[PATCH 5.14 318/334] KVM: arm64: vgic: Resample HW pending state on deactivation

From: Greg Kroah-Hartman
Date: Mon Sep 13 2021 - 10:49:50 EST


From: Marc Zyngier <maz@xxxxxxxxxx>

commit 3134cc8beb69d0db9de651081707c4651c011621 upstream.

When a mapped level interrupt (a timer, for example) is deactivated
by the guest, the corresponding host interrupt is equally deactivated.
However, the fate of the pending state still needs to be dealt
with in SW.

This is specially true when the interrupt was in the active+pending
state in the virtual distributor at the point where the guest
was entered. On exit, the pending state is potentially stale
(the guest may have put the interrupt in a non-pending state).

If we don't do anything, the interrupt will be spuriously injected
in the guest. Although this shouldn't have any ill effect (spurious
interrupts are always possible), we can improve the emulation by
detecting the deactivation-while-pending case and resample the
interrupt.

While we're at it, move the logic into a common helper that can
be shared between the two GIC implementations.

Fixes: e40cc57bac79 ("KVM: arm/arm64: vgic: Support level-triggered mapped interrupts")
Reported-by: Raghavendra Rao Ananta <rananta@xxxxxxxxxx>
Tested-by: Raghavendra Rao Ananta <rananta@xxxxxxxxxx>
Reviewed-by: Oliver Upton <oupton@xxxxxxxxxx>
Signed-off-by: Marc Zyngier <maz@xxxxxxxxxx>
Cc: stable@xxxxxxxxxxxxxxx
Link: https://lore.kernel.org/r/20210819180305.1670525-1-maz@xxxxxxxxxx
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
arch/arm64/kvm/vgic/vgic-v2.c | 36 +++++-------------------------------
arch/arm64/kvm/vgic/vgic-v3.c | 36 +++++-------------------------------
arch/arm64/kvm/vgic/vgic.c | 38 ++++++++++++++++++++++++++++++++++++++
arch/arm64/kvm/vgic/vgic.h | 2 ++
4 files changed, 50 insertions(+), 62 deletions(-)

--- a/arch/arm64/kvm/vgic/vgic-v2.c
+++ b/arch/arm64/kvm/vgic/vgic-v2.c
@@ -60,6 +60,7 @@ void vgic_v2_fold_lr_state(struct kvm_vc
u32 val = cpuif->vgic_lr[lr];
u32 cpuid, intid = val & GICH_LR_VIRTUALID;
struct vgic_irq *irq;
+ bool deactivated;

/* Extract the source vCPU id from the LR */
cpuid = val & GICH_LR_PHYSID_CPUID;
@@ -75,7 +76,8 @@ void vgic_v2_fold_lr_state(struct kvm_vc

raw_spin_lock(&irq->irq_lock);

- /* Always preserve the active bit */
+ /* Always preserve the active bit, note deactivation */
+ deactivated = irq->active && !(val & GICH_LR_ACTIVE_BIT);
irq->active = !!(val & GICH_LR_ACTIVE_BIT);

if (irq->active && vgic_irq_is_sgi(intid))
@@ -96,36 +98,8 @@ void vgic_v2_fold_lr_state(struct kvm_vc
if (irq->config == VGIC_CONFIG_LEVEL && !(val & GICH_LR_STATE))
irq->pending_latch = false;

- /*
- * Level-triggered mapped IRQs are special because we only
- * observe rising edges as input to the VGIC.
- *
- * If the guest never acked the interrupt we have to sample
- * the physical line and set the line level, because the
- * device state could have changed or we simply need to
- * process the still pending interrupt later.
- *
- * If this causes us to lower the level, we have to also clear
- * the physical active state, since we will otherwise never be
- * told when the interrupt becomes asserted again.
- *
- * Another case is when the interrupt requires a helping hand
- * on deactivation (no HW deactivation, for example).
- */
- if (vgic_irq_is_mapped_level(irq)) {
- bool resample = false;
-
- if (val & GICH_LR_PENDING_BIT) {
- irq->line_level = vgic_get_phys_line_level(irq);
- resample = !irq->line_level;
- } else if (vgic_irq_needs_resampling(irq) &&
- !(irq->active || irq->pending_latch)) {
- resample = true;
- }
-
- if (resample)
- vgic_irq_set_phys_active(irq, false);
- }
+ /* Handle resampling for mapped interrupts if required */
+ vgic_irq_handle_resampling(irq, deactivated, val & GICH_LR_PENDING_BIT);

raw_spin_unlock(&irq->irq_lock);
vgic_put_irq(vcpu->kvm, irq);
--- a/arch/arm64/kvm/vgic/vgic-v3.c
+++ b/arch/arm64/kvm/vgic/vgic-v3.c
@@ -46,6 +46,7 @@ void vgic_v3_fold_lr_state(struct kvm_vc
u32 intid, cpuid;
struct vgic_irq *irq;
bool is_v2_sgi = false;
+ bool deactivated;

cpuid = val & GICH_LR_PHYSID_CPUID;
cpuid >>= GICH_LR_PHYSID_CPUID_SHIFT;
@@ -68,7 +69,8 @@ void vgic_v3_fold_lr_state(struct kvm_vc

raw_spin_lock(&irq->irq_lock);

- /* Always preserve the active bit */
+ /* Always preserve the active bit, note deactivation */
+ deactivated = irq->active && !(val & ICH_LR_ACTIVE_BIT);
irq->active = !!(val & ICH_LR_ACTIVE_BIT);

if (irq->active && is_v2_sgi)
@@ -89,36 +91,8 @@ void vgic_v3_fold_lr_state(struct kvm_vc
if (irq->config == VGIC_CONFIG_LEVEL && !(val & ICH_LR_STATE))
irq->pending_latch = false;

- /*
- * Level-triggered mapped IRQs are special because we only
- * observe rising edges as input to the VGIC.
- *
- * If the guest never acked the interrupt we have to sample
- * the physical line and set the line level, because the
- * device state could have changed or we simply need to
- * process the still pending interrupt later.
- *
- * If this causes us to lower the level, we have to also clear
- * the physical active state, since we will otherwise never be
- * told when the interrupt becomes asserted again.
- *
- * Another case is when the interrupt requires a helping hand
- * on deactivation (no HW deactivation, for example).
- */
- if (vgic_irq_is_mapped_level(irq)) {
- bool resample = false;
-
- if (val & ICH_LR_PENDING_BIT) {
- irq->line_level = vgic_get_phys_line_level(irq);
- resample = !irq->line_level;
- } else if (vgic_irq_needs_resampling(irq) &&
- !(irq->active || irq->pending_latch)) {
- resample = true;
- }
-
- if (resample)
- vgic_irq_set_phys_active(irq, false);
- }
+ /* Handle resampling for mapped interrupts if required */
+ vgic_irq_handle_resampling(irq, deactivated, val & ICH_LR_PENDING_BIT);

raw_spin_unlock(&irq->irq_lock);
vgic_put_irq(vcpu->kvm, irq);
--- a/arch/arm64/kvm/vgic/vgic.c
+++ b/arch/arm64/kvm/vgic/vgic.c
@@ -1022,3 +1022,41 @@ bool kvm_vgic_map_is_active(struct kvm_v

return map_is_active;
}
+
+/*
+ * Level-triggered mapped IRQs are special because we only observe rising
+ * edges as input to the VGIC.
+ *
+ * If the guest never acked the interrupt we have to sample the physical
+ * line and set the line level, because the device state could have changed
+ * or we simply need to process the still pending interrupt later.
+ *
+ * We could also have entered the guest with the interrupt active+pending.
+ * On the next exit, we need to re-evaluate the pending state, as it could
+ * otherwise result in a spurious interrupt by injecting a now potentially
+ * stale pending state.
+ *
+ * If this causes us to lower the level, we have to also clear the physical
+ * active state, since we will otherwise never be told when the interrupt
+ * becomes asserted again.
+ *
+ * Another case is when the interrupt requires a helping hand on
+ * deactivation (no HW deactivation, for example).
+ */
+void vgic_irq_handle_resampling(struct vgic_irq *irq,
+ bool lr_deactivated, bool lr_pending)
+{
+ if (vgic_irq_is_mapped_level(irq)) {
+ bool resample = false;
+
+ if (unlikely(vgic_irq_needs_resampling(irq))) {
+ resample = !(irq->active || irq->pending_latch);
+ } else if (lr_pending || (lr_deactivated && irq->line_level)) {
+ irq->line_level = vgic_get_phys_line_level(irq);
+ resample = !irq->line_level;
+ }
+
+ if (resample)
+ vgic_irq_set_phys_active(irq, false);
+ }
+}
--- a/arch/arm64/kvm/vgic/vgic.h
+++ b/arch/arm64/kvm/vgic/vgic.h
@@ -169,6 +169,8 @@ void vgic_irq_set_phys_active(struct vgi
bool vgic_queue_irq_unlock(struct kvm *kvm, struct vgic_irq *irq,
unsigned long flags);
void vgic_kick_vcpus(struct kvm *kvm);
+void vgic_irq_handle_resampling(struct vgic_irq *irq,
+ bool lr_deactivated, bool lr_pending);

int vgic_check_ioaddr(struct kvm *kvm, phys_addr_t *ioaddr,
phys_addr_t addr, phys_addr_t alignment);