[RFC PATCH v5 32/52] hw/xen: Implement EVTCHNOP_bind_virq

[David Woodhouse <dwmw2@infradead.org>]

From: David Woodhouse <dwmw@amazon.co.uk>

Add the array of virq ports to each vCPU so that we can deliver timers,
debug ports, etc. Global virqs are allocated against vCPU 0 initially,
but can be migrated to other vCPUs (when we implement that).

The kernel needs to know about VIRQ_TIMER in order to accelerate timers,
so tell it via KVM_XEN_VCPU_ATTR_TYPE_TIMER. Also save/restore the value
of the singleshot timer across migration, as the kernel will handle the
hypercalls automatically now.

Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
---
 hw/i386/kvm/xen_evtchn.c  | 85 ++++++++++++++++++++++++++++++++++++
 hw/i386/kvm/xen_evtchn.h  |  2 +
 include/sysemu/kvm_xen.h  |  1 +
 target/i386/cpu.h         |  4 ++
 target/i386/kvm/xen-emu.c | 91 +++++++++++++++++++++++++++++++++++++++
 target/i386/machine.c     |  2 +
 6 files changed, 185 insertions(+)

diff --git a/hw/i386/kvm/xen_evtchn.c b/hw/i386/kvm/xen_evtchn.c
index bfdcc8de67..f8e7170a84 100644
--- a/hw/i386/kvm/xen_evtchn.c
+++ b/hw/i386/kvm/xen_evtchn.c
@@ -239,6 +239,11 @@ static bool valid_port(evtchn_port_t port)
     }
 }
 
+static bool valid_vcpu(uint32_t vcpu)
+{
+    return !!qemu_get_cpu(vcpu);
+}
+
 int xen_evtchn_status_op(struct evtchn_status *status)
 {
     XenEvtchnState *s = xen_evtchn_singleton;
@@ -489,6 +494,43 @@ static void free_port(XenEvtchnState *s, evtchn_port_t port)
     clear_port_pending(s, port);
 }
 
+static int allocate_port(XenEvtchnState *s, uint32_t vcpu, uint16_t type,
+                         uint16_t val, evtchn_port_t *port)
+{
+    evtchn_port_t p = 1;
+
+    for (p = 1; valid_port(p); p++) {
+        if (s->port_table[p].type == EVTCHNSTAT_closed) {
+            s->port_table[p].vcpu = vcpu;
+            s->port_table[p].type = type;
+            s->port_table[p].type_val = val;
+
+            *port = p;
+
+            if (s->nr_ports < p + 1) {
+                s->nr_ports = p + 1;
+            }
+
+            return 0;
+        }
+    }
+    return -ENOSPC;
+}
+
+static bool virq_is_global(uint32_t virq)
+{
+    switch (virq) {
+    case VIRQ_TIMER:
+    case VIRQ_DEBUG:
+    case VIRQ_XENOPROF:
+    case VIRQ_XENPMU:
+        return false;
+
+    default:
+        return true;
+    }
+}
+
 static int close_port(XenEvtchnState *s, evtchn_port_t port)
 {
     XenEvtchnPort *p = &s->port_table[port];
@@ -497,6 +539,11 @@ static int close_port(XenEvtchnState *s, evtchn_port_t port)
     case EVTCHNSTAT_closed:
         return -ENOENT;
 
+    case EVTCHNSTAT_virq:
+        kvm_xen_set_vcpu_virq(virq_is_global(p->type_val) ? 0 : p->vcpu,
+                              p->type_val, 0);
+        break;
+
     default:
         break;
     }
@@ -548,3 +595,41 @@ int xen_evtchn_unmask_op(struct evtchn_unmask *unmask)
 
     return ret;
 }
+
+int xen_evtchn_bind_virq_op(struct evtchn_bind_virq *virq)
+{
+    XenEvtchnState *s = xen_evtchn_singleton;
+    int ret;
+
+    if (!s) {
+        return -ENOTSUP;
+    }
+
+    if (virq->virq >= NR_VIRQS) {
+        return -EINVAL;
+    }
+
+    /* Global VIRQ must be allocated on vCPU0 first */
+    if (virq_is_global(virq->virq) && virq->vcpu != 0) {
+        return -EINVAL;
+    }
+
+    if (!valid_vcpu(virq->vcpu)) {
+        return -ENOENT;
+    }
+
+    qemu_mutex_lock(&s->port_lock);
+
+    ret = allocate_port(s, virq->vcpu, EVTCHNSTAT_virq, virq->virq,
+                        &virq->port);
+    if (!ret) {
+        ret = kvm_xen_set_vcpu_virq(virq->vcpu, virq->virq, virq->port);
+        if (ret) {
+            free_port(s, virq->port);
+        }
+    }
+
+    qemu_mutex_unlock(&s->port_lock);
+
+    return ret;
+}
diff --git a/hw/i386/kvm/xen_evtchn.h b/hw/i386/kvm/xen_evtchn.h
index 69c6b0d743..0ea13dda3a 100644
--- a/hw/i386/kvm/xen_evtchn.h
+++ b/hw/i386/kvm/xen_evtchn.h
@@ -18,8 +18,10 @@ int xen_evtchn_set_callback_param(uint64_t param);
 struct evtchn_status;
 struct evtchn_close;
 struct evtchn_unmask;
+struct evtchn_bind_virq;
 int xen_evtchn_status_op(struct evtchn_status *status);
 int xen_evtchn_close_op(struct evtchn_close *close);
 int xen_evtchn_unmask_op(struct evtchn_unmask *unmask);
+int xen_evtchn_bind_virq_op(struct evtchn_bind_virq *virq);
 
 #endif /* QEMU_XEN_EVTCHN_H */
diff --git a/include/sysemu/kvm_xen.h b/include/sysemu/kvm_xen.h
index ee53294deb..864772514f 100644
--- a/include/sysemu/kvm_xen.h
+++ b/include/sysemu/kvm_xen.h
@@ -19,6 +19,7 @@
 uint32_t kvm_xen_get_caps(void);
 void *kvm_xen_get_vcpu_info_hva(uint32_t vcpu_id);
 void kvm_xen_inject_vcpu_callback_vector(uint32_t vcpu_id, int type);
+int kvm_xen_set_vcpu_virq(uint32_t vcpu_id, uint16_t virq, uint16_t port);
 
 #define kvm_xen_has_cap(cap) (!!(kvm_xen_get_caps() &           \
                                  KVM_XEN_HVM_CONFIG_ ## cap))
diff --git a/target/i386/cpu.h b/target/i386/cpu.h
index 938a1b9c8b..000ed2fed9 100644
--- a/target/i386/cpu.h
+++ b/target/i386/cpu.h
@@ -27,6 +27,8 @@
 #include "qapi/qapi-types-common.h"
 #include "qemu/cpu-float.h"
 
+#define XEN_NR_VIRQS 24
+
 /* The x86 has a strong memory model with some store-after-load re-ordering */
 #define TCG_GUEST_DEFAULT_MO      (TCG_MO_ALL & ~TCG_MO_ST_LD)
 
@@ -1793,6 +1795,8 @@ typedef struct CPUArchState {
     uint64_t xen_vcpu_time_info_gpa;
     uint64_t xen_vcpu_runstate_gpa;
     uint8_t xen_vcpu_callback_vector;
+    uint16_t xen_virq[XEN_NR_VIRQS];
+    uint64_t xen_singleshot_timer_ns;
 #endif
 #if defined(CONFIG_HVF)
     HVFX86LazyFlags hvf_lflags;
diff --git a/target/i386/kvm/xen-emu.c b/target/i386/kvm/xen-emu.c
index 29a187fdf8..f3d456f4b8 100644
--- a/target/i386/kvm/xen-emu.c
+++ b/target/i386/kvm/xen-emu.c
@@ -342,6 +342,53 @@ void kvm_xen_inject_vcpu_callback_vector(uint32_t vcpu_id, int type)
     }
 }
 
+static int kvm_xen_set_vcpu_timer(CPUState *cs)
+{
+    X86CPU *cpu = X86_CPU(cs);
+    CPUX86State *env = &cpu->env;
+
+    struct kvm_xen_vcpu_attr va = {
+        .type = KVM_XEN_VCPU_ATTR_TYPE_TIMER,
+        .u.timer.port = env->xen_virq[VIRQ_TIMER],
+        .u.timer.priority = KVM_IRQ_ROUTING_XEN_EVTCHN_PRIO_2LEVEL,
+        .u.timer.expires_ns = env->xen_singleshot_timer_ns,
+    };
+
+    return kvm_vcpu_ioctl(cs, KVM_XEN_VCPU_SET_ATTR, &va);
+}
+
+static void do_set_vcpu_timer_virq(CPUState *cs, run_on_cpu_data data)
+{
+    kvm_xen_set_vcpu_timer(cs);
+}
+
+int kvm_xen_set_vcpu_virq(uint32_t vcpu_id, uint16_t virq, uint16_t port)
+{
+    CPUState *cs = qemu_get_cpu(vcpu_id);
+
+    if (!cs) {
+        return -ENOENT;
+    }
+
+    /* cpu.h doesn't include the actual Xen header. */
+    qemu_build_assert(NR_VIRQS == XEN_NR_VIRQS);
+
+    if (virq >= NR_VIRQS) {
+        return -EINVAL;
+    }
+
+    if (port && X86_CPU(cs)->env.xen_virq[virq]) {
+        return -EEXIST;
+    }
+
+    X86_CPU(cs)->env.xen_virq[virq] = port;
+    if (virq == VIRQ_TIMER && kvm_xen_has_cap(EVTCHN_SEND)) {
+        async_run_on_cpu(cs, do_set_vcpu_timer_virq,
+                         RUN_ON_CPU_HOST_INT(port));
+    }
+    return 0;
+}
+
 static void do_set_vcpu_time_info_gpa(CPUState *cs, run_on_cpu_data data)
 {
     X86CPU *cpu = X86_CPU(cs);
@@ -374,6 +421,8 @@ static void do_vcpu_soft_reset(CPUState *cs, run_on_cpu_data data)
     env->xen_vcpu_time_info_gpa = INVALID_GPA;
     env->xen_vcpu_runstate_gpa = INVALID_GPA;
     env->xen_vcpu_callback_vector = 0;
+    env->xen_singleshot_timer_ns = 0;
+    memset(env->xen_virq, 0, sizeof(env->xen_virq));
 
     kvm_xen_set_vcpu_attr(cs, KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO, INVALID_GPA);
     kvm_xen_set_vcpu_attr(cs, KVM_XEN_VCPU_ATTR_TYPE_VCPU_TIME_INFO,
@@ -382,6 +431,7 @@ static void do_vcpu_soft_reset(CPUState *cs, run_on_cpu_data data)
                           INVALID_GPA);
     if (kvm_xen_has_cap(EVTCHN_SEND)) {
         kvm_xen_set_vcpu_callback_vector(cs);
+        kvm_xen_set_vcpu_timer(cs);
     }
 
 }
@@ -811,6 +861,21 @@ static bool kvm_xen_hcall_evtchn_op(struct kvm_xen_exit *exit, X86CPU *cpu,
         err = xen_evtchn_unmask_op(&unmask);
         break;
     }
+    case EVTCHNOP_bind_virq: {
+        struct evtchn_bind_virq virq;
+
+        qemu_build_assert(sizeof(virq) == 12);
+        if (kvm_copy_from_gva(cs, arg, &virq, sizeof(virq))) {
+            err = -EFAULT;
+            break;
+        }
+
+        err = xen_evtchn_bind_virq_op(&virq);
+        if (!err && kvm_copy_to_gva(cs, arg, &virq, sizeof(virq))) {
+            err = -EFAULT;
+        }
+        break;
+    }
     default:
         return false;
     }
@@ -1030,6 +1095,12 @@ int kvm_put_xen_state(CPUState *cs)
         }
     }
 
+    if (env->xen_virq[VIRQ_TIMER]) {
+        ret = kvm_xen_set_vcpu_timer(cs);
+        if (ret < 0) {
+            return ret;
+        }
+    }
     return 0;
 }
 
@@ -1038,6 +1109,7 @@ int kvm_get_xen_state(CPUState *cs)
     X86CPU *cpu = X86_CPU(cs);
     CPUX86State *env = &cpu->env;
     uint64_t gpa;
+    int ret;
 
     /*
      * The kernel does not mark vcpu_info as dirty when it delivers interrupts
@@ -1059,5 +1131,24 @@ int kvm_get_xen_state(CPUState *cs)
         }
     }
 
+    if (!kvm_xen_has_cap(EVTCHN_SEND)) {
+        return 0;
+    }
+
+    /*
+     * If the kernel is accelerating timers, read out the current value of the
+     * singleshot timer deadline.
+     */
+    if (env->xen_virq[VIRQ_TIMER]) {
+        struct kvm_xen_vcpu_attr va = {
+            .type = KVM_XEN_VCPU_ATTR_TYPE_TIMER,
+        };
+        ret = kvm_vcpu_ioctl(cs, KVM_XEN_VCPU_GET_ATTR, &va);
+        if (ret < 0) {
+            return ret;
+        }
+        env->xen_singleshot_timer_ns = va.u.timer.expires_ns;
+    }
+
     return 0;
 }
diff --git a/target/i386/machine.c b/target/i386/machine.c
index a4874eda90..603a1077e3 100644
--- a/target/i386/machine.c
+++ b/target/i386/machine.c
@@ -1275,6 +1275,8 @@ static const VMStateDescription vmstate_xen_vcpu = {
         VMSTATE_UINT64(env.xen_vcpu_time_info_gpa, X86CPU),
         VMSTATE_UINT64(env.xen_vcpu_runstate_gpa, X86CPU),
         VMSTATE_UINT8(env.xen_vcpu_callback_vector, X86CPU),
+        VMSTATE_UINT16_ARRAY(env.xen_virq, X86CPU, XEN_NR_VIRQS),
+        VMSTATE_UINT64(env.xen_singleshot_timer_ns, X86CPU),
         VMSTATE_END_OF_LIST()
     }
 };
-- 
2.35.3