Currently, checks for whether VT-d PI can be used refer to the current status of the feature in the current vCPU; or they more or less pick vCPU 0 in case a specific vCPU is not available.
However, these checks do not attempt to synchronize with changes to the IRTE. In particular, there is no path that updates the IRTE when APICv is re-activated on vCPU 0; and there is no path to wakeup a CPU that has APICv disabled, if the wakeup occurs because of an IRTE that points to a posted interrupt.
To fix this, always go through the VT-d PI path as long as there are assigned devices and APICv is available on both the host and the VM side. Since the relevant condition was copied over three times, take the hint and factor it into a separate function.
Suggested-by: Sean Christopherson seanjc@google.com Cc: stable@vger.kernel.org Reviewed-by: Sean Christopherson seanjc@google.com Signed-off-by: Paolo Bonzini pbonzini@redhat.com --- arch/x86/kvm/vmx/posted_intr.c | 20 +++++++++++--------- 1 file changed, 11 insertions(+), 9 deletions(-)
diff --git a/arch/x86/kvm/vmx/posted_intr.c b/arch/x86/kvm/vmx/posted_intr.c index 5f81ef092bd4..1c94783b5a54 100644 --- a/arch/x86/kvm/vmx/posted_intr.c +++ b/arch/x86/kvm/vmx/posted_intr.c @@ -5,6 +5,7 @@ #include <asm/cpu.h>
#include "lapic.h" +#include "irq.h" #include "posted_intr.h" #include "trace.h" #include "vmx.h" @@ -77,13 +78,18 @@ void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu) pi_set_on(pi_desc); }
+static bool vmx_can_use_vtd_pi(struct kvm *kvm) +{ + return irqchip_in_kernel(kvm) && enable_apicv && + kvm_arch_has_assigned_device(kvm) && + irq_remapping_cap(IRQ_POSTING_CAP); +} + void vmx_vcpu_pi_put(struct kvm_vcpu *vcpu) { struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
- if (!kvm_arch_has_assigned_device(vcpu->kvm) || - !irq_remapping_cap(IRQ_POSTING_CAP) || - !kvm_vcpu_apicv_active(vcpu)) + if (!vmx_can_use_vtd_pi(vcpu->kvm)) return;
/* Set SN when the vCPU is preempted */ @@ -141,9 +147,7 @@ int pi_pre_block(struct kvm_vcpu *vcpu) struct pi_desc old, new; struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
- if (!kvm_arch_has_assigned_device(vcpu->kvm) || - !irq_remapping_cap(IRQ_POSTING_CAP) || - !kvm_vcpu_apicv_active(vcpu)) + if (!vmx_can_use_vtd_pi(vcpu->kvm)) return 0;
WARN_ON(irqs_disabled()); @@ -270,9 +274,7 @@ int pi_update_irte(struct kvm *kvm, unsigned int host_irq, uint32_t guest_irq, struct vcpu_data vcpu_info; int idx, ret = 0;
- if (!kvm_arch_has_assigned_device(kvm) || - !irq_remapping_cap(IRQ_POSTING_CAP) || - !kvm_vcpu_apicv_active(kvm->vcpus[0])) + if (!vmx_can_use_vtd_pi(kvm)) return 0;
idx = srcu_read_lock(&kvm->irq_srcu);
On Mon, Nov 22, 2021 at 07:43:11PM -0500, Paolo Bonzini wrote:
Currently, checks for whether VT-d PI can be used refer to the current status of the feature in the current vCPU; or they more or less pick vCPU 0 in case a specific vCPU is not available.
However, these checks do not attempt to synchronize with changes to the IRTE. In particular, there is no path that updates the IRTE when APICv is re-activated on vCPU 0; and there is no path to wakeup a CPU that has APICv disabled, if the wakeup occurs because of an IRTE that points to a posted interrupt.
To fix this, always go through the VT-d PI path as long as there are assigned devices and APICv is available on both the host and the VM side. Since the relevant condition was copied over three times, take the hint and factor it into a separate function.
Suggested-by: Sean Christopherson seanjc@google.com Cc: stable@vger.kernel.org Reviewed-by: Sean Christopherson seanjc@google.com Signed-off-by: Paolo Bonzini pbonzini@redhat.com
Reviewed-by: David Matlack dmatlack@google.com
arch/x86/kvm/vmx/posted_intr.c | 20 +++++++++++--------- 1 file changed, 11 insertions(+), 9 deletions(-)
diff --git a/arch/x86/kvm/vmx/posted_intr.c b/arch/x86/kvm/vmx/posted_intr.c index 5f81ef092bd4..1c94783b5a54 100644 --- a/arch/x86/kvm/vmx/posted_intr.c +++ b/arch/x86/kvm/vmx/posted_intr.c @@ -5,6 +5,7 @@ #include <asm/cpu.h> #include "lapic.h" +#include "irq.h" #include "posted_intr.h" #include "trace.h" #include "vmx.h" @@ -77,13 +78,18 @@ void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu) pi_set_on(pi_desc); } +static bool vmx_can_use_vtd_pi(struct kvm *kvm) +{
- return irqchip_in_kernel(kvm) && enable_apicv &&
kvm_arch_has_assigned_device(kvm) &&irq_remapping_cap(IRQ_POSTING_CAP);+}
void vmx_vcpu_pi_put(struct kvm_vcpu *vcpu) { struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
- if (!kvm_arch_has_assigned_device(vcpu->kvm) ||
!irq_remapping_cap(IRQ_POSTING_CAP) ||!kvm_vcpu_apicv_active(vcpu))
- if (!vmx_can_use_vtd_pi(vcpu->kvm)) return;
/* Set SN when the vCPU is preempted */ @@ -141,9 +147,7 @@ int pi_pre_block(struct kvm_vcpu *vcpu) struct pi_desc old, new; struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
- if (!kvm_arch_has_assigned_device(vcpu->kvm) ||
!irq_remapping_cap(IRQ_POSTING_CAP) ||!kvm_vcpu_apicv_active(vcpu))
- if (!vmx_can_use_vtd_pi(vcpu->kvm)) return 0;
WARN_ON(irqs_disabled()); @@ -270,9 +274,7 @@ int pi_update_irte(struct kvm *kvm, unsigned int host_irq, uint32_t guest_irq, struct vcpu_data vcpu_info; int idx, ret = 0;
- if (!kvm_arch_has_assigned_device(kvm) ||
!irq_remapping_cap(IRQ_POSTING_CAP) ||!kvm_vcpu_apicv_active(kvm->vcpus[0]))
- if (!vmx_can_use_vtd_pi(kvm)) return 0;
idx = srcu_read_lock(&kvm->irq_srcu); -- 2.27.0
On Mon, 2021-11-22 at 19:43 -0500, Paolo Bonzini wrote:
Currently, checks for whether VT-d PI can be used refer to the current status of the feature in the current vCPU; or they more or less pick vCPU 0 in case a specific vCPU is not available.
However, these checks do not attempt to synchronize with changes to the IRTE. In particular, there is no path that updates the IRTE when APICv is re-activated on vCPU 0; and there is no path to wakeup a CPU that has APICv disabled, if the wakeup occurs because of an IRTE that points to a posted interrupt.
To fix this, always go through the VT-d PI path as long as there are assigned devices and APICv is available on both the host and the VM side. Since the relevant condition was copied over three times, take the hint and factor it into a separate function.
Suggested-by: Sean Christopherson seanjc@google.com Cc: stable@vger.kernel.org Reviewed-by: Sean Christopherson seanjc@google.com Signed-off-by: Paolo Bonzini pbonzini@redhat.com
arch/x86/kvm/vmx/posted_intr.c | 20 +++++++++++--------- 1 file changed, 11 insertions(+), 9 deletions(-)
diff --git a/arch/x86/kvm/vmx/posted_intr.c b/arch/x86/kvm/vmx/posted_intr.c index 5f81ef092bd4..1c94783b5a54 100644 --- a/arch/x86/kvm/vmx/posted_intr.c +++ b/arch/x86/kvm/vmx/posted_intr.c @@ -5,6 +5,7 @@ #include <asm/cpu.h> #include "lapic.h" +#include "irq.h" #include "posted_intr.h" #include "trace.h" #include "vmx.h" @@ -77,13 +78,18 @@ void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu) pi_set_on(pi_desc); } +static bool vmx_can_use_vtd_pi(struct kvm *kvm) +{
- return irqchip_in_kernel(kvm) && enable_apicv &&
kvm_arch_has_assigned_device(kvm) &&irq_remapping_cap(IRQ_POSTING_CAP);+}
void vmx_vcpu_pi_put(struct kvm_vcpu *vcpu) { struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
- if (!kvm_arch_has_assigned_device(vcpu->kvm) ||
!irq_remapping_cap(IRQ_POSTING_CAP) ||!kvm_vcpu_apicv_active(vcpu))
- if (!vmx_can_use_vtd_pi(vcpu->kvm)) return;
/* Set SN when the vCPU is preempted */ @@ -141,9 +147,7 @@ int pi_pre_block(struct kvm_vcpu *vcpu) struct pi_desc old, new; struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
- if (!kvm_arch_has_assigned_device(vcpu->kvm) ||
!irq_remapping_cap(IRQ_POSTING_CAP) ||!kvm_vcpu_apicv_active(vcpu))
- if (!vmx_can_use_vtd_pi(vcpu->kvm)) return 0;
WARN_ON(irqs_disabled()); @@ -270,9 +274,7 @@ int pi_update_irte(struct kvm *kvm, unsigned int host_irq, uint32_t guest_irq, struct vcpu_data vcpu_info; int idx, ret = 0;
- if (!kvm_arch_has_assigned_device(kvm) ||
!irq_remapping_cap(IRQ_POSTING_CAP) ||!kvm_vcpu_apicv_active(kvm->vcpus[0]))
- if (!vmx_can_use_vtd_pi(kvm)) return 0;
idx = srcu_read_lock(&kvm->irq_srcu);
Reviewed-by: Maxim Levitsky mlevitsk@redhat.com
Best regards, Maxim Levitsky
linux-stable-mirror@lists.linaro.org
-
David Matlack -
Maxim Levitsky -
Paolo Bonzini