KVM: VMX: Save HOST_CR3 in vmx_set_host_fs_gs()

[linux-2.6-microblaze.git] / arch / x86 / kvm / vmx / vmx.c

diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 63615d2..ebf511f 100644 (file)
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -1069,9 +1069,14 @@ static void pt_guest_exit(struct vcpu_vmx *vmx)
                wrmsrl(MSR_IA32_RTIT_CTL, vmx->pt_desc.host.ctl);
 }
 
-void vmx_set_host_fs_gs(struct vmcs_host_state *host, u16 fs_sel, u16 gs_sel,
-                       unsigned long fs_base, unsigned long gs_base)
+void vmx_set_vmcs_host_state(struct vmcs_host_state *host, unsigned long cr3,
+                            u16 fs_sel, u16 gs_sel,
+                            unsigned long fs_base, unsigned long gs_base)
 {
+       if (unlikely(cr3 != host->cr3)) {
+               vmcs_writel(HOST_CR3, cr3);
+               host->cr3 = cr3;
+       }
        if (unlikely(fs_sel != host->fs_sel)) {
                if (!(fs_sel & 7))
                        vmcs_write16(HOST_FS_SELECTOR, fs_sel);
@@ -1103,7 +1108,6 @@ void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu)
 #ifdef CONFIG_X86_64
        int cpu = raw_smp_processor_id();
 #endif
-       unsigned long cr3;
        unsigned long fs_base, gs_base;
        u16 fs_sel, gs_sel;
        int i;
@@ -1167,14 +1171,8 @@ void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu)
        gs_base = segment_base(gs_sel);
 #endif
 
-       vmx_set_host_fs_gs(host_state, fs_sel, gs_sel, fs_base, gs_base);
-
-       /* Host CR3 including its PCID is stable when guest state is loaded. */
-       cr3 = __get_current_cr3_fast();
-       if (unlikely(cr3 != host_state->cr3)) {
-               vmcs_writel(HOST_CR3, cr3);
-               host_state->cr3 = cr3;
-       }
+       vmx_set_vmcs_host_state(host_state, __get_current_cr3_fast(),
+                               fs_sel, gs_sel, fs_base, gs_base);
 
        vmx->guest_state_loaded = true;
 }
@@ -1372,6 +1370,11 @@ void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags)
                vmx->emulation_required = vmx_emulation_required(vcpu);
 }
 
+static bool vmx_get_if_flag(struct kvm_vcpu *vcpu)
+{
+       return vmx_get_rflags(vcpu) & X86_EFLAGS_IF;
+}
+
 u32 vmx_get_interrupt_shadow(struct kvm_vcpu *vcpu)
 {
        u32 interruptibility = vmcs_read32(GUEST_INTERRUPTIBILITY_INFO);
@@ -3995,8 +3998,7 @@ static int vmx_deliver_posted_interrupt(struct kvm_vcpu *vcpu, int vector)
         * guaranteed to see PID.ON=1 and sync the PIR to IRR if triggering a
         * posted interrupt "fails" because vcpu->mode != IN_GUEST_MODE.
         */
-       if (vcpu != kvm_get_running_vcpu() &&
-           !kvm_vcpu_trigger_posted_interrupt(vcpu, false))
+       if (!kvm_vcpu_trigger_posted_interrupt(vcpu, false))
                kvm_vcpu_kick(vcpu);
 
        return 0;
@@ -5921,18 +5923,14 @@ static int __vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath)
                vmx_flush_pml_buffer(vcpu);
 
        /*
-        * We should never reach this point with a pending nested VM-Enter, and
-        * more specifically emulation of L2 due to invalid guest state (see
-        * below) should never happen as that means we incorrectly allowed a
-        * nested VM-Enter with an invalid vmcs12.
+        * KVM should never reach this point with a pending nested VM-Enter.
+        * More specifically, short-circuiting VM-Entry to emulate L2 due to
+        * invalid guest state should never happen as that means KVM knowingly
+        * allowed a nested VM-Enter with an invalid vmcs12.  More below.
         */
        if (KVM_BUG_ON(vmx->nested.nested_run_pending, vcpu->kvm))
                return -EIO;
 
-       /* If guest state is invalid, start emulating */
-       if (vmx->emulation_required)
-               return handle_invalid_guest_state(vcpu);
-
        if (is_guest_mode(vcpu)) {
                /*
                 * PML is never enabled when running L2, bail immediately if a
@@ -5954,10 +5952,30 @@ static int __vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath)
                 */
                nested_mark_vmcs12_pages_dirty(vcpu);
 
+               /*
+                * Synthesize a triple fault if L2 state is invalid.  In normal
+                * operation, nested VM-Enter rejects any attempt to enter L2
+                * with invalid state.  However, those checks are skipped if
+                * state is being stuffed via RSM or KVM_SET_NESTED_STATE.  If
+                * L2 state is invalid, it means either L1 modified SMRAM state
+                * or userspace provided bad state.  Synthesize TRIPLE_FAULT as
+                * doing so is architecturally allowed in the RSM case, and is
+                * the least awful solution for the userspace case without
+                * risking false positives.
+                */
+               if (vmx->emulation_required) {
+                       nested_vmx_vmexit(vcpu, EXIT_REASON_TRIPLE_FAULT, 0, 0);
+                       return 1;
+               }
+
                if (nested_vmx_reflect_vmexit(vcpu))
                        return 1;
        }
 
+       /* If guest state is invalid, start emulating.  L2 is handled above. */
+       if (vmx->emulation_required)
+               return handle_invalid_guest_state(vcpu);
+
        if (exit_reason.failed_vmentry) {
                dump_vmcs(vcpu);
                vcpu->run->exit_reason = KVM_EXIT_FAIL_ENTRY;
@@ -6652,9 +6670,7 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu)
         * consistency check VM-Exit due to invalid guest state and bail.
         */
        if (unlikely(vmx->emulation_required)) {
-
-               /* We don't emulate invalid state of a nested guest */
-               vmx->fail = is_guest_mode(vcpu);
+               vmx->fail = 0;
 
                vmx->exit_reason.full = EXIT_REASON_INVALID_STATE;
                vmx->exit_reason.failed_vmentry = 1;
@@ -7609,6 +7625,7 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = {
        .cache_reg = vmx_cache_reg,
        .get_rflags = vmx_get_rflags,
        .set_rflags = vmx_set_rflags,
+       .get_if_flag = vmx_get_if_flag,
 
        .tlb_flush_all = vmx_flush_tlb_all,
        .tlb_flush_current = vmx_flush_tlb_current,