KVM: x86: do mask out upper bits of PAE CR3

[karo-tx-linux.git] / arch / x86 / kvm / x86.c

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 6c7266f7766dcb6ec02b13b9b1439c9f9d547071..6c97c82814c45a2412da6e28b4393606da450bb3 100644 (file)
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -134,8 +134,6 @@ module_param(lapic_timer_advance_ns, uint, S_IRUGO | S_IWUSR);
 static bool __read_mostly vector_hashing = true;
 module_param(vector_hashing, bool, S_IRUGO);
 
-static bool __read_mostly backwards_tsc_observed = false;
-
 #define KVM_NR_SHARED_MSRS 16
 
 struct kvm_shared_msrs_global {
@@ -452,7 +450,12 @@ EXPORT_SYMBOL_GPL(kvm_complete_insn_gp);
 void kvm_inject_page_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault)
 {
        ++vcpu->stat.pf_guest;
-       vcpu->arch.cr2 = fault->address;
+       vcpu->arch.exception.nested_apf =
+               is_guest_mode(vcpu) && fault->async_page_fault;
+       if (vcpu->arch.exception.nested_apf)
+               vcpu->arch.apf.nested_apf_token = fault->address;
+       else
+               vcpu->arch.cr2 = fault->address;
        kvm_queue_exception_e(vcpu, PF_VECTOR, fault->error_code);
 }
 EXPORT_SYMBOL_GPL(kvm_inject_page_fault);
@@ -594,8 +597,8 @@ bool pdptrs_changed(struct kvm_vcpu *vcpu)
                      (unsigned long *)&vcpu->arch.regs_avail))
                return true;
 
-       gfn = (kvm_read_cr3(vcpu) & ~31u) >> PAGE_SHIFT;
-       offset = (kvm_read_cr3(vcpu) & ~31u) & (PAGE_SIZE - 1);
+       gfn = (kvm_read_cr3(vcpu) & 0xffffffe0ul) >> PAGE_SHIFT;
+       offset = (kvm_read_cr3(vcpu) & 0xffffffe0ul) & (PAGE_SIZE - 1);
        r = kvm_read_nested_guest_page(vcpu, gfn, pdpte, offset, sizeof(pdpte),
                                       PFERR_USER_MASK | PFERR_WRITE_MASK);
        if (r < 0)
@@ -1719,7 +1722,7 @@ static void pvclock_update_vm_gtod_copy(struct kvm *kvm)
                                        &ka->master_cycle_now);
 
        ka->use_master_clock = host_tsc_clocksource && vcpus_matched
-                               && !backwards_tsc_observed
+                               && !ka->backwards_tsc_observed
                                && !ka->boot_vcpu_runs_old_kvmclock;
 
        if (ka->use_master_clock)
@@ -2060,8 +2063,8 @@ static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data)
 {
        gpa_t gpa = data & ~0x3f;
 
-       /* Bits 2:5 are reserved, Should be zero */
-       if (data & 0x3c)
+       /* Bits 3:5 are reserved, Should be zero */
+       if (data & 0x38)
                return 1;
 
        vcpu->arch.apf.msr_val = data;
@@ -2077,6 +2080,7 @@ static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data)
                return 1;
 
        vcpu->arch.apf.send_user_only = !(data & KVM_ASYNC_PF_SEND_ALWAYS);
+       vcpu->arch.apf.delivery_as_pf_vmexit = data & KVM_ASYNC_PF_DELIVERY_AS_PF_VMEXIT;
        kvm_async_pf_wakeup_all(vcpu);
        return 0;
 }
@@ -2661,6 +2665,8 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
        case KVM_CAP_HYPERV_VAPIC:
        case KVM_CAP_HYPERV_SPIN:
        case KVM_CAP_HYPERV_SYNIC:
+       case KVM_CAP_HYPERV_SYNIC2:
+       case KVM_CAP_HYPERV_VP_INDEX:
        case KVM_CAP_PCI_SEGMENT:
        case KVM_CAP_DEBUGREGS:
        case KVM_CAP_X86_ROBUST_SINGLESTEP:
@@ -3384,10 +3390,14 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
                return -EINVAL;
 
        switch (cap->cap) {
+       case KVM_CAP_HYPERV_SYNIC2:
+               if (cap->args[0])
+                       return -EINVAL;
        case KVM_CAP_HYPERV_SYNIC:
                if (!irqchip_in_kernel(vcpu->kvm))
                        return -EINVAL;
-               return kvm_hv_activate_synic(vcpu);
+               return kvm_hv_activate_synic(vcpu, cap->cap ==
+                                            KVM_CAP_HYPERV_SYNIC2);
        default:
                return -EINVAL;
        }
@@ -4188,9 +4198,15 @@ long kvm_arch_vm_ioctl(struct file *filp,
                        goto out;
 
                r = 0;
+               /*
+                * TODO: userspace has to take care of races with VCPU_RUN, so
+                * kvm_gen_update_masterclock() can be cut down to locked
+                * pvclock_update_vm_gtod_copy().
+                */
+               kvm_gen_update_masterclock(kvm);
                now_ns = get_kvmclock_ns(kvm);
                kvm->arch.kvmclock_offset += user_ns.clock - now_ns;
-               kvm_gen_update_masterclock(kvm);
+               kvm_make_all_cpus_request(kvm, KVM_REQ_CLOCK_UPDATE);
                break;
        }
        case KVM_GET_CLOCK: {
@@ -6347,10 +6363,7 @@ static int inject_pending_event(struct kvm_vcpu *vcpu, bool req_int_win)
                        kvm_update_dr7(vcpu);
                }
 
-               kvm_x86_ops->queue_exception(vcpu, vcpu->arch.exception.nr,
-                                         vcpu->arch.exception.has_error_code,
-                                         vcpu->arch.exception.error_code,
-                                         vcpu->arch.exception.reinject);
+               kvm_x86_ops->queue_exception(vcpu);
                return 0;
        }
 
@@ -7676,6 +7689,8 @@ void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
        struct msr_data msr;
        struct kvm *kvm = vcpu->kvm;
 
+       kvm_hv_vcpu_postcreate(vcpu);
+
        if (vcpu_load(vcpu))
                return;
        msr.data = 0x0;
@@ -7829,8 +7844,8 @@ int kvm_arch_hardware_enable(void)
         */
        if (backwards_tsc) {
                u64 delta_cyc = max_tsc - local_tsc;
-               backwards_tsc_observed = true;
                list_for_each_entry(kvm, &vm_list, vm_list) {
+                       kvm->arch.backwards_tsc_observed = true;
                        kvm_for_each_vcpu(i, vcpu, kvm) {
                                vcpu->arch.tsc_offset_adjustment += delta_cyc;
                                vcpu->arch.last_host_tsc = local_tsc;
@@ -8576,6 +8591,7 @@ void kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu,
                fault.error_code = 0;
                fault.nested_page_fault = false;
                fault.address = work->arch.token;
+               fault.async_page_fault = true;
                kvm_inject_page_fault(vcpu, &fault);
        }
 }
@@ -8598,6 +8614,7 @@ void kvm_arch_async_page_present(struct kvm_vcpu *vcpu,
                fault.error_code = 0;
                fault.nested_page_fault = false;
                fault.address = work->arch.token;
+               fault.async_page_fault = true;
                kvm_inject_page_fault(vcpu, &fault);
        }
        vcpu->arch.apf.halted = false;