kvm/x86: Hyper-V synthetic interrupt controller

SynIC (synthetic interrupt controller) is a lapic extension,
which is controlled via MSRs and maintains for each vCPU
 - 16 synthetic interrupt "lines" (SINT's); each can be configured to
   trigger a specific interrupt vector optionally with auto-EOI
   semantics
 - a message page in the guest memory with 16 256-byte per-SINT message
   slots
 - an event flag page in the guest memory with 16 2048-bit per-SINT
   event flag areas

The host triggers a SINT whenever it delivers a new message to the
corresponding slot or flips an event flag bit in the corresponding area.
The guest informs the host that it can try delivering a message by
explicitly asserting EOI in lapic or writing to End-Of-Message (EOM)
MSR.

The userspace (qemu) triggers interrupts and receives EOM notifications
via irqfd with resampler; for that, a GSI is allocated for each
configured SINT, and irq_routing api is extended to support GSI-SINT
mapping.

Changes v4:
* added activation of SynIC by vcpu KVM_ENABLE_CAP
* added per SynIC active flag
* added deactivation of APICv upon SynIC activation

Changes v3:
* added KVM_CAP_HYPERV_SYNIC and KVM_IRQ_ROUTING_HV_SINT notes into
docs

Changes v2:
* do not use posted interrupts for Hyper-V SynIC AutoEOI vectors
* add Hyper-V SynIC vectors into EOI exit bitmap
* Hyper-V SyniIC SINT msr write logic simplified

Signed-off-by: Andrey Smetanin <asmetanin@virtuozzo.com>
Reviewed-by: Roman Kagan <rkagan@virtuozzo.com>
Signed-off-by: Denis V. Lunev <den@openvz.org>
CC: Gleb Natapov <gleb@kernel.org>
CC: Paolo Bonzini <pbonzini@redhat.com>
CC: Roman Kagan <rkagan@virtuozzo.com>
CC: Denis V. Lunev <den@openvz.org>
CC: qemu-devel@nongnu.org
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

1 files changed, 34 insertions, 0 deletions

diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c
index ece901c29351..8fc89efb5250 100644
--- a/arch/x86/kvm/irq_comm.c
+++ b/arch/x86/kvm/irq_comm.c
@@ -33,6 +33,8 @@
 
 #include "lapic.h"
 
+#include "hyperv.h"
+
 static int kvm_set_pic_irq(struct kvm_kernel_irq_routing_entry *e,
 			   struct kvm *kvm, int irq_source_id, int level,
 			   bool line_status)
@@ -219,6 +221,16 @@ void kvm_fire_mask_notifiers(struct kvm *kvm, unsigned irqchip, unsigned pin,
 	srcu_read_unlock(&kvm->irq_srcu, idx);
 }
 
+static int kvm_hv_set_sint(struct kvm_kernel_irq_routing_entry *e,
+		    struct kvm *kvm, int irq_source_id, int level,
+		    bool line_status)
+{
+	if (!level)
+		return -1;
+
+	return kvm_hv_synic_set_irq(kvm, e->hv_sint.vcpu, e->hv_sint.sint);
+}
+
 int kvm_set_routing_entry(struct kvm_kernel_irq_routing_entry *e,
 			  const struct kvm_irq_routing_entry *ue)
 {
@@ -257,6 +269,11 @@ int kvm_set_routing_entry(struct kvm_kernel_irq_routing_entry *e,
 		e->msi.address_hi = ue->u.msi.address_hi;
 		e->msi.data = ue->u.msi.data;
 		break;
+	case KVM_IRQ_ROUTING_HV_SINT:
+		e->set = kvm_hv_set_sint;
+		e->hv_sint.vcpu = ue->u.hv_sint.vcpu;
+		e->hv_sint.sint = ue->u.hv_sint.sint;
+		break;
 	default:
 		goto out;
 	}
@@ -376,3 +393,20 @@ void kvm_scan_ioapic_routes(struct kvm_vcpu *vcpu,
 	}
 	srcu_read_unlock(&kvm->irq_srcu, idx);
 }
+
+int kvm_arch_set_irq(struct kvm_kernel_irq_routing_entry *irq, struct kvm *kvm,
+		     int irq_source_id, int level, bool line_status)
+{
+	switch (irq->type) {
+	case KVM_IRQ_ROUTING_HV_SINT:
+		return kvm_hv_set_sint(irq, kvm, irq_source_id, level,
+				       line_status);
+	default:
+		return -EWOULDBLOCK;
+	}
+}
+
+void kvm_arch_irq_routing_update(struct kvm *kvm)
+{
+	kvm_hv_irq_routing_update(kvm);
+}