cpufreq: Call transition notifier only once for each policy

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

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index a0d1fc80ac5a8407c123d8df12eb2215d4d70392..22cc90baa67fe673a8a28fa6112af00892f07f65 100644 (file)
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -136,10 +136,14 @@ EXPORT_SYMBOL_GPL(kvm_default_tsc_scaling_ratio);
 static u32 __read_mostly tsc_tolerance_ppm = 250;
 module_param(tsc_tolerance_ppm, uint, S_IRUGO | S_IWUSR);
 
-/* lapic timer advance (tscdeadline mode only) in nanoseconds */
-unsigned int __read_mostly lapic_timer_advance_ns = 1000;
+/*
+ * lapic timer advance (tscdeadline mode only) in nanoseconds.  '-1' enables
+ * adaptive tuning starting from default advancment of 1000ns.  '0' disables
+ * advancement entirely.  Any other value is used as-is and disables adaptive
+ * tuning, i.e. allows priveleged userspace to set an exact advancement time.
+ */
+static int __read_mostly lapic_timer_advance_ns = -1;
 module_param(lapic_timer_advance_ns, uint, S_IRUGO | S_IWUSR);
-EXPORT_SYMBOL_GPL(lapic_timer_advance_ns);
 
 static bool __read_mostly vector_hashing = true;
 module_param(vector_hashing, bool, S_IRUGO);
@@ -6535,6 +6539,12 @@ int kvm_emulate_instruction_from_buffer(struct kvm_vcpu *vcpu,
 }
 EXPORT_SYMBOL_GPL(kvm_emulate_instruction_from_buffer);
 
+static int complete_fast_pio_out_port_0x7e(struct kvm_vcpu *vcpu)
+{
+       vcpu->arch.pio.count = 0;
+       return 1;
+}
+
 static int complete_fast_pio_out(struct kvm_vcpu *vcpu)
 {
        vcpu->arch.pio.count = 0;
@@ -6551,12 +6561,23 @@ static int kvm_fast_pio_out(struct kvm_vcpu *vcpu, int size,
        unsigned long val = kvm_register_read(vcpu, VCPU_REGS_RAX);
        int ret = emulator_pio_out_emulated(&vcpu->arch.emulate_ctxt,
                                            size, port, &val, 1);
+       if (ret)
+               return ret;
 
-       if (!ret) {
+       /*
+        * Workaround userspace that relies on old KVM behavior of %rip being
+        * incremented prior to exiting to userspace to handle "OUT 0x7e".
+        */
+       if (port == 0x7e &&
+           kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_OUT_7E_INC_RIP)) {
+               vcpu->arch.complete_userspace_io =
+                       complete_fast_pio_out_port_0x7e;
+               kvm_skip_emulated_instruction(vcpu);
+       } else {
                vcpu->arch.pio.linear_rip = kvm_get_linear_rip(vcpu);
                vcpu->arch.complete_userspace_io = complete_fast_pio_out;
        }
-       return ret;
+       return 0;
 }
 
 static int complete_fast_pio_in(struct kvm_vcpu *vcpu)
@@ -6677,10 +6698,8 @@ static void kvm_hyperv_tsc_notifier(void)
 }
 #endif
 
-static int kvmclock_cpufreq_notifier(struct notifier_block *nb, unsigned long val,
-                                    void *data)
+static void __kvmclock_cpufreq_notifier(struct cpufreq_freqs *freq, int cpu)
 {
-       struct cpufreq_freqs *freq = data;
        struct kvm *kvm;
        struct kvm_vcpu *vcpu;
        int i, send_ipi = 0;
@@ -6724,17 +6743,12 @@ static int kvmclock_cpufreq_notifier(struct notifier_block *nb, unsigned long va
         *
         */
 
-       if (val == CPUFREQ_PRECHANGE && freq->old > freq->new)
-               return 0;
-       if (val == CPUFREQ_POSTCHANGE && freq->old < freq->new)
-               return 0;
-
-       smp_call_function_single(freq->cpu, tsc_khz_changed, freq, 1);
+       smp_call_function_single(cpu, tsc_khz_changed, freq, 1);
 
        spin_lock(&kvm_lock);
        list_for_each_entry(kvm, &vm_list, vm_list) {
                kvm_for_each_vcpu(i, vcpu, kvm) {
-                       if (vcpu->cpu != freq->cpu)
+                       if (vcpu->cpu != cpu)
                                continue;
                        kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
                        if (vcpu->cpu != smp_processor_id())
@@ -6756,8 +6770,24 @@ static int kvmclock_cpufreq_notifier(struct notifier_block *nb, unsigned long va
                 * guest context is entered kvmclock will be updated,
                 * so the guest will not see stale values.
                 */
-               smp_call_function_single(freq->cpu, tsc_khz_changed, freq, 1);
+               smp_call_function_single(cpu, tsc_khz_changed, freq, 1);
        }
+}
+
+static int kvmclock_cpufreq_notifier(struct notifier_block *nb, unsigned long val,
+                                    void *data)
+{
+       struct cpufreq_freqs *freq = data;
+       int cpu;
+
+       if (val == CPUFREQ_PRECHANGE && freq->old > freq->new)
+               return 0;
+       if (val == CPUFREQ_POSTCHANGE && freq->old < freq->new)
+               return 0;
+
+       for_each_cpu(cpu, freq->policy->cpus)
+               __kvmclock_cpufreq_notifier(freq, cpu);
+
        return 0;
 }
 
@@ -7873,7 +7903,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
        }
 
        trace_kvm_entry(vcpu->vcpu_id);
-       if (lapic_timer_advance_ns)
+       if (lapic_in_kernel(vcpu) &&
+           vcpu->arch.apic->lapic_timer.timer_advance_ns)
                wait_lapic_expire(vcpu);
        guest_enter_irqoff();
 
@@ -9061,7 +9092,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 
        if (irqchip_in_kernel(vcpu->kvm)) {
                vcpu->arch.apicv_active = kvm_x86_ops->get_enable_apicv(vcpu);
-               r = kvm_create_lapic(vcpu);
+               r = kvm_create_lapic(vcpu, lapic_timer_advance_ns);
                if (r < 0)
                        goto fail_mmu_destroy;
        } else