From: David Woodhouse Date: Wed, 9 Dec 2020 20:08:30 +0000 (+0000) Subject: KVM: x86/xen: Add event channel interrupt vector upcall X-Git-Url: https://www.infradead.org/git/?a=commitdiff_plain;h=refs%2Fheads%2Fxenpv-brim-merge-20201212;p=users%2Fdwmw2%2Flinux.git 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. But actually, I don't quite see how that works reliably for interrupts injected with KVM_INTERRUPT either. In kvm_vcpu_ioctl_interrupt() the KVM_REQ_EVENT request is set once, but that'll get cleared the first time through vcpu_enter_guest(). So if the first exit is for something *else* without interrupts being enabled yet, won't the KVM_REQ_EVENT request have been consumed already and just be lost? I wonder if my addition of '|| kvm_xen_has_interrupt(vcpu)' should actually be '|| kvm_has_injectable_intr(vcpu)' to fix that pre-existing bug? Signed-off-by: David Woodhouse --- diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 62f8dc78807bf..36f2a2756bcc3 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -902,6 +902,7 @@ struct msr_bitmap_range { /* Xen emulation context */ struct kvm_xen { bool long_mode; + u8 upcall_vector; struct kvm_host_map shinfo_map; void *shinfo; }; diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c index 814698e5b1526..24668b51b5c89 100644 --- a/arch/x86/kvm/irq.c +++ b/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; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index ad9eea8f4f268..1711072b36165 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -8891,7 +8891,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) kvm_x86_ops.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) { diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c index 8a807b610d2bd..fd7164e641bdf 100644 --- a/arch/x86/kvm/xen.c +++ b/arch/x86/kvm/xen.c @@ -257,6 +257,22 @@ void kvm_xen_setup_pvclock_page(struct kvm_vcpu *v) srcu_read_unlock(&v->kvm->srcu, idx); } +int kvm_xen_has_interrupt(struct kvm_vcpu *v) +{ + int rc = 0; + + if (v->kvm->arch.xen.upcall_vector) { + int idx = srcu_read_lock(&v->kvm->srcu); + struct vcpu_info *vcpu_info = xen_vcpu_info(v); + + if (vcpu_info && READ_ONCE(vcpu_info->evtchn_upcall_pending)) + rc = 1; + + srcu_read_unlock(&v->kvm->srcu, idx); + } + return rc; +} + static int vcpu_attr_loc(struct kvm_vcpu *vcpu, u16 type, struct kvm_host_map **map, void ***hva, size_t *sz) { @@ -335,6 +351,14 @@ int kvm_xen_hvm_set_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data) break; } + case KVM_XEN_ATTR_TYPE_UPCALL_VECTOR: + if (data->u.vector < 0x10) + return -EINVAL; + + kvm->arch.xen.upcall_vector = data->u.vector; + r = 0; + break; + default: break; } @@ -382,6 +406,11 @@ 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; } diff --git a/arch/x86/kvm/xen.h b/arch/x86/kvm/xen.h index ccd6002f55bc0..1f599342f02cf 100644 --- a/arch/x86/kvm/xen.h +++ b/arch/x86/kvm/xen.h @@ -25,6 +25,7 @@ static inline struct kvm_vcpu *xen_vcpu_to_vcpu(struct kvm_vcpu_xen *xen_vcpu) void kvm_xen_setup_pvclock_page(struct kvm_vcpu *vcpu); void kvm_xen_setup_runstate_page(struct kvm_vcpu *vcpu); void kvm_xen_runstate_set_preempted(struct kvm_vcpu *vcpu); +int kvm_xen_has_interrupt (struct kvm_vcpu *vcpu); int kvm_xen_hvm_set_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data); int kvm_xen_hvm_get_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data); int kvm_xen_hypercall(struct kvm_vcpu *vcpu); diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 1047364d1adff..113279fa9e1e3 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1587,6 +1587,7 @@ struct kvm_xen_hvm_attr { union { __u8 long_mode; + __u8 vector; struct { __u64 gfn; } shared_info; @@ -1604,6 +1605,7 @@ struct kvm_xen_hvm_attr { #define KVM_XEN_ATTR_TYPE_VCPU_INFO 0x2 #define KVM_XEN_ATTR_TYPE_VCPU_TIME_INFO 0x3 #define KVM_XEN_ATTR_TYPE_VCPU_RUNSTATE 0x4 +#define KVM_XEN_ATTR_TYPE_UPCALL_VECTOR 0x5 /* Secure Encrypted Virtualization command */ enum sev_cmd_id {