The purpose of the KVM_SET_SIGNAL_MASK API is to let userspace "kick"
a VCPU out of KVM_RUN through a POSIX signal. A signal is attached
to a dummy signal handler; by blocking the signal outside KVM_RUN and
unblocking it inside, this possible race is closed:
VCPU thread service thread
--------------------------------------------------------------
check flag
set flag
raise signal
(signal handler does nothing)
KVM_RUN
However, one issue with KVM_SET_SIGNAL_MASK is that it has to take
tsk->sighand->siglock on every KVM_RUN. This lock is often on a
remote NUMA node, because it is on the node of a thread's creator.
Taking this lock can be very expensive if there are many userspace
exits (as is the case for SMP Windows VMs without Hyper-V reference
time counter).
As an alternative, we can put the flag directly in kvm_run so that
KVM can see it:
VCPU thread service thread
--------------------------------------------------------------
raise signal
signal handler
set run->immediate_exit
KVM_RUN
check run->immediate_exit
Reviewed-by: Radim Krčmář <rkrcmar@redhat.com>
Reviewed-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Request that KVM_RUN return when it becomes possible to inject external
interrupts into the guest. Useful in conjunction with KVM_INTERRUPT.
Request that KVM_RUN return when it becomes possible to inject external
interrupts into the guest. Useful in conjunction with KVM_INTERRUPT.
+ __u8 immediate_exit;
+
+This field is polled once when KVM_RUN starts; if non-zero, KVM_RUN
+exits immediately, returning -EINTR. In the common scenario where a
+signal is used to "kick" a VCPU out of KVM_RUN, this field can be used
+to avoid usage of KVM_SET_SIGNAL_MASK, which has worse scalability.
+Rather than blocking the signal outside KVM_RUN, userspace can set up
+a signal handler that sets run->immediate_exit to a non-zero value.
+
+This field is ignored if KVM_CAP_IMMEDIATE_EXIT is not available.
+
+ __u8 padding1[6];
/* out */
__u32 exit_reason;
/* out */
__u32 exit_reason;
case KVM_CAP_ARM_PSCI_0_2:
case KVM_CAP_READONLY_MEM:
case KVM_CAP_MP_STATE:
case KVM_CAP_ARM_PSCI_0_2:
case KVM_CAP_READONLY_MEM:
case KVM_CAP_MP_STATE:
+ case KVM_CAP_IMMEDIATE_EXIT:
r = 1;
break;
case KVM_CAP_COALESCED_MMIO:
r = 1;
break;
case KVM_CAP_COALESCED_MMIO:
+ if (run->immediate_exit)
+ return -EINTR;
+
if (vcpu->sigset_active)
sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved);
if (vcpu->sigset_active)
sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved);
int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
{
int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
{
sigset_t sigsaved;
if (vcpu->sigset_active)
sigset_t sigsaved;
if (vcpu->sigset_active)
+ if (run->immediate_exit)
+ goto out;
+
lose_fpu(1);
local_irq_disable();
lose_fpu(1);
local_irq_disable();
guest_exit_irqoff();
local_irq_enable();
guest_exit_irqoff();
local_irq_enable();
if (vcpu->sigset_active)
sigprocmask(SIG_SETMASK, &sigsaved, NULL);
if (vcpu->sigset_active)
sigprocmask(SIG_SETMASK, &sigsaved, NULL);
case KVM_CAP_ENABLE_CAP:
case KVM_CAP_READONLY_MEM:
case KVM_CAP_SYNC_MMU:
case KVM_CAP_ENABLE_CAP:
case KVM_CAP_READONLY_MEM:
case KVM_CAP_SYNC_MMU:
+ case KVM_CAP_IMMEDIATE_EXIT:
r = 1;
break;
case KVM_CAP_COALESCED_MMIO:
r = 1;
break;
case KVM_CAP_COALESCED_MMIO:
case KVM_CAP_ONE_REG:
case KVM_CAP_IOEVENTFD:
case KVM_CAP_DEVICE_CTRL:
case KVM_CAP_ONE_REG:
case KVM_CAP_IOEVENTFD:
case KVM_CAP_DEVICE_CTRL:
+ case KVM_CAP_IMMEDIATE_EXIT:
r = 1;
break;
case KVM_CAP_PPC_PAIRED_SINGLES:
r = 1;
break;
case KVM_CAP_PPC_PAIRED_SINGLES:
- r = kvmppc_vcpu_run(run, vcpu);
+ if (run->immediate_exit)
+ r = -EINTR;
+ else
+ r = kvmppc_vcpu_run(run, vcpu);
if (vcpu->sigset_active)
sigprocmask(SIG_SETMASK, &sigsaved, NULL);
if (vcpu->sigset_active)
sigprocmask(SIG_SETMASK, &sigsaved, NULL);
case KVM_CAP_S390_IRQCHIP:
case KVM_CAP_VM_ATTRIBUTES:
case KVM_CAP_MP_STATE:
case KVM_CAP_S390_IRQCHIP:
case KVM_CAP_VM_ATTRIBUTES:
case KVM_CAP_MP_STATE:
+ case KVM_CAP_IMMEDIATE_EXIT:
case KVM_CAP_S390_INJECT_IRQ:
case KVM_CAP_S390_USER_SIGP:
case KVM_CAP_S390_USER_STSI:
case KVM_CAP_S390_INJECT_IRQ:
case KVM_CAP_S390_USER_SIGP:
case KVM_CAP_S390_USER_STSI:
int rc;
sigset_t sigsaved;
int rc;
sigset_t sigsaved;
+ if (kvm_run->immediate_exit)
+ return -EINTR;
+
if (guestdbg_exit_pending(vcpu)) {
kvm_s390_prepare_debug_exit(vcpu);
return 0;
if (guestdbg_exit_pending(vcpu)) {
kvm_s390_prepare_debug_exit(vcpu);
return 0;
case KVM_CAP_DISABLE_QUIRKS:
case KVM_CAP_SET_BOOT_CPU_ID:
case KVM_CAP_SPLIT_IRQCHIP:
case KVM_CAP_DISABLE_QUIRKS:
case KVM_CAP_SET_BOOT_CPU_ID:
case KVM_CAP_SPLIT_IRQCHIP:
+ case KVM_CAP_IMMEDIATE_EXIT:
#ifdef CONFIG_KVM_DEVICE_ASSIGNMENT
case KVM_CAP_ASSIGN_DEV_IRQ:
case KVM_CAP_PCI_2_3:
#ifdef CONFIG_KVM_DEVICE_ASSIGNMENT
case KVM_CAP_ASSIGN_DEV_IRQ:
case KVM_CAP_PCI_2_3:
} else
WARN_ON(vcpu->arch.pio.count || vcpu->mmio_needed);
} else
WARN_ON(vcpu->arch.pio.count || vcpu->mmio_needed);
+ if (kvm_run->immediate_exit)
+ r = -EINTR;
+ else
+ r = vcpu_run(vcpu);
out:
post_kvm_run_save(vcpu);
out:
post_kvm_run_save(vcpu);
struct kvm_run {
/* in */
__u8 request_interrupt_window;
struct kvm_run {
/* in */
__u8 request_interrupt_window;
+ __u8 immediate_exit;
+ __u8 padding1[6];
/* out */
__u32 exit_reason;
/* out */
__u32 exit_reason;
#define KVM_CAP_SPAPR_RESIZE_HPT 133
#define KVM_CAP_PPC_MMU_RADIX 134
#define KVM_CAP_PPC_MMU_HASH_V3 135
#define KVM_CAP_SPAPR_RESIZE_HPT 133
#define KVM_CAP_PPC_MMU_RADIX 134
#define KVM_CAP_PPC_MMU_HASH_V3 135
+#define KVM_CAP_IMMEDIATE_EXIT 136
#ifdef KVM_CAP_IRQ_ROUTING
#ifdef KVM_CAP_IRQ_ROUTING