22 files changed, 225 insertions, 109 deletions

diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index edc90f2..8406ed7 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -33,7 +33,7 @@ extern unsigned long asmlinkage efi_call_phys(void *, ...);
 #define efi_call_virt6(f, a1, a2, a3, a4, a5, a6)	\
 	efi_call_virt(f, a1, a2, a3, a4, a5, a6)
 
-#define efi_ioremap(addr, size)			ioremap_cache(addr, size)
+#define efi_ioremap(addr, size, type)		ioremap_cache(addr, size)
 
 #else /* !CONFIG_X86_32 */
 
@@ -84,7 +84,8 @@ extern u64 efi_call6(void *fp, u64 arg1, u64 arg2, u64 arg3,
 	efi_call6((void *)(efi.systab->runtime->f), (u64)(a1), (u64)(a2), \
 		  (u64)(a3), (u64)(a4), (u64)(a5), (u64)(a6))
 
-extern void __iomem *efi_ioremap(unsigned long addr, unsigned long size);
+extern void __iomem *efi_ioremap(unsigned long addr, unsigned long size,
+				 u32 type);
 
 #endif /* CONFIG_X86_32 */
 
diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h
index 2bdab21..c6ccbe7 100644
--- a/arch/x86/include/asm/irqflags.h
+++ b/arch/x86/include/asm/irqflags.h
@@ -12,9 +12,15 @@ static inline unsigned long native_save_fl(void)
 {
 	unsigned long flags;
 
+	/*
+	 * Note: this needs to be "=r" not "=rm", because we have the
+	 * stack offset from what gcc expects at the time the "pop" is
+	 * executed, and so a memory reference with respect to the stack
+	 * would end up using the wrong address.
+	 */
 	asm volatile("# __raw_save_flags\n\t"
 		     "pushf ; pop %0"
-		     : "=g" (flags)
+		     : "=r" (flags)
 		     : /* no input */
 		     : "memory");
 
diff --git a/arch/x86/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h
index 341070f..77a6850 100644
--- a/arch/x86/include/asm/uv/uv_hub.h
+++ b/arch/x86/include/asm/uv/uv_hub.h
@@ -175,7 +175,7 @@ DECLARE_PER_CPU(struct uv_hub_info_s, __uv_hub_info);
 #define UV_GLOBAL_MMR32_PNODE_BITS(p)	((p) << (UV_GLOBAL_MMR32_PNODE_SHIFT))
 
 #define UV_GLOBAL_MMR64_PNODE_BITS(p)					\
-	((unsigned long)(UV_PNODE_TO_GNODE(p)) << UV_GLOBAL_MMR64_PNODE_SHIFT)
+	(((unsigned long)(p)) << UV_GLOBAL_MMR64_PNODE_SHIFT)
 
 #define UV_APIC_PNODE_SHIFT	6
 
@@ -327,6 +327,7 @@ struct uv_blade_info {
 	unsigned short	nr_possible_cpus;
 	unsigned short	nr_online_cpus;
 	unsigned short	pnode;
+	short		memory_nid;
 };
 extern struct uv_blade_info *uv_blade_info;
 extern short *uv_node_to_blade;
@@ -363,6 +364,12 @@ static inline int uv_blade_to_pnode(int bid)
 	return uv_blade_info[bid].pnode;
 }
 
+/* Nid of memory node on blade. -1 if no blade-local memory */
+static inline int uv_blade_to_memory_nid(int bid)
+{
+	return uv_blade_info[bid].memory_nid;
+}
+
 /* Determine the number of possible cpus on a blade */
 static inline int uv_blade_nr_possible_cpus(int bid)
 {
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 2284a48..d2ed6c5 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -3793,6 +3793,9 @@ int arch_enable_uv_irq(char *irq_name, unsigned int irq, int cpu, int mmr_blade,
 	mmr_pnode = uv_blade_to_pnode(mmr_blade);
 	uv_write_global_mmr64(mmr_pnode, mmr_offset, mmr_value);
 
+	if (cfg->move_in_progress)
+		send_cleanup_vector(cfg);
+
 	return irq;
 }
 
diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c
index 8e4cbb2..a5371ec 100644
--- a/arch/x86/kernel/apic/x2apic_cluster.c
+++ b/arch/x86/kernel/apic/x2apic_cluster.c
@@ -17,11 +17,13 @@ static int x2apic_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
 	return x2apic_enabled();
 }
 
-/* Start with all IRQs pointing to boot CPU.  IRQ balancing will shift them. */
-
+/*
+ * need to use more than cpu 0, because we need more vectors when
+ * MSI-X are used.
+ */
 static const struct cpumask *x2apic_target_cpus(void)
 {
-	return cpumask_of(0);
+	return cpu_online_mask;
 }
 
 /*
@@ -170,7 +172,7 @@ static unsigned long set_apic_id(unsigned int id)
 
 static int x2apic_cluster_phys_pkg_id(int initial_apicid, int index_msb)
 {
-	return current_cpu_data.initial_apicid >> index_msb;
+	return initial_apicid >> index_msb;
 }
 
 static void x2apic_send_IPI_self(int vector)
diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c
index a284359..a8989aa 100644
--- a/arch/x86/kernel/apic/x2apic_phys.c
+++ b/arch/x86/kernel/apic/x2apic_phys.c
@@ -27,11 +27,13 @@ static int x2apic_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
 		return 0;
 }
 
-/* Start with all IRQs pointing to boot CPU.  IRQ balancing will shift them. */
-
+/*
+ * need to use more than cpu 0, because we need more vectors when
+ * MSI-X are used.
+ */
 static const struct cpumask *x2apic_target_cpus(void)
 {
-	return cpumask_of(0);
+	return cpu_online_mask;
 }
 
 static void x2apic_vector_allocation_domain(int cpu, struct cpumask *retmask)
@@ -162,7 +164,7 @@ static unsigned long set_apic_id(unsigned int id)
 
 static int x2apic_phys_pkg_id(int initial_apicid, int index_msb)
 {
-	return current_cpu_data.initial_apicid >> index_msb;
+	return initial_apicid >> index_msb;
 }
 
 static void x2apic_send_IPI_self(int vector)
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index 096d19a..832e908 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -261,7 +261,7 @@ struct apic apic_x2apic_uv_x = {
 	.apic_id_registered		= uv_apic_id_registered,
 
 	.irq_delivery_mode		= dest_Fixed,
-	.irq_dest_mode			= 1, /* logical */
+	.irq_dest_mode			= 0, /* physical */
 
 	.target_cpus			= uv_target_cpus,
 	.disable_esr			= 0,
@@ -362,12 +362,6 @@ static __init void get_lowmem_redirect(unsigned long *base, unsigned long *size)
 	BUG();
 }
 
-static __init void map_low_mmrs(void)
-{
-	init_extra_mapping_uc(UV_GLOBAL_MMR32_BASE, UV_GLOBAL_MMR32_SIZE);
-	init_extra_mapping_uc(UV_LOCAL_MMR_BASE, UV_LOCAL_MMR_SIZE);
-}
-
 enum map_type {map_wb, map_uc};
 
 static __init void map_high(char *id, unsigned long base, int shift,
@@ -395,26 +389,6 @@ static __init void map_gru_high(int max_pnode)
 		map_high("GRU", gru.s.base, shift, max_pnode, map_wb);
 }
 
-static __init void map_config_high(int max_pnode)
-{
-	union uvh_rh_gam_cfg_overlay_config_mmr_u cfg;
-	int shift = UVH_RH_GAM_CFG_OVERLAY_CONFIG_MMR_BASE_SHFT;
-
-	cfg.v = uv_read_local_mmr(UVH_RH_GAM_CFG_OVERLAY_CONFIG_MMR);
-	if (cfg.s.enable)
-		map_high("CONFIG", cfg.s.base, shift, max_pnode, map_uc);
-}
-
-static __init void map_mmr_high(int max_pnode)
-{
-	union uvh_rh_gam_mmr_overlay_config_mmr_u mmr;
-	int shift = UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR_BASE_SHFT;
-
-	mmr.v = uv_read_local_mmr(UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR);
-	if (mmr.s.enable)
-		map_high("MMR", mmr.s.base, shift, max_pnode, map_uc);
-}
-
 static __init void map_mmioh_high(int max_pnode)
 {
 	union uvh_rh_gam_mmioh_overlay_config_mmr_u mmioh;
@@ -566,8 +540,6 @@ void __init uv_system_init(void)
 	unsigned long mmr_base, present, paddr;
 	unsigned short pnode_mask;
 
-	map_low_mmrs();
-
 	m_n_config.v = uv_read_local_mmr(UVH_SI_ADDR_MAP_CONFIG);
 	m_val = m_n_config.s.m_skt;
 	n_val = m_n_config.s.n_skt;
@@ -591,6 +563,8 @@ void __init uv_system_init(void)
 	bytes = sizeof(struct uv_blade_info) * uv_num_possible_blades();
 	uv_blade_info = kmalloc(bytes, GFP_KERNEL);
 	BUG_ON(!uv_blade_info);
+	for (blade = 0; blade < uv_num_possible_blades(); blade++)
+		uv_blade_info[blade].memory_nid = -1;
 
 	get_lowmem_redirect(&lowmem_redir_base, &lowmem_redir_size);
 
@@ -629,6 +603,9 @@ void __init uv_system_init(void)
 		lcpu = uv_blade_info[blade].nr_possible_cpus;
 		uv_blade_info[blade].nr_possible_cpus++;
 
+		/* Any node on the blade, else will contain -1. */
+		uv_blade_info[blade].memory_nid = nid;
+
 		uv_cpu_hub_info(cpu)->lowmem_remap_base = lowmem_redir_base;
 		uv_cpu_hub_info(cpu)->lowmem_remap_top = lowmem_redir_size;
 		uv_cpu_hub_info(cpu)->m_val = m_val;
@@ -662,11 +639,10 @@ void __init uv_system_init(void)
 		pnode = (paddr >> m_val) & pnode_mask;
 		blade = boot_pnode_to_blade(pnode);
 		uv_node_to_blade[nid] = blade;
+		max_pnode = max(pnode, max_pnode);
 	}
 
 	map_gru_high(max_pnode);
-	map_mmr_high(max_pnode);
-	map_config_high(max_pnode);
 	map_mmioh_high(max_pnode);
 
 	uv_cpu_init();
diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c
index 79302e9..442b550 100644
--- a/arch/x86/kernel/apm_32.c
+++ b/arch/x86/kernel/apm_32.c
@@ -811,7 +811,7 @@ static int apm_do_idle(void)
 	u8 ret = 0;
 	int idled = 0;
 	int polling;
-	int err;
+	int err = 0;
 
 	polling = !!(current_thread_info()->status & TS_POLLING);
 	if (polling) {
diff --git a/arch/x86/kernel/efi.c b/arch/x86/kernel/efi.c
index 96f7ac0..fe26ba3 100644
--- a/arch/x86/kernel/efi.c
+++ b/arch/x86/kernel/efi.c
@@ -354,7 +354,7 @@ void __init efi_init(void)
 	 */
 	c16 = tmp = early_ioremap(efi.systab->fw_vendor, 2);
 	if (c16) {
-		for (i = 0; i < sizeof(vendor) && *c16; ++i)
+		for (i = 0; i < sizeof(vendor) - 1 && *c16; ++i)
 			vendor[i] = *c16++;
 		vendor[i] = '\0';
 	} else
@@ -512,7 +512,7 @@ void __init efi_enter_virtual_mode(void)
 			&& end_pfn <= max_pfn_mapped))
 			va = __va(md->phys_addr);
 		else
-			va = efi_ioremap(md->phys_addr, size);
+			va = efi_ioremap(md->phys_addr, size, md->type);
 
 		md->virt_addr = (u64) (unsigned long) va;
 
diff --git a/arch/x86/kernel/efi_64.c b/arch/x86/kernel/efi_64.c
index 22c3b78..ac0621a 100644
--- a/arch/x86/kernel/efi_64.c
+++ b/arch/x86/kernel/efi_64.c
@@ -98,10 +98,14 @@ void __init efi_call_phys_epilog(void)
 	early_runtime_code_mapping_set_exec(0);
 }
 
-void __iomem *__init efi_ioremap(unsigned long phys_addr, unsigned long size)
+void __iomem *__init efi_ioremap(unsigned long phys_addr, unsigned long size,
+				 u32 type)
 {
 	unsigned long last_map_pfn;
 
+	if (type == EFI_MEMORY_MAPPED_IO)
+		return ioremap(phys_addr, size);
+
 	last_map_pfn = init_memory_mapping(phys_addr, phys_addr + size);
 	if ((last_map_pfn << PAGE_SHIFT) < phys_addr + size)
 		return NULL;
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index 8663afb..0d98a01 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -602,7 +602,11 @@ ignore_int:
 #endif
 	iret
 
-.section .cpuinit.data,"wa"
+#ifndef CONFIG_HOTPLUG_CPU
+	__CPUINITDATA
+#else
+	__REFDATA
+#endif
 .align 4
 ENTRY(initial_code)
 	.long i386_start_kernel
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 508e982..9eb8976 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -3,6 +3,7 @@
 #include <linux/init.h>
 #include <linux/pm.h>
 #include <linux/efi.h>
+#include <linux/dmi.h>
 #include <acpi/reboot.h>
 #include <asm/io.h>
 #include <asm/apic.h>
@@ -17,7 +18,6 @@
 #include <asm/cpu.h>
 
 #ifdef CONFIG_X86_32
-# include <linux/dmi.h>
 # include <linux/ctype.h>
 # include <linux/mc146818rtc.h>
 #else
@@ -404,6 +404,46 @@ EXPORT_SYMBOL(machine_real_restart);
 
 #endif /* CONFIG_X86_32 */
 
+/*
+ * Some Apple MacBook and MacBookPro's needs reboot=p to be able to reboot
+ */
+static int __init set_pci_reboot(const struct dmi_system_id *d)
+{
+	if (reboot_type != BOOT_CF9) {
+		reboot_type = BOOT_CF9;
+		printk(KERN_INFO "%s series board detected. "
+		       "Selecting PCI-method for reboots.\n", d->ident);
+	}
+	return 0;
+}
+
+static struct dmi_system_id __initdata pci_reboot_dmi_table[] = {
+	{	/* Handle problems with rebooting on Apple MacBook5,2 */
+		.callback = set_pci_reboot,
+		.ident = "Apple MacBook",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Apple Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "MacBook5,2"),
+		},
+	},
+	{	/* Handle problems with rebooting on Apple MacBookPro5,1 */
+		.callback = set_pci_reboot,
+		.ident = "Apple MacBookPro5,1",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Apple Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "MacBookPro5,1"),
+		},
+	},
+	{ }
+};
+
+static int __init pci_reboot_init(void)
+{
+	dmi_check_system(pci_reboot_dmi_table);
+	return 0;
+}
+core_initcall(pci_reboot_init);
+
 static inline void kb_wait(void)
 {
 	int i;
diff --git a/arch/x86/kernel/vmi_32.c b/arch/x86/kernel/vmi_32.c
index b263423..95a7289 100644
--- a/arch/x86/kernel/vmi_32.c
+++ b/arch/x86/kernel/vmi_32.c
@@ -441,7 +441,7 @@ vmi_startup_ipi_hook(int phys_apicid, unsigned long start_eip,
 	ap.ds = __USER_DS;
 	ap.es = __USER_DS;
 	ap.fs = __KERNEL_PERCPU;
-	ap.gs = 0;
+	ap.gs = __KERNEL_STACK_CANARY;
 
 	ap.eflags = 0;
 
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 59f31d2..78d185d 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -393,8 +393,8 @@ SECTIONS
 
 
 #ifdef CONFIG_X86_32
-ASSERT((_end - LOAD_OFFSET <= KERNEL_IMAGE_SIZE),
-        "kernel image bigger than KERNEL_IMAGE_SIZE")
+. = ASSERT((_end - LOAD_OFFSET <= KERNEL_IMAGE_SIZE),
+	   "kernel image bigger than KERNEL_IMAGE_SIZE");
 #else
 /*
  * Per-cpu symbols which need to be offset from __per_cpu_load
@@ -407,12 +407,12 @@ INIT_PER_CPU(irq_stack_union);
 /*
  * Build-time check on the image size:
  */
-ASSERT((_end - _text <= KERNEL_IMAGE_SIZE),
-	"kernel image bigger than KERNEL_IMAGE_SIZE")
+. = ASSERT((_end - _text <= KERNEL_IMAGE_SIZE),
+	   "kernel image bigger than KERNEL_IMAGE_SIZE");
 
 #ifdef CONFIG_SMP
-ASSERT((per_cpu__irq_stack_union == 0),
-        "irq_stack_union is not at start of per-cpu area");
+. = ASSERT((per_cpu__irq_stack_union == 0),
+           "irq_stack_union is not at start of per-cpu area");
 #endif
 
 #endif /* CONFIG_X86_32 */
@@ -420,7 +420,7 @@ ASSERT((per_cpu__irq_stack_union == 0),
 #ifdef CONFIG_KEXEC
 #include <asm/kexec.h>
 
-ASSERT(kexec_control_code_size <= KEXEC_CONTROL_CODE_MAX_SIZE,
-       "kexec control code size is too big")
+. = ASSERT(kexec_control_code_size <= KEXEC_CONTROL_CODE_MAX_SIZE,
+           "kexec control code size is too big");
 #endif
 
diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c
index 4d6f0d2..21f68e0 100644
--- a/arch/x86/kvm/i8254.c
+++ b/arch/x86/kvm/i8254.c
@@ -104,6 +104,9 @@ static s64 __kpit_elapsed(struct kvm *kvm)
 	ktime_t remaining;
 	struct kvm_kpit_state *ps = &kvm->arch.vpit->pit_state;
 
+	if (!ps->pit_timer.period)
+		return 0;
+
 	/*
 	 * The Counter does not stop when it reaches zero. In
 	 * Modes 0, 1, 4, and 5 the Counter ``wraps around'' to
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 7030b5f..0ef5bb2 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -489,16 +489,20 @@ static unsigned long *gfn_to_rmap(struct kvm *kvm, gfn_t gfn, int lpage)
  *
  * If rmapp bit zero is one, (then rmap & ~1) points to a struct kvm_rmap_desc
  * containing more mappings.
+ *
+ * Returns the number of rmap entries before the spte was added or zero if
+ * the spte was not added.
+ *
  */
-static void rmap_add(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn, int lpage)
+static int rmap_add(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn, int lpage)
 {
 	struct kvm_mmu_page *sp;
 	struct kvm_rmap_desc *desc;
 	unsigned long *rmapp;
-	int i;
+	int i, count = 0;
 
 	if (!is_rmap_pte(*spte))
-		return;
+		return count;
 	gfn = unalias_gfn(vcpu->kvm, gfn);
 	sp = page_header(__pa(spte));
 	sp->gfns[spte - sp->spt] = gfn;
@@ -515,8 +519,10 @@ static void rmap_add(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn, int lpage)
 	} else {
 		rmap_printk("rmap_add: %p %llx many->many\n", spte, *spte);
 		desc = (struct kvm_rmap_desc *)(*rmapp & ~1ul);
-		while (desc->shadow_ptes[RMAP_EXT-1] && desc->more)
+		while (desc->shadow_ptes[RMAP_EXT-1] && desc->more) {
 			desc = desc->more;
+			count += RMAP_EXT;
+		}
 		if (desc->shadow_ptes[RMAP_EXT-1]) {
 			desc->more = mmu_alloc_rmap_desc(vcpu);
 			desc = desc->more;
@@ -525,6 +531,7 @@ static void rmap_add(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn, int lpage)
 			;
 		desc->shadow_ptes[i] = spte;
 	}
+	return count;
 }
 
 static void rmap_desc_remove_entry(unsigned long *rmapp,
@@ -754,6 +761,19 @@ static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp)
 	return young;
 }
 
+#define RMAP_RECYCLE_THRESHOLD 1000
+
+static void rmap_recycle(struct kvm_vcpu *vcpu, gfn_t gfn, int lpage)
+{
+	unsigned long *rmapp;
+
+	gfn = unalias_gfn(vcpu->kvm, gfn);
+	rmapp = gfn_to_rmap(vcpu->kvm, gfn, lpage);
+
+	kvm_unmap_rmapp(vcpu->kvm, rmapp);
+	kvm_flush_remote_tlbs(vcpu->kvm);
+}
+
 int kvm_age_hva(struct kvm *kvm, unsigned long hva)
 {
 	return kvm_handle_hva(kvm, hva, kvm_age_rmapp);
@@ -1407,24 +1427,25 @@ static int kvm_mmu_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp)
  */
 void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned int kvm_nr_mmu_pages)
 {
+	int used_pages;
+
+	used_pages = kvm->arch.n_alloc_mmu_pages - kvm->arch.n_free_mmu_pages;
+	used_pages = max(0, used_pages);
+
 	/*
 	 * If we set the number of mmu pages to be smaller be than the
 	 * number of actived pages , we must to free some mmu pages before we
 	 * change the value
 	 */
 
-	if ((kvm->arch.n_alloc_mmu_pages - kvm->arch.n_free_mmu_pages) >
-	    kvm_nr_mmu_pages) {
-		int n_used_mmu_pages = kvm->arch.n_alloc_mmu_pages
-				       - kvm->arch.n_free_mmu_pages;
-
-		while (n_used_mmu_pages > kvm_nr_mmu_pages) {
+	if (used_pages > kvm_nr_mmu_pages) {
+		while (used_pages > kvm_nr_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);
-			n_used_mmu_pages--;
+			used_pages--;
 		}
 		kvm->arch.n_free_mmu_pages = 0;
 	}
@@ -1740,6 +1761,7 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *shadow_pte,
 {
 	int was_rmapped = 0;
 	int was_writeble = is_writeble_pte(*shadow_pte);
+	int rmap_count;
 
 	pgprintk("%s: spte %llx access %x write_fault %d"
 		 " user_fault %d gfn %lx\n",
@@ -1781,9 +1803,11 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *shadow_pte,
 
 	page_header_update_slot(vcpu->kvm, shadow_pte, gfn);
 	if (!was_rmapped) {
-		rmap_add(vcpu, shadow_pte, gfn, largepage);
+		rmap_count = rmap_add(vcpu, shadow_pte, gfn, largepage);
 		if (!is_rmap_pte(*shadow_pte))
 			kvm_release_pfn_clean(pfn);
+		if (rmap_count > RMAP_RECYCLE_THRESHOLD)
+			rmap_recycle(vcpu, gfn, largepage);
 	} else {
 		if (was_writeble)
 			kvm_release_pfn_dirty(pfn);
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 71510e0..b1f658a 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -711,6 +711,7 @@ static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 		svm->vmcb->control.tsc_offset += delta;
 		vcpu->cpu = cpu;
 		kvm_migrate_timers(vcpu);
+		svm->asid_generation = 0;
 	}
 
 	for (i = 0; i < NR_HOST_SAVE_USER_MSRS; i++)
@@ -1031,7 +1032,6 @@ static void new_asid(struct vcpu_svm *svm, struct svm_cpu_data *svm_data)
 		svm->vmcb->control.tlb_ctl = TLB_CONTROL_FLUSH_ALL_ASID;
 	}
 
-	svm->vcpu.cpu = svm_data->cpu;
 	svm->asid_generation = svm_data->asid_generation;
 	svm->vmcb->control.asid = svm_data->next_asid++;
 }
@@ -2300,8 +2300,8 @@ static void pre_svm_run(struct vcpu_svm *svm)
 	struct svm_cpu_data *svm_data = per_cpu(svm_data, cpu);
 
 	svm->vmcb->control.tlb_ctl = TLB_CONTROL_DO_NOTHING;
-	if (svm->vcpu.cpu != cpu ||
-	    svm->asid_generation != svm_data->asid_generation)
+	/* FIXME: handle wraparound of asid_generation */
+	if (svm->asid_generation != svm_data->asid_generation)
 		new_asid(svm, svm_data);
 }
 
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 356a0ce..29f9129 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -3157,8 +3157,8 @@ static void handle_invalid_guest_state(struct kvm_vcpu *vcpu,
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	enum emulation_result err = EMULATE_DONE;
 
-	preempt_enable();
 	local_irq_enable();
+	preempt_enable();
 
 	while (!guest_state_valid(vcpu)) {
 		err = emulate_instruction(vcpu, kvm_run, 0, 0, 0);
@@ -3168,7 +3168,7 @@ static void handle_invalid_guest_state(struct kvm_vcpu *vcpu,
 
 		if (err != EMULATE_DONE) {
 			kvm_report_emulation_failure(vcpu, "emulation failure");
-			return;
+			break;
 		}
 
 		if (signal_pending(current))
@@ -3177,8 +3177,8 @@ static void handle_invalid_guest_state(struct kvm_vcpu *vcpu,
 			schedule();
 	}
 
-	local_irq_disable();
 	preempt_disable();
+	local_irq_disable();
 
 	vmx->invalid_state_emulation_result = err;
 }
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index fe5474a..3d45290 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -704,11 +704,48 @@ static bool msr_mtrr_valid(unsigned msr)
 	return false;
 }
 
+static bool valid_pat_type(unsigned t)
+{
+	return t < 8 && (1 << t) & 0xf3; /* 0, 1, 4, 5, 6, 7 */
+}
+
+static bool valid_mtrr_type(unsigned t)
+{
+	return t < 8 && (1 << t) & 0x73; /* 0, 1, 4, 5, 6 */
+}
+
+static bool mtrr_valid(struct kvm_vcpu *vcpu, u32 msr, u64 data)
+{
+	int i;
+
+	if (!msr_mtrr_valid(msr))
+		return false;
+
+	if (msr == MSR_IA32_CR_PAT) {
+		for (i = 0; i < 8; i++)
+			if (!valid_pat_type((data >> (i * 8)) & 0xff))
+				return false;
+		return true;
+	} else if (msr == MSR_MTRRdefType) {
+		if (data & ~0xcff)
+			return false;
+		return valid_mtrr_type(data & 0xff);
+	} else if (msr >= MSR_MTRRfix64K_00000 && msr <= MSR_MTRRfix4K_F8000) {
+		for (i = 0; i < 8 ; i++)
+			if (!valid_mtrr_type((data >> (i * 8)) & 0xff))
+				return false;
+		return true;
+	}
+
+	/* variable MTRRs */
+	return valid_mtrr_type(data & 0xff);
+}
+
 static int set_msr_mtrr(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 {
 	u64 *p = (u64 *)&vcpu->arch.mtrr_state.fixed_ranges;
 
-	if (!msr_mtrr_valid(msr))
+	if (!mtrr_valid(vcpu, msr, data))
 		return 1;
 
 	if (msr == MSR_MTRRdefType) {
@@ -1079,14 +1116,13 @@ long kvm_arch_dev_ioctl(struct file *filp,
 		if (copy_to_user(user_msr_list, &msr_list, sizeof msr_list))
 			goto out;
 		r = -E2BIG;
-		if (n < num_msrs_to_save)
+		if (n < msr_list.nmsrs)
 			goto out;
 		r = -EFAULT;
 		if (copy_to_user(user_msr_list->indices, &msrs_to_save,
 				 num_msrs_to_save * sizeof(u32)))
 			goto out;
-		if (copy_to_user(user_msr_list->indices
-				 + num_msrs_to_save * sizeof(u32),
+		if (copy_to_user(user_msr_list->indices + num_msrs_to_save,
 				 &emulated_msrs,
 				 ARRAY_SIZE(emulated_msrs) * sizeof(u32)))
 			goto out;
diff --git a/arch/x86/lib/msr.c b/arch/x86/lib/msr.c
index 1440b9c..caa24ac 100644
--- a/arch/x86/lib/msr.c
+++ b/arch/x86/lib/msr.c
@@ -89,16 +89,13 @@ void rdmsr_on_cpus(const cpumask_t *mask, u32 msr_no, struct msr *msrs)
 	rv.msrs	  = msrs;
 	rv.msr_no = msr_no;
 
-	preempt_disable();
-	/*
-	 * FIXME: handle the CPU we're executing on separately for now until
-	 * smp_call_function_many has been fixed to not skip it.
-	 */
-	this_cpu = raw_smp_processor_id();
-	smp_call_function_single(this_cpu, __rdmsr_on_cpu, &rv, 1);
+	this_cpu = get_cpu();
+
+	if (cpumask_test_cpu(this_cpu, mask))
+		__rdmsr_on_cpu(&rv);
 
 	smp_call_function_many(mask, __rdmsr_on_cpu, &rv, 1);
-	preempt_enable();
+	put_cpu();
 }
 EXPORT_SYMBOL(rdmsr_on_cpus);
 
@@ -121,16 +118,13 @@ void wrmsr_on_cpus(const cpumask_t *mask, u32 msr_no, struct msr *msrs)
 	rv.msrs   = msrs;
 	rv.msr_no = msr_no;
 
-	preempt_disable();
-	/*
-	 * FIXME: handle the CPU we're executing on separately for now until
-	 * smp_call_function_many has been fixed to not skip it.
-	 */
-	this_cpu = raw_smp_processor_id();
-	smp_call_function_single(this_cpu, __wrmsr_on_cpu, &rv, 1);
+	this_cpu = get_cpu();
+
+	if (cpumask_test_cpu(this_cpu, mask))
+		__wrmsr_on_cpu(&rv);
 
 	smp_call_function_many(mask, __wrmsr_on_cpu, &rv, 1);
-	preempt_enable();
+	put_cpu();
 }
 EXPORT_SYMBOL(wrmsr_on_cpus);
 
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 1b734d7..7e600c1 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -591,9 +591,12 @@ static int __change_page_attr(struct cpa_data *cpa, int primary)
 	unsigned int level;
 	pte_t *kpte, old_pte;
 
-	if (cpa->flags & CPA_PAGES_ARRAY)
-		address = (unsigned long)page_address(cpa->pages[cpa->curpage]);
-	else if (cpa->flags & CPA_ARRAY)
+	if (cpa->flags & CPA_PAGES_ARRAY) {
+		struct page *page = cpa->pages[cpa->curpage];
+		if (unlikely(PageHighMem(page)))
+			return 0;
+		address = (unsigned long)page_address(page);
+	} else if (cpa->flags & CPA_ARRAY)
 		address = cpa->vaddr[cpa->curpage];
 	else
 		address = *cpa->vaddr;
@@ -697,9 +700,12 @@ static int cpa_process_alias(struct cpa_data *cpa)
 	 * No need to redo, when the primary call touched the direct
 	 * mapping already:
 	 */
-	if (cpa->flags & CPA_PAGES_ARRAY)
-		vaddr = (unsigned long)page_address(cpa->pages[cpa->curpage]);
-	else if (cpa->flags & CPA_ARRAY)
+	if (cpa->flags & CPA_PAGES_ARRAY) {
+		struct page *page = cpa->pages[cpa->curpage];
+		if (unlikely(PageHighMem(page)))
+			return 0;
+		vaddr = (unsigned long)page_address(page);
+	} else if (cpa->flags & CPA_ARRAY)
 		vaddr = cpa->vaddr[cpa->curpage];
 	else
 		vaddr = *cpa->vaddr;
@@ -997,12 +1003,15 @@ EXPORT_SYMBOL(set_memory_array_uc);
 int _set_memory_wc(unsigned long addr, int numpages)
 {
 	int ret;
+	unsigned long addr_copy = addr;
+
 	ret = change_page_attr_set(&addr, numpages,
 				    __pgprot(_PAGE_CACHE_UC_MINUS), 0);
-
 	if (!ret) {
-		ret = change_page_attr_set(&addr, numpages,
-				    __pgprot(_PAGE_CACHE_WC), 0);
+		ret = change_page_attr_set_clr(&addr_copy, numpages,
+					       __pgprot(_PAGE_CACHE_WC),
+					       __pgprot(_PAGE_CACHE_MASK),
+					       0, 0, NULL);
 	}
 	return ret;
 }
@@ -1119,7 +1128,9 @@ int set_pages_array_uc(struct page **pages, int addrinarray)
 	int free_idx;
 
 	for (i = 0; i < addrinarray; i++) {
-		start = (unsigned long)page_address(pages[i]);
+		if (PageHighMem(pages[i]))
+			continue;
+		start = page_to_pfn(pages[i]) << PAGE_SHIFT;
 		end = start + PAGE_SIZE;
 		if (reserve_memtype(start, end, _PAGE_CACHE_UC_MINUS, NULL))
 			goto err_out;
@@ -1132,7 +1143,9 @@ int set_pages_array_uc(struct page **pages, int addrinarray)
 err_out:
 	free_idx = i;
 	for (i = 0; i < free_idx; i++) {
-		start = (unsigned long)page_address(pages[i]);
+		if (PageHighMem(pages[i]))
+			continue;
+		start = page_to_pfn(pages[i]) << PAGE_SHIFT;
 		end = start + PAGE_SIZE;
 		free_memtype(start, end);
 	}
@@ -1161,7 +1174,9 @@ int set_pages_array_wb(struct page **pages, int addrinarray)
 		return retval;
 
 	for (i = 0; i < addrinarray; i++) {
-		start = (unsigned long)page_address(pages[i]);
+		if (PageHighMem(pages[i]))
+			continue;
+		start = page_to_pfn(pages[i]) << PAGE_SHIFT;
 		end = start + PAGE_SIZE;
 		free_memtype(start, end);
 	}
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index af8f965..ed34f5e 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -329,7 +329,6 @@ void __init reserve_top_address(unsigned long reserve)
 	printk(KERN_INFO "Reserving virtual address space above 0x%08x\n",
 	       (int)-reserve);
 	__FIXADDR_TOP = -reserve - PAGE_SIZE;
-	__VMALLOC_RESERVE += reserve;
 #endif
 }