1 files changed, 88 insertions, 41 deletions

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 506bd2b4b8bb..edbf00ec56b3 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -628,7 +628,7 @@ bool pdptrs_changed(struct kvm_vcpu *vcpu)
         gfn_t gfn;
         int r;
 
-        if (is_long_mode(vcpu) || !is_pae(vcpu))
+        if (is_long_mode(vcpu) || !is_pae(vcpu) || !is_paging(vcpu))
                 return false;
 
         if (!test_bit(VCPU_EXREG_PDPTR,
@@ -2537,7 +2537,6 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
                 break;
         case MSR_PLATFORM_INFO:
                 if (!msr_info->host_initiated ||
-                    data & ~MSR_PLATFORM_INFO_CPUID_FAULT ||
                     (!(data & MSR_PLATFORM_INFO_CPUID_FAULT) &&
                      cpuid_fault_enabled(vcpu)))
                         return 1;
@@ -2780,6 +2779,9 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
                 msr_info->data = vcpu->arch.osvw.status;
                 break;
         case MSR_PLATFORM_INFO:
+                if (!msr_info->host_initiated &&
+                    !vcpu->kvm->arch.guest_can_read_msr_platform_info)
+                        return 1;
                 msr_info->data = vcpu->arch.msr_platform_info;
                 break;
         case MSR_MISC_FEATURES_ENABLES:
@@ -2927,6 +2929,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
         case KVM_CAP_SPLIT_IRQCHIP:
         case KVM_CAP_IMMEDIATE_EXIT:
         case KVM_CAP_GET_MSR_FEATURES:
+        case KVM_CAP_MSR_PLATFORM_INFO:
                 r = 1;
                 break;
         case KVM_CAP_SYNC_REGS:
@@ -4007,19 +4010,23 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
                         break;
 
                 BUILD_BUG_ON(sizeof(user_data_size) != sizeof(user_kvm_nested_state->size));
+                r = -EFAULT;
                 if (get_user(user_data_size, &user_kvm_nested_state->size))
-                        return -EFAULT;
+                        break;
 
                 r = kvm_x86_ops->get_nested_state(vcpu, user_kvm_nested_state,
                                                   user_data_size);
                 if (r < 0)
-                        return r;
+                        break;
 
                 if (r > user_data_size) {
                         if (put_user(r, &user_kvm_nested_state->size))
-                                return -EFAULT;
-                        return -E2BIG;
+                                r = -EFAULT;
+                        else
+                                r = -E2BIG;
+                        break;
                 }
+
                 r = 0;
                 break;
         }
@@ -4031,19 +4038,21 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
                 if (!kvm_x86_ops->set_nested_state)
                         break;
 
+                r = -EFAULT;
                 if (copy_from_user(&kvm_state, user_kvm_nested_state, sizeof(kvm_state)))
-                        return -EFAULT;
+                        break;
 
+                r = -EINVAL;
                 if (kvm_state.size < sizeof(kvm_state))
-                        return -EINVAL;
+                        break;
 
                 if (kvm_state.flags &
                     ~(KVM_STATE_NESTED_RUN_PENDING | KVM_STATE_NESTED_GUEST_MODE))
-                        return -EINVAL;
+                        break;
 
                 /* nested_run_pending implies guest_mode.  */
                 if (kvm_state.flags == KVM_STATE_NESTED_RUN_PENDING)
-                        return -EINVAL;
+                        break;
 
                 r = kvm_x86_ops->set_nested_state(vcpu, user_kvm_nested_state, &kvm_state);
                 break;
@@ -4350,6 +4359,10 @@ split_irqchip_unlock:
                         kvm->arch.pause_in_guest = true;
                 r = 0;
                 break;
+        case KVM_CAP_MSR_PLATFORM_INFO:
+                kvm->arch.guest_can_read_msr_platform_info = cap->args[0];
+                r = 0;
+                break;
         default:
                 r = -EINVAL;
                 break;
@@ -4987,7 +5000,7 @@ int handle_ud(struct kvm_vcpu *vcpu)
                 emul_type = 0;
         }
 
-        er = emulate_instruction(vcpu, emul_type);
+        er = kvm_emulate_instruction(vcpu, emul_type);
         if (er == EMULATE_USER_EXIT)
                 return 0;
         if (er != EMULATE_DONE)
@@ -5870,7 +5883,10 @@ static bool reexecute_instruction(struct kvm_vcpu *vcpu, gva_t cr2,
         gpa_t gpa = cr2;
         kvm_pfn_t pfn;
 
-        if (emulation_type & EMULTYPE_NO_REEXECUTE)
+        if (!(emulation_type & EMULTYPE_ALLOW_RETRY))
+                return false;
+
+        if (WARN_ON_ONCE(is_guest_mode(vcpu)))
                 return false;
 
         if (!vcpu->arch.mmu.direct_map) {
@@ -5958,7 +5974,10 @@ static bool retry_instruction(struct x86_emulate_ctxt *ctxt,
          */
         vcpu->arch.last_retry_eip = vcpu->arch.last_retry_addr = 0;
 
-        if (!(emulation_type & EMULTYPE_RETRY))
+        if (!(emulation_type & EMULTYPE_ALLOW_RETRY))
+                return false;
+
+        if (WARN_ON_ONCE(is_guest_mode(vcpu)))
                 return false;
 
         if (x86_page_table_writing_insn(ctxt))
@@ -6276,7 +6295,19 @@ restart:
 
         return r;
 }
-EXPORT_SYMBOL_GPL(x86_emulate_instruction);
+
+int kvm_emulate_instruction(struct kvm_vcpu *vcpu, int emulation_type)
+{
+        return x86_emulate_instruction(vcpu, 0, emulation_type, NULL, 0);
+}
+EXPORT_SYMBOL_GPL(kvm_emulate_instruction);
+
+int kvm_emulate_instruction_from_buffer(struct kvm_vcpu *vcpu,
+                                        void *insn, int insn_len)
+{
+        return x86_emulate_instruction(vcpu, 0, 0, insn, insn_len);
+}
+EXPORT_SYMBOL_GPL(kvm_emulate_instruction_from_buffer);
 
 static int kvm_fast_pio_out(struct kvm_vcpu *vcpu, int size,
                             unsigned short port)
@@ -7343,6 +7374,12 @@ void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu)
 }
 EXPORT_SYMBOL_GPL(kvm_vcpu_reload_apic_access_page);
 
+void __kvm_request_immediate_exit(struct kvm_vcpu *vcpu)
+{
+        smp_send_reschedule(vcpu->cpu);
+}
+EXPORT_SYMBOL_GPL(__kvm_request_immediate_exit);
+
 /*
  * Returns 1 to let vcpu_run() continue the guest execution loop without
  * exiting to the userspace.  Otherwise, the value will be returned to the
@@ -7547,7 +7584,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 
         if (req_immediate_exit) {
                 kvm_make_request(KVM_REQ_EVENT, vcpu);
-                smp_send_reschedule(vcpu->cpu);
+                kvm_x86_ops->request_immediate_exit(vcpu);
         }
 
         trace_kvm_entry(vcpu->vcpu_id);
@@ -7734,7 +7771,7 @@ static inline int complete_emulated_io(struct kvm_vcpu *vcpu)
 {
         int r;
         vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
-        r = emulate_instruction(vcpu, EMULTYPE_NO_DECODE);
+        r = kvm_emulate_instruction(vcpu, EMULTYPE_NO_DECODE);
         srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
         if (r != EMULATE_DONE)
                 return 0;
@@ -7811,6 +7848,29 @@ static int complete_emulated_mmio(struct kvm_vcpu *vcpu)
         return 0;
 }
 
+/* Swap (qemu) user FPU context for the guest FPU context. */
+static void kvm_load_guest_fpu(struct kvm_vcpu *vcpu)
+{
+        preempt_disable();
+        copy_fpregs_to_fpstate(&vcpu->arch.user_fpu);
+        /* PKRU is separately restored in kvm_x86_ops->run.  */
+        __copy_kernel_to_fpregs(&vcpu->arch.guest_fpu.state,
+                                ~XFEATURE_MASK_PKRU);
+        preempt_enable();
+        trace_kvm_fpu(1);
+}
+
+/* When vcpu_run ends, restore user space FPU context. */
+static void kvm_put_guest_fpu(struct kvm_vcpu *vcpu)
+{
+        preempt_disable();
+        copy_fpregs_to_fpstate(&vcpu->arch.guest_fpu);
+        copy_kernel_to_fpregs(&vcpu->arch.user_fpu.state);
+        preempt_enable();
+        ++vcpu->stat.fpu_reload;
+        trace_kvm_fpu(0);
+}
+
 int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 {
         int r;
@@ -8159,7 +8219,7 @@ static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
                 kvm_update_cpuid(vcpu);
 
         idx = srcu_read_lock(&vcpu->kvm->srcu);
-        if (!is_long_mode(vcpu) && is_pae(vcpu)) {
+        if (!is_long_mode(vcpu) && is_pae(vcpu) && is_paging(vcpu)) {
                 load_pdptrs(vcpu, vcpu->arch.walk_mmu, kvm_read_cr3(vcpu));
                 mmu_reset_needed = 1;
         }
@@ -8388,29 +8448,6 @@ static void fx_init(struct kvm_vcpu *vcpu)
         vcpu->arch.cr0 |= X86_CR0_ET;
 }
 
-/* Swap (qemu) user FPU context for the guest FPU context. */
-void kvm_load_guest_fpu(struct kvm_vcpu *vcpu)
-{
-        preempt_disable();
-        copy_fpregs_to_fpstate(&vcpu->arch.user_fpu);
-        /* PKRU is separately restored in kvm_x86_ops->run.  */
-        __copy_kernel_to_fpregs(&vcpu->arch.guest_fpu.state,
-                                ~XFEATURE_MASK_PKRU);
-        preempt_enable();
-        trace_kvm_fpu(1);
-}
-
-/* When vcpu_run ends, restore user space FPU context. */
-void kvm_put_guest_fpu(struct kvm_vcpu *vcpu)
-{
-        preempt_disable();
-        copy_fpregs_to_fpstate(&vcpu->arch.guest_fpu);
-        copy_kernel_to_fpregs(&vcpu->arch.user_fpu.state);
-        preempt_enable();
-        ++vcpu->stat.fpu_reload;
-        trace_kvm_fpu(0);
-}
-
 void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu)
 {
         void *wbinvd_dirty_mask = vcpu->arch.wbinvd_dirty_mask;
@@ -8834,6 +8871,8 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
         kvm->arch.kvmclock_offset = -ktime_get_boot_ns();
         pvclock_update_vm_gtod_copy(kvm);
 
+        kvm->arch.guest_can_read_msr_platform_info = true;
+
         INIT_DELAYED_WORK(&kvm->arch.kvmclock_update_work, kvmclock_update_fn);
         INIT_DELAYED_WORK(&kvm->arch.kvmclock_sync_work, kvmclock_sync_fn);
 
@@ -9182,6 +9221,13 @@ void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
         kvm_page_track_flush_slot(kvm, slot);
 }
 
+static inline bool kvm_guest_apic_has_interrupt(struct kvm_vcpu *vcpu)
+{
+        return (is_guest_mode(vcpu) &&
+                        kvm_x86_ops->guest_apic_has_interrupt &&
+                        kvm_x86_ops->guest_apic_has_interrupt(vcpu));
+}
+
 static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu)
 {
         if (!list_empty_careful(&vcpu->async_pf.done))
@@ -9206,7 +9252,8 @@ static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu)
                 return true;
 
         if (kvm_arch_interrupt_allowed(vcpu) &&
-            kvm_cpu_has_interrupt(vcpu))
+            (kvm_cpu_has_interrupt(vcpu) ||
+            kvm_guest_apic_has_interrupt(vcpu)))
                 return true;
 
         if (kvm_hv_has_stimer_pending(vcpu))