KVM: VMX: Optimize tscdeadline timer latency

'Commit d0659d946be0 ("KVM: x86: add option to advance tscdeadline
hrtimer expiration")' advances the tscdeadline (the timer is emulated
by hrtimer) expiration in order that the latency which is incurred
by hypervisor (apic_timer_fn -> vmentry) can be avoided. This patch
adds the advance tscdeadline expiration support to which the tscdeadline
timer is emulated by VMX preemption timer to reduce the hypervisor
lantency (handle_preemption_timer -> vmentry). The guest can also
set an expiration that is very small (for example in Linux if an
hrtimer feeds a expiration in the past); in that case we set delta_tsc
to 0, leading to an immediately vmexit when delta_tsc is not bigger than
advance ns.

This patch can reduce ~63% latency (~4450 cycles to ~1660 cycles on
a haswell desktop) for kvm-unit-tests/tscdeadline_latency when testing
busy waits.

Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Radim Krčmář <rkrcmar@redhat.com>
Signed-off-by: Wanpeng Li <wanpengli@tencent.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index d205e9246f991b8e329bb7c662710a0a7dc05c4e..aff0f3ee6a1d79c5b279183586d5deb61027d602 100644 (file)
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -12435,7 +12435,7 @@ static inline int u64_shl_div_u64(u64 a, unsigned int shift,
 static int vmx_set_hv_timer(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc)
 {
        struct vcpu_vmx *vmx;
-       u64 tscl, guest_tscl, delta_tsc;
+       u64 tscl, guest_tscl, delta_tsc, lapic_timer_advance_cycles;
 
        if (kvm_mwait_in_guest(vcpu->kvm))
                return -EOPNOTSUPP;
@@ -12444,6 +12444,12 @@ static int vmx_set_hv_timer(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc)
        tscl = rdtsc();
        guest_tscl = kvm_read_l1_tsc(vcpu, tscl);
        delta_tsc = max(guest_deadline_tsc, guest_tscl) - guest_tscl;
+       lapic_timer_advance_cycles = nsec_to_cycles(vcpu, lapic_timer_advance_ns);
+
+       if (delta_tsc > lapic_timer_advance_cycles)
+               delta_tsc -= lapic_timer_advance_cycles;
+       else
+               delta_tsc = 0;
 
        /* Convert to host delta tsc if tsc scaling is enabled */
        if (vcpu->arch.tsc_scaling_ratio != kvm_default_tsc_scaling_ratio &&

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 1d3dfc2c941d4bba802b2514c873e94732277f82..93dd25d005a17490d3ad29aca19685a3b61cfe6c 100644 (file)
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -138,6 +138,7 @@ 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 = 0;
 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);