NB_L3_INDEX_DISABLE;
 
-	dev = NULL;
-	i = 0;
-	while ((dev = next_k8_northbridge(dev)) != NULL) {
-		k8_northbridges.nb_misc[i] = dev;
-		if (k8_northbridges.gart_supported)
-			pci_read_config_dword(dev, 0x9c, &flush_words[i++]);
-	}
-	k8_northbridges.nb_misc[i] = NULL;
 	return 0;
 }
-EXPORT_SYMBOL_GPL(cache_k8_northbridges);
+EXPORT_SYMBOL_GPL(amd_cache_northbridges);
 
 /* Ignores subdevice/subvendor but as far as I can figure out
    they're useless anyways */
-int __init early_is_k8_nb(u32 device)
+int __init early_is_amd_nb(u32 device)
 {
 	struct pci_device_id *id;
 	u32 vendor = device & 0xffff;
 	device >>= 16;
-	for (id = k8_nb_ids; id->vendor; id++)
+	for (id = amd_nb_misc_ids; id->vendor; id++)
 		if (vendor == id->vendor && device == id->device)
 			return 1;
 	return 0;
 }
 
-void k8_flush_garts(void)
+int amd_cache_gart(void)
+{
+       int i;
+
+       if (!amd_nb_has_feature(AMD_NB_GART))
+               return 0;
+
+       flush_words = kmalloc(amd_nb_num() * sizeof(u32), GFP_KERNEL);
+       if (!flush_words) {
+               amd_northbridges.flags &= ~AMD_NB_GART;
+               return -ENOMEM;
+       }
+
+       for (i = 0; i != amd_nb_num(); i++)
+               pci_read_config_dword(node_to_amd_nb(i)->misc, 0x9c,
+                                     &flush_words[i]);
+
+       return 0;
+}
+
+void amd_flush_garts(void)
 {
 	int flushed, i;
 	unsigned long flags;
 	static DEFINE_SPINLOCK(gart_lock);
 
-	if (!k8_northbridges.gart_supported)
+	if (!amd_nb_has_feature(AMD_NB_GART))
 		return;
 
 	/* Avoid races between AGP and IOMMU. In theory it's not needed
@@ -109,16 +130,16 @@ void k8_flush_garts(void)
 	   that it doesn't matter to serialize more. -AK */
 	spin_lock_irqsave(&gart_lock, flags);
 	flushed = 0;
-	for (i = 0; i < k8_northbridges.num; i++) {
-		pci_write_config_dword(k8_northbridges.nb_misc[i], 0x9c,
-				       flush_words[i]|1);
+	for (i = 0; i < amd_nb_num(); i++) {
+		pci_write_config_dword(node_to_amd_nb(i)->misc, 0x9c,
+				       flush_words[i] | 1);
 		flushed++;
 	}
-	for (i = 0; i < k8_northbridges.num; i++) {
+	for (i = 0; i < amd_nb_num(); i++) {
 		u32 w;
 		/* Make sure the hardware actually executed the flush*/
 		for (;;) {
-			pci_read_config_dword(k8_northbridges.nb_misc[i],
+			pci_read_config_dword(node_to_amd_nb(i)->misc,
 					      0x9c, &w);
 			if (!(w & 1))
 				break;
@@ -129,19 +150,23 @@ void k8_flush_garts(void)
 	if (!flushed)
 		printk("nothing to flush?\n");
 }
-EXPORT_SYMBOL_GPL(k8_flush_garts);
+EXPORT_SYMBOL_GPL(amd_flush_garts);
 
-static __init int init_k8_nbs(void)
+static __init int init_amd_nbs(void)
 {
 	int err = 0;
 
-	err = cache_k8_northbridges();
+	err = amd_cache_northbridges();
 
 	if (err < 0)
-		printk(KERN_NOTICE "K8 NB: Cannot enumerate AMD northbridges.\n");
+		printk(KERN_NOTICE "AMD NB: Cannot enumerate AMD northbridges.\n");
+
+	if (amd_cache_gart() < 0)
+		printk(KERN_NOTICE "AMD NB: Cannot initialize GART flush words, "
+		       "GART support disabled.\n");
 
 	return err;
 }
 
 /* This has to go after the PCI subsystem */
-fs_initcall(init_k8_nbs);
+fs_initcall(init_amd_nbs);
diff --git a/arch/x86/kernel/apb_timer.c b/arch/x86/kernel/apb_timer.c
index 92543c73cf8e..7c9ab59653e8 100644
--- a/arch/x86/kernel/apb_timer.c
+++ b/arch/x86/kernel/apb_timer.c
@@ -315,6 +315,7 @@ static void apbt_setup_irq(struct apbt_dev *adev)
 
 	if (system_state == SYSTEM_BOOTING) {
 		irq_modify_status(adev->irq, 0, IRQ_MOVE_PCNTXT);
+		irq_set_affinity(adev->irq, cpumask_of(adev->cpu));
 		/* APB timer irqs are set up as mp_irqs, timer is edge type */
 		__set_irq_handler(adev->irq, handle_edge_irq, 0, "edge");
 		if (request_irq(adev->irq, apbt_interrupt_handler,
diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c
index b3a16e8f0703..dcd7c83e1659 100644
--- a/arch/x86/kernel/aperture_64.c
+++ b/arch/x86/kernel/aperture_64.c
@@ -206,7 +206,7 @@ static u32 __init read_agp(int bus, int slot, int func, int cap, u32 *order)
  * Do an PCI bus scan by hand because we're running before the PCI
  * subsystem.
  *
- * All K8 AGP bridges are AGPv3 compliant, so we can do this scan
+ * All AMD AGP bridges are AGPv3 compliant, so we can do this scan
  * generically. It's probably overkill to always scan all slots because
  * the AGP bridges should be always an own bus on the HT hierarchy,
  * but do it here for future safety.
@@ -303,7 +303,7 @@ void __init early_gart_iommu_check(void)
 		dev_limit = bus_dev_ranges[i].dev_limit;
 
 		for (slot = dev_base; slot < dev_limit; slot++) {
-			if (!early_is_k8_nb(read_pci_config(bus, slot, 3, 0x00)))
+			if (!early_is_amd_nb(read_pci_config(bus, slot, 3, 0x00)))
 				continue;
 
 			ctl = read_pci_config(bus, slot, 3, AMD64_GARTAPERTURECTL);
@@ -358,7 +358,7 @@ void __init early_gart_iommu_check(void)
 		dev_limit = bus_dev_ranges[i].dev_limit;
 
 		for (slot = dev_base; slot < dev_limit; slot++) {
-			if (!early_is_k8_nb(read_pci_config(bus, slot, 3, 0x00)))
+			if (!early_is_amd_nb(read_pci_config(bus, slot, 3, 0x00)))
 				continue;
 
 			ctl = read_pci_config(bus, slot, 3, AMD64_GARTAPERTURECTL);
@@ -400,7 +400,7 @@ int __init gart_iommu_hole_init(void)
 		dev_limit = bus_dev_ranges[i].dev_limit;
 
 		for (slot = dev_base; slot < dev_limit; slot++) {
-			if (!early_is_k8_nb(read_pci_config(bus, slot, 3, 0x00)))
+			if (!early_is_amd_nb(read_pci_config(bus, slot, 3, 0x00)))
 				continue;
 
 			iommu_detected = 1;
@@ -518,7 +518,7 @@ out:
 		dev_base = bus_dev_ranges[i].dev_base;
 		dev_limit = bus_dev_ranges[i].dev_limit;
 		for (slot = dev_base; slot < dev_limit; slot++) {
-			if (!early_is_k8_nb(read_pci_config(bus, slot, 3, 0x00)))
+			if (!early_is_amd_nb(read_pci_config(bus, slot, 3, 0x00)))
 				continue;
 
 			write_pci_config(bus, slot, 3, AMD64_GARTAPERTURECTL, ctl);
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index fb7657822aad..879999a5230f 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -431,17 +431,18 @@ int setup_APIC_eilvt(u8 offset, u8 vector, u8 msg_type, u8 mask)
 	reserved = reserve_eilvt_offset(offset, new);
 
 	if (reserved != new) {
-		pr_err(FW_BUG "cpu %d, try to setup vector 0x%x, but "
-		       "vector 0x%x was already reserved by another core, "
-		       "APIC%lX=0x%x\n",
-		       smp_processor_id(), new, reserved, reg, old);
+		pr_err(FW_BUG "cpu %d, try to use APIC%lX (LVT offset %d) for "
+		       "vector 0x%x, but the register is already in use for "
+		       "vector 0x%x on another cpu\n",
+		       smp_processor_id(), reg, offset, new, reserved);
 		return -EINVAL;
 	}
 
 	if (!eilvt_entry_is_changeable(old, new)) {
-		pr_err(FW_BUG "cpu %d, try to setup vector 0x%x but "
-		       "register already in use, APIC%lX=0x%x\n",
-		       smp_processor_id(), new, reg, old);
+		pr_err(FW_BUG "cpu %d, try to use APIC%lX (LVT offset %d) for "
+		       "vector 0x%x, but the register is already in use for "
+		       "vector 0x%x on this cpu\n",
+		       smp_processor_id(), reg, offset, new, old);
 		return -EBUSY;
 	}
 
@@ -1532,13 +1533,60 @@ static int __init detect_init_APIC(void)
 	return 0;
 }
 #else
+
+static int apic_verify(void)
+{
+	u32 features, h, l;
+
+	/*
+	 * The APIC feature bit should now be enabled
+	 * in `cpuid'
+	 */
+	features = cpuid_edx(1);
+	if (!(features & (1 << X86_FEATURE_APIC))) {
+		pr_warning("Could not enable APIC!\n");
+		return -1;
+	}
+	set_cpu_cap(&boot_cpu_data, X86_FEATURE_APIC);
+	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;
+
+	pr_info("Found and enabled local APIC!\n");
+	return 0;
+}
+
+int apic_force_enable(void)
+{
+	u32 h, l;
+
+	if (disable_apic)
+		return -1;
+
+	/*
+	 * Some BIOSes disable the local APIC in the APIC_BASE
+	 * 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 | APIC_DEFAULT_PHYS_BASE;
+		wrmsr(MSR_IA32_APICBASE, l, h);
+		enabled_via_apicbase = 1;
+	}
+	return apic_verify();
+}
+
 /*
  * Detect and initialize APIC
  */
 static int __init detect_init_APIC(void)
 {
-	u32 h, l, features;
-
 	/* Disabled by kernel option? */
 	if (disable_apic)
 		return -1;
@@ -1568,38 +1616,12 @@ static int __init detect_init_APIC(void)
 				"you can enable it with \"lapic\"\n");
 			return -1;
 		}
-		/*
-		 * Some BIOSes disable the local APIC in the APIC_BASE
-		 * 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 | APIC_DEFAULT_PHYS_BASE;
-			wrmsr(MSR_IA32_APICBASE, l, h);
-			enabled_via_apicbase = 1;
-		}
-	}
-	/*
-	 * The APIC feature bit should now be enabled
-	 * in `cpuid'
-	 */
-	features = cpuid_edx(1);
-	if (!(features & (1 << X86_FEATURE_APIC))) {
-		pr_warning("Could not enable APIC!\n");
-		return -1;
+		if (apic_force_enable())
+			return -1;
+	} else {
+		if (apic_verify())
+			return -1;
 	}
-	set_cpu_cap(&boot_cpu_data, X86_FEATURE_APIC);
-	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;
-
-	pr_info("Found and enabled local APIC!\n");
 
 	apic_pm_activate();
 
@@ -1687,7 +1709,7 @@ void __init init_apic_mappings(void)
  * This initializes the IO-APIC and APIC hardware if this is
  * a UP kernel.
  */
-int apic_version[MAX_APICS];
+int apic_version[MAX_LOCAL_APIC];
 
 int __init APIC_init_uniprocessor(void)
 {
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 16c2db8750a2..f6cd5b410770 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -1933,8 +1933,7 @@ void disable_IO_APIC(void)
  *
  * by Matt Domsch <Matt_Domsch@dell.com>  Tue Dec 21 12:25:05 CST 1999
  */
-
-void __init setup_ioapic_ids_from_mpc(void)
+void __init setup_ioapic_ids_from_mpc_nocheck(void)
 {
 	union IO_APIC_reg_00 reg_00;
 	physid_mask_t phys_id_present_map;
@@ -1943,15 +1942,6 @@ void __init setup_ioapic_ids_from_mpc(void)
 	unsigned char old_id;
 	unsigned long flags;
 
-	if (acpi_ioapic)
-		return;
-	/*
-	 * Don't check I/O APIC IDs for xAPIC systems.  They have
-	 * no meaning without the serial APIC bus.
-	 */
-	if (!(boot_cpu_data.x86_vendor == X86_VENDOR_INTEL)
-		|| APIC_XAPIC(apic_version[boot_cpu_physical_apicid]))
-		return;
 	/*
 	 * This is broken; anything with a real cpu count has to
 	 * circumvent this idiocy regardless.
@@ -2005,7 +1995,6 @@ void __init setup_ioapic_ids_from_mpc(void)
 			physids_or(phys_id_present_map, phys_id_present_map, tmp);
 		}
 
-
 		/*
 		 * We need to adjust the IRQ routing table
 		 * if the ID changed.
@@ -2041,6 +2030,21 @@ void __init setup_ioapic_ids_from_mpc(void)
 			apic_printk(APIC_VERBOSE, " ok.\n");
 	}
 }
+
+void __init setup_ioapic_ids_from_mpc(void)
+{
+
+	if (acpi_ioapic)
+		return;
+	/*
+	 * Don't check I/O APIC IDs for xAPIC systems.  They have
+	 * no meaning without the serial APIC bus.
+	 */
+	if (!(boot_cpu_data.x86_vendor == X86_VENDOR_INTEL)
+		|| APIC_XAPIC(apic_version[boot_cpu_physical_apicid]))
+		return;
+	setup_ioapic_ids_from_mpc_nocheck();
+}
 #endif
 
 int no_timer_check __initdata;
@@ -3593,7 +3597,7 @@ int __init io_apic_get_redir_entries (int ioapic)
 	return reg_01.bits.entries + 1;
 }
 
-void __init probe_nr_irqs_gsi(void)
+static void __init probe_nr_irqs_gsi(void)
 {
 	int nr;
 
@@ -3910,7 +3914,7 @@ static struct resource * __init ioapic_setup_resources(int nr_ioapics)
 	return res;
 }
 
-void __init ioapic_init_mappings(void)
+void __init ioapic_and_gsi_init(void)
 {
 	unsigned long ioapic_phys, idx = FIX_IO_APIC_BASE_0;
 	struct resource *ioapic_res;
@@ -3948,6 +3952,8 @@ fake_ioapic_page:
 		ioapic_res->end = ioapic_phys + IO_APIC_SLOT_SIZE - 1;
 		ioapic_res++;
 	}
+
+	probe_nr_irqs_gsi();
 }
 
 void __init ioapic_insert_resources(void)
@@ -4057,7 +4063,8 @@ void __init pre_init_apic_IRQ0(void)
 
 	printk(KERN_INFO "Early APIC setup for system timer0\n");
 #ifndef CONFIG_SMP
-	phys_cpu_present_map = physid_mask_of_physid(boot_cpu_physical_apicid);
+	physid_set_mask_of_physid(boot_cpu_physical_apicid,
+					 &phys_cpu_present_map);
 #endif
 	/* Make sure the irq descriptor is set up */
 	cfg = alloc_irq_and_cfg_at(0, 0);
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index 927902d90fe6..936613e77113 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -48,6 +48,16 @@ unsigned int uv_apicid_hibits;
 EXPORT_SYMBOL_GPL(uv_apicid_hibits);
 static DEFINE_SPINLOCK(uv_nmi_lock);
 
+static unsigned long __init uv_early_read_mmr(unsigned long addr)
+{
+	unsigned long val, *mmr;
+
+	mmr = early_ioremap(UV_LOCAL_MMR_BASE | addr, sizeof(*mmr));
+	val = *mmr;
+	early_iounmap(mmr, sizeof(*mmr));
+	return val;
+}
+
 static inline bool is_GRU_range(u64 start, u64 end)
 {
 	return start >= gru_start_paddr && end <= gru_end_paddr;
@@ -58,28 +68,24 @@ static bool uv_is_untracked_pat_range(u64 start, u64 end)
 	return is_ISA_range(start, end) || is_GRU_range(start, end);
 }
 
-static int early_get_nodeid(void)
+static int __init early_get_pnodeid(void)
 {
 	union uvh_node_id_u node_id;
-	unsigned long *mmr;
-
-	mmr = early_ioremap(UV_LOCAL_MMR_BASE | UVH_NODE_ID, sizeof(*mmr));
-	node_id.v = *mmr;
-	early_iounmap(mmr, sizeof(*mmr));
+	union uvh_rh_gam_config_mmr_u  m_n_config;
+	int pnode;
 
 	/* Currently, all blades have same revision number */
+	node_id.v = uv_early_read_mmr(UVH_NODE_ID);
+	m_n_config.v = uv_early_read_mmr(UVH_RH_GAM_CONFIG_MMR);
 	uv_min_hub_revision_id = node_id.s.revision;
 
-	return node_id.s.node_id;
+	pnode = (node_id.s.node_id >> 1) & ((1 << m_n_config.s.n_skt) - 1);
+	return pnode;
 }
 
 static void __init early_get_apic_pnode_shift(void)
 {
-	unsigned long *mmr;
-
-	mmr = early_ioremap(UV_LOCAL_MMR_BASE | UVH_APICID, sizeof(*mmr));
-	uvh_apicid.v = *mmr;
-	early_iounmap(mmr, sizeof(*mmr));
+	uvh_apicid.v = uv_early_read_mmr(UVH_APICID);
 	if (!uvh_apicid.v)
 		/*
 		 * Old bios, use default value
@@ -95,21 +101,17 @@ static void __init early_get_apic_pnode_shift(void)
 static void __init uv_set_apicid_hibit(void)
 {
 	union uvh_lb_target_physical_apic_id_mask_u apicid_mask;
-	unsigned long *mmr;
 
-	mmr = early_ioremap(UV_LOCAL_MMR_BASE |
-		UVH_LB_TARGET_PHYSICAL_APIC_ID_MASK, sizeof(*mmr));
-	apicid_mask.v = *mmr;
-	early_iounmap(mmr, sizeof(*mmr));
+	apicid_mask.v = uv_early_read_mmr(UVH_LB_TARGET_PHYSICAL_APIC_ID_MASK);
 	uv_apicid_hibits = apicid_mask.s.bit_enables & UV_APICID_HIBIT_MASK;
 }
 
 static int __init uv_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
 {
-	int nodeid;
+	int pnodeid;
 
 	if (!strcmp(oem_id, "SGI")) {
-		nodeid = early_get_nodeid();
+		pnodeid = early_get_pnodeid();
 		early_get_apic_pnode_shift();
 		x86_platform.is_untracked_pat_range =  uv_is_untracked_pat_range;
 		x86_platform.nmi_init = uv_nmi_init;
@@ -119,7 +121,7 @@ static int __init uv_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
 			uv_system_type = UV_X2APIC;
 		else if (!strcmp(oem_table_id, "UVH")) {
 			__get_cpu_var(x2apic_extra_bits) =
-				nodeid << (uvh_apicid.s.pnode_shift - 1);
+				pnodeid << uvh_apicid.s.pnode_shift;
 			uv_system_type = UV_NON_UNIQUE_APIC;
 			uv_set_apicid_hibit();
 			return 1;
@@ -682,27 +684,32 @@ void uv_nmi_init(void)
 void __init uv_system_init(void)
 {
 	union uvh_rh_gam_config_mmr_u  m_n_config;
+	union uvh_rh_gam_mmioh_overlay_config_mmr_u mmioh;
 	union uvh_node_id_u node_id;
 	unsigned long gnode_upper, lowmem_redir_base, lowmem_redir_size;
-	int bytes, nid, cpu, lcpu, pnode, blade, i, j, m_val, n_val;
+	int bytes, nid, cpu, lcpu, pnode, blade, i, j, m_val, n_val, n_io;
 	int gnode_extra, max_pnode = 0;
 	unsigned long mmr_base, present, paddr;
-	unsigned short pnode_mask;
+	unsigned short pnode_mask, pnode_io_mask;
 
 	map_low_mmrs();
 
 	m_n_config.v = uv_read_local_mmr(UVH_RH_GAM_CONFIG_MMR );
 	m_val = m_n_config.s.m_skt;
 	n_val = m_n_config.s.n_skt;
+	mmioh.v = uv_read_local_mmr(UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR);
+	n_io = mmioh.s.n_io;
 	mmr_base =
 	    uv_read_local_mmr(UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR) &
 	    ~UV_MMR_ENABLE;
 	pnode_mask = (1 << n_val) - 1;
+	pnode_io_mask = (1 << n_io) - 1;
+
 	node_id.v = uv_read_local_mmr(UVH_NODE_ID);
 	gnode_extra = (node_id.s.node_id & ~((1 << n_val) - 1)) >> 1;
 	gnode_upper = ((unsigned long)gnode_extra  << m_val);
-	printk(KERN_DEBUG "UV: N %d, M %d, gnode_upper 0x%lx, gnode_extra 0x%x\n",
-			n_val, m_val, gnode_upper, gnode_extra);
+	printk(KERN_INFO "UV: N %d, M %d, N_IO: %d, gnode_upper 0x%lx, gnode_extra 0x%x, pnode_mask 0x%x, pnode_io_mask 0x%x\n",
+			n_val, m_val, n_io, gnode_upper, gnode_extra, pnode_mask, pnode_io_mask);
 
 	printk(KERN_DEBUG "UV: global MMR base 0x%lx\n", mmr_base);
 
@@ -735,7 +742,7 @@ void __init uv_system_init(void)
 		for (j = 0; j < 64; j++) {
 			if (!test_bit(j, &present))
 				continue;
-			pnode = (i * 64 + j);
+			pnode = (i * 64 + j) & pnode_mask;
 			uv_blade_info[blade].pnode = pnode;
 			uv_blade_info[blade].nr_possible_cpus = 0;
 			uv_blade_info[blade].nr_online_cpus = 0;
@@ -756,6 +763,7 @@ void __init uv_system_init(void)
 		/*
 		 * apic_pnode_shift must be set before calling uv_apicid_to_pnode();
 		 */
+		uv_cpu_hub_info(cpu)->pnode_mask = pnode_mask;
 		uv_cpu_hub_info(cpu)->apic_pnode_shift = uvh_apicid.s.pnode_shift;
 		pnode = uv_apicid_to_pnode(apicid);
 		blade = boot_pnode_to_blade(pnode);
@@ -772,7 +780,6 @@ void __init uv_system_init(void)
 		uv_cpu_hub_info(cpu)->numa_blade_id = blade;
 		uv_cpu_hub_info(cpu)->blade_processor_id = lcpu;
 		uv_cpu_hub_info(cpu)->pnode = pnode;
-		uv_cpu_hub_info(cpu)->pnode_mask = pnode_mask;
 		uv_cpu_hub_info(cpu)->gpa_mask = (1UL << (m_val + n_val)) - 1;
 		uv_cpu_hub_info(cpu)->gnode_upper = gnode_upper;
 		uv_cpu_hub_info(cpu)->gnode_extra = gnode_extra;
@@ -796,7 +803,7 @@ void __init uv_system_init(void)
 
 	map_gru_high(max_pnode);
 	map_mmr_high(max_pnode);
-	map_mmioh_high(max_pnode);
+	map_mmioh_high(max_pnode & pnode_io_mask);
 
 	uv_cpu_init();
 	uv_scir_register_cpu_notifier();
diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
index 17ad03366211..9ecf81f9b90f 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -149,8 +149,7 @@ union _cpuid4_leaf_ecx {
 };
 
 struct amd_l3_cache {
-	struct	 pci_dev *dev;
-	bool	 can_disable;
+	struct	 amd_northbridge *nb;
 	unsigned indices;
 	u8	 subcaches[4];
 };
@@ -311,14 +310,12 @@ struct _cache_attr {
 /*
  * L3 cache descriptors
  */
-static struct amd_l3_cache **__cpuinitdata l3_caches;
-
 static void __cpuinit amd_calc_l3_indices(struct amd_l3_cache *l3)
 {
 	unsigned int sc0, sc1, sc2, sc3;
 	u32 val = 0;
 
-	pci_read_config_dword(l3->dev, 0x1C4, &val);
+	pci_read_config_dword(l3->nb->misc, 0x1C4, &val);
 
 	/* calculate subcache sizes */
 	l3->subcaches[0] = sc0 = !(val & BIT(0));
@@ -330,47 +327,14 @@ static void __cpuinit amd_calc_l3_indices(struct amd_l3_cache *l3)
 	l3->indices = (max(max3(sc0, sc1, sc2), sc3) << 10) - 1;
 }
 
-static struct amd_l3_cache * __cpuinit amd_init_l3_cache(int node)
-{
-	struct amd_l3_cache *l3;
-	struct pci_dev *dev = node_to_k8_nb_misc(node);
-
-	l3 = kzalloc(sizeof(struct amd_l3_cache), GFP_ATOMIC);
-	if (!l3) {
-		printk(KERN_WARNING "Error allocating L3 struct\n");
-		return NULL;
-	}
-
-	l3->dev = dev;
-
-	amd_calc_l3_indices(l3);
-
-	return l3;
-}
-
-static void __cpuinit amd_check_l3_disable(struct _cpuid4_info_regs *this_leaf,
-					   int index)
+static void __cpuinit amd_init_l3_cache(struct _cpuid4_info_regs *this_leaf,
+					int index)
 {
+	static struct amd_l3_cache *__cpuinitdata l3_caches;
 	int node;
 
-	if (boot_cpu_data.x86 != 0x10)
-		return;
-
-	if (index < 3)
-		return;
-
-	/* see errata #382 and #388 */
-	if (boot_cpu_data.x86_model < 0x8)
-		return;
-
-	if ((boot_cpu_data.x86_model == 0x8 ||
-	     boot_cpu_data.x86_model == 0x9)
-		&&
-	     boot_cpu_data.x86_mask < 0x1)
-			return;
-
-	/* not in virtualized environments */
-	if (k8_northbridges.num == 0)
+	/* only for L3, and not in virtualized environments */
+	if (index < 3 || amd_nb_num() == 0)
 		return;
 
 	/*
@@ -378,7 +342,7 @@ static void __cpuinit amd_check_l3_disable(struct _cpuid4_info_regs *this_leaf,
 	 * never freed but this is done only on shutdown so it doesn't matter.
 	 */
 	if (!l3_caches) {
-		int size = k8_northbridges.num * sizeof(struct amd_l3_cache *);
+		int size = amd_nb_num() * sizeof(struct amd_l3_cache);
 
 		l3_caches = kzalloc(size, GFP_ATOMIC);
 		if (!l3_caches)
@@ -387,14 +351,12 @@ static void __cpuinit amd_check_l3_disable(struct _cpuid4_info_regs *this_leaf,
 
 	node = amd_get_nb_id(smp_processor_id());
 
-	if (!l3_caches[node]) {
-		l3_caches[node] = amd_init_l3_cache(node);
-		l3_caches[node]->can_disable = true;
+	if (!l3_caches[node].nb) {
+		l3_caches[node].nb = node_to_amd_nb(node);
+		amd_calc_l3_indices(&l3_caches[node]);
 	}
 
-	WARN_ON(!l3_caches[node]);
-
-	this_leaf->l3 = l3_caches[node];
+	this_leaf->l3 = &l3_caches[node];
 }
 
 /*
@@ -408,7 +370,7 @@ int amd_get_l3_disable_slot(struct amd_l3_cache *l3, unsigned slot)
 {
 	unsigned int reg = 0;
 
-	pci_read_config_dword(l3->dev, 0x1BC + slot * 4, &reg);
+	pci_read_config_dword(l3->nb->misc, 0x1BC + slot * 4, &reg);
 
 	/* check whether this slot is activated already */
 	if (reg & (3UL << 30))
@@ -422,7 +384,8 @@ static ssize_t show_cache_disable(struct _cpuid4_info *this_leaf, char *buf,
 {
 	int index;
 
-	if (!this_leaf->l3 || !this_leaf->l3->can_disable)
+	if (!this_leaf->l3 ||
+	    !amd_nb_has_feature(AMD_NB_L3_INDEX_DISABLE))
 		return -EINVAL;
 
 	index = amd_get_l3_disable_slot(this_leaf->l3, slot);
@@ -457,7 +420,7 @@ static void amd_l3_disable_index(struct amd_l3_cache *l3, int cpu,
 		if (!l3->subcaches[i])
 			continue;
 
-		pci_write_config_dword(l3->dev, 0x1BC + slot * 4, reg);
+		pci_write_config_dword(l3->nb->misc, 0x1BC + slot * 4, reg);
 
 		/*
 		 * We need to WBINVD on a core on the node containing the L3
@@ -467,7 +430,7 @@ static void amd_l3_disable_index(struct amd_l3_cache *l3, int cpu,
 		wbinvd_on_cpu(cpu);
 
 		reg |= BIT(31);
-		pci_write_config_dword(l3->dev, 0x1BC + slot * 4, reg);
+		pci_write_config_dword(l3->nb->misc, 0x1BC + slot * 4, reg);
 	}
 }
 
@@ -524,7 +487,8 @@ static ssize_t store_cache_disable(struct _cpuid4_info *this_leaf,
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
-	if (!this_leaf->l3 || !this_leaf->l3->can_disable)
+	if (!this_leaf->l3 ||
+	    !amd_nb_has_feature(AMD_NB_L3_INDEX_DISABLE))
 		return -EINVAL;
 
 	cpu = cpumask_first(to_cpumask(this_leaf->shared_cpu_map));
@@ -545,7 +509,7 @@ static ssize_t store_cache_disable(struct _cpuid4_info *this_leaf,
 #define STORE_CACHE_DISABLE(slot)					\
 static ssize_t								\
 store_cache_disable_##slot(struct _cpuid4_info *this_leaf,		\
-			    const char *buf, size_t count)		\
+			   const char *buf, size_t count)		\
 {									\
 	return store_cache_disable(this_leaf, buf, count, slot);	\
 }
@@ -558,10 +522,7 @@ static struct _cache_attr cache_disable_1 = __ATTR(cache_disable_1, 0644,
 		show_cache_disable_1, store_cache_disable_1);
 
 #else	/* CONFIG_AMD_NB */
-static void __cpuinit
-amd_check_l3_disable(struct _cpuid4_info_regs *this_leaf, int index)
-{
-};
+#define amd_init_l3_cache(x, y)
 #endif /* CONFIG_AMD_NB */
 
 static int
@@ -575,7 +536,7 @@ __cpuinit cpuid4_cache_lookup_regs(int index,
 
 	if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) {
 		amd_cpuid4(index, &eax, &ebx, &ecx);
-		amd_check_l3_disable(this_leaf, index);
+		amd_init_l3_cache(this_leaf, index);
 	} else {
 		cpuid_count(4, index, &eax.full, &ebx.full, &ecx.full, &edx);
 	}
@@ -983,30 +944,48 @@ define_one_ro(size);
 define_one_ro(shared_cpu_map);
 define_one_ro(shared_cpu_list);
 
-#define DEFAULT_SYSFS_CACHE_ATTRS	\
-	&type.attr,			\
-	&level.attr,			\
-	&coherency_line_size.attr,	\
-	&physical_line_partition.attr,	\
-	&ways_of_associativity.attr,	\
-	&number_of_sets.attr,		\
-	&size.attr,			\
-	&shared_cpu_map.attr,		\
-	&shared_cpu_list.attr
-
 static struct attribute *default_attrs[] = {
-	DEFAULT_SYSFS_CACHE_ATTRS,
+	&type.attr,
+	&level.attr,
+	&coherency_line_size.attr,
+	&physical_line_partition.attr,
+	&ways_of_associativity.attr,
+	&number_of_sets.attr,
+	&size.attr,
+	&shared_cpu_map.attr,
+	&shared_cpu_list.attr,
 	NULL
 };
 
-static struct attribute *default_l3_attrs[] = {
-	DEFAULT_SYSFS_CACHE_ATTRS,
 #ifdef CONFIG_AMD_NB
-	&cache_disable_0.attr,
-	&cache_disable_1.attr,
+static struct attribute ** __cpuinit amd_l3_attrs(void)
+{
+	static struct attribute **attrs;
+	int n;
+
+	if (attrs)
+		return attrs;
+
+	n = sizeof (default_attrs) / sizeof (struct attribute *);
+
+	if (amd_nb_has_feature(AMD_NB_L3_INDEX_DISABLE))
+		n += 2;
+
+	attrs = kzalloc(n * sizeof (struct attribute *), GFP_KERNEL);
+	if (attrs == NULL)
+		return attrs = default_attrs;
+
+	for (n = 0; default_attrs[n]; n++)
+		attrs[n] = default_attrs[n];
+
+	if (amd_nb_has_feature(AMD_NB_L3_INDEX_DISABLE)) {
+		attrs[n++] = &cache_disable_0.attr;
+		attrs[n++] = &cache_disable_1.attr;
+	}
+
+	return attrs;
+}
 #endif
-	NULL
-};
 
 static ssize_t show(struct kobject *kobj, struct attribute *attr, char *buf)
 {
@@ -1117,11 +1096,11 @@ static int __cpuinit cache_add_dev(struct sys_device * sys_dev)
 
 		this_leaf = CPUID4_INFO_IDX(cpu, i);
 
-		if (this_leaf->l3 && this_leaf->l3->can_disable)
-			ktype_cache.default_attrs = default_l3_attrs;
-		else
-			ktype_cache.default_attrs = default_attrs;
-
+		ktype_cache.default_attrs = default_attrs;
+#ifdef CONFIG_AMD_NB
+		if (this_leaf->l3)
+			ktype_cache.default_attrs = amd_l3_attrs();
+#endif
 		retval = kobject_init_and_add(&(this_object->kobj),
 					      &ktype_cache,
 					      per_cpu(ici_cache_kobject, cpu),
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index 80c482382d5c..5bf2fac52aca 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -31,8 +31,6 @@
 #include <asm/mce.h>
 #include <asm/msr.h>
 
-#define PFX               "mce_threshold: "
-#define VERSION           "version 1.1.1"
 #define NR_BANKS          6
 #define NR_BLOCKS         9
 #define THRESHOLD_MAX     0xFFF
@@ -59,12 +57,6 @@ struct threshold_block {
 	struct list_head	miscj;
 };
 
-/* defaults used early on boot */
-static struct threshold_block threshold_defaults = {
-	.interrupt_enable	= 0,
-	.threshold_limit	= THRESHOLD_MAX,
-};
-
 struct threshold_bank {
 	struct kobject		*kobj;
 	struct threshold_block	*blocks;
@@ -89,50 +81,101 @@ static void amd_threshold_interrupt(void);
 struct thresh_restart {
 	struct threshold_block	*b;
 	int			reset;
+	int			set_lvt_off;
+	int			lvt_off;
 	u16			old_limit;
 };
 
+static int lvt_off_valid(struct threshold_block *b, int apic, u32 lo, u32 hi)
+{
+	int msr = (hi & MASK_LVTOFF_HI) >> 20;
+
+	if (apic < 0) {
+		pr_err(FW_BUG "cpu %d, failed to setup threshold interrupt "
+		       "for bank %d, block %d (MSR%08X=0x%x%08x)\n", b->cpu,
+		       b->bank, b->block, b->address, hi, lo);
+		return 0;
+	}
+
+	if (apic != msr) {
+		pr_err(FW_BUG "cpu %d, invalid threshold interrupt offset %d "
+		       "for bank %d, block %d (MSR%08X=0x%x%08x)\n",
+		       b->cpu, apic, b->bank, b->block, b->address, hi, lo);
+		return 0;
+	}
+
+	return 1;
+};
+
 /* must be called with correct cpu affinity */
 /* Called via smp_call_function_single() */
 static void threshold_restart_bank(void *_tr)
 {
 	struct thresh_restart *tr = _tr;
-	u32 mci_misc_hi, mci_misc_lo;
+	u32 hi, lo;
 
-	rdmsr(tr->b->address, mci_misc_lo, mci_misc_hi);
+	rdmsr(tr->b->address, lo, hi);
 
-	if (tr->b->threshold_limit < (mci_misc_hi & THRESHOLD_MAX))
+	if (tr->b->threshold_limit < (hi & THRESHOLD_MAX))
 		tr->reset = 1;	/* limit cannot be lower than err count */
 
 	if (tr->reset) {		/* reset err count and overflow bit */
-		mci_misc_hi =
-		    (mci_misc_hi & ~(MASK_ERR_COUNT_HI | MASK_OVERFLOW_HI)) |
+		hi =
+		    (hi & ~(MASK_ERR_COUNT_HI | MASK_OVERFLOW_HI)) |
 		    (THRESHOLD_MAX - tr->b->threshold_limit);
 	} else if (tr->old_limit) {	/* change limit w/o reset */
-		int new_count = (mci_misc_hi & THRESHOLD_MAX) +
+		int new_count = (hi & THRESHOLD_MAX) +
 		    (tr->old_limit - tr->b->threshold_limit);
 
-		mci_misc_hi = (mci_misc_hi & ~MASK_ERR_COUNT_HI) |
+		hi = (hi & ~MASK_ERR_COUNT_HI) |
 		    (new_count & THRESHOLD_MAX);
 	}
 
+	if (tr->set_lvt_off) {
+		if (lvt_off_valid(tr->b, tr->lvt_off, lo, hi)) {
+			/* set new lvt offset */
+			hi &= ~MASK_LVTOFF_HI;
+			hi |= tr->lvt_off << 20;
+		}
+	}
+
 	tr->b->interrupt_enable ?
-	    (mci_misc_hi = (mci_misc_hi & ~MASK_INT_TYPE_HI) | INT_TYPE_APIC) :
-	    (mci_misc_hi &= ~MASK_INT_TYPE_HI);
+	    (hi = (hi & ~MASK_INT_TYPE_HI) | INT_TYPE_APIC) :
+	    (hi &= ~MASK_INT_TYPE_HI);
 
-	mci_misc_hi |= MASK_COUNT_EN_HI;
-	wrmsr(tr->b->address, mci_misc_lo, mci_misc_hi);
+	hi |= MASK_COUNT_EN_HI;
+	wrmsr(tr->b->address, lo, hi);
+}
+
+static void mce_threshold_block_init(struct threshold_block *b, int offset)
+{
+	struct thresh_restart tr = {
+		.b			= b,
+		.set_lvt_off		= 1,
+		.lvt_off		= offset,
+	};
+
+	b->threshold_limit		= THRESHOLD_MAX;
+	threshold_restart_bank(&tr);
+};
+
+static int setup_APIC_mce(int reserved, int new)
+{
+	if (reserved < 0 && !setup_APIC_eilvt(new, THRESHOLD_APIC_VECTOR,
+					      APIC_EILVT_MSG_FIX, 0))
+		return new;
+
+	return reserved;
 }
 
 /* cpu init entry point, called from mce.c with preempt off */
 void mce_amd_feature_init(struct cpuinfo_x86 *c)
 {
+	struct threshold_block b;
 	unsigned int cpu = smp_processor_id();
 	u32 low = 0, high = 0, address = 0;
 	unsigned int bank, block;
-	struct thresh_restart tr;
-	int lvt_off = -1;
-	u8 offset;
+	int offset = -1;
 
 	for (bank = 0; bank < NR_BANKS; ++bank) {
 		for (block = 0; block < NR_BLOCKS; ++block) {
@@ -163,39 +206,16 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c)
 			if (shared_bank[bank] && c->cpu_core_id)
 				break;
 #endif
-			offset = (high & MASK_LVTOFF_HI) >> 20;
-			if (lvt_off < 0) {
-				if (setup_APIC_eilvt(offset,
-						     THRESHOLD_APIC_VECTOR,
-						     APIC_EILVT_MSG_FIX, 0)) {
-					pr_err(FW_BUG "cpu %d, failed to "
-					       "setup threshold interrupt "
-					       "for bank %d, block %d "
-					       "(MSR%08X=0x%x%08x)",
-					       smp_processor_id(), bank, block,
-					       address, high, low);
-					continue;
-				}
-				lvt_off = offset;
-			} else if (lvt_off != offset) {
-				pr_err(FW_BUG "cpu %d, invalid threshold "
-				       "interrupt offset %d for bank %d,"
-				       "block %d (MSR%08X=0x%x%08x)",
-				       smp_processor_id(), lvt_off, bank,
-				       block, address, high, low);
-				continue;
-			}
-
-			high &= ~MASK_LVTOFF_HI;
-			high |= lvt_off << 20;
-			wrmsr(address, low, high);
+			offset = setup_APIC_mce(offset,
+						(high & MASK_LVTOFF_HI) >> 20);
 
-			threshold_defaults.address = address;
-			tr.b = &threshold_defaults;
-			tr.reset = 0;
-			tr.old_limit = 0;
-			threshold_restart_bank(&tr);
+			memset(&b, 0, sizeof(b));
+			b.cpu		= cpu;
+			b.bank		= bank;
+			b.block		= block;
+			b.address	= address;
 
+			mce_threshold_block_init(&b, offset);
 			mce_threshold_vector = amd_threshold_interrupt;
 		}
 	}
@@ -298,9 +318,8 @@ store_interrupt_enable(struct threshold_block *b, const char *buf, size_t size)
 
 	b->interrupt_enable = !!new;
 
+	memset(&tr, 0, sizeof(tr));
 	tr.b		= b;
-	tr.reset	= 0;
-	tr.old_limit	= 0;
 
 	smp_call_function_single(b->cpu, threshold_restart_bank, &tr, 1);
 
@@ -321,10 +340,10 @@ store_threshold_limit(struct threshold_block *b, const char *buf, size_t size)
 	if (new < 1)
 		new = 1;
 
+	memset(&tr, 0, sizeof(tr));
 	tr.old_limit = b->threshold_limit;
 	b->threshold_limit = new;
 	tr.b = b;
-	tr.reset = 0;
 
 	smp_call_function_single(b->cpu, threshold_restart_bank, &tr, 1);
 
@@ -603,9 +622,9 @@ static __cpuinit int threshold_create_device(unsigned int cpu)
 			continue;
 		err = threshold_create_bank(cpu, bank);
 		if (err)
-			goto out;
+			return err;
 	}
-out:
+
 	return err;
 }
 
diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c
index 4b683267eca5..e12246ff5aa6 100644
--- a/arch/x86/kernel/cpu/mcheck/therm_throt.c
+++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c
@@ -53,8 +53,13 @@ struct thermal_state {
 	struct _thermal_state core_power_limit;
 	struct _thermal_state package_throttle;
 	struct _thermal_state package_power_limit;
+	struct _thermal_state core_thresh0;
+	struct _thermal_state core_thresh1;
 };
 
+/* Callback to handle core threshold interrupts */
+int (*platform_thermal_notify)(__u64 msr_val);
+
 static DEFINE_PER_CPU(struct thermal_state, thermal_state);
 
 static atomic_t therm_throt_en	= ATOMIC_INIT(0);
@@ -200,6 +205,22 @@ static int therm_throt_process(bool new_event, int event, int level)
 	return 0;
 }
 
+static int thresh_event_valid(int event)
+{
+	struct _thermal_state *state;
+	unsigned int this_cpu = smp_processor_id();
+	struct thermal_state *pstate = &per_cpu(thermal_state, this_cpu);
+	u64 now = get_jiffies_64();
+
+	state = (event == 0) ? &pstate->core_thresh0 : &pstate->core_thresh1;
+
+	if (time_before64(now, state->next_check))
+		return 0;
+
+	state->next_check = now + CHECK_INTERVAL;
+	return 1;
+}
+
 #ifdef CONFIG_SYSFS
 /* Add/Remove thermal_throttle interface for CPU device: */
 static __cpuinit int thermal_throttle_add_dev(struct sys_device *sys_dev,
@@ -313,6 +334,22 @@ device_initcall(thermal_throttle_init_device);
 #define PACKAGE_THROTTLED	((__u64)2 << 62)
 #define PACKAGE_POWER_LIMIT	((__u64)3 << 62)
 
+static void notify_thresholds(__u64 msr_val)
+{
+	/* check whether the interrupt handler is defined;
+	 * otherwise simply return
+	 */
+	if (!platform_thermal_notify)
+		return;
+
+	/* lower threshold reached */
+	if ((msr_val & THERM_LOG_THRESHOLD0) &&	thresh_event_valid(0))
+		platform_thermal_notify(msr_val);
+	/* higher threshold reached */
+	if ((msr_val & THERM_LOG_THRESHOLD1) && thresh_event_valid(1))
+		platform_thermal_notify(msr_val);
+}
+
 /* Thermal transition interrupt handler */
 static void intel_thermal_interrupt(void)
 {
@@ -321,6 +358,9 @@ static void intel_thermal_interrupt(void)
 
 	rdmsrl(MSR_IA32_THERM_STATUS, msr_val);
 
+	/* Check for violation of core thermal thresholds*/
+	notify_thresholds(msr_val);
+
 	if (therm_throt_process(msr_val & THERM_STATUS_PROCHOT,
 				THERMAL_THROTTLING_EVENT,
 				CORE_LEVEL) != 0)
diff --git a/arch/x86/kernel/early_printk.c b/arch/x86/kernel/early_printk.c
index 4572f25f9325..cd28a350f7f9 100644
--- a/arch/x86/kernel/early_printk.c
+++ b/arch/x86/kernel/early_printk.c
@@ -240,7 +240,7 @@ static int __init setup_early_printk(char *buf)
 		if (!strncmp(buf, "xen", 3))
 			early_console_register(&xenboot_console, keep);
 #endif
-#ifdef CONFIG_X86_MRST_EARLY_PRINTK
+#ifdef CONFIG_EARLY_PRINTK_MRST
 		if (!strncmp(buf, "mrst", 4)) {
 			mrst_early_console_init();
 			early_console_register(&early_mrst_console, keep);
@@ -250,7 +250,6 @@ static int __init setup_early_printk(char *buf)
 			hsu_early_console_init();
 			early_console_register(&early_hsu_console, keep);
 		}
-
 #endif
 		buf++;
 	}
diff --git a/arch/x86/kernel/early_printk_mrst.c b/arch/x86/kernel/early_printk_mrst.c
deleted file mode 100644
index 65df603622b2..000000000000
--- a/arch/x86/kernel/early_printk_mrst.c
+++ /dev/null
@@ -1,319 +0,0 @@
-/*
- * early_printk_mrst.c - early consoles for Intel MID platforms
- *
- * Copyright (c) 2008-2010, Intel Corporation
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; version 2
- * of the License.
- */
-
-/*
- * This file implements two early consoles named mrst and hsu.
- * mrst is based on Maxim3110 spi-uart device, it exists in both
- * Moorestown and Medfield platforms, while hsu is based on a High
- * Speed UART device which only exists in the Medfield platform
- */
-
-#include <linux/serial_reg.h>
-#include <linux/serial_mfd.h>
-#include <linux/kmsg_dump.h>
-#include <linux/console.h>
-#include <linux/kernel.h>
-#include <linux/delay.h>
-#include <linux/init.h>
-#include <linux/io.h>
-
-#include <asm/fixmap.h>
-#include <asm/pgtable.h>
-#include <asm/mrst.h>
-
-#define MRST_SPI_TIMEOUT		0x200000
-#define MRST_REGBASE_SPI0		0xff128000
-#define MRST_REGBASE_SPI1		0xff128400
-#define MRST_CLK_SPI0_REG		0xff11d86c
-
-/* Bit fields in CTRLR0 */
-#define SPI_DFS_OFFSET			0
-
-#define SPI_FRF_OFFSET			4
-#define SPI_FRF_SPI			0x0
-#define SPI_FRF_SSP			0x1
-#define SPI_FRF_MICROWIRE		0x2
-#define SPI_FRF_RESV			0x3
-
-#define SPI_MODE_OFFSET			6
-#define SPI_SCPH_OFFSET			6
-#define SPI_SCOL_OFFSET			7
-#define SPI_TMOD_OFFSET			8
-#define	SPI_TMOD_TR			0x0		/* xmit & recv */
-#define SPI_TMOD_TO			0x1		/* xmit only */
-#define SPI_TMOD_RO			0x2		/* recv only */
-#define SPI_TMOD_EPROMREAD		0x3		/* eeprom read mode */
-
-#define SPI_SLVOE_OFFSET		10
-#define SPI_SRL_OFFSET			11
-#define SPI_CFS_OFFSET			12
-
-/* Bit fields in SR, 7 bits */
-#define SR_MASK				0x7f		/* cover 7 bits */
-#define SR_BUSY				(1 << 0)
-#define SR_TF_NOT_FULL			(1 << 1)
-#define SR_TF_EMPT			(1 << 2)
-#define SR_RF_NOT_EMPT			(1 << 3)
-#define SR_RF_FULL			(1 << 4)
-#define SR_TX_ERR			(1 << 5)
-#define SR_DCOL				(1 << 6)
-
-struct dw_spi_reg {
-	u32	ctrl0;
-	u32	ctrl1;
-	u32	ssienr;
-	u32	mwcr;
-	u32	ser;
-	u32	baudr;
-	u32	txfltr;
-	u32	rxfltr;
-	u32	txflr;
-	u32	rxflr;
-	u32	sr;
-	u32	imr;
-	u32	isr;
-	u32	risr;
-	u32	txoicr;
-	u32	rxoicr;
-	u32	rxuicr;
-	u32	msticr;
-	u32	icr;
-	u32	dmacr;
-	u32	dmatdlr;
-	u32	dmardlr;
-	u32	idr;
-	u32	version;
-
-	/* Currently operates as 32 bits, though only the low 16 bits matter */
-	u32	dr;
-} __packed;
-
-#define dw_readl(dw, name)		__raw_readl(&(dw)->name)
-#define dw_writel(dw, name, val)	__raw_writel((val), &(dw)->name)
-
-/* Default use SPI0 register for mrst, we will detect Penwell and use SPI1 */
-static unsigned long mrst_spi_paddr = MRST_REGBASE_SPI0;
-
-static u32 *pclk_spi0;
-/* Always contains an accessable address, start with 0 */
-static struct dw_spi_reg *pspi;
-
-static struct kmsg_dumper dw_dumper;
-static int dumper_registered;
-
-static void dw_kmsg_dump(struct kmsg_dumper *dumper,
-			enum kmsg_dump_reason reason,
-			const char *s1, unsigned long l1,
-			const char *s2, unsigned long l2)
-{
-	int i;
-
-	/* When run to this, we'd better re-init the HW */
-	mrst_early_console_init();
-
-	for (i = 0; i < l1; i++)
-		early_mrst_console.write(&early_mrst_console, s1 + i, 1);
-	for (i = 0; i < l2; i++)
-		early_mrst_console.write(&early_mrst_console, s2 + i, 1);
-}
-
-/* Set the ratio rate to 115200, 8n1, IRQ disabled */
-static void max3110_write_config(void)
-{
-	u16 config;
-
-	config = 0xc001;
-	dw_writel(pspi, dr, config);
-}
-
-/* Translate char to a eligible word and send to max3110 */
-static void max3110_write_data(char c)
-{
-	u16 data;
-
-	data = 0x8000 | c;
-	dw_writel(pspi, dr, data);
-}
-
-void mrst_early_console_init(void)
-{
-	u32 ctrlr0 = 0;
-	u32 spi0_cdiv;
-	u32 freq; /* Freqency info only need be searched once */
-
-	/* Base clk is 100 MHz, the actual clk = 100M / (clk_divider + 1) */
-	pclk_spi0 = (void *)set_fixmap_offset_nocache(FIX_EARLYCON_MEM_BASE,
-							MRST_CLK_SPI0_REG);
-	spi0_cdiv = ((*pclk_spi0) & 0xe00) >> 9;
-	freq = 100000000 / (spi0_cdiv + 1);
-
-	if (mrst_identify_cpu() == MRST_CPU_CHIP_PENWELL)
-		mrst_spi_paddr = MRST_REGBASE_SPI1;
-
-	pspi = (void *)set_fixmap_offset_nocache(FIX_EARLYCON_MEM_BASE,
-						mrst_spi_paddr);
-
-	/* Disable SPI controller */
-	dw_writel(pspi, ssienr, 0);
-
-	/* Set control param, 8 bits, transmit only mode */
-	ctrlr0 = dw_readl(pspi, ctrl0);
-
-	ctrlr0 &= 0xfcc0;
-	ctrlr0 |= 0xf | (SPI_FRF_SPI << SPI_FRF_OFFSET)
-		      | (SPI_TMOD_TO << SPI_TMOD_OFFSET);
-	dw_writel(pspi, ctrl0, ctrlr0);
-
-	/*
-	 * Change the spi0 clk to comply with 115200 bps, use 100000 to
-	 * calculate the clk dividor to make the clock a little slower
-	 * than real baud rate.
-	 */
-	dw_writel(pspi, baudr, freq/100000);
-
-	/* Disable all INT for early phase */
-	dw_writel(pspi, imr, 0x0);
-
-	/* Set the cs to spi-uart */
-	dw_writel(pspi, ser, 0x2);
-
-	/* Enable the HW, the last step for HW init */
-	dw_writel(pspi, ssienr, 0x1);
-
-	/* Set the default configuration */
-	max3110_write_config();
-
-	/* Register the kmsg dumper */
-	if (!dumper_registered) {
-		dw_dumper.dump = dw_kmsg_dump;
-		kmsg_dump_register(&dw_dumper);
-		dumper_registered = 1;
-	}
-}
-
-/* Slave select should be called in the read/write function */
-static void early_mrst_spi_putc(char c)
-{
-	unsigned int timeout;
-	u32 sr;
-
-	timeout = MRST_SPI_TIMEOUT;
-	/* Early putc needs to make sure the TX FIFO is not full */
-	while (--timeout) {
-		sr = dw_readl(pspi, sr);
-		if (!(sr & SR_TF_NOT_FULL))
-			cpu_relax();
-		else
-			break;
-	}
-
-	if (!timeout)
-		pr_warning("MRST earlycon: timed out\n");
-	else
-		max3110_write_data(c);
-}
-
-/* Early SPI only uses polling mode */
-static void early_mrst_spi_write(struct console *con, const char *str, unsigned n)
-{
-	int i;
-
-	for (i = 0; i < n && *str; i++) {
-		if (*str == '\n')
-			early_mrst_spi_putc('\r');
-		early_mrst_spi_putc(*str);
-		str++;
-	}
-}
-
-struct console early_mrst_console = {
-	.name =		"earlymrst",
-	.write =	early_mrst_spi_write,
-	.flags =	CON_PRINTBUFFER,
-	.index =	-1,
-};
-
-/*
- * Following is the early console based on Medfield HSU (High
- * Speed UART) device.
- */
-#define HSU_PORT2_PADDR		0xffa28180
-
-static void __iomem *phsu;
-
-void hsu_early_console_init(void)
-{
-	u8 lcr;
-
-	phsu = (void *)set_fixmap_offset_nocache(FIX_EARLYCON_MEM_BASE,
-							HSU_PORT2_PADDR);
-
-	/* Disable FIFO */
-	writeb(0x0, phsu + UART_FCR);
-
-	/* Set to default 115200 bps, 8n1 */
-	lcr = readb(phsu + UART_LCR);
-	writeb((0x80 | lcr), phsu + UART_LCR);
-	writeb(0x18, phsu + UART_DLL);
-	writeb(lcr,  phsu + UART_LCR);
-	writel(0x3600, phsu + UART_MUL*4);
-
-	writeb(0x8, phsu + UART_MCR);
-	writeb(0x7, phsu + UART_FCR);
-	writeb(0x3, phsu + UART_LCR);
-
-	/* Clear IRQ status */
-	readb(phsu + UART_LSR);
-	readb(phsu + UART_RX);
-	readb(phsu + UART_IIR);
-	readb(phsu + UART_MSR);
-
-	/* Enable FIFO */
-	writeb(0x7, phsu + UART_FCR);
-}
-
-#define BOTH_EMPTY (UART_LSR_TEMT | UART_LSR_THRE)
-
-static void early_hsu_putc(char ch)
-{
-	unsigned int timeout = 10000; /* 10ms */
-	u8 status;
-
-	while (--timeout) {
-		status = readb(phsu + UART_LSR);
-		if (status & BOTH_EMPTY)
-			break;
-		udelay(1);
-	}
-
-	/* Only write the char when there was no timeout */
-	if (timeout)
-		writeb(ch, phsu + UART_TX);
-}
-
-static void early_hsu_write(struct console *con, const char *str, unsigned n)
-{
-	int i;
-
-	for (i = 0; i < n && *str; i++) {
-		if (*str == '\n')
-			early_hsu_putc('\r');
-		early_hsu_putc(*str);
-		str++;
-	}
-}
-
-struct console early_hsu_console = {
-	.name =		"earlyhsu",
-	.write =	early_hsu_write,
-	.flags =	CON_PRINTBUFFER,
-	.index =	-1,
-};
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 3afb33f14d2d..298448656b60 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -19,6 +19,7 @@
 #include <linux/sched.h>
 #include <linux/init.h>
 #include <linux/list.h>
+#include <linux/module.h>
 
 #include <trace/syscall.h>
 
@@ -49,6 +50,7 @@ static DEFINE_PER_CPU(int, save_modifying_code);
 int ftrace_arch_code_modify_prepare(void)
 {
 	set_kernel_text_rw();
+	set_all_modules_text_rw();
 	modifying_code = 1;
 	return 0;
 }
@@ -56,6 +58,7 @@ int ftrace_arch_code_modify_prepare(void)
 int ftrace_arch_code_modify_post_process(void)
 {
 	modifying_code = 0;
+	set_all_modules_text_ro();
 	set_kernel_text_ro();
 	return 0;
 }
diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c
index 763310165fa0..7f138b3c3c52 100644
--- a/arch/x86/kernel/head32.c
+++ b/arch/x86/kernel/head32.c
@@ -61,6 +61,9 @@ void __init i386_start_kernel(void)
 	case X86_SUBARCH_MRST:
 		x86_mrst_early_setup();
 		break;
+	case X86_SUBARCH_CE4100:
+		x86_ce4100_early_setup();
+		break;
 	default:
 		i386_default_early_setup();
 		break;
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index c0dbd9ac24f0..9f54b209c378 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -139,39 +139,6 @@ ENTRY(startup_32)
 	movl %eax, pa(olpc_ofw_pgd)
 #endif
 
-#ifdef CONFIG_PARAVIRT
-	/* This is can only trip for a broken bootloader... */
-	cmpw $0x207, pa(boot_params + BP_version)
-	jb default_entry
-
-	/* Paravirt-compatible boot parameters.  Look to see what architecture
-		we're booting under. */
-	movl pa(boot_params + BP_hardware_subarch), %eax
-	cmpl $num_subarch_entries, %eax
-	jae bad_subarch
-
-	movl pa(subarch_entries)(,%eax,4), %eax
-	subl $__PAGE_OFFSET, %eax
-	jmp *%eax
-
-bad_subarch:
-WEAK(lguest_entry)
-WEAK(xen_entry)
-	/* Unknown implementation; there's really
-	   nothing we can do at this point. */
-	ud2a
-
-	__INITDATA
-
-subarch_entries:
-	.long default_entry		/* normal x86/PC */
-	.long lguest_entry		/* lguest hypervisor */
-	.long xen_entry			/* Xen hypervisor */
-	.long default_entry		/* Moorestown MID */
-num_subarch_entries = (. - subarch_entries) / 4
-.previous
-#endif /* CONFIG_PARAVIRT */
-
 /*
  * Initialize page tables.  This creates a PDE and a set of page
  * tables, which are located immediately beyond __brk_base.  The variable
@@ -181,7 +148,6 @@ num_subarch_entries = (. - subarch_entries) / 4
  *
  * Note that the stack is not yet set up!
  */
-default_entry:
 #ifdef CONFIG_X86_PAE
 
 	/*
@@ -261,7 +227,42 @@ page_pde_offset = (__PAGE_OFFSET >> 20);
 	movl $pa(initial_pg_fixmap)+PDE_IDENT_ATTR,%eax
 	movl %eax,pa(initial_page_table+0xffc)
 #endif
-	jmp 3f
+
+#ifdef CONFIG_PARAVIRT
+	/* This is can only trip for a broken bootloader... */
+	cmpw $0x207, pa(boot_params + BP_version)
+	jb default_entry
+
+	/* Paravirt-compatible boot parameters.  Look to see what architecture
+		we're booting under. */
+	movl pa(boot_params + BP_hardware_subarch), %eax
+	cmpl $num_subarch_entries, %eax
+	jae bad_subarch
+
+	movl pa(subarch_entries)(,%eax,4), %eax
+	subl $__PAGE_OFFSET, %eax
+	jmp *%eax
+
+bad_subarch:
+WEAK(lguest_entry)
+WEAK(xen_entry)
+	/* Unknown implementation; there's really
+	   nothing we can do at this point. */
+	ud2a
+
+	__INITDATA
+
+subarch_entries:
+	.long default_entry		/* normal x86/PC */
+	.long lguest_entry		/* lguest hypervisor */
+	.long xen_entry			/* Xen hypervisor */
+	.long default_entry		/* Moorestown MID */
+num_subarch_entries = (. - subarch_entries) / 4
+.previous
+#else
+	jmp default_entry
+#endif /* CONFIG_PARAVIRT */
+
 /*
  * Non-boot CPU entry point; entered from trampoline.S
  * We can't lgdt here, because lgdt itself uses a data segment, but
@@ -282,7 +283,7 @@ ENTRY(startup_32_smp)
 	movl %eax,%fs
 	movl %eax,%gs
 #endif /* CONFIG_SMP */
-3:
+default_entry:
 
 /*
  *	New page tables may be in 4Mbyte page mode and may
@@ -316,6 +317,10 @@ ENTRY(startup_32_smp)
 	subl $0x80000001, %eax
 	cmpl $(0x8000ffff-0x80000001), %eax
 	ja 6f
+
+	/* Clear bogus XD_DISABLE bits */
+	call verify_cpu
+
 	mov $0x80000001, %eax
 	cpuid
 	/* Execute Disable bit supported? */
@@ -611,6 +616,8 @@ ignore_int:
 #endif
 	iret
 
+#include "verify_cpu.S"
+
 	__REFDATA
 .align 4
 ENTRY(initial_code)
@@ -622,13 +629,13 @@ ENTRY(initial_code)
 __PAGE_ALIGNED_BSS
 	.align PAGE_SIZE_asm
 #ifdef CONFIG_X86_PAE
-ENTRY(initial_pg_pmd)
+initial_pg_pmd:
 	.fill 1024*KPMDS,4,0
 #else
 ENTRY(initial_page_table)
 	.fill 1024,4,0
 #endif
-ENTRY(initial_pg_fixmap)
+initial_pg_fixmap:
 	.fill 1024,4,0
 ENTRY(empty_zero_page)
 	.fill 4096,1,0
diff --git a/arch/x86/kernel/microcode_amd.c b/arch/x86/kernel/microcode_amd.c
index ce0cb4721c9a..0fe6d1a66c38 100644
--- a/arch/x86/kernel/microcode_amd.c
+++ b/arch/x86/kernel/microcode_amd.c
@@ -155,12 +155,6 @@ static int apply_microcode_amd(int cpu)
 	return 0;
 }
 
-static int get_ucode_data(void *to, const u8 *from, size_t n)
-{
-	memcpy(to, from, n);
-	return 0;
-}
-
 static void *
 get_next_ucode(const u8 *buf, unsigned int size, unsigned int *mc_size)
 {
@@ -168,8 +162,7 @@ get_next_ucode(const u8 *buf, unsigned int size, unsigned int *mc_size)
 	u8 section_hdr[UCODE_CONTAINER_SECTION_HDR];
 	void *mc;
 
-	if (get_ucode_data(section_hdr, buf, UCODE_CONTAINER_SECTION_HDR))
-		return NULL;
+	get_ucode_data(section_hdr, buf, UCODE_CONTAINER_SECTION_HDR);
 
 	if (section_hdr[0] != UCODE_UCODE_TYPE) {
 		pr_err("error: invalid type field in container file section header\n");
@@ -183,16 +176,13 @@ get_next_ucode(const u8 *buf, unsigned int size, unsigned int *mc_size)
 		return NULL;
 	}
 
-	mc = vmalloc(UCODE_MAX_SIZE);
-	if (mc) {
-		memset(mc, 0, UCODE_MAX_SIZE);
-		if (get_ucode_data(mc, buf + UCODE_CONTAINER_SECTION_HDR,
-				   total_size)) {
-			vfree(mc);
-			mc = NULL;
-		} else
-			*mc_size = total_size + UCODE_CONTAINER_SECTION_HDR;
-	}
+	mc = vzalloc(UCODE_MAX_SIZE);
+	if (!mc)
+		return NULL;
+
+	get_ucode_data(mc, buf + UCODE_CONTAINER_SECTION_HDR, total_size);
+	*mc_size = total_size + UCODE_CONTAINER_SECTION_HDR;
+
 	return mc;
 }
 
@@ -202,8 +192,7 @@ static int install_equiv_cpu_table(const u8 *buf)
 	unsigned int *buf_pos = (unsigned int *)container_hdr;
 	unsigned long size;
 
-	if (get_ucode_data(&container_hdr, buf, UCODE_CONTAINER_HEADER_SIZE))
-		return 0;
+	get_ucode_data(&container_hdr, buf, UCODE_CONTAINER_HEADER_SIZE);
 
 	size = buf_pos[2];
 
@@ -219,10 +208,7 @@ static int install_equiv_cpu_table(const u8 *buf)
 	}
 
 	buf += UCODE_CONTAINER_HEADER_SIZE;
-	if (get_ucode_data(equiv_cpu_table, buf, size)) {
-		vfree(equiv_cpu_table);
-		return 0;
-	}
+	get_ucode_data(equiv_cpu_table, buf, size);
 
 	return size + UCODE_CONTAINER_HEADER_SIZE; /* add header length */
 }
diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c
index ba0f0ca9f280..c01ffa5b9b87 100644
--- a/arch/x86/kernel/pci-gart_64.c
+++ b/arch/x86/kernel/pci-gart_64.c
@@ -143,7 +143,7 @@ static void flush_gart(void)
 
 	spin_lock_irqsave(&iommu_bitmap_lock, flags);
 	if (need_flush) {
-		k8_flush_garts();
+		amd_flush_garts();
 		need_flush = false;
 	}
 	spin_unlock_irqrestore(&iommu_bitmap_lock, flags);
@@ -561,17 +561,17 @@ static void enable_gart_translations(void)
 {
 	int i;
 
-	if (!k8_northbridges.gart_supported)
+	if (!amd_nb_has_feature(AMD_NB_GART))
 		return;
 
-	for (i = 0; i < k8_northbridges.num; i++) {
-		struct pci_dev *dev = k8_northbridges.nb_misc[i];
+	for (i = 0; i < amd_nb_num(); i++) {
+		struct pci_dev *dev = node_to_amd_nb(i)->misc;
 
 		enable_gart_translation(dev, __pa(agp_gatt_table));
 	}
 
 	/* Flush the GART-TLB to remove stale entries */
-	k8_flush_garts();
+	amd_flush_garts();
 }
 
 /*
@@ -596,13 +596,13 @@ static void gart_fixup_northbridges(struct sys_device *dev)
 	if (!fix_up_north_bridges)
 		return;
 
-	if (!k8_northbridges.gart_supported)
+	if (!amd_nb_has_feature(AMD_NB_GART))
 		return;
 
 	pr_info("PCI-DMA: Restoring GART aperture settings\n");
 
-	for (i = 0; i < k8_northbridges.num; i++) {
-		struct pci_dev *dev = k8_northbridges.nb_misc[i];
+	for (i = 0; i < amd_nb_num(); i++) {
+		struct pci_dev *dev = node_to_amd_nb(i)->misc;
 
 		/*
 		 * Don't enable translations just yet.  That is the next
@@ -644,7 +644,7 @@ static struct sys_device device_gart = {
  * Private Northbridge GATT initialization in case we cannot use the
  * AGP driver for some reason.
  */
-static __init int init_k8_gatt(struct agp_kern_info *info)
+static __init int init_amd_gatt(struct agp_kern_info *info)
 {
 	unsigned aper_size, gatt_size, new_aper_size;
 	unsigned aper_base, new_aper_base;
@@ -656,8 +656,8 @@ static __init int init_k8_gatt(struct agp_kern_info *info)
 
 	aper_size = aper_base = info->aper_size = 0;
 	dev = NULL;
-	for (i = 0; i < k8_northbridges.num; i++) {
-		dev = k8_northbridges.nb_misc[i];
+	for (i = 0; i < amd_nb_num(); i++) {
+		dev = node_to_amd_nb(i)->misc;
 		new_aper_base = read_aperture(dev, &new_aper_size);
 		if (!new_aper_base)
 			goto nommu;
@@ -725,13 +725,13 @@ static void gart_iommu_shutdown(void)
 	if (!no_agp)
 		return;
 
-	if (!k8_northbridges.gart_supported)
+	if (!amd_nb_has_feature(AMD_NB_GART))
 		return;
 
-	for (i = 0; i < k8_northbridges.num; i++) {
+	for (i = 0; i < amd_nb_num(); i++) {
 		u32 ctl;
 
-		dev = k8_northbridges.nb_misc[i];
+		dev = node_to_amd_nb(i)->misc;
 		pci_read_config_dword(dev, AMD64_GARTAPERTURECTL, &ctl);
 
 		ctl &= ~GARTEN;
@@ -749,14 +749,14 @@ int __init gart_iommu_init(void)
 	unsigned long scratch;
 	long i;
 
-	if (!k8_northbridges.gart_supported)
+	if (!amd_nb_has_feature(AMD_NB_GART))
 		return 0;
 
 #ifndef CONFIG_AGP_AMD64
 	no_agp = 1;
 #else
 	/* Makefile puts PCI initialization via subsys_initcall first. */
-	/* Add other K8 AGP bridge drivers here */
+	/* Add other AMD AGP bridge drivers here */
 	no_agp = no_agp ||
 		(agp_amd64_init() < 0) ||
 		(agp_copy_info(agp_bridge, &info) < 0);
@@ -765,7 +765,7 @@ int __init gart_iommu_init(void)
 	if (no_iommu ||
 	    (!force_iommu && max_pfn <= MAX_DMA32_PFN) ||
 	    !gart_iommu_aperture ||
-	    (no_agp && init_k8_gatt(&info) < 0)) {
+	    (no_agp && init_amd_gatt(&info) < 0)) {
 		if (max_pfn > MAX_DMA32_PFN) {
 			pr_warning("More than 4GB of memory but GART IOMMU not available.\n");
 			pr_warning("falling back to iommu=soft.\n");
diff --git a/arch/x86/kernel/reboot_fixups_32.c b/arch/x86/kernel/reboot_fixups_32.c
index fda313ebbb03..c8e41e90f59c 100644
--- a/arch/x86/kernel/reboot_fixups_32.c
+++ b/arch/x86/kernel/reboot_fixups_32.c
@@ -43,17 +43,33 @@ static void rdc321x_reset(struct pci_dev *dev)
 	outb(1, 0x92);
 }
 
+static void ce4100_reset(struct pci_dev *dev)
+{
+	int i;
+
+	for (i = 0; i < 10; i++) {
+		outb(0x2, 0xcf9);
+		udelay(50);
+	}
+}
+
 struct device_fixup {
 	unsigned int vendor;
 	unsigned int device;
 	void (*reboot_fixup)(struct pci_dev *);
 };
 
+/*
+ * PCI ids solely used for fixups_table go here
+ */
+#define PCI_DEVICE_ID_INTEL_CE4100	0x0708
+
 static const struct device_fixup fixups_table[] = {
 { PCI_VENDOR_ID_CYRIX, PCI_DEVICE_ID_CYRIX_5530_LEGACY, cs5530a_warm_reset },
 { PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CS5536_ISA, cs5536_warm_reset },
 { PCI_VENDOR_ID_NS, PCI_DEVICE_ID_NS_SC1100_BRIDGE, cs5530a_warm_reset },
 { PCI_VENDOR_ID_RDC, PCI_DEVICE_ID_RDC_R6030, rdc321x_reset },
+{ PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CE4100, ce4100_reset },
 };
 
 /*
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index a0f52af256a0..d3cfe26c0252 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -705,7 +705,7 @@ static u64 __init get_max_mapped(void)
 void __init setup_arch(char **cmdline_p)
 {
 	int acpi = 0;
-	int k8 = 0;
+	int amd = 0;
 	unsigned long flags;
 
 #ifdef CONFIG_X86_32
@@ -991,12 +991,12 @@ void __init setup_arch(char **cmdline_p)
 	acpi = acpi_numa_init();
 #endif
 
-#ifdef CONFIG_K8_NUMA
+#ifdef CONFIG_AMD_NUMA
 	if (!acpi)
-		k8 = !k8_numa_init(0, max_pfn);
+		amd = !amd_numa_init(0, max_pfn);
 #endif
 
-	initmem_init(0, max_pfn, acpi, k8);
+	initmem_init(0, max_pfn, acpi, amd);
 	memblock_find_dma_reserve();
 	dma32_reserve_bootmem();
 
@@ -1045,10 +1045,7 @@ void __init setup_arch(char **cmdline_p)
 #endif
 
 	init_apic_mappings();
-	ioapic_init_mappings();
-
-	/* need to wait for io_apic is mapped */
-	probe_nr_irqs_gsi();
+	ioapic_and_gsi_init();
 
 	kvm_guest_init();
 
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 68f61ac632e1..ee886fe10ef4 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -1161,6 +1161,20 @@ out:
 	preempt_enable();
 }
 
+void arch_disable_nonboot_cpus_begin(void)
+{
+	/*
+	 * Avoid the smp alternatives switch during the disable_nonboot_cpus().
+	 * In the suspend path, we will be back in the SMP mode shortly anyways.
+	 */
+	skip_smp_alternatives = true;
+}
+
+void arch_disable_nonboot_cpus_end(void)
+{
+	skip_smp_alternatives = false;
+}
+
 void arch_enable_nonboot_cpus_begin(void)
 {
 	set_mtrr_aps_delayed_init();
diff --git a/arch/x86/kernel/trampoline_64.S b/arch/x86/kernel/trampoline_64.S
index 3af2dff58b21..075d130efcf9 100644
--- a/arch/x86/kernel/trampoline_64.S
+++ b/arch/x86/kernel/trampoline_64.S
@@ -127,7 +127,7 @@ startup_64:
 no_longmode:
 	hlt
 	jmp no_longmode
-#include "verify_cpu_64.S"
+#include "verify_cpu.S"
 
 	# Careful these need to be in the same 64K segment as the above;
 tidt:
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 0c40d8b72416..356a0d455cf9 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -872,6 +872,9 @@ __cpuinit int unsynchronized_tsc(void)
 
 	if (boot_cpu_has(X86_FEATURE_CONSTANT_TSC))
 		return 0;
+
+	if (tsc_clocksource_reliable)
+		return 0;
 	/*
 	 * Intel systems are normally all synchronized.
 	 * Exceptions must mark TSC as unstable:
@@ -879,14 +882,92 @@ __cpuinit int unsynchronized_tsc(void)
 	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) {
 		/* assume multi socket systems are not synchronized: */
 		if (num_possible_cpus() > 1)
-			tsc_unstable = 1;
+			return 1;
 	}
 
-	return tsc_unstable;
+	return 0;
+}
+
+
+static void tsc_refine_calibration_work(struct work_struct *work);
+static DECLARE_DELAYED_WORK(tsc_irqwork, tsc_refine_calibration_work);
+/**
+ * tsc_refine_calibration_work - Further refine tsc freq calibration
+ * @work - ignored.
+ *
+ * This functions uses delayed work over a period of a
+ * second to further refine the TSC freq value. Since this is
+ * timer based, instead of loop based, we don't block the boot
+ * process while this longer calibration is done.
+ *
+ * If there are any calibration anomolies (too many SMIs, etc),
+ * or the refined calibration is off by 1% of the fast early
+ * calibration, we throw out the new calibration and use the
+ * early calibration.
+ */
+static void tsc_refine_calibration_work(struct work_struct *work)
+{
+	static u64 tsc_start = -1, ref_start;
+	static int hpet;
+	u64 tsc_stop, ref_stop, delta;
+	unsigned long freq;
+
+	/* Don't bother refining TSC on unstable systems */
+	if (check_tsc_unstable())
+		goto out;
+
+	/*
+	 * Since the work is started early in boot, we may be
+	 * delayed the first time we expire. So set the workqueue
+	 * again once we know timers are working.
+	 */
+	if (tsc_start == -1) {
+		/*
+		 * Only set hpet once, to avoid mixing hardware
+		 * if the hpet becomes enabled later.
+		 */
+		hpet = is_hpet_enabled();
+		schedule_delayed_work(&tsc_irqwork, HZ);
+		tsc_start = tsc_read_refs(&ref_start, hpet);
+		return;
+	}
+
+	tsc_stop = tsc_read_refs(&ref_stop, hpet);
+
+	/* hpet or pmtimer available ? */
+	if (!hpet && !ref_start && !ref_stop)
+		goto out;
+
+	/* Check, whether the sampling was disturbed by an SMI */
+	if (tsc_start == ULLONG_MAX || tsc_stop == ULLONG_MAX)
+		goto out;
+
+	delta = tsc_stop - tsc_start;
+	delta *= 1000000LL;
+	if (hpet)
+		freq = calc_hpet_ref(delta, ref_start, ref_stop);
+	else
+		freq = calc_pmtimer_ref(delta, ref_start, ref_stop);
+
+	/* Make sure we're within 1% */
+	if (abs(tsc_khz - freq) > tsc_khz/100)
+		goto out;
+
+	tsc_khz = freq;
+	printk(KERN_INFO "Refined TSC clocksource calibration: "
+		"%lu.%03lu MHz.\n", (unsigned long)tsc_khz / 1000,
+					(unsigned long)tsc_khz % 1000);
+
+out:
+	clocksource_register_khz(&clocksource_tsc, tsc_khz);
 }
 
-static void __init init_tsc_clocksource(void)
+
+static int __init init_tsc_clocksource(void)
 {
+	if (!cpu_has_tsc || tsc_disabled > 0)
+		return 0;
+
 	if (tsc_clocksource_reliable)
 		clocksource_tsc.flags &= ~CLOCK_SOURCE_MUST_VERIFY;
 	/* lower the rating if we already know its unstable: */
@@ -894,8 +975,14 @@ static void __init init_tsc_clocksource(void)
 		clocksource_tsc.rating = 0;
 		clocksource_tsc.flags &= ~CLOCK_SOURCE_IS_CONTINUOUS;
 	}
-	clocksource_register_khz(&clocksource_tsc, tsc_khz);
+	schedule_delayed_work(&tsc_irqwork, 0);
+	return 0;
 }
+/*
+ * We use device_initcall here, to ensure we run after the hpet
+ * is fully initialized, which may occur at fs_initcall time.
+ */
+device_initcall(init_tsc_clocksource);
 
 void __init tsc_init(void)
 {
@@ -949,6 +1036,5 @@ void __init tsc_init(void)
 		mark_tsc_unstable("TSCs unsynchronized");
 
 	check_system_tsc_reliable();
-	init_tsc_clocksource();
 }
 
diff --git a/arch/x86/kernel/verify_cpu_64.S b/arch/x86/kernel/verify_cpu.S
index 56a8c2a867d9..0edefc19a113 100644
--- a/arch/x86/kernel/verify_cpu_64.S
+++ b/arch/x86/kernel/verify_cpu.S
@@ -7,6 +7,7 @@
  *	Copyright (c) 2007  Andi Kleen (ak@suse.de)
  *	Copyright (c) 2007  Eric Biederman (ebiederm@xmission.com)
  *	Copyright (c) 2007  Vivek Goyal (vgoyal@in.ibm.com)
+ *	Copyright (c) 2010  Kees Cook (kees.cook@canonical.com)
  *
  * 	This source code is licensed under the GNU General Public License,
  * 	Version 2.  See the file COPYING for more details.
@@ -14,18 +15,17 @@
  *	This is a common code for verification whether CPU supports
  * 	long mode and SSE or not. It is not called directly instead this
  *	file is included at various places and compiled in that context.
- * 	Following are the current usage.
+ *	This file is expected to run in 32bit code.  Currently:
  *
- * 	This file is included by both 16bit and 32bit code.
+ *	arch/x86/boot/compressed/head_64.S: Boot cpu verification
+ *	arch/x86/kernel/trampoline_64.S: secondary processor verfication
+ *	arch/x86/kernel/head_32.S: processor startup
  *
- *	arch/x86_64/boot/setup.S : Boot cpu verification (16bit)
- *	arch/x86_64/boot/compressed/head.S: Boot cpu verification (32bit)
- *	arch/x86_64/kernel/trampoline.S: secondary processor verfication (16bit)
- *	arch/x86_64/kernel/acpi/wakeup.S:Verfication at resume (16bit)
- *
- *	verify_cpu, returns the status of cpu check in register %eax.
+ *	verify_cpu, returns the status of longmode and SSE in register %eax.
  *		0: Success    1: Failure
  *
+ *	On Intel, the XD_DISABLE flag will be cleared as a side-effect.
+ *
  * 	The caller needs to check for the error code and take the action
  * 	appropriately. Either display a message or halt.
  */
@@ -62,8 +62,41 @@ verify_cpu:
 	cmpl	$0x444d4163,%ecx
 	jnz	verify_cpu_noamd
 	mov	$1,%di			# cpu is from AMD
+	jmp	verify_cpu_check
 
 verify_cpu_noamd:
+	cmpl	$0x756e6547,%ebx        # GenuineIntel?
+	jnz	verify_cpu_check
+	cmpl	$0x49656e69,%edx
+	jnz	verify_cpu_check
+	cmpl	$0x6c65746e,%ecx
+	jnz	verify_cpu_check
+
+	# only call IA32_MISC_ENABLE when:
+	# family > 6 || (family == 6 && model >= 0xd)
+	movl	$0x1, %eax		# check CPU family and model
+	cpuid
+	movl	%eax, %ecx
+
+	andl	$0x0ff00f00, %eax	# mask family and extended family
+	shrl	$8, %eax
+	cmpl	$6, %eax
+	ja	verify_cpu_clear_xd	# family > 6, ok
+	jb	verify_cpu_check	# family < 6, skip
+
+	andl	$0x000f00f0, %ecx	# mask model and extended model
+	shrl	$4, %ecx
+	cmpl	$0xd, %ecx
+	jb	verify_cpu_check	# family == 6, model < 0xd, skip
+
+verify_cpu_clear_xd:
+	movl	$MSR_IA32_MISC_ENABLE, %ecx
+	rdmsr
+	btrl	$2, %edx		# clear MSR_IA32_MISC_ENABLE_XD_DISABLE
+	jnc	verify_cpu_check	# only write MSR if bit was changed
+	wrmsr
+
+verify_cpu_check:
 	movl    $0x1,%eax		# Does the cpu have what it takes
 	cpuid
 	andl	$REQUIRED_MASK0,%edx
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index e03530aebfd0..bf4700755184 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -69,7 +69,7 @@ jiffies_64 = jiffies;
 
 PHDRS {
 	text PT_LOAD FLAGS(5);          /* R_E */
-	data PT_LOAD FLAGS(7);          /* RWE */
+	data PT_LOAD FLAGS(6);          /* RW_ */
 #ifdef CONFIG_X86_64
 	user PT_LOAD FLAGS(5);          /* R_E */
 #ifdef CONFIG_SMP
@@ -116,6 +116,10 @@ SECTIONS
 
 	EXCEPTION_TABLE(16) :text = 0x9090
 
+#if defined(CONFIG_DEBUG_RODATA)
+	/* .text should occupy whole number of pages */
+	. = ALIGN(PAGE_SIZE);
+#endif
 	X64_ALIGN_DEBUG_RODATA_BEGIN
 	RO_DATA(PAGE_SIZE)
 	X64_ALIGN_DEBUG_RODATA_END
@@ -335,7 +339,7 @@ SECTIONS
 		__bss_start = .;
 		*(.bss..page_aligned)
 		*(.bss)
-		. = ALIGN(4);
+		. = ALIGN(PAGE_SIZE);
 		__bss_stop = .;
 	}