spapr/irq: add KVM support to the 'dual' machine

The interrupt mode is chosen by the CAS negotiation process and
activated after a reset to take into account the required changes in
the machine. This brings new constraints on how the associated KVM IRQ
device is initialized.

Currently, each model takes care of the initialization of the KVM
device in their realize method but this is not possible anymore as the
initialization needs to be done globaly when the interrupt mode is
known, i.e. when machine is reseted. It also means that we need a way
to delete a KVM device when another mode is chosen.

Also, to support migration, the QEMU objects holding the state to
transfer should always be available but not necessarily activated.

The overall approach of this proposal is to initialize both interrupt
mode at the QEMU level to keep the IRQ number space in sync and to
allow switching from one mode to another. For the KVM side of things,
the whole initialization of the KVM device, sources and presenters, is
grouped in a single routine. The XICS and XIVE sPAPR IRQ reset
handlers are modified accordingly to handle the init and the delete
sequences of the KVM device.

Signed-off-by: Cédric Le Goater <clg@kaod.org>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Message-Id: <20190513084245.25755-15-clg@kaod.org>
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>

3 files changed, 59 insertions, 5 deletions

diff --git a/hw/intc/spapr_xive_kvm.c b/hw/intc/spapr_xive_kvm.c
index 078d18d..ec170b3 100644
--- a/hw/intc/spapr_xive_kvm.c
+++ b/hw/intc/spapr_xive_kvm.c
@@ -246,7 +246,7 @@ void kvmppc_xive_source_reset_one(XiveSource *xsrc, int srcno, Error **errp)
                       true, errp);
 }
 
-void kvmppc_xive_source_reset(XiveSource *xsrc, Error **errp)
+static void kvmppc_xive_source_reset(XiveSource *xsrc, Error **errp)
 {
     int i;
 
@@ -697,6 +697,15 @@ void kvmppc_xive_connect(SpaprXive *xive, Error **errp)
     Error *local_err = NULL;
     size_t esb_len = (1ull << xsrc->esb_shift) * xsrc->nr_irqs;
     size_t tima_len = 4ull << TM_SHIFT;
+    CPUState *cs;
+
+    /*
+     * The KVM XIVE device already in use. This is the case when
+     * rebooting under the XIVE-only interrupt mode.
+     */
+    if (xive->fd != -1) {
+        return;
+    }
 
     if (!kvmppc_has_cap_xive()) {
         error_setg(errp, "IRQ_XIVE capability must be present for KVM");
@@ -745,6 +754,24 @@ void kvmppc_xive_connect(SpaprXive *xive, Error **errp)
     xive->change = qemu_add_vm_change_state_handler(
         kvmppc_xive_change_state_handler, xive);
 
+    /* Connect the presenters to the initial VCPUs of the machine */
+    CPU_FOREACH(cs) {
+        PowerPCCPU *cpu = POWERPC_CPU(cs);
+
+        kvmppc_xive_cpu_connect(spapr_cpu_state(cpu)->tctx, &local_err);
+        if (local_err) {
+            error_propagate(errp, local_err);
+            return;
+        }
+    }
+
+    /* Update the KVM sources */
+    kvmppc_xive_source_reset(xsrc, &local_err);
+    if (local_err) {
+            error_propagate(errp, local_err);
+            return;
+    }
+
     kvm_kernel_irqchip = true;
     kvm_msi_via_irqfd_allowed = true;
     kvm_gsi_direct_mapping = true;
diff --git a/hw/intc/xics_kvm.c b/hw/intc/xics_kvm.c
index 12bd519..5ba5b77 100644
--- a/hw/intc/xics_kvm.c
+++ b/hw/intc/xics_kvm.c
@@ -33,6 +33,7 @@
 #include "trace.h"
 #include "sysemu/kvm.h"
 #include "hw/ppc/spapr.h"
+#include "hw/ppc/spapr_cpu_core.h"
 #include "hw/ppc/xics.h"
 #include "hw/ppc/xics_spapr.h"
 #include "kvm_ppc.h"
@@ -342,6 +343,16 @@ static void rtas_dummy(PowerPCCPU *cpu, SpaprMachineState *spapr,
 int xics_kvm_init(SpaprMachineState *spapr, Error **errp)
 {
     int rc;
+    CPUState *cs;
+    Error *local_err = NULL;
+
+    /*
+     * The KVM XICS device already in use. This is the case when
+     * rebooting under the XICS-only interrupt mode.
+     */
+    if (kernel_xics_fd != -1) {
+        return 0;
+    }
 
     if (!kvm_enabled() || !kvm_check_extension(kvm_state, KVM_CAP_IRQ_XICS)) {
         error_setg(errp,
@@ -390,6 +401,26 @@ int xics_kvm_init(SpaprMachineState *spapr, Error **errp)
     kvm_msi_via_irqfd_allowed = true;
     kvm_gsi_direct_mapping = true;
 
+    /* Create the presenters */
+    CPU_FOREACH(cs) {
+        PowerPCCPU *cpu = POWERPC_CPU(cs);
+
+        icp_kvm_realize(DEVICE(spapr_cpu_state(cpu)->icp), &local_err);
+        if (local_err) {
+            error_propagate(errp, local_err);
+            goto fail;
+        }
+    }
+
+    /* Update the KVM sources */
+    ics_set_kvm_state(spapr->ics);
+
+    /* Connect the presenters to the initial VCPUs of the machine */
+    CPU_FOREACH(cs) {
+        PowerPCCPU *cpu = POWERPC_CPU(cs);
+        icp_set_kvm_state(spapr_cpu_state(cpu)->icp);
+    }
+
     return 0;
 
 fail:
diff --git a/hw/intc/xive.c b/hw/intc/xive.c
index b5ebb33..0c74e47 100644
--- a/hw/intc/xive.c
+++ b/hw/intc/xive.c
@@ -993,10 +993,6 @@ static void xive_source_reset(void *dev)
 
     /* PQs are initialized to 0b01 (Q=1) which corresponds to "ints off" */
     memset(xsrc->status, XIVE_ESB_OFF, xsrc->nr_irqs);
-
-    if (kvm_irqchip_in_kernel()) {
-        kvmppc_xive_source_reset(xsrc, &error_fatal);
-    }
 }
 
 static void xive_source_realize(DeviceState *dev, Error **errp)