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

15 files changed, 88 insertions, 114 deletions

diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 631086159c53..6b8ca3a0285d 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 bbbe4bbb6f34..8c44c232efcb 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 7c074eec39fb..d296f4a195c9 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 b7a79207295e..4d0216fcb36c 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 e5b27d8f1b47..28e5f5956042 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 6b26d4deada0..f1961c07af9a 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 cba8cd3e957b..20d498351105 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 5fdf63aaaba1..13bd6d6cf0bd 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 95ea5fa7d444..c8405718a4c3 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 7271fa33d791..c4ca89d9aaf4 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 328592fb6044..1a041bcf506b 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 a1712f2b50f1..6af96ee44200 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 be5ae80f897f..de2cab132844 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 124d40c575df..8ccabb8a2f6a 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 a0f48f5671c0..5204332f475d 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);