p71924506
/
linux_old1
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

KVM: VMX: Optimize tscdeadline timer latency 

'Commit d0659d946b ("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>
This commit is contained in:
Wanpeng Li 2018-05-29 14:53:17 +08:00 committed by Paolo Bonzini
parent 71e9d9aeec
commit c5ce8235cf
2 changed files with 8 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
arch/x86/kvm/vmx.c
View File

@ -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) static int vmx_set_hv_timer(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc)
{ {
struct vcpu_vmx *vmx; 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)) if (kvm_mwait_in_guest(vcpu->kvm))
return -EOPNOTSUPP; return -EOPNOTSUPP;
@ -12444,6 +12444,12 @@ static int vmx_set_hv_timer(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc)
tscl = rdtsc(); tscl = rdtsc();
guest_tscl = kvm_read_l1_tsc(vcpu, tscl); guest_tscl = kvm_read_l1_tsc(vcpu, tscl);
delta_tsc = max(guest_deadline_tsc, guest_tscl) - guest_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 */ /* Convert to host delta tsc if tsc scaling is enabled */
if (vcpu->arch.tsc_scaling_ratio != kvm_default_tsc_scaling_ratio && if (vcpu->arch.tsc_scaling_ratio != kvm_default_tsc_scaling_ratio &&

1
arch/x86/kvm/x86.c
View File

@ -138,6 +138,7 @@ module_param(tsc_tolerance_ppm, uint, S_IRUGO | S_IWUSR);
/* lapic timer advance (tscdeadline mode only) in nanoseconds */ /* lapic timer advance (tscdeadline mode only) in nanoseconds */
unsigned int __read_mostly lapic_timer_advance_ns = 0; unsigned int __read_mostly lapic_timer_advance_ns = 0;
module_param(lapic_timer_advance_ns, uint, S_IRUGO | S_IWUSR); 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; static bool __read_mostly vector_hashing = true;
module_param(vector_hashing, bool, S_IRUGO); module_param(vector_hashing, bool, S_IRUGO);