From f76e17a3787f3690a20b3da36e4b38d4a37ff0de Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Wed, 17 Apr 2019 10:15:33 -0700 Subject: [PATCH] KVM: lapic: Allow user to disable adaptive tuning of timer advancement The introduction of adaptive tuning of lapic timer advancement did not allow for the scenario where userspace would want to disable adaptive tuning but still employ timer advancement, e.g. for testing purposes or to handle a use case where adaptive tuning is unable to settle on a suitable time. This is epecially pertinent now that KVM places a hard threshold on the maximum advancment time. Rework the timer semantics to accept signed values, with a value of '-1' being interpreted as "use adaptive tuning with KVM's internal default", and any other value being used as an explicit advancement time, e.g. a time of '0' effectively disables advancement. Note, this does not completely restore the original behavior of lapic_timer_advance_ns. Prior to tracking the advancement per vCPU, which is necessary to support autotuning, userspace could adjust lapic_timer_advance_ns for *running* vCPU. With per-vCPU tracking, the module params are snapshotted at vCPU creation, i.e. applying a new advancement effectively requires restarting a VM. Dynamically updating a running vCPU is possible, e.g. a helper could be added to retrieve the desired delay, choosing between the global module param and the per-VCPU value depending on whether or not auto-tuning is (globally) enabled, but introduces a great deal of complexity. The wrapper itself is not complex, but understanding and documenting the effects of dynamically toggling auto-tuning and/or adjusting the timer advancement is nigh impossible since the behavior would be dependent on KVM's implementation as well as compiler optimizations. In other words, providing stable behavior would require extremely careful consideration now and in the future. Given that the expected use of a manually-tuned timer advancement is to "tune once, run many", use the vastly simpler approach of recognizing changes to the module params only when creating a new vCPU. Cc: Liran Alon Cc: Wanpeng Li Reviewed-by: Liran Alon Cc: stable@vger.kernel.org Fixes: 0ca11c83f85ea ("KVM: LAPIC: Tune lapic_timer_advance_ns automatically") Signed-off-by: Sean Christopherson Signed-off-by: Paolo Bonzini --- arch/x86/kvm/lapic.c | 11 +++++++++-- arch/x86/kvm/lapic.h | 2 +- arch/x86/kvm/x86.c | 9 +++++++-- 3 files changed, 17 insertions(+), 5 deletions(-) diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 7decd58c9cea6..12f2f7dc121fb 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -2263,7 +2263,7 @@ static enum hrtimer_restart apic_timer_fn(struct hrtimer *data) return HRTIMER_NORESTART; } -int kvm_create_lapic(struct kvm_vcpu *vcpu, u32 timer_advance_ns) +int kvm_create_lapic(struct kvm_vcpu *vcpu, int timer_advance_ns) { struct kvm_lapic *apic; @@ -2287,7 +2287,14 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu, u32 timer_advance_ns) hrtimer_init(&apic->lapic_timer.timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED); apic->lapic_timer.timer.function = apic_timer_fn; - apic->lapic_timer.timer_advance_ns = timer_advance_ns; + if (timer_advance_ns == -1) { + apic->lapic_timer.timer_advance_ns = 1000; + apic->lapic_timer.timer_advance_adjust_done = false; + } else { + apic->lapic_timer.timer_advance_ns = timer_advance_ns; + apic->lapic_timer.timer_advance_adjust_done = true; + } + /* * APIC is created enabled. This will prevent kvm_lapic_set_base from diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index 3e97f8a68967b..d6d049ba30452 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -64,7 +64,7 @@ struct kvm_lapic { struct dest_map; -int kvm_create_lapic(struct kvm_vcpu *vcpu, u32 timer_advance_ns); +int kvm_create_lapic(struct kvm_vcpu *vcpu, int timer_advance_ns); void kvm_free_lapic(struct kvm_vcpu *vcpu); int kvm_apic_has_interrupt(struct kvm_vcpu *vcpu); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index aa26a3cfc765d..9482cb36b92ac 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -136,8 +136,13 @@ 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 */ -static u32 __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); static bool __read_mostly vector_hashing = true; -- 2.39.5