X-Git-Url: https://err.no/cgi-bin/gitweb.cgi?a=blobdiff_plain;f=drivers%2Fkvm%2Fkvm_main.c;h=c0f372f1d761312bc648d9deccd8e74609fbc513;hb=444ad82bc3eaa554be40d22dc248e58aeefd54d9;hp=ffbdadd879713de75d7ec182707d0817de47829a;hpb=1fd4f2a5ed8f80cf6e23d2bdf78554f6a1ac7997;p=linux-2.6

diff --git a/drivers/kvm/kvm_main.c b/drivers/kvm/kvm_main.c
index ffbdadd879..c0f372f1d7 100644
--- a/drivers/kvm/kvm_main.c
+++ b/drivers/kvm/kvm_main.c
@@ -38,6 +38,7 @@
 #include <linux/cpumask.h>
 #include <linux/smp.h>
 #include <linux/anon_inodes.h>
+#include <linux/profile.h>
 
 #include <asm/processor.h>
 #include <asm/msr.h>
@@ -53,7 +54,7 @@ static LIST_HEAD(vm_list);
 
 static cpumask_t cpus_hardware_enabled;
 
-struct kvm_arch_ops *kvm_arch_ops;
+struct kvm_x86_ops *kvm_x86_ops;
 struct kmem_cache *kvm_vcpu_cache;
 EXPORT_SYMBOL_GPL(kvm_vcpu_cache);
 
@@ -76,6 +77,7 @@ static struct kvm_stats_debugfs_item {
 	{ "signal_exits", STAT_OFFSET(signal_exits) },
 	{ "irq_window", STAT_OFFSET(irq_window_exits) },
 	{ "halt_exits", STAT_OFFSET(halt_exits) },
+	{ "halt_wakeup", STAT_OFFSET(halt_wakeup) },
 	{ "request_irq", STAT_OFFSET(request_irq_exits) },
 	{ "irq_exits", STAT_OFFSET(irq_exits) },
 	{ "light_exits", STAT_OFFSET(light_exits) },
@@ -181,14 +183,14 @@ static void vcpu_load(struct kvm_vcpu *vcpu)
 	mutex_lock(&vcpu->mutex);
 	cpu = get_cpu();
 	preempt_notifier_register(&vcpu->preempt_notifier);
-	kvm_arch_ops->vcpu_load(vcpu, cpu);
+	kvm_x86_ops->vcpu_load(vcpu, cpu);
 	put_cpu();
 }
 
 static void vcpu_put(struct kvm_vcpu *vcpu)
 {
 	preempt_disable();
-	kvm_arch_ops->vcpu_put(vcpu);
+	kvm_x86_ops->vcpu_put(vcpu);
 	preempt_notifier_unregister(&vcpu->preempt_notifier);
 	preempt_enable();
 	mutex_unlock(&vcpu->mutex);
@@ -196,21 +198,15 @@ static void vcpu_put(struct kvm_vcpu *vcpu)
 
 static void ack_flush(void *_completed)
 {
-	atomic_t *completed = _completed;
-
-	atomic_inc(completed);
 }
 
 void kvm_flush_remote_tlbs(struct kvm *kvm)
 {
-	int i, cpu, needed;
+	int i, cpu;
 	cpumask_t cpus;
 	struct kvm_vcpu *vcpu;
-	atomic_t completed;
 
-	atomic_set(&completed, 0);
 	cpus_clear(cpus);
-	needed = 0;
 	for (i = 0; i < KVM_MAX_VCPUS; ++i) {
 		vcpu = kvm->vcpus[i];
 		if (!vcpu)
@@ -219,23 +215,9 @@ void kvm_flush_remote_tlbs(struct kvm *kvm)
 			continue;
 		cpu = vcpu->cpu;
 		if (cpu != -1 && cpu != raw_smp_processor_id())
-			if (!cpu_isset(cpu, cpus)) {
-				cpu_set(cpu, cpus);
-				++needed;
-			}
-	}
-
-	/*
-	 * We really want smp_call_function_mask() here.  But that's not
-	 * available, so ipi all cpus in parallel and wait for them
-	 * to complete.
-	 */
-	for (cpu = first_cpu(cpus); cpu != NR_CPUS; cpu = next_cpu(cpu, cpus))
-		smp_call_function_single(cpu, ack_flush, &completed, 1, 0);
-	while (atomic_read(&completed) != needed) {
-		cpu_relax();
-		barrier();
+			cpu_set(cpu, cpus);
 	}
+	smp_call_function_mask(cpus, ack_flush, NULL, 1);
 }
 
 int kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id)
@@ -248,6 +230,11 @@ int kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id)
 	vcpu->mmu.root_hpa = INVALID_PAGE;
 	vcpu->kvm = kvm;
 	vcpu->vcpu_id = id;
+	if (!irqchip_in_kernel(kvm) || id == 0)
+		vcpu->mp_state = VCPU_MP_STATE_RUNNABLE;
+	else
+		vcpu->mp_state = VCPU_MP_STATE_UNINITIALIZED;
+	init_waitqueue_head(&vcpu->wq);
 
 	page = alloc_page(GFP_KERNEL | __GFP_ZERO);
 	if (!page) {
@@ -281,6 +268,8 @@ EXPORT_SYMBOL_GPL(kvm_vcpu_init);
 void kvm_vcpu_uninit(struct kvm_vcpu *vcpu)
 {
 	kvm_mmu_destroy(vcpu);
+	if (vcpu->apic)
+		hrtimer_cancel(&vcpu->apic->timer.dev);
 	kvm_free_apic(vcpu->apic);
 	free_page((unsigned long)vcpu->pio_data);
 	free_page((unsigned long)vcpu->run);
@@ -366,7 +355,7 @@ static void kvm_free_vcpus(struct kvm *kvm)
 			kvm_unload_vcpu_mmu(kvm->vcpus[i]);
 	for (i = 0; i < KVM_MAX_VCPUS; ++i) {
 		if (kvm->vcpus[i]) {
-			kvm_arch_ops->vcpu_free(kvm->vcpus[i]);
+			kvm_x86_ops->vcpu_free(kvm->vcpus[i]);
 			kvm->vcpus[i] = NULL;
 		}
 	}
@@ -397,7 +386,7 @@ static int kvm_vm_release(struct inode *inode, struct file *filp)
 
 static void inject_gp(struct kvm_vcpu *vcpu)
 {
-	kvm_arch_ops->inject_gp(vcpu, 0);
+	kvm_x86_ops->inject_gp(vcpu, 0);
 }
 
 /*
@@ -472,7 +461,7 @@ void set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
 				inject_gp(vcpu);
 				return;
 			}
-			kvm_arch_ops->get_cs_db_l_bits(vcpu, &cs_db, &cs_l);
+			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");
@@ -491,7 +480,7 @@ void set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
 
 	}
 
-	kvm_arch_ops->set_cr0(vcpu, cr0);
+	kvm_x86_ops->set_cr0(vcpu, cr0);
 	vcpu->cr0 = cr0;
 
 	mutex_lock(&vcpu->kvm->lock);
@@ -534,7 +523,8 @@ void set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 		inject_gp(vcpu);
 		return;
 	}
-	kvm_arch_ops->set_cr4(vcpu, cr4);
+	kvm_x86_ops->set_cr4(vcpu, cr4);
+	vcpu->cr4 = cr4;
 	mutex_lock(&vcpu->kvm->lock);
 	kvm_mmu_reset_context(vcpu);
 	mutex_unlock(&vcpu->kvm->lock);
@@ -647,6 +637,7 @@ void fx_init(struct kvm_vcpu *vcpu)
 	fx_restore(&vcpu->host_fx_image);
 	preempt_enable();
 
+	vcpu->cr0 |= X86_CR0_ET;
 	after_mxcsr_mask = offsetof(struct i387_fxsave_struct, st_space);
 	vcpu->guest_fx_image.mxcsr = 0x1f80;
 	memset((void *)&vcpu->guest_fx_image + after_mxcsr_mask,
@@ -669,7 +660,6 @@ static int kvm_vm_ioctl_set_memory_region(struct kvm *kvm,
 	unsigned long i;
 	struct kvm_memory_slot *memslot;
 	struct kvm_memory_slot old, new;
-	int memory_config_version;
 
 	r = -EINVAL;
 	/* General sanity checks */
@@ -689,10 +679,8 @@ static int kvm_vm_ioctl_set_memory_region(struct kvm *kvm,
 	if (!npages)
 		mem->flags &= ~KVM_MEM_LOG_DIRTY_PAGES;
 
-raced:
 	mutex_lock(&kvm->lock);
 
-	memory_config_version = kvm->memory_config_version;
 	new = old = *memslot;
 
 	new.base_gfn = base_gfn;
@@ -715,11 +703,6 @@ raced:
 		      (base_gfn >= s->base_gfn + s->npages)))
 			goto out_unlock;
 	}
-	/*
-	 * Do memory allocations outside lock.  memory_config_version will
-	 * detect any races.
-	 */
-	mutex_unlock(&kvm->lock);
 
 	/* Deallocate if slot is being removed */
 	if (!npages)
@@ -736,14 +719,14 @@ raced:
 		new.phys_mem = vmalloc(npages * sizeof(struct page *));
 
 		if (!new.phys_mem)
-			goto out_free;
+			goto out_unlock;
 
 		memset(new.phys_mem, 0, npages * sizeof(struct page *));
 		for (i = 0; i < npages; ++i) {
 			new.phys_mem[i] = alloc_page(GFP_HIGHUSER
 						     | __GFP_ZERO);
 			if (!new.phys_mem[i])
-				goto out_free;
+				goto out_unlock;
 			set_page_private(new.phys_mem[i],0);
 		}
 	}
@@ -754,27 +737,14 @@ raced:
 
 		new.dirty_bitmap = vmalloc(dirty_bytes);
 		if (!new.dirty_bitmap)
-			goto out_free;
+			goto out_unlock;
 		memset(new.dirty_bitmap, 0, dirty_bytes);
 	}
 
-	mutex_lock(&kvm->lock);
-
-	if (memory_config_version != kvm->memory_config_version) {
-		mutex_unlock(&kvm->lock);
-		kvm_free_physmem_slot(&new, &old);
-		goto raced;
-	}
-
-	r = -EAGAIN;
-	if (kvm->busy)
-		goto out_unlock;
-
 	if (mem->slot >= kvm->nmemslots)
 		kvm->nmemslots = mem->slot + 1;
 
 	*memslot = new;
-	++kvm->memory_config_version;
 
 	kvm_mmu_slot_remove_write_access(kvm, mem->slot);
 	kvm_flush_remote_tlbs(kvm);
@@ -786,7 +756,6 @@ raced:
 
 out_unlock:
 	mutex_unlock(&kvm->lock);
-out_free:
 	kvm_free_physmem_slot(&new, &old);
 out:
 	return r;
@@ -805,12 +774,6 @@ static int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
 
 	mutex_lock(&kvm->lock);
 
-	/*
-	 * Prevent changes to guest memory configuration even while the lock
-	 * is not taken.
-	 */
-	++kvm->busy;
-	mutex_unlock(&kvm->lock);
 	r = -EINVAL;
 	if (log->slot >= KVM_MEMORY_SLOTS)
 		goto out;
@@ -831,18 +794,14 @@ static int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
 
 	/* If nothing is dirty, don't bother messing with page tables. */
 	if (any) {
-		mutex_lock(&kvm->lock);
 		kvm_mmu_slot_remove_write_access(kvm, log->slot);
 		kvm_flush_remote_tlbs(kvm);
 		memset(memslot->dirty_bitmap, 0, n);
-		mutex_unlock(&kvm->lock);
 	}
 
 	r = 0;
 
 out:
-	mutex_lock(&kvm->lock);
-	--kvm->busy;
 	mutex_unlock(&kvm->lock);
 	return r;
 }
@@ -895,6 +854,63 @@ out:
 	return r;
 }
 
+static int kvm_vm_ioctl_get_irqchip(struct kvm *kvm, struct kvm_irqchip *chip)
+{
+	int r;
+
+	r = 0;
+	switch (chip->chip_id) {
+	case KVM_IRQCHIP_PIC_MASTER:
+		memcpy (&chip->chip.pic,
+			&pic_irqchip(kvm)->pics[0],
+			sizeof(struct kvm_pic_state));
+		break;
+	case KVM_IRQCHIP_PIC_SLAVE:
+		memcpy (&chip->chip.pic,
+			&pic_irqchip(kvm)->pics[1],
+			sizeof(struct kvm_pic_state));
+		break;
+	case KVM_IRQCHIP_IOAPIC:
+		memcpy (&chip->chip.ioapic,
+			ioapic_irqchip(kvm),
+			sizeof(struct kvm_ioapic_state));
+		break;
+	default:
+		r = -EINVAL;
+		break;
+	}
+	return r;
+}
+
+static int kvm_vm_ioctl_set_irqchip(struct kvm *kvm, struct kvm_irqchip *chip)
+{
+	int r;
+
+	r = 0;
+	switch (chip->chip_id) {
+	case KVM_IRQCHIP_PIC_MASTER:
+		memcpy (&pic_irqchip(kvm)->pics[0],
+			&chip->chip.pic,
+			sizeof(struct kvm_pic_state));
+		break;
+	case KVM_IRQCHIP_PIC_SLAVE:
+		memcpy (&pic_irqchip(kvm)->pics[1],
+			&chip->chip.pic,
+			sizeof(struct kvm_pic_state));
+		break;
+	case KVM_IRQCHIP_IOAPIC:
+		memcpy (ioapic_irqchip(kvm),
+			&chip->chip.ioapic,
+			sizeof(struct kvm_ioapic_state));
+		break;
+	default:
+		r = -EINVAL;
+		break;
+	}
+	kvm_pic_update_irq(pic_irqchip(kvm));
+	return r;
+}
+
 static gfn_t unalias_gfn(struct kvm *kvm, gfn_t gfn)
 {
 	int i;
@@ -1099,7 +1115,7 @@ static int emulator_write_emulated_onepage(unsigned long addr,
 	gpa_t                 gpa = vcpu->mmu.gva_to_gpa(vcpu, addr);
 
 	if (gpa == UNMAPPED_GVA) {
-		kvm_arch_ops->inject_page_fault(vcpu, addr, 2);
+		kvm_x86_ops->inject_page_fault(vcpu, addr, 2);
 		return X86EMUL_PROPAGATE_FAULT;
 	}
 
@@ -1162,7 +1178,7 @@ static int emulator_cmpxchg_emulated(unsigned long addr,
 
 static unsigned long get_segment_base(struct kvm_vcpu *vcpu, int seg)
 {
-	return kvm_arch_ops->get_segment_base(vcpu, seg);
+	return kvm_x86_ops->get_segment_base(vcpu, seg);
 }
 
 int emulate_invlpg(struct kvm_vcpu *vcpu, gva_t address)
@@ -1172,10 +1188,7 @@ int emulate_invlpg(struct kvm_vcpu *vcpu, gva_t address)
 
 int emulate_clts(struct kvm_vcpu *vcpu)
 {
-	unsigned long cr0;
-
-	cr0 = vcpu->cr0 & ~X86_CR0_TS;
-	kvm_arch_ops->set_cr0(vcpu, cr0);
+	kvm_x86_ops->set_cr0(vcpu, vcpu->cr0 & ~X86_CR0_TS);
 	return X86EMUL_CONTINUE;
 }
 
@@ -1185,7 +1198,7 @@ int emulator_get_dr(struct x86_emulate_ctxt* ctxt, int dr, unsigned long *dest)
 
 	switch (dr) {
 	case 0 ... 3:
-		*dest = kvm_arch_ops->get_dr(vcpu, dr);
+		*dest = kvm_x86_ops->get_dr(vcpu, dr);
 		return X86EMUL_CONTINUE;
 	default:
 		pr_unimpl(vcpu, "%s: unexpected dr %u\n", __FUNCTION__, dr);
@@ -1198,7 +1211,7 @@ int emulator_set_dr(struct x86_emulate_ctxt *ctxt, int dr, unsigned long value)
 	unsigned long mask = (ctxt->mode == X86EMUL_MODE_PROT64) ? ~0ULL : ~0U;
 	int exception;
 
-	kvm_arch_ops->set_dr(ctxt->vcpu, dr, value & mask, &exception);
+	kvm_x86_ops->set_dr(ctxt->vcpu, dr, value & mask, &exception);
 	if (exception) {
 		/* FIXME: better handling */
 		return X86EMUL_UNHANDLEABLE;
@@ -1206,25 +1219,25 @@ int emulator_set_dr(struct x86_emulate_ctxt *ctxt, int dr, unsigned long value)
 	return X86EMUL_CONTINUE;
 }
 
-static void report_emulation_failure(struct x86_emulate_ctxt *ctxt)
+void kvm_report_emulation_failure(struct kvm_vcpu *vcpu, const char *context)
 {
 	static int reported;
 	u8 opcodes[4];
-	unsigned long rip = ctxt->vcpu->rip;
+	unsigned long rip = vcpu->rip;
 	unsigned long rip_linear;
 
-	rip_linear = rip + get_segment_base(ctxt->vcpu, VCPU_SREG_CS);
+	rip_linear = rip + get_segment_base(vcpu, VCPU_SREG_CS);
 
 	if (reported)
 		return;
 
-	emulator_read_std(rip_linear, (void *)opcodes, 4, ctxt->vcpu);
+	emulator_read_std(rip_linear, (void *)opcodes, 4, vcpu);
 
-	printk(KERN_ERR "emulation failed but !mmio_needed?"
-	       " rip %lx %02x %02x %02x %02x\n",
-	       rip, opcodes[0], opcodes[1], opcodes[2], opcodes[3]);
+	printk(KERN_ERR "emulation failed (%s) rip %lx %02x %02x %02x %02x\n",
+	       context, rip, opcodes[0], opcodes[1], opcodes[2], opcodes[3]);
 	reported = 1;
 }
+EXPORT_SYMBOL_GPL(kvm_report_emulation_failure);
 
 struct x86_emulate_ops emulate_ops = {
 	.read_std            = emulator_read_std,
@@ -1244,12 +1257,12 @@ int emulate_instruction(struct kvm_vcpu *vcpu,
 	int cs_db, cs_l;
 
 	vcpu->mmio_fault_cr2 = cr2;
-	kvm_arch_ops->cache_regs(vcpu);
+	kvm_x86_ops->cache_regs(vcpu);
 
-	kvm_arch_ops->get_cs_db_l_bits(vcpu, &cs_db, &cs_l);
+	kvm_x86_ops->get_cs_db_l_bits(vcpu, &cs_db, &cs_l);
 
 	emulate_ctxt.vcpu = vcpu;
-	emulate_ctxt.eflags = kvm_arch_ops->get_rflags(vcpu);
+	emulate_ctxt.eflags = kvm_x86_ops->get_rflags(vcpu);
 	emulate_ctxt.cr2 = cr2;
 	emulate_ctxt.mode = (emulate_ctxt.eflags & X86_EFLAGS_VM)
 		? X86EMUL_MODE_REAL : cs_l
@@ -1289,14 +1302,14 @@ int emulate_instruction(struct kvm_vcpu *vcpu,
 		if (kvm_mmu_unprotect_page_virt(vcpu, cr2))
 			return EMULATE_DONE;
 		if (!vcpu->mmio_needed) {
-			report_emulation_failure(&emulate_ctxt);
+			kvm_report_emulation_failure(vcpu, "mmio");
 			return EMULATE_FAIL;
 		}
 		return EMULATE_DO_MMIO;
 	}
 
-	kvm_arch_ops->decache_regs(vcpu);
-	kvm_arch_ops->set_rflags(vcpu, emulate_ctxt.eflags);
+	kvm_x86_ops->decache_regs(vcpu);
+	kvm_x86_ops->set_rflags(vcpu, emulate_ctxt.eflags);
 
 	if (vcpu->mmio_is_write) {
 		vcpu->mmio_needed = 0;
@@ -1307,15 +1320,45 @@ int emulate_instruction(struct kvm_vcpu *vcpu,
 }
 EXPORT_SYMBOL_GPL(emulate_instruction);
 
-int kvm_emulate_halt(struct kvm_vcpu *vcpu)
+/*
+ * The vCPU has executed a HLT instruction with in-kernel mode enabled.
+ */
+static void kvm_vcpu_block(struct kvm_vcpu *vcpu)
 {
-	if (vcpu->irq_summary ||
-		(irqchip_in_kernel(vcpu->kvm) && kvm_cpu_has_interrupt(vcpu)))
-		return 1;
+	DECLARE_WAITQUEUE(wait, current);
+
+	add_wait_queue(&vcpu->wq, &wait);
 
-	vcpu->run->exit_reason = KVM_EXIT_HLT;
+	/*
+	 * We will block until either an interrupt or a signal wakes us up
+	 */
+	while (!kvm_cpu_has_interrupt(vcpu)
+	       && !signal_pending(current)
+	       && vcpu->mp_state != VCPU_MP_STATE_RUNNABLE
+	       && vcpu->mp_state != VCPU_MP_STATE_SIPI_RECEIVED) {
+		set_current_state(TASK_INTERRUPTIBLE);
+		vcpu_put(vcpu);
+		schedule();
+		vcpu_load(vcpu);
+	}
+
+	__set_current_state(TASK_RUNNING);
+	remove_wait_queue(&vcpu->wq, &wait);
+}
+
+int kvm_emulate_halt(struct kvm_vcpu *vcpu)
+{
 	++vcpu->stat.halt_exits;
-	return 0;
+	if (irqchip_in_kernel(vcpu->kvm)) {
+		vcpu->mp_state = VCPU_MP_STATE_HALTED;
+		kvm_vcpu_block(vcpu);
+		if (vcpu->mp_state != VCPU_MP_STATE_RUNNABLE)
+			return -EINTR;
+		return 1;
+	} else {
+		vcpu->run->exit_reason = KVM_EXIT_HLT;
+		return 0;
+	}
 }
 EXPORT_SYMBOL_GPL(kvm_emulate_halt);
 
@@ -1323,7 +1366,7 @@ int kvm_hypercall(struct kvm_vcpu *vcpu, struct kvm_run *run)
 {
 	unsigned long nr, a0, a1, a2, a3, a4, a5, ret;
 
-	kvm_arch_ops->cache_regs(vcpu);
+	kvm_x86_ops->cache_regs(vcpu);
 	ret = -KVM_EINVAL;
 #ifdef CONFIG_X86_64
 	if (is_long_mode(vcpu)) {
@@ -1356,11 +1399,11 @@ int kvm_hypercall(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		run->hypercall.args[5] = a5;
 		run->hypercall.ret = ret;
 		run->hypercall.longmode = is_long_mode(vcpu);
-		kvm_arch_ops->decache_regs(vcpu);
+		kvm_x86_ops->decache_regs(vcpu);
 		return 0;
 	}
 	vcpu->regs[VCPU_REGS_RAX] = ret;
-	kvm_arch_ops->decache_regs(vcpu);
+	kvm_x86_ops->decache_regs(vcpu);
 	return 1;
 }
 EXPORT_SYMBOL_GPL(kvm_hypercall);
@@ -1374,26 +1417,26 @@ void realmode_lgdt(struct kvm_vcpu *vcpu, u16 limit, unsigned long base)
 {
 	struct descriptor_table dt = { limit, base };
 
-	kvm_arch_ops->set_gdt(vcpu, &dt);
+	kvm_x86_ops->set_gdt(vcpu, &dt);
 }
 
 void realmode_lidt(struct kvm_vcpu *vcpu, u16 limit, unsigned long base)
 {
 	struct descriptor_table dt = { limit, base };
 
-	kvm_arch_ops->set_idt(vcpu, &dt);
+	kvm_x86_ops->set_idt(vcpu, &dt);
 }
 
 void realmode_lmsw(struct kvm_vcpu *vcpu, unsigned long msw,
 		   unsigned long *rflags)
 {
 	lmsw(vcpu, msw);
-	*rflags = kvm_arch_ops->get_rflags(vcpu);
+	*rflags = kvm_x86_ops->get_rflags(vcpu);
 }
 
 unsigned long realmode_get_cr(struct kvm_vcpu *vcpu, int cr)
 {
-	kvm_arch_ops->decache_cr4_guest_bits(vcpu);
+	kvm_x86_ops->decache_cr4_guest_bits(vcpu);
 	switch (cr) {
 	case 0:
 		return vcpu->cr0;
@@ -1415,7 +1458,7 @@ void realmode_set_cr(struct kvm_vcpu *vcpu, int cr, unsigned long val,
 	switch (cr) {
 	case 0:
 		set_cr0(vcpu, mk_cr_64(vcpu->cr0, val));
-		*rflags = kvm_arch_ops->get_rflags(vcpu);
+		*rflags = kvm_x86_ops->get_rflags(vcpu);
 		break;
 	case 2:
 		vcpu->cr2 = val;
@@ -1489,7 +1532,7 @@ static int vcpu_register_para(struct kvm_vcpu *vcpu, gpa_t para_state_gpa)
 	mark_page_dirty(vcpu->kvm, hypercall_gpa >> PAGE_SHIFT);
 	hypercall = kmap_atomic(pfn_to_page(hypercall_hpa >> PAGE_SHIFT),
 				KM_USER1) + (hypercall_hpa & ~PAGE_MASK);
-	kvm_arch_ops->patch_hypercall(vcpu, hypercall);
+	kvm_x86_ops->patch_hypercall(vcpu, hypercall);
 	kunmap_atomic(hypercall, KM_USER1);
 
 	para_state->ret = 0;
@@ -1556,7 +1599,7 @@ EXPORT_SYMBOL_GPL(kvm_get_msr_common);
  */
 int kvm_get_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata)
 {
-	return kvm_arch_ops->get_msr(vcpu, msr_index, pdata);
+	return kvm_x86_ops->get_msr(vcpu, msr_index, pdata);
 }
 
 #ifdef CONFIG_X86_64
@@ -1577,7 +1620,7 @@ static void set_efer(struct kvm_vcpu *vcpu, u64 efer)
 		return;
 	}
 
-	kvm_arch_ops->set_efer(vcpu, efer);
+	kvm_x86_ops->set_efer(vcpu, efer);
 
 	efer &= ~EFER_LMA;
 	efer |= vcpu->shadow_efer & EFER_LMA;
@@ -1634,7 +1677,7 @@ EXPORT_SYMBOL_GPL(kvm_set_msr_common);
  */
 int kvm_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data)
 {
-	return kvm_arch_ops->set_msr(vcpu, msr_index, data);
+	return kvm_x86_ops->set_msr(vcpu, msr_index, data);
 }
 
 void kvm_resched(struct kvm_vcpu *vcpu)
@@ -1651,7 +1694,7 @@ void kvm_emulate_cpuid(struct kvm_vcpu *vcpu)
 	u32 function;
 	struct kvm_cpuid_entry *e, *best;
 
-	kvm_arch_ops->cache_regs(vcpu);
+	kvm_x86_ops->cache_regs(vcpu);
 	function = vcpu->regs[VCPU_REGS_RAX];
 	vcpu->regs[VCPU_REGS_RAX] = 0;
 	vcpu->regs[VCPU_REGS_RBX] = 0;
@@ -1677,8 +1720,8 @@ void kvm_emulate_cpuid(struct kvm_vcpu *vcpu)
 		vcpu->regs[VCPU_REGS_RCX] = best->ecx;
 		vcpu->regs[VCPU_REGS_RDX] = best->edx;
 	}
-	kvm_arch_ops->decache_regs(vcpu);
-	kvm_arch_ops->skip_emulated_instruction(vcpu);
+	kvm_x86_ops->decache_regs(vcpu);
+	kvm_x86_ops->skip_emulated_instruction(vcpu);
 }
 EXPORT_SYMBOL_GPL(kvm_emulate_cpuid);
 
@@ -1713,7 +1756,7 @@ static int complete_pio(struct kvm_vcpu *vcpu)
 	long delta;
 	int r;
 
-	kvm_arch_ops->cache_regs(vcpu);
+	kvm_x86_ops->cache_regs(vcpu);
 
 	if (!io->string) {
 		if (io->in)
@@ -1723,7 +1766,7 @@ static int complete_pio(struct kvm_vcpu *vcpu)
 		if (io->in) {
 			r = pio_copy_data(vcpu);
 			if (r) {
-				kvm_arch_ops->cache_regs(vcpu);
+				kvm_x86_ops->cache_regs(vcpu);
 				return r;
 			}
 		}
@@ -1746,13 +1789,11 @@ static int complete_pio(struct kvm_vcpu *vcpu)
 			vcpu->regs[VCPU_REGS_RSI] += delta;
 	}
 
-	kvm_arch_ops->decache_regs(vcpu);
+	kvm_x86_ops->decache_regs(vcpu);
 
 	io->count -= io->cur_count;
 	io->cur_count = 0;
 
-	if (!io->count)
-		kvm_arch_ops->skip_emulated_instruction(vcpu);
 	return 0;
 }
 
@@ -1762,6 +1803,7 @@ static void kernel_pio(struct kvm_io_device *pio_dev,
 {
 	/* TODO: String I/O for in kernel device */
 
+	mutex_lock(&vcpu->kvm->lock);
 	if (vcpu->pio.in)
 		kvm_iodevice_read(pio_dev, vcpu->pio.port,
 				  vcpu->pio.size,
@@ -1770,6 +1812,7 @@ static void kernel_pio(struct kvm_io_device *pio_dev,
 		kvm_iodevice_write(pio_dev, vcpu->pio.port,
 				   vcpu->pio.size,
 				   pd);
+	mutex_unlock(&vcpu->kvm->lock);
 }
 
 static void pio_string_write(struct kvm_io_device *pio_dev,
@@ -1779,12 +1822,14 @@ static void pio_string_write(struct kvm_io_device *pio_dev,
 	void *pd = vcpu->pio_data;
 	int i;
 
+	mutex_lock(&vcpu->kvm->lock);
 	for (i = 0; i < io->cur_count; i++) {
 		kvm_iodevice_write(pio_dev, io->port,
 				   io->size,
 				   pd);
 		pd += io->size;
 	}
+	mutex_unlock(&vcpu->kvm->lock);
 }
 
 int kvm_emulate_pio (struct kvm_vcpu *vcpu, struct kvm_run *run, int in,
@@ -1804,9 +1849,11 @@ int kvm_emulate_pio (struct kvm_vcpu *vcpu, struct kvm_run *run, int in,
 	vcpu->pio.guest_page_offset = 0;
 	vcpu->pio.rep = 0;
 
-	kvm_arch_ops->cache_regs(vcpu);
+	kvm_x86_ops->cache_regs(vcpu);
 	memcpy(vcpu->pio_data, &vcpu->regs[VCPU_REGS_RAX], 4);
-	kvm_arch_ops->decache_regs(vcpu);
+	kvm_x86_ops->decache_regs(vcpu);
+
+	kvm_x86_ops->skip_emulated_instruction(vcpu);
 
 	pio_dev = vcpu_find_pio_dev(vcpu, port);
 	if (pio_dev) {
@@ -1841,7 +1888,7 @@ int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, struct kvm_run *run, int in,
 	vcpu->pio.rep = rep;
 
 	if (!count) {
-		kvm_arch_ops->skip_emulated_instruction(vcpu);
+		kvm_x86_ops->skip_emulated_instruction(vcpu);
 		return 1;
 	}
 
@@ -1870,6 +1917,9 @@ int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, struct kvm_run *run, int in,
 	vcpu->run->io.count = now;
 	vcpu->pio.cur_count = now;
 
+	if (vcpu->pio.cur_count == vcpu->pio.count)
+		kvm_x86_ops->skip_emulated_instruction(vcpu);
+
 	for (i = 0; i < nr_pages; ++i) {
 		mutex_lock(&vcpu->kvm->lock);
 		page = gva_to_page(vcpu, address + i * PAGE_SIZE);
@@ -1903,6 +1953,138 @@ int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, struct kvm_run *run, int in,
 }
 EXPORT_SYMBOL_GPL(kvm_emulate_pio_string);
 
+/*
+ * Check if userspace requested an interrupt window, and that the
+ * interrupt window is open.
+ *
+ * No need to exit to userspace if we already have an interrupt queued.
+ */
+static int dm_request_for_irq_injection(struct kvm_vcpu *vcpu,
+					  struct kvm_run *kvm_run)
+{
+	return (!vcpu->irq_summary &&
+		kvm_run->request_interrupt_window &&
+		vcpu->interrupt_window_open &&
+		(kvm_x86_ops->get_rflags(vcpu) & X86_EFLAGS_IF));
+}
+
+static void post_kvm_run_save(struct kvm_vcpu *vcpu,
+			      struct kvm_run *kvm_run)
+{
+	kvm_run->if_flag = (kvm_x86_ops->get_rflags(vcpu) & X86_EFLAGS_IF) != 0;
+	kvm_run->cr8 = get_cr8(vcpu);
+	kvm_run->apic_base = kvm_get_apic_base(vcpu);
+	if (irqchip_in_kernel(vcpu->kvm))
+		kvm_run->ready_for_interrupt_injection = 1;
+	else
+		kvm_run->ready_for_interrupt_injection =
+					(vcpu->interrupt_window_open &&
+					 vcpu->irq_summary == 0);
+}
+
+static int __vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+{
+	int r;
+
+	if (unlikely(vcpu->mp_state == VCPU_MP_STATE_SIPI_RECEIVED)) {
+		printk("vcpu %d received sipi with vector # %x\n",
+		       vcpu->vcpu_id, vcpu->sipi_vector);
+		kvm_lapic_reset(vcpu);
+		kvm_x86_ops->vcpu_reset(vcpu);
+		vcpu->mp_state = VCPU_MP_STATE_RUNNABLE;
+	}
+
+preempted:
+	if (vcpu->guest_debug.enabled)
+		kvm_x86_ops->guest_debug_pre(vcpu);
+
+again:
+	r = kvm_mmu_reload(vcpu);
+	if (unlikely(r))
+		goto out;
+
+	preempt_disable();
+
+	kvm_x86_ops->prepare_guest_switch(vcpu);
+	kvm_load_guest_fpu(vcpu);
+
+	local_irq_disable();
+
+	if (signal_pending(current)) {
+		local_irq_enable();
+		preempt_enable();
+		r = -EINTR;
+		kvm_run->exit_reason = KVM_EXIT_INTR;
+		++vcpu->stat.signal_exits;
+		goto out;
+	}
+
+	if (irqchip_in_kernel(vcpu->kvm))
+		kvm_x86_ops->inject_pending_irq(vcpu);
+	else if (!vcpu->mmio_read_completed)
+		kvm_x86_ops->inject_pending_vectors(vcpu, kvm_run);
+
+	vcpu->guest_mode = 1;
+	kvm_guest_enter();
+
+	if (vcpu->requests)
+		if (test_and_clear_bit(KVM_TLB_FLUSH, &vcpu->requests))
+			kvm_x86_ops->tlb_flush(vcpu);
+
+	kvm_x86_ops->run(vcpu, kvm_run);
+
+	vcpu->guest_mode = 0;
+	local_irq_enable();
+
+	++vcpu->stat.exits;
+
+	/*
+	 * We must have an instruction between local_irq_enable() and
+	 * kvm_guest_exit(), so the timer interrupt isn't delayed by
+	 * the interrupt shadow.  The stat.exits increment will do nicely.
+	 * But we need to prevent reordering, hence this barrier():
+	 */
+	barrier();
+
+	kvm_guest_exit();
+
+	preempt_enable();
+
+	/*
+	 * Profile KVM exit RIPs:
+	 */
+	if (unlikely(prof_on == KVM_PROFILING)) {
+		kvm_x86_ops->cache_regs(vcpu);
+		profile_hit(KVM_PROFILING, (void *)vcpu->rip);
+	}
+
+	r = kvm_x86_ops->handle_exit(kvm_run, vcpu);
+
+	if (r > 0) {
+		if (dm_request_for_irq_injection(vcpu, kvm_run)) {
+			r = -EINTR;
+			kvm_run->exit_reason = KVM_EXIT_INTR;
+			++vcpu->stat.request_irq_exits;
+			goto out;
+		}
+		if (!need_resched()) {
+			++vcpu->stat.light_exits;
+			goto again;
+		}
+	}
+
+out:
+	if (r > 0) {
+		kvm_resched(vcpu);
+		goto preempted;
+	}
+
+	post_kvm_run_save(vcpu, kvm_run);
+
+	return r;
+}
+
+
 static int kvm_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 {
 	int r;
@@ -1910,11 +2092,18 @@ static int kvm_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 
 	vcpu_load(vcpu);
 
+	if (unlikely(vcpu->mp_state == VCPU_MP_STATE_UNINITIALIZED)) {
+		kvm_vcpu_block(vcpu);
+		vcpu_put(vcpu);
+		return -EAGAIN;
+	}
+
 	if (vcpu->sigset_active)
 		sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved);
 
 	/* re-sync apic's tpr */
-	set_cr8(vcpu, kvm_run->cr8);
+	if (!irqchip_in_kernel(vcpu->kvm))
+		set_cr8(vcpu, kvm_run->cr8);
 
 	if (vcpu->pio.cur_count) {
 		r = complete_pio(vcpu);
@@ -1938,12 +2127,12 @@ static int kvm_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	}
 
 	if (kvm_run->exit_reason == KVM_EXIT_HYPERCALL) {
-		kvm_arch_ops->cache_regs(vcpu);
+		kvm_x86_ops->cache_regs(vcpu);
 		vcpu->regs[VCPU_REGS_RAX] = kvm_run->hypercall.ret;
-		kvm_arch_ops->decache_regs(vcpu);
+		kvm_x86_ops->decache_regs(vcpu);
 	}
 
-	r = kvm_arch_ops->run(vcpu, kvm_run);
+	r = __vcpu_run(vcpu, kvm_run);
 
 out:
 	if (vcpu->sigset_active)
@@ -1958,7 +2147,7 @@ static int kvm_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu,
 {
 	vcpu_load(vcpu);
 
-	kvm_arch_ops->cache_regs(vcpu);
+	kvm_x86_ops->cache_regs(vcpu);
 
 	regs->rax = vcpu->regs[VCPU_REGS_RAX];
 	regs->rbx = vcpu->regs[VCPU_REGS_RBX];
@@ -1980,7 +2169,7 @@ static int kvm_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu,
 #endif
 
 	regs->rip = vcpu->rip;
-	regs->rflags = kvm_arch_ops->get_rflags(vcpu);
+	regs->rflags = kvm_x86_ops->get_rflags(vcpu);
 
 	/*
 	 * Don't leak debug flags in case they were set for guest debugging
@@ -2018,9 +2207,9 @@ static int kvm_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu,
 #endif
 
 	vcpu->rip = regs->rip;
-	kvm_arch_ops->set_rflags(vcpu, regs->rflags);
+	kvm_x86_ops->set_rflags(vcpu, regs->rflags);
 
-	kvm_arch_ops->decache_regs(vcpu);
+	kvm_x86_ops->decache_regs(vcpu);
 
 	vcpu_put(vcpu);
 
@@ -2030,13 +2219,14 @@ static int kvm_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu,
 static void get_segment(struct kvm_vcpu *vcpu,
 			struct kvm_segment *var, int seg)
 {
-	return kvm_arch_ops->get_segment(vcpu, var, seg);
+	return kvm_x86_ops->get_segment(vcpu, var, seg);
 }
 
 static int kvm_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
 				    struct kvm_sregs *sregs)
 {
 	struct descriptor_table dt;
+	int pending_vec;
 
 	vcpu_load(vcpu);
 
@@ -2050,14 +2240,14 @@ static int kvm_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
 	get_segment(vcpu, &sregs->tr, VCPU_SREG_TR);
 	get_segment(vcpu, &sregs->ldt, VCPU_SREG_LDTR);
 
-	kvm_arch_ops->get_idt(vcpu, &dt);
+	kvm_x86_ops->get_idt(vcpu, &dt);
 	sregs->idt.limit = dt.limit;
 	sregs->idt.base = dt.base;
-	kvm_arch_ops->get_gdt(vcpu, &dt);
+	kvm_x86_ops->get_gdt(vcpu, &dt);
 	sregs->gdt.limit = dt.limit;
 	sregs->gdt.base = dt.base;
 
-	kvm_arch_ops->decache_cr4_guest_bits(vcpu);
+	kvm_x86_ops->decache_cr4_guest_bits(vcpu);
 	sregs->cr0 = vcpu->cr0;
 	sregs->cr2 = vcpu->cr2;
 	sregs->cr3 = vcpu->cr3;
@@ -2066,8 +2256,15 @@ static int kvm_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
 	sregs->efer = vcpu->shadow_efer;
 	sregs->apic_base = kvm_get_apic_base(vcpu);
 
-	memcpy(sregs->interrupt_bitmap, vcpu->irq_pending,
-	       sizeof sregs->interrupt_bitmap);
+	if (irqchip_in_kernel(vcpu->kvm)) {
+		memset(sregs->interrupt_bitmap, 0,
+		       sizeof sregs->interrupt_bitmap);
+		pending_vec = kvm_x86_ops->get_irq(vcpu);
+		if (pending_vec >= 0)
+			set_bit(pending_vec, (unsigned long *)sregs->interrupt_bitmap);
+	} else
+		memcpy(sregs->interrupt_bitmap, vcpu->irq_pending,
+		       sizeof sregs->interrupt_bitmap);
 
 	vcpu_put(vcpu);
 
@@ -2077,24 +2274,24 @@ static int kvm_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
 static void set_segment(struct kvm_vcpu *vcpu,
 			struct kvm_segment *var, int seg)
 {
-	return kvm_arch_ops->set_segment(vcpu, var, seg);
+	return kvm_x86_ops->set_segment(vcpu, var, seg);
 }
 
 static int kvm_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
 				    struct kvm_sregs *sregs)
 {
 	int mmu_reset_needed = 0;
-	int i;
+	int i, pending_vec, max_bits;
 	struct descriptor_table dt;
 
 	vcpu_load(vcpu);
 
 	dt.limit = sregs->idt.limit;
 	dt.base = sregs->idt.base;
-	kvm_arch_ops->set_idt(vcpu, &dt);
+	kvm_x86_ops->set_idt(vcpu, &dt);
 	dt.limit = sregs->gdt.limit;
 	dt.base = sregs->gdt.base;
-	kvm_arch_ops->set_gdt(vcpu, &dt);
+	kvm_x86_ops->set_gdt(vcpu, &dt);
 
 	vcpu->cr2 = sregs->cr2;
 	mmu_reset_needed |= vcpu->cr3 != sregs->cr3;
@@ -2104,29 +2301,42 @@ static int kvm_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
 
 	mmu_reset_needed |= vcpu->shadow_efer != sregs->efer;
 #ifdef CONFIG_X86_64
-	kvm_arch_ops->set_efer(vcpu, sregs->efer);
+	kvm_x86_ops->set_efer(vcpu, sregs->efer);
 #endif
 	kvm_set_apic_base(vcpu, sregs->apic_base);
 
-	kvm_arch_ops->decache_cr4_guest_bits(vcpu);
+	kvm_x86_ops->decache_cr4_guest_bits(vcpu);
 
 	mmu_reset_needed |= vcpu->cr0 != sregs->cr0;
-	kvm_arch_ops->set_cr0(vcpu, sregs->cr0);
+	vcpu->cr0 = sregs->cr0;
+	kvm_x86_ops->set_cr0(vcpu, sregs->cr0);
 
 	mmu_reset_needed |= vcpu->cr4 != sregs->cr4;
-	kvm_arch_ops->set_cr4(vcpu, sregs->cr4);
+	kvm_x86_ops->set_cr4(vcpu, sregs->cr4);
 	if (!is_long_mode(vcpu) && is_pae(vcpu))
 		load_pdptrs(vcpu, vcpu->cr3);
 
 	if (mmu_reset_needed)
 		kvm_mmu_reset_context(vcpu);
 
-	memcpy(vcpu->irq_pending, sregs->interrupt_bitmap,
-	       sizeof vcpu->irq_pending);
-	vcpu->irq_summary = 0;
-	for (i = 0; i < ARRAY_SIZE(vcpu->irq_pending); ++i)
-		if (vcpu->irq_pending[i])
-			__set_bit(i, &vcpu->irq_summary);
+	if (!irqchip_in_kernel(vcpu->kvm)) {
+		memcpy(vcpu->irq_pending, sregs->interrupt_bitmap,
+		       sizeof vcpu->irq_pending);
+		vcpu->irq_summary = 0;
+		for (i = 0; i < ARRAY_SIZE(vcpu->irq_pending); ++i)
+			if (vcpu->irq_pending[i])
+				__set_bit(i, &vcpu->irq_summary);
+	} else {
+		max_bits = (sizeof sregs->interrupt_bitmap) << 3;
+		pending_vec = find_first_bit(
+			(const unsigned long *)sregs->interrupt_bitmap,
+			max_bits);
+		/* Only pending external irq is handled here */
+		if (pending_vec < max_bits) {
+			kvm_x86_ops->set_irq(vcpu, pending_vec);
+			printk("Set back pending irq %d\n", pending_vec);
+		}
+	}
 
 	set_segment(vcpu, &sregs->cs, VCPU_SREG_CS);
 	set_segment(vcpu, &sregs->ds, VCPU_SREG_DS);
@@ -2143,6 +2353,16 @@ static int kvm_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
 	return 0;
 }
 
+void kvm_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l)
+{
+	struct kvm_segment cs;
+
+	get_segment(vcpu, &cs, VCPU_SREG_CS);
+	*db = cs.db;
+	*l = cs.l;
+}
+EXPORT_SYMBOL_GPL(kvm_get_cs_db_l_bits);
+
 /*
  * List of msr numbers which we expose to userspace through KVM_GET_MSRS
  * and KVM_SET_MSRS, and KVM_GET_MSR_INDEX_LIST.
@@ -2306,7 +2526,7 @@ static int kvm_vcpu_ioctl_debug_guest(struct kvm_vcpu *vcpu,
 
 	vcpu_load(vcpu);
 
-	r = kvm_arch_ops->set_guest_debug(vcpu, dbg);
+	r = kvm_x86_ops->set_guest_debug(vcpu, dbg);
 
 	vcpu_put(vcpu);
 
@@ -2388,7 +2608,7 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, int n)
 	if (!valid_vcpu(n))
 		return -EINVAL;
 
-	vcpu = kvm_arch_ops->vcpu_create(kvm, n);
+	vcpu = kvm_x86_ops->vcpu_create(kvm, n);
 	if (IS_ERR(vcpu))
 		return PTR_ERR(vcpu);
 
@@ -2429,7 +2649,7 @@ mmu_unload:
 	vcpu_put(vcpu);
 
 free_vcpu:
-	kvm_arch_ops->vcpu_free(vcpu);
+	kvm_x86_ops->vcpu_free(vcpu);
 	return r;
 }
 
@@ -2547,6 +2767,27 @@ static int kvm_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
 	return 0;
 }
 
+static int kvm_vcpu_ioctl_get_lapic(struct kvm_vcpu *vcpu,
+				    struct kvm_lapic_state *s)
+{
+	vcpu_load(vcpu);
+	memcpy(s->regs, vcpu->apic->regs, sizeof *s);
+	vcpu_put(vcpu);
+
+	return 0;
+}
+
+static int kvm_vcpu_ioctl_set_lapic(struct kvm_vcpu *vcpu,
+				    struct kvm_lapic_state *s)
+{
+	vcpu_load(vcpu);
+	memcpy(vcpu->apic->regs, s->regs, sizeof *s);
+	kvm_apic_post_state_restore(vcpu);
+	vcpu_put(vcpu);
+
+	return 0;
+}
+
 static long kvm_vcpu_ioctl(struct file *filp,
 			   unsigned int ioctl, unsigned long arg)
 {
@@ -2716,6 +2957,31 @@ static long kvm_vcpu_ioctl(struct file *filp,
 		r = 0;
 		break;
 	}
+	case KVM_GET_LAPIC: {
+		struct kvm_lapic_state lapic;
+
+		memset(&lapic, 0, sizeof lapic);
+		r = kvm_vcpu_ioctl_get_lapic(vcpu, &lapic);
+		if (r)
+			goto out;
+		r = -EFAULT;
+		if (copy_to_user(argp, &lapic, sizeof lapic))
+			goto out;
+		r = 0;
+		break;
+	}
+	case KVM_SET_LAPIC: {
+		struct kvm_lapic_state lapic;
+
+		r = -EFAULT;
+		if (copy_from_user(&lapic, argp, sizeof lapic))
+			goto out;
+		r = kvm_vcpu_ioctl_set_lapic(vcpu, &lapic);;
+		if (r)
+			goto out;
+		r = 0;
+		break;
+	}
 	default:
 		;
 	}
@@ -2790,6 +3056,7 @@ static long kvm_vm_ioctl(struct file *filp,
 		if (copy_from_user(&irq_event, argp, sizeof irq_event))
 			goto out;
 		if (irqchip_in_kernel(kvm)) {
+			mutex_lock(&kvm->lock);
 			if (irq_event.irq < 16)
 				kvm_pic_set_irq(pic_irqchip(kvm),
 					irq_event.irq,
@@ -2797,10 +3064,46 @@ static long kvm_vm_ioctl(struct file *filp,
 			kvm_ioapic_set_irq(kvm->vioapic,
 					irq_event.irq,
 					irq_event.level);
+			mutex_unlock(&kvm->lock);
 			r = 0;
 		}
 		break;
 	}
+	case KVM_GET_IRQCHIP: {
+		/* 0: PIC master, 1: PIC slave, 2: IOAPIC */
+		struct kvm_irqchip chip;
+
+		r = -EFAULT;
+		if (copy_from_user(&chip, argp, sizeof chip))
+			goto out;
+		r = -ENXIO;
+		if (!irqchip_in_kernel(kvm))
+			goto out;
+		r = kvm_vm_ioctl_get_irqchip(kvm, &chip);
+		if (r)
+			goto out;
+		r = -EFAULT;
+		if (copy_to_user(argp, &chip, sizeof chip))
+			goto out;
+		r = 0;
+		break;
+	}
+	case KVM_SET_IRQCHIP: {
+		/* 0: PIC master, 1: PIC slave, 2: IOAPIC */
+		struct kvm_irqchip chip;
+
+		r = -EFAULT;
+		if (copy_from_user(&chip, argp, sizeof chip))
+			goto out;
+		r = -ENXIO;
+		if (!irqchip_in_kernel(kvm))
+			goto out;
+		r = kvm_vm_ioctl_set_irqchip(kvm, &chip);
+		if (r)
+			goto out;
+		r = 0;
+		break;
+	}
 	default:
 		;
 	}
@@ -2916,6 +3219,7 @@ static long kvm_dev_ioctl(struct file *filp,
 
 		switch (ext) {
 		case KVM_CAP_IRQCHIP:
+		case KVM_CAP_HLT:
 			r = 1;
 			break;
 		default:
@@ -2974,7 +3278,7 @@ static void decache_vcpus_on_cpu(int cpu)
 			 */
 			if (mutex_trylock(&vcpu->mutex)) {
 				if (vcpu->cpu == cpu) {
-					kvm_arch_ops->vcpu_decache(vcpu);
+					kvm_x86_ops->vcpu_decache(vcpu);
 					vcpu->cpu = -1;
 				}
 				mutex_unlock(&vcpu->mutex);
@@ -2990,7 +3294,7 @@ static void hardware_enable(void *junk)
 	if (cpu_isset(cpu, cpus_hardware_enabled))
 		return;
 	cpu_set(cpu, cpus_hardware_enabled);
-	kvm_arch_ops->hardware_enable(NULL);
+	kvm_x86_ops->hardware_enable(NULL);
 }
 
 static void hardware_disable(void *junk)
@@ -3001,7 +3305,7 @@ static void hardware_disable(void *junk)
 		return;
 	cpu_clear(cpu, cpus_hardware_enabled);
 	decache_vcpus_on_cpu(cpu);
-	kvm_arch_ops->hardware_disable(NULL);
+	kvm_x86_ops->hardware_disable(NULL);
 }
 
 static int kvm_cpu_hotplug(struct notifier_block *notifier, unsigned long val,
@@ -3147,7 +3451,7 @@ static int kvm_resume(struct sys_device *dev)
 }
 
 static struct sysdev_class kvm_sysdev_class = {
-	set_kset_name("kvm"),
+	.name = "kvm",
 	.suspend = kvm_suspend,
 	.resume = kvm_resume,
 };
@@ -3169,7 +3473,7 @@ static void kvm_sched_in(struct preempt_notifier *pn, int cpu)
 {
 	struct kvm_vcpu *vcpu = preempt_notifier_to_vcpu(pn);
 
-	kvm_arch_ops->vcpu_load(vcpu, cpu);
+	kvm_x86_ops->vcpu_load(vcpu, cpu);
 }
 
 static void kvm_sched_out(struct preempt_notifier *pn,
@@ -3177,16 +3481,16 @@ static void kvm_sched_out(struct preempt_notifier *pn,
 {
 	struct kvm_vcpu *vcpu = preempt_notifier_to_vcpu(pn);
 
-	kvm_arch_ops->vcpu_put(vcpu);
+	kvm_x86_ops->vcpu_put(vcpu);
 }
 
-int kvm_init_arch(struct kvm_arch_ops *ops, unsigned int vcpu_size,
+int kvm_init_x86(struct kvm_x86_ops *ops, unsigned int vcpu_size,
 		  struct module *module)
 {
 	int r;
 	int cpu;
 
-	if (kvm_arch_ops) {
+	if (kvm_x86_ops) {
 		printk(KERN_ERR "kvm: already loaded the other module\n");
 		return -EEXIST;
 	}
@@ -3200,15 +3504,15 @@ int kvm_init_arch(struct kvm_arch_ops *ops, unsigned int vcpu_size,
 		return -EOPNOTSUPP;
 	}
 
-	kvm_arch_ops = ops;
+	kvm_x86_ops = ops;
 
-	r = kvm_arch_ops->hardware_setup();
+	r = kvm_x86_ops->hardware_setup();
 	if (r < 0)
 		goto out;
 
 	for_each_online_cpu(cpu) {
 		smp_call_function_single(cpu,
-				kvm_arch_ops->check_processor_compatibility,
+				kvm_x86_ops->check_processor_compatibility,
 				&r, 0, 1);
 		if (r < 0)
 			goto out_free_0;
@@ -3261,13 +3565,13 @@ out_free_2:
 out_free_1:
 	on_each_cpu(hardware_disable, NULL, 0, 1);
 out_free_0:
-	kvm_arch_ops->hardware_unsetup();
+	kvm_x86_ops->hardware_unsetup();
 out:
-	kvm_arch_ops = NULL;
+	kvm_x86_ops = NULL;
 	return r;
 }
 
-void kvm_exit_arch(void)
+void kvm_exit_x86(void)
 {
 	misc_deregister(&kvm_dev);
 	kmem_cache_destroy(kvm_vcpu_cache);
@@ -3276,8 +3580,8 @@ void kvm_exit_arch(void)
 	unregister_reboot_notifier(&kvm_reboot_notifier);
 	unregister_cpu_notifier(&kvm_cpu_notifier);
 	on_each_cpu(hardware_disable, NULL, 0, 1);
-	kvm_arch_ops->hardware_unsetup();
-	kvm_arch_ops = NULL;
+	kvm_x86_ops->hardware_unsetup();
+	kvm_x86_ops = NULL;
 }
 
 static __init int kvm_init(void)
@@ -3320,5 +3624,5 @@ static __exit void kvm_exit(void)
 module_init(kvm_init)
 module_exit(kvm_exit)
 
-EXPORT_SYMBOL_GPL(kvm_init_arch);
-EXPORT_SYMBOL_GPL(kvm_exit_arch);
+EXPORT_SYMBOL_GPL(kvm_init_x86);
+EXPORT_SYMBOL_GPL(kvm_exit_x86);