Merge branch 'devel-stable' into devel

Conflicts:
	arch/arm/Kconfig
	arch/arm/include/asm/system.h
	arch/arm/mm/Kconfig

69 files changed, 355 insertions, 121 deletions

diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 0061ea263061..cd40aba6aa95 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -31,6 +31,7 @@
 #include <linux/module.h>
 #include <linux/dmi.h>
 #include <linux/irq.h>
+#include <linux/slab.h>
 #include <linux/bootmem.h>
 #include <linux/ioport.h>
 #include <linux/pci.h>
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 3a4bf35c179b..1a160d5d44d0 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -8,6 +8,7 @@
 #include <linux/vmalloc.h>
 #include <linux/memory.h>
 #include <linux/stop_machine.h>
+#include <linux/slab.h>
 #include <asm/alternative.h>
 #include <asm/sections.h>
 #include <asm/pgtable.h>
diff --git a/arch/x86/kernel/amd_iommu.c b/arch/x86/kernel/amd_iommu.c
index adb0ba025702..f854d89b7edf 100644
--- a/arch/x86/kernel/amd_iommu.c
+++ b/arch/x86/kernel/amd_iommu.c
@@ -18,8 +18,8 @@
  */
 
 #include <linux/pci.h>
-#include <linux/gfp.h>
 #include <linux/bitmap.h>
+#include <linux/slab.h>
 #include <linux/debugfs.h>
 #include <linux/scatterlist.h>
 #include <linux/dma-mapping.h>
@@ -118,7 +118,7 @@ static bool check_device(struct device *dev)
 		return false;
 
 	/* No device or no PCI device */
-	if (!dev || dev->bus != &pci_bus_type)
+	if (dev->bus != &pci_bus_type)
 		return false;
 
 	devid = get_device_id(dev);
@@ -392,6 +392,7 @@ static int __iommu_queue_command(struct amd_iommu *iommu, struct iommu_cmd *cmd)
 	u32 tail, head;
 	u8 *target;
 
+	WARN_ON(iommu->cmd_buf_size & CMD_BUFFER_UNINITIALIZED);
 	tail = readl(iommu->mmio_base + MMIO_CMD_TAIL_OFFSET);
 	target = iommu->cmd_buf + tail;
 	memcpy_toio(target, cmd, sizeof(*cmd));
@@ -2186,7 +2187,7 @@ static void prealloc_protection_domains(void)
 	struct dma_ops_domain *dma_dom;
 	u16 devid;
 
-	while ((dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev)) != NULL) {
+	for_each_pci_dev(dev) {
 
 		/* Do we handle this device? */
 		if (!check_device(&dev->dev))
@@ -2298,7 +2299,7 @@ static void cleanup_domain(struct protection_domain *domain)
 	list_for_each_entry_safe(dev_data, next, &domain->dev_list, list) {
 		struct device *dev = dev_data->dev;
 
-		do_detach(dev);
+		__detach_device(dev);
 		atomic_set(&dev_data->bind, 0);
 	}
 
@@ -2327,6 +2328,7 @@ static struct protection_domain *protection_domain_alloc(void)
 		return NULL;
 
 	spin_lock_init(&domain->lock);
+	mutex_init(&domain->api_lock);
 	domain->id = domain_id_alloc();
 	if (!domain->id)
 		goto out_err;
@@ -2379,9 +2381,7 @@ static void amd_iommu_domain_destroy(struct iommu_domain *dom)
 
 	free_pagetable(domain);
 
-	domain_id_free(domain->id);
-
-	kfree(domain);
+	protection_domain_free(domain);
 
 	dom->priv = NULL;
 }
@@ -2456,6 +2456,8 @@ static int amd_iommu_map_range(struct iommu_domain *dom,
 	iova  &= PAGE_MASK;
 	paddr &= PAGE_MASK;
 
+	mutex_lock(&domain->api_lock);
+
 	for (i = 0; i < npages; ++i) {
 		ret = iommu_map_page(domain, iova, paddr, prot, PM_MAP_4k);
 		if (ret)
@@ -2465,6 +2467,8 @@ static int amd_iommu_map_range(struct iommu_domain *dom,
 		paddr += PAGE_SIZE;
 	}
 
+	mutex_unlock(&domain->api_lock);
+
 	return 0;
 }
 
@@ -2477,12 +2481,16 @@ static void amd_iommu_unmap_range(struct iommu_domain *dom,
 
 	iova  &= PAGE_MASK;
 
+	mutex_lock(&domain->api_lock);
+
 	for (i = 0; i < npages; ++i) {
 		iommu_unmap_page(domain, iova, PM_MAP_4k);
 		iova  += PAGE_SIZE;
 	}
 
 	iommu_flush_tlb_pde(domain);
+
+	mutex_unlock(&domain->api_lock);
 }
 
 static phys_addr_t amd_iommu_iova_to_phys(struct iommu_domain *dom,
diff --git a/arch/x86/kernel/amd_iommu_init.c b/arch/x86/kernel/amd_iommu_init.c
index 9dc91b431470..6360abf993d4 100644
--- a/arch/x86/kernel/amd_iommu_init.c
+++ b/arch/x86/kernel/amd_iommu_init.c
@@ -19,8 +19,8 @@
 
 #include <linux/pci.h>
 #include <linux/acpi.h>
-#include <linux/gfp.h>
 #include <linux/list.h>
+#include <linux/slab.h>
 #include <linux/sysdev.h>
 #include <linux/interrupt.h>
 #include <linux/msi.h>
@@ -138,9 +138,9 @@ int amd_iommus_present;
 bool amd_iommu_np_cache __read_mostly;
 
 /*
- * Set to true if ACPI table parsing and hardware intialization went properly
+ * The ACPI table parsing functions set this variable on an error
  */
-static bool amd_iommu_initialized;
+static int __initdata amd_iommu_init_err;
 
 /*
  * List of protection domains - used during resume
@@ -391,9 +391,11 @@ static int __init find_last_devid_acpi(struct acpi_table_header *table)
 	 */
 	for (i = 0; i < table->length; ++i)
 		checksum += p[i];
-	if (checksum != 0)
+	if (checksum != 0) {
 		/* ACPI table corrupt */
-		return -ENODEV;
+		amd_iommu_init_err = -ENODEV;
+		return 0;
+	}
 
 	p += IVRS_HEADER_LENGTH;
 
@@ -436,7 +438,7 @@ static u8 * __init alloc_command_buffer(struct amd_iommu *iommu)
 	if (cmd_buf == NULL)
 		return NULL;
 
-	iommu->cmd_buf_size = CMD_BUFFER_SIZE;
+	iommu->cmd_buf_size = CMD_BUFFER_SIZE | CMD_BUFFER_UNINITIALIZED;
 
 	return cmd_buf;
 }
@@ -472,12 +474,13 @@ static void iommu_enable_command_buffer(struct amd_iommu *iommu)
 		    &entry, sizeof(entry));
 
 	amd_iommu_reset_cmd_buffer(iommu);
+	iommu->cmd_buf_size &= ~(CMD_BUFFER_UNINITIALIZED);
 }
 
 static void __init free_command_buffer(struct amd_iommu *iommu)
 {
 	free_pages((unsigned long)iommu->cmd_buf,
-		   get_order(iommu->cmd_buf_size));
+		   get_order(iommu->cmd_buf_size & ~(CMD_BUFFER_UNINITIALIZED)));
 }
 
 /* allocates the memory where the IOMMU will log its events to */
@@ -920,11 +923,16 @@ static int __init init_iommu_all(struct acpi_table_header *table)
 				    h->mmio_phys);
 
 			iommu = kzalloc(sizeof(struct amd_iommu), GFP_KERNEL);
-			if (iommu == NULL)
-				return -ENOMEM;
+			if (iommu == NULL) {
+				amd_iommu_init_err = -ENOMEM;
+				return 0;
+			}
+
 			ret = init_iommu_one(iommu, h);
-			if (ret)
-				return ret;
+			if (ret) {
+				amd_iommu_init_err = ret;
+				return 0;
+			}
 			break;
 		default:
 			break;
@@ -934,8 +942,6 @@ static int __init init_iommu_all(struct acpi_table_header *table)
 	}
 	WARN_ON(p != end);
 
-	amd_iommu_initialized = true;
-
 	return 0;
 }
 
@@ -1211,6 +1217,10 @@ static int __init amd_iommu_init(void)
 	if (acpi_table_parse("IVRS", find_last_devid_acpi) != 0)
 		return -ENODEV;
 
+	ret = amd_iommu_init_err;
+	if (ret)
+		goto out;
+
 	dev_table_size     = tbl_size(DEV_TABLE_ENTRY_SIZE);
 	alias_table_size   = tbl_size(ALIAS_TABLE_ENTRY_SIZE);
 	rlookup_table_size = tbl_size(RLOOKUP_TABLE_ENTRY_SIZE);
@@ -1270,12 +1280,19 @@ static int __init amd_iommu_init(void)
 	if (acpi_table_parse("IVRS", init_iommu_all) != 0)
 		goto free;
 
-	if (!amd_iommu_initialized)
+	if (amd_iommu_init_err) {
+		ret = amd_iommu_init_err;
 		goto free;
+	}
 
 	if (acpi_table_parse("IVRS", init_memory_definitions) != 0)
 		goto free;
 
+	if (amd_iommu_init_err) {
+		ret = amd_iommu_init_err;
+		goto free;
+	}
+
 	ret = sysdev_class_register(&amd_iommu_sysdev_class);
 	if (ret)
 		goto free;
@@ -1288,6 +1305,8 @@ static int __init amd_iommu_init(void)
 	if (ret)
 		goto free;
 
+	enable_iommus();
+
 	if (iommu_pass_through)
 		ret = amd_iommu_init_passthrough();
 	else
@@ -1300,8 +1319,6 @@ static int __init amd_iommu_init(void)
 
 	amd_iommu_init_notifier();
 
-	enable_iommus();
-
 	if (iommu_pass_through)
 		goto out;
 
@@ -1315,6 +1332,7 @@ out:
 	return ret;
 
 free:
+	disable_iommus();
 
 	amd_iommu_uninit_devices();
 
diff --git a/arch/x86/kernel/apb_timer.c b/arch/x86/kernel/apb_timer.c
index 4b7099526d2c..a35347501d36 100644
--- a/arch/x86/kernel/apb_timer.c
+++ b/arch/x86/kernel/apb_timer.c
@@ -33,6 +33,7 @@
 #include <linux/errno.h>
 #include <linux/init.h>
 #include <linux/sysdev.h>
+#include <linux/slab.h>
 #include <linux/pm.h>
 #include <linux/pci.h>
 #include <linux/sfi.h>
@@ -428,7 +429,7 @@ static int apbt_cpuhp_notify(struct notifier_block *n,
 
 static __init int apbt_late_init(void)
 {
-	if (disable_apbt_percpu)
+	if (disable_apbt_percpu || !apb_timer_block_enabled)
 		return 0;
 	/* This notifier should be called after workqueue is ready */
 	hotcpu_notifier(apbt_cpuhp_notify, -20);
diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c
index 3704997e8b25..b5d8b0bcf235 100644
--- a/arch/x86/kernel/aperture_64.c
+++ b/arch/x86/kernel/aperture_64.c
@@ -393,6 +393,7 @@ void __init gart_iommu_hole_init(void)
 	for (i = 0; i < ARRAY_SIZE(bus_dev_ranges); i++) {
 		int bus;
 		int dev_base, dev_limit;
+		u32 ctl;
 
 		bus = bus_dev_ranges[i].bus;
 		dev_base = bus_dev_ranges[i].dev_base;
@@ -406,7 +407,19 @@ void __init gart_iommu_hole_init(void)
 			gart_iommu_aperture = 1;
 			x86_init.iommu.iommu_init = gart_iommu_init;
 
-			aper_order = (read_pci_config(bus, slot, 3, AMD64_GARTAPERTURECTL) >> 1) & 7;
+			ctl = read_pci_config(bus, slot, 3,
+					      AMD64_GARTAPERTURECTL);
+
+			/*
+			 * Before we do anything else disable the GART. It may
+			 * still be enabled if we boot into a crash-kernel here.
+			 * Reconfiguring the GART while it is enabled could have
+			 * unknown side-effects.
+			 */
+			ctl &= ~GARTEN;
+			write_pci_config(bus, slot, 3, AMD64_GARTAPERTURECTL, ctl);
+
+			aper_order = (ctl >> 1) & 7;
 			aper_size = (32 * 1024 * 1024) << aper_order;
 			aper_base = read_pci_config(bus, slot, 3, AMD64_GARTAPERTUREBASE) & 0x7fff;
 			aper_base <<= 25;
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 00187f1fcfb7..e5a4a1e01618 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -1640,8 +1640,10 @@ int __init APIC_init_uniprocessor(void)
 	}
 #endif
 
+#ifndef CONFIG_SMP
 	enable_IR_x2apic();
 	default_setup_apic_routing();
+#endif
 
 	verify_local_APIC();
 	connect_bsp_APIC();
diff --git a/arch/x86/kernel/apic/es7000_32.c b/arch/x86/kernel/apic/es7000_32.c
index dd2b5f264643..03ba1b895f5e 100644
--- a/arch/x86/kernel/apic/es7000_32.c
+++ b/arch/x86/kernel/apic/es7000_32.c
@@ -42,6 +42,7 @@
 #include <linux/errno.h>
 #include <linux/acpi.h>
 #include <linux/init.h>
+#include <linux/gfp.h>
 #include <linux/nmi.h>
 #include <linux/smp.h>
 #include <linux/io.h>
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index e4e0ddcb1546..eb2789c3f721 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -36,6 +36,7 @@
 #include <linux/freezer.h>
 #include <linux/kthread.h>
 #include <linux/jiffies.h>	/* time_after() */
+#include <linux/slab.h>
 #ifdef CONFIG_ACPI
 #include <acpi/acpi_bus.h>
 #endif
@@ -1268,6 +1269,14 @@ void __setup_vector_irq(int cpu)
 	/* Mark the inuse vectors */
 	for_each_irq_desc(irq, desc) {
 		cfg = desc->chip_data;
+
+		/*
+		 * If it is a legacy IRQ handled by the legacy PIC, this cpu
+		 * will be part of the irq_cfg's domain.
+		 */
+		if (irq < legacy_pic->nr_legacy_irqs && !IO_APIC_IRQ(irq))
+			cpumask_set_cpu(cpu, cfg->domain);
+
 		if (!cpumask_test_cpu(cpu, cfg->domain))
 			continue;
 		vector = cfg->vector;
@@ -2536,6 +2545,9 @@ void irq_force_complete_move(int irq)
 	struct irq_desc *desc = irq_to_desc(irq);
 	struct irq_cfg *cfg = desc->chip_data;
 
+	if (!cfg)
+		return;
+
 	__irq_complete_move(&desc, cfg->vector);
 }
 #else
diff --git a/arch/x86/kernel/apic/nmi.c b/arch/x86/kernel/apic/nmi.c
index 8aa65adbd25d..1edaf15c0b8e 100644
--- a/arch/x86/kernel/apic/nmi.c
+++ b/arch/x86/kernel/apic/nmi.c
@@ -18,6 +18,7 @@
 #include <linux/delay.h>
 #include <linux/interrupt.h>
 #include <linux/module.h>
+#include <linux/slab.h>
 #include <linux/sysdev.h>
 #include <linux/sysctl.h>
 #include <linux/percpu.h>
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index 49dbeaef2a27..c085d52dbaf2 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -17,6 +17,7 @@
 #include <linux/ctype.h>
 #include <linux/sched.h>
 #include <linux/timer.h>
+#include <linux/slab.h>
 #include <linux/cpu.h>
 #include <linux/init.h>
 #include <linux/io.h>
diff --git a/arch/x86/kernel/bootflag.c b/arch/x86/kernel/bootflag.c
index 30f25a75fe28..5de7f4c56971 100644
--- a/arch/x86/kernel/bootflag.c
+++ b/arch/x86/kernel/bootflag.c
@@ -5,7 +5,6 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/string.h>
-#include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/acpi.h>
 #include <asm/io.h>
diff --git a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
index 1b1920fa7c80..459168083b77 100644
--- a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
+++ b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
@@ -33,6 +33,7 @@
 #include <linux/cpufreq.h>
 #include <linux/compiler.h>
 #include <linux/dmi.h>
+#include <linux/slab.h>
 #include <trace/events/power.h>
 
 #include <linux/acpi.h>
diff --git a/arch/x86/kernel/cpu/cpufreq/elanfreq.c b/arch/x86/kernel/cpu/cpufreq/elanfreq.c
index 006b278b0d5d..c587db472a75 100644
--- a/arch/x86/kernel/cpu/cpufreq/elanfreq.c
+++ b/arch/x86/kernel/cpu/cpufreq/elanfreq.c
@@ -20,7 +20,6 @@
 #include <linux/module.h>
 #include <linux/init.h>
 
-#include <linux/slab.h>
 #include <linux/delay.h>
 #include <linux/cpufreq.h>
 
diff --git a/arch/x86/kernel/cpu/cpufreq/gx-suspmod.c b/arch/x86/kernel/cpu/cpufreq/gx-suspmod.c
index ac27ec2264d5..16e3483be9e3 100644
--- a/arch/x86/kernel/cpu/cpufreq/gx-suspmod.c
+++ b/arch/x86/kernel/cpu/cpufreq/gx-suspmod.c
@@ -80,6 +80,7 @@
 #include <linux/cpufreq.h>
 #include <linux/pci.h>
 #include <linux/errno.h>
+#include <linux/slab.h>
 
 #include <asm/processor-cyrix.h>
 
diff --git a/arch/x86/kernel/cpu/cpufreq/longrun.c b/arch/x86/kernel/cpu/cpufreq/longrun.c
index da5f70fcb766..e7b559d74c52 100644
--- a/arch/x86/kernel/cpu/cpufreq/longrun.c
+++ b/arch/x86/kernel/cpu/cpufreq/longrun.c
@@ -9,7 +9,6 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/init.h>
-#include <linux/slab.h>
 #include <linux/cpufreq.h>
 #include <linux/timex.h>
 
diff --git a/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c b/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c
index 869615193720..7b8a8ba67b07 100644
--- a/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c
+++ b/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c
@@ -25,7 +25,6 @@
 #include <linux/init.h>
 #include <linux/smp.h>
 #include <linux/cpufreq.h>
-#include <linux/slab.h>
 #include <linux/cpumask.h>
 #include <linux/timex.h>
 
diff --git a/arch/x86/kernel/cpu/cpufreq/pcc-cpufreq.c b/arch/x86/kernel/cpu/cpufreq/pcc-cpufreq.c
index ff36d2979a90..ce7cde713e71 100644
--- a/arch/x86/kernel/cpu/cpufreq/pcc-cpufreq.c
+++ b/arch/x86/kernel/cpu/cpufreq/pcc-cpufreq.c
@@ -30,6 +30,7 @@
 #include <linux/sched.h>
 #include <linux/cpufreq.h>
 #include <linux/compiler.h>
+#include <linux/slab.h>
 
 #include <linux/acpi.h>
 #include <linux/io.h>
diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k6.c b/arch/x86/kernel/cpu/cpufreq/powernow-k6.c
index cb01dac267d3..b3379d6a5c57 100644
--- a/arch/x86/kernel/cpu/cpufreq/powernow-k6.c
+++ b/arch/x86/kernel/cpu/cpufreq/powernow-k6.c
@@ -13,7 +13,6 @@
 #include <linux/init.h>
 #include <linux/cpufreq.h>
 #include <linux/ioport.h>
-#include <linux/slab.h>
 #include <linux/timex.h>
 #include <linux/io.h>
 
diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
index d360b56e9825..b6215b9798e2 100644
--- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
+++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
@@ -929,7 +929,8 @@ static int fill_powernow_table_pstate(struct powernow_k8_data *data,
 		powernow_table[i].index = index;
 
 		/* Frequency may be rounded for these */
-		if (boot_cpu_data.x86 == 0x10 || boot_cpu_data.x86 == 0x11) {
+		if ((boot_cpu_data.x86 == 0x10 && boot_cpu_data.x86_model < 10)
+				 || boot_cpu_data.x86 == 0x11) {
 			powernow_table[i].frequency =
 				freq_from_fid_did(lo & 0x3f, (lo >> 6) & 7);
 		} else
diff --git a/arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c b/arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c
index 8d672ef162ce..9b1ff37de46a 100644
--- a/arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c
+++ b/arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c
@@ -20,6 +20,7 @@
 #include <linux/sched.h>	/* current */
 #include <linux/delay.h>
 #include <linux/compiler.h>
+#include <linux/gfp.h>
 
 #include <asm/msr.h>
 #include <asm/processor.h>
diff --git a/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c b/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c
index 2ce8e0b5cc54..561758e95180 100644
--- a/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c
+++ b/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c
@@ -23,7 +23,6 @@
 #include <linux/init.h>
 #include <linux/cpufreq.h>
 #include <linux/pci.h>
-#include <linux/slab.h>
 #include <linux/sched.h>
 
 #include "speedstep-lib.h"
diff --git a/arch/x86/kernel/cpu/cpufreq/speedstep-lib.c b/arch/x86/kernel/cpu/cpufreq/speedstep-lib.c
index ad0083abfa23..a94ec6be69fa 100644
--- a/arch/x86/kernel/cpu/cpufreq/speedstep-lib.c
+++ b/arch/x86/kernel/cpu/cpufreq/speedstep-lib.c
@@ -13,7 +13,6 @@
 #include <linux/moduleparam.h>
 #include <linux/init.h>
 #include <linux/cpufreq.h>
-#include <linux/slab.h>
 
 #include <asm/msr.h>
 #include <asm/tsc.h>
diff --git a/arch/x86/kernel/cpu/cpufreq/speedstep-smi.c b/arch/x86/kernel/cpu/cpufreq/speedstep-smi.c
index 04d73c114e49..8abd869baabf 100644
--- a/arch/x86/kernel/cpu/cpufreq/speedstep-smi.c
+++ b/arch/x86/kernel/cpu/cpufreq/speedstep-smi.c
@@ -17,7 +17,6 @@
 #include <linux/moduleparam.h>
 #include <linux/init.h>
 #include <linux/cpufreq.h>
-#include <linux/slab.h>
 #include <linux/delay.h>
 #include <linux/io.h>
 #include <asm/ist.h>
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 7e1cca13af35..1366c7cfd483 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -47,6 +47,27 @@ static void __cpuinit early_init_intel(struct cpuinfo_x86 *c)
 		(c->x86 == 0x6 && c->x86_model >= 0x0e))
 		set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
 
+	/*
+	 * Atom erratum AAE44/AAF40/AAG38/AAH41:
+	 *
+	 * A race condition between speculative fetches and invalidating
+	 * a large page.  This is worked around in microcode, but we
+	 * need the microcode to have already been loaded... so if it is
+	 * not, recommend a BIOS update and disable large pages.
+	 */
+	if (c->x86 == 6 && c->x86_model == 0x1c && c->x86_mask <= 2) {
+		u32 ucode, junk;
+
+		wrmsr(MSR_IA32_UCODE_REV, 0, 0);
+		sync_core();
+		rdmsr(MSR_IA32_UCODE_REV, junk, ucode);
+
+		if (ucode < 0x20e) {
+			printk(KERN_WARNING "Atom PSE erratum detected, BIOS microcode update recommended\n");
+			clear_cpu_cap(c, X86_FEATURE_PSE);
+		}
+	}
+
 #ifdef CONFIG_X86_64
 	set_cpu_cap(c, X86_FEATURE_SYSENTER32);
 #else
diff --git a/arch/x86/kernel/cpu/mcheck/mce-inject.c b/arch/x86/kernel/cpu/mcheck/mce-inject.c
index 73734baa50f2..e7dbde7bfedb 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-inject.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-inject.c
@@ -22,6 +22,7 @@
 #include <linux/kdebug.h>
 #include <linux/cpu.h>
 #include <linux/sched.h>
+#include <linux/gfp.h>
 #include <asm/mce.h>
 #include <asm/apic.h>
 
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 3ab9c886b613..8a6f0afa767e 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -26,6 +26,7 @@
 #include <linux/sched.h>
 #include <linux/sysfs.h>
 #include <linux/types.h>
+#include <linux/slab.h>
 #include <linux/init.h>
 #include <linux/kmod.h>
 #include <linux/poll.h>
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index cda932ca3ade..224392d8fe8c 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -21,6 +21,7 @@
 #include <linux/errno.h>
 #include <linux/sched.h>
 #include <linux/sysfs.h>
+#include <linux/slab.h>
 #include <linux/init.h>
 #include <linux/cpu.h>
 #include <linux/smp.h>
diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c
index d15df6e49bf0..62b48e40920a 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_intel.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c
@@ -5,6 +5,7 @@
  * Author: Andi Kleen
  */
 
+#include <linux/gfp.h>
 #include <linux/init.h>
 #include <linux/interrupt.h>
 #include <linux/percpu.h>
diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c
index 9aa5dc76ff4a..fd31a441c61c 100644
--- a/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/arch/x86/kernel/cpu/mtrr/generic.c
@@ -6,7 +6,6 @@
 
 #include <linux/module.h>
 #include <linux/init.h>
-#include <linux/slab.h>
 #include <linux/io.h>
 #include <linux/mm.h>
 
diff --git a/arch/x86/kernel/cpu/mtrr/if.c b/arch/x86/kernel/cpu/mtrr/if.c
index e006e56f699c..79289632cb27 100644
--- a/arch/x86/kernel/cpu/mtrr/if.c
+++ b/arch/x86/kernel/cpu/mtrr/if.c
@@ -5,6 +5,7 @@
 #include <linux/module.h>
 #include <linux/ctype.h>
 #include <linux/string.h>
+#include <linux/slab.h>
 #include <linux/init.h>
 
 #define LINE_SIZE 80
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 60398a0d947c..db5bdc8addf8 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -21,6 +21,7 @@
 #include <linux/kdebug.h>
 #include <linux/sched.h>
 #include <linux/uaccess.h>
+#include <linux/slab.h>
 #include <linux/highmem.h>
 #include <linux/cpu.h>
 #include <linux/bitops.h>
@@ -28,6 +29,7 @@
 #include <asm/apic.h>
 #include <asm/stacktrace.h>
 #include <asm/nmi.h>
+#include <asm/compat.h>
 
 static u64 perf_event_mask __read_mostly;
 
@@ -158,7 +160,7 @@ struct x86_pmu {
 						 struct perf_event *event);
 	struct event_constraint *event_constraints;
 
-	void		(*cpu_prepare)(int cpu);
+	int		(*cpu_prepare)(int cpu);
 	void		(*cpu_starting)(int cpu);
 	void		(*cpu_dying)(int cpu);
 	void		(*cpu_dead)(int cpu);
@@ -1333,11 +1335,12 @@ static int __cpuinit
 x86_pmu_notifier(struct notifier_block *self, unsigned long action, void *hcpu)
 {
 	unsigned int cpu = (long)hcpu;
+	int ret = NOTIFY_OK;
 
 	switch (action & ~CPU_TASKS_FROZEN) {
 	case CPU_UP_PREPARE:
 		if (x86_pmu.cpu_prepare)
-			x86_pmu.cpu_prepare(cpu);
+			ret = x86_pmu.cpu_prepare(cpu);
 		break;
 
 	case CPU_STARTING:
@@ -1350,6 +1353,7 @@ x86_pmu_notifier(struct notifier_block *self, unsigned long action, void *hcpu)
 			x86_pmu.cpu_dying(cpu);
 		break;
 
+	case CPU_UP_CANCELED:
 	case CPU_DEAD:
 		if (x86_pmu.cpu_dead)
 			x86_pmu.cpu_dead(cpu);
@@ -1359,7 +1363,7 @@ x86_pmu_notifier(struct notifier_block *self, unsigned long action, void *hcpu)
 		break;
 	}
 
-	return NOTIFY_OK;
+	return ret;
 }
 
 static void __init pmu_check_apic(void)
@@ -1628,14 +1632,42 @@ copy_from_user_nmi(void *to, const void __user *from, unsigned long n)
 	return len;
 }
 
-static int copy_stack_frame(const void __user *fp, struct stack_frame *frame)
+#ifdef CONFIG_COMPAT
+static inline int
+perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry)
 {
-	unsigned long bytes;
+	/* 32-bit process in 64-bit kernel. */
+	struct stack_frame_ia32 frame;
+	const void __user *fp;
 
-	bytes = copy_from_user_nmi(frame, fp, sizeof(*frame));
+	if (!test_thread_flag(TIF_IA32))
+		return 0;
+
+	fp = compat_ptr(regs->bp);
+	while (entry->nr < PERF_MAX_STACK_DEPTH) {
+		unsigned long bytes;
+		frame.next_frame     = 0;
+		frame.return_address = 0;
+
+		bytes = copy_from_user_nmi(&frame, fp, sizeof(frame));
+		if (bytes != sizeof(frame))
+			break;
+
+		if (fp < compat_ptr(regs->sp))
+			break;
 
-	return bytes == sizeof(*frame);
+		callchain_store(entry, frame.return_address);
+		fp = compat_ptr(frame.next_frame);
+	}
+	return 1;
+}
+#else
+static inline int
+perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry)
+{
+    return 0;
 }
+#endif
 
 static void
 perf_callchain_user(struct pt_regs *regs, struct perf_callchain_entry *entry)
@@ -1651,11 +1683,16 @@ perf_callchain_user(struct pt_regs *regs, struct perf_callchain_entry *entry)
 	callchain_store(entry, PERF_CONTEXT_USER);
 	callchain_store(entry, regs->ip);
 
+	if (perf_callchain_user32(regs, entry))
+		return;
+
 	while (entry->nr < PERF_MAX_STACK_DEPTH) {
+		unsigned long bytes;
 		frame.next_frame	     = NULL;
 		frame.return_address = 0;
 
-		if (!copy_stack_frame(fp, &frame))
+		bytes = copy_from_user_nmi(&frame, fp, sizeof(frame));
+		if (bytes != sizeof(frame))
 			break;
 
 		if ((unsigned long)fp < regs->sp)
@@ -1702,7 +1739,6 @@ struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
 	return entry;
 }
 
-#ifdef CONFIG_EVENT_TRACING
 void perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip, int skip)
 {
 	regs->ip = ip;
@@ -1714,4 +1750,3 @@ void perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip, int ski
 	regs->cs = __KERNEL_CS;
 	local_save_flags(regs->flags);
 }
-#endif
diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c
index 573458f1caf2..db6f7d4056e1 100644
--- a/arch/x86/kernel/cpu/perf_event_amd.c
+++ b/arch/x86/kernel/cpu/perf_event_amd.c
@@ -137,6 +137,13 @@ static inline int amd_is_nb_event(struct hw_perf_event *hwc)
 	return (hwc->config & 0xe0) == 0xe0;
 }
 
+static inline int amd_has_nb(struct cpu_hw_events *cpuc)
+{
+	struct amd_nb *nb = cpuc->amd_nb;
+
+	return nb && nb->nb_id != -1;
+}
+
 static void amd_put_event_constraints(struct cpu_hw_events *cpuc,
 				      struct perf_event *event)
 {
@@ -147,7 +154,7 @@ static void amd_put_event_constraints(struct cpu_hw_events *cpuc,
 	/*
 	 * only care about NB events
 	 */
-	if (!(nb && amd_is_nb_event(hwc)))
+	if (!(amd_has_nb(cpuc) && amd_is_nb_event(hwc)))
 		return;
 
 	/*
@@ -214,7 +221,7 @@ amd_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event)
 	/*
 	 * if not NB event or no NB, then no constraints
 	 */
-	if (!(nb && amd_is_nb_event(hwc)))
+	if (!(amd_has_nb(cpuc) && amd_is_nb_event(hwc)))
 		return &unconstrained;
 
 	/*
@@ -293,51 +300,55 @@ static struct amd_nb *amd_alloc_nb(int cpu, int nb_id)
 	return nb;
 }
 
-static void amd_pmu_cpu_online(int cpu)
+static int amd_pmu_cpu_prepare(int cpu)
+{
+	struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu);
+
+	WARN_ON_ONCE(cpuc->amd_nb);
+
+	if (boot_cpu_data.x86_max_cores < 2)
+		return NOTIFY_OK;
+
+	cpuc->amd_nb = amd_alloc_nb(cpu, -1);
+	if (!cpuc->amd_nb)
+		return NOTIFY_BAD;
+
+	return NOTIFY_OK;
+}
+
+static void amd_pmu_cpu_starting(int cpu)
 {
-	struct cpu_hw_events *cpu1, *cpu2;
-	struct amd_nb *nb = NULL;
+	struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu);
+	struct amd_nb *nb;
 	int i, nb_id;
 
 	if (boot_cpu_data.x86_max_cores < 2)
 		return;
 
-	/*
-	 * function may be called too early in the
-	 * boot process, in which case nb_id is bogus
-	 */
 	nb_id = amd_get_nb_id(cpu);
-	if (nb_id == BAD_APICID)
-		return;
-
-	cpu1 = &per_cpu(cpu_hw_events, cpu);
-	cpu1->amd_nb = NULL;
+	WARN_ON_ONCE(nb_id == BAD_APICID);
 
 	raw_spin_lock(&amd_nb_lock);
 
 	for_each_online_cpu(i) {
-		cpu2 = &per_cpu(cpu_hw_events, i);
-		nb = cpu2->amd_nb;
-		if (!nb)
+		nb = per_cpu(cpu_hw_events, i).amd_nb;
+		if (WARN_ON_ONCE(!nb))
 			continue;
-		if (nb->nb_id == nb_id)
-			goto found;
-	}
 
-	nb = amd_alloc_nb(cpu, nb_id);
-	if (!nb) {
-		pr_err("perf_events: failed NB allocation for CPU%d\n", cpu);
-		raw_spin_unlock(&amd_nb_lock);
-		return;
+		if (nb->nb_id == nb_id) {
+			kfree(cpuc->amd_nb);
+			cpuc->amd_nb = nb;
+			break;
+		}
 	}
-found:
-	nb->refcnt++;
-	cpu1->amd_nb = nb;
+
+	cpuc->amd_nb->nb_id = nb_id;
+	cpuc->amd_nb->refcnt++;
 
 	raw_spin_unlock(&amd_nb_lock);
 }
 
-static void amd_pmu_cpu_offline(int cpu)
+static void amd_pmu_cpu_dead(int cpu)
 {
 	struct cpu_hw_events *cpuhw;
 
@@ -348,10 +359,14 @@ static void amd_pmu_cpu_offline(int cpu)
 
 	raw_spin_lock(&amd_nb_lock);
 
-	if (--cpuhw->amd_nb->refcnt == 0)
-		kfree(cpuhw->amd_nb);
+	if (cpuhw->amd_nb) {
+		struct amd_nb *nb = cpuhw->amd_nb;
+
+		if (nb->nb_id == -1 || --nb->refcnt == 0)
+			kfree(nb);
 
-	cpuhw->amd_nb = NULL;
+		cpuhw->amd_nb = NULL;
+	}
 
 	raw_spin_unlock(&amd_nb_lock);
 }
@@ -377,8 +392,9 @@ static __initconst struct x86_pmu amd_pmu = {
 	.get_event_constraints	= amd_get_event_constraints,
 	.put_event_constraints	= amd_put_event_constraints,
 
-	.cpu_prepare		= amd_pmu_cpu_online,
-	.cpu_dead		= amd_pmu_cpu_offline,
+	.cpu_prepare		= amd_pmu_cpu_prepare,
+	.cpu_starting		= amd_pmu_cpu_starting,
+	.cpu_dead		= amd_pmu_cpu_dead,
 };
 
 static __init int amd_pmu_init(void)
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 84bfde64a337..9c794ac87837 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -936,6 +936,7 @@ static __init int intel_pmu_init(void)
 
 	case 26: /* 45 nm nehalem, "Bloomfield" */
 	case 30: /* 45 nm nehalem, "Lynnfield" */
+	case 46: /* 45 nm nehalem-ex, "Beckton" */
 		memcpy(hw_cache_event_ids, nehalem_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
 
diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c
index 1cbed97b59cf..dfdb4dba2320 100644
--- a/arch/x86/kernel/cpu/vmware.c
+++ b/arch/x86/kernel/cpu/vmware.c
@@ -22,6 +22,7 @@
  */
 
 #include <linux/dmi.h>
+#include <linux/module.h>
 #include <asm/div64.h>
 #include <asm/vmware.h>
 #include <asm/x86_init.h>
@@ -101,6 +102,7 @@ int vmware_platform(void)
 
 	return 0;
 }
+EXPORT_SYMBOL(vmware_platform);
 
 /*
  * VMware hypervisor takes care of exporting a reliable TSC to the guest.
diff --git a/arch/x86/kernel/cpuid.c b/arch/x86/kernel/cpuid.c
index 83e5e628de73..8b862d5900fe 100644
--- a/arch/x86/kernel/cpuid.c
+++ b/arch/x86/kernel/cpuid.c
@@ -40,6 +40,7 @@
 #include <linux/cpu.h>
 #include <linux/notifier.h>
 #include <linux/uaccess.h>
+#include <linux/gfp.h>
 
 #include <asm/processor.h>
 #include <asm/msr.h>
diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c
index a4849c10a77e..ebd4c51d096a 100644
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -27,7 +27,6 @@
 #include <asm/cpu.h>
 #include <asm/reboot.h>
 #include <asm/virtext.h>
-#include <asm/x86_init.h>
 
 #if defined(CONFIG_SMP) && defined(CONFIG_X86_LOCAL_APIC)
 
@@ -103,10 +102,5 @@ void native_machine_crash_shutdown(struct pt_regs *regs)
 #ifdef CONFIG_HPET_TIMER
 	hpet_disable();
 #endif
-
-#ifdef CONFIG_X86_64
-	x86_platform.iommu_shutdown();
-#endif
-
 	crash_save_cpu(regs, safe_smp_processor_id());
 }
diff --git a/arch/x86/kernel/crash_dump_32.c b/arch/x86/kernel/crash_dump_32.c
index cd97ce18c29d..67414550c3cc 100644
--- a/arch/x86/kernel/crash_dump_32.c
+++ b/arch/x86/kernel/crash_dump_32.c
@@ -5,6 +5,7 @@
  *	Copyright (C) IBM Corporation, 2004. All rights reserved
  */
 
+#include <linux/slab.h>
 #include <linux/errno.h>
 #include <linux/highmem.h>
 #include <linux/crash_dump.h>
diff --git a/arch/x86/kernel/dumpstack.h b/arch/x86/kernel/dumpstack.h
index 29e5f7c845b2..e1a93be4fd44 100644
--- a/arch/x86/kernel/dumpstack.h
+++ b/arch/x86/kernel/dumpstack.h
@@ -14,6 +14,8 @@
 #define get_bp(bp) asm("movq %%rbp, %0" : "=r" (bp) :)
 #endif
 
+#include <linux/uaccess.h>
+
 extern void
 show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
 		unsigned long *stack, unsigned long bp, char *log_lvl);
@@ -30,6 +32,11 @@ struct stack_frame {
 	unsigned long return_address;
 };
 
+struct stack_frame_ia32 {
+    u32 next_frame;
+    u32 return_address;
+};
+
 static inline unsigned long rewind_frame_pointer(int n)
 {
 	struct stack_frame *frame;
@@ -37,8 +44,10 @@ static inline unsigned long rewind_frame_pointer(int n)
 	get_bp(frame);
 
 #ifdef CONFIG_FRAME_POINTER
-	while (n--)
-		frame = frame->next_frame;
+	while (n--) {
+		if (probe_kernel_address(&frame->next_frame, frame))
+			break;
+	}
 #endif
 
 	return (unsigned long)frame;
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 740b440fbd73..7bca3c6a02fb 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -519,29 +519,45 @@ u64 __init e820_remove_range(u64 start, u64 size, unsigned old_type,
 	printk(KERN_DEBUG "e820 remove range: %016Lx - %016Lx ",
 		       (unsigned long long) start,
 		       (unsigned long long) end);
-	e820_print_type(old_type);
+	if (checktype)
+		e820_print_type(old_type);
 	printk(KERN_CONT "\n");
 
 	for (i = 0; i < e820.nr_map; i++) {
 		struct e820entry *ei = &e820.map[i];
 		u64 final_start, final_end;
+		u64 ei_end;
 
 		if (checktype && ei->type != old_type)
 			continue;
+
+		ei_end = ei->addr + ei->size;
 		/* totally covered? */
-		if (ei->addr >= start &&
-		    (ei->addr + ei->size) <= (start + size)) {
+		if (ei->addr >= start && ei_end <= end) {
 			real_removed_size += ei->size;
 			memset(ei, 0, sizeof(struct e820entry));
 			continue;
 		}
+
+		/* new range is totally covered? */
+		if (ei->addr < start && ei_end > end) {
+			e820_add_region(end, ei_end - end, ei->type);
+			ei->size = start - ei->addr;
+			real_removed_size += size;
+			continue;
+		}
+
 		/* partially covered */
 		final_start = max(start, ei->addr);
-		final_end = min(start + size, ei->addr + ei->size);
+		final_end = min(end, ei_end);
 		if (final_start >= final_end)
 			continue;
 		real_removed_size += final_end - final_start;
 
+		/*
+		 * left range could be head or tail, so need to update
+		 * size at first.
+		 */
 		ei->size -= final_end - final_start;
 		if (ei->addr < final_start)
 			continue;
diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c
index adedeef1dedc..b2e246037392 100644
--- a/arch/x86/kernel/head32.c
+++ b/arch/x86/kernel/head32.c
@@ -7,6 +7,7 @@
 
 #include <linux/init.h>
 #include <linux/start_kernel.h>
+#include <linux/mm.h>
 
 #include <asm/setup.h>
 #include <asm/sections.h>
@@ -44,9 +45,10 @@ void __init i386_start_kernel(void)
 #ifdef CONFIG_BLK_DEV_INITRD
 	/* Reserve INITRD */
 	if (boot_params.hdr.type_of_loader && boot_params.hdr.ramdisk_image) {
+		/* Assume only end is not page aligned */
 		u64 ramdisk_image = boot_params.hdr.ramdisk_image;
 		u64 ramdisk_size  = boot_params.hdr.ramdisk_size;
-		u64 ramdisk_end   = ramdisk_image + ramdisk_size;
+		u64 ramdisk_end   = PAGE_ALIGN(ramdisk_image + ramdisk_size);
 		reserve_early(ramdisk_image, ramdisk_end, "RAMDISK");
 	}
 #endif
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index b5a9896ca1e7..7147143fd614 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -103,9 +103,10 @@ void __init x86_64_start_reservations(char *real_mode_data)
 #ifdef CONFIG_BLK_DEV_INITRD
 	/* Reserve INITRD */
 	if (boot_params.hdr.type_of_loader && boot_params.hdr.ramdisk_image) {
+		/* Assume only end is not page aligned */
 		unsigned long ramdisk_image = boot_params.hdr.ramdisk_image;
 		unsigned long ramdisk_size  = boot_params.hdr.ramdisk_size;
-		unsigned long ramdisk_end   = ramdisk_image + ramdisk_size;
+		unsigned long ramdisk_end   = PAGE_ALIGN(ramdisk_image + ramdisk_size);
 		reserve_early(ramdisk_image, ramdisk_end, "RAMDISK");
 	}
 #endif
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index ee4fa1bfcb33..23b4ecdffa9b 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -4,6 +4,7 @@
 #include <linux/sysdev.h>
 #include <linux/delay.h>
 #include <linux/errno.h>
+#include <linux/slab.h>
 #include <linux/hpet.h>
 #include <linux/init.h>
 #include <linux/cpu.h>
@@ -399,9 +400,15 @@ static int hpet_next_event(unsigned long delta,
 	 * then we might have a real hardware problem. We can not do
 	 * much about it here, but at least alert the user/admin with
 	 * a prominent warning.
+	 * An erratum on some chipsets (ICH9,..), results in comparator read
+	 * immediately following a write returning old value. Workaround
+	 * for this is to read this value second time, when first
+	 * read returns old value.
 	 */
-	WARN_ONCE(hpet_readl(HPET_Tn_CMP(timer)) != cnt,
+	if (unlikely((u32)hpet_readl(HPET_Tn_CMP(timer)) != cnt)) {
+		WARN_ONCE(hpet_readl(HPET_Tn_CMP(timer)) != cnt,
 		  KERN_WARNING "hpet: compare register read back failed.\n");
+	}
 
 	return (s32)(hpet_readl(HPET_COUNTER) - cnt) >= 0 ? -ETIME : 0;
 }
@@ -1143,6 +1150,7 @@ int hpet_set_periodic_freq(unsigned long freq)
 		do_div(clc, freq);
 		clc >>= hpet_clockevent.shift;
 		hpet_pie_delta = clc;
+		hpet_pie_limit = 0;
 	}
 	return 1;
 }
diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c
index c01a2b846d47..54c31c285488 100644
--- a/arch/x86/kernel/i387.c
+++ b/arch/x86/kernel/i387.c
@@ -8,6 +8,7 @@
 #include <linux/module.h>
 #include <linux/regset.h>
 #include <linux/sched.h>
+#include <linux/slab.h>
 
 #include <asm/sigcontext.h>
 #include <asm/processor.h>
diff --git a/arch/x86/kernel/i8259.c b/arch/x86/kernel/i8259.c
index fb725ee15f55..7c9f02c130f3 100644
--- a/arch/x86/kernel/i8259.c
+++ b/arch/x86/kernel/i8259.c
@@ -5,7 +5,6 @@
 #include <linux/ioport.h>
 #include <linux/interrupt.h>
 #include <linux/timex.h>
-#include <linux/slab.h>
 #include <linux/random.h>
 #include <linux/init.h>
 #include <linux/kernel_stat.h>
diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c
index ef257fc2921b..0ed2d300cd46 100644
--- a/arch/x86/kernel/irqinit.c
+++ b/arch/x86/kernel/irqinit.c
@@ -5,7 +5,6 @@
 #include <linux/ioport.h>
 #include <linux/interrupt.h>
 #include <linux/timex.h>
-#include <linux/slab.h>
 #include <linux/random.h>
 #include <linux/kprobes.h>
 #include <linux/init.h>
@@ -141,6 +140,28 @@ void __init init_IRQ(void)
 	x86_init.irqs.intr_init();
 }
 
+/*
+ * Setup the vector to irq mappings.
+ */
+void setup_vector_irq(int cpu)
+{
+#ifndef CONFIG_X86_IO_APIC
+	int irq;
+
+	/*
+	 * On most of the platforms, legacy PIC delivers the interrupts on the
+	 * boot cpu. But there are certain platforms where PIC interrupts are
+	 * delivered to multiple cpu's. If the legacy IRQ is handled by the
+	 * legacy PIC, for the new cpu that is coming online, setup the static
+	 * legacy vector to irq mapping:
+	 */
+	for (irq = 0; irq < legacy_pic->nr_legacy_irqs; irq++)
+		per_cpu(vector_irq, cpu)[IRQ0_VECTOR + irq] = irq;
+#endif
+
+	__setup_vector_irq(cpu);
+}
+
 static void __init smp_intr_init(void)
 {
 #ifdef CONFIG_SMP
diff --git a/arch/x86/kernel/k8.c b/arch/x86/kernel/k8.c
index 9b895464dd03..0f7bc20cfcde 100644
--- a/arch/x86/kernel/k8.c
+++ b/arch/x86/kernel/k8.c
@@ -2,8 +2,8 @@
  * Shared support code for AMD K8 northbridges and derivates.
  * Copyright 2006 Andi Kleen, SUSE Labs. Subject to GPLv2.
  */
-#include <linux/gfp.h>
 #include <linux/types.h>
+#include <linux/slab.h>
 #include <linux/init.h>
 #include <linux/errno.h>
 #include <linux/module.h>
diff --git a/arch/x86/kernel/kdebugfs.c b/arch/x86/kernel/kdebugfs.c
index e444357375ce..8afd9f321f10 100644
--- a/arch/x86/kernel/kdebugfs.c
+++ b/arch/x86/kernel/kdebugfs.c
@@ -9,6 +9,7 @@
 #include <linux/debugfs.h>
 #include <linux/uaccess.h>
 #include <linux/module.h>
+#include <linux/slab.h>
 #include <linux/init.h>
 #include <linux/stat.h>
 #include <linux/io.h>
diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c
index bfba6019d762..b2258ca91003 100644
--- a/arch/x86/kernel/kgdb.c
+++ b/arch/x86/kernel/kgdb.c
@@ -618,8 +618,8 @@ int kgdb_arch_init(void)
 	 * portion of kgdb because this operation requires mutexs to
 	 * complete.
 	 */
+	hw_breakpoint_init(&attr);
 	attr.bp_addr = (unsigned long)kgdb_arch_init;
-	attr.type = PERF_TYPE_BREAKPOINT;
 	attr.bp_len = HW_BREAKPOINT_LEN_1;
 	attr.bp_type = HW_BREAKPOINT_W;
 	attr.disabled = 1;
diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c
index ec6ef60cbd17..ea697263b373 100644
--- a/arch/x86/kernel/ldt.c
+++ b/arch/x86/kernel/ldt.c
@@ -7,6 +7,7 @@
  */
 
 #include <linux/errno.h>
+#include <linux/gfp.h>
 #include <linux/sched.h>
 #include <linux/string.h>
 #include <linux/mm.h>
diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c
index 4a8bb82248ae..035c8c529181 100644
--- a/arch/x86/kernel/machine_kexec_64.c
+++ b/arch/x86/kernel/machine_kexec_64.c
@@ -9,6 +9,7 @@
 #include <linux/mm.h>
 #include <linux/kexec.h>
 #include <linux/string.h>
+#include <linux/gfp.h>
 #include <linux/reboot.h>
 #include <linux/numa.h>
 #include <linux/ftrace.h>
diff --git a/arch/x86/kernel/mca_32.c b/arch/x86/kernel/mca_32.c
index 845d80ce1ef1..63eaf6596233 100644
--- a/arch/x86/kernel/mca_32.c
+++ b/arch/x86/kernel/mca_32.c
@@ -42,6 +42,7 @@
 #include <linux/kernel.h>
 #include <linux/mca.h>
 #include <linux/kprobes.h>
+#include <linux/slab.h>
 #include <asm/system.h>
 #include <asm/io.h>
 #include <linux/proc_fs.h>
diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c
index 89f386f044e4..e0bc186d7501 100644
--- a/arch/x86/kernel/module.c
+++ b/arch/x86/kernel/module.c
@@ -23,6 +23,7 @@
 #include <linux/kernel.h>
 #include <linux/bug.h>
 #include <linux/mm.h>
+#include <linux/gfp.h>
 
 #include <asm/system.h>
 #include <asm/page.h>
diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c
index a2c1edd2d3ac..e81030f71a8f 100644
--- a/arch/x86/kernel/mpparse.c
+++ b/arch/x86/kernel/mpparse.c
@@ -664,7 +664,7 @@ static void __init smp_reserve_memory(struct mpf_intel *mpf)
 {
 	unsigned long size = get_mpc_size(mpf->physptr);
 
-	reserve_early(mpf->physptr, mpf->physptr+size, "MP-table mpc");
+	reserve_early_overlap_ok(mpf->physptr, mpf->physptr+size, "MP-table mpc");
 }
 
 static int __init smp_scan_config(unsigned long base, unsigned long length)
@@ -693,7 +693,7 @@ static int __init smp_scan_config(unsigned long base, unsigned long length)
 			       mpf, (u64)virt_to_phys(mpf));
 
 			mem = virt_to_phys(mpf);
-			reserve_early(mem, mem + sizeof(*mpf), "MP-table mpf");
+			reserve_early_overlap_ok(mem, mem + sizeof(*mpf), "MP-table mpf");
 			if (mpf->physptr)
 				smp_reserve_memory(mpf);
 
diff --git a/arch/x86/kernel/msr.c b/arch/x86/kernel/msr.c
index 206735ac8cbd..4d4468e9f47c 100644
--- a/arch/x86/kernel/msr.c
+++ b/arch/x86/kernel/msr.c
@@ -37,6 +37,7 @@
 #include <linux/cpu.h>
 #include <linux/notifier.h>
 #include <linux/uaccess.h>
+#include <linux/gfp.h>
 
 #include <asm/processor.h>
 #include <asm/msr.h>
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index a4ac764a6880..4b7e3d8b01dd 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -2,6 +2,7 @@
 #include <linux/dma-debug.h>
 #include <linux/dmar.h>
 #include <linux/bootmem.h>
+#include <linux/gfp.h>
 #include <linux/pci.h>
 #include <linux/kmemleak.h>
 
diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c
index f3af115a573a..0f7f130caa67 100644
--- a/arch/x86/kernel/pci-gart_64.c
+++ b/arch/x86/kernel/pci-gart_64.c
@@ -29,6 +29,7 @@
 #include <linux/iommu-helper.h>
 #include <linux/sysdev.h>
 #include <linux/io.h>
+#include <linux/gfp.h>
 #include <asm/atomic.h>
 #include <asm/mtrr.h>
 #include <asm/pgtable.h>
@@ -564,6 +565,9 @@ static void enable_gart_translations(void)
 
 		enable_gart_translation(dev, __pa(agp_gatt_table));
 	}
+
+	/* Flush the GART-TLB to remove stale entries */
+	k8_flush_garts();
 }
 
 /*
diff --git a/arch/x86/kernel/pci-nommu.c b/arch/x86/kernel/pci-nommu.c
index 22be12b60a8f..3af4af810c07 100644
--- a/arch/x86/kernel/pci-nommu.c
+++ b/arch/x86/kernel/pci-nommu.c
@@ -4,6 +4,7 @@
 #include <linux/scatterlist.h>
 #include <linux/string.h>
 #include <linux/init.h>
+#include <linux/gfp.h>
 #include <linux/pci.h>
 #include <linux/mm.h>
 
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index ad9540676fcc..28ad9f4d8b94 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -526,21 +526,37 @@ static int __cpuinit mwait_usable(const struct cpuinfo_x86 *c)
 }
 
 /*
- * Check for AMD CPUs, which have potentially C1E support
+ * Check for AMD CPUs, where APIC timer interrupt does not wake up CPU from C1e.
+ * For more information see
+ * - Erratum #400 for NPT family 0xf and family 0x10 CPUs
+ * - Erratum #365 for family 0x11 (not affected because C1e not in use)
  */
 static int __cpuinit check_c1e_idle(const struct cpuinfo_x86 *c)
 {
+	u64 val;
 	if (c->x86_vendor != X86_VENDOR_AMD)
-		return 0;
-
-	if (c->x86 < 0x0F)
-		return 0;
+		goto no_c1e_idle;
 
 	/* Family 0x0f models < rev F do not have C1E */
-	if (c->x86 == 0x0f && c->x86_model < 0x40)
-		return 0;
+	if (c->x86 == 0x0F && c->x86_model >= 0x40)
+		return 1;
 
-	return 1;
+	if (c->x86 == 0x10) {
+		/*
+		 * check OSVW bit for CPUs that are not affected
+		 * by erratum #400
+		 */
+		rdmsrl(MSR_AMD64_OSVW_ID_LENGTH, val);
+		if (val >= 2) {
+			rdmsrl(MSR_AMD64_OSVW_STATUS, val);
+			if (!(val & BIT(1)))
+				goto no_c1e_idle;
+		}
+		return 1;
+	}
+
+no_c1e_idle:
+	return 0;
 }
 
 static cpumask_var_t c1e_mask;
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index dc9690b4c4cc..17cb3295cbf7 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -276,12 +276,12 @@ int copy_thread(unsigned long clone_flags, unsigned long sp,
 
 	set_tsk_thread_flag(p, TIF_FORK);
 
-	p->thread.fs = me->thread.fs;
-	p->thread.gs = me->thread.gs;
 	p->thread.io_bitmap_ptr = NULL;
 
 	savesegment(gs, p->thread.gsindex);
+	p->thread.gs = p->thread.gsindex ? 0 : me->thread.gs;
 	savesegment(fs, p->thread.fsindex);
+	p->thread.fs = p->thread.fsindex ? 0 : me->thread.fs;
 	savesegment(es, p->thread.es);
 	savesegment(ds, p->thread.ds);
 
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index a503b1fd04e5..2e9b55027b7e 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -12,6 +12,7 @@
 #include <linux/mm.h>
 #include <linux/smp.h>
 #include <linux/errno.h>
+#include <linux/slab.h>
 #include <linux/ptrace.h>
 #include <linux/regset.h>
 #include <linux/tracehook.h>
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 5d7ba1a449bd..c4851eff57b3 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -55,7 +55,6 @@
 #include <linux/stddef.h>
 #include <linux/unistd.h>
 #include <linux/ptrace.h>
-#include <linux/slab.h>
 #include <linux/user.h>
 #include <linux/delay.h>
 
@@ -314,16 +313,17 @@ static void __init reserve_brk(void)
 #define MAX_MAP_CHUNK	(NR_FIX_BTMAPS << PAGE_SHIFT)
 static void __init relocate_initrd(void)
 {
-
+	/* Assume only end is not page aligned */
 	u64 ramdisk_image = boot_params.hdr.ramdisk_image;
 	u64 ramdisk_size  = boot_params.hdr.ramdisk_size;
+	u64 area_size     = PAGE_ALIGN(ramdisk_size);
 	u64 end_of_lowmem = max_low_pfn_mapped << PAGE_SHIFT;
 	u64 ramdisk_here;
 	unsigned long slop, clen, mapaddr;
 	char *p, *q;
 
 	/* We need to move the initrd down into lowmem */
-	ramdisk_here = find_e820_area(0, end_of_lowmem, ramdisk_size,
+	ramdisk_here = find_e820_area(0, end_of_lowmem, area_size,
 					 PAGE_SIZE);
 
 	if (ramdisk_here == -1ULL)
@@ -332,7 +332,7 @@ static void __init relocate_initrd(void)
 
 	/* Note: this includes all the lowmem currently occupied by
 	   the initrd, we rely on that fact to keep the data intact. */
-	reserve_early(ramdisk_here, ramdisk_here + ramdisk_size,
+	reserve_early(ramdisk_here, ramdisk_here + area_size,
 			 "NEW RAMDISK");
 	initrd_start = ramdisk_here + PAGE_OFFSET;
 	initrd_end   = initrd_start + ramdisk_size;
@@ -376,9 +376,10 @@ static void __init relocate_initrd(void)
 
 static void __init reserve_initrd(void)
 {
+	/* Assume only end is not page aligned */
 	u64 ramdisk_image = boot_params.hdr.ramdisk_image;
 	u64 ramdisk_size  = boot_params.hdr.ramdisk_size;
-	u64 ramdisk_end   = ramdisk_image + ramdisk_size;
+	u64 ramdisk_end   = PAGE_ALIGN(ramdisk_image + ramdisk_size);
 	u64 end_of_lowmem = max_low_pfn_mapped << PAGE_SHIFT;
 
 	if (!boot_params.hdr.type_of_loader ||
@@ -606,6 +607,16 @@ static int __init setup_elfcorehdr(char *arg)
 early_param("elfcorehdr", setup_elfcorehdr);
 #endif
 
+static __init void reserve_ibft_region(void)
+{
+	unsigned long addr, size = 0;
+
+	addr = find_ibft_region(&size);
+
+	if (size)
+		reserve_early_overlap_ok(addr, addr + size, "ibft");
+}
+
 #ifdef CONFIG_X86_RESERVE_LOW_64K
 static int __init dmi_low_memory_corruption(const struct dmi_system_id *d)
 {
@@ -908,6 +919,8 @@ void __init setup_arch(char **cmdline_p)
 	 */
 	find_smp_config();
 
+	reserve_ibft_region();
+
 	reserve_trampoline_memory();
 
 #ifdef CONFIG_ACPI_SLEEP
@@ -975,8 +988,6 @@ void __init setup_arch(char **cmdline_p)
 
 	dma32_reserve_bootmem();
 
-	reserve_ibft_region();
-
 #ifdef CONFIG_KVM_CLOCK
 	kvmclock_init();
 #endif
diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c
index ec1de97600e7..d801210945d6 100644
--- a/arch/x86/kernel/smp.c
+++ b/arch/x86/kernel/smp.c
@@ -21,6 +21,7 @@
 #include <linux/cache.h>
 #include <linux/interrupt.h>
 #include <linux/cpu.h>
+#include <linux/gfp.h>
 
 #include <asm/mtrr.h>
 #include <asm/tlbflush.h>
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index a02e80c3c54b..763d815e27a0 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -49,6 +49,7 @@
 #include <linux/nmi.h>
 #include <linux/tboot.h>
 #include <linux/stackprotector.h>
+#include <linux/gfp.h>
 
 #include <asm/acpi.h>
 #include <asm/desc.h>
@@ -242,12 +243,10 @@ static void __cpuinit smp_callin(void)
 	end_local_APIC_setup();
 	map_cpu_to_logical_apicid();
 
-	notify_cpu_starting(cpuid);
-
 	/*
 	 * Need to setup vector mappings before we enable interrupts.
 	 */
-	__setup_vector_irq(smp_processor_id());
+	setup_vector_irq(smp_processor_id());
 	/*
 	 * Get our bogomips.
 	 *
@@ -264,6 +263,8 @@ static void __cpuinit smp_callin(void)
 	 */
 	smp_store_cpu_info(cpuid);
 
+	notify_cpu_starting(cpuid);
+
 	/*
 	 * Allow the master to continue.
 	 */
diff --git a/arch/x86/kernel/tlb_uv.c b/arch/x86/kernel/tlb_uv.c
index 364d015efebc..17b03dd3a6b5 100644
--- a/arch/x86/kernel/tlb_uv.c
+++ b/arch/x86/kernel/tlb_uv.c
@@ -9,6 +9,7 @@
 #include <linux/seq_file.h>
 #include <linux/proc_fs.h>
 #include <linux/kernel.h>
+#include <linux/slab.h>
 
 #include <asm/mmu_context.h>
 #include <asm/uv/uv.h>
diff --git a/arch/x86/kernel/uv_irq.c b/arch/x86/kernel/uv_irq.c
index ece73d8e3240..1d40336b030a 100644
--- a/arch/x86/kernel/uv_irq.c
+++ b/arch/x86/kernel/uv_irq.c
@@ -10,6 +10,7 @@
 
 #include <linux/module.h>
 #include <linux/rbtree.h>
+#include <linux/slab.h>
 #include <linux/irq.h>
 
 #include <asm/apic.h>
diff --git a/arch/x86/kernel/uv_time.c b/arch/x86/kernel/uv_time.c
index 2b75ef638dbc..56e421bc379b 100644
--- a/arch/x86/kernel/uv_time.c
+++ b/arch/x86/kernel/uv_time.c
@@ -19,6 +19,7 @@
  *  Copyright (c) Dimitri Sivanich
  */
 #include <linux/clockchips.h>
+#include <linux/slab.h>
 
 #include <asm/uv/uv_mmrs.h>
 #include <asm/uv/uv_hub.h>
diff --git a/arch/x86/kernel/vmi_32.c b/arch/x86/kernel/vmi_32.c
index 7dd599deca4a..ce9fbacb7526 100644
--- a/arch/x86/kernel/vmi_32.c
+++ b/arch/x86/kernel/vmi_32.c
@@ -28,6 +28,7 @@
 #include <linux/mm.h>
 #include <linux/highmem.h>
 #include <linux/sched.h>
+#include <linux/gfp.h>
 #include <asm/vmi.h>
 #include <asm/io.h>
 #include <asm/fixmap.h>
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 44879df55696..2cc249718c46 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -291,8 +291,8 @@ SECTIONS
 	.smp_locks : AT(ADDR(.smp_locks) - LOAD_OFFSET) {
 		__smp_locks = .;
 		*(.smp_locks)
-		__smp_locks_end = .;
 		. = ALIGN(PAGE_SIZE);
+		__smp_locks_end = .;
 	}
 
 #ifdef CONFIG_X86_64