KVM: VMX: modify preemption timer bit only when arming timer

Provide a singular location where the VMX preemption timer bit is
set/cleared so that future usages of the preemption timer can ensure
the VMCS bit is up-to-date without having to modify unrelated code
paths.  For example, the preemption timer can be used to force an
immediate VMExit.  Cache the status of the timer to avoid redundant
VMREAD and VMWRITE, e.g. if the timer stays armed across multiple
VMEnters/VMExits.

Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 4655d6dd6759126d41db15f6caa08986ace5464a..62670b2f6d487308cdd315250213c4fab762f352 100644 (file)
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -397,6 +397,7 @@ struct loaded_vmcs {
        int cpu;
        bool launched;
        bool nmi_known_unmasked;
+       bool hv_timer_armed;
        /* Support for vnmi-less CPUs */
        int soft_vnmi_blocked;
        ktime_t entry_time;
@@ -10595,24 +10596,38 @@ static void atomic_switch_perf_msrs(struct vcpu_vmx *vmx)
                                        msrs[i].host, false);
 }
 
-static void vmx_arm_hv_timer(struct kvm_vcpu *vcpu)
+static void vmx_arm_hv_timer(struct vcpu_vmx *vmx, u32 val)
+{
+       vmcs_write32(VMX_PREEMPTION_TIMER_VALUE, val);
+       if (!vmx->loaded_vmcs->hv_timer_armed)
+               vmcs_set_bits(PIN_BASED_VM_EXEC_CONTROL,
+                             PIN_BASED_VMX_PREEMPTION_TIMER);
+       vmx->loaded_vmcs->hv_timer_armed = true;
+}
+
+static void vmx_update_hv_timer(struct kvm_vcpu *vcpu)
 {
        struct vcpu_vmx *vmx = to_vmx(vcpu);
        u64 tscl;
        u32 delta_tsc;
 
-       if (vmx->hv_deadline_tsc == -1)
-               return;
+       if (vmx->hv_deadline_tsc != -1) {
+               tscl = rdtsc();
+               if (vmx->hv_deadline_tsc > tscl)
+                       /* set_hv_timer ensures the delta fits in 32-bits */
+                       delta_tsc = (u32)((vmx->hv_deadline_tsc - tscl) >>
+                               cpu_preemption_timer_multi);
+               else
+                       delta_tsc = 0;
 
-       tscl = rdtsc();
-       if (vmx->hv_deadline_tsc > tscl)
-               /* sure to be 32 bit only because checked on set_hv_timer */
-               delta_tsc = (u32)((vmx->hv_deadline_tsc - tscl) >>
-                       cpu_preemption_timer_multi);
-       else
-               delta_tsc = 0;
+               vmx_arm_hv_timer(vmx, delta_tsc);
+               return;
+       }
 
-       vmcs_write32(VMX_PREEMPTION_TIMER_VALUE, delta_tsc);
+       if (vmx->loaded_vmcs->hv_timer_armed)
+               vmcs_clear_bits(PIN_BASED_VM_EXEC_CONTROL,
+                               PIN_BASED_VMX_PREEMPTION_TIMER);
+       vmx->loaded_vmcs->hv_timer_armed = false;
 }
 
 static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
@@ -10672,7 +10687,7 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
 
        atomic_switch_perf_msrs(vmx);
 
-       vmx_arm_hv_timer(vcpu);
+       vmx_update_hv_timer(vcpu);
 
        /*
         * If this vCPU has touched SPEC_CTRL, restore the guest's value if
@@ -12078,11 +12093,10 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 
        exec_control = vmcs12->pin_based_vm_exec_control;
 
-       /* Preemption timer setting is only taken from vmcs01.  */
-       exec_control &= ~PIN_BASED_VMX_PREEMPTION_TIMER;
+       /* Preemption timer setting is computed directly in vmx_vcpu_run.  */
        exec_control |= vmcs_config.pin_based_exec_ctrl;
-       if (vmx->hv_deadline_tsc == -1)
-               exec_control &= ~PIN_BASED_VMX_PREEMPTION_TIMER;
+       exec_control &= ~PIN_BASED_VMX_PREEMPTION_TIMER;
+       vmx->loaded_vmcs->hv_timer_armed = false;
 
        /* Posted interrupts setting is only taken from vmcs12.  */
        if (nested_cpu_has_posted_intr(vmcs12)) {
@@ -13255,12 +13269,7 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
        vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr);
        vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.guest.nr);
        vmcs_write64(TSC_OFFSET, vcpu->arch.tsc_offset);
-       if (vmx->hv_deadline_tsc == -1)
-               vmcs_clear_bits(PIN_BASED_VM_EXEC_CONTROL,
-                               PIN_BASED_VMX_PREEMPTION_TIMER);
-       else
-               vmcs_set_bits(PIN_BASED_VM_EXEC_CONTROL,
-                             PIN_BASED_VMX_PREEMPTION_TIMER);
+
        if (kvm_has_tsc_control)
                decache_tsc_multiplier(vmx);
 
@@ -13464,18 +13473,12 @@ static int vmx_set_hv_timer(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc)
                return -ERANGE;
 
        vmx->hv_deadline_tsc = tscl + delta_tsc;
-       vmcs_set_bits(PIN_BASED_VM_EXEC_CONTROL,
-                       PIN_BASED_VMX_PREEMPTION_TIMER);
-
        return delta_tsc == 0;
 }
 
 static void vmx_cancel_hv_timer(struct kvm_vcpu *vcpu)
 {
-       struct vcpu_vmx *vmx = to_vmx(vcpu);
-       vmx->hv_deadline_tsc = -1;
-       vmcs_clear_bits(PIN_BASED_VM_EXEC_CONTROL,
-                       PIN_BASED_VMX_PREEMPTION_TIMER);
+       to_vmx(vcpu)->hv_deadline_tsc = -1;
 }
 #endif