1 files changed, 441 insertions, 109 deletions

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 4fc80174191c..9d068966fb2a 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -37,6 +37,7 @@
 #include <linux/iommu.h>
 #include <linux/intel-iommu.h>
 #include <linux/cpufreq.h>
+#include <linux/user-return-notifier.h>
 #include <trace/events/kvm.h>
 #undef TRACE_INCLUDE_FILE
 #define CREATE_TRACE_POINTS
@@ -88,6 +89,25 @@ EXPORT_SYMBOL_GPL(kvm_x86_ops);
 int ignore_msrs = 0;
 module_param_named(ignore_msrs, ignore_msrs, bool, S_IRUGO | S_IWUSR);
 
+#define KVM_NR_SHARED_MSRS 16
+
+struct kvm_shared_msrs_global {
+        int nr;
+        struct kvm_shared_msr {
+                u32 msr;
+                u64 value;
+        } msrs[KVM_NR_SHARED_MSRS];
+};
+
+struct kvm_shared_msrs {
+        struct user_return_notifier urn;
+        bool registered;
+        u64 current_value[KVM_NR_SHARED_MSRS];
+};
+
+static struct kvm_shared_msrs_global __read_mostly shared_msrs_global;
+static DEFINE_PER_CPU(struct kvm_shared_msrs, shared_msrs);
+
 struct kvm_stats_debugfs_item debugfs_entries[] = {
         { "pf_fixed", VCPU_STAT(pf_fixed) },
         { "pf_guest", VCPU_STAT(pf_guest) },
@@ -124,6 +144,72 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
         { NULL }
 };
 
+static void kvm_on_user_return(struct user_return_notifier *urn)
+{
+        unsigned slot;
+        struct kvm_shared_msr *global;
+        struct kvm_shared_msrs *locals
+                = container_of(urn, struct kvm_shared_msrs, urn);
+
+        for (slot = 0; slot < shared_msrs_global.nr; ++slot) {
+                global = &shared_msrs_global.msrs[slot];
+                if (global->value != locals->current_value[slot]) {
+                        wrmsrl(global->msr, global->value);
+                        locals->current_value[slot] = global->value;
+                }
+        }
+        locals->registered = false;
+        user_return_notifier_unregister(urn);
+}
+
+void kvm_define_shared_msr(unsigned slot, u32 msr)
+{
+        int cpu;
+        u64 value;
+
+        if (slot >= shared_msrs_global.nr)
+                shared_msrs_global.nr = slot + 1;
+        shared_msrs_global.msrs[slot].msr = msr;
+        rdmsrl_safe(msr, &value);
+        shared_msrs_global.msrs[slot].value = value;
+        for_each_online_cpu(cpu)
+                per_cpu(shared_msrs, cpu).current_value[slot] = value;
+}
+EXPORT_SYMBOL_GPL(kvm_define_shared_msr);
+
+static void kvm_shared_msr_cpu_online(void)
+{
+        unsigned i;
+        struct kvm_shared_msrs *locals = &__get_cpu_var(shared_msrs);
+
+        for (i = 0; i < shared_msrs_global.nr; ++i)
+                locals->current_value[i] = shared_msrs_global.msrs[i].value;
+}
+
+void kvm_set_shared_msr(unsigned slot, u64 value, u64 mask)
+{
+        struct kvm_shared_msrs *smsr = &__get_cpu_var(shared_msrs);
+
+        if (((value ^ smsr->current_value[slot]) & mask) == 0)
+                return;
+        smsr->current_value[slot] = value;
+        wrmsrl(shared_msrs_global.msrs[slot].msr, value);
+        if (!smsr->registered) {
+                smsr->urn.on_user_return = kvm_on_user_return;
+                user_return_notifier_register(&smsr->urn);
+                smsr->registered = true;
+        }
+}
+EXPORT_SYMBOL_GPL(kvm_set_shared_msr);
+
+static void drop_user_return_notifiers(void *ignore)
+{
+        struct kvm_shared_msrs *smsr = &__get_cpu_var(shared_msrs);
+
+        if (smsr->registered)
+                kvm_on_user_return(&smsr->urn);
+}
+
 unsigned long segment_base(u16 selector)
 {
         struct descriptor_table gdt;
@@ -485,16 +571,19 @@ static inline u32 bit(int bitno)
  * and KVM_SET_MSRS, and KVM_GET_MSR_INDEX_LIST.
  *
  * This list is modified at module load time to reflect the
- * capabilities of the host cpu.
+ * capabilities of the host cpu. This capabilities test skips MSRs that are
+ * kvm-specific. Those are put in the beginning of the list.
  */
+
+#define KVM_SAVE_MSRS_BEGIN     2
 static u32 msrs_to_save[] = {
+        MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK,
         MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP,
         MSR_K6_STAR,
 #ifdef CONFIG_X86_64
         MSR_CSTAR, MSR_KERNEL_GS_BASE, MSR_SYSCALL_MASK, MSR_LSTAR,
 #endif
-        MSR_IA32_TSC, MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK,
-        MSR_IA32_PERF_STATUS, MSR_IA32_CR_PAT, MSR_VM_HSAVE_PA
+        MSR_IA32_TSC, MSR_IA32_PERF_STATUS, MSR_IA32_CR_PAT, MSR_VM_HSAVE_PA
 };
 
 static unsigned num_msrs_to_save;
@@ -678,7 +767,8 @@ static void kvm_write_guest_time(struct kvm_vcpu *v)
         /* With all the info we got, fill in the values */
 
         vcpu->hv_clock.system_time = ts.tv_nsec +
-                                     (NSEC_PER_SEC * (u64)ts.tv_sec);
+                                     (NSEC_PER_SEC * (u64)ts.tv_sec) + v->kvm->arch.kvmclock_offset;
+
         /*
          * The interface expects us to write an even number signaling that the
          * update is finished. Since the guest won't see the intermediate
@@ -836,6 +926,38 @@ static int set_msr_mce(struct kvm_vcpu *vcpu, u32 msr, u64 data)
         return 0;
 }
 
+static int xen_hvm_config(struct kvm_vcpu *vcpu, u64 data)
+{
+        struct kvm *kvm = vcpu->kvm;
+        int lm = is_long_mode(vcpu);
+        u8 *blob_addr = lm ? (u8 *)(long)kvm->arch.xen_hvm_config.blob_addr_64
+                : (u8 *)(long)kvm->arch.xen_hvm_config.blob_addr_32;
+        u8 blob_size = lm ? kvm->arch.xen_hvm_config.blob_size_64
+                : kvm->arch.xen_hvm_config.blob_size_32;
+        u32 page_num = data & ~PAGE_MASK;
+        u64 page_addr = data & PAGE_MASK;
+        u8 *page;
+        int r;
+
+        r = -E2BIG;
+        if (page_num >= blob_size)
+                goto out;
+        r = -ENOMEM;
+        page = kzalloc(PAGE_SIZE, GFP_KERNEL);
+        if (!page)
+                goto out;
+        r = -EFAULT;
+        if (copy_from_user(page, blob_addr + (page_num * PAGE_SIZE), PAGE_SIZE))
+                goto out_free;
+        if (kvm_write_guest(kvm, page_addr, page, PAGE_SIZE))
+                goto out_free;
+        r = 0;
+out_free:
+        kfree(page);
+out:
+        return r;
+}
+
 int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 {
         switch (msr) {
@@ -951,6 +1073,8 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data)
                         "0x%x data 0x%llx\n", msr, data);
                 break;
         default:
+                if (msr && (msr == vcpu->kvm->arch.xen_hvm_config.msr))
+                        return xen_hvm_config(vcpu, data);
                 if (!ignore_msrs) {
                         pr_unimpl(vcpu, "unhandled wrmsr: 0x%x data %llx\n",
                                 msr, data);
@@ -1225,6 +1349,9 @@ int kvm_dev_ioctl_check_extension(long ext)
         case KVM_CAP_PIT2:
         case KVM_CAP_PIT_STATE2:
         case KVM_CAP_SET_IDENTITY_MAP_ADDR:
+        case KVM_CAP_XEN_HVM:
+        case KVM_CAP_ADJUST_CLOCK:
+        case KVM_CAP_VCPU_EVENTS:
                 r = 1;
                 break;
         case KVM_CAP_COALESCED_MMIO:
@@ -1239,8 +1366,8 @@ int kvm_dev_ioctl_check_extension(long ext)
         case KVM_CAP_NR_MEMSLOTS:
                 r = KVM_MEMORY_SLOTS;
                 break;
-        case KVM_CAP_PV_MMU:
-                r = !tdp_enabled;
+        case KVM_CAP_PV_MMU:    /* obsolete */
+                r = 0;
                 break;
         case KVM_CAP_IOMMU:
                 r = iommu_found();
@@ -1327,6 +1454,12 @@ out:
 void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
         kvm_x86_ops->vcpu_load(vcpu, cpu);
+        if (unlikely(per_cpu(cpu_tsc_khz, cpu) == 0)) {
+                unsigned long khz = cpufreq_quick_get(cpu);
+                if (!khz)
+                        khz = tsc_khz;
+                per_cpu(cpu_tsc_khz, cpu) = khz;
+        }
         kvm_request_guest_time_update(vcpu);
 }
 
@@ -1760,6 +1893,61 @@ static int kvm_vcpu_ioctl_x86_set_mce(struct kvm_vcpu *vcpu,
         return 0;
 }
 
+static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu,
+                                               struct kvm_vcpu_events *events)
+{
+        vcpu_load(vcpu);
+
+        events->exception.injected = vcpu->arch.exception.pending;
+        events->exception.nr = vcpu->arch.exception.nr;
+        events->exception.has_error_code = vcpu->arch.exception.has_error_code;
+        events->exception.error_code = vcpu->arch.exception.error_code;
+
+        events->interrupt.injected = vcpu->arch.interrupt.pending;
+        events->interrupt.nr = vcpu->arch.interrupt.nr;
+        events->interrupt.soft = vcpu->arch.interrupt.soft;
+
+        events->nmi.injected = vcpu->arch.nmi_injected;
+        events->nmi.pending = vcpu->arch.nmi_pending;
+        events->nmi.masked = kvm_x86_ops->get_nmi_mask(vcpu);
+
+        events->sipi_vector = vcpu->arch.sipi_vector;
+
+        events->flags = 0;
+
+        vcpu_put(vcpu);
+}
+
+static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
+                                              struct kvm_vcpu_events *events)
+{
+        if (events->flags)
+                return -EINVAL;
+
+        vcpu_load(vcpu);
+
+        vcpu->arch.exception.pending = events->exception.injected;
+        vcpu->arch.exception.nr = events->exception.nr;
+        vcpu->arch.exception.has_error_code = events->exception.has_error_code;
+        vcpu->arch.exception.error_code = events->exception.error_code;
+
+        vcpu->arch.interrupt.pending = events->interrupt.injected;
+        vcpu->arch.interrupt.nr = events->interrupt.nr;
+        vcpu->arch.interrupt.soft = events->interrupt.soft;
+        if (vcpu->arch.interrupt.pending && irqchip_in_kernel(vcpu->kvm))
+                kvm_pic_clear_isr_ack(vcpu->kvm);
+
+        vcpu->arch.nmi_injected = events->nmi.injected;
+        vcpu->arch.nmi_pending = events->nmi.pending;
+        kvm_x86_ops->set_nmi_mask(vcpu, events->nmi.masked);
+
+        vcpu->arch.sipi_vector = events->sipi_vector;
+
+        vcpu_put(vcpu);
+
+        return 0;
+}
+
 long kvm_arch_vcpu_ioctl(struct file *filp,
                          unsigned int ioctl, unsigned long arg)
 {
@@ -1770,6 +1958,9 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 
         switch (ioctl) {
         case KVM_GET_LAPIC: {
+                r = -EINVAL;
+                if (!vcpu->arch.apic)
+                        goto out;
                 lapic = kzalloc(sizeof(struct kvm_lapic_state), GFP_KERNEL);
 
                 r = -ENOMEM;
@@ -1785,6 +1976,9 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
                 break;
         }
         case KVM_SET_LAPIC: {
+                r = -EINVAL;
+                if (!vcpu->arch.apic)
+                        goto out;
                 lapic = kmalloc(sizeof(struct kvm_lapic_state), GFP_KERNEL);
                 r = -ENOMEM;
                 if (!lapic)
@@ -1911,6 +2105,27 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
                 r = kvm_vcpu_ioctl_x86_set_mce(vcpu, &mce);
                 break;
         }
+        case KVM_GET_VCPU_EVENTS: {
+                struct kvm_vcpu_events events;
+
+                kvm_vcpu_ioctl_x86_get_vcpu_events(vcpu, &events);
+
+                r = -EFAULT;
+                if (copy_to_user(argp, &events, sizeof(struct kvm_vcpu_events)))
+                        break;
+                r = 0;
+                break;
+        }
+        case KVM_SET_VCPU_EVENTS: {
+                struct kvm_vcpu_events events;
+
+                r = -EFAULT;
+                if (copy_from_user(&events, argp, sizeof(struct kvm_vcpu_events)))
+                        break;
+
+                r = kvm_vcpu_ioctl_x86_set_vcpu_events(vcpu, &events);
+                break;
+        }
         default:
                 r = -EINVAL;
         }
@@ -2039,9 +2254,7 @@ static int kvm_vm_ioctl_get_irqchip(struct kvm *kvm, struct kvm_irqchip *chip)
                         sizeof(struct kvm_pic_state));
                 break;
         case KVM_IRQCHIP_IOAPIC:
-                memcpy(&chip->chip.ioapic,
-                        ioapic_irqchip(kvm),
-                        sizeof(struct kvm_ioapic_state));
+                r = kvm_get_ioapic(kvm, &chip->chip.ioapic);
                 break;
         default:
                 r = -EINVAL;
@@ -2071,11 +2284,7 @@ static int kvm_vm_ioctl_set_irqchip(struct kvm *kvm, struct kvm_irqchip *chip)
                 spin_unlock(&pic_irqchip(kvm)->lock);
                 break;
         case KVM_IRQCHIP_IOAPIC:
-                mutex_lock(&kvm->irq_lock);
-                memcpy(ioapic_irqchip(kvm),
-                        &chip->chip.ioapic,
-                        sizeof(struct kvm_ioapic_state));
-                mutex_unlock(&kvm->irq_lock);
+                r = kvm_set_ioapic(kvm, &chip->chip.ioapic);
                 break;
         default:
                 r = -EINVAL;
@@ -2183,7 +2392,7 @@ long kvm_arch_vm_ioctl(struct file *filp,
 {
         struct kvm *kvm = filp->private_data;
         void __user *argp = (void __user *)arg;
-        int r = -EINVAL;
+        int r = -ENOTTY;
         /*
          * This union makes it completely explicit to gcc-3.x
          * that these two variables' stack usage should be
@@ -2245,25 +2454,39 @@ long kvm_arch_vm_ioctl(struct file *filp,
                 if (r)
                         goto out;
                 break;
-        case KVM_CREATE_IRQCHIP:
+        case KVM_CREATE_IRQCHIP: {
+                struct kvm_pic *vpic;
+
+                mutex_lock(&kvm->lock);
+                r = -EEXIST;
+                if (kvm->arch.vpic)
+                        goto create_irqchip_unlock;
                 r = -ENOMEM;
-                kvm->arch.vpic = kvm_create_pic(kvm);
-                if (kvm->arch.vpic) {
+                vpic = kvm_create_pic(kvm);
+                if (vpic) {
                         r = kvm_ioapic_init(kvm);
                         if (r) {
-                                kfree(kvm->arch.vpic);
-                                kvm->arch.vpic = NULL;
-                                goto out;
+                                kfree(vpic);
+                                goto create_irqchip_unlock;
                         }
                 } else
-                        goto out;
+                        goto create_irqchip_unlock;
+                smp_wmb();
+                kvm->arch.vpic = vpic;
+                smp_wmb();
                 r = kvm_setup_default_irq_routing(kvm);
                 if (r) {
+                        mutex_lock(&kvm->irq_lock);
                         kfree(kvm->arch.vpic);
                         kfree(kvm->arch.vioapic);
-                        goto out;
+                        kvm->arch.vpic = NULL;
+                        kvm->arch.vioapic = NULL;
+                        mutex_unlock(&kvm->irq_lock);
                 }
+        create_irqchip_unlock:
+                mutex_unlock(&kvm->lock);
                 break;
+        }
         case KVM_CREATE_PIT:
                 u.pit_config.flags = KVM_PIT_SPEAKER_DUMMY;
                 goto create_pit;
@@ -2293,10 +2516,8 @@ long kvm_arch_vm_ioctl(struct file *filp,
                         goto out;
                 if (irqchip_in_kernel(kvm)) {
                         __s32 status;
-                        mutex_lock(&kvm->irq_lock);
                         status = kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID,
                                         irq_event.irq, irq_event.level);
-                        mutex_unlock(&kvm->irq_lock);
                         if (ioctl == KVM_IRQ_LINE_STATUS) {
                                 irq_event.status = status;
                                 if (copy_to_user(argp, &irq_event,
@@ -2422,6 +2643,55 @@ long kvm_arch_vm_ioctl(struct file *filp,
                 r = 0;
                 break;
         }
+        case KVM_XEN_HVM_CONFIG: {
+                r = -EFAULT;
+                if (copy_from_user(&kvm->arch.xen_hvm_config, argp,
+                                   sizeof(struct kvm_xen_hvm_config)))
+                        goto out;
+                r = -EINVAL;
+                if (kvm->arch.xen_hvm_config.flags)
+                        goto out;
+                r = 0;
+                break;
+        }
+        case KVM_SET_CLOCK: {
+                struct timespec now;
+                struct kvm_clock_data user_ns;
+                u64 now_ns;
+                s64 delta;
+
+                r = -EFAULT;
+                if (copy_from_user(&user_ns, argp, sizeof(user_ns)))
+                        goto out;
+
+                r = -EINVAL;
+                if (user_ns.flags)
+                        goto out;
+
+                r = 0;
+                ktime_get_ts(&now);
+                now_ns = timespec_to_ns(&now);
+                delta = user_ns.clock - now_ns;
+                kvm->arch.kvmclock_offset = delta;
+                break;
+        }
+        case KVM_GET_CLOCK: {
+                struct timespec now;
+                struct kvm_clock_data user_ns;
+                u64 now_ns;
+
+                ktime_get_ts(&now);
+                now_ns = timespec_to_ns(&now);
+                user_ns.clock = kvm->arch.kvmclock_offset + now_ns;
+                user_ns.flags = 0;
+
+                r = -EFAULT;
+                if (copy_to_user(argp, &user_ns, sizeof(user_ns)))
+                        goto out;
+                r = 0;
+                break;
+        }
+
         default:
                 ;
         }
@@ -2434,7 +2704,8 @@ static void kvm_init_msr_list(void)
         u32 dummy[2];
         unsigned i, j;
 
-        for (i = j = 0; i < ARRAY_SIZE(msrs_to_save); i++) {
+        /* skip the first msrs in the list. KVM-specific */
+        for (i = j = KVM_SAVE_MSRS_BEGIN; i < ARRAY_SIZE(msrs_to_save); i++) {
                 if (rdmsr_safe(msrs_to_save[i], &dummy[0], &dummy[1]) < 0)
                         continue;
                 if (j < i)
@@ -2758,13 +3029,13 @@ static void cache_all_regs(struct kvm_vcpu *vcpu)
 }
 
 int emulate_instruction(struct kvm_vcpu *vcpu,
-                        struct kvm_run *run,
                         unsigned long cr2,
                         u16 error_code,
                         int emulation_type)
 {
         int r, shadow_mask;
         struct decode_cache *c;
+        struct kvm_run *run = vcpu->run;
 
         kvm_clear_exception_queue(vcpu);
         vcpu->arch.mmio_fault_cr2 = cr2;
@@ -2784,7 +3055,7 @@ int emulate_instruction(struct kvm_vcpu *vcpu,
                 kvm_x86_ops->get_cs_db_l_bits(vcpu, &cs_db, &cs_l);
 
                 vcpu->arch.emulate_ctxt.vcpu = vcpu;
-                vcpu->arch.emulate_ctxt.eflags = kvm_x86_ops->get_rflags(vcpu);
+                vcpu->arch.emulate_ctxt.eflags = kvm_get_rflags(vcpu);
                 vcpu->arch.emulate_ctxt.mode =
                         (vcpu->arch.emulate_ctxt.eflags & X86_EFLAGS_VM)
                         ? X86EMUL_MODE_REAL : cs_l
@@ -2862,7 +3133,7 @@ int emulate_instruction(struct kvm_vcpu *vcpu,
                 return EMULATE_DO_MMIO;
         }
 
-        kvm_x86_ops->set_rflags(vcpu, vcpu->arch.emulate_ctxt.eflags);
+        kvm_set_rflags(vcpu, vcpu->arch.emulate_ctxt.eflags);
 
         if (vcpu->mmio_is_write) {
                 vcpu->mmio_needed = 0;
@@ -2970,8 +3241,7 @@ static int pio_string_write(struct kvm_vcpu *vcpu)
         return r;
 }
 
-int kvm_emulate_pio(struct kvm_vcpu *vcpu, struct kvm_run *run, int in,
-                  int size, unsigned port)
+int kvm_emulate_pio(struct kvm_vcpu *vcpu, int in, int size, unsigned port)
 {
         unsigned long val;
 
@@ -3000,7 +3270,7 @@ int kvm_emulate_pio(struct kvm_vcpu *vcpu, struct kvm_run *run, int in,
 }
 EXPORT_SYMBOL_GPL(kvm_emulate_pio);
 
-int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, struct kvm_run *run, int in,
+int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, int in,
                   int size, unsigned long count, int down,
                   gva_t address, int rep, unsigned port)
 {
@@ -3073,9 +3343,6 @@ 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)
 {
@@ -3084,14 +3351,11 @@ static int kvmclock_cpufreq_notifier(struct notifier_block *nb, unsigned long va
         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);
+        per_cpu(cpu_tsc_khz, freq->cpu) = freq->new;
 
         spin_lock(&kvm_lock);
         list_for_each_entry(kvm, &vm_list, vm_list) {
@@ -3128,9 +3392,28 @@ static struct notifier_block kvmclock_cpufreq_notifier_block = {
         .notifier_call  = kvmclock_cpufreq_notifier
 };
 
+static void kvm_timer_init(void)
+{
+        int cpu;
+
+        if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) {
+                cpufreq_register_notifier(&kvmclock_cpufreq_notifier_block,
+                                          CPUFREQ_TRANSITION_NOTIFIER);
+                for_each_online_cpu(cpu) {
+                        unsigned long khz = cpufreq_get(cpu);
+                        if (!khz)
+                                khz = tsc_khz;
+                        per_cpu(cpu_tsc_khz, cpu) = khz;
+                }
+        } else {
+                for_each_possible_cpu(cpu)
+                        per_cpu(cpu_tsc_khz, cpu) = tsc_khz;
+        }
+}
+
 int kvm_arch_init(void *opaque)
 {
-        int r, cpu;
+        int r;
         struct kvm_x86_ops *ops = (struct kvm_x86_ops *)opaque;
 
         if (kvm_x86_ops) {
@@ -3162,13 +3445,7 @@ int kvm_arch_init(void *opaque)
         kvm_mmu_set_mask_ptes(PT_USER_MASK, PT_ACCESSED_MASK,
                         PT_DIRTY_MASK, PT64_NX_MASK, 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);
-        }
+        kvm_timer_init();
 
         return 0;
 
@@ -3296,7 +3573,7 @@ void realmode_lmsw(struct kvm_vcpu *vcpu, unsigned long msw,
                    unsigned long *rflags)
 {
         kvm_lmsw(vcpu, msw);
-        *rflags = kvm_x86_ops->get_rflags(vcpu);
+        *rflags = kvm_get_rflags(vcpu);
 }
 
 unsigned long realmode_get_cr(struct kvm_vcpu *vcpu, int cr)
@@ -3334,7 +3611,7 @@ void realmode_set_cr(struct kvm_vcpu *vcpu, int cr, unsigned long val,
         switch (cr) {
         case 0:
                 kvm_set_cr0(vcpu, mk_cr_64(vcpu->arch.cr0, val));
-                *rflags = kvm_x86_ops->get_rflags(vcpu);
+                *rflags = kvm_get_rflags(vcpu);
                 break;
         case 2:
                 vcpu->arch.cr2 = val;
@@ -3454,18 +3731,18 @@ EXPORT_SYMBOL_GPL(kvm_emulate_cpuid);
  *
  * 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)
+static int dm_request_for_irq_injection(struct kvm_vcpu *vcpu)
 {
         return (!irqchip_in_kernel(vcpu->kvm) && !kvm_cpu_has_interrupt(vcpu) &&
-                kvm_run->request_interrupt_window &&
+                vcpu->run->request_interrupt_window &&
                 kvm_arch_interrupt_allowed(vcpu));
 }
 
-static void post_kvm_run_save(struct kvm_vcpu *vcpu,
-                              struct kvm_run *kvm_run)
+static void post_kvm_run_save(struct kvm_vcpu *vcpu)
 {
-        kvm_run->if_flag = (kvm_x86_ops->get_rflags(vcpu) & X86_EFLAGS_IF) != 0;
+        struct kvm_run *kvm_run = vcpu->run;
+
+        kvm_run->if_flag = (kvm_get_rflags(vcpu) & X86_EFLAGS_IF) != 0;
         kvm_run->cr8 = kvm_get_cr8(vcpu);
         kvm_run->apic_base = kvm_get_apic_base(vcpu);
         if (irqchip_in_kernel(vcpu->kvm))
@@ -3526,7 +3803,7 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu)
         kvm_x86_ops->update_cr8_intercept(vcpu, tpr, max_irr);
 }
 
-static void inject_pending_event(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+static void inject_pending_event(struct kvm_vcpu *vcpu)
 {
         /* try to reinject previous events if any */
         if (vcpu->arch.exception.pending) {
@@ -3562,11 +3839,11 @@ static void inject_pending_event(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
         }
 }
 
-static int vcpu_enter_guest(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 {
         int r;
         bool req_int_win = !irqchip_in_kernel(vcpu->kvm) &&
-                kvm_run->request_interrupt_window;
+                vcpu->run->request_interrupt_window;
 
         if (vcpu->requests)
                 if (test_and_clear_bit(KVM_REQ_MMU_RELOAD, &vcpu->requests))
@@ -3587,12 +3864,12 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
                         kvm_x86_ops->tlb_flush(vcpu);
                 if (test_and_clear_bit(KVM_REQ_REPORT_TPR_ACCESS,
                                        &vcpu->requests)) {
-                        kvm_run->exit_reason = KVM_EXIT_TPR_ACCESS;
+                        vcpu->run->exit_reason = KVM_EXIT_TPR_ACCESS;
                         r = 0;
                         goto out;
                 }
                 if (test_and_clear_bit(KVM_REQ_TRIPLE_FAULT, &vcpu->requests)) {
-                        kvm_run->exit_reason = KVM_EXIT_SHUTDOWN;
+                        vcpu->run->exit_reason = KVM_EXIT_SHUTDOWN;
                         r = 0;
                         goto out;
                 }
@@ -3616,7 +3893,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
                 goto out;
         }
 
-        inject_pending_event(vcpu, kvm_run);
+        inject_pending_event(vcpu);
 
         /* enable NMI/IRQ window open exits if needed */
         if (vcpu->arch.nmi_pending)
@@ -3642,7 +3919,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
         }
 
         trace_kvm_entry(vcpu->vcpu_id);
-        kvm_x86_ops->run(vcpu, kvm_run);
+        kvm_x86_ops->run(vcpu);
 
         /*
          * If the guest has used debug registers, at least dr7
@@ -3684,13 +3961,13 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 
         kvm_lapic_sync_from_vapic(vcpu);
 
-        r = kvm_x86_ops->handle_exit(kvm_run, vcpu);
+        r = kvm_x86_ops->handle_exit(vcpu);
 out:
         return r;
 }
 
 
-static int __vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+static int __vcpu_run(struct kvm_vcpu *vcpu)
 {
         int r;
 
@@ -3710,7 +3987,7 @@ static int __vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
         r = 1;
         while (r > 0) {
                 if (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE)
-                        r = vcpu_enter_guest(vcpu, kvm_run);
+                        r = vcpu_enter_guest(vcpu);
                 else {
                         up_read(&vcpu->kvm->slots_lock);
                         kvm_vcpu_block(vcpu);
@@ -3738,14 +4015,14 @@ static int __vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
                 if (kvm_cpu_has_pending_timer(vcpu))
                         kvm_inject_pending_timer_irqs(vcpu);
 
-                if (dm_request_for_irq_injection(vcpu, kvm_run)) {
+                if (dm_request_for_irq_injection(vcpu)) {
                         r = -EINTR;
-                        kvm_run->exit_reason = KVM_EXIT_INTR;
+                        vcpu->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->run->exit_reason = KVM_EXIT_INTR;
                         ++vcpu->stat.signal_exits;
                 }
                 if (need_resched()) {
@@ -3756,7 +4033,7 @@ static int __vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
         }
 
         up_read(&vcpu->kvm->slots_lock);
-        post_kvm_run_save(vcpu, kvm_run);
+        post_kvm_run_save(vcpu);
 
         vapic_exit(vcpu);
 
@@ -3789,15 +4066,13 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
                 if (r)
                         goto out;
         }
-#if CONFIG_HAS_IOMEM
         if (vcpu->mmio_needed) {
                 memcpy(vcpu->mmio_data, kvm_run->mmio.data, 8);
                 vcpu->mmio_read_completed = 1;
                 vcpu->mmio_needed = 0;
 
                 down_read(&vcpu->kvm->slots_lock);
-                r = emulate_instruction(vcpu, kvm_run,
-                                        vcpu->arch.mmio_fault_cr2, 0,
+                r = emulate_instruction(vcpu, vcpu->arch.mmio_fault_cr2, 0,
                                         EMULTYPE_NO_DECODE);
                 up_read(&vcpu->kvm->slots_lock);
                 if (r == EMULATE_DO_MMIO) {
@@ -3808,12 +4083,11 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
                         goto out;
                 }
         }
-#endif
         if (kvm_run->exit_reason == KVM_EXIT_HYPERCALL)
                 kvm_register_write(vcpu, VCPU_REGS_RAX,
                                      kvm_run->hypercall.ret);
 
-        r = __vcpu_run(vcpu, kvm_run);
+        r = __vcpu_run(vcpu);
 
 out:
         if (vcpu->sigset_active)
@@ -3847,13 +4121,7 @@ int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 #endif
 
         regs->rip = kvm_rip_read(vcpu);
-        regs->rflags = kvm_x86_ops->get_rflags(vcpu);
-
-        /*
-         * Don't leak debug flags in case they were set for guest debugging
-         */
-        if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)
-                regs->rflags &= ~(X86_EFLAGS_TF | X86_EFLAGS_RF);
+        regs->rflags = kvm_get_rflags(vcpu);
 
         vcpu_put(vcpu);
 
@@ -3881,12 +4149,10 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
         kvm_register_write(vcpu, VCPU_REGS_R13, regs->r13);
         kvm_register_write(vcpu, VCPU_REGS_R14, regs->r14);
         kvm_register_write(vcpu, VCPU_REGS_R15, regs->r15);
-
 #endif
 
         kvm_rip_write(vcpu, regs->rip);
-        kvm_x86_ops->set_rflags(vcpu, regs->rflags);
-
+        kvm_set_rflags(vcpu, regs->rflags);
 
         vcpu->arch.exception.pending = false;
 
@@ -4105,7 +4371,7 @@ static int is_vm86_segment(struct kvm_vcpu *vcpu, int seg)
 {
         return (seg != VCPU_SREG_LDTR) &&
                 (seg != VCPU_SREG_TR) &&
-                (kvm_x86_ops->get_rflags(vcpu) & X86_EFLAGS_VM);
+                (kvm_get_rflags(vcpu) & X86_EFLAGS_VM);
 }
 
 int kvm_load_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector,
@@ -4133,7 +4399,7 @@ static void save_state_to_tss32(struct kvm_vcpu *vcpu,
 {
         tss->cr3 = vcpu->arch.cr3;
         tss->eip = kvm_rip_read(vcpu);
-        tss->eflags = kvm_x86_ops->get_rflags(vcpu);
+        tss->eflags = kvm_get_rflags(vcpu);
         tss->eax = kvm_register_read(vcpu, VCPU_REGS_RAX);
         tss->ecx = kvm_register_read(vcpu, VCPU_REGS_RCX);
         tss->edx = kvm_register_read(vcpu, VCPU_REGS_RDX);
@@ -4157,7 +4423,7 @@ static int load_state_from_tss32(struct kvm_vcpu *vcpu,
         kvm_set_cr3(vcpu, tss->cr3);
 
         kvm_rip_write(vcpu, tss->eip);
-        kvm_x86_ops->set_rflags(vcpu, tss->eflags | 2);
+        kvm_set_rflags(vcpu, tss->eflags | 2);
 
         kvm_register_write(vcpu, VCPU_REGS_RAX, tss->eax);
         kvm_register_write(vcpu, VCPU_REGS_RCX, tss->ecx);
@@ -4195,7 +4461,7 @@ static void save_state_to_tss16(struct kvm_vcpu *vcpu,
                                 struct tss_segment_16 *tss)
 {
         tss->ip = kvm_rip_read(vcpu);
-        tss->flag = kvm_x86_ops->get_rflags(vcpu);
+        tss->flag = kvm_get_rflags(vcpu);
         tss->ax = kvm_register_read(vcpu, VCPU_REGS_RAX);
         tss->cx = kvm_register_read(vcpu, VCPU_REGS_RCX);
         tss->dx = kvm_register_read(vcpu, VCPU_REGS_RDX);
@@ -4210,14 +4476,13 @@ static void save_state_to_tss16(struct kvm_vcpu *vcpu,
         tss->ss = get_segment_selector(vcpu, VCPU_SREG_SS);
         tss->ds = get_segment_selector(vcpu, VCPU_SREG_DS);
         tss->ldt = get_segment_selector(vcpu, VCPU_SREG_LDTR);
-        tss->prev_task_link = get_segment_selector(vcpu, VCPU_SREG_TR);
 }
 
 static int load_state_from_tss16(struct kvm_vcpu *vcpu,
                                  struct tss_segment_16 *tss)
 {
         kvm_rip_write(vcpu, tss->ip);
-        kvm_x86_ops->set_rflags(vcpu, tss->flag | 2);
+        kvm_set_rflags(vcpu, tss->flag | 2);
         kvm_register_write(vcpu, VCPU_REGS_RAX, tss->ax);
         kvm_register_write(vcpu, VCPU_REGS_RCX, tss->cx);
         kvm_register_write(vcpu, VCPU_REGS_RDX, tss->dx);
@@ -4363,8 +4628,8 @@ int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason)
         }
 
         if (reason == TASK_SWITCH_IRET) {
-                u32 eflags = kvm_x86_ops->get_rflags(vcpu);
-                kvm_x86_ops->set_rflags(vcpu, eflags & ~X86_EFLAGS_NT);
+                u32 eflags = kvm_get_rflags(vcpu);
+                kvm_set_rflags(vcpu, eflags & ~X86_EFLAGS_NT);
         }
 
         /* set back link to prev task only if NT bit is set in eflags
@@ -4372,11 +4637,6 @@ int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason)
         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_sel,
                                          old_tss_base, &nseg_desc);
@@ -4385,8 +4645,8 @@ int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason)
                                          old_tss_base, &nseg_desc);
 
         if (reason == TASK_SWITCH_CALL || reason == TASK_SWITCH_GATE) {
-                u32 eflags = kvm_x86_ops->get_rflags(vcpu);
-                kvm_x86_ops->set_rflags(vcpu, eflags | X86_EFLAGS_NT);
+                u32 eflags = kvm_get_rflags(vcpu);
+                kvm_set_rflags(vcpu, eflags | X86_EFLAGS_NT);
         }
 
         if (reason != TASK_SWITCH_IRET) {
@@ -4438,8 +4698,10 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
 
         mmu_reset_needed |= vcpu->arch.cr4 != sregs->cr4;
         kvm_x86_ops->set_cr4(vcpu, sregs->cr4);
-        if (!is_long_mode(vcpu) && is_pae(vcpu))
+        if (!is_long_mode(vcpu) && is_pae(vcpu)) {
                 load_pdptrs(vcpu, vcpu->arch.cr3);
+                mmu_reset_needed = 1;
+        }
 
         if (mmu_reset_needed)
                 kvm_mmu_reset_context(vcpu);
@@ -4480,12 +4742,32 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
 int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
                                         struct kvm_guest_debug *dbg)
 {
+        unsigned long rflags;
         int i, r;
 
         vcpu_load(vcpu);
 
-        if ((dbg->control & (KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_HW_BP)) ==
-            (KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_HW_BP)) {
+        if (dbg->control & (KVM_GUESTDBG_INJECT_DB | KVM_GUESTDBG_INJECT_BP)) {
+                r = -EBUSY;
+                if (vcpu->arch.exception.pending)
+                        goto unlock_out;
+                if (dbg->control & KVM_GUESTDBG_INJECT_DB)
+                        kvm_queue_exception(vcpu, DB_VECTOR);
+                else
+                        kvm_queue_exception(vcpu, BP_VECTOR);
+        }
+
+        /*
+         * Read rflags as long as potentially injected trace flags are still
+         * filtered out.
+         */
+        rflags = kvm_get_rflags(vcpu);
+
+        vcpu->guest_debug = dbg->control;
+        if (!(vcpu->guest_debug & KVM_GUESTDBG_ENABLE))
+                vcpu->guest_debug = 0;
+
+        if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) {
                 for (i = 0; i < KVM_NR_DB_REGS; ++i)
                         vcpu->arch.eff_db[i] = dbg->arch.debugreg[i];
                 vcpu->arch.switch_db_regs =
@@ -4496,13 +4778,23 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
                 vcpu->arch.switch_db_regs = (vcpu->arch.dr7 & DR7_BP_EN_MASK);
         }
 
-        r = kvm_x86_ops->set_guest_debug(vcpu, dbg);
+        if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) {
+                vcpu->arch.singlestep_cs =
+                        get_segment_selector(vcpu, VCPU_SREG_CS);
+                vcpu->arch.singlestep_rip = kvm_rip_read(vcpu);
+        }
+
+        /*
+         * Trigger an rflags update that will inject or remove the trace
+         * flags.
+         */
+        kvm_set_rflags(vcpu, rflags);
+
+        kvm_x86_ops->set_guest_debug(vcpu, dbg);
 
-        if (dbg->control & KVM_GUESTDBG_INJECT_DB)
-                kvm_queue_exception(vcpu, DB_VECTOR);
-        else if (dbg->control & KVM_GUESTDBG_INJECT_BP)
-                kvm_queue_exception(vcpu, BP_VECTOR);
+        r = 0;
 
+unlock_out:
         vcpu_put(vcpu);
 
         return r;
@@ -4703,14 +4995,26 @@ int kvm_arch_vcpu_reset(struct kvm_vcpu *vcpu)
         return kvm_x86_ops->vcpu_reset(vcpu);
 }
 
-void kvm_arch_hardware_enable(void *garbage)
+int kvm_arch_hardware_enable(void *garbage)
 {
-        kvm_x86_ops->hardware_enable(garbage);
+        /*
+         * Since this may be called from a hotplug notifcation,
+         * we can't get the CPU frequency directly.
+         */
+        if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) {
+                int cpu = raw_smp_processor_id();
+                per_cpu(cpu_tsc_khz, cpu) = 0;
+        }
+
+        kvm_shared_msr_cpu_online();
+
+        return kvm_x86_ops->hardware_enable(garbage);
 }
 
 void kvm_arch_hardware_disable(void *garbage)
 {
         kvm_x86_ops->hardware_disable(garbage);
+        drop_user_return_notifiers(garbage);
 }
 
 int kvm_arch_hardware_setup(void)
@@ -4948,8 +5252,36 @@ int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu)
         return kvm_x86_ops->interrupt_allowed(vcpu);
 }
 
+unsigned long kvm_get_rflags(struct kvm_vcpu *vcpu)
+{
+        unsigned long rflags;
+
+        rflags = kvm_x86_ops->get_rflags(vcpu);
+        if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)
+                rflags &= ~(unsigned long)(X86_EFLAGS_TF | X86_EFLAGS_RF);
+        return rflags;
+}
+EXPORT_SYMBOL_GPL(kvm_get_rflags);
+
+void kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags)
+{
+        if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP &&
+            vcpu->arch.singlestep_cs ==
+                        get_segment_selector(vcpu, VCPU_SREG_CS) &&
+            vcpu->arch.singlestep_rip == kvm_rip_read(vcpu))
+                rflags |= X86_EFLAGS_TF | X86_EFLAGS_RF;
+        kvm_x86_ops->set_rflags(vcpu, rflags);
+}
+EXPORT_SYMBOL_GPL(kvm_set_rflags);
+
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_exit);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_inj_virq);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_page_fault);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_msr);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_cr);
+EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_vmrun);
+EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_vmexit);
+EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_vmexit_inject);
+EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_intr_vmexit);
+EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_invlpga);
+EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_skinit);