On Sun, Mar 03, 2013 at 09:21:43PM +0100, Jan Kiszka wrote:
> From: Jan Kiszka <jan.kiszka@xxxxxxxxxxx>
>
> A VCPU sending INIT or SIPI to some other VCPU races for setting the
> remote VCPU's mp_state. When we were unlucky, KVM_MP_STATE_INIT_RECEIVED
> was overwritten by kvm_emulate_halt and, thus, got lost.
>
> Fix this by raising requests on the sender side that will then be
> handled synchronously over the target VCPU context.
>
> Signed-off-by: Jan Kiszka <jan.kiszka@xxxxxxxxxxx>
> ---
>
> Turned out to be simpler than expected. I'm no longer able to reproduce
> the race I saw before.
>
> arch/x86/kvm/lapic.c | 9 ++++-----
> arch/x86/kvm/x86.c | 16 +++++++++++++++-
> include/linux/kvm_host.h | 2 ++
> 3 files changed, 21 insertions(+), 6 deletions(-)
>
> diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
> index 02b51dd..be1e37a 100644
> --- a/arch/x86/kvm/lapic.c
> +++ b/arch/x86/kvm/lapic.c
> @@ -731,8 +731,7 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode,
> case APIC_DM_INIT:
> if (!trig_mode || level) {
> result = 1;
> - vcpu->arch.mp_state = KVM_MP_STATE_INIT_RECEIVED;
> - kvm_make_request(KVM_REQ_EVENT, vcpu);
> + kvm_make_request(KVM_REQ_INIT, vcpu);
> kvm_vcpu_kick(vcpu);
> } else {
> apic_debug("Ignoring de-assert INIT to vcpu %d\n",
> @@ -743,11 +742,11 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode,
> case APIC_DM_STARTUP:
> apic_debug("SIPI to vcpu %d vector 0x%02x\n",
> vcpu->vcpu_id, vector);
> - if (vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED) {
> + if (vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED ||
> + test_bit(KVM_REQ_INIT, &vcpu->requests)) {
> result = 1;
> vcpu->arch.sipi_vector = vector;
> - vcpu->arch.mp_state = KVM_MP_STATE_SIPI_RECEIVED;
> - kvm_make_request(KVM_REQ_EVENT, vcpu);
> + kvm_make_request(KVM_REQ_SIPI, vcpu);
> kvm_vcpu_kick(vcpu);
> }
> break;
> diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
> index d0cf737..8c8843c 100644
> --- a/arch/x86/kvm/x86.c
> +++ b/arch/x86/kvm/x86.c
> @@ -5641,6 +5641,18 @@ static void update_eoi_exitmap(struct kvm_vcpu *vcpu)
> kvm_x86_ops->load_eoi_exitmap(vcpu, eoi_exit_bitmap);
> }
>
> +static bool kvm_check_init_and_sipi(struct kvm_vcpu *vcpu)
> +{
> + if (kvm_check_request(KVM_REQ_INIT, vcpu))
> + vcpu->arch.mp_state = KVM_MP_STATE_INIT_RECEIVED;
> + if (kvm_check_request(KVM_REQ_SIPI, vcpu) &&
> + vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED) {
> + vcpu->arch.mp_state = KVM_MP_STATE_SIPI_RECEIVED;
> + return true;
> + }
> + return false;
> +}
> +
> static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
> {
> int r;
> @@ -5649,6 +5661,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
> bool req_immediate_exit = 0;
>
> if (vcpu->requests) {
> + kvm_check_init_and_sipi(vcpu);
> if (kvm_check_request(KVM_REQ_MMU_RELOAD, vcpu))
> kvm_mmu_unload(vcpu);
> if (kvm_check_request(KVM_REQ_MIGRATE_TIMER, vcpu))
> @@ -6977,10 +6990,11 @@ void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
>
> int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
> {
> + if (kvm_check_init_and_sipi(vcpu))
> + return 1;
> return (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE &&
> !vcpu->arch.apf.halted)
> || !list_empty_careful(&vcpu->async_pf.done)
> - || vcpu->arch.mp_state == KVM_MP_STATE_SIPI_RECEIVED
> || atomic_read(&vcpu->arch.nmi_queued) ||
> (kvm_arch_interrupt_allowed(vcpu) &&
> kvm_cpu_has_interrupt(vcpu));
This makes two subsequent calls to kvm_arch_vcpu_runnable() return
different values if SIPI is pending. While it may not cause problem to
current code (I haven't thought it through) with such semantics you
gonna have a bad time.
--
Gleb.
--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
