Implements the kvm_arch_vcpu_spin/preempt_in_kernel(), because get_cpl requires vcpu_load, so we must cache the result(whether the vcpu was preempted when its cpl=0) in kvm_arch_vcpu. Signed-off-by: Longpeng(Mike) <longpeng2@xxxxxxxxxx> --- arch/x86/include/asm/kvm_host.h | 5 +++++ arch/x86/kvm/svm.c | 6 ++++++ arch/x86/kvm/vmx.c | 20 ++++++++++++++++++++ arch/x86/kvm/x86.c | 9 +++++++-- 4 files changed, 38 insertions(+), 2 deletions(-) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 87ac4fb..d2b2d57 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -688,6 +688,9 @@ struct kvm_vcpu_arch { /* GPA available (AMD only) */ bool gpa_available; + + /* be preempted when it's in kernel-mode(cpl=0) */ + bool preempted_in_kernel; }; struct kvm_lpage_info { @@ -1057,6 +1060,8 @@ struct kvm_x86_ops { void (*cancel_hv_timer)(struct kvm_vcpu *vcpu); void (*setup_mce)(struct kvm_vcpu *vcpu); + + bool (*spin_in_kernel)(struct kvm_vcpu *vcpu); }; struct kvm_arch_async_pf { diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 4d8141e..552ab4c 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -5352,6 +5352,11 @@ static void svm_setup_mce(struct kvm_vcpu *vcpu) vcpu->arch.mcg_cap &= 0x1ff; } +static bool svm_spin_in_kernel(struct kvm_vcpu *vcpu) +{ + return svm_get_cpl(vcpu) == 0; +} + static struct kvm_x86_ops svm_x86_ops __ro_after_init = { .cpu_has_kvm_support = has_svm, .disabled_by_bios = is_disabled, @@ -5464,6 +5469,7 @@ static void svm_setup_mce(struct kvm_vcpu *vcpu) .deliver_posted_interrupt = svm_deliver_avic_intr, .update_pi_irte = svm_update_pi_irte, .setup_mce = svm_setup_mce, + .spin_in_kernel = svm_spin_in_kernel, }; static int __init svm_init(void) diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 39a6222..d0dfe2e 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -11547,6 +11547,25 @@ static void vmx_setup_mce(struct kvm_vcpu *vcpu) ~FEATURE_CONTROL_LMCE; } +static bool vmx_spin_in_kernel(struct kvm_vcpu *vcpu) +{ + u32 secondary_exec_ctrl = 0; + + /* + * Intel sdm vol3 ch-25.1.3 says: The “PAUSE-loop exiting” + * VM-execution control is ignored if CPL > 0. So the vcpu + * is always exiting with CPL=0 if it uses PLE. + * + * The following block needs less cycles than vmx_get_cpl(). + */ + if (cpu_has_secondary_exec_ctrls()) + secondary_exec_ctrl = vmcs_read32(SECONDARY_VM_EXEC_CONTROL); + if (secondary_exec_ctrl & SECONDARY_EXEC_PAUSE_LOOP_EXITING) + return true; + + return vmx_get_cpl(vcpu) == 0; +} + static struct kvm_x86_ops vmx_x86_ops __ro_after_init = { .cpu_has_kvm_support = cpu_has_kvm_support, .disabled_by_bios = vmx_disabled_by_bios, @@ -11674,6 +11693,7 @@ static void vmx_setup_mce(struct kvm_vcpu *vcpu) #endif .setup_mce = vmx_setup_mce, + .spin_in_kernel = vmx_spin_in_kernel, }; static int __init vmx_init(void) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 04c6a1f..fa79a60 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -2881,6 +2881,10 @@ static void kvm_steal_time_set_preempted(struct kvm_vcpu *vcpu) void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) { int idx; + + if (vcpu->preempted) + vcpu->arch.preempted_in_kernel = !kvm_x86_ops->get_cpl(vcpu); + /* * Disable page faults because we're in atomic context here. * kvm_write_guest_offset_cached() would call might_fault() @@ -7988,6 +7992,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) kvm_pmu_init(vcpu); vcpu->arch.pending_external_vector = -1; + vcpu->arch.preempted_in_kernel = false; kvm_hv_vcpu_init(vcpu); @@ -8437,12 +8442,12 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu) bool kvm_arch_vcpu_spin_in_kernel(struct kvm_vcpu *vcpu) { - return false; + return kvm_x86_ops->spin_in_kernel(vcpu); } bool kvm_arch_vcpu_preempt_in_kernel(struct kvm_vcpu *vcpu) { - return false; + return vcpu->arch.preempted_in_kernel; } int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu) -- 1.8.3.1