KVM: x86/xen: Add event channel interrupt vector upcall

It turns out that we can't handle event channels *entirely* in userspace
by delivering them as ExtINT, because KVM is a bit picky about when it
accepts ExtINT interrupts from a legacy PIC. The in-kernel local APIC
has to have LVT0 configured in APIC_MODE_EXTINT and unmasked, which
isn't necessarily the case for Xen guests especially on secondary CPUs.

To cope with this, add kvm_xen_get_interrupt() which checks the
evtchn_pending_upcall field in the Xen vcpu_info, and delivers the Xen
upcall vector (configured by KVM_XEN_ATTR_TYPE_UPCALL_VECTOR) if it's
set regardless of LAPIC LVT0 configuration. This gives us the minimum
support we need for completely userspace-based implementation of event
channels.

This does mean that vcpu_enter_guest() needs to check for the
evtchn_pending_upcall flag being set, because it can't rely on someone
having set KVM_REQ_EVENT unless we were to add some way for userspace to
do so manually.
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>

arch/x86/include/asm/kvm_host.h

@@ -913,6 +913,7 @@ struct msr_bitmap_range {
 struct kvm_xen {
 	bool long_mode;
 	bool shinfo_set;
+	u8 upcall_vector;
 	struct gfn_to_hva_cache shinfo_cache;
 };
 

arch/x86/kvm/irq.c

@@ -14,6 +14,7 @@
 #include "irq.h"
 #include "i8254.h"
 #include "x86.h"
+#include "xen.h"
 
 /*
  * check if there are pending timer events
@@ -56,6 +57,9 @@ int kvm_cpu_has_extint(struct kvm_vcpu *v)
 	if (!lapic_in_kernel(v))
 		return v->arch.interrupt.injected;
 
+	if (kvm_xen_has_interrupt(v))
+		return 1;
+
 	if (!kvm_apic_accept_pic_intr(v))
 		return 0;
 
@@ -110,6 +114,9 @@ static int kvm_cpu_get_extint(struct kvm_vcpu *v)
 	if (!lapic_in_kernel(v))
 		return v->arch.interrupt.nr;
 
+	if (kvm_xen_has_interrupt(v))
+		return v->kvm->arch.xen.upcall_vector;
+
 	if (irqchip_split(v->kvm)) {
 		int vector = v->arch.pending_external_vector;
 

arch/x86/kvm/x86.c

@@ -8987,7 +8987,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 			static_call(kvm_x86_msr_filter_changed)(vcpu);
 	}
 
-	if (kvm_check_request(KVM_REQ_EVENT, vcpu) || req_int_win) {
+	if (kvm_check_request(KVM_REQ_EVENT, vcpu) || req_int_win ||
+	    kvm_xen_has_interrupt(vcpu)) {
 		++vcpu->stat.req_event;
 		kvm_apic_accept_events(vcpu);
 		if (vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED) {

arch/x86/kvm/xen.c

@@ -61,6 +61,44 @@ static int kvm_xen_shared_info_init(struct kvm *kvm, gfn_t gfn)
 	return ret;
 }
 
+int __kvm_xen_has_interrupt(struct kvm_vcpu *v)
+{
+	u8 rc = 0;
+
+	/*
+	 * If the global upcall vector (HVMIRQ_callback_vector) is set and
+	 * the vCPU's evtchn_upcall_pending flag is set, the IRQ is pending.
+	 */
+	struct gfn_to_hva_cache *ghc = &v->arch.xen.vcpu_info_cache;
+	struct kvm_memslots *slots = kvm_memslots(v->kvm);
+	unsigned int offset = offsetof(struct vcpu_info, evtchn_upcall_pending);
+
+	/* No need for compat handling here */
+	BUILD_BUG_ON(offsetof(struct vcpu_info, evtchn_upcall_pending) !=
+		     offsetof(struct compat_vcpu_info, evtchn_upcall_pending));
+	BUILD_BUG_ON(sizeof(rc) !=
+		     sizeof(((struct vcpu_info *)0)->evtchn_upcall_pending));
+	BUILD_BUG_ON(sizeof(rc) !=
+		     sizeof(((struct compat_vcpu_info *)0)->evtchn_upcall_pending));
+
+	/*
+	 * For efficiency, this mirrors the checks for using the valid
+	 * cache in kvm_read_guest_offset_cached(), but just uses
+	 * __get_user() instead. And falls back to the slow path.
+	 */
+	if (likely(slots->generation == ghc->generation &&
+		   !kvm_is_error_hva(ghc->hva) && ghc->memslot)) {
+		/* Fast path */
+		__get_user(rc, (u8 __user *)ghc->hva + offset);
+	} else {
+		/* Slow path */
+		kvm_read_guest_offset_cached(v->kvm, ghc, &rc, offset,
+					     sizeof(rc));
+	}
+
+	return rc;
+}
+
 int kvm_xen_hvm_set_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data)
 {
 	int r = -ENOENT;
@@ -83,6 +121,16 @@ int kvm_xen_hvm_set_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data)
 		r = kvm_xen_shared_info_init(kvm, data->u.shared_info.gfn);
 		break;
 
+
+	case KVM_XEN_ATTR_TYPE_UPCALL_VECTOR:
+		if (data->u.vector < 0x10)
+			r = -EINVAL;
+		else {
+			kvm->arch.xen.upcall_vector = data->u.vector;
+			r = 0;
+		}
+		break;
+
 	default:
 		break;
 	}
@@ -110,6 +158,11 @@ int kvm_xen_hvm_get_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data)
 		}
 		break;
 
+	case KVM_XEN_ATTR_TYPE_UPCALL_VECTOR:
+		data->u.vector = kvm->arch.xen.upcall_vector;
+		r = 0;
+		break;
+
 	default:
 		break;
 	}

arch/x86/kvm/xen.h

@@ -13,6 +13,7 @@
 
 extern struct static_key_false_deferred kvm_xen_enabled;
 
+int __kvm_xen_has_interrupt(struct kvm_vcpu *vcpu);
 int kvm_xen_vcpu_set_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data);
 int kvm_xen_vcpu_get_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data);
 int kvm_xen_hvm_set_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data);
@@ -29,6 +30,14 @@ static inline bool kvm_xen_hypercall_enabled(struct kvm *kvm)
 		 KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL);
 }
 
+static inline int kvm_xen_has_interrupt(struct kvm_vcpu *vcpu)
+{
+	if (static_branch_unlikely(&kvm_xen_enabled.key) &&
+	    vcpu->arch.xen.vcpu_info_set && vcpu->kvm->arch.xen.upcall_vector)
+		return __kvm_xen_has_interrupt(vcpu);
+
+	return 0;
+}
 
 /* 32-bit compatibility definitions, also used natively in 32-bit build */
 #include <asm/pvclock-abi.h>

include/uapi/linux/kvm.h

@@ -1596,6 +1596,7 @@ struct kvm_xen_hvm_attr {
 	__u16 pad[3];
 	union {
 		__u8 long_mode;
+		__u8 vector;
 		struct {
 			__u64 gfn;
 		} shared_info;
@@ -1605,6 +1606,7 @@ struct kvm_xen_hvm_attr {
 
 #define KVM_XEN_ATTR_TYPE_LONG_MODE		0x0
 #define KVM_XEN_ATTR_TYPE_SHARED_INFO		0x1
+#define KVM_XEN_ATTR_TYPE_UPCALL_VECTOR		0x2
 
 /* Per-vCPU Xen attributes */
 #define KVM_XEN_VCPU_GET_ATTR	_IOWR(KVMIO, 0xca, struct kvm_xen_vcpu_attr)