i386/xen: implement HVMOP_set_evtchn_upcall_vector

The HVMOP_set_evtchn_upcall_vector hypercall sets the per-vCPU upcall
vector, to be delivered to the local APIC just like an MSI (with an EOI).

This takes precedence over the system-wide delivery method set by the
HVMOP_set_param hypercall with HVM_PARAM_CALLBACK_IRQ. It's used by
Windows and Xen (PV shim) guests but normally not by Linux.

Signed-off-by: Ankur Arora <ankur.a.arora@oracle.com>
Signed-off-by: Joao Martins <joao.m.martins@oracle.com>
[dwmw2: Rework for upstream kernel changes and split from HVMOP_set_param]
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Reviewed-by: Paul Durrant <paul@xen.org>

target/i386/cpu.h

@@ -1803,6 +1803,7 @@ typedef struct CPUArchState {
     uint64_t xen_vcpu_info_default_gpa;
     uint64_t xen_vcpu_time_info_gpa;
     uint64_t xen_vcpu_runstate_gpa;
+    uint8_t xen_vcpu_callback_vector;
 #endif
 #if defined(CONFIG_HVF)
     HVFX86LazyFlags hvf_lflags;

target/i386/kvm/trace-events

@@ -11,3 +11,4 @@ kvm_xen_hypercall(int cpu, uint8_t cpl, uint64_t input, uint64_t a0, uint64_t a1
 kvm_xen_soft_reset(void) ""
 kvm_xen_set_shared_info(uint64_t gfn) "shared info at gfn 0x%" PRIx64
 kvm_xen_set_vcpu_attr(int cpu, int type, uint64_t gpa) "vcpu attr cpu %d type %d gpa 0x%" PRIx64
+kvm_xen_set_vcpu_callback(int cpu, int vector) "callback vcpu %d vector %d"

target/i386/kvm/xen-emu.c

@@ -27,6 +27,7 @@
 #include "hw/xen/interface/sched.h"
 #include "hw/xen/interface/memory.h"
 #include "hw/xen/interface/hvm/hvm_op.h"
+#include "hw/xen/interface/hvm/params.h"
 #include "hw/xen/interface/vcpu.h"
 #include "hw/xen/interface/event_channel.h"
 
@@ -193,7 +194,8 @@ static bool kvm_xen_hcall_xen_version(struct kvm_xen_exit *exit, X86CPU *cpu,
             fi.submap |= 1 << XENFEAT_writable_page_tables |
                          1 << XENFEAT_writable_descriptor_tables |
                          1 << XENFEAT_auto_translated_physmap |
-                         1 << XENFEAT_supervisor_mode_kernel;
+                         1 << XENFEAT_supervisor_mode_kernel |
+                         1 << XENFEAT_hvm_callback_vector;
         }
 
         err = kvm_copy_to_gva(CPU(cpu), arg, &fi, sizeof(fi));
@@ -220,6 +222,31 @@ static int kvm_xen_set_vcpu_attr(CPUState *cs, uint16_t type, uint64_t gpa)
     return kvm_vcpu_ioctl(cs, KVM_XEN_VCPU_SET_ATTR, &xhsi);
 }
 
+static int kvm_xen_set_vcpu_callback_vector(CPUState *cs)
+{
+    uint8_t vector = X86_CPU(cs)->env.xen_vcpu_callback_vector;
+    struct kvm_xen_vcpu_attr xva;
+
+    xva.type = KVM_XEN_VCPU_ATTR_TYPE_UPCALL_VECTOR;
+    xva.u.vector = vector;
+
+    trace_kvm_xen_set_vcpu_callback(cs->cpu_index, vector);
+
+    return kvm_vcpu_ioctl(cs, KVM_XEN_HVM_SET_ATTR, &xva);
+}
+
+static void do_set_vcpu_callback_vector(CPUState *cs, run_on_cpu_data data)
+{
+    X86CPU *cpu = X86_CPU(cs);
+    CPUX86State *env = &cpu->env;
+
+    env->xen_vcpu_callback_vector = data.host_int;
+
+    if (kvm_xen_has_cap(EVTCHN_SEND)) {
+        kvm_xen_set_vcpu_callback_vector(cs);
+    }
+}
+
 static void do_set_vcpu_info_default_gpa(CPUState *cs, run_on_cpu_data data)
 {
     X86CPU *cpu = X86_CPU(cs);
@@ -276,12 +303,16 @@ static void do_vcpu_soft_reset(CPUState *cs, run_on_cpu_data data)
     env->xen_vcpu_info_default_gpa = INVALID_GPA;
     env->xen_vcpu_time_info_gpa = INVALID_GPA;
     env->xen_vcpu_runstate_gpa = INVALID_GPA;
+    env->xen_vcpu_callback_vector = 0;
 
     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,
                           INVALID_GPA);
     kvm_xen_set_vcpu_attr(cs, KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADDR,
                           INVALID_GPA);
+    if (kvm_xen_has_cap(EVTCHN_SEND)) {
+        kvm_xen_set_vcpu_callback_vector(cs);
+    }
 
 }
 
@@ -458,17 +489,53 @@ static bool kvm_xen_hcall_memory_op(struct kvm_xen_exit *exit, X86CPU *cpu,
     return true;
 }
 
+static int kvm_xen_hcall_evtchn_upcall_vector(struct kvm_xen_exit *exit,
+                                              X86CPU *cpu, uint64_t arg)
+{
+    struct xen_hvm_evtchn_upcall_vector up;
+    CPUState *target_cs;
+
+    /* No need for 32/64 compat handling */
+    qemu_build_assert(sizeof(up) == 8);
+
+    if (kvm_copy_from_gva(CPU(cpu), arg, &up, sizeof(up))) {
+        return -EFAULT;
+    }
+
+    if (up.vector < 0x10) {
+        return -EINVAL;
+    }
+
+    target_cs = qemu_get_cpu(up.vcpu);
+    if (!target_cs) {
+        return -EINVAL;
+    }
+
+    async_run_on_cpu(target_cs, do_set_vcpu_callback_vector,
+                     RUN_ON_CPU_HOST_INT(up.vector));
+    return 0;
+}
+
 static bool kvm_xen_hcall_hvm_op(struct kvm_xen_exit *exit, X86CPU *cpu,
                                  int cmd, uint64_t arg)
 {
+    int ret = -ENOSYS;
     switch (cmd) {
+    case HVMOP_set_evtchn_upcall_vector:
+        ret = kvm_xen_hcall_evtchn_upcall_vector(exit, cpu,
+                                                 exit->u.hcall.params[0]);
+        break;
+
     case HVMOP_pagetable_dying:
-        exit->u.hcall.result = -ENOSYS;
+        ret = -ENOSYS;
-        return true;
+        break;
 
     default:
         return false;
     }
+
+    exit->u.hcall.result = ret;
+    return true;
 }
 
 static int vcpuop_register_vcpu_info(CPUState *cs, CPUState *target,
@@ -812,6 +879,17 @@ int kvm_put_xen_state(CPUState *cs)
         }
     }
 
+    if (!kvm_xen_has_cap(EVTCHN_SEND)) {
+        return 0;
+    }
+
+    if (env->xen_vcpu_callback_vector) {
+        ret = kvm_xen_set_vcpu_callback_vector(cs);
+        if (ret < 0) {
+            return ret;
+        }
+    }
+
     return 0;
 }
 

target/i386/machine.c

@@ -1274,6 +1274,7 @@ static const VMStateDescription vmstate_xen_vcpu = {
         VMSTATE_UINT64(env.xen_vcpu_info_default_gpa, X86CPU),
         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_END_OF_LIST()
     }
 };