From d6185f20a0efbf175e12831d0de330e4f21725aa Mon Sep 17 00:00:00 2001 From: Nadav Har'El Date: Thu, 22 Sep 2011 13:52:56 +0300 Subject: [PATCH] KVM: nVMX: Add KVM_REQ_IMMEDIATE_EXIT This patch adds a new vcpu->requests bit, KVM_REQ_IMMEDIATE_EXIT. This bit requests that when next entering the guest, we should run it only for as little as possible, and exit again. We use this new option in nested VMX: When L1 launches L2, but L0 wishes L1 to continue running so it can inject an event to it, we unfortunately cannot just pretend to have run L2 for a little while - We must really launch L2, otherwise certain one-off vmcs12 parameters (namely, L1 injection into L2) will be lost. So the existing code runs L2 in this case. But L2 could potentially run for a long time until it exits, and the injection into L1 will be delayed. The new KVM_REQ_IMMEDIATE_EXIT allows us to request that L2 will be entered, as necessary, but will exit as soon as possible after entry. Our implementation of this request uses smp_send_reschedule() to send a self-IPI, with interrupts disabled. The interrupts remain disabled until the guest is entered, and then, after the entry is complete (often including processing an injection and jumping to the relevant handler), the physical interrupt is noticed and causes an exit. On recent Intel processors, we could have achieved the same goal by using MTF instead of a self-IPI. Another technique worth considering in the future is to use VM_EXIT_ACK_INTR_ON_EXIT and a highest-priority vector IPI - to slightly improve performance by avoiding the useless interrupt handler which ends up being called when smp_send_reschedule() is used. Signed-off-by: Nadav Har'El Signed-off-by: Avi Kivity --- arch/x86/kvm/vmx.c | 11 +++++++---- arch/x86/kvm/x86.c | 7 ++++++- include/linux/kvm_host.h | 1 + 3 files changed, 14 insertions(+), 5 deletions(-) diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 579a0b51696a..d75d91465246 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -3945,12 +3945,15 @@ static bool nested_exit_on_intr(struct kvm_vcpu *vcpu) static void enable_irq_window(struct kvm_vcpu *vcpu) { u32 cpu_based_vm_exec_control; - if (is_guest_mode(vcpu) && nested_exit_on_intr(vcpu)) - /* We can get here when nested_run_pending caused - * vmx_interrupt_allowed() to return false. In this case, do - * nothing - the interrupt will be injected later. + if (is_guest_mode(vcpu) && nested_exit_on_intr(vcpu)) { + /* + * We get here if vmx_interrupt_allowed() said we can't + * inject to L1 now because L2 must run. Ask L2 to exit + * right after entry, so we can inject to L1 more promptly. */ + kvm_make_request(KVM_REQ_IMMEDIATE_EXIT, vcpu); return; + } cpu_based_vm_exec_control = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL); cpu_based_vm_exec_control |= CPU_BASED_VIRTUAL_INTR_PENDING; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 4c938da2ba00..e24edbc7f2ec 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -5648,6 +5648,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) int r; bool req_int_win = !irqchip_in_kernel(vcpu->kvm) && vcpu->run->request_interrupt_window; + bool req_immediate_exit = 0; if (vcpu->requests) { if (kvm_check_request(KVM_REQ_MMU_RELOAD, vcpu)) @@ -5687,7 +5688,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) record_steal_time(vcpu); if (kvm_check_request(KVM_REQ_NMI, vcpu)) process_nmi(vcpu); - + req_immediate_exit = + kvm_check_request(KVM_REQ_IMMEDIATE_EXIT, vcpu); } r = kvm_mmu_reload(vcpu); @@ -5738,6 +5740,9 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); + if (req_immediate_exit) + smp_send_reschedule(vcpu->cpu); + kvm_guest_enter(); if (unlikely(vcpu->arch.switch_db_regs)) { diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index d52623199978..9fedeb356b95 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -50,6 +50,7 @@ #define KVM_REQ_APF_HALT 12 #define KVM_REQ_STEAL_UPDATE 13 #define KVM_REQ_NMI 14 +#define KVM_REQ_IMMEDIATE_EXIT 15 #define KVM_USERSPACE_IRQ_SOURCE_ID 0 -- 2.34.1