KVM: arm64: nv: Request vPE doorbell upon nested ERET to L2

Running an L2 guest with GICv4 enabled goes absolutely nowhere, and gets
into a vicious cycle of nested ERET followed by nested exception entry
into the L1.

When KVM does a put on a runnable vCPU, it marks the vPE as nonresident
but does not request a doorbell IRQ. Behind the scenes in the ITS
driver's view of the vCPU, its_vpe::pending_last gets set to true to
indicate that context is still runnable.

This comes to a head when doing the nested ERET into L2. The vPE doesn't
get scheduled on the redistributor as it is exclusively part of the L1's
VGIC context. kvm_vgic_vcpu_pending_irq() returns true because the vPE
appears runnable, and KVM does a nested exception entry into the L1
before L2 ever gets off the ground.

This issue can be papered over by requesting a doorbell IRQ when
descheduling a vPE as part of a nested ERET. KVM needs this anyway to
kick the vCPU out of the L2 when an IRQ becomes pending for the L1.

Link: https://lore.kernel.org/r/20240823212703.3576061-4-oliver.upton@linux.dev
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20250225172930.1850838-13-maz@kernel.org
Signed-off-by: Oliver Upton <oliver.upton@linux.dev>

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 86519a73971ed6f514b530d73e0610bee1caa3e2..74be23236aacaba5d67780acede762c7bcecc56a 100644 (file)
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -946,6 +946,8 @@ struct kvm_vcpu_arch {
 #define PMUSERENR_ON_CPU       __vcpu_single_flag(sflags, BIT(5))
 /* WFI instruction trapped */
 #define IN_WFI                 __vcpu_single_flag(sflags, BIT(6))
+/* KVM is currently emulating a nested ERET */
+#define IN_NESTED_ERET         __vcpu_single_flag(sflags, BIT(7))
 
 
 /* Pointer to the vcpu's SVE FFR for sve_{save,load}_state() */

diff --git a/arch/arm64/kvm/emulate-nested.c b/arch/arm64/kvm/emulate-nested.c
index 9986bb88c259743088ea9110199d33c392270569..834c587500699036ce2b1697d4d29ec680c29368 100644 (file)
--- a/arch/arm64/kvm/emulate-nested.c
+++ b/arch/arm64/kvm/emulate-nested.c
@@ -2503,6 +2503,7 @@ void kvm_emulate_nested_eret(struct kvm_vcpu *vcpu)
        }
 
        preempt_disable();
+       vcpu_set_flag(vcpu, IN_NESTED_ERET);
        kvm_arch_vcpu_put(vcpu);
 
        if (!esr_iss_is_eretax(esr))
@@ -2514,6 +2515,7 @@ void kvm_emulate_nested_eret(struct kvm_vcpu *vcpu)
        *vcpu_cpsr(vcpu) = spsr;
 
        kvm_arch_vcpu_load(vcpu, smp_processor_id());
+       vcpu_clear_flag(vcpu, IN_NESTED_ERET);
        preempt_enable();
 
        kvm_pmu_nested_transition(vcpu);

diff --git a/arch/arm64/kvm/vgic/vgic-v4.c b/arch/arm64/kvm/vgic/vgic-v4.c
index eedecbbbcf31bb746ecf839d1c0462f2dd9fea51..0d9fb235c0180067b54173b6526cc71ad21974cf 100644 (file)
--- a/arch/arm64/kvm/vgic/vgic-v4.c
+++ b/arch/arm64/kvm/vgic/vgic-v4.c
@@ -336,6 +336,22 @@ void vgic_v4_teardown(struct kvm *kvm)
        its_vm->vpes = NULL;
 }
 
+static inline bool vgic_v4_want_doorbell(struct kvm_vcpu *vcpu)
+{
+       if (vcpu_get_flag(vcpu, IN_WFI))
+               return true;
+
+       if (likely(!vcpu_has_nv(vcpu)))
+               return false;
+
+       /*
+        * GICv4 hardware is only ever used for the L1. Mark the vPE (i.e. the
+        * L1 context) nonresident and request a doorbell to kick us out of the
+        * L2 when an IRQ becomes pending.
+        */
+       return vcpu_get_flag(vcpu, IN_NESTED_ERET);
+}
+
 int vgic_v4_put(struct kvm_vcpu *vcpu)
 {
        struct its_vpe *vpe = &vcpu->arch.vgic_cpu.vgic_v3.its_vpe;
@@ -343,7 +359,7 @@ int vgic_v4_put(struct kvm_vcpu *vcpu)
        if (!vgic_supports_direct_msis(vcpu->kvm) || !vpe->resident)
                return 0;
 
-       return its_make_vpe_non_resident(vpe, !!vcpu_get_flag(vcpu, IN_WFI));
+       return its_make_vpe_non_resident(vpe, vgic_v4_want_doorbell(vcpu));
 }
 
 int vgic_v4_load(struct kvm_vcpu *vcpu)