hw/xen: Simplify emulated Xen platform init

I initially put the basic platform init (overlay pages, grant tables,
event channels) into mc->kvm_type because that was the earliest place
that could sensibly test for xen_mode==XEN_EMULATE.

The intent was to do this early enough that we could then initialise the
XenBus and other parts which would have depended on them, from a generic
location for both Xen and KVM/Xen in the PC-specific code, as seen in
https://lore.kernel.org/qemu-devel/20230116221919.1124201-16-dwmw2@infradead.org/

However, then the Xen on Arm patches came along, and *they* wanted to
do the XenBus init from a 'generic' Xen-specific location instead:
https://lore.kernel.org/qemu-devel/20230210222729.957168-4-sstabellini@kernel.org/

Since there's no generic location that covers all three, I conceded to
do it for XEN_EMULATE mode in pc_basic_devices_init().

And now there's absolutely no point in having some of the platform init
done from pc_machine_kvm_type(); we can move it all up to live in a
single place in pc_basic_devices_init(). This has the added benefit that
we can drop the separate xen_evtchn_connect_gsis() function completely,
and pass just the system GSIs in directly to xen_evtchn_create().

While I'm at it, it does no harm to explicitly pass in the *number* of
said GSIs, because it does make me twitch a bit to pass an array of
impicit size. During the lifetime of the KVM/Xen patchset, that had
already changed (albeit just cosmetically) from GSI_NUM_PINS to
IOAPIC_NUM_PINS.

And document a bit better that this is for the *output* GSI for raising
CPU0's events when the per-CPU vector isn't available. The fact that
we create a whole set of them and then only waggle the one we're told
to, instead of having a single output and only *connecting* it to the
GSI that it should be connected to, is still non-intuitive for me.

Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Reviewed-by: Paul Durrant <paul@xen.org>
Message-Id: <20230412185102.441523-2-dwmw2@infradead.org>
Signed-off-by: Anthony PERARD <anthony.perard@citrix.com>

hw/i386/kvm/xen_evtchn.c

@@ -147,7 +147,10 @@ struct XenEvtchnState {
     QemuMutex port_lock;
     uint32_t nr_ports;
     XenEvtchnPort port_table[EVTCHN_2L_NR_CHANNELS];
-    qemu_irq gsis[IOAPIC_NUM_PINS];
+
+    /* Connected to the system GSIs for raising callback as GSI / INTx */
+    unsigned int nr_callback_gsis;
+    qemu_irq *callback_gsis;
 
     struct xenevtchn_handle *be_handles[EVTCHN_2L_NR_CHANNELS];
 
@@ -299,7 +302,7 @@ static void gsi_assert_bh(void *opaque)
     }
 }
 
-void xen_evtchn_create(void)
+void xen_evtchn_create(unsigned int nr_gsis, qemu_irq *system_gsis)
 {
     XenEvtchnState *s = XEN_EVTCHN(sysbus_create_simple(TYPE_XEN_EVTCHN,
                                                         -1, NULL));
@@ -310,8 +313,19 @@ void xen_evtchn_create(void)
     qemu_mutex_init(&s->port_lock);
     s->gsi_bh = aio_bh_new(qemu_get_aio_context(), gsi_assert_bh, s);
 
-    for (i = 0; i < IOAPIC_NUM_PINS; i++) {
+    /*
-        sysbus_init_irq(SYS_BUS_DEVICE(s), &s->gsis[i]);
+     * These are the *output* GSI from event channel support, for
+     * signalling CPU0's events via GSI or PCI INTx instead of the
+     * per-CPU vector. We create a *set* of irqs and connect one to
+     * each of the system GSIs which were passed in from the platform
+     * code, and then just trigger the right one as appropriate from
+     * xen_evtchn_set_callback_level().
+     */
+    s->nr_callback_gsis = nr_gsis;
+    s->callback_gsis = g_new0(qemu_irq, nr_gsis);
+    for (i = 0; i < nr_gsis; i++) {
+        sysbus_init_irq(SYS_BUS_DEVICE(s), &s->callback_gsis[i]);
+        sysbus_connect_irq(SYS_BUS_DEVICE(s), i, system_gsis[i]);
     }
 
     /*
@@ -336,20 +350,6 @@ void xen_evtchn_create(void)
     xen_evtchn_ops = &emu_evtchn_backend_ops;
 }
 
-void xen_evtchn_connect_gsis(qemu_irq *system_gsis)
-{
-    XenEvtchnState *s = xen_evtchn_singleton;
-    int i;
-
-    if (!s) {
-        return;
-    }
-
-    for (i = 0; i < IOAPIC_NUM_PINS; i++) {
-        sysbus_connect_irq(SYS_BUS_DEVICE(s), i, system_gsis[i]);
-    }
-}
-
 static void xen_evtchn_register_types(void)
 {
     type_register_static(&xen_evtchn_info);
@@ -430,8 +430,8 @@ void xen_evtchn_set_callback_level(int level)
         return;
     }
 
-    if (s->callback_gsi && s->callback_gsi < IOAPIC_NUM_PINS) {
+    if (s->callback_gsi && s->callback_gsi < s->nr_callback_gsis) {
-        qemu_set_irq(s->gsis[s->callback_gsi], level);
+        qemu_set_irq(s->callback_gsis[s->callback_gsi], level);
         if (level) {
             /* Ensure the vCPU polls for deassertion */
             kvm_xen_set_callback_asserted();

hw/i386/kvm/xen_evtchn.h

@@ -16,10 +16,9 @@
 
 typedef uint32_t evtchn_port_t;
 
-void xen_evtchn_create(void);
+void xen_evtchn_create(unsigned int nr_gsis, qemu_irq *system_gsis);
 int xen_evtchn_soft_reset(void);
 int xen_evtchn_set_callback_param(uint64_t param);
-void xen_evtchn_connect_gsis(qemu_irq *system_gsis);
 void xen_evtchn_set_callback_level(int level);
 
 int xen_evtchn_set_port(uint16_t port);

hw/i386/pc.c

@@ -1332,7 +1332,10 @@ void pc_basic_device_init(struct PCMachineState *pcms,
 
 #ifdef CONFIG_XEN_EMU
     if (xen_mode == XEN_EMULATE) {
-        xen_evtchn_connect_gsis(gsi);
+        xen_overlay_create();
+        xen_evtchn_create(IOAPIC_NUM_PINS, gsi);
+        xen_gnttab_create();
+        xen_xenstore_create();
         if (pcms->bus) {
             pci_create_simple(pcms->bus, -1, "xen-platform");
         }
@@ -1882,14 +1885,6 @@ static void pc_machine_initfn(Object *obj)
 
 int pc_machine_kvm_type(MachineState *machine, const char *kvm_type)
 {
-#ifdef CONFIG_XEN_EMU
-    if (xen_mode == XEN_EMULATE) {
-        xen_overlay_create();
-        xen_evtchn_create();
-        xen_gnttab_create();
-        xen_xenstore_create();
-    }
-#endif
     return 0;
 }