On 20/05/2016 03:45, Yunhong Jiang wrote:
> From: Yunhong Jiang <yunhong.jiang@xxxxxxxxx>
>
> Adding the basic VMX preemption timer functionality, including checking
> if the feature is supported, setup/clean the VMX preemption timer. Also
> adds a parameter to state if the VMX preemption timer should be utilized.
>
> Signed-off-by: Yunhong Jiang <yunhong.jiang@xxxxxxxxx>
> ---
> arch/x86/include/asm/kvm_host.h | 4 ++++
> arch/x86/kvm/lapic.c | 7 +++++++
> arch/x86/kvm/vmx.c | 45 ++++++++++++++++++++++++++++++++++++++++-
> 3 files changed, 55 insertions(+), 1 deletion(-)
>
> diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
> index 5e6b3ce7748f..8e58db20b3a4 100644
> --- a/arch/x86/include/asm/kvm_host.h
> +++ b/arch/x86/include/asm/kvm_host.h
> @@ -1006,6 +1006,10 @@ struct kvm_x86_ops {
> int (*update_pi_irte)(struct kvm *kvm, unsigned int host_irq,
> uint32_t guest_irq, bool set);
> void (*apicv_post_state_restore)(struct kvm_vcpu *vcpu);
> +
> + int (*hw_emul_timer)(struct kvm_vcpu *vcpu);
> + void (*set_hwemul_timer)(struct kvm_vcpu *vcpu, u64 tsc);
> + void (*clear_hwemul_timer)(struct kvm_vcpu *vcpu);
> };
>
> struct kvm_arch_async_pf {
> diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
> index bbb5b283ff63..8908ee514f6c 100644
> --- a/arch/x86/kvm/lapic.c
> +++ b/arch/x86/kvm/lapic.c
> @@ -256,6 +256,13 @@ static inline int apic_lvtt_tscdeadline(struct kvm_lapic *apic)
> return apic->lapic_timer.timer_mode == APIC_LVT_TIMER_TSCDEADLINE;
> }
>
> +static inline int hw_emul_timer(struct kvm_lapic *apic)
> +{
> + if (kvm_x86_ops->hw_emul_timer)
> + return kvm_x86_ops->hw_emul_timer(apic->vcpu);
> + return 0;
> +}
> +
> static inline int apic_lvt_nmi_mode(u32 lvt_val)
> {
> return (lvt_val & (APIC_MODE_MASK | APIC_LVT_MASKED)) == APIC_DM_NMI;
> diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
> index 9e078ff29f86..5475a7699ee5 100644
> --- a/arch/x86/kvm/vmx.c
> +++ b/arch/x86/kvm/vmx.c
> @@ -110,6 +110,9 @@ module_param_named(pml, enable_pml, bool, S_IRUGO);
>
> #define KVM_VMX_TSC_MULTIPLIER_MAX 0xffffffffffffffffULL
>
> +static bool __read_mostly hwemul_timer;
> +module_param_named(hwemul_timer, hwemul_timer, bool, S_IRUGO);
> +
> #define KVM_GUEST_CR0_MASK (X86_CR0_NW | X86_CR0_CD)
> #define KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST (X86_CR0_WP | X86_CR0_NE)
> #define KVM_VM_CR0_ALWAYS_ON \
> @@ -1056,6 +1059,20 @@ static inline bool cpu_has_vmx_virtual_intr_delivery(void)
> SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY;
> }
>
> +static inline bool cpu_has_preemption_timer(void)
> +{
> + return vmcs_config.pin_based_exec_ctrl &
> + PIN_BASED_VMX_PREEMPTION_TIMER;
> +}
> +
> +static inline int cpu_preemption_timer_multi(void)
> +{
> + u64 vmx_msr;
> +
> + rdmsrl(MSR_IA32_VMX_MISC, vmx_msr);
> + return vmx_msr & VMX_MISC_PREEMPTION_TIMER_RATE_MASK;
> +}
> +
> static inline bool cpu_has_vmx_posted_intr(void)
> {
> return IS_ENABLED(CONFIG_X86_LOCAL_APIC) &&
> @@ -3306,7 +3323,8 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf)
> return -EIO;
>
> min = PIN_BASED_EXT_INTR_MASK | PIN_BASED_NMI_EXITING;
> - opt = PIN_BASED_VIRTUAL_NMIS | PIN_BASED_POSTED_INTR;
> + opt = PIN_BASED_VIRTUAL_NMIS | PIN_BASED_POSTED_INTR |
> + PIN_BASED_VMX_PREEMPTION_TIMER;
> if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_PINBASED_CTLS,
> &_pin_based_exec_control) < 0)
> return -EIO;
> @@ -4779,6 +4797,8 @@ static u32 vmx_pin_based_exec_ctrl(struct vcpu_vmx *vmx)
>
> if (!kvm_vcpu_apicv_active(&vmx->vcpu))
> pin_based_exec_ctrl &= ~PIN_BASED_POSTED_INTR;
> + /* Enable the preemption timer dynamically */
> + pin_based_exec_ctrl &= ~PIN_BASED_VMX_PREEMPTION_TIMER;
> return pin_based_exec_ctrl;
> }
>
> @@ -10650,6 +10670,25 @@ static int vmx_check_intercept(struct kvm_vcpu *vcpu,
> return X86EMUL_CONTINUE;
> }
>
> +static int vmx_hwemul_timer(struct kvm_vcpu *vcpu)
> +{
> + return hwemul_timer && cpu_has_preemption_timer();
> +}
Please clear the vmx_x86_ops members instead if the preemption timer is
not usable. Then you can check kvm_x86_ops->set_hwemul_timer and
kvm_x86_ops->clear_hwemul_timer instead of calling this function.
For what it's worth, I prefer "vmx_{set,cancel}_hv_timer" instead.
> +static void vmx_set_hwemul_timer(struct kvm_vcpu *vcpu, u64 target_tsc)
This is not a target_tsc, it is a delta_tsc.
> +{
> + vmcs_write32(VMX_PREEMPTION_TIMER_VALUE,
> + target_tsc >> cpu_preemption_timer_multi());
Please cache the value of cpu_preemption_timer_multi(); rdmsr is slow.
Thanks,
Paolo
> + vmcs_set_bits(PIN_BASED_VM_EXEC_CONTROL,
> + PIN_BASED_VMX_PREEMPTION_TIMER);
> +}
> +
> +static void vmx_clear_hwemul_timer(struct kvm_vcpu *vcpu)
> +{
> + vmcs_clear_bits(PIN_BASED_VM_EXEC_CONTROL,
> + PIN_BASED_VMX_PREEMPTION_TIMER);
> +}
> +
> static void vmx_sched_in(struct kvm_vcpu *vcpu, int cpu)
> {
> if (ple_gap)
> @@ -11018,6 +11057,10 @@ static struct kvm_x86_ops vmx_x86_ops = {
> .pmu_ops = &intel_pmu_ops,
>
> .update_pi_irte = vmx_update_pi_irte,
> +
> + .hw_emul_timer = vmx_hwemul_timer,
> + .set_hwemul_timer = vmx_set_hwemul_timer,
> + .clear_hwemul_timer = vmx_clear_hwemul_timer,
> };
>
> static int __init vmx_init(void)
>
--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
