Merge branch 'master' into next

111 files changed, 495 insertions, 262 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 0eacb1f..9458685 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1216,8 +1216,8 @@ config NUMA_EMU
 
 config NODES_SHIFT
 	int "Maximum NUMA Nodes (as a power of 2)" if !MAXSMP
-	range 1 9
-	default "9" if MAXSMP
+	range 1 10
+	default "10" if MAXSMP
 	default "6" if X86_64
 	default "4" if X86_NUMAQ
 	default "3"
diff --git a/arch/x86/crypto/fpu.c b/arch/x86/crypto/fpu.c
index daef6cd..1a8f864 100644
--- a/arch/x86/crypto/fpu.c
+++ b/arch/x86/crypto/fpu.c
@@ -16,6 +16,7 @@
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
+#include <linux/slab.h>
 #include <asm/i387.h>
 
 struct crypto_fpu_ctx {
diff --git a/arch/x86/ia32/ia32_aout.c b/arch/x86/ia32/ia32_aout.c
index 280c019..0350311 100644
--- a/arch/x86/ia32/ia32_aout.c
+++ b/arch/x86/ia32/ia32_aout.c
@@ -21,7 +21,6 @@
 #include <linux/fcntl.h>
 #include <linux/ptrace.h>
 #include <linux/user.h>
-#include <linux/slab.h>
 #include <linux/binfmts.h>
 #include <linux/personality.h>
 #include <linux/init.h>
diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S
index 59b4556..e790bc1 100644
--- a/arch/x86/ia32/ia32entry.S
+++ b/arch/x86/ia32/ia32entry.S
@@ -626,7 +626,7 @@ ia32_sys_call_table:
 	.quad stub32_sigreturn
 	.quad stub32_clone		/* 120 */
 	.quad sys_setdomainname
-	.quad sys_uname
+	.quad sys_newuname
 	.quad sys_modify_ldt
 	.quad compat_sys_adjtimex
 	.quad sys32_mprotect		/* 125 */
diff --git a/arch/x86/ia32/sys_ia32.c b/arch/x86/ia32/sys_ia32.c
index 74c3543..626be15 100644
--- a/arch/x86/ia32/sys_ia32.c
+++ b/arch/x86/ia32/sys_ia32.c
@@ -40,6 +40,7 @@
 #include <linux/ptrace.h>
 #include <linux/highuid.h>
 #include <linux/sysctl.h>
+#include <linux/slab.h>
 #include <asm/mman.h>
 #include <asm/types.h>
 #include <asm/uaccess.h>
diff --git a/arch/x86/include/asm/amd_iommu_types.h b/arch/x86/include/asm/amd_iommu_types.h
index ba19ad4..86a0ff0 100644
--- a/arch/x86/include/asm/amd_iommu_types.h
+++ b/arch/x86/include/asm/amd_iommu_types.h
@@ -21,6 +21,7 @@
 #define _ASM_X86_AMD_IOMMU_TYPES_H
 
 #include <linux/types.h>
+#include <linux/mutex.h>
 #include <linux/list.h>
 #include <linux/spinlock.h>
 
@@ -140,6 +141,7 @@
 
 /* constants to configure the command buffer */
 #define CMD_BUFFER_SIZE    8192
+#define CMD_BUFFER_UNINITIALIZED 1
 #define CMD_BUFFER_ENTRIES 512
 #define MMIO_CMD_SIZE_SHIFT 56
 #define MMIO_CMD_SIZE_512 (0x9ULL << MMIO_CMD_SIZE_SHIFT)
@@ -237,6 +239,7 @@ struct protection_domain {
 	struct list_head list;  /* for list of all protection domains */
 	struct list_head dev_list; /* List of all devices in this domain */
 	spinlock_t lock;	/* mostly used to lock the page table*/
+	struct mutex api_lock;	/* protect page tables in the iommu-api path */
 	u16 id;			/* the domain id written to the device table */
 	int mode;		/* paging mode (0-6 levels) */
 	u64 *pt_root;		/* page table root pointer */
diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h
index a1dcfa3..30a3e97 100644
--- a/arch/x86/include/asm/io.h
+++ b/arch/x86/include/asm/io.h
@@ -347,6 +347,7 @@ extern void __iomem *early_ioremap(resource_size_t phys_addr,
 extern void __iomem *early_memremap(resource_size_t phys_addr,
 				    unsigned long size);
 extern void early_iounmap(void __iomem *addr, unsigned long size);
+extern void fixup_early_ioremap(void);
 
 #define IO_SPACE_LIMIT 0xffff
 
diff --git a/arch/x86/include/asm/lguest_hcall.h b/arch/x86/include/asm/lguest_hcall.h
index ba0eed8..b60f292 100644
--- a/arch/x86/include/asm/lguest_hcall.h
+++ b/arch/x86/include/asm/lguest_hcall.h
@@ -28,22 +28,39 @@
 
 #ifndef __ASSEMBLY__
 #include <asm/hw_irq.h>
-#include <asm/kvm_para.h>
 
 /*G:030
  * But first, how does our Guest contact the Host to ask for privileged
  * operations?  There are two ways: the direct way is to make a "hypercall",
  * to make requests of the Host Itself.
  *
- * We use the KVM hypercall mechanism, though completely different hypercall
- * numbers. Seventeen hypercalls are available: the hypercall number is put in
- * the %eax register, and the arguments (when required) are placed in %ebx,
- * %ecx, %edx and %esi.  If a return value makes sense, it's returned in %eax.
+ * Our hypercall mechanism uses the highest unused trap code (traps 32 and
+ * above are used by real hardware interrupts).  Seventeen hypercalls are
+ * available: the hypercall number is put in the %eax register, and the
+ * arguments (when required) are placed in %ebx, %ecx, %edx and %esi.
+ * If a return value makes sense, it's returned in %eax.
  *
  * Grossly invalid calls result in Sudden Death at the hands of the vengeful
  * Host, rather than returning failure.  This reflects Winston Churchill's
  * definition of a gentleman: "someone who is only rude intentionally".
-:*/
+ */
+static inline unsigned long
+hcall(unsigned long call,
+      unsigned long arg1, unsigned long arg2, unsigned long arg3,
+      unsigned long arg4)
+{
+	/* "int" is the Intel instruction to trigger a trap. */
+	asm volatile("int $" __stringify(LGUEST_TRAP_ENTRY)
+		     /* The call in %eax (aka "a") might be overwritten */
+		     : "=a"(call)
+		       /* The arguments are in %eax, %ebx, %ecx, %edx & %esi */
+		     : "a"(call), "b"(arg1), "c"(arg2), "d"(arg3), "S"(arg4)
+		       /* "memory" means this might write somewhere in memory.
+			* This isn't true for all calls, but it's safe to tell
+			* gcc that it might happen so it doesn't get clever. */
+		     : "memory");
+	return call;
+}
 
 /* Can't use our min() macro here: needs to be a constant */
 #define LGUEST_IRQS (NR_IRQS < 32 ? NR_IRQS: 32)
diff --git a/arch/x86/include/asm/pgtable_32.h b/arch/x86/include/asm/pgtable_32.h
index 47339a1..2984a25 100644
--- a/arch/x86/include/asm/pgtable_32.h
+++ b/arch/x86/include/asm/pgtable_32.h
@@ -19,7 +19,6 @@
 #include <asm/paravirt.h>
 
 #include <linux/bitops.h>
-#include <linux/slab.h>
 #include <linux/list.h>
 #include <linux/spinlock.h>
 
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 0061ea2..cd40aba 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 3a4bf35..1a160d5 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 adb0ba0..f854d89b 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 9dc91b4..6360abf 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 4b70995..a353475 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 3704997..b5d8b0b 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 00187f1..e5a4a1e 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 dd2b5f2..03ba1b8 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 463de9a..eb2789c 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
@@ -2544,6 +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 8aa65ad..1edaf15 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 49dbeae..c085d52 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 30f25a7..5de7f4c 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 1b1920f..4591680 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 006b278..c587db4 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 ac27ec2..16e3483 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 da5f70f..e7b559d 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 8696151..7b8a8ba 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 ff36d29..ce7cde7 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 cb01dac..b3379d6 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 d360b56..b6215b9 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 8d672ef..9b1ff37 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 2ce8e0b..561758e 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 ad0083a..a94ec6b 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 04d73c1..8abd869 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 7e1cca1..1366c7c 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 73734ba..e7dbde7 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 3ab9c88..8a6f0af 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 cda932c..224392d 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 d15df6e..62b48e4 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 9aa5dc7..fd31a44 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 e006e56..7928963 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 60398a0..db5bdc8 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 b87e0b6..db6f7d4 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;
 
@@ -349,8 +360,10 @@ static void amd_pmu_cpu_offline(int cpu)
 	raw_spin_lock(&amd_nb_lock);
 
 	if (cpuhw->amd_nb) {
-		if (--cpuhw->amd_nb->refcnt == 0)
-			kfree(cpuhw->amd_nb);
+		struct amd_nb *nb = cpuhw->amd_nb;
+
+		if (nb->nb_id == -1 || --nb->refcnt == 0)
+			kfree(nb);
 
 		cpuhw->amd_nb = NULL;
 	}
@@ -379,8 +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 84bfde6..9c794ac 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 1cbed97..dfdb4db 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 83e5e62..8b862d5 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 a4849c1..ebd4c51 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 cd97ce1..6741455 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 29e5f7c..e1a93be 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 740b440..7bca3c6 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/hpet.c b/arch/x86/kernel/hpet.c
index ee4fa1b..23b4ecd 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 c01a2b8..54c31c2 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 fb725ee..7c9f02c 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 f01d390..0ed2d30 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>
diff --git a/arch/x86/kernel/k8.c b/arch/x86/kernel/k8.c
index 9b89546..0f7bc20 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 e444357..8afd9f3 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 bfba601..b2258ca 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 ec6ef60..ea69726 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 4a8bb82..035c8c5 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 845d80c..63eaf65 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 89f386f..e0bc186 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 a2c1edd..e81030f 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 206735a..4d4468e 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 a4ac764..4b7e3d8 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 f3af115..0f7f130 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 22be12b..3af4af8 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_64.c b/arch/x86/kernel/process_64.c
index dc9690b..17cb329 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 a503b1f..2e9b550 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 d76e185..c4851ef 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>
 
@@ -608,6 +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)
 {
@@ -910,6 +919,8 @@ void __init setup_arch(char **cmdline_p)
 	 */
 	find_smp_config();
 
+	reserve_ibft_region();
+
 	reserve_trampoline_memory();
 
 #ifdef CONFIG_ACPI_SLEEP
@@ -977,8 +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 ec1de97..d801210 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 06d98ae..763d815 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>
@@ -242,8 +243,6 @@ 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.
 	 */
@@ -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 364d015ef..17b03dd 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 ece73d8..1d40336 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 2b75ef63..56e421b 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 7dd599d..ce9fbac 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/kvm/i8254.c b/arch/x86/kvm/i8254.c
index 294698b..0150aff 100644
--- a/arch/x86/kvm/i8254.c
+++ b/arch/x86/kvm/i8254.c
@@ -32,6 +32,7 @@
 #define pr_fmt(fmt) "pit: " fmt
 
 #include <linux/kvm_host.h>
+#include <linux/slab.h>
 
 #include "irq.h"
 #include "i8254.h"
diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c
index 07771da..a790fa1 100644
--- a/arch/x86/kvm/i8259.c
+++ b/arch/x86/kvm/i8259.c
@@ -26,6 +26,7 @@
  *   Port from Qemu.
  */
 #include <linux/mm.h>
+#include <linux/slab.h>
 #include <linux/bitops.h>
 #include "irq.h"
 
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 4b224f9..1eb7a4a 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -26,6 +26,7 @@
 #include <linux/io.h>
 #include <linux/module.h>
 #include <linux/math64.h>
+#include <linux/slab.h>
 #include <asm/processor.h>
 #include <asm/msr.h>
 #include <asm/page.h>
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 741373e..19a8906 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -31,6 +31,7 @@
 #include <linux/hugetlb.h>
 #include <linux/compiler.h>
 #include <linux/srcu.h>
+#include <linux/slab.h>
 
 #include <asm/page.h>
 #include <asm/cmpxchg.h>
@@ -1489,8 +1490,8 @@ static int mmu_zap_unsync_children(struct kvm *kvm,
 		for_each_sp(pages, sp, parents, i) {
 			kvm_mmu_zap_page(kvm, sp);
 			mmu_pages_clear_parents(&parents);
+			zapped++;
 		}
-		zapped += pages.nr;
 		kvm_mmu_pages_init(parent, &parents, &pages);
 	}
 
@@ -1541,14 +1542,16 @@ void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned int kvm_nr_mmu_pages)
 	 */
 
 	if (used_pages > kvm_nr_mmu_pages) {
-		while (used_pages > kvm_nr_mmu_pages) {
+		while (used_pages > kvm_nr_mmu_pages &&
+			!list_empty(&kvm->arch.active_mmu_pages)) {
 			struct kvm_mmu_page *page;
 
 			page = container_of(kvm->arch.active_mmu_pages.prev,
 					    struct kvm_mmu_page, link);
-			kvm_mmu_zap_page(kvm, page);
+			used_pages -= kvm_mmu_zap_page(kvm, page);
 			used_pages--;
 		}
+		kvm_nr_mmu_pages = used_pages;
 		kvm->arch.n_free_mmu_pages = 0;
 	}
 	else
@@ -1595,7 +1598,8 @@ static void mmu_unshadow(struct kvm *kvm, gfn_t gfn)
 		    && !sp->role.invalid) {
 			pgprintk("%s: zap %lx %x\n",
 				 __func__, gfn, sp->role.word);
-			kvm_mmu_zap_page(kvm, sp);
+			if (kvm_mmu_zap_page(kvm, sp))
+				nn = bucket->first;
 		}
 	}
 }
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 52f78dd0..2ba5820 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -26,6 +26,7 @@
 #include <linux/highmem.h>
 #include <linux/sched.h>
 #include <linux/ftrace_event.h>
+#include <linux/slab.h>
 
 #include <asm/desc.h>
 
@@ -705,29 +706,28 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id)
 	if (err)
 		goto free_svm;
 
+	err = -ENOMEM;
 	page = alloc_page(GFP_KERNEL);
-	if (!page) {
-		err = -ENOMEM;
+	if (!page)
 		goto uninit;
-	}
 
-	err = -ENOMEM;
 	msrpm_pages = alloc_pages(GFP_KERNEL, MSRPM_ALLOC_ORDER);
 	if (!msrpm_pages)
-		goto uninit;
+		goto free_page1;
 
 	nested_msrpm_pages = alloc_pages(GFP_KERNEL, MSRPM_ALLOC_ORDER);
 	if (!nested_msrpm_pages)
-		goto uninit;
-
-	svm->msrpm = page_address(msrpm_pages);
-	svm_vcpu_init_msrpm(svm->msrpm);
+		goto free_page2;
 
 	hsave_page = alloc_page(GFP_KERNEL);
 	if (!hsave_page)
-		goto uninit;
+		goto free_page3;
+
 	svm->nested.hsave = page_address(hsave_page);
 
+	svm->msrpm = page_address(msrpm_pages);
+	svm_vcpu_init_msrpm(svm->msrpm);
+
 	svm->nested.msrpm = page_address(nested_msrpm_pages);
 
 	svm->vmcb = page_address(page);
@@ -743,6 +743,12 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id)
 
 	return &svm->vcpu;
 
+free_page3:
+	__free_pages(nested_msrpm_pages, MSRPM_ALLOC_ORDER);
+free_page2:
+	__free_pages(msrpm_pages, MSRPM_ALLOC_ORDER);
+free_page1:
+	__free_page(page);
 uninit:
 	kvm_vcpu_uninit(&svm->vcpu);
 free_svm:
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 14873b9..bc933cf 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -26,6 +26,7 @@
 #include <linux/sched.h>
 #include <linux/moduleparam.h>
 #include <linux/ftrace_event.h>
+#include <linux/slab.h>
 #include "kvm_cache_regs.h"
 #include "x86.h"
 
@@ -76,6 +77,8 @@ module_param(emulate_invalid_guest_state, bool, S_IRUGO);
 #define KVM_PMODE_VM_CR4_ALWAYS_ON (X86_CR4_PAE | X86_CR4_VMXE)
 #define KVM_RMODE_VM_CR4_ALWAYS_ON (X86_CR4_VME | X86_CR4_PAE | X86_CR4_VMXE)
 
+#define RMODE_GUEST_OWNED_EFLAGS_BITS (~(X86_EFLAGS_IOPL | X86_EFLAGS_VM))
+
 /*
  * These 2 parameters are used to config the controls for Pause-Loop Exiting:
  * ple_gap:    upper bound on the amount of time between two successive
@@ -130,7 +133,7 @@ struct vcpu_vmx {
 	} host_state;
 	struct {
 		int vm86_active;
-		u8 save_iopl;
+		ulong save_rflags;
 		struct kvm_save_segment {
 			u16 selector;
 			unsigned long base;
@@ -817,18 +820,23 @@ static void vmx_fpu_deactivate(struct kvm_vcpu *vcpu)
 
 static unsigned long vmx_get_rflags(struct kvm_vcpu *vcpu)
 {
-	unsigned long rflags;
+	unsigned long rflags, save_rflags;
 
 	rflags = vmcs_readl(GUEST_RFLAGS);
-	if (to_vmx(vcpu)->rmode.vm86_active)
-		rflags &= ~(unsigned long)(X86_EFLAGS_IOPL | X86_EFLAGS_VM);
+	if (to_vmx(vcpu)->rmode.vm86_active) {
+		rflags &= RMODE_GUEST_OWNED_EFLAGS_BITS;
+		save_rflags = to_vmx(vcpu)->rmode.save_rflags;
+		rflags |= save_rflags & ~RMODE_GUEST_OWNED_EFLAGS_BITS;
+	}
 	return rflags;
 }
 
 static void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags)
 {
-	if (to_vmx(vcpu)->rmode.vm86_active)
+	if (to_vmx(vcpu)->rmode.vm86_active) {
+		to_vmx(vcpu)->rmode.save_rflags = rflags;
 		rflags |= X86_EFLAGS_IOPL | X86_EFLAGS_VM;
+	}
 	vmcs_writel(GUEST_RFLAGS, rflags);
 }
 
@@ -1482,8 +1490,8 @@ static void enter_pmode(struct kvm_vcpu *vcpu)
 	vmcs_write32(GUEST_TR_AR_BYTES, vmx->rmode.tr.ar);
 
 	flags = vmcs_readl(GUEST_RFLAGS);
-	flags &= ~(X86_EFLAGS_IOPL | X86_EFLAGS_VM);
-	flags |= (vmx->rmode.save_iopl << IOPL_SHIFT);
+	flags &= RMODE_GUEST_OWNED_EFLAGS_BITS;
+	flags |= vmx->rmode.save_rflags & ~RMODE_GUEST_OWNED_EFLAGS_BITS;
 	vmcs_writel(GUEST_RFLAGS, flags);
 
 	vmcs_writel(GUEST_CR4, (vmcs_readl(GUEST_CR4) & ~X86_CR4_VME) |
@@ -1556,8 +1564,7 @@ static void enter_rmode(struct kvm_vcpu *vcpu)
 	vmcs_write32(GUEST_TR_AR_BYTES, 0x008b);
 
 	flags = vmcs_readl(GUEST_RFLAGS);
-	vmx->rmode.save_iopl
-		= (flags & X86_EFLAGS_IOPL) >> IOPL_SHIFT;
+	vmx->rmode.save_rflags = flags;
 
 	flags |= X86_EFLAGS_IOPL | X86_EFLAGS_VM;
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index e46282a..3c4ca98 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -39,6 +39,7 @@
 #include <linux/cpufreq.h>
 #include <linux/user-return-notifier.h>
 #include <linux/srcu.h>
+#include <linux/slab.h>
 #include <trace/events/kvm.h>
 #undef TRACE_INCLUDE_FILE
 #define CREATE_TRACE_POINTS
@@ -432,8 +433,6 @@ void kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
 
 #ifdef CONFIG_X86_64
 	if (cr0 & 0xffffffff00000000UL) {
-		printk(KERN_DEBUG "set_cr0: 0x%lx #GP, reserved bits 0x%lx\n",
-		       cr0, kvm_read_cr0(vcpu));
 		kvm_inject_gp(vcpu, 0);
 		return;
 	}
@@ -442,14 +441,11 @@ void kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
 	cr0 &= ~CR0_RESERVED_BITS;
 
 	if ((cr0 & X86_CR0_NW) && !(cr0 & X86_CR0_CD)) {
-		printk(KERN_DEBUG "set_cr0: #GP, CD == 0 && NW == 1\n");
 		kvm_inject_gp(vcpu, 0);
 		return;
 	}
 
 	if ((cr0 & X86_CR0_PG) && !(cr0 & X86_CR0_PE)) {
-		printk(KERN_DEBUG "set_cr0: #GP, set PG flag "
-		       "and a clear PE flag\n");
 		kvm_inject_gp(vcpu, 0);
 		return;
 	}
@@ -460,15 +456,11 @@ void kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
 			int cs_db, cs_l;
 
 			if (!is_pae(vcpu)) {
-				printk(KERN_DEBUG "set_cr0: #GP, start paging "
-				       "in long mode while PAE is disabled\n");
 				kvm_inject_gp(vcpu, 0);
 				return;
 			}
 			kvm_x86_ops->get_cs_db_l_bits(vcpu, &cs_db, &cs_l);
 			if (cs_l) {
-				printk(KERN_DEBUG "set_cr0: #GP, start paging "
-				       "in long mode while CS.L == 1\n");
 				kvm_inject_gp(vcpu, 0);
 				return;
 
@@ -476,8 +468,6 @@ void kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
 		} else
 #endif
 		if (is_pae(vcpu) && !load_pdptrs(vcpu, vcpu->arch.cr3)) {
-			printk(KERN_DEBUG "set_cr0: #GP, pdptrs "
-			       "reserved bits\n");
 			kvm_inject_gp(vcpu, 0);
 			return;
 		}
@@ -504,28 +494,23 @@ void kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 	unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE;
 
 	if (cr4 & CR4_RESERVED_BITS) {
-		printk(KERN_DEBUG "set_cr4: #GP, reserved bits\n");
 		kvm_inject_gp(vcpu, 0);
 		return;
 	}
 
 	if (is_long_mode(vcpu)) {
 		if (!(cr4 & X86_CR4_PAE)) {
-			printk(KERN_DEBUG "set_cr4: #GP, clearing PAE while "
-			       "in long mode\n");
 			kvm_inject_gp(vcpu, 0);
 			return;
 		}
 	} else if (is_paging(vcpu) && (cr4 & X86_CR4_PAE)
 		   && ((cr4 ^ old_cr4) & pdptr_bits)
 		   && !load_pdptrs(vcpu, vcpu->arch.cr3)) {
-		printk(KERN_DEBUG "set_cr4: #GP, pdptrs reserved bits\n");
 		kvm_inject_gp(vcpu, 0);
 		return;
 	}
 
 	if (cr4 & X86_CR4_VMXE) {
-		printk(KERN_DEBUG "set_cr4: #GP, setting VMXE\n");
 		kvm_inject_gp(vcpu, 0);
 		return;
 	}
@@ -546,21 +531,16 @@ void kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
 
 	if (is_long_mode(vcpu)) {
 		if (cr3 & CR3_L_MODE_RESERVED_BITS) {
-			printk(KERN_DEBUG "set_cr3: #GP, reserved bits\n");
 			kvm_inject_gp(vcpu, 0);
 			return;
 		}
 	} else {
 		if (is_pae(vcpu)) {
 			if (cr3 & CR3_PAE_RESERVED_BITS) {
-				printk(KERN_DEBUG
-				       "set_cr3: #GP, reserved bits\n");
 				kvm_inject_gp(vcpu, 0);
 				return;
 			}
 			if (is_paging(vcpu) && !load_pdptrs(vcpu, cr3)) {
-				printk(KERN_DEBUG "set_cr3: #GP, pdptrs "
-				       "reserved bits\n");
 				kvm_inject_gp(vcpu, 0);
 				return;
 			}
@@ -592,7 +572,6 @@ EXPORT_SYMBOL_GPL(kvm_set_cr3);
 void kvm_set_cr8(struct kvm_vcpu *vcpu, unsigned long cr8)
 {
 	if (cr8 & CR8_RESERVED_BITS) {
-		printk(KERN_DEBUG "set_cr8: #GP, reserved bits 0x%lx\n", cr8);
 		kvm_inject_gp(vcpu, 0);
 		return;
 	}
@@ -648,15 +627,12 @@ static u32 emulated_msrs[] = {
 static void set_efer(struct kvm_vcpu *vcpu, u64 efer)
 {
 	if (efer & efer_reserved_bits) {
-		printk(KERN_DEBUG "set_efer: 0x%llx #GP, reserved bits\n",
-		       efer);
 		kvm_inject_gp(vcpu, 0);
 		return;
 	}
 
 	if (is_paging(vcpu)
 	    && (vcpu->arch.efer & EFER_LME) != (efer & EFER_LME)) {
-		printk(KERN_DEBUG "set_efer: #GP, change LME while paging\n");
 		kvm_inject_gp(vcpu, 0);
 		return;
 	}
@@ -666,7 +642,6 @@ static void set_efer(struct kvm_vcpu *vcpu, u64 efer)
 
 		feat = kvm_find_cpuid_entry(vcpu, 0x80000001, 0);
 		if (!feat || !(feat->edx & bit(X86_FEATURE_FXSR_OPT))) {
-			printk(KERN_DEBUG "set_efer: #GP, enable FFXSR w/o CPUID capability\n");
 			kvm_inject_gp(vcpu, 0);
 			return;
 		}
@@ -677,7 +652,6 @@ static void set_efer(struct kvm_vcpu *vcpu, u64 efer)
 
 		feat = kvm_find_cpuid_entry(vcpu, 0x80000001, 0);
 		if (!feat || !(feat->ecx & bit(X86_FEATURE_SVM))) {
-			printk(KERN_DEBUG "set_efer: #GP, enable SVM w/o SVM\n");
 			kvm_inject_gp(vcpu, 0);
 			return;
 		}
@@ -966,9 +940,13 @@ static int set_msr_mce(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 		if (msr >= MSR_IA32_MC0_CTL &&
 		    msr < MSR_IA32_MC0_CTL + 4 * bank_num) {
 			u32 offset = msr - MSR_IA32_MC0_CTL;
-			/* only 0 or all 1s can be written to IA32_MCi_CTL */
+			/* only 0 or all 1s can be written to IA32_MCi_CTL
+			 * some Linux kernels though clear bit 10 in bank 4 to
+			 * workaround a BIOS/GART TBL issue on AMD K8s, ignore
+			 * this to avoid an uncatched #GP in the guest
+			 */
 			if ((offset & 0x3) == 0 &&
-			    data != 0 && data != ~(u64)0)
+			    data != 0 && (data | (1 << 10)) != ~(u64)0)
 				return -1;
 			vcpu->arch.mce_banks[offset] = data;
 			break;
@@ -2634,8 +2612,9 @@ static int kvm_vm_ioctl_reinject(struct kvm *kvm,
 int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
 				      struct kvm_dirty_log *log)
 {
-	int r, n, i;
+	int r, i;
 	struct kvm_memory_slot *memslot;
+	unsigned long n;
 	unsigned long is_dirty = 0;
 	unsigned long *dirty_bitmap = NULL;
 
@@ -2650,7 +2629,7 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
 	if (!memslot->dirty_bitmap)
 		goto out;
 
-	n = ALIGN(memslot->npages, BITS_PER_LONG) / 8;
+	n = kvm_dirty_bitmap_bytes(memslot);
 
 	r = -ENOMEM;
 	dirty_bitmap = vmalloc(n);
@@ -4482,7 +4461,9 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 		kvm_set_cr8(vcpu, kvm_run->cr8);
 
 	if (vcpu->arch.pio.cur_count) {
+		vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
 		r = complete_pio(vcpu);
+		srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
 		if (r)
 			goto out;
 	}
@@ -5145,6 +5126,7 @@ int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason)
 	int ret = 0;
 	u32 old_tss_base = get_segment_base(vcpu, VCPU_SREG_TR);
 	u16 old_tss_sel = get_segment_selector(vcpu, VCPU_SREG_TR);
+	u32 desc_limit;
 
 	old_tss_base = kvm_mmu_gva_to_gpa_write(vcpu, old_tss_base, NULL);
 
@@ -5167,7 +5149,10 @@ int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason)
 		}
 	}
 
-	if (!nseg_desc.p || get_desc_limit(&nseg_desc) < 0x67) {
+	desc_limit = get_desc_limit(&nseg_desc);
+	if (!nseg_desc.p ||
+	    ((desc_limit < 0x67 && (nseg_desc.type & 8)) ||
+	     desc_limit < 0x2b)) {
 		kvm_queue_exception_e(vcpu, TS_VECTOR, tss_selector & 0xfffc);
 		return 1;
 	}
diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c
index 7e59dc1..2bdf628 100644
--- a/arch/x86/lguest/boot.c
+++ b/arch/x86/lguest/boot.c
@@ -115,7 +115,7 @@ static void async_hcall(unsigned long call, unsigned long arg1,
 	local_irq_save(flags);
 	if (lguest_data.hcall_status[next_call] != 0xFF) {
 		/* Table full, so do normal hcall which will flush table. */
-		kvm_hypercall4(call, arg1, arg2, arg3, arg4);
+		hcall(call, arg1, arg2, arg3, arg4);
 	} else {
 		lguest_data.hcalls[next_call].arg0 = call;
 		lguest_data.hcalls[next_call].arg1 = arg1;
@@ -145,46 +145,45 @@ static void async_hcall(unsigned long call, unsigned long arg1,
  * So, when we're in lazy mode, we call async_hcall() to store the call for
  * future processing:
  */
-static void lazy_hcall1(unsigned long call,
-		       unsigned long arg1)
+static void lazy_hcall1(unsigned long call, unsigned long arg1)
 {
 	if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE)
-		kvm_hypercall1(call, arg1);
+		hcall(call, arg1, 0, 0, 0);
 	else
 		async_hcall(call, arg1, 0, 0, 0);
 }
 
 /* You can imagine what lazy_hcall2, 3 and 4 look like. :*/
 static void lazy_hcall2(unsigned long call,
-		       unsigned long arg1,
-		       unsigned long arg2)
+			unsigned long arg1,
+			unsigned long arg2)
 {
 	if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE)
-		kvm_hypercall2(call, arg1, arg2);
+		hcall(call, arg1, arg2, 0, 0);
 	else
 		async_hcall(call, arg1, arg2, 0, 0);
 }
 
 static void lazy_hcall3(unsigned long call,
-		       unsigned long arg1,
-		       unsigned long arg2,
-		       unsigned long arg3)
+			unsigned long arg1,
+			unsigned long arg2,
+			unsigned long arg3)
 {
 	if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE)
-		kvm_hypercall3(call, arg1, arg2, arg3);
+		hcall(call, arg1, arg2, arg3, 0);
 	else
 		async_hcall(call, arg1, arg2, arg3, 0);
 }
 
 #ifdef CONFIG_X86_PAE
 static void lazy_hcall4(unsigned long call,
-		       unsigned long arg1,
-		       unsigned long arg2,
-		       unsigned long arg3,
-		       unsigned long arg4)
+			unsigned long arg1,
+			unsigned long arg2,
+			unsigned long arg3,
+			unsigned long arg4)
 {
 	if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE)
-		kvm_hypercall4(call, arg1, arg2, arg3, arg4);
+		hcall(call, arg1, arg2, arg3, arg4);
 	else
 		async_hcall(call, arg1, arg2, arg3, arg4);
 }
@@ -196,13 +195,13 @@ static void lazy_hcall4(unsigned long call,
 :*/
 static void lguest_leave_lazy_mmu_mode(void)
 {
-	kvm_hypercall0(LHCALL_FLUSH_ASYNC);
+	hcall(LHCALL_FLUSH_ASYNC, 0, 0, 0, 0);
 	paravirt_leave_lazy_mmu();
 }
 
 static void lguest_end_context_switch(struct task_struct *next)
 {
-	kvm_hypercall0(LHCALL_FLUSH_ASYNC);
+	hcall(LHCALL_FLUSH_ASYNC, 0, 0, 0, 0);
 	paravirt_end_context_switch(next);
 }
 
@@ -286,7 +285,7 @@ static void lguest_write_idt_entry(gate_desc *dt,
 	/* Keep the local copy up to date. */
 	native_write_idt_entry(dt, entrynum, g);
 	/* Tell Host about this new entry. */
-	kvm_hypercall3(LHCALL_LOAD_IDT_ENTRY, entrynum, desc[0], desc[1]);
+	hcall(LHCALL_LOAD_IDT_ENTRY, entrynum, desc[0], desc[1], 0);
 }
 
 /*
@@ -300,7 +299,7 @@ static void lguest_load_idt(const struct desc_ptr *desc)
 	struct desc_struct *idt = (void *)desc->address;
 
 	for (i = 0; i < (desc->size+1)/8; i++)
-		kvm_hypercall3(LHCALL_LOAD_IDT_ENTRY, i, idt[i].a, idt[i].b);
+		hcall(LHCALL_LOAD_IDT_ENTRY, i, idt[i].a, idt[i].b, 0);
 }
 
 /*
@@ -321,7 +320,7 @@ static void lguest_load_gdt(const struct desc_ptr *desc)
 	struct desc_struct *gdt = (void *)desc->address;
 
 	for (i = 0; i < (desc->size+1)/8; i++)
-		kvm_hypercall3(LHCALL_LOAD_GDT_ENTRY, i, gdt[i].a, gdt[i].b);
+		hcall(LHCALL_LOAD_GDT_ENTRY, i, gdt[i].a, gdt[i].b, 0);
 }
 
 /*
@@ -334,8 +333,8 @@ static void lguest_write_gdt_entry(struct desc_struct *dt, int entrynum,
 {
 	native_write_gdt_entry(dt, entrynum, desc, type);
 	/* Tell Host about this new entry. */
-	kvm_hypercall3(LHCALL_LOAD_GDT_ENTRY, entrynum,
-		       dt[entrynum].a, dt[entrynum].b);
+	hcall(LHCALL_LOAD_GDT_ENTRY, entrynum,
+	      dt[entrynum].a, dt[entrynum].b, 0);
 }
 
 /*
@@ -931,7 +930,7 @@ static int lguest_clockevent_set_next_event(unsigned long delta,
 	}
 
 	/* Please wake us this far in the future. */
-	kvm_hypercall1(LHCALL_SET_CLOCKEVENT, delta);
+	hcall(LHCALL_SET_CLOCKEVENT, delta, 0, 0, 0);
 	return 0;
 }
 
@@ -942,7 +941,7 @@ static void lguest_clockevent_set_mode(enum clock_event_mode mode,
 	case CLOCK_EVT_MODE_UNUSED:
 	case CLOCK_EVT_MODE_SHUTDOWN:
 		/* A 0 argument shuts the clock down. */
-		kvm_hypercall0(LHCALL_SET_CLOCKEVENT);
+		hcall(LHCALL_SET_CLOCKEVENT, 0, 0, 0, 0);
 		break;
 	case CLOCK_EVT_MODE_ONESHOT:
 		/* This is what we expect. */
@@ -1100,7 +1099,7 @@ static void set_lguest_basic_apic_ops(void)
 /* STOP!  Until an interrupt comes in. */
 static void lguest_safe_halt(void)
 {
-	kvm_hypercall0(LHCALL_HALT);
+	hcall(LHCALL_HALT, 0, 0, 0, 0);
 }
 
 /*
@@ -1112,8 +1111,8 @@ static void lguest_safe_halt(void)
  */
 static void lguest_power_off(void)
 {
-	kvm_hypercall2(LHCALL_SHUTDOWN, __pa("Power down"),
-					LGUEST_SHUTDOWN_POWEROFF);
+	hcall(LHCALL_SHUTDOWN, __pa("Power down"),
+	      LGUEST_SHUTDOWN_POWEROFF, 0, 0);
 }
 
 /*
@@ -1123,7 +1122,7 @@ static void lguest_power_off(void)
  */
 static int lguest_panic(struct notifier_block *nb, unsigned long l, void *p)
 {
-	kvm_hypercall2(LHCALL_SHUTDOWN, __pa(p), LGUEST_SHUTDOWN_POWEROFF);
+	hcall(LHCALL_SHUTDOWN, __pa(p), LGUEST_SHUTDOWN_POWEROFF, 0, 0);
 	/* The hcall won't return, but to keep gcc happy, we're "done". */
 	return NOTIFY_DONE;
 }
@@ -1162,7 +1161,7 @@ static __init int early_put_chars(u32 vtermno, const char *buf, int count)
 		len = sizeof(scratch) - 1;
 	scratch[len] = '\0';
 	memcpy(scratch, buf, len);
-	kvm_hypercall1(LHCALL_NOTIFY, __pa(scratch));
+	hcall(LHCALL_NOTIFY, __pa(scratch), 0, 0, 0);
 
 	/* This routine returns the number of bytes actually written. */
 	return len;
@@ -1174,7 +1173,7 @@ static __init int early_put_chars(u32 vtermno, const char *buf, int count)
  */
 static void lguest_restart(char *reason)
 {
-	kvm_hypercall2(LHCALL_SHUTDOWN, __pa(reason), LGUEST_SHUTDOWN_RESTART);
+	hcall(LHCALL_SHUTDOWN, __pa(reason), LGUEST_SHUTDOWN_RESTART, 0, 0);
 }
 
 /*G:050
diff --git a/arch/x86/lguest/i386_head.S b/arch/x86/lguest/i386_head.S
index 27eac0f..4f420c2f 100644
--- a/arch/x86/lguest/i386_head.S
+++ b/arch/x86/lguest/i386_head.S
@@ -32,7 +32,7 @@ ENTRY(lguest_entry)
 	 */
 	movl $LHCALL_LGUEST_INIT, %eax
 	movl $lguest_data - __PAGE_OFFSET, %ebx
-	.byte 0x0f,0x01,0xc1 /* KVM_HYPERCALL */
+	int $LGUEST_TRAP_ENTRY
 
 	/* Set up the initial stack so we can run C code. */
 	movl $(init_thread_union+THREAD_SIZE),%esp
diff --git a/arch/x86/lib/rwsem_64.S b/arch/x86/lib/rwsem_64.S
index 15acecf..41fcf00 100644
--- a/arch/x86/lib/rwsem_64.S
+++ b/arch/x86/lib/rwsem_64.S
@@ -60,7 +60,7 @@ ENTRY(call_rwsem_down_write_failed)
 	ENDPROC(call_rwsem_down_write_failed)
 
 ENTRY(call_rwsem_wake)
-	decw %dx    /* do nothing if still outstanding active readers */
+	decl %edx	/* do nothing if still outstanding active readers */
 	jnz 1f
 	save_common_regs
 	movq %rax,%rdi
diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c
index f46c340..069ce7c 100644
--- a/arch/x86/mm/hugetlbpage.c
+++ b/arch/x86/mm/hugetlbpage.c
@@ -9,7 +9,6 @@
 #include <linux/mm.h>
 #include <linux/hugetlb.h>
 #include <linux/pagemap.h>
-#include <linux/slab.h>
 #include <linux/err.h>
 #include <linux/sysctl.h>
 #include <asm/mman.h>
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 452ee5b..b278535 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -1,3 +1,4 @@
+#include <linux/gfp.h>
 #include <linux/initrd.h>
 #include <linux/ioport.h>
 #include <linux/swap.h>
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 5cb3f0f..bca7909 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -25,11 +25,11 @@
 #include <linux/pfn.h>
 #include <linux/poison.h>
 #include <linux/bootmem.h>
-#include <linux/slab.h>
 #include <linux/proc_fs.h>
 #include <linux/memory_hotplug.h>
 #include <linux/initrd.h>
 #include <linux/cpumask.h>
+#include <linux/gfp.h>
 
 #include <asm/asm.h>
 #include <asm/bios_ebda.h>
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index e9b040e..ee41bba 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -29,6 +29,7 @@
 #include <linux/module.h>
 #include <linux/memory_hotplug.h>
 #include <linux/nmi.h>
+#include <linux/gfp.h>
 
 #include <asm/processor.h>
 #include <asm/bios_ebda.h>
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index 5eb1ba7..12e4d2d 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -448,6 +448,20 @@ static inline void __init early_clear_fixmap(enum fixed_addresses idx)
 static void __iomem *prev_map[FIX_BTMAPS_SLOTS] __initdata;
 static unsigned long prev_size[FIX_BTMAPS_SLOTS] __initdata;
 
+void __init fixup_early_ioremap(void)
+{
+	int i;
+
+	for (i = 0; i < FIX_BTMAPS_SLOTS; i++) {
+		if (prev_map[i]) {
+			WARN_ON(1);
+			break;
+		}
+	}
+
+	early_ioremap_init();
+}
+
 static int __init check_early_ioremap_leak(void)
 {
 	int count = 0;
diff --git a/arch/x86/mm/kmmio.c b/arch/x86/mm/kmmio.c
index 536fb68..5d0e67f 100644
--- a/arch/x86/mm/kmmio.c
+++ b/arch/x86/mm/kmmio.c
@@ -21,6 +21,7 @@
 #include <linux/kdebug.h>
 #include <linux/mutex.h>
 #include <linux/io.h>
+#include <linux/slab.h>
 #include <asm/cacheflush.h>
 #include <asm/tlbflush.h>
 #include <linux/errno.h>
diff --git a/arch/x86/mm/mmio-mod.c b/arch/x86/mm/mmio-mod.c
index 34a3291..3adff7d 100644
--- a/arch/x86/mm/mmio-mod.c
+++ b/arch/x86/mm/mmio-mod.c
@@ -26,6 +26,7 @@
 
 #include <linux/module.h>
 #include <linux/debugfs.h>
+#include <linux/slab.h>
 #include <linux/uaccess.h>
 #include <linux/io.h>
 #include <linux/version.h>
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index cf07c26..28195c3 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -6,13 +6,13 @@
 #include <linux/bootmem.h>
 #include <linux/module.h>
 #include <linux/sched.h>
-#include <linux/slab.h>
 #include <linux/mm.h>
 #include <linux/interrupt.h>
 #include <linux/seq_file.h>
 #include <linux/debugfs.h>
 #include <linux/pfn.h>
 #include <linux/percpu.h>
+#include <linux/gfp.h>
 
 #include <asm/e820.h>
 #include <asm/processor.h>
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index ae9648e..edc8b95 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -12,7 +12,7 @@
 #include <linux/debugfs.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/gfp.h>
+#include <linux/slab.h>
 #include <linux/mm.h>
 #include <linux/fs.h>
 #include <linux/rbtree.h>
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index c9ba9de..5c4ee42 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -1,4 +1,5 @@
 #include <linux/mm.h>
+#include <linux/gfp.h>
 #include <asm/pgalloc.h>
 #include <asm/pgtable.h>
 #include <asm/tlb.h>
diff --git a/arch/x86/mm/pgtable_32.c b/arch/x86/mm/pgtable_32.c
index 46c8834..7928540 100644
--- a/arch/x86/mm/pgtable_32.c
+++ b/arch/x86/mm/pgtable_32.c
@@ -6,7 +6,6 @@
 #include <linux/swap.h>
 #include <linux/smp.h>
 #include <linux/highmem.h>
-#include <linux/slab.h>
 #include <linux/pagemap.h>
 #include <linux/spinlock.h>
 #include <linux/module.h>
@@ -19,6 +18,7 @@
 #include <asm/e820.h>
 #include <asm/tlb.h>
 #include <asm/tlbflush.h>
+#include <asm/io.h>
 
 unsigned int __VMALLOC_RESERVE = 128 << 20;
 
@@ -129,6 +129,7 @@ static int __init parse_reservetop(char *arg)
 
 	address = memparse(arg, &arg);
 	reserve_top_address(address);
+	fixup_early_ioremap();
 	return 0;
 }
 early_param("reservetop", parse_reservetop);
diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c
index e311602..31930fd 100644
--- a/arch/x86/pci/acpi.c
+++ b/arch/x86/pci/acpi.c
@@ -3,6 +3,7 @@
 #include <linux/init.h>
 #include <linux/irq.h>
 #include <linux/dmi.h>
+#include <linux/slab.h>
 #include <asm/numa.h>
 #include <asm/pci_x86.h>
 
@@ -65,14 +66,44 @@ resource_to_addr(struct acpi_resource *resource,
 			struct acpi_resource_address64 *addr)
 {
 	acpi_status status;
-
-	status = acpi_resource_to_address64(resource, addr);
-	if (ACPI_SUCCESS(status) &&
-	    (addr->resource_type == ACPI_MEMORY_RANGE ||
-	    addr->resource_type == ACPI_IO_RANGE) &&
-	    addr->address_length > 0 &&
-	    addr->producer_consumer == ACPI_PRODUCER) {
+	struct acpi_resource_memory24 *memory24;
+	struct acpi_resource_memory32 *memory32;
+	struct acpi_resource_fixed_memory32 *fixed_memory32;
+
+	memset(addr, 0, sizeof(*addr));
+	switch (resource->type) {
+	case ACPI_RESOURCE_TYPE_MEMORY24:
+		memory24 = &resource->data.memory24;
+		addr->resource_type = ACPI_MEMORY_RANGE;
+		addr->minimum = memory24->minimum;
+		addr->address_length = memory24->address_length;
+		addr->maximum = addr->minimum + addr->address_length - 1;
+		return AE_OK;
+	case ACPI_RESOURCE_TYPE_MEMORY32:
+		memory32 = &resource->data.memory32;
+		addr->resource_type = ACPI_MEMORY_RANGE;
+		addr->minimum = memory32->minimum;
+		addr->address_length = memory32->address_length;
+		addr->maximum = addr->minimum + addr->address_length - 1;
 		return AE_OK;
+	case ACPI_RESOURCE_TYPE_FIXED_MEMORY32:
+		fixed_memory32 = &resource->data.fixed_memory32;
+		addr->resource_type = ACPI_MEMORY_RANGE;
+		addr->minimum = fixed_memory32->address;
+		addr->address_length = fixed_memory32->address_length;
+		addr->maximum = addr->minimum + addr->address_length - 1;
+		return AE_OK;
+	case ACPI_RESOURCE_TYPE_ADDRESS16:
+	case ACPI_RESOURCE_TYPE_ADDRESS32:
+	case ACPI_RESOURCE_TYPE_ADDRESS64:
+		status = acpi_resource_to_address64(resource, addr);
+		if (ACPI_SUCCESS(status) &&
+		    (addr->resource_type == ACPI_MEMORY_RANGE ||
+		    addr->resource_type == ACPI_IO_RANGE) &&
+		    addr->address_length > 0) {
+			return AE_OK;
+		}
+		break;
 	}
 	return AE_ERROR;
 }
@@ -90,30 +121,6 @@ count_resource(struct acpi_resource *acpi_res, void *data)
 	return AE_OK;
 }
 
-static void
-align_resource(struct acpi_device *bridge, struct resource *res)
-{
-	int align = (res->flags & IORESOURCE_MEM) ? 16 : 4;
-
-	/*
-	 * Host bridge windows are not BARs, but the decoders on the PCI side
-	 * that claim this address space have starting alignment and length
-	 * constraints, so fix any obvious BIOS goofs.
-	 */
-	if (!IS_ALIGNED(res->start, align)) {
-		dev_printk(KERN_DEBUG, &bridge->dev,
-			   "host bridge window %pR invalid; "
-			   "aligning start to %d-byte boundary\n", res, align);
-		res->start &= ~(align - 1);
-	}
-	if (!IS_ALIGNED(res->end + 1, align)) {
-		dev_printk(KERN_DEBUG, &bridge->dev,
-			   "host bridge window %pR invalid; "
-			   "aligning end to %d-byte boundary\n", res, align);
-		res->end = ALIGN(res->end, align) - 1;
-	}
-}
-
 static acpi_status
 setup_resource(struct acpi_resource *acpi_res, void *data)
 {
@@ -123,7 +130,7 @@ setup_resource(struct acpi_resource *acpi_res, void *data)
 	acpi_status status;
 	unsigned long flags;
 	struct resource *root, *conflict;
-	u64 start, end, max_len;
+	u64 start, end;
 
 	status = resource_to_addr(acpi_res, &addr);
 	if (!ACPI_SUCCESS(status))
@@ -140,19 +147,8 @@ setup_resource(struct acpi_resource *acpi_res, void *data)
 	} else
 		return AE_OK;
 
-	max_len = addr.maximum - addr.minimum + 1;
-	if (addr.address_length > max_len) {
-		dev_printk(KERN_DEBUG, &info->bridge->dev,
-			   "host bridge window length %#llx doesn't fit in "
-			   "%#llx-%#llx, trimming\n",
-			   (unsigned long long) addr.address_length,
-			   (unsigned long long) addr.minimum,
-			   (unsigned long long) addr.maximum);
-		addr.address_length = max_len;
-	}
-
 	start = addr.minimum + addr.translation_offset;
-	end = start + addr.address_length - 1;
+	end = addr.maximum + addr.translation_offset;
 
 	res = &info->res[info->res_num];
 	res->name = info->name;
@@ -160,7 +156,6 @@ setup_resource(struct acpi_resource *acpi_res, void *data)
 	res->start = start;
 	res->end = end;
 	res->child = NULL;
-	align_resource(info->bridge, res);
 
 	if (!pci_use_crs) {
 		dev_printk(KERN_DEBUG, &info->bridge->dev,
diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c
index 294e10c..cf2e938 100644
--- a/arch/x86/pci/common.c
+++ b/arch/x86/pci/common.c
@@ -9,6 +9,7 @@
 #include <linux/ioport.h>
 #include <linux/init.h>
 #include <linux/dmi.h>
+#include <linux/slab.h>
 
 #include <asm/acpi.h>
 #include <asm/segment.h>
diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c
index 46fd43f..97da2ba 100644
--- a/arch/x86/pci/i386.c
+++ b/arch/x86/pci/i386.c
@@ -72,6 +72,9 @@ pcibios_align_resource(void *data, const struct resource *res,
 			return start;
 		if (start & 0x300)
 			start = (start + 0x3ff) & ~0x3ff;
+	} else if (res->flags & IORESOURCE_MEM) {
+		if (start < BIOS_END)
+			start = BIOS_END;
 	}
 	return start;
 }
diff --git a/arch/x86/pci/irq.c b/arch/x86/pci/irq.c
index 8b10752..5d362b5 100644
--- a/arch/x86/pci/irq.c
+++ b/arch/x86/pci/irq.c
@@ -8,7 +8,6 @@
 #include <linux/kernel.h>
 #include <linux/pci.h>
 #include <linux/init.h>
-#include <linux/slab.h>
 #include <linux/interrupt.h>
 #include <linux/dmi.h>
 #include <linux/io.h>
diff --git a/arch/x86/pci/mmconfig-shared.c b/arch/x86/pci/mmconfig-shared.c
index 8f3f9a5..39b9ebe 100644
--- a/arch/x86/pci/mmconfig-shared.c
+++ b/arch/x86/pci/mmconfig-shared.c
@@ -16,6 +16,7 @@
 #include <linux/sfi_acpi.h>
 #include <linux/bitmap.h>
 #include <linux/dmi.h>
+#include <linux/slab.h>
 #include <asm/e820.h>
 #include <asm/pci_x86.h>
 #include <asm/acpi.h>
diff --git a/arch/x86/pci/pcbios.c b/arch/x86/pci/pcbios.c
index 1c975cc..59a225c 100644
--- a/arch/x86/pci/pcbios.c
+++ b/arch/x86/pci/pcbios.c
@@ -4,6 +4,7 @@
 
 #include <linux/pci.h>
 #include <linux/init.h>
+#include <linux/slab.h>
 #include <linux/module.h>
 #include <linux/uaccess.h>
 #include <asm/pci_x86.h>
diff --git a/arch/x86/power/hibernate_32.c b/arch/x86/power/hibernate_32.c
index 81197c6..3769079 100644
--- a/arch/x86/power/hibernate_32.c
+++ b/arch/x86/power/hibernate_32.c
@@ -6,6 +6,7 @@
  * Copyright (c) 2006 Rafael J. Wysocki <rjw@sisk.pl>
  */
 
+#include <linux/gfp.h>
 #include <linux/suspend.h>
 #include <linux/bootmem.h>
 
diff --git a/arch/x86/power/hibernate_64.c b/arch/x86/power/hibernate_64.c
index 65fdc86..d24f983 100644
--- a/arch/x86/power/hibernate_64.c
+++ b/arch/x86/power/hibernate_64.c
@@ -8,6 +8,7 @@
  * Copyright (c) 2001 Patrick Mochel <mochel@osdl.org>
  */
 
+#include <linux/gfp.h>
 #include <linux/smp.h>
 #include <linux/suspend.h>
 #include <asm/proto.h>
diff --git a/arch/x86/power/hibernate_asm_32.S b/arch/x86/power/hibernate_asm_32.S
index b641388..ad47dae 100644
--- a/arch/x86/power/hibernate_asm_32.S
+++ b/arch/x86/power/hibernate_asm_32.S
@@ -27,10 +27,17 @@ ENTRY(swsusp_arch_suspend)
 	ret
 
 ENTRY(restore_image)
+	movl	mmu_cr4_features, %ecx
 	movl	resume_pg_dir, %eax
 	subl	$__PAGE_OFFSET, %eax
 	movl	%eax, %cr3
 
+	jecxz	1f	# cr4 Pentium and higher, skip if zero
+	andl	$~(X86_CR4_PGE), %ecx
+	movl	%ecx, %cr4;  # turn off PGE
+	movl	%cr3, %eax;  # flush TLB
+	movl	%eax, %cr3
+1:
 	movl	restore_pblist, %edx
 	.p2align 4,,7
 
@@ -54,16 +61,8 @@ done:
 	movl	$swapper_pg_dir, %eax
 	subl	$__PAGE_OFFSET, %eax
 	movl	%eax, %cr3
-	/* Flush TLB, including "global" things (vmalloc) */
 	movl	mmu_cr4_features, %ecx
 	jecxz	1f	# cr4 Pentium and higher, skip if zero
-	movl	%ecx, %edx
-	andl	$~(X86_CR4_PGE), %edx
-	movl	%edx, %cr4;  # turn off PGE
-1:
-	movl	%cr3, %eax;  # flush TLB
-	movl	%eax, %cr3
-	jecxz	1f	# cr4 Pentium and higher, skip if zero
 	movl	%ecx, %cr4;  # turn PGE back on
 1:
 
diff --git a/arch/x86/vdso/vma.c b/arch/x86/vdso/vma.c
index 21e1aeb..ac74869 100644
--- a/arch/x86/vdso/vma.c
+++ b/arch/x86/vdso/vma.c
@@ -6,6 +6,7 @@
 #include <linux/mm.h>
 #include <linux/err.h>
 #include <linux/sched.h>
+#include <linux/slab.h>
 #include <linux/init.h>
 #include <linux/random.h>
 #include <linux/elf.h>
diff --git a/arch/x86/xen/debugfs.c b/arch/x86/xen/debugfs.c
index e133ce2..1304bce 100644
--- a/arch/x86/xen/debugfs.c
+++ b/arch/x86/xen/debugfs.c
@@ -1,5 +1,6 @@
 #include <linux/init.h>
 #include <linux/debugfs.h>
+#include <linux/slab.h>
 #include <linux/module.h>
 
 #include "debugfs.h"
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index b607239..65d8d79 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -28,6 +28,7 @@
 #include <linux/highmem.h>
 #include <linux/console.h>
 #include <linux/pci.h>
+#include <linux/gfp.h>
 
 #include <xen/xen.h>
 #include <xen/interface/xen.h>
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index f9eb7de..914f046 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -43,6 +43,7 @@
 #include <linux/debugfs.h>
 #include <linux/bug.h>
 #include <linux/module.h>
+#include <linux/gfp.h>
 
 #include <asm/pgtable.h>
 #include <asm/tlbflush.h>
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index deafb65..a29693f 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -14,6 +14,7 @@
  */
 #include <linux/sched.h>
 #include <linux/err.h>
+#include <linux/slab.h>
 #include <linux/smp.h>
 
 #include <asm/paravirt.h>
diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c
index 24ded31..e0500646 100644
--- a/arch/x86/xen/spinlock.c
+++ b/arch/x86/xen/spinlock.c
@@ -6,6 +6,7 @@
 #include <linux/spinlock.h>
 #include <linux/debugfs.h>
 #include <linux/log2.h>
+#include <linux/gfp.h>
 
 #include <asm/paravirt.h>
 
diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c
index 0d3f07c..32764b8 100644
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -13,6 +13,7 @@
 #include <linux/clockchips.h>
 #include <linux/kernel_stat.h>
 #include <linux/math64.h>
+#include <linux/gfp.h>
 
 #include <asm/pvclock.h>
 #include <asm/xen/hypervisor.h>