[RFC PATCH v5 40/52] hw/xen: Support HVM_PARAM_CALLBACK_TYPE_GSI callback

[David Woodhouse]

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

The GSI callback (and later PCI_INTX) is a level triggered interrupt. It
is asserted when an event channel is delivered to vCPU0, and is supposed
to be cleared when the vcpu_info->evtchn_upcall_pending field for vCPU0
is cleared again.

Thankfully, Xen does *not* assert the GSI if the guest sets its own
evtchn_upcall_pending field; we only need to assert the GSI when we
have delivered an event for ourselves. So that's the easy part.

However, we *do* need to poll for the evtchn_upcall_pending flag being
cleared. In an ideal world we would poll that when the EOI happens on
the PIC/IOAPIC. That's how it works in the kernel with the VFIO eventfd
pairs — one is used to trigger the interrupt, and the other works in the
other direction to 'resample' on EOI, and trigger the first eventfd
again if the line is still active.

However, QEMU doesn't seem to do that. Even VFIO level interrupts seem
to be supported by temporarily unmapping the device's BARs from the
guest when an interrupt happens, then trapping *all* MMIO to the device
and sending the 'resample' event on *every* MMIO access until the IRQ
is cleared! Maybe in future we'll plumb the 'resample' concept through
QEMU's irq framework but for now we'll do what Xen itself does: just
check the flag on every vmexit if the upcall GSI is known to be
asserted.

Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
---
 hw/i386/kvm/xen_evtchn.c  | 45 ++++++++++++++++++++++++++++++++++++++
 hw/i386/kvm/xen_evtchn.h  |  4 ++++
 hw/i386/pc.c              |  6 +++++
 target/i386/cpu.h         |  1 +
 target/i386/kvm/kvm.c     | 13 +++++++++++
 target/i386/kvm/xen-emu.c | 46 ++++++++++++++++++++++++++++++---------
 target/i386/kvm/xen-emu.h |  1 +
 7 files changed, 106 insertions(+), 10 deletions(-)

diff --git a/hw/i386/kvm/xen_evtchn.c b/hw/i386/kvm/xen_evtchn.c
index 87136334f5..29f5e60172 100644
--- a/hw/i386/kvm/xen_evtchn.c
+++ b/hw/i386/kvm/xen_evtchn.c
@@ -24,6 +24,8 @@
 
 #include "hw/sysbus.h"
 #include "hw/xen/xen.h"
+#include "hw/i386/x86.h"
+#include "hw/irq.h"
 
 #include "xen_evtchn.h"
 #include "xen_overlay.h"
@@ -102,6 +104,7 @@ struct XenEvtchnState {
     QemuMutex port_lock;
     uint32_t nr_ports;
     XenEvtchnPort port_table[EVTCHN_2L_NR_CHANNELS];
+    qemu_irq gsis[GSI_NUM_PINS];
 };
 
 struct XenEvtchnState *xen_evtchn_singleton;
@@ -170,9 +173,29 @@ void xen_evtchn_create(void)
 {
     XenEvtchnState *s = XEN_EVTCHN(sysbus_create_simple(TYPE_XEN_EVTCHN,
                                                         -1, NULL));
+    int i;
+
     xen_evtchn_singleton = s;
 
     qemu_mutex_init(&s->port_lock);
+
+    for (i = 0; i < GSI_NUM_PINS; i++) {
+        sysbus_init_irq(SYS_BUS_DEVICE(s), &s->gsis[i]);
+    }
+}
+
+void xen_evtchn_connect_gsis(qemu_irq *system_gsis)
+{
+    XenEvtchnState *s = xen_evtchn_singleton;
+    int i;
+
+    if (!s) {
+        return;
+    }
+
+    for (i = 0; i < GSI_NUM_PINS; i++) {
+        sysbus_connect_irq(SYS_BUS_DEVICE(s), i, system_gsis[i]);
+    }
 }
 
 static void xen_evtchn_register_types(void)
@@ -182,6 +205,23 @@ static void xen_evtchn_register_types(void)
 
 type_init(xen_evtchn_register_types)
 
+void xen_evtchn_set_callback_level(int level)
+{
+    XenEvtchnState *s = xen_evtchn_singleton;
+
+    if (s) {
+        uint32_t param = (uint32_t)s->callback_param;
+
+        switch (s->callback_param >> CALLBACK_VIA_TYPE_SHIFT) {
+        case HVM_PARAM_CALLBACK_TYPE_GSI:
+            if (param < GSI_NUM_PINS) {
+                qemu_set_irq(s->gsis[param], level);
+            }
+            break;
+        }
+    }
+}
+
 int xen_evtchn_set_callback_param(uint64_t param)
 {
     XenEvtchnState *s = xen_evtchn_singleton;
@@ -207,6 +247,11 @@ int xen_evtchn_set_callback_param(uint64_t param)
         }
         break;
     }
+
+    case HVM_PARAM_CALLBACK_TYPE_GSI:
+        ret = 0;
+        break;
+
     default:
         ret = -ENOSYS;
         break;
diff --git a/hw/i386/kvm/xen_evtchn.h b/hw/i386/kvm/xen_evtchn.h
index 1de53daa52..86f154e359 100644
--- a/hw/i386/kvm/xen_evtchn.h
+++ b/hw/i386/kvm/xen_evtchn.h
@@ -12,9 +12,13 @@
 #ifndef QEMU_XEN_EVTCHN_H
 #define QEMU_XEN_EVTCHN_H
 
+#include "hw/sysbus.h"
+
 void xen_evtchn_create(void);
 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);
 
 void hmp_xen_event_list(Monitor *mon, const QDict *qdict);
 void hmp_xen_event_inject(Monitor *mon, const QDict *qdict);
diff --git a/hw/i386/pc.c b/hw/i386/pc.c
index c1328a779d..1c4941de8f 100644
--- a/hw/i386/pc.c
+++ b/hw/i386/pc.c
@@ -1303,6 +1303,12 @@ void pc_basic_device_init(struct PCMachineState *pcms,
     }
     *rtc_state = mc146818_rtc_init(isa_bus, 2000, rtc_irq);
 
+#ifdef CONFIG_XEN_EMU
+    if (xen_mode == XEN_EMULATE) {
+        xen_evtchn_connect_gsis(gsi);
+    }
+#endif
+
     qemu_register_boot_set(pc_boot_set, *rtc_state);
 
     if (!xen_enabled() &&
diff --git a/target/i386/cpu.h b/target/i386/cpu.h
index 000ed2fed9..144b1c3038 100644
--- a/target/i386/cpu.h
+++ b/target/i386/cpu.h
@@ -1795,6 +1795,7 @@ typedef struct CPUArchState {
     uint64_t xen_vcpu_time_info_gpa;
     uint64_t xen_vcpu_runstate_gpa;
     uint8_t xen_vcpu_callback_vector;
+    bool xen_callback_asserted;
     uint16_t xen_virq[XEN_NR_VIRQS];
     uint64_t xen_singleshot_timer_ns;
 #endif
diff --git a/target/i386/kvm/kvm.c b/target/i386/kvm/kvm.c
index 52d69e87e7..2488773e1e 100644
--- a/target/i386/kvm/kvm.c
+++ b/target/i386/kvm/kvm.c
@@ -5415,6 +5415,19 @@ int kvm_arch_handle_exit(CPUState *cs, struct kvm_run 
*run)
     char str[256];
     KVMState *state;
 
+#ifdef CONFIG_XEN_EMU
+    /*
+     * If the callback is asserted as a GSI (or PCI INTx) then check if
+     * vcpu_info->evtchn_upcall_pending has been cleared, and deassert
+     * the callback IRQ if so. Ideally we could hook into the PIC/IOAPIC
+     * EOI and only resample then, exactly how the VFIO eventfd pairs
+     * are designed to work for level triggered interrupts.
+     */
+    if (cpu->env.xen_callback_asserted) {
+        kvm_xen_maybe_deassert_callback(cs);
+    }
+#endif
+
     switch (run->exit_reason) {
     case KVM_EXIT_HLT:
         DPRINTF("handle_hlt\n");
diff --git a/target/i386/kvm/xen-emu.c b/target/i386/kvm/xen-emu.c
index e4104b67c3..9a8eb0f1f9 100644
--- a/target/i386/kvm/xen-emu.c
+++ b/target/i386/kvm/xen-emu.c
@@ -285,18 +285,11 @@ static void *gpa_to_hva(uint64_t gpa)
                                              mrs.offset_within_region);
 }
 
-void *kvm_xen_get_vcpu_info_hva(uint32_t vcpu_id)
+static void *vcpu_info_hva_from_cs(CPUState *cs)
 {
-    CPUState *cs = qemu_get_cpu(vcpu_id);
-    CPUX86State *env;
-    uint64_t gpa;
-
-    if (!cs) {
-        return NULL;
-    }
-    env = &X86_CPU(cs)->env;
+    CPUX86State *env = &X86_CPU(cs)->env;
+    uint64_t gpa = env->xen_vcpu_info_gpa;
 
-    gpa = env->xen_vcpu_info_gpa;
     if (gpa == INVALID_GPA) {
         gpa = env->xen_vcpu_info_default_gpa;
     }
@@ -307,6 +300,31 @@ void *kvm_xen_get_vcpu_info_hva(uint32_t vcpu_id)
     return gpa_to_hva(gpa);
 }
 
+void *kvm_xen_get_vcpu_info_hva(uint32_t vcpu_id)
+{
+    CPUState *cs = qemu_get_cpu(vcpu_id);
+
+    if (!cs) {
+            return NULL;
+    }
+
+    return vcpu_info_hva_from_cs(cs);
+}
+
+void kvm_xen_maybe_deassert_callback(CPUState *cs)
+{
+    struct vcpu_info *vi = vcpu_info_hva_from_cs(cs);
+    if (!vi) {
+            return;
+    }
+
+    /* If the evtchn_upcall_pending flag is cleared, turn the GSI off. */
+    if (!vi->evtchn_upcall_pending) {
+        X86_CPU(cs)->env.xen_callback_asserted = false;
+        xen_evtchn_set_callback_level(0);
+    }
+}
+
 void kvm_xen_inject_vcpu_callback_vector(uint32_t vcpu_id, int type)
 {
     CPUState *cs = qemu_get_cpu(vcpu_id);
@@ -339,6 +357,14 @@ void kvm_xen_inject_vcpu_callback_vector(uint32_t vcpu_id, 
int type)
          */
         qemu_cpu_kick(cs);
         break;
+
+    case HVM_PARAM_CALLBACK_TYPE_GSI:
+    case HVM_PARAM_CALLBACK_TYPE_PCI_INTX:
+        if (vcpu_id == 0) {
+            xen_evtchn_set_callback_level(1);
+            X86_CPU(cs)->env.xen_callback_asserted = true;
+        }
+        break;
     }
 }
 
diff --git a/target/i386/kvm/xen-emu.h b/target/i386/kvm/xen-emu.h
index 452605699a..fe85e0b195 100644
--- a/target/i386/kvm/xen-emu.h
+++ b/target/i386/kvm/xen-emu.h
@@ -28,5 +28,6 @@ int kvm_xen_init_vcpu(CPUState *cs);
 int kvm_xen_handle_exit(X86CPU *cpu, struct kvm_xen_exit *exit);
 int kvm_put_xen_state(CPUState *cs);
 int kvm_get_xen_state(CPUState *cs);
+void kvm_xen_maybe_deassert_callback(CPUState *cs);
 
 #endif /* QEMU_I386_KVM_XEN_EMU_H */
-- 
2.35.3