Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/avi/kvm

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/avi/kvm: (80 commits)
  KVM: Use CPU_DYING for disabling virtualization
  KVM: Tune hotplug/suspend IPIs
  KVM: Keep track of which cpus have virtualization enabled
  SMP: Allow smp_call_function_single() to current cpu
  i386: Allow smp_call_function_single() to current cpu
  x86_64: Allow smp_call_function_single() to current cpu
  HOTPLUG: Adapt thermal throttle to CPU_DYING
  HOTPLUG: Adapt cpuset hotplug callback to CPU_DYING
  HOTPLUG: Add CPU_DYING notifier
  KVM: Clean up #includes
  KVM: Remove kvmfs in favor of the anonymous inodes source
  KVM: SVM: Reliably detect if SVM was disabled by BIOS
  KVM: VMX: Remove unnecessary code in vmx_tlb_flush()
  KVM: MMU: Fix Wrong tlb flush order
  KVM: VMX: Reinitialize the real-mode tss when entering real mode
  KVM: Avoid useless memory write when possible
  KVM: Fix x86 emulator writeback
  KVM: Add support for in-kernel pio handlers
  KVM: VMX: Fix interrupt checking on lightweight exit
  KVM: Adds support for in-kernel mmio handlers
  ...

arch/i386/kernel/cpu/mcheck/therm_throt.c

@@ -134,19 +134,21 @@ static __cpuinit int thermal_throttle_cpu_callback(struct notifier_block *nfb,
 	int err;
 
 	sys_dev = get_cpu_sysdev(cpu);
-	mutex_lock(&therm_cpu_lock);
 	switch (action) {
 	case CPU_ONLINE:
 	case CPU_ONLINE_FROZEN:
+		mutex_lock(&therm_cpu_lock);
 		err = thermal_throttle_add_dev(sys_dev);
+		mutex_unlock(&therm_cpu_lock);
 		WARN_ON(err);
 		break;
 	case CPU_DEAD:
 	case CPU_DEAD_FROZEN:
+		mutex_lock(&therm_cpu_lock);
 		thermal_throttle_remove_dev(sys_dev);
+		mutex_unlock(&therm_cpu_lock);
 		break;
 	}
-	mutex_unlock(&therm_cpu_lock);
 	return NOTIFY_OK;
 }
 

arch/i386/kernel/smpcommon.c

@@ -47,7 +47,7 @@ int smp_call_function(void (*func) (void *info), void *info, int nonatomic,
 EXPORT_SYMBOL(smp_call_function);
 
 /**
- * smp_call_function_single - Run a function on another CPU
+ * smp_call_function_single - Run a function on a specific CPU
  * @cpu: The target CPU.  Cannot be the calling CPU.
  * @func: The function to run. This must be fast and non-blocking.
  * @info: An arbitrary pointer to pass to the function.
@@ -66,9 +66,11 @@ int smp_call_function_single(int cpu, void (*func) (void *info), void *info,
 	int ret;
 	int me = get_cpu();
 	if (cpu == me) {
-		WARN_ON(1);
+		local_irq_disable();
+		func(info);
+		local_irq_enable();
 		put_cpu();
-		return -EBUSY;
+		return 0;
 	}
 
 	ret = smp_call_function_mask(cpumask_of_cpu(cpu), func, info, wait);

arch/x86_64/kernel/smp.c

@@ -357,7 +357,7 @@ __smp_call_function_single(int cpu, void (*func) (void *info), void *info,
 }
 
 /*
- * smp_call_function_single - Run a function on another CPU
+ * smp_call_function_single - Run a function on a specific CPU
  * @func: The function to run. This must be fast and non-blocking.
  * @info: An arbitrary pointer to pass to the function.
  * @nonatomic: Currently unused.
@@ -374,14 +374,18 @@ int smp_call_function_single (int cpu, void (*func) (void *info), void *info,
 {
 	/* prevent preemption and reschedule on another processor */
 	int me = get_cpu();
+
+	/* Can deadlock when called with interrupts disabled */
+	WARN_ON(irqs_disabled());
+
 	if (cpu == me) {
+		local_irq_disable();
+		func(info);
+		local_irq_enable();
 		put_cpu();
 		return 0;
 	}
 
-	/* Can deadlock when called with interrupts disabled */
-	WARN_ON(irqs_disabled());
-
 	spin_lock_bh(&call_lock);
 	__smp_call_function_single(cpu, func, info, nonatomic, wait);
 	spin_unlock_bh(&call_lock);

drivers/kvm/Kconfig

 #
 # KVM configuration
 #
-menu "Virtualization"
+menuconfig VIRTUALIZATION
+	bool "Virtualization"
 	depends on X86
+	default y
+
+if VIRTUALIZATION
 
 config KVM
 	tristate "Kernel-based Virtual Machine (KVM) support"
 	depends on X86 && EXPERIMENTAL
+	depends on X86_CMPXCHG64 || 64BIT
 	---help---
 	  Support hosting fully virtualized guest machines using hardware
 	  virtualization extensions.  You will need a fairly recent
@@ -35,4 +40,4 @@ config KVM_AMD
 	  Provides support for KVM on AMD processors equipped with the AMD-V
 	  (SVM) extensions.
 
-endmenu
+endif # VIRTUALIZATION

drivers/kvm/kvm.h

@@ -10,6 +10,8 @@
 #include <linux/list.h>
 #include <linux/mutex.h>
 #include <linux/spinlock.h>
+#include <linux/signal.h>
+#include <linux/sched.h>
 #include <linux/mm.h>
 #include <asm/signal.h>
 
@@ -18,6 +20,7 @@
 #include <linux/kvm_para.h>
 
 #define CR0_PE_MASK (1ULL << 0)
+#define CR0_MP_MASK (1ULL << 1)
 #define CR0_TS_MASK (1ULL << 3)
 #define CR0_NE_MASK (1ULL << 5)
 #define CR0_WP_MASK (1ULL << 16)
@@ -42,7 +45,8 @@
 	(CR0_PG_MASK | CR0_PE_MASK | CR0_WP_MASK | CR0_NE_MASK \
 	 | CR0_NW_MASK | CR0_CD_MASK)
 #define KVM_VM_CR0_ALWAYS_ON \
-	(CR0_PG_MASK | CR0_PE_MASK | CR0_WP_MASK | CR0_NE_MASK)
+	(CR0_PG_MASK | CR0_PE_MASK | CR0_WP_MASK | CR0_NE_MASK | CR0_TS_MASK \
+	 | CR0_MP_MASK)
 #define KVM_GUEST_CR4_MASK \
 	(CR4_PSE_MASK | CR4_PAE_MASK | CR4_PGE_MASK | CR4_VMXE_MASK | CR4_VME_MASK)
 #define KVM_PMODE_VM_CR4_ALWAYS_ON (CR4_VMXE_MASK | CR4_PAE_MASK)
@@ -51,10 +55,10 @@
 #define INVALID_PAGE (~(hpa_t)0)
 #define UNMAPPED_GVA (~(gpa_t)0)
 
-#define KVM_MAX_VCPUS 1
+#define KVM_MAX_VCPUS 4
 #define KVM_ALIAS_SLOTS 4
 #define KVM_MEMORY_SLOTS 4
-#define KVM_NUM_MMU_PAGES 256
+#define KVM_NUM_MMU_PAGES 1024
 #define KVM_MIN_FREE_MMU_PAGES 5
 #define KVM_REFILL_PAGES 25
 #define KVM_MAX_CPUID_ENTRIES 40
@@ -79,6 +83,11 @@
 
 #define KVM_PIO_PAGE_OFFSET 1
 
+/*
+ * vcpu->requests bit members
+ */
+#define KVM_TLB_FLUSH 0
+
 /*
  * Address types:
  *
@@ -137,7 +146,7 @@ struct kvm_mmu_page {
 	gfn_t gfn;
 	union kvm_mmu_page_role role;
 
-	hpa_t page_hpa;
+	u64 *spt;
 	unsigned long slot_bitmap; /* One bit set per slot which has memory
 				    * in this shadow page.
 				    */
@@ -232,6 +241,7 @@ struct kvm_pio_request {
 	struct page *guest_pages[2];
 	unsigned guest_page_offset;
 	int in;
+	int port;
 	int size;
 	int string;
 	int down;
@@ -252,8 +262,70 @@ struct kvm_stat {
 	u32 halt_exits;
 	u32 request_irq_exits;
 	u32 irq_exits;
+	u32 light_exits;
+	u32 efer_reload;
+};
+
+struct kvm_io_device {
+	void (*read)(struct kvm_io_device *this,
+		     gpa_t addr,
+		     int len,
+		     void *val);
+	void (*write)(struct kvm_io_device *this,
+		      gpa_t addr,
+		      int len,
+		      const void *val);
+	int (*in_range)(struct kvm_io_device *this, gpa_t addr);
+	void (*destructor)(struct kvm_io_device *this);
+
+	void             *private;
+};
+
+static inline void kvm_iodevice_read(struct kvm_io_device *dev,
+				     gpa_t addr,
+				     int len,
+				     void *val)
+{
+	dev->read(dev, addr, len, val);
+}
+
+static inline void kvm_iodevice_write(struct kvm_io_device *dev,
+				      gpa_t addr,
+				      int len,
+				      const void *val)
+{
+	dev->write(dev, addr, len, val);
+}
+
+static inline int kvm_iodevice_inrange(struct kvm_io_device *dev, gpa_t addr)
+{
+	return dev->in_range(dev, addr);
+}
+
+static inline void kvm_iodevice_destructor(struct kvm_io_device *dev)
+{
+	if (dev->destructor)
+		dev->destructor(dev);
+}
+
+/*
+ * It would be nice to use something smarter than a linear search, TBD...
+ * Thankfully we dont expect many devices to register (famous last words :),
+ * so until then it will suffice.  At least its abstracted so we can change
+ * in one place.
+ */
+struct kvm_io_bus {
+	int                   dev_count;
+#define NR_IOBUS_DEVS 6
+	struct kvm_io_device *devs[NR_IOBUS_DEVS];
 };
 
+void kvm_io_bus_init(struct kvm_io_bus *bus);
+void kvm_io_bus_destroy(struct kvm_io_bus *bus);
+struct kvm_io_device *kvm_io_bus_find_dev(struct kvm_io_bus *bus, gpa_t addr);
+void kvm_io_bus_register_dev(struct kvm_io_bus *bus,
+			     struct kvm_io_device *dev);
+
 struct kvm_vcpu {
 	struct kvm *kvm;
 	union {
@@ -266,6 +338,8 @@ struct kvm_vcpu {
 	u64 host_tsc;
 	struct kvm_run *run;
 	int interrupt_window_open;
+	int guest_mode;
+	unsigned long requests;
 	unsigned long irq_summary; /* bit vector: 1 per word in irq_pending */
 #define NR_IRQ_WORDS KVM_IRQ_BITMAP_SIZE(unsigned long)
 	unsigned long irq_pending[NR_IRQ_WORDS];
@@ -285,15 +359,20 @@ struct kvm_vcpu {
 	u64 apic_base;
 	u64 ia32_misc_enable_msr;
 	int nmsrs;
+	int save_nmsrs;
+	int msr_offset_efer;
+#ifdef CONFIG_X86_64
+	int msr_offset_kernel_gs_base;
+#endif
 	struct vmx_msr_entry *guest_msrs;
 	struct vmx_msr_entry *host_msrs;
 
-	struct list_head free_pages;
-	struct kvm_mmu_page page_header_buf[KVM_NUM_MMU_PAGES];
 	struct kvm_mmu mmu;
 
 	struct kvm_mmu_memory_cache mmu_pte_chain_cache;
 	struct kvm_mmu_memory_cache mmu_rmap_desc_cache;
+	struct kvm_mmu_memory_cache mmu_page_cache;
+	struct kvm_mmu_memory_cache mmu_page_header_cache;
 
 	gfn_t last_pt_write_gfn;
 	int   last_pt_write_count;
@@ -305,6 +384,11 @@ struct kvm_vcpu {
 	char *guest_fx_image;
 	int fpu_active;
 	int guest_fpu_loaded;
+	struct vmx_host_state {
+		int loaded;
+		u16 fs_sel, gs_sel, ldt_sel;
+		int fs_gs_ldt_reload_needed;
+	} vmx_host_state;
 
 	int mmio_needed;
 	int mmio_read_completed;
@@ -331,6 +415,7 @@ struct kvm_vcpu {
 			u32 ar;
 		} tr, es, ds, fs, gs;
 	} rmode;
+	int halt_request; /* real mode on Intel only */
 
 	int cpuid_nent;
 	struct kvm_cpuid_entry cpuid_entries[KVM_MAX_CPUID_ENTRIES];
@@ -362,12 +447,15 @@ struct kvm {
 	struct list_head active_mmu_pages;
 	int n_free_mmu_pages;
 	struct hlist_head mmu_page_hash[KVM_NUM_MMU_PAGES];
+	int nvcpus;
 	struct kvm_vcpu vcpus[KVM_MAX_VCPUS];
 	int memory_config_version;
 	int busy;
 	unsigned long rmap_overflow;
 	struct list_head vm_list;
 	struct file *filp;
+	struct kvm_io_bus mmio_bus;
+	struct kvm_io_bus pio_bus;
 };
 
 struct descriptor_table {
@@ -488,6 +576,7 @@ int kvm_setup_pio(struct kvm_vcpu *vcpu, struct kvm_run *run, int in,
 		  int size, unsigned long count, int string, int down,
 		  gva_t address, int rep, unsigned port);
 void kvm_emulate_cpuid(struct kvm_vcpu *vcpu);
+int kvm_emulate_halt(struct kvm_vcpu *vcpu);
 int emulate_invlpg(struct kvm_vcpu *vcpu, gva_t address);
 int emulate_clts(struct kvm_vcpu *vcpu);
 int emulator_get_dr(struct x86_emulate_ctxt* ctxt, int dr,
@@ -511,6 +600,7 @@ void save_msrs(struct vmx_msr_entry *e, int n);
 void kvm_resched(struct kvm_vcpu *vcpu);
 void kvm_load_guest_fpu(struct kvm_vcpu *vcpu);
 void kvm_put_guest_fpu(struct kvm_vcpu *vcpu);
+void kvm_flush_remote_tlbs(struct kvm *kvm);
 
 int kvm_read_guest(struct kvm_vcpu *vcpu,
 	       gva_t addr,
@@ -524,10 +614,12 @@ int kvm_write_guest(struct kvm_vcpu *vcpu,
 
 unsigned long segment_base(u16 selector);
 
-void kvm_mmu_pre_write(struct kvm_vcpu *vcpu, gpa_t gpa, int bytes);
-void kvm_mmu_post_write(struct kvm_vcpu *vcpu, gpa_t gpa, int bytes);
+void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
+		       const u8 *old, const u8 *new, int bytes);
 int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva);
 void kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu);
+int kvm_mmu_load(struct kvm_vcpu *vcpu);
+void kvm_mmu_unload(struct kvm_vcpu *vcpu);
 
 int kvm_hypercall(struct kvm_vcpu *vcpu, struct kvm_run *run);
 
@@ -539,6 +631,14 @@ static inline int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t gva,
 	return vcpu->mmu.page_fault(vcpu, gva, error_code);
 }
 
+static inline int kvm_mmu_reload(struct kvm_vcpu *vcpu)
+{
+	if (likely(vcpu->mmu.root_hpa != INVALID_PAGE))
+		return 0;
+
+	return kvm_mmu_load(vcpu);
+}
+
 static inline int is_long_mode(struct kvm_vcpu *vcpu)
 {
 #ifdef CONFIG_X86_64

drivers/kvm/svm.c

@@ -14,16 +14,17 @@
  *
  */
 
+#include "kvm_svm.h"
+#include "x86_emulate.h"
+
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/vmalloc.h>
 #include <linux/highmem.h>
 #include <linux/profile.h>
 #include <linux/sched.h>
-#include <asm/desc.h>
 
-#include "kvm_svm.h"
-#include "x86_emulate.h"
+#include <asm/desc.h>
 
 MODULE_AUTHOR("Qumranet");
 MODULE_LICENSE("GPL");
@@ -378,7 +379,7 @@ static __init int svm_hardware_setup(void)
 	int cpu;
 	struct page *iopm_pages;
 	struct page *msrpm_pages;
-	void *msrpm_va;
+	void *iopm_va, *msrpm_va;
 	int r;
 
 	kvm_emulator_want_group7_invlpg();
@@ -387,8 +388,10 @@ static __init int svm_hardware_setup(void)
 
 	if (!iopm_pages)
 		return -ENOMEM;
-	memset(page_address(iopm_pages), 0xff,
-					PAGE_SIZE * (1 << IOPM_ALLOC_ORDER));
+
+	iopm_va = page_address(iopm_pages);
+	memset(iopm_va, 0xff, PAGE_SIZE * (1 << IOPM_ALLOC_ORDER));
+	clear_bit(0x80, iopm_va); /* allow direct access to PC debug port */
 	iopm_base = page_to_pfn(iopm_pages) << PAGE_SHIFT;
 
 
@@ -579,7 +582,7 @@ static int svm_create_vcpu(struct kvm_vcpu *vcpu)
 		goto out2;
 
 	vcpu->svm->vmcb = page_address(page);
-	memset(vcpu->svm->vmcb, 0, PAGE_SIZE);
+	clear_page(vcpu->svm->vmcb);
 	vcpu->svm->vmcb_pa = page_to_pfn(page) << PAGE_SHIFT;
 	vcpu->svm->asid_generation = 0;
 	memset(vcpu->svm->db_regs, 0, sizeof(vcpu->svm->db_regs));
@@ -587,9 +590,9 @@ static int svm_create_vcpu(struct kvm_vcpu *vcpu)
 
 	fx_init(vcpu);
 	vcpu->fpu_active = 1;
-	vcpu->apic_base = 0xfee00000 |
-			/*for vcpu 0*/ MSR_IA32_APICBASE_BSP |
-			MSR_IA32_APICBASE_ENABLE;
+	vcpu->apic_base = 0xfee00000 | MSR_IA32_APICBASE_ENABLE;
+	if (vcpu == &vcpu->kvm->vcpus[0])
+		vcpu->apic_base |= MSR_IA32_APICBASE_BSP;
 
 	return 0;
 
@@ -955,7 +958,7 @@ static int shutdown_interception(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	 * VMCB is undefined after a SHUTDOWN intercept
 	 * so reinitialize it.
 	 */
-	memset(vcpu->svm->vmcb, 0, PAGE_SIZE);
+	clear_page(vcpu->svm->vmcb);
 	init_vmcb(vcpu->svm->vmcb);
 
 	kvm_run->exit_reason = KVM_EXIT_SHUTDOWN;
@@ -1113,12 +1116,7 @@ static int halt_interception(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 {
 	vcpu->svm->next_rip = vcpu->svm->vmcb->save.rip + 1;
 	skip_emulated_instruction(vcpu);
-	if (vcpu->irq_summary)
-		return 1;
-
-	kvm_run->exit_reason = KVM_EXIT_HLT;
-	++vcpu->stat.halt_exits;
-	return 0;
+	return kvm_emulate_halt(vcpu);
 }
 
 static int vmmcall_interception(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
@@ -1473,6 +1471,11 @@ static void load_db_regs(unsigned long *db_regs)
 	asm volatile ("mov %0, %%dr3" : : "r"(db_regs[3]));
 }
 
+static void svm_flush_tlb(struct kvm_vcpu *vcpu)
+{
+	force_new_asid(vcpu);
+}
+
 static int svm_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 {
 	u16 fs_selector;
@@ -1481,11 +1484,20 @@ static int svm_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	int r;
 
 again:
+	r = kvm_mmu_reload(vcpu);
+	if (unlikely(r))
+		return r;
+
 	if (!vcpu->mmio_read_completed)
 		do_interrupt_requests(vcpu, kvm_run);
 
 	clgi();
 
+	vcpu->guest_mode = 1;
+	if (vcpu->requests)
+		if (test_and_clear_bit(KVM_TLB_FLUSH, &vcpu->requests))
+		    svm_flush_tlb(vcpu);
+
 	pre_svm_run(vcpu);
 
 	save_host_msrs(vcpu);
@@ -1617,6 +1629,8 @@ again:
 #endif
 		: "cc", "memory" );
 
+	vcpu->guest_mode = 0;
+
 	if (vcpu->fpu_active) {
 		fx_save(vcpu->guest_fx_image);
 		fx_restore(vcpu->host_fx_image);
@@ -1681,11 +1695,6 @@ again:
 	return r;
 }
 
-static void svm_flush_tlb(struct kvm_vcpu *vcpu)
-{
-	force_new_asid(vcpu);
-}
-
 static void svm_set_cr3(struct kvm_vcpu *vcpu, unsigned long root)
 {
 	vcpu->svm->vmcb->save.cr3 = root;
@@ -1727,6 +1736,12 @@ static void svm_inject_page_fault(struct kvm_vcpu *vcpu,
 
 static int is_disabled(void)
 {
+	u64 vm_cr;
+
+	rdmsrl(MSR_VM_CR, vm_cr);
+	if (vm_cr & (1 << SVM_VM_CR_SVM_DISABLE))
+		return 1;
+
 	return 0;
 }
 

drivers/kvm/svm.h

@@ -175,8 +175,11 @@ struct __attribute__ ((__packed__)) vmcb {
 #define SVM_CPUID_FUNC 0x8000000a
 
 #define MSR_EFER_SVME_MASK (1ULL << 12)
+#define MSR_VM_CR       0xc0010114
 #define MSR_VM_HSAVE_PA 0xc0010117ULL
 
+#define SVM_VM_CR_SVM_DISABLE 4
+
 #define SVM_SELECTOR_S_SHIFT 4
 #define SVM_SELECTOR_DPL_SHIFT 5
 #define SVM_SELECTOR_P_SHIFT 7

drivers/kvm/x86_emulate.c

@@ -98,8 +98,11 @@ static u8 opcode_table[256] = {
 	0, 0, 0, 0,
 	/* 0x40 - 0x4F */
 	0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
-	/* 0x50 - 0x5F */
-	0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+	/* 0x50 - 0x57 */
+	0, 0, 0, 0, 0, 0, 0, 0,
+	/* 0x58 - 0x5F */
+	ImplicitOps, ImplicitOps, ImplicitOps, ImplicitOps,
+	ImplicitOps, ImplicitOps, ImplicitOps, ImplicitOps,
 	/* 0x60 - 0x6F */
 	0, 0, 0, DstReg | SrcMem32 | ModRM | Mov /* movsxd (x86/64) */ ,
 	0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
@@ -128,9 +131,9 @@ static u8 opcode_table[256] = {
 	/* 0xB0 - 0xBF */
 	0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
 	/* 0xC0 - 0xC7 */
-	ByteOp | DstMem | SrcImm | ModRM, DstMem | SrcImmByte | ModRM, 0, 0,
-	0, 0, ByteOp | DstMem | SrcImm | ModRM | Mov,
-	    DstMem | SrcImm | ModRM | Mov,
+	ByteOp | DstMem | SrcImm | ModRM, DstMem | SrcImmByte | ModRM,
+	0, ImplicitOps, 0, 0,
+	ByteOp | DstMem | SrcImm | ModRM | Mov, DstMem | SrcImm | ModRM | Mov,
 	/* 0xC8 - 0xCF */
 	0, 0, 0, 0, 0, 0, 0, 0,
 	/* 0xD0 - 0xD7 */
@@ -143,7 +146,8 @@ static u8 opcode_table[256] = {
 	0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
 	/* 0xF0 - 0xF7 */
 	0, 0, 0, 0,
-	0, 0, ByteOp | DstMem | SrcNone | ModRM, DstMem | SrcNone | ModRM,
+	ImplicitOps, 0,
+	ByteOp | DstMem | SrcNone | ModRM, DstMem | SrcNone | ModRM,
 	/* 0xF8 - 0xFF */
 	0, 0, 0, 0,
 	0, 0, ByteOp | DstMem | SrcNone | ModRM, DstMem | SrcNone | ModRM
@@ -152,7 +156,7 @@ static u8 opcode_table[256] = {
 static u16 twobyte_table[256] = {
 	/* 0x00 - 0x0F */
 	0, SrcMem | ModRM | DstReg, 0, 0, 0, 0, ImplicitOps, 0,
-	0, 0, 0, 0, 0, ImplicitOps | ModRM, 0, 0,
+	0, ImplicitOps, 0, 0, 0, ImplicitOps | ModRM, 0, 0,
 	/* 0x10 - 0x1F */
 	0, 0, 0, 0, 0, 0, 0, 0, ImplicitOps | ModRM, 0, 0, 0, 0, 0, 0, 0,
 	/* 0x20 - 0x2F */
@@ -481,6 +485,7 @@ x86_emulate_memop(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 	int mode = ctxt->mode;
 	unsigned long modrm_ea;
 	int use_modrm_ea, index_reg = 0, base_reg = 0, scale, rip_relative = 0;
+	int no_wb = 0;
 
 	/* Shadow copy of register state. Committed on successful emulation. */
 	unsigned long _regs[NR_VCPU_REGS];
@@ -1047,7 +1052,7 @@ done_prefixes:
 						      _regs[VCPU_REGS_RSP]),
 				     &dst.val, dst.bytes, ctxt)) != 0)
 				goto done;
-			dst.val = dst.orig_val;	/* skanky: disable writeback */
+			no_wb = 1;
 			break;
 		default:
 			goto cannot_emulate;
@@ -1056,7 +1061,7 @@ done_prefixes:
 	}
 
 writeback:
-	if ((d & Mov) || (dst.orig_val != dst.val)) {
+	if (!no_wb) {
 		switch (dst.type) {
 		case OP_REG:
 			/* The 4-byte case *is* correct: in 64-bit mode we zero-extend. */
@@ -1149,6 +1154,23 @@ special_insn:
 	case 0xae ... 0xaf:	/* scas */
 		DPRINTF("Urk! I don't handle SCAS.\n");
 		goto cannot_emulate;
+	case 0xf4:              /* hlt */
+		ctxt->vcpu->halt_request = 1;
+		goto done;
+	case 0xc3: /* ret */
+		dst.ptr = &_eip;
+		goto pop_instruction;
+	case 0x58 ... 0x5f: /* pop reg */
+		dst.ptr = (unsigned long *)&_regs[b & 0x7];
+
+pop_instruction:
+		if ((rc = ops->read_std(register_address(ctxt->ss_base,
+			_regs[VCPU_REGS_RSP]), dst.ptr, op_bytes, ctxt)) != 0)
+			goto done;
+
+		register_address_increment(_regs[VCPU_REGS_RSP], op_bytes);
+		no_wb = 1; /* Disable writeback. */
+		break;
 	}
 	goto writeback;
 
@@ -1302,8 +1324,10 @@ twobyte_insn:
 
 twobyte_special_insn:
 	/* Disable writeback. */
-	dst.orig_val = dst.val;
+	no_wb = 1;
 	switch (b) {
+	case 0x09:		/* wbinvd */
+		break;
 	case 0x0d:		/* GrpP (prefetch) */
 	case 0x18:		/* Grp16 (prefetch/nop) */
 		break;

fs/anon_inodes.c

@@ -139,6 +139,7 @@ err_put_filp:
 	put_filp(file);
 	return error;
 }
+EXPORT_SYMBOL_GPL(anon_inode_getfd);
 
 /*
  * A single inode exists for all anon_inode files. Contrary to pipes,

include/linux/magic.h

@@ -13,7 +13,6 @@
 #define HPFS_SUPER_MAGIC	0xf995e849
 #define ISOFS_SUPER_MAGIC	0x9660
 #define JFFS2_SUPER_MAGIC	0x72b6
-#define KVMFS_SUPER_MAGIC	0x19700426
 #define ANON_INODE_FS_MAGIC	0x09041934
 
 #define MINIX_SUPER_MAGIC	0x137F		/* original minix fs */

include/linux/notifier.h

@@ -196,6 +196,8 @@ extern int __srcu_notifier_call_chain(struct srcu_notifier_head *nh,
 #define CPU_DEAD		0x0007 /* CPU (unsigned)v dead */
 #define CPU_LOCK_ACQUIRE	0x0008 /* Acquire all hotcpu locks */
 #define CPU_LOCK_RELEASE	0x0009 /* Release all hotcpu locks */
+#define CPU_DYING		0x000A /* CPU (unsigned)v not running any task,
+				        * not handling interrupts, soon dead */
 
 /* Used for CPU hotplug events occuring while tasks are frozen due to a suspend
  * operation in progress
@@ -208,6 +210,7 @@ extern int __srcu_notifier_call_chain(struct srcu_notifier_head *nh,
 #define CPU_DOWN_PREPARE_FROZEN	(CPU_DOWN_PREPARE | CPU_TASKS_FROZEN)
 #define CPU_DOWN_FAILED_FROZEN	(CPU_DOWN_FAILED | CPU_TASKS_FROZEN)
 #define CPU_DEAD_FROZEN		(CPU_DEAD | CPU_TASKS_FROZEN)
+#define CPU_DYING_FROZEN	(CPU_DYING | CPU_TASKS_FROZEN)
 
 #endif /* __KERNEL__ */
 #endif /* _LINUX_NOTIFIER_H */

include/linux/smp.h

@@ -7,6 +7,7 @@
  */
 
 #include <linux/errno.h>
+#include <asm/system.h>
 
 extern void cpu_idle(void);
 
@@ -102,7 +103,11 @@ static inline void smp_send_reschedule(int cpu) { }
 static inline int smp_call_function_single(int cpuid, void (*func) (void *info),
 					   void *info, int retry, int wait)
 {
-	return -EBUSY;
+	WARN_ON(cpuid != 0);
+	local_irq_disable();
+	func(info);
+	local_irq_enable();
+	return 0;
 }
 
 #endif /* !SMP */

kernel/cpu.c

@@ -103,11 +103,19 @@ static inline void check_for_tasks(int cpu)
 	write_unlock_irq(&tasklist_lock);
 }
 
+struct take_cpu_down_param {
+	unsigned long mod;
+	void *hcpu;
+};
+
 /* Take this CPU down. */
-static int take_cpu_down(void *unused)
+static int take_cpu_down(void *_param)
 {
+	struct take_cpu_down_param *param = _param;
 	int err;
 
+	raw_notifier_call_chain(&cpu_chain, CPU_DYING | param->mod,
+				param->hcpu);
 	/* Ensure this CPU doesn't handle any more interrupts. */
 	err = __cpu_disable();
 	if (err < 0)
@@ -127,6 +135,10 @@ static int _cpu_down(unsigned int cpu, int tasks_frozen)
 	cpumask_t old_allowed, tmp;
 	void *hcpu = (void *)(long)cpu;
 	unsigned long mod = tasks_frozen ? CPU_TASKS_FROZEN : 0;
+	struct take_cpu_down_param tcd_param = {
+		.mod = mod,
+		.hcpu = hcpu,
+	};
 
 	if (num_online_cpus() == 1)
 		return -EBUSY;
@@ -153,7 +165,7 @@ static int _cpu_down(unsigned int cpu, int tasks_frozen)
 	set_cpus_allowed(current, tmp);
 
 	mutex_lock(&cpu_bitmask_lock);
-	p = __stop_machine_run(take_cpu_down, NULL, cpu);
+	p = __stop_machine_run(take_cpu_down, &tcd_param, cpu);
 	mutex_unlock(&cpu_bitmask_lock);
 
 	if (IS_ERR(p) || cpu_online(cpu)) {

kernel/cpuset.c

@@ -2138,6 +2138,9 @@ static void common_cpu_mem_hotplug_unplug(void)
 static int cpuset_handle_cpuhp(struct notifier_block *nb,
 				unsigned long phase, void *cpu)
 {
+	if (phase == CPU_DYING || phase == CPU_DYING_FROZEN)
+		return NOTIFY_DONE;
+
 	common_cpu_mem_hotplug_unplug();
 	return 0;
 }