Commit 460df4c1 authored by Paolo Bonzini's avatar Paolo Bonzini
Browse files

KVM: race-free exit from KVM_RUN without POSIX signals 



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: default avatarRadim Krčmář <rkrcmar@redhat.com>
Reviewed-by: default avatarDavid Hildenbrand <david@redhat.com>
Signed-off-by: default avatarPaolo Bonzini <pbonzini@redhat.com>
parent bbd64115

Documentation/virtual/kvm/api.txt

+12 −1
Original line number Diff line number Diff line
@@ -3389,7 +3389,18 @@ struct kvm_run { 
Request that KVM_RUN return when it becomes possible to inject external

interrupts into the guest.  Useful in conjunction with KVM_INTERRUPT.



	__u8 padding1[7];

	__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;

arch/arm/kvm/arm.c

+4 −0
Original line number Diff line number Diff line
@@ -206,6 +206,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) 
	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:
@@ -604,6 +605,9 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) 
			return ret;

	}



	if (run->immediate_exit)

		return -EINTR;



	if (vcpu->sigset_active)

		sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved);

arch/mips/kvm/mips.c

+6 −1
Original line number Diff line number Diff line
@@ -397,7 +397,7 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, 


int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)

{

	int r = 0;

	int r = -EINTR;

	sigset_t sigsaved;



	if (vcpu->sigset_active)
@@ -409,6 +409,9 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) 
		vcpu->mmio_needed = 0;

	}



	if (run->immediate_exit)

		goto out;



	lose_fpu(1);



	local_irq_disable();
@@ -429,6 +432,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) 
	guest_exit_irqoff();

	local_irq_enable();



out:

	if (vcpu->sigset_active)

		sigprocmask(SIG_SETMASK, &sigsaved, NULL);
@@ -1021,6 +1025,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) 
	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:

arch/powerpc/kvm/powerpc.c

+5 −1
Original line number Diff line number Diff line
@@ -511,6 +511,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) 
	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:
@@ -1117,6 +1118,9 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) 
#endif

	}



	if (run->immediate_exit)

		r = -EINTR;

	else

		r = kvmppc_vcpu_run(run, vcpu);



	if (vcpu->sigset_active)

arch/s390/kvm/kvm-s390.c

+4 −0
Original line number Diff line number Diff line
@@ -370,6 +370,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) 
	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:
@@ -2798,6 +2799,9 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) 
	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;

CRA Git | Maintained and supported by SUSTech CRA and CCSE