Merge branch 'master' into for-next

Pull linus#master to merge PER_CPU_DEF_ATTRIBUTES and alpha build fix
changes.  As alpha in percpu tree uses 'weak' attribute instead of
inline assembly, there's no need for __used attribute.

Conflicts:
	arch/alpha/include/asm/percpu.h
	arch/mn10300/kernel/vmlinux.lds.S
	include/linux/percpu-defs.h

34 files changed, 230 insertions, 163 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index a48a90076d8..646fcabb0ad 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1910,25 +1910,14 @@ config DMAR_DEFAULT_ON
 	  recommended you say N here while the DMAR code remains
 	  experimental.
 
-config DMAR_GFX_WA
-	def_bool y
-	prompt "Support for Graphics workaround"
-	depends on DMAR
-	---help---
-	  Current Graphics drivers tend to use physical address
-	  for DMA and avoid using DMA APIs. Setting this config
-	  option permits the IOMMU driver to set a unity map for
-	  all the OS-visible memory. Hence the driver can continue
-	  to use physical addresses for DMA.
-
 config DMAR_FLOPPY_WA
 	def_bool y
 	depends on DMAR
 	---help---
-	  Floppy disk drivers are know to bypass DMA API calls
+	  Floppy disk drivers are known to bypass DMA API calls
 	  thereby failing to work when IOMMU is enabled. This
 	  workaround will setup a 1:1 mapping for the first
-	  16M to make floppy (an ISA device) work.
+	  16MiB to make floppy (an ISA device) work.
 
 config INTR_REMAP
 	bool "Support for Interrupt Remapping (EXPERIMENTAL)"
diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h
index 4518dc50090..20d1465a2ab 100644
--- a/arch/x86/include/asm/acpi.h
+++ b/arch/x86/include/asm/acpi.h
@@ -144,6 +144,7 @@ static inline unsigned int acpi_processor_cstate_check(unsigned int max_cstate)
 
 #else /* !CONFIG_ACPI */
 
+#define acpi_disabled 1
 #define acpi_lapic 0
 #define acpi_ioapic 0
 static inline void acpi_noirq_set(void) { }
diff --git a/arch/x86/include/asm/boot.h b/arch/x86/include/asm/boot.h
index 418e632d4a8..7a1065958ba 100644
--- a/arch/x86/include/asm/boot.h
+++ b/arch/x86/include/asm/boot.h
@@ -8,7 +8,7 @@
 
 #ifdef __KERNEL__
 
-#include <asm/page_types.h>
+#include <asm/pgtable_types.h>
 
 /* Physical address where kernel should be loaded. */
 #define LOAD_PHYSICAL_ADDR ((CONFIG_PHYSICAL_START \
@@ -16,10 +16,10 @@
 				& ~(CONFIG_PHYSICAL_ALIGN - 1))
 
 /* Minimum kernel alignment, as a power of two */
-#ifdef CONFIG_x86_64
+#ifdef CONFIG_X86_64
 #define MIN_KERNEL_ALIGN_LG2	PMD_SHIFT
 #else
-#define MIN_KERNEL_ALIGN_LG2	(PAGE_SHIFT+1)
+#define MIN_KERNEL_ALIGN_LG2	(PAGE_SHIFT + THREAD_ORDER)
 #endif
 #define MIN_KERNEL_ALIGN	(_AC(1, UL) << MIN_KERNEL_ALIGN_LG2)
 
diff --git a/arch/x86/include/asm/iommu.h b/arch/x86/include/asm/iommu.h
index af326a2975b..fd6d21bbee6 100644
--- a/arch/x86/include/asm/iommu.h
+++ b/arch/x86/include/asm/iommu.h
@@ -6,6 +6,7 @@ extern void no_iommu_init(void);
 extern struct dma_map_ops nommu_dma_ops;
 extern int force_iommu, no_iommu;
 extern int iommu_detected;
+extern int iommu_pass_through;
 
 /* 10 seconds */
 #define DMAR_OPERATION_TIMEOUT ((cycles_t) tsc_khz*10*1000)
diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h
index b51a1e8b0ba..1ff685ca221 100644
--- a/arch/x86/include/asm/pci.h
+++ b/arch/x86/include/asm/pci.h
@@ -91,7 +91,7 @@ extern void pci_iommu_alloc(void);
 
 #define PCI_DMA_BUS_IS_PHYS (dma_ops->is_phys)
 
-#if defined(CONFIG_X86_64) || defined(CONFIG_DMA_API_DEBUG)
+#if defined(CONFIG_X86_64) || defined(CONFIG_DMAR) || defined(CONFIG_DMA_API_DEBUG)
 
 #define DECLARE_PCI_UNMAP_ADDR(ADDR_NAME)       \
 	        dma_addr_t ADDR_NAME;
@@ -130,6 +130,7 @@ extern void pci_iommu_alloc(void);
 
 /* generic pci stuff */
 #include <asm-generic/pci.h>
+#define PCIBIOS_MAX_MEM_32 0xffffffff
 
 #ifdef CONFIG_NUMA
 /* Returns the node based on pci bus */
diff --git a/arch/x86/include/asm/pci_x86.h b/arch/x86/include/asm/pci_x86.h
index e60fd3e14bd..b399988eee3 100644
--- a/arch/x86/include/asm/pci_x86.h
+++ b/arch/x86/include/asm/pci_x86.h
@@ -121,6 +121,9 @@ extern int __init pcibios_init(void);
 extern int __init pci_mmcfg_arch_init(void);
 extern void __init pci_mmcfg_arch_free(void);
 
+extern struct acpi_mcfg_allocation *pci_mmcfg_config;
+extern int pci_mmcfg_config_num;
+
 /*
  * AMD Fam10h CPUs are buggy, and cannot access MMIO config space
  * on their northbrige except through the * %eax register. As such, you MUST
diff --git a/arch/x86/include/asm/perf_counter.h b/arch/x86/include/asm/perf_counter.h
index 5fb33e160ea..fa64e401589 100644
--- a/arch/x86/include/asm/perf_counter.h
+++ b/arch/x86/include/asm/perf_counter.h
@@ -87,6 +87,9 @@ union cpuid10_edx {
 #ifdef CONFIG_PERF_COUNTERS
 extern void init_hw_perf_counters(void);
 extern void perf_counters_lapic_init(void);
+
+#define PERF_COUNTER_INDEX_OFFSET			0
+
 #else
 static inline void init_hw_perf_counters(void)		{ }
 static inline void perf_counters_lapic_init(void)	{ }
diff --git a/arch/x86/include/asm/proto.h b/arch/x86/include/asm/proto.h
index 49fb3ecf3bb..621f56d7312 100644
--- a/arch/x86/include/asm/proto.h
+++ b/arch/x86/include/asm/proto.h
@@ -22,7 +22,14 @@ extern int reboot_force;
 
 long do_arch_prctl(struct task_struct *task, int code, unsigned long addr);
 
-#define round_up(x, y) (((x) + (y) - 1) & ~((y) - 1))
-#define round_down(x, y) ((x) & ~((y) - 1))
+/*
+ * This looks more complex than it should be. But we need to
+ * get the type for the ~ right in round_down (it needs to be
+ * as wide as the result!), and we want to evaluate the macro
+ * arguments just once each.
+ */
+#define __round_mask(x,y) ((__typeof__(x))((y)-1))
+#define round_up(x,y) ((((x)-1) | __round_mask(x,y))+1)
+#define round_down(x,y) ((x) & ~__round_mask(x,y))
 
 #endif /* _ASM_X86_PROTO_H */
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 631086159c5..6b8ca3a0285 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -44,11 +44,7 @@
 
 static int __initdata acpi_force = 0;
 u32 acpi_rsdt_forced;
-#ifdef	CONFIG_ACPI
-int acpi_disabled = 0;
-#else
-int acpi_disabled = 1;
-#endif
+int acpi_disabled;
 EXPORT_SYMBOL(acpi_disabled);
 
 #ifdef	CONFIG_X86_64
@@ -122,72 +118,6 @@ void __init __acpi_unmap_table(char *map, unsigned long size)
 	early_iounmap(map, size);
 }
 
-#ifdef CONFIG_PCI_MMCONFIG
-
-static int acpi_mcfg_64bit_base_addr __initdata = FALSE;
-
-/* The physical address of the MMCONFIG aperture.  Set from ACPI tables. */
-struct acpi_mcfg_allocation *pci_mmcfg_config;
-int pci_mmcfg_config_num;
-
-static int __init acpi_mcfg_oem_check(struct acpi_table_mcfg *mcfg)
-{
-	if (!strcmp(mcfg->header.oem_id, "SGI"))
-		acpi_mcfg_64bit_base_addr = TRUE;
-
-	return 0;
-}
-
-int __init acpi_parse_mcfg(struct acpi_table_header *header)
-{
-	struct acpi_table_mcfg *mcfg;
-	unsigned long i;
-	int config_size;
-
-	if (!header)
-		return -EINVAL;
-
-	mcfg = (struct acpi_table_mcfg *)header;
-
-	/* how many config structures do we have */
-	pci_mmcfg_config_num = 0;
-	i = header->length - sizeof(struct acpi_table_mcfg);
-	while (i >= sizeof(struct acpi_mcfg_allocation)) {
-		++pci_mmcfg_config_num;
-		i -= sizeof(struct acpi_mcfg_allocation);
-	};
-	if (pci_mmcfg_config_num == 0) {
-		printk(KERN_ERR PREFIX "MMCONFIG has no entries\n");
-		return -ENODEV;
-	}
-
-	config_size = pci_mmcfg_config_num * sizeof(*pci_mmcfg_config);
-	pci_mmcfg_config = kmalloc(config_size, GFP_KERNEL);
-	if (!pci_mmcfg_config) {
-		printk(KERN_WARNING PREFIX
-		       "No memory for MCFG config tables\n");
-		return -ENOMEM;
-	}
-
-	memcpy(pci_mmcfg_config, &mcfg[1], config_size);
-
-	acpi_mcfg_oem_check(mcfg);
-
-	for (i = 0; i < pci_mmcfg_config_num; ++i) {
-		if ((pci_mmcfg_config[i].address > 0xFFFFFFFF) &&
-		    !acpi_mcfg_64bit_base_addr) {
-			printk(KERN_ERR PREFIX
-			       "MMCONFIG not in low 4GB of memory\n");
-			kfree(pci_mmcfg_config);
-			pci_mmcfg_config_num = 0;
-			return -ENODEV;
-		}
-	}
-
-	return 0;
-}
-#endif				/* CONFIG_PCI_MMCONFIG */
-
 #ifdef CONFIG_X86_LOCAL_APIC
 static int __init acpi_parse_madt(struct acpi_table_header *table)
 {
@@ -1519,14 +1449,6 @@ static struct dmi_system_id __initdata acpi_dmi_table[] = {
 	 },
 	{
 	 .callback = force_acpi_ht,
-	 .ident = "ASUS P4B266",
-	 .matches = {
-		     DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK Computer INC."),
-		     DMI_MATCH(DMI_BOARD_NAME, "P4B266"),
-		     },
-	 },
-	{
-	 .callback = force_acpi_ht,
 	 .ident = "ASUS P2B-DS",
 	 .matches = {
 		     DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK Computer INC."),
diff --git a/arch/x86/kernel/acpi/cstate.c b/arch/x86/kernel/acpi/cstate.c
index bbbe4bbb6f3..8c44c232efc 100644
--- a/arch/x86/kernel/acpi/cstate.c
+++ b/arch/x86/kernel/acpi/cstate.c
@@ -34,12 +34,22 @@ void acpi_processor_power_init_bm_check(struct acpi_processor_flags *flags,
 		flags->bm_check = 1;
 	else if (c->x86_vendor == X86_VENDOR_INTEL) {
 		/*
-		 * Today all CPUs that support C3 share cache.
-		 * TBD: This needs to look at cache shared map, once
-		 * multi-core detection patch makes to the base.
+		 * Today all MP CPUs that support C3 share cache.
+		 * And caches should not be flushed by software while
+		 * entering C3 type state.
 		 */
 		flags->bm_check = 1;
 	}
+
+	/*
+	 * On all recent Intel platforms, ARB_DISABLE is a nop.
+	 * So, set bm_control to zero to indicate that ARB_DISABLE
+	 * is not required while entering C3 type state on
+	 * P4, Core and beyond CPUs
+	 */
+	if (c->x86_vendor == X86_VENDOR_INTEL &&
+	    (c->x86 > 0x6 || (c->x86 == 6 && c->x86_model >= 14)))
+			flags->bm_control = 0;
 }
 EXPORT_SYMBOL(acpi_processor_power_init_bm_check);
 
diff --git a/arch/x86/kernel/acpi/processor.c b/arch/x86/kernel/acpi/processor.c
index 7c074eec39f..d296f4a195c 100644
--- a/arch/x86/kernel/acpi/processor.c
+++ b/arch/x86/kernel/acpi/processor.c
@@ -72,6 +72,7 @@ static void init_intel_pdc(struct acpi_processor *pr, struct cpuinfo_x86 *c)
 	return;
 }
 
+
 /* Initialize _PDC data based on the CPU vendor */
 void arch_acpi_processor_init_pdc(struct acpi_processor *pr)
 {
@@ -85,3 +86,15 @@ void arch_acpi_processor_init_pdc(struct acpi_processor *pr)
 }
 
 EXPORT_SYMBOL(arch_acpi_processor_init_pdc);
+
+void arch_acpi_processor_cleanup_pdc(struct acpi_processor *pr)
+{
+	if (pr->pdc) {
+		kfree(pr->pdc->pointer->buffer.pointer);
+		kfree(pr->pdc->pointer);
+		kfree(pr->pdc);
+		pr->pdc = NULL;
+	}
+}
+
+EXPORT_SYMBOL(arch_acpi_processor_cleanup_pdc);
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index b7a79207295..4d0216fcb36 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -1414,6 +1414,9 @@ int setup_ioapic_entry(int apic_id, int irq,
 		irte.vector = vector;
 		irte.dest_id = IRTE_DEST(destination);
 
+		/* Set source-id of interrupt request */
+		set_ioapic_sid(&irte, apic_id);
+
 		modify_irte(irq, &irte);
 
 		ir_entry->index2 = (index >> 15) & 0x1;
@@ -3290,6 +3293,9 @@ static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq, struct msi_ms
 		irte.vector = cfg->vector;
 		irte.dest_id = IRTE_DEST(dest);
 
+		/* Set source-id of interrupt request */
+		set_msi_sid(&irte, pdev);
+
 		modify_irte(irq, &irte);
 
 		msg->address_hi = MSI_ADDR_BASE_HI;
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index e5b27d8f1b4..28e5f595604 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -258,13 +258,15 @@ static void __cpuinit amd_detect_cmp(struct cpuinfo_x86 *c)
 {
 #ifdef CONFIG_X86_HT
 	unsigned bits;
+	int cpu = smp_processor_id();
 
 	bits = c->x86_coreid_bits;
-
 	/* Low order bits define the core id (index of core in socket) */
 	c->cpu_core_id = c->initial_apicid & ((1 << bits)-1);
 	/* Convert the initial APIC ID into the socket ID */
 	c->phys_proc_id = c->initial_apicid >> bits;
+	/* use socket ID also for last level cache */
+	per_cpu(cpu_llc_id, cpu) = c->phys_proc_id;
 #endif
 }
 
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 6b26d4deada..f1961c07af9 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -848,9 +848,6 @@ static void __cpuinit identify_cpu(struct cpuinfo_x86 *c)
 #if defined(CONFIG_NUMA) && defined(CONFIG_X86_64)
 	numa_add_cpu(smp_processor_id());
 #endif
-
-	/* Cap the iomem address space to what is addressable on all CPUs */
-	iomem_resource.end &= (1ULL << c->x86_phys_bits) - 1;
 }
 
 #ifdef CONFIG_X86_64
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index cba8cd3e957..20d49835110 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -1117,7 +1117,7 @@ static void mcheck_timer(unsigned long data)
 		*n = min(*n*2, (int)round_jiffies_relative(check_interval*HZ));
 
 	t->expires = jiffies + *n;
-	add_timer(t);
+	add_timer_on(t, smp_processor_id());
 }
 
 static void mce_do_trigger(struct work_struct *work)
@@ -1321,7 +1321,7 @@ static void mce_init_timer(void)
 		return;
 	setup_timer(t, mcheck_timer, smp_processor_id());
 	t->expires = round_jiffies(jiffies + *n);
-	add_timer(t);
+	add_timer_on(t, smp_processor_id());
 }
 
 /*
diff --git a/arch/x86/kernel/cpu/perf_counter.c b/arch/x86/kernel/cpu/perf_counter.c
index 5fdf63aaaba..13bd6d6cf0b 100644
--- a/arch/x86/kernel/cpu/perf_counter.c
+++ b/arch/x86/kernel/cpu/perf_counter.c
@@ -401,7 +401,7 @@ static const u64 amd_hw_cache_event_ids
 		[ C(RESULT_MISS)   ] = 0x0041, /* Data Cache Misses          */
 	},
 	[ C(OP_WRITE) ] = {
-		[ C(RESULT_ACCESS) ] = 0x0042, /* Data Cache Refills from L2 */
+		[ C(RESULT_ACCESS) ] = 0x0142, /* Data Cache Refills :system */
 		[ C(RESULT_MISS)   ] = 0,
 	},
 	[ C(OP_PREFETCH) ] = {
@@ -912,6 +912,8 @@ x86_perf_counter_set_period(struct perf_counter *counter,
 	err = checking_wrmsrl(hwc->counter_base + idx,
 			     (u64)(-left) & x86_pmu.counter_mask);
 
+	perf_counter_update_userpage(counter);
+
 	return ret;
 }
 
@@ -969,13 +971,6 @@ fixed_mode_idx(struct perf_counter *counter, struct hw_perf_counter *hwc)
 	if (!x86_pmu.num_counters_fixed)
 		return -1;
 
-	/*
-	 * Quirk, IA32_FIXED_CTRs do not work on current Atom processors:
-	 */
-	if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL &&
-					boot_cpu_data.x86_model == 28)
-		return -1;
-
 	event = hwc->config & ARCH_PERFMON_EVENT_MASK;
 
 	if (unlikely(event == x86_pmu.event_map(PERF_COUNT_HW_INSTRUCTIONS)))
@@ -1041,6 +1036,8 @@ try_generic:
 	x86_perf_counter_set_period(counter, hwc, idx);
 	x86_pmu.enable(hwc, idx);
 
+	perf_counter_update_userpage(counter);
+
 	return 0;
 }
 
@@ -1133,6 +1130,8 @@ static void x86_pmu_disable(struct perf_counter *counter)
 	x86_perf_counter_update(counter, hwc, idx);
 	cpuc->counters[idx] = NULL;
 	clear_bit(idx, cpuc->used_mask);
+
+	perf_counter_update_userpage(counter);
 }
 
 /*
@@ -1428,8 +1427,6 @@ static int intel_pmu_init(void)
 	 */
 	x86_pmu.num_counters_fixed	= max((int)edx.split.num_counters_fixed, 3);
 
-	rdmsrl(MSR_CORE_PERF_GLOBAL_CTRL, x86_pmu.intel_ctrl);
-
 	/*
 	 * Install the hw-cache-events table:
 	 */
@@ -1499,21 +1496,22 @@ void __init init_hw_perf_counters(void)
 	pr_cont("%s PMU driver.\n", x86_pmu.name);
 
 	if (x86_pmu.num_counters > X86_PMC_MAX_GENERIC) {
-		x86_pmu.num_counters = X86_PMC_MAX_GENERIC;
 		WARN(1, KERN_ERR "hw perf counters %d > max(%d), clipping!",
 		     x86_pmu.num_counters, X86_PMC_MAX_GENERIC);
+		x86_pmu.num_counters = X86_PMC_MAX_GENERIC;
 	}
 	perf_counter_mask = (1 << x86_pmu.num_counters) - 1;
 	perf_max_counters = x86_pmu.num_counters;
 
 	if (x86_pmu.num_counters_fixed > X86_PMC_MAX_FIXED) {
-		x86_pmu.num_counters_fixed = X86_PMC_MAX_FIXED;
 		WARN(1, KERN_ERR "hw perf counters fixed %d > max(%d), clipping!",
 		     x86_pmu.num_counters_fixed, X86_PMC_MAX_FIXED);
+		x86_pmu.num_counters_fixed = X86_PMC_MAX_FIXED;
 	}
 
 	perf_counter_mask |=
 		((1LL << x86_pmu.num_counters_fixed)-1) << X86_PMC_IDX_FIXED;
+	x86_pmu.intel_ctrl = perf_counter_mask;
 
 	perf_counters_lapic_init();
 	register_die_notifier(&perf_counter_nmi_notifier);
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index 95ea5fa7d44..c8405718a4c 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -22,6 +22,7 @@
 #include "dumpstack.h"
 
 int panic_on_unrecovered_nmi;
+int panic_on_io_nmi;
 unsigned int code_bytes = 64;
 int kstack_depth_to_print = 3 * STACKSLOTS_PER_LINE;
 static int die_counter;
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 7271fa33d79..c4ca89d9aaf 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -1383,6 +1383,8 @@ static unsigned long ram_alignment(resource_size_t pos)
 	return 32*1024*1024;
 }
 
+#define MAX_RESOURCE_SIZE ((resource_size_t)-1)
+
 void __init e820_reserve_resources_late(void)
 {
 	int i;
@@ -1400,17 +1402,19 @@ void __init e820_reserve_resources_late(void)
 	 * avoid stolen RAM:
 	 */
 	for (i = 0; i < e820.nr_map; i++) {
-		struct e820entry *entry = &e820_saved.map[i];
-		resource_size_t start, end;
+		struct e820entry *entry = &e820.map[i];
+		u64 start, end;
 
 		if (entry->type != E820_RAM)
 			continue;
 		start = entry->addr + entry->size;
-		end = round_up(start, ram_alignment(start));
-		if (start == end)
+		end = round_up(start, ram_alignment(start)) - 1;
+		if (end > MAX_RESOURCE_SIZE)
+			end = MAX_RESOURCE_SIZE;
+		if (start >= end)
 			continue;
-		reserve_region_with_split(&iomem_resource, start,
-						  end - 1, "RAM buffer");
+		reserve_region_with_split(&iomem_resource, start, end,
+					  "RAM buffer");
 	}
 }
 
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index 328592fb604..1a041bcf506 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -32,6 +32,8 @@ int no_iommu __read_mostly;
 /* Set this to 1 if there is a HW IOMMU in the system */
 int iommu_detected __read_mostly = 0;
 
+int iommu_pass_through;
+
 dma_addr_t bad_dma_address __read_mostly = 0;
 EXPORT_SYMBOL(bad_dma_address);
 
@@ -210,6 +212,10 @@ static __init int iommu_setup(char *p)
 		if (!strncmp(p, "soft", 4))
 			swiotlb = 1;
 #endif
+		if (!strncmp(p, "pt", 2)) {
+			iommu_pass_through = 1;
+			return 1;
+		}
 
 		gart_parse_options(p);
 
diff --git a/arch/x86/kernel/pci-swiotlb.c b/arch/x86/kernel/pci-swiotlb.c
index a1712f2b50f..6af96ee4420 100644
--- a/arch/x86/kernel/pci-swiotlb.c
+++ b/arch/x86/kernel/pci-swiotlb.c
@@ -71,7 +71,8 @@ void __init pci_swiotlb_init(void)
 {
 	/* don't initialize swiotlb if iommu=off (no_iommu=1) */
 #ifdef CONFIG_X86_64
-	if (!iommu_detected && !no_iommu && max_pfn > MAX_DMA32_PFN)
+	if ((!iommu_detected && !no_iommu && max_pfn > MAX_DMA32_PFN) ||
+		iommu_pass_through)
 	       swiotlb = 1;
 #endif
 	if (swiotlb_force)
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index be5ae80f897..de2cab13284 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -289,6 +289,20 @@ void * __init extend_brk(size_t size, size_t align)
 	return ret;
 }
 
+#ifdef CONFIG_X86_64
+static void __init init_gbpages(void)
+{
+	if (direct_gbpages && cpu_has_gbpages)
+		printk(KERN_INFO "Using GB pages for direct mapping\n");
+	else
+		direct_gbpages = 0;
+}
+#else
+static inline void init_gbpages(void)
+{
+}
+#endif
+
 static void __init reserve_brk(void)
 {
 	if (_brk_end > _brk_start)
@@ -871,6 +885,8 @@ void __init setup_arch(char **cmdline_p)
 
 	reserve_brk();
 
+	init_gbpages();
+
 	/* max_pfn_mapped is updated here */
 	max_low_pfn_mapped = init_memory_mapping(0, max_low_pfn<<PAGE_SHIFT);
 	max_pfn_mapped = max_low_pfn_mapped;
diff --git a/arch/x86/kernel/tlb_uv.c b/arch/x86/kernel/tlb_uv.c
index 124d40c575d..8ccabb8a2f6 100644
--- a/arch/x86/kernel/tlb_uv.c
+++ b/arch/x86/kernel/tlb_uv.c
@@ -711,7 +711,6 @@ uv_activation_descriptor_init(int node, int pnode)
 	unsigned long pa;
 	unsigned long m;
 	unsigned long n;
-	unsigned long mmr_image;
 	struct bau_desc *adp;
 	struct bau_desc *ad2;
 
@@ -727,12 +726,8 @@ uv_activation_descriptor_init(int node, int pnode)
 	n = pa >> uv_nshift;
 	m = pa & uv_mmask;
 
-	mmr_image = uv_read_global_mmr64(pnode, UVH_LB_BAU_SB_DESCRIPTOR_BASE);
-	if (mmr_image) {
-		uv_write_global_mmr64(pnode, (unsigned long)
-				      UVH_LB_BAU_SB_DESCRIPTOR_BASE,
-				      (n << UV_DESC_BASE_PNODE_SHIFT | m));
-	}
+	uv_write_global_mmr64(pnode, UVH_LB_BAU_SB_DESCRIPTOR_BASE,
+			      (n << UV_DESC_BASE_PNODE_SHIFT | m));
 
 	/*
 	 * initializing all 8 (UV_ITEMS_PER_DESCRIPTOR) descriptors for each
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index a0f48f5671c..5204332f475 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -346,6 +346,9 @@ io_check_error(unsigned char reason, struct pt_regs *regs)
 	printk(KERN_EMERG "NMI: IOCK error (debug interrupt?)\n");
 	show_registers(regs);
 
+	if (panic_on_io_nmi)
+		panic("NMI IOCK error: Not continuing");
+
 	/* Re-enable the IOCK line, wait for a few seconds */
 	reason = (reason & 0xf) | 8;
 	outb(reason, 0x61);
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 5c3d6e81a7d..7030b5f911b 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -2157,7 +2157,7 @@ static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu, int level)
 		else
 			/* 32 bits PSE 4MB page */
 			context->rsvd_bits_mask[1][1] = rsvd_bits(13, 21);
-		context->rsvd_bits_mask[1][0] = ~0ull;
+		context->rsvd_bits_mask[1][0] = context->rsvd_bits_mask[1][0];
 		break;
 	case PT32E_ROOT_LEVEL:
 		context->rsvd_bits_mask[0][2] =
@@ -2170,7 +2170,7 @@ static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu, int level)
 		context->rsvd_bits_mask[1][1] = exb_bit_rsvd |
 			rsvd_bits(maxphyaddr, 62) |
 			rsvd_bits(13, 20);		/* large page */
-		context->rsvd_bits_mask[1][0] = ~0ull;
+		context->rsvd_bits_mask[1][0] = context->rsvd_bits_mask[1][0];
 		break;
 	case PT64_ROOT_LEVEL:
 		context->rsvd_bits_mask[0][3] = exb_bit_rsvd |
@@ -2186,7 +2186,7 @@ static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu, int level)
 		context->rsvd_bits_mask[1][1] = exb_bit_rsvd |
 			rsvd_bits(maxphyaddr, 51) |
 			rsvd_bits(13, 20);		/* large page */
-		context->rsvd_bits_mask[1][0] = ~0ull;
+		context->rsvd_bits_mask[1][0] = context->rsvd_bits_mask[1][0];
 		break;
 	}
 }
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index 258e4591e1c..67785f63539 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -281,7 +281,7 @@ static u64 *FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
 {
 	unsigned access = gw->pt_access;
 	struct kvm_mmu_page *shadow_page;
-	u64 spte, *sptep;
+	u64 spte, *sptep = NULL;
 	int direct;
 	gfn_t table_gfn;
 	int r;
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index e770bf349ec..356a0ce85c6 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -3012,6 +3012,12 @@ static int handle_vmcall(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	return 1;
 }
 
+static int handle_vmx_insn(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+{
+	kvm_queue_exception(vcpu, UD_VECTOR);
+	return 1;
+}
+
 static int handle_invlpg(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 {
 	unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
@@ -3198,6 +3204,15 @@ static int (*kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu,
 	[EXIT_REASON_HLT]                     = handle_halt,
 	[EXIT_REASON_INVLPG]		      = handle_invlpg,
 	[EXIT_REASON_VMCALL]                  = handle_vmcall,
+	[EXIT_REASON_VMCLEAR]	              = handle_vmx_insn,
+	[EXIT_REASON_VMLAUNCH]                = handle_vmx_insn,
+	[EXIT_REASON_VMPTRLD]                 = handle_vmx_insn,
+	[EXIT_REASON_VMPTRST]                 = handle_vmx_insn,
+	[EXIT_REASON_VMREAD]                  = handle_vmx_insn,
+	[EXIT_REASON_VMRESUME]                = handle_vmx_insn,
+	[EXIT_REASON_VMWRITE]                 = handle_vmx_insn,
+	[EXIT_REASON_VMOFF]                   = handle_vmx_insn,
+	[EXIT_REASON_VMON]                    = handle_vmx_insn,
 	[EXIT_REASON_TPR_BELOW_THRESHOLD]     = handle_tpr_below_threshold,
 	[EXIT_REASON_APIC_ACCESS]             = handle_apic_access,
 	[EXIT_REASON_WBINVD]                  = handle_wbinvd,
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 249540f9851..fe5474aec41 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -898,6 +898,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
 	case MSR_VM_HSAVE_PA:
 	case MSR_P6_EVNTSEL0:
 	case MSR_P6_EVNTSEL1:
+	case MSR_K7_EVNTSEL0:
 		data = 0;
 		break;
 	case MSR_MTRRcap:
diff --git a/arch/x86/kvm/x86_emulate.c b/arch/x86/kvm/x86_emulate.c
index c1b6c232e02..616de4628d6 100644
--- a/arch/x86/kvm/x86_emulate.c
+++ b/arch/x86/kvm/x86_emulate.c
@@ -1361,7 +1361,7 @@ static inline int writeback(struct x86_emulate_ctxt *ctxt,
 	return 0;
 }
 
-void toggle_interruptibility(struct x86_emulate_ctxt *ctxt, u32 mask)
+static void toggle_interruptibility(struct x86_emulate_ctxt *ctxt, u32 mask)
 {
 	u32 int_shadow = kvm_x86_ops->get_interrupt_shadow(ctxt->vcpu, mask);
 	/*
diff --git a/arch/x86/lib/delay.c b/arch/x86/lib/delay.c
index f4568605d7d..ff485d36118 100644
--- a/arch/x86/lib/delay.c
+++ b/arch/x86/lib/delay.c
@@ -55,8 +55,10 @@ static void delay_tsc(unsigned long loops)
 
 	preempt_disable();
 	cpu = smp_processor_id();
+	rdtsc_barrier();
 	rdtscl(bclock);
 	for (;;) {
+		rdtsc_barrier();
 		rdtscl(now);
 		if ((now - bclock) >= loops)
 			break;
@@ -78,6 +80,7 @@ static void delay_tsc(unsigned long loops)
 		if (unlikely(cpu != smp_processor_id())) {
 			loops -= (now - bclock);
 			cpu = smp_processor_id();
+			rdtsc_barrier();
 			rdtscl(bclock);
 		}
 	}
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index f53b57e4086..47ce9a2ce5e 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -177,20 +177,6 @@ static int __meminit save_mr(struct map_range *mr, int nr_range,
 	return nr_range;
 }
 
-#ifdef CONFIG_X86_64
-static void __init init_gbpages(void)
-{
-	if (direct_gbpages && cpu_has_gbpages)
-		printk(KERN_INFO "Using GB pages for direct mapping\n");
-	else
-		direct_gbpages = 0;
-}
-#else
-static inline void init_gbpages(void)
-{
-}
-#endif
-
 /*
  * Setup the direct mapping of the physical memory at PAGE_OFFSET.
  * This runs before bootmem is initialized and gets pages directly from
@@ -210,9 +196,6 @@ unsigned long __init_refok init_memory_mapping(unsigned long start,
 
 	printk(KERN_INFO "init_memory_mapping: %016lx-%016lx\n", start, end);
 
-	if (!after_bootmem)
-		init_gbpages();
-
 #if defined(CONFIG_DEBUG_PAGEALLOC) || defined(CONFIG_KMEMCHECK)
 	/*
 	 * For CONFIG_DEBUG_PAGEALLOC, identity mapping will use small pages.
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index c4378f4fd4a..b177652251a 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -598,6 +598,8 @@ void __init paging_init(void)
 
 	sparse_memory_present_with_active_regions(MAX_NUMNODES);
 	sparse_init();
+	/* clear the default setting with node 0 */
+	nodes_clear(node_states[N_NORMAL_MEMORY]);
 	free_area_init_nodes(max_zone_pfns);
 }
 
diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c
index c0ecf250fe5..b26626dc517 100644
--- a/arch/x86/pci/acpi.c
+++ b/arch/x86/pci/acpi.c
@@ -38,15 +38,26 @@ count_resource(struct acpi_resource *acpi_res, void *data)
 	struct acpi_resource_address64 addr;
 	acpi_status status;
 
-	if (info->res_num >= PCI_BUS_NUM_RESOURCES)
-		return AE_OK;
-
 	status = resource_to_addr(acpi_res, &addr);
 	if (ACPI_SUCCESS(status))
 		info->res_num++;
 	return AE_OK;
 }
 
+static int
+bus_has_transparent_bridge(struct pci_bus *bus)
+{
+	struct pci_dev *dev;
+
+	list_for_each_entry(dev, &bus->devices, bus_list) {
+		u16 class = dev->class >> 8;
+
+		if (class == PCI_CLASS_BRIDGE_PCI && dev->transparent)
+			return true;
+	}
+	return false;
+}
+
 static acpi_status
 setup_resource(struct acpi_resource *acpi_res, void *data)
 {
@@ -56,9 +67,7 @@ setup_resource(struct acpi_resource *acpi_res, void *data)
 	acpi_status status;
 	unsigned long flags;
 	struct resource *root;
-
-	if (info->res_num >= PCI_BUS_NUM_RESOURCES)
-		return AE_OK;
+	int max_root_bus_resources = PCI_BUS_NUM_RESOURCES;
 
 	status = resource_to_addr(acpi_res, &addr);
 	if (!ACPI_SUCCESS(status))
@@ -82,6 +91,18 @@ setup_resource(struct acpi_resource *acpi_res, void *data)
 	res->end = res->start + addr.address_length - 1;
 	res->child = NULL;
 
+	if (bus_has_transparent_bridge(info->bus))
+		max_root_bus_resources -= 3;
+	if (info->res_num >= max_root_bus_resources) {
+		printk(KERN_WARNING "PCI: Failed to allocate 0x%lx-0x%lx "
+			"from %s for %s due to _CRS returning more than "
+			"%d resource descriptors\n", (unsigned long) res->start,
+			(unsigned long) res->end, root->name, info->name,
+			max_root_bus_resources);
+		info->res_num++;
+		return AE_OK;
+	}
+
 	if (insert_resource(root, res)) {
 		printk(KERN_ERR "PCI: Failed to allocate 0x%lx-0x%lx "
 			"from %s for %s\n", (unsigned long) res->start,
diff --git a/arch/x86/pci/mmconfig-shared.c b/arch/x86/pci/mmconfig-shared.c
index 8766b0e216c..712443ec6d4 100644
--- a/arch/x86/pci/mmconfig-shared.c
+++ b/arch/x86/pci/mmconfig-shared.c
@@ -523,6 +523,69 @@ reject:
 
 static int __initdata known_bridge;
 
+static int acpi_mcfg_64bit_base_addr __initdata = FALSE;
+
+/* The physical address of the MMCONFIG aperture.  Set from ACPI tables. */
+struct acpi_mcfg_allocation *pci_mmcfg_config;
+int pci_mmcfg_config_num;
+
+static int __init acpi_mcfg_oem_check(struct acpi_table_mcfg *mcfg)
+{
+	if (!strcmp(mcfg->header.oem_id, "SGI"))
+		acpi_mcfg_64bit_base_addr = TRUE;
+
+	return 0;
+}
+
+static int __init pci_parse_mcfg(struct acpi_table_header *header)
+{
+	struct acpi_table_mcfg *mcfg;
+	unsigned long i;
+	int config_size;
+
+	if (!header)
+		return -EINVAL;
+
+	mcfg = (struct acpi_table_mcfg *)header;
+
+	/* how many config structures do we have */
+	pci_mmcfg_config_num = 0;
+	i = header->length - sizeof(struct acpi_table_mcfg);
+	while (i >= sizeof(struct acpi_mcfg_allocation)) {
+		++pci_mmcfg_config_num;
+		i -= sizeof(struct acpi_mcfg_allocation);
+	};
+	if (pci_mmcfg_config_num == 0) {
+		printk(KERN_ERR PREFIX "MMCONFIG has no entries\n");
+		return -ENODEV;
+	}
+
+	config_size = pci_mmcfg_config_num * sizeof(*pci_mmcfg_config);
+	pci_mmcfg_config = kmalloc(config_size, GFP_KERNEL);
+	if (!pci_mmcfg_config) {
+		printk(KERN_WARNING PREFIX
+		       "No memory for MCFG config tables\n");
+		return -ENOMEM;
+	}
+
+	memcpy(pci_mmcfg_config, &mcfg[1], config_size);
+
+	acpi_mcfg_oem_check(mcfg);
+
+	for (i = 0; i < pci_mmcfg_config_num; ++i) {
+		if ((pci_mmcfg_config[i].address > 0xFFFFFFFF) &&
+		    !acpi_mcfg_64bit_base_addr) {
+			printk(KERN_ERR PREFIX
+			       "MMCONFIG not in low 4GB of memory\n");
+			kfree(pci_mmcfg_config);
+			pci_mmcfg_config_num = 0;
+			return -ENODEV;
+		}
+	}
+
+	return 0;
+}
+
 static void __init __pci_mmcfg_init(int early)
 {
 	/* MMCONFIG disabled */
@@ -543,7 +606,7 @@ static void __init __pci_mmcfg_init(int early)
 	}
 
 	if (!known_bridge)
-		acpi_table_parse(ACPI_SIG_MCFG, acpi_parse_mcfg);
+		acpi_table_parse(ACPI_SIG_MCFG, pci_parse_mcfg);
 
 	pci_mmcfg_reject_broken(early);
 
diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c
index d277ef1eea5..b3d20b9cac6 100644
--- a/arch/x86/power/cpu.c
+++ b/arch/x86/power/cpu.c
@@ -244,7 +244,7 @@ static void __restore_processor_state(struct saved_context *ctxt)
 	do_fpu_end();
 	mtrr_ap_init();
 
-#ifdef CONFIG_X86_32
+#ifdef CONFIG_X86_OLD_MCE
 	mcheck_init(&boot_cpu_data);
 #endif
 }