X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=arch%2Fx86%2Fkvm%2Fx86.c;h=b5ac1b72245469e45ce7b6ad37579fce25e2e9e3;hb=c2d0ee46e6e633a3c23ecbcb9b03ad731906cd79;hp=6fbc346033752132dccd2a5227c150078bc60bb4;hpb=269e05e48502f1cc06802e9fba90f5100dd6bb0d;p=safe%2Fjmp%2Flinux-2.6

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 6fbc346..b5ac1b7 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -36,6 +36,7 @@
 #include <linux/highmem.h>
 #include <linux/iommu.h>
 #include <linux/intel-iommu.h>
+#include <linux/cpufreq.h>
 
 #include <asm/uaccess.h>
 #include <asm/msr.h>
@@ -107,7 +108,6 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 	{ "mmu_recycled", VM_STAT(mmu_recycled) },
 	{ "mmu_cache_miss", VM_STAT(mmu_cache_miss) },
 	{ "mmu_unsync", VM_STAT(mmu_unsync) },
-	{ "mmu_unsync_global", VM_STAT(mmu_unsync_global) },
 	{ "remote_tlb_flush", VM_STAT(remote_tlb_flush) },
 	{ "largepages", VM_STAT(lpages) },
 	{ NULL }
@@ -233,7 +233,8 @@ int load_pdptrs(struct kvm_vcpu *vcpu, unsigned long cr3)
 		goto out;
 	}
 	for (i = 0; i < ARRAY_SIZE(pdpte); ++i) {
-		if ((pdpte[i] & 1) && (pdpte[i] & 0xfffffff0000001e6ull)) {
+		if (is_present_pte(pdpte[i]) &&
+		    (pdpte[i] & vcpu->arch.mmu.rsvd_bits_mask[0][2])) {
 			ret = 0;
 			goto out;
 		}
@@ -320,7 +321,6 @@ void kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
 	kvm_x86_ops->set_cr0(vcpu, cr0);
 	vcpu->arch.cr0 = cr0;
 
-	kvm_mmu_sync_global(vcpu);
 	kvm_mmu_reset_context(vcpu);
 	return;
 }
@@ -337,6 +337,9 @@ EXPORT_SYMBOL_GPL(kvm_lmsw);
 
 void kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 {
+	unsigned long old_cr4 = vcpu->arch.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);
@@ -350,7 +353,8 @@ void kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 			kvm_inject_gp(vcpu, 0);
 			return;
 		}
-	} else if (is_paging(vcpu) && !is_pae(vcpu) && (cr4 & X86_CR4_PAE)
+	} 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);
@@ -364,8 +368,7 @@ void kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 	}
 	kvm_x86_ops->set_cr4(vcpu, cr4);
 	vcpu->arch.cr4 = cr4;
-	vcpu->arch.mmu.base_role.cr4_pge = !!(cr4 & X86_CR4_PGE);
-	kvm_mmu_sync_global(vcpu);
+	vcpu->arch.mmu.base_role.cr4_pge = (cr4 & X86_CR4_PGE) && !tdp_enabled;
 	kvm_mmu_reset_context(vcpu);
 }
 EXPORT_SYMBOL_GPL(kvm_set_cr4);
@@ -490,6 +493,17 @@ static void set_efer(struct kvm_vcpu *vcpu, u64 efer)
 		return;
 	}
 
+	if (efer & EFER_FFXSR) {
+		struct kvm_cpuid_entry2 *feat;
+
+		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;
+		}
+	}
+
 	if (efer & EFER_SVME) {
 		struct kvm_cpuid_entry2 *feat;
 
@@ -507,6 +521,9 @@ static void set_efer(struct kvm_vcpu *vcpu, u64 efer)
 	efer |= vcpu->arch.shadow_efer & EFER_LMA;
 
 	vcpu->arch.shadow_efer = efer;
+
+	vcpu->arch.mmu.base_role.nxe = (efer & EFER_NX) && !tdp_enabled;
+	kvm_mmu_reset_context(vcpu);
 }
 
 void kvm_enable_efer_bits(u64 mask)
@@ -606,6 +623,8 @@ static void kvm_set_time_scale(uint32_t tsc_khz, struct pvclock_vcpu_time_info *
 		 hv_clock->tsc_to_system_mul);
 }
 
+static DEFINE_PER_CPU(unsigned long, cpu_tsc_khz);
+
 static void kvm_write_guest_time(struct kvm_vcpu *v)
 {
 	struct timespec ts;
@@ -616,10 +635,12 @@ static void kvm_write_guest_time(struct kvm_vcpu *v)
 	if ((!vcpu->time_page))
 		return;
 
-	if (unlikely(vcpu->hv_clock_tsc_khz != tsc_khz)) {
-		kvm_set_time_scale(tsc_khz, &vcpu->hv_clock);
-		vcpu->hv_clock_tsc_khz = tsc_khz;
+	preempt_disable();
+	if (unlikely(vcpu->hv_clock_tsc_khz != __get_cpu_var(cpu_tsc_khz))) {
+		kvm_set_time_scale(__get_cpu_var(cpu_tsc_khz), &vcpu->hv_clock);
+		vcpu->hv_clock_tsc_khz = __get_cpu_var(cpu_tsc_khz);
 	}
+	preempt_enable();
 
 	/* Keep irq disabled to prevent changes to the clock */
 	local_irq_save(flags);
@@ -649,6 +670,16 @@ static void kvm_write_guest_time(struct kvm_vcpu *v)
 	mark_page_dirty(v->kvm, vcpu->time >> PAGE_SHIFT);
 }
 
+static int kvm_request_guest_time_update(struct kvm_vcpu *v)
+{
+	struct kvm_vcpu_arch *vcpu = &v->arch;
+
+	if (!vcpu->time_page)
+		return 0;
+	set_bit(KVM_REQ_KVMCLOCK_UPDATE, &v->requests);
+	return 1;
+}
+
 static bool msr_mtrr_valid(unsigned msr)
 {
 	switch (msr) {
@@ -779,7 +810,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 			vcpu->arch.time_page = NULL;
 		}
 
-		kvm_write_guest_time(vcpu);
+		kvm_request_guest_time_update(vcpu);
 		break;
 	}
 	default:
@@ -865,6 +896,8 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
 	case MSR_IA32_LASTINTFROMIP:
 	case MSR_IA32_LASTINTTOIP:
 	case MSR_VM_HSAVE_PA:
+	case MSR_P6_EVNTSEL0:
+	case MSR_P6_EVNTSEL1:
 		data = 0;
 		break;
 	case MSR_MTRRcap:
@@ -989,11 +1022,14 @@ int kvm_dev_ioctl_check_extension(long ext)
 	case KVM_CAP_MMU_SHADOW_CACHE_CONTROL:
 	case KVM_CAP_SET_TSS_ADDR:
 	case KVM_CAP_EXT_CPUID:
+	case KVM_CAP_CLOCKSOURCE:
 	case KVM_CAP_PIT:
 	case KVM_CAP_NOP_IO_DELAY:
 	case KVM_CAP_MP_STATE:
 	case KVM_CAP_SYNC_MMU:
 	case KVM_CAP_REINJECT_CONTROL:
+	case KVM_CAP_IRQ_INJECT_STATUS:
+	case KVM_CAP_ASSIGN_DEV_IRQ:
 		r = 1;
 		break;
 	case KVM_CAP_COALESCED_MMIO:
@@ -1014,9 +1050,6 @@ int kvm_dev_ioctl_check_extension(long ext)
 	case KVM_CAP_IOMMU:
 		r = iommu_found();
 		break;
-	case KVM_CAP_CLOCKSOURCE:
-		r = boot_cpu_has(X86_FEATURE_CONSTANT_TSC);
-		break;
 	default:
 		r = 0;
 		break;
@@ -1067,7 +1100,7 @@ long kvm_arch_dev_ioctl(struct file *filp,
 		if (copy_from_user(&cpuid, cpuid_arg, sizeof cpuid))
 			goto out;
 		r = kvm_dev_ioctl_get_supported_cpuid(&cpuid,
-			cpuid_arg->entries);
+						      cpuid_arg->entries);
 		if (r)
 			goto out;
 
@@ -1087,7 +1120,7 @@ out:
 void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
 	kvm_x86_ops->vcpu_load(vcpu, cpu);
-	kvm_write_guest_time(vcpu);
+	kvm_request_guest_time_update(vcpu);
 }
 
 void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
@@ -1098,9 +1131,9 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 
 static int is_efer_nx(void)
 {
-	u64 efer;
+	unsigned long long efer = 0;
 
-	rdmsrl(MSR_EFER, efer);
+	rdmsrl_safe(MSR_EFER, &efer);
 	return efer & EFER_NX;
 }
 
@@ -1165,8 +1198,8 @@ out:
 }
 
 static int kvm_vcpu_ioctl_set_cpuid2(struct kvm_vcpu *vcpu,
-				    struct kvm_cpuid2 *cpuid,
-				    struct kvm_cpuid_entry2 __user *entries)
+				     struct kvm_cpuid2 *cpuid,
+				     struct kvm_cpuid_entry2 __user *entries)
 {
 	int r;
 
@@ -1185,8 +1218,8 @@ out:
 }
 
 static int kvm_vcpu_ioctl_get_cpuid2(struct kvm_vcpu *vcpu,
-				    struct kvm_cpuid2 *cpuid,
-				    struct kvm_cpuid_entry2 __user *entries)
+				     struct kvm_cpuid2 *cpuid,
+				     struct kvm_cpuid_entry2 __user *entries)
 {
 	int r;
 
@@ -1195,7 +1228,7 @@ static int kvm_vcpu_ioctl_get_cpuid2(struct kvm_vcpu *vcpu,
 		goto out;
 	r = -EFAULT;
 	if (copy_to_user(entries, &vcpu->arch.cpuid_entries,
-			   vcpu->arch.cpuid_nent * sizeof(struct kvm_cpuid_entry2)))
+			 vcpu->arch.cpuid_nent * sizeof(struct kvm_cpuid_entry2)))
 		goto out;
 	return 0;
 
@@ -1205,12 +1238,12 @@ out:
 }
 
 static void do_cpuid_1_ent(struct kvm_cpuid_entry2 *entry, u32 function,
-			  u32 index)
+			   u32 index)
 {
 	entry->function = function;
 	entry->index = index;
 	cpuid_count(entry->function, entry->index,
-		&entry->eax, &entry->ebx, &entry->ecx, &entry->edx);
+		    &entry->eax, &entry->ebx, &entry->ecx, &entry->edx);
 	entry->flags = 0;
 }
 
@@ -1236,10 +1269,11 @@ static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 		bit(X86_FEATURE_CMOV) | bit(X86_FEATURE_PSE36) |
 		bit(X86_FEATURE_MMX) | bit(X86_FEATURE_FXSR) |
 		bit(X86_FEATURE_SYSCALL) |
-		(bit(X86_FEATURE_NX) && is_efer_nx()) |
+		(is_efer_nx() ? bit(X86_FEATURE_NX) : 0) |
 #ifdef CONFIG_X86_64
 		bit(X86_FEATURE_LM) |
 #endif
+		bit(X86_FEATURE_FXSR_OPT) |
 		bit(X86_FEATURE_MMXEXT) |
 		bit(X86_FEATURE_3DNOWEXT) |
 		bit(X86_FEATURE_3DNOW);
@@ -1249,7 +1283,7 @@ static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 		bit(X86_FEATURE_LAHF_LM) | bit(X86_FEATURE_CMP_LEGACY) |
 		bit(X86_FEATURE_SVM);
 
-	/* all func 2 cpuid_count() should be called on the same cpu */
+	/* all calls to cpuid_count() should be made on the same cpu */
 	get_cpu();
 	do_cpuid_1_ent(entry, function, index);
 	++*nent;
@@ -1323,7 +1357,7 @@ static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 }
 
 static int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid,
-				    struct kvm_cpuid_entry2 __user *entries)
+				     struct kvm_cpuid_entry2 __user *entries)
 {
 	struct kvm_cpuid_entry2 *cpuid_entries;
 	int limit, nent = 0, r = -E2BIG;
@@ -1340,7 +1374,7 @@ static int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid,
 	limit = cpuid_entries[0].eax;
 	for (func = 1; func <= limit && nent < cpuid->nent; ++func)
 		do_cpuid_ent(&cpuid_entries[nent], func, 0,
-				&nent, cpuid->nent);
+			     &nent, cpuid->nent);
 	r = -E2BIG;
 	if (nent >= cpuid->nent)
 		goto out_free;
@@ -1349,10 +1383,10 @@ static int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid,
 	limit = cpuid_entries[nent - 1].eax;
 	for (func = 0x80000001; func <= limit && nent < cpuid->nent; ++func)
 		do_cpuid_ent(&cpuid_entries[nent], func, 0,
-			       &nent, cpuid->nent);
+			     &nent, cpuid->nent);
 	r = -EFAULT;
 	if (copy_to_user(entries, cpuid_entries,
-			nent * sizeof(struct kvm_cpuid_entry2)))
+			 nent * sizeof(struct kvm_cpuid_entry2)))
 		goto out_free;
 	cpuid->nent = nent;
 	r = 0;
@@ -1496,7 +1530,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 		if (copy_from_user(&cpuid, cpuid_arg, sizeof cpuid))
 			goto out;
 		r = kvm_vcpu_ioctl_set_cpuid2(vcpu, &cpuid,
-				cpuid_arg->entries);
+					      cpuid_arg->entries);
 		if (r)
 			goto out;
 		break;
@@ -1509,7 +1543,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 		if (copy_from_user(&cpuid, cpuid_arg, sizeof cpuid))
 			goto out;
 		r = kvm_vcpu_ioctl_get_cpuid2(vcpu, &cpuid,
-				cpuid_arg->entries);
+					      cpuid_arg->entries);
 		if (r)
 			goto out;
 		r = -EFAULT;
@@ -1556,8 +1590,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 		r = -EINVAL;
 	}
 out:
-	if (lapic)
-		kfree(lapic);
+	kfree(lapic);
 	return r;
 }
 
@@ -1835,6 +1868,12 @@ long kvm_arch_vm_ioctl(struct file *filp,
 			}
 		} else
 			goto out;
+		r = kvm_setup_default_irq_routing(kvm);
+		if (r) {
+			kfree(kvm->arch.vpic);
+			kfree(kvm->arch.vioapic);
+			goto out;
+		}
 		break;
 	case KVM_CREATE_PIT:
 		mutex_lock(&kvm->lock);
@@ -1848,6 +1887,7 @@ long kvm_arch_vm_ioctl(struct file *filp,
 	create_pit_unlock:
 		mutex_unlock(&kvm->lock);
 		break;
+	case KVM_IRQ_LINE_STATUS:
 	case KVM_IRQ_LINE: {
 		struct kvm_irq_level irq_event;
 
@@ -1855,10 +1895,17 @@ long kvm_arch_vm_ioctl(struct file *filp,
 		if (copy_from_user(&irq_event, argp, sizeof irq_event))
 			goto out;
 		if (irqchip_in_kernel(kvm)) {
+			__s32 status;
 			mutex_lock(&kvm->lock);
-			kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID,
-				    irq_event.irq, irq_event.level);
+			status = kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID,
+					irq_event.irq, irq_event.level);
 			mutex_unlock(&kvm->lock);
+			if (ioctl == KVM_IRQ_LINE_STATUS) {
+				irq_event.status = status;
+				if (copy_to_user(argp, &irq_event,
+							sizeof irq_event))
+					goto out;
+			}
 			r = 0;
 		}
 		break;
@@ -2005,8 +2052,8 @@ static struct kvm_io_device *vcpu_find_mmio_dev(struct kvm_vcpu *vcpu,
 	return dev;
 }
 
-int kvm_read_guest_virt(gva_t addr, void *val, unsigned int bytes,
-			struct kvm_vcpu *vcpu)
+static int kvm_read_guest_virt(gva_t addr, void *val, unsigned int bytes,
+			       struct kvm_vcpu *vcpu)
 {
 	void *data = val;
 	int r = X86EMUL_CONTINUE;
@@ -2035,8 +2082,8 @@ out:
 	return r;
 }
 
-int kvm_write_guest_virt(gva_t addr, void *val, unsigned int bytes,
-			 struct kvm_vcpu *vcpu)
+static int kvm_write_guest_virt(gva_t addr, void *val, unsigned int bytes,
+				struct kvm_vcpu *vcpu)
 {
 	void *data = val;
 	int r = X86EMUL_CONTINUE;
@@ -2624,9 +2671,72 @@ int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, struct kvm_run *run, int in,
 }
 EXPORT_SYMBOL_GPL(kvm_emulate_pio_string);
 
+static void bounce_off(void *info)
+{
+	/* nothing */
+}
+
+static unsigned int  ref_freq;
+static unsigned long tsc_khz_ref;
+
+static int kvmclock_cpufreq_notifier(struct notifier_block *nb, unsigned long val,
+				     void *data)
+{
+	struct cpufreq_freqs *freq = data;
+	struct kvm *kvm;
+	struct kvm_vcpu *vcpu;
+	int i, send_ipi = 0;
+
+	if (!ref_freq)
+		ref_freq = freq->old;
+
+	if (val == CPUFREQ_PRECHANGE && freq->old > freq->new)
+		return 0;
+	if (val == CPUFREQ_POSTCHANGE && freq->old < freq->new)
+		return 0;
+	per_cpu(cpu_tsc_khz, freq->cpu) = cpufreq_scale(tsc_khz_ref, ref_freq, freq->new);
+
+	spin_lock(&kvm_lock);
+	list_for_each_entry(kvm, &vm_list, vm_list) {
+		for (i = 0; i < KVM_MAX_VCPUS; ++i) {
+			vcpu = kvm->vcpus[i];
+			if (!vcpu)
+				continue;
+			if (vcpu->cpu != freq->cpu)
+				continue;
+			if (!kvm_request_guest_time_update(vcpu))
+				continue;
+			if (vcpu->cpu != smp_processor_id())
+				send_ipi++;
+		}
+	}
+	spin_unlock(&kvm_lock);
+
+	if (freq->old < freq->new && send_ipi) {
+		/*
+		 * We upscale the frequency.  Must make the guest
+		 * doesn't see old kvmclock values while running with
+		 * the new frequency, otherwise we risk the guest sees
+		 * time go backwards.
+		 *
+		 * In case we update the frequency for another cpu
+		 * (which might be in guest context) send an interrupt
+		 * to kick the cpu out of guest context.  Next time
+		 * guest context is entered kvmclock will be updated,
+		 * so the guest will not see stale values.
+		 */
+		smp_call_function_single(freq->cpu, bounce_off, NULL, 1);
+	}
+	return 0;
+}
+
+static struct notifier_block kvmclock_cpufreq_notifier_block = {
+        .notifier_call  = kvmclock_cpufreq_notifier
+};
+
 int kvm_arch_init(void *opaque)
 {
-	int r;
+	int r, cpu;
 	struct kvm_x86_ops *ops = (struct kvm_x86_ops *)opaque;
 
 	if (kvm_x86_ops) {
@@ -2657,6 +2767,15 @@ int kvm_arch_init(void *opaque)
 	kvm_mmu_set_base_ptes(PT_PRESENT_MASK);
 	kvm_mmu_set_mask_ptes(PT_USER_MASK, PT_ACCESSED_MASK,
 			PT_DIRTY_MASK, PT64_NX_MASK, 0, 0);
+
+	for_each_possible_cpu(cpu)
+		per_cpu(cpu_tsc_khz, cpu) = tsc_khz;
+	if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) {
+		tsc_khz_ref = tsc_khz;
+		cpufreq_register_notifier(&kvmclock_cpufreq_notifier_block,
+					  CPUFREQ_TRANSITION_NOTIFIER);
+	}
+
 	return 0;
 
 out:
@@ -2665,6 +2784,9 @@ out:
 
 void kvm_arch_exit(void)
 {
+	if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC))
+		cpufreq_unregister_notifier(&kvmclock_cpufreq_notifier_block,
+					    CPUFREQ_TRANSITION_NOTIFIER);
 	kvm_x86_ops = NULL;
 	kvm_mmu_module_exit();
 }
@@ -2864,7 +2986,7 @@ static int is_matching_cpuid_entry(struct kvm_cpuid_entry2 *e,
 	if ((e->flags & KVM_CPUID_FLAG_SIGNIFCANT_INDEX) && e->index != index)
 		return 0;
 	if ((e->flags & KVM_CPUID_FLAG_STATEFUL_FUNC) &&
-		!(e->flags & KVM_CPUID_FLAG_STATE_READ_NEXT))
+	    !(e->flags & KVM_CPUID_FLAG_STATE_READ_NEXT))
 		return 0;
 	return 1;
 }
@@ -2892,10 +3014,19 @@ struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu,
 			if (!best || e->function > best->function)
 				best = e;
 	}
-
 	return best;
 }
 
+int cpuid_maxphyaddr(struct kvm_vcpu *vcpu)
+{
+	struct kvm_cpuid_entry2 *best;
+
+	best = kvm_find_cpuid_entry(vcpu, 0x80000008, 0);
+	if (best)
+		return best->eax & 0xff;
+	return 36;
+}
+
 void kvm_emulate_cpuid(struct kvm_vcpu *vcpu)
 {
 	u32 function, index;
@@ -2993,6 +3124,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	if (vcpu->requests) {
 		if (test_and_clear_bit(KVM_REQ_MIGRATE_TIMER, &vcpu->requests))
 			__kvm_migrate_timers(vcpu);
+		if (test_and_clear_bit(KVM_REQ_KVMCLOCK_UPDATE, &vcpu->requests))
+			kvm_write_guest_time(vcpu);
 		if (test_and_clear_bit(KVM_REQ_MMU_SYNC, &vcpu->requests))
 			kvm_mmu_sync_roots(vcpu);
 		if (test_and_clear_bit(KVM_REQ_TLB_FLUSH, &vcpu->requests))
@@ -3010,9 +3143,6 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 		}
 	}
 
-	clear_bit(KVM_REQ_PENDING_TIMER, &vcpu->requests);
-	kvm_inject_pending_timer_irqs(vcpu);
-
 	preempt_disable();
 
 	kvm_x86_ops->prepare_guest_switch(vcpu);
@@ -3112,6 +3242,7 @@ out:
 	return r;
 }
 
+
 static int __vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 {
 	int r;
@@ -3138,29 +3269,42 @@ static int __vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 			kvm_vcpu_block(vcpu);
 			down_read(&vcpu->kvm->slots_lock);
 			if (test_and_clear_bit(KVM_REQ_UNHALT, &vcpu->requests))
-				if (vcpu->arch.mp_state == KVM_MP_STATE_HALTED)
+			{
+				switch(vcpu->arch.mp_state) {
+				case KVM_MP_STATE_HALTED:
 					vcpu->arch.mp_state =
-							KVM_MP_STATE_RUNNABLE;
-			if (vcpu->arch.mp_state != KVM_MP_STATE_RUNNABLE)
-				r = -EINTR;
+						KVM_MP_STATE_RUNNABLE;
+				case KVM_MP_STATE_RUNNABLE:
+					break;
+				case KVM_MP_STATE_SIPI_RECEIVED:
+				default:
+					r = -EINTR;
+					break;
+				}
+			}
 		}
 
-		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;
-			}
-			if (signal_pending(current)) {
-				r = -EINTR;
-				kvm_run->exit_reason = KVM_EXIT_INTR;
-				++vcpu->stat.signal_exits;
-			}
-			if (need_resched()) {
-				up_read(&vcpu->kvm->slots_lock);
-				kvm_resched(vcpu);
-				down_read(&vcpu->kvm->slots_lock);
-			}
+		if (r <= 0)
+			break;
+
+		clear_bit(KVM_REQ_PENDING_TIMER, &vcpu->requests);
+		if (kvm_cpu_has_pending_timer(vcpu))
+			kvm_inject_pending_timer_irqs(vcpu);
+
+		if (dm_request_for_irq_injection(vcpu, kvm_run)) {
+			r = -EINTR;
+			kvm_run->exit_reason = KVM_EXIT_INTR;
+			++vcpu->stat.request_irq_exits;
+		}
+		if (signal_pending(current)) {
+			r = -EINTR;
+			kvm_run->exit_reason = KVM_EXIT_INTR;
+			++vcpu->stat.signal_exits;
+		}
+		if (need_resched()) {
+			up_read(&vcpu->kvm->slots_lock);
+			kvm_resched(vcpu);
+			down_read(&vcpu->kvm->slots_lock);
 		}
 	}
 
@@ -3570,7 +3714,6 @@ static void save_state_to_tss32(struct kvm_vcpu *vcpu,
 	tss->fs = get_segment_selector(vcpu, VCPU_SREG_FS);
 	tss->gs = get_segment_selector(vcpu, VCPU_SREG_GS);
 	tss->ldt_selector = get_segment_selector(vcpu, VCPU_SREG_LDTR);
-	tss->prev_task_link = get_segment_selector(vcpu, VCPU_SREG_TR);
 }
 
 static int load_state_from_tss32(struct kvm_vcpu *vcpu,
@@ -3667,8 +3810,8 @@ static int load_state_from_tss16(struct kvm_vcpu *vcpu,
 }
 
 static int kvm_task_switch_16(struct kvm_vcpu *vcpu, u16 tss_selector,
-		       u32 old_tss_base,
-		       struct desc_struct *nseg_desc)
+			      u16 old_tss_sel, u32 old_tss_base,
+			      struct desc_struct *nseg_desc)
 {
 	struct tss_segment_16 tss_segment_16;
 	int ret = 0;
@@ -3687,6 +3830,16 @@ static int kvm_task_switch_16(struct kvm_vcpu *vcpu, u16 tss_selector,
 			   &tss_segment_16, sizeof tss_segment_16))
 		goto out;
 
+	if (old_tss_sel != 0xffff) {
+		tss_segment_16.prev_task_link = old_tss_sel;
+
+		if (kvm_write_guest(vcpu->kvm,
+				    get_tss_base_addr(vcpu, nseg_desc),
+				    &tss_segment_16.prev_task_link,
+				    sizeof tss_segment_16.prev_task_link))
+			goto out;
+	}
+
 	if (load_state_from_tss16(vcpu, &tss_segment_16))
 		goto out;
 
@@ -3696,7 +3849,7 @@ out:
 }
 
 static int kvm_task_switch_32(struct kvm_vcpu *vcpu, u16 tss_selector,
-		       u32 old_tss_base,
+		       u16 old_tss_sel, u32 old_tss_base,
 		       struct desc_struct *nseg_desc)
 {
 	struct tss_segment_32 tss_segment_32;
@@ -3716,6 +3869,16 @@ static int kvm_task_switch_32(struct kvm_vcpu *vcpu, u16 tss_selector,
 			   &tss_segment_32, sizeof tss_segment_32))
 		goto out;
 
+	if (old_tss_sel != 0xffff) {
+		tss_segment_32.prev_task_link = old_tss_sel;
+
+		if (kvm_write_guest(vcpu->kvm,
+				    get_tss_base_addr(vcpu, nseg_desc),
+				    &tss_segment_32.prev_task_link,
+				    sizeof tss_segment_32.prev_task_link))
+			goto out;
+	}
+
 	if (load_state_from_tss32(vcpu, &tss_segment_32))
 		goto out;
 
@@ -3769,14 +3932,22 @@ int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason)
 		kvm_x86_ops->set_rflags(vcpu, eflags & ~X86_EFLAGS_NT);
 	}
 
-	kvm_x86_ops->skip_emulated_instruction(vcpu);
+	/* set back link to prev task only if NT bit is set in eflags
+	   note that old_tss_sel is not used afetr this point */
+	if (reason != TASK_SWITCH_CALL && reason != TASK_SWITCH_GATE)
+		old_tss_sel = 0xffff;
+
+	/* set back link to prev task only if NT bit is set in eflags
+	   note that old_tss_sel is not used afetr this point */
+	if (reason != TASK_SWITCH_CALL && reason != TASK_SWITCH_GATE)
+		old_tss_sel = 0xffff;
 
 	if (nseg_desc.type & 8)
-		ret = kvm_task_switch_32(vcpu, tss_selector, old_tss_base,
-					 &nseg_desc);
+		ret = kvm_task_switch_32(vcpu, tss_selector, old_tss_sel,
+					 old_tss_base, &nseg_desc);
 	else
-		ret = kvm_task_switch_16(vcpu, tss_selector, old_tss_base,
-					 &nseg_desc);
+		ret = kvm_task_switch_16(vcpu, tss_selector, old_tss_sel,
+					 old_tss_base, &nseg_desc);
 
 	if (reason == TASK_SWITCH_CALL || reason == TASK_SWITCH_GATE) {
 		u32 eflags = kvm_x86_ops->get_rflags(vcpu);
@@ -4048,6 +4219,11 @@ EXPORT_SYMBOL_GPL(kvm_put_guest_fpu);
 
 void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu)
 {
+	if (vcpu->arch.time_page) {
+		kvm_release_page_dirty(vcpu->arch.time_page);
+		vcpu->arch.time_page = NULL;
+	}
+
 	kvm_x86_ops->vcpu_free(vcpu);
 }
 
@@ -4185,7 +4361,6 @@ struct  kvm *kvm_arch_create_vm(void)
 		return ERR_PTR(-ENOMEM);
 
 	INIT_LIST_HEAD(&kvm->arch.active_mmu_pages);
-	INIT_LIST_HEAD(&kvm->arch.oos_global_pages);
 	INIT_LIST_HEAD(&kvm->arch.assigned_dev_head);
 
 	/* Reserve bit 0 of irq_sources_bitmap for userspace irq source */
@@ -4336,3 +4511,8 @@ void kvm_vcpu_kick(struct kvm_vcpu *vcpu)
 		smp_call_function_single(ipi_pcpu, vcpu_kick_intr, vcpu, 0);
 	put_cpu();
 }
+
+int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu)
+{
+	return kvm_x86_ops->interrupt_allowed(vcpu);
+}